diff options
984 files changed, 62619 insertions, 3944 deletions
diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs new file mode 100644 index 000000000000..4a6694194ba6 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-aufs @@ -0,0 +1,55 @@ +What: /debug/aufs/si_<id>/ +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + Under /debug/aufs, a directory named si_<id> is created + per aufs mount, where <id> is a unique id generated + internally. + +What: /debug/aufs/si_<id>/plink +Date: Apr 2013 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It has three lines and shows the information about the + pseudo-link. The first line is a single number + representing a number of buckets. The second line is a + number of pseudo-links per buckets (separated by a + blank). The last line is a single number representing a + total number of psedo-links. + When the aufs mount option 'noplink' is specified, it + will show "1\n0\n0\n". + +What: /debug/aufs/si_<id>/xib +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the consumed blocks by xib (External Inode Number + Bitmap), its block size and file size. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. + +What: /debug/aufs/si_<id>/xi0, xi1 ... xiN and xiN-N +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the consumed blocks by xino (External Inode Number + Translation Table), its link count, block size and file + size. + Due to the file size limit, there may exist multiple + xino files per branch. In this case, "-N" is added to + the filename and it corresponds to the index of the + internal xino array. "-0" is omitted. + When the aufs mount option 'noxino' is specified, Those + entries won't exist. About XINO files, see the aufs + manual. + +What: /debug/aufs/si_<id>/xigen +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the consumed blocks by xigen (External Inode + Generation Table), its block size and file size. + If CONFIG_AUFS_EXPORT is disabled, this entry will not + be created. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. diff --git a/Documentation/ABI/testing/sysfs-aufs b/Documentation/ABI/testing/sysfs-aufs new file mode 100644 index 000000000000..82f9518495ea --- /dev/null +++ b/Documentation/ABI/testing/sysfs-aufs @@ -0,0 +1,31 @@ +What: /sys/fs/aufs/si_<id>/ +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + Under /sys/fs/aufs, a directory named si_<id> is created + per aufs mount, where <id> is a unique id generated + internally. + +What: /sys/fs/aufs/si_<id>/br0, br1 ... brN +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the abolute path of a member directory (which + is called branch) in aufs, and its permission. + +What: /sys/fs/aufs/si_<id>/brid0, brid1 ... bridN +Date: July 2013 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the id of a member directory (which is called + branch) in aufs. + +What: /sys/fs/aufs/si_<id>/xi_path +Date: March 2009 +Contact: J. R. Okajima <hooanon05g@gmail.com> +Description: + It shows the abolute path of XINO (External Inode Number + Bitmap, Translation Table and Generation Table) file + even if it is the default path. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index fb95fad81c79..6746f91ebc49 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -577,7 +577,7 @@ loops can be debugged more effectively on production systems. - clearcpuid=BITNUM [X86] + clearcpuid=BITNUM[,BITNUM...] [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit numbers. Note the Linux specific bits are not necessarily diff --git a/Documentation/devicetree/bindings/crypto/allwinner,sun4i-a10-crypto.yaml b/Documentation/devicetree/bindings/crypto/allwinner,sun4i-a10-crypto.yaml index fc823572bcff..90c6d039b91b 100644 --- a/Documentation/devicetree/bindings/crypto/allwinner,sun4i-a10-crypto.yaml +++ b/Documentation/devicetree/bindings/crypto/allwinner,sun4i-a10-crypto.yaml @@ -23,8 +23,7 @@ properties: - items: - const: allwinner,sun7i-a20-crypto - const: allwinner,sun4i-a10-crypto - - items: - - const: allwinner,sun8i-a33-crypto + - const: allwinner,sun8i-a33-crypto reg: maxItems: 1 @@ -59,7 +58,9 @@ if: properties: compatible: contains: - const: allwinner,sun6i-a31-crypto + enum: + - allwinner,sun6i-a31-crypto + - allwinner,sun8i-a33-crypto then: required: diff --git a/Documentation/devicetree/bindings/net/socionext-netsec.txt b/Documentation/devicetree/bindings/net/socionext-netsec.txt index 9d6c9feb12ff..a3c1dffaa4bb 100644 --- a/Documentation/devicetree/bindings/net/socionext-netsec.txt +++ b/Documentation/devicetree/bindings/net/socionext-netsec.txt @@ -30,7 +30,9 @@ Optional properties: (See ethernet.txt file in the same directory) - max-frame-size: See ethernet.txt in the same directory. The MAC address will be determined using the optional properties -defined in ethernet.txt. +defined in ethernet.txt. The 'phy-mode' property is required, but may +be set to the empty string if the PHY configuration is programmed by +the firmware or set by hardware straps, and needs to be preserved. Example: eth0: ethernet@522d0000 { diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README new file mode 100644 index 000000000000..3e655d357134 --- /dev/null +++ b/Documentation/filesystems/aufs/README @@ -0,0 +1,401 @@ + +Aufs5 -- advanced multi layered unification filesystem version 5.x +http://aufs.sf.net +Junjiro R. Okajima + + +0. Introduction +---------------------------------------- +In the early days, aufs was entirely re-designed and re-implemented +Unionfs Version 1.x series. Adding many original ideas, approaches, +improvements and implementations, it became totally different from +Unionfs while keeping the basic features. +Later, Unionfs Version 2.x series began taking some of the same +approaches to aufs1's. +Unionfs was being developed by Professor Erez Zadok at Stony Brook +University and his team. + +Aufs5 supports linux-v5.0 and later, If you want older kernel version +support, +- for linux-v4.x series, try aufs4-linux.git or aufs4-standalone.git +- for linux-v3.x series, try aufs3-linux.git or aufs3-standalone.git +- for linux-v2.6.16 and later, try aufs2-2.6.git, aufs2-standalone.git + or aufs1 from CVS on SourceForge. + +Note: it becomes clear that "Aufs was rejected. Let's give it up." + According to Christoph Hellwig, linux rejects all union-type + filesystems but UnionMount. +<http://marc.info/?l=linux-kernel&m=123938533724484&w=2> + +PS. Al Viro seems have a plan to merge aufs as well as overlayfs and + UnionMount, and he pointed out an issue around a directory mutex + lock and aufs addressed it. But it is still unsure whether aufs will + be merged (or any other union solution). +<http://marc.info/?l=linux-kernel&m=136312705029295&w=1> + + +1. Features +---------------------------------------- +- unite several directories into a single virtual filesystem. The member + directory is called as a branch. +- you can specify the permission flags to the branch, which are 'readonly', + 'readwrite' and 'whiteout-able.' +- by upper writable branch, internal copyup and whiteout, files/dirs on + readonly branch are modifiable logically. +- dynamic branch manipulation, add, del. +- etc... + +Also there are many enhancements in aufs, such as: +- test only the highest one for the directory permission (dirperm1) +- copyup on open (coo=) +- 'move' policy for copy-up between two writable branches, after + checking free space. +- xattr, acl +- readdir(3) in userspace. +- keep inode number by external inode number table +- keep the timestamps of file/dir in internal copyup operation +- seekable directory, supporting NFS readdir. +- whiteout is hardlinked in order to reduce the consumption of inodes + on branch +- do not copyup, nor create a whiteout when it is unnecessary +- revert a single systemcall when an error occurs in aufs +- remount interface instead of ioctl +- maintain /etc/mtab by an external command, /sbin/mount.aufs. +- loopback mounted filesystem as a branch +- kernel thread for removing the dir who has a plenty of whiteouts +- support copyup sparse file (a file which has a 'hole' in it) +- default permission flags for branches +- selectable permission flags for ro branch, whether whiteout can + exist or not +- export via NFS. +- support <sysfs>/fs/aufs and <debugfs>/aufs. +- support multiple writable branches, some policies to select one + among multiple writable branches. +- a new semantics for link(2) and rename(2) to support multiple + writable branches. +- no glibc changes are required. +- pseudo hardlink (hardlink over branches) +- allow a direct access manually to a file on branch, e.g. bypassing aufs. + including NFS or remote filesystem branch. +- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX. +- and more... + +Currently these features are dropped temporary from aufs5. +See design/08plan.txt in detail. +- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs + (robr) +- statistics of aufs thread (/sys/fs/aufs/stat) + +Features or just an idea in the future (see also design/*.txt), +- reorder the branch index without del/re-add. +- permanent xino files for NFSD +- an option for refreshing the opened files after add/del branches +- light version, without branch manipulation. (unnecessary?) +- copyup in userspace +- inotify in userspace +- readv/writev + + +2. Download +---------------------------------------- +There are three GIT trees for aufs5, aufs5-linux.git, +aufs5-standalone.git, and aufs-util.git. Note that there is no "5" in +"aufs-util.git." +While the aufs-util is always necessary, you need either of aufs5-linux +or aufs5-standalone. + +The aufs5-linux tree includes the whole linux mainline GIT tree, +git://git.kernel.org/.../torvalds/linux.git. +And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot +build aufs5 as an external kernel module. +Several extra patches are not included in this tree. Only +aufs5-standalone tree contains them. They are described in the later +section "Configuration and Compilation." + +On the other hand, the aufs5-standalone tree has only aufs source files +and necessary patches, and you can select CONFIG_AUFS_FS=m. +But you need to apply all aufs patches manually. + +You will find GIT branches whose name is in form of "aufs5.x" where "x" +represents the linux kernel version, "linux-5.x". For instance, +"aufs5.0" is for linux-5.0. For latest "linux-5.x-rcN", use +"aufs5.x-rcN" branch. + +o aufs5-linux tree +$ git clone --reference /your/linux/git/tree \ + git://github.com/sfjro/aufs5-linux.git aufs5-linux.git +- if you don't have linux GIT tree, then remove "--reference ..." +$ cd aufs5-linux.git +$ git checkout origin/aufs5.0 + +Or You may want to directly git-pull aufs into your linux GIT tree, and +leave the patch-work to GIT. +$ cd /your/linux/git/tree +$ git remote add aufs5 git://github.com/sfjro/aufs5-linux.git +$ git fetch aufs5 +$ git checkout -b my5.0 v5.0 +$ (add your local change...) +$ git pull aufs5 aufs5.0 +- now you have v5.0 + your_changes + aufs5.0 in you my5.0 branch. +- you may need to solve some conflicts between your_changes and + aufs5.0. in this case, git-rerere is recommended so that you can + solve the similar conflicts automatically when you upgrade to 5.1 or + later in the future. + +o aufs5-standalone tree +$ git clone git://github.com/sfjro/aufs5-standalone.git aufs5-standalone.git +$ cd aufs5-standalone.git +$ git checkout origin/aufs5.0 + +o aufs-util tree +$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git +- note that the public aufs-util.git is on SourceForge instead of + GitHUB. +$ cd aufs-util.git +$ git checkout origin/aufs5.0 + +Note: The 5.x-rcN branch is to be used with `rc' kernel versions ONLY. +The minor version number, 'x' in '5.x', of aufs may not always +follow the minor version number of the kernel. +Because changes in the kernel that cause the use of a new +minor version number do not always require changes to aufs-util. + +Since aufs-util has its own minor version number, you may not be +able to find a GIT branch in aufs-util for your kernel's +exact minor version number. +In this case, you should git-checkout the branch for the +nearest lower number. + +For (an unreleased) example: +If you are using "linux-5.10" and the "aufs5.10" branch +does not exist in aufs-util repository, then "aufs5.9", "aufs5.8" +or something numerically smaller is the branch for your kernel. + +Also you can view all branches by + $ git branch -a + + +3. Configuration and Compilation +---------------------------------------- +Make sure you have git-checkout'ed the correct branch. + +For aufs5-linux tree, +- enable CONFIG_AUFS_FS. +- set other aufs configurations if necessary. + +For aufs5-standalone tree, +There are several ways to build. + +1. +- apply ./aufs5-kbuild.patch to your kernel source files. +- apply ./aufs5-base.patch too. +- apply ./aufs5-mmap.patch too. +- apply ./aufs5-standalone.patch too, if you have a plan to set + CONFIG_AUFS_FS=m. otherwise you don't need ./aufs5-standalone.patch. +- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your + kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild. +- enable CONFIG_AUFS_FS, you can select either + =m or =y. +- and build your kernel as usual. +- install the built kernel. +- install the header files too by "make headers_install" to the + directory where you specify. By default, it is $PWD/usr. + "make help" shows a brief note for headers_install. +- and reboot your system. + +2. +- module only (CONFIG_AUFS_FS=m). +- apply ./aufs5-base.patch to your kernel source files. +- apply ./aufs5-mmap.patch too. +- apply ./aufs5-standalone.patch too. +- build your kernel, don't forget "make headers_install", and reboot. +- edit ./config.mk and set other aufs configurations if necessary. + Note: You should read $PWD/fs/aufs/Kconfig carefully which describes + every aufs configurations. +- build the module by simple "make". +- you can specify ${KDIR} make variable which points to your kernel + source tree. +- install the files + + run "make install" to install the aufs module, or copy the built + $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply). + + run "make install_headers" (instead of headers_install) to install + the modified aufs header file (you can specify DESTDIR which is + available in aufs standalone version's Makefile only), or copy + $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever + you like manually. By default, the target directory is $PWD/usr. +- no need to apply aufs5-kbuild.patch, nor copying source files to your + kernel source tree. + +Note: The header file aufs_type.h is necessary to build aufs-util + as well as "make headers_install" in the kernel source tree. + headers_install is subject to be forgotten, but it is essentially + necessary, not only for building aufs-util. + You may not meet problems without headers_install in some older + version though. + +And then, +- read README in aufs-util, build and install it +- note that your distribution may contain an obsoleted version of + aufs_type.h in /usr/include/linux or something. When you build aufs + utilities, make sure that your compiler refers the correct aufs header + file which is built by "make headers_install." +- if you want to use readdir(3) in userspace or pathconf(3) wrapper, + then run "make install_ulib" too. And refer to the aufs manual in + detail. + +There several other patches in aufs5-standalone.git. They are all +optional. When you meet some problems, they will help you. +- aufs5-loopback.patch + Supports a nested loopback mount in a branch-fs. This patch is + unnecessary until aufs produces a message like "you may want to try + another patch for loopback file". +- proc_mounts.patch + When there are many mountpoints and many mount(2)/umount(2) are + running, then /proc/mounts may not show the all mountpoints. This + patch makes /proc/mounts always show the full mountpoints list. + If you don't want to apply this patch and meet such problem, then you + need to increase the value of 'ProcMounts_Times' make-variable in + aufs-util.git as a second best solution. +- vfs-ino.patch + Modifies a system global kernel internal function get_next_ino() in + order to stop assigning 0 for an inode-number. Not directly related to + aufs, but recommended generally. +- tmpfs-idr.patch + Keeps the tmpfs inode number as the lowest value. Effective to reduce + the size of aufs XINO files for tmpfs branch. Also it prevents the + duplication of inode number, which is important for backup tools and + other utilities. When you find aufs XINO files for tmpfs branch + growing too much, try this patch. +- lockdep-debug.patch + Because aufs is not only an ordinary filesystem (callee of VFS), but + also a caller of VFS functions for branch filesystems, subclassing of + the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging + feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will + need to apply this debug patch to expand several constant values. + If you don't know what LOCKDEP is, then you don't have apply this + patch. + + +4. Usage +---------------------------------------- +At first, make sure aufs-util are installed, and please read the aufs +manual, aufs.5 in aufs-util.git tree. +$ man -l aufs.5 + +And then, +$ mkdir /tmp/rw /tmp/aufs +# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs + +Here is another example. The result is equivalent. +# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs + Or +# mount -t aufs -o br:/tmp/rw none /tmp/aufs +# mount -o remount,append:${HOME} /tmp/aufs + +Then, you can see whole tree of your home dir through /tmp/aufs. If +you modify a file under /tmp/aufs, the one on your home directory is +not affected, instead the same named file will be newly created under +/tmp/rw. And all of your modification to a file will be applied to +the one under /tmp/rw. This is called the file based Copy on Write +(COW) method. +Aufs mount options are described in aufs.5. +If you run chroot or something and make your aufs as a root directory, +then you need to customize the shutdown script. See the aufs manual in +detail. + +Additionally, there are some sample usages of aufs which are a +diskless system with network booting, and LiveCD over NFS. +See sample dir in CVS tree on SourceForge. + + +5. Contact +---------------------------------------- +When you have any problems or strange behaviour in aufs, please let me +know with: +- /proc/mounts (instead of the output of mount(8)) +- /sys/module/aufs/* +- /sys/fs/aufs/* (if you have them) +- /debug/aufs/* (if you have them) +- linux kernel version + if your kernel is not plain, for example modified by distributor, + the url where i can download its source is necessary too. +- aufs version which was printed at loading the module or booting the + system, instead of the date you downloaded. +- configuration (define/undefine CONFIG_AUFS_xxx) +- kernel configuration or /proc/config.gz (if you have it) +- LSM (linux security module, if you are using) +- behaviour which you think to be incorrect +- actual operation, reproducible one is better +- mailto: aufs-users at lists.sourceforge.net + +Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches, +and Feature Requests) on SourceForge. Please join and write to +aufs-users ML. + + +6. Acknowledgements +---------------------------------------- +Thanks to everyone who have tried and are using aufs, whoever +have reported a bug or any feedback. + +Especially donators: +Tomas Matejicek(slax.org) made a donation (much more than once). + Since Apr 2010, Tomas M (the author of Slax and Linux Live + scripts) is making "doubling" donations. + Unfortunately I cannot list all of the donators, but I really + appreciate. + It ends Aug 2010, but the ordinary donation URL is still available. + <http://sourceforge.net/donate/index.php?group_id=167503> +Dai Itasaka made a donation (2007/8). +Chuck Smith made a donation (2008/4, 10 and 12). +Henk Schoneveld made a donation (2008/9). +Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). +Francois Dupoux made a donation (2008/11). +Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public + aufs2 GIT tree (2009/2). +William Grant made a donation (2009/3). +Patrick Lane made a donation (2009/4). +The Mail Archive (mail-archive.com) made donations (2009/5). +Nippy Networks (Ed Wildgoose) made a donation (2009/7). +New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). +Pavel Pronskiy made a donation (2011/2). +Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy + Networks (Ed Wildgoose) made a donation for hardware (2011/3). +Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and +11). +Sam Liddicott made a donation (2011/9). +Era Scarecrow made a donation (2013/4). +Bor Ratajc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +POIRETTE Marc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +lauri kasvandik made a donation (2013/5). +"pemasu from Finland" made a donation (2013/7). +The Parted Magic Project made a donation (2013/9 and 11). +Pavel Barta made a donation (2013/10). +Nikolay Pertsev made a donation (2014/5). +James B made a donation (2014/7 and 2015/7). +Stefano Di Biase made a donation (2014/8). +Daniel Epellei made a donation (2015/1). +OmegaPhil made a donation (2016/1, 2018/4). +Tomasz Szewczyk made a donation (2016/4). +James Burry made a donation (2016/12). +Carsten Rose made a donation (2018/9). +Porteus Kiosk made a donation (2018/10). + +Thank you very much. +Donations are always, including future donations, very important and +helpful for me to keep on developing aufs. + + +7. +---------------------------------------- +If you are an experienced user, no explanation is needed. Aufs is +just a linux filesystem. + + +Enjoy! + +# Local variables: ; +# mode: text; +# End: ; diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt new file mode 100644 index 000000000000..47e0a01a8af2 --- /dev/null +++ b/Documentation/filesystems/aufs/design/01intro.txt @@ -0,0 +1,171 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Introduction +---------------------------------------- + +aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s] +1. abbrev. for "advanced multi-layered unification filesystem". +2. abbrev. for "another unionfs". +3. abbrev. for "auf das" in German which means "on the" in English. + Ex. "Butter aufs Brot"(G) means "butter onto bread"(E). + But "Filesystem aufs Filesystem" is hard to understand. +4. abbrev. for "African Urban Fashion Show". + +AUFS is a filesystem with features: +- multi layered stackable unification filesystem, the member directory + is called as a branch. +- branch permission and attribute, 'readonly', 'real-readonly', + 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their + combination. +- internal "file copy-on-write". +- logical deletion, whiteout. +- dynamic branch manipulation, adding, deleting and changing permission. +- allow bypassing aufs, user's direct branch access. +- external inode number translation table and bitmap which maintains the + persistent aufs inode number. +- seekable directory, including NFS readdir. +- file mapping, mmap and sharing pages. +- pseudo-link, hardlink over branches. +- loopback mounted filesystem as a branch. +- several policies to select one among multiple writable branches. +- revert a single systemcall when an error occurs in aufs. +- and more... + + +Multi Layered Stackable Unification Filesystem +---------------------------------------------------------------------- +Most people already knows what it is. +It is a filesystem which unifies several directories and provides a +merged single directory. When users access a file, the access will be +passed/re-directed/converted (sorry, I am not sure which English word is +correct) to the real file on the member filesystem. The member +filesystem is called 'lower filesystem' or 'branch' and has a mode +'readonly' and 'readwrite.' And the deletion for a file on the lower +readonly branch is handled by creating 'whiteout' on the upper writable +branch. + +On LKML, there have been discussions about UnionMount (Jan Blunck, +Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took +different approaches to implement the merged-view. +The former tries putting it into VFS, and the latter implements as a +separate filesystem. +(If I misunderstand about these implementations, please let me know and +I shall correct it. Because it is a long time ago when I read their +source files last time). + +UnionMount's approach will be able to small, but may be hard to share +branches between several UnionMount since the whiteout in it is +implemented in the inode on branch filesystem and always +shared. According to Bharata's post, readdir does not seems to be +finished yet. +There are several missing features known in this implementations such as +- for users, the inode number may change silently. eg. copy-up. +- link(2) may break by copy-up. +- read(2) may get an obsoleted filedata (fstat(2) too). +- fcntl(F_SETLK) may be broken by copy-up. +- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after + open(O_RDWR). + +In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was +merged into mainline. This is another implementation of UnionMount as a +separated filesystem. All the limitations and known problems which +UnionMount are equally inherited to "overlay" filesystem. + +Unionfs has a longer history. When I started implementing a stackable +filesystem (Aug 2005), it already existed. It has virtual super_block, +inode, dentry and file objects and they have an array pointing lower +same kind objects. After contributing many patches for Unionfs, I +re-started my project AUFS (Jun 2006). + +In AUFS, the structure of filesystem resembles to Unionfs, but I +implemented my own ideas, approaches and enhancements and it became +totally different one. + +Comparing DM snapshot and fs based implementation +- the number of bytes to be copied between devices is much smaller. +- the type of filesystem must be one and only. +- the fs must be writable, no readonly fs, even for the lower original + device. so the compression fs will not be usable. but if we use + loopback mount, we may address this issue. + for instance, + mount /cdrom/squashfs.img /sq + losetup /sq/ext2.img + losetup /somewhere/cow + dmsetup "snapshot /dev/loop0 /dev/loop1 ..." +- it will be difficult (or needs more operations) to extract the + difference between the original device and COW. +- DM snapshot-merge may help a lot when users try merging. in the + fs-layer union, users will use rsync(1). + +You may want to read my old paper "Filesystems in LiveCD" +(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf). + + +Several characters/aspects/persona of aufs +---------------------------------------------------------------------- + +Aufs has several characters, aspects or persona. +1. a filesystem, callee of VFS helper +2. sub-VFS, caller of VFS helper for branches +3. a virtual filesystem which maintains persistent inode number +4. reader/writer of files on branches such like an application + +1. Callee of VFS Helper +As an ordinary linux filesystem, aufs is a callee of VFS. For instance, +unlink(2) from an application reaches sys_unlink() kernel function and +then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it +calls filesystem specific unlink operation. Actually aufs implements the +unlink operation but it behaves like a redirector. + +2. Caller of VFS Helper for Branches +aufs_unlink() passes the unlink request to the branch filesystem as if +it were called from VFS. So the called unlink operation of the branch +filesystem acts as usual. As a caller of VFS helper, aufs should handle +every necessary pre/post operation for the branch filesystem. +- acquire the lock for the parent dir on a branch +- lookup in a branch +- revalidate dentry on a branch +- mnt_want_write() for a branch +- vfs_unlink() for a branch +- mnt_drop_write() for a branch +- release the lock on a branch + +3. Persistent Inode Number +One of the most important issue for a filesystem is to maintain inode +numbers. This is particularly important to support exporting a +filesystem via NFS. Aufs is a virtual filesystem which doesn't have a +backend block device for its own. But some storage is necessary to +keep and maintain the inode numbers. It may be a large space and may not +suit to keep in memory. Aufs rents some space from its first writable +branch filesystem (by default) and creates file(s) on it. These files +are created by aufs internally and removed soon (currently) keeping +opened. +Note: Because these files are removed, they are totally gone after + unmounting aufs. It means the inode numbers are not persistent + across unmount or reboot. I have a plan to make them really + persistent which will be important for aufs on NFS server. + +4. Read/Write Files Internally (copy-on-write) +Because a branch can be readonly, when you write a file on it, aufs will +"copy-up" it to the upper writable branch internally. And then write the +originally requested thing to the file. Generally kernel doesn't +open/read/write file actively. In aufs, even a single write may cause a +internal "file copy". This behaviour is very similar to cp(1) command. + +Some people may think it is better to pass such work to user space +helper, instead of doing in kernel space. Actually I am still thinking +about it. But currently I have implemented it in kernel space. diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt new file mode 100644 index 000000000000..0092b3dcfbe0 --- /dev/null +++ b/Documentation/filesystems/aufs/design/02struct.txt @@ -0,0 +1,258 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Basic Aufs Internal Structure + +Superblock/Inode/Dentry/File Objects +---------------------------------------------------------------------- +As like an ordinary filesystem, aufs has its own +superblock/inode/dentry/file objects. All these objects have a +dynamically allocated array and store the same kind of pointers to the +lower filesystem, branch. +For example, when you build a union with one readwrite branch and one +readonly, mounted /au, /rw and /ro respectively. +- /au = /rw + /ro +- /ro/fileA exists but /rw/fileA + +Aufs lookup operation finds /ro/fileA and gets dentry for that. These +pointers are stored in a aufs dentry. The array in aufs dentry will be, +- [0] = NULL (because /rw/fileA doesn't exist) +- [1] = /ro/fileA + +This style of an array is essentially same to the aufs +superblock/inode/dentry/file objects. + +Because aufs supports manipulating branches, ie. add/delete/change +branches dynamically, these objects has its own generation. When +branches are changed, the generation in aufs superblock is +incremented. And a generation in other object are compared when it is +accessed. When a generation in other objects are obsoleted, aufs +refreshes the internal array. + + +Superblock +---------------------------------------------------------------------- +Additionally aufs superblock has some data for policies to select one +among multiple writable branches, XIB files, pseudo-links and kobject. +See below in detail. +About the policies which supports copy-down a directory, see +wbr_policy.txt too. + + +Branch and XINO(External Inode Number Translation Table) +---------------------------------------------------------------------- +Every branch has its own xino (external inode number translation table) +file. The xino file is created and unlinked by aufs internally. When two +members of a union exist on the same filesystem, they share the single +xino file. +The struct of a xino file is simple, just a sequence of aufs inode +numbers which is indexed by the lower inode number. +In the above sample, assume the inode number of /ro/fileA is i111 and +aufs assigns the inode number i999 for fileA. Then aufs writes 999 as +4(8) bytes at 111 * 4(8) bytes offset in the xino file. + +When the inode numbers are not contiguous, the xino file will be sparse +which has a hole in it and doesn't consume as much disk space as it +might appear. If your branch filesystem consumes disk space for such +holes, then you should specify 'xino=' option at mounting aufs. + +Aufs has a mount option to free the disk blocks for such holes in XINO +files on tmpfs or ramdisk. But it is not so effective actually. If you +meet a problem of disk shortage due to XINO files, then you should try +"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git. +The patch localizes the assignment inumbers per tmpfs-mount and avoid +the holes in XINO files. + +Also a writable branch has three kinds of "whiteout bases". All these +are existed when the branch is joined to aufs, and their names are +whiteout-ed doubly, so that users will never see their names in aufs +hierarchy. +1. a regular file which will be hardlinked to all whiteouts. +2. a directory to store a pseudo-link. +3. a directory to store an "orphan"-ed file temporary. + +1. Whiteout Base + When you remove a file on a readonly branch, aufs handles it as a + logical deletion and creates a whiteout on the upper writable branch + as a hardlink of this file in order not to consume inode on the + writable branch. +2. Pseudo-link Dir + See below, Pseudo-link. +3. Step-Parent Dir + When "fileC" exists on the lower readonly branch only and it is + opened and removed with its parent dir, and then user writes + something into it, then aufs copies-up fileC to this + directory. Because there is no other dir to store fileC. After + creating a file under this dir, the file is unlinked. + +Because aufs supports manipulating branches, ie. add/delete/change +dynamically, a branch has its own id. When the branch order changes, +aufs finds the new index by searching the branch id. + + +Pseudo-link +---------------------------------------------------------------------- +Assume "fileA" exists on the lower readonly branch only and it is +hardlinked to "fileB" on the branch. When you write something to fileA, +aufs copies-up it to the upper writable branch. Additionally aufs +creates a hardlink under the Pseudo-link Directory of the writable +branch. The inode of a pseudo-link is kept in aufs super_block as a +simple list. If fileB is read after unlinking fileA, aufs returns +filedata from the pseudo-link instead of the lower readonly +branch. Because the pseudo-link is based upon the inode, to keep the +inode number by xino (see above) is essentially necessary. + +All the hardlinks under the Pseudo-link Directory of the writable branch +should be restored in a proper location later. Aufs provides a utility +to do this. The userspace helpers executed at remounting and unmounting +aufs by default. +During this utility is running, it puts aufs into the pseudo-link +maintenance mode. In this mode, only the process which began the +maintenance mode (and its child processes) is allowed to operate in +aufs. Some other processes which are not related to the pseudo-link will +be allowed to run too, but the rest have to return an error or wait +until the maintenance mode ends. If a process already acquires an inode +mutex (in VFS), it has to return an error. + + +XIB(external inode number bitmap) +---------------------------------------------------------------------- +Addition to the xino file per a branch, aufs has an external inode number +bitmap in a superblock object. It is also an internal file such like a +xino file. +It is a simple bitmap to mark whether the aufs inode number is in-use or +not. +To reduce the file I/O, aufs prepares a single memory page to cache xib. + +As well as XINO files, aufs has a feature to truncate/refresh XIB to +reduce the number of consumed disk blocks for these files. + + +Virtual or Vertical Dir, and Readdir in Userspace +---------------------------------------------------------------------- +In order to support multiple layers (branches), aufs readdir operation +constructs a virtual dir block on memory. For readdir, aufs calls +vfs_readdir() internally for each dir on branches, merges their entries +with eliminating the whiteout-ed ones, and sets it to file (dir) +object. So the file object has its entry list until it is closed. The +entry list will be updated when the file position is zero and becomes +obsoleted. This decision is made in aufs automatically. + +The dynamically allocated memory block for the name of entries has a +unit of 512 bytes (by default) and stores the names contiguously (no +padding). Another block for each entry is handled by kmem_cache too. +During building dir blocks, aufs creates hash list and judging whether +the entry is whiteouted by its upper branch or already listed. +The merged result is cached in the corresponding inode object and +maintained by a customizable life-time option. + +Some people may call it can be a security hole or invite DoS attack +since the opened and once readdir-ed dir (file object) holds its entry +list and becomes a pressure for system memory. But I'd say it is similar +to files under /proc or /sys. The virtual files in them also holds a +memory page (generally) while they are opened. When an idea to reduce +memory for them is introduced, it will be applied to aufs too. +For those who really hate this situation, I've developed readdir(3) +library which operates this merging in userspace. You just need to set +LD_PRELOAD environment variable, and aufs will not consume no memory in +kernel space for readdir(3). + + +Workqueue +---------------------------------------------------------------------- +Aufs sometimes requires privilege access to a branch. For instance, +in copy-up/down operation. When a user process is going to make changes +to a file which exists in the lower readonly branch only, and the mode +of one of ancestor directories may not be writable by a user +process. Here aufs copy-up the file with its ancestors and they may +require privilege to set its owner/group/mode/etc. +This is a typical case of a application character of aufs (see +Introduction). + +Aufs uses workqueue synchronously for this case. It creates its own +workqueue. The workqueue is a kernel thread and has privilege. Aufs +passes the request to call mkdir or write (for example), and wait for +its completion. This approach solves a problem of a signal handler +simply. +If aufs didn't adopt the workqueue and changed the privilege of the +process, then the process may receive the unexpected SIGXFSZ or other +signals. + +Also aufs uses the system global workqueue ("events" kernel thread) too +for asynchronous tasks, such like handling inotify/fsnotify, re-creating a +whiteout base and etc. This is unrelated to a privilege. +Most of aufs operation tries acquiring a rw_semaphore for aufs +superblock at the beginning, at the same time waits for the completion +of all queued asynchronous tasks. + + +Whiteout +---------------------------------------------------------------------- +The whiteout in aufs is very similar to Unionfs's. That is represented +by its filename. UnionMount takes an approach of a file mode, but I am +afraid several utilities (find(1) or something) will have to support it. + +Basically the whiteout represents "logical deletion" which stops aufs to +lookup further, but also it represents "dir is opaque" which also stop +further lookup. + +In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively. +In order to make several functions in a single systemcall to be +revertible, aufs adopts an approach to rename a directory to a temporary +unique whiteouted name. +For example, in rename(2) dir where the target dir already existed, aufs +renames the target dir to a temporary unique whiteouted name before the +actual rename on a branch, and then handles other actions (make it opaque, +update the attributes, etc). If an error happens in these actions, aufs +simply renames the whiteouted name back and returns an error. If all are +succeeded, aufs registers a function to remove the whiteouted unique +temporary name completely and asynchronously to the system global +workqueue. + + +Copy-up +---------------------------------------------------------------------- +It is a well-known feature or concept. +When user modifies a file on a readonly branch, aufs operate "copy-up" +internally and makes change to the new file on the upper writable branch. +When the trigger systemcall does not update the timestamps of the parent +dir, aufs reverts it after copy-up. + + +Move-down (aufs3.9 and later) +---------------------------------------------------------------------- +"Copy-up" is one of the essential feature in aufs. It copies a file from +the lower readonly branch to the upper writable branch when a user +changes something about the file. +"Move-down" is an opposite action of copy-up. Basically this action is +ran manually instead of automatically and internally. +For desgin and implementation, aufs has to consider these issues. +- whiteout for the file may exist on the lower branch. +- ancestor directories may not exist on the lower branch. +- diropq for the ancestor directories may exist on the upper branch. +- free space on the lower branch will reduce. +- another access to the file may happen during moving-down, including + UDBA (see "Revalidate Dentry and UDBA"). +- the file should not be hard-linked nor pseudo-linked. they should be + handled by auplink utility later. + +Sometimes users want to move-down a file from the upper writable branch +to the lower readonly or writable branch. For instance, +- the free space of the upper writable branch is going to run out. +- create a new intermediate branch between the upper and lower branch. +- etc. + +For this purpose, use "aumvdown" command in aufs-util.git. diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt new file mode 100644 index 000000000000..fb8cf0bc8c72 --- /dev/null +++ b/Documentation/filesystems/aufs/design/03atomic_open.txt @@ -0,0 +1,85 @@ + +# Copyright (C) 2015-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Support for a branch who has its ->atomic_open() +---------------------------------------------------------------------- +The filesystems who implement its ->atomic_open() are not majority. For +example NFSv4 does, and aufs should call NFSv4 ->atomic_open, +particularly for open(O_CREAT|O_EXCL, 0400) case. Other than +->atomic_open(), NFSv4 returns an error for this open(2). While I am not +sure whether all filesystems who have ->atomic_open() behave like this, +but NFSv4 surely returns the error. + +In order to support ->atomic_open() for aufs, there are a few +approaches. + +A. Introduce aufs_atomic_open() + - calls one of VFS:do_last(), lookup_open() or atomic_open() for + branch fs. +B. Introduce aufs_atomic_open() calling create, open and chmod. this is + an aufs user Pip Cet's approach + - calls aufs_create(), VFS finish_open() and notify_change(). + - pass fake-mode to finish_open(), and then correct the mode by + notify_change(). +C. Extend aufs_open() to call branch fs's ->atomic_open() + - no aufs_atomic_open(). + - aufs_lookup() registers the TID to an aufs internal object. + - aufs_create() does nothing when the matching TID is registered, but + registers the mode. + - aufs_open() calls branch fs's ->atomic_open() when the matching + TID is registered. +D. Extend aufs_open() to re-try branch fs's ->open() with superuser's + credential + - no aufs_atomic_open(). + - aufs_create() registers the TID to an internal object. this info + represents "this process created this file just now." + - when aufs gets EACCES from branch fs's ->open(), then confirm the + registered TID and re-try open() with superuser's credential. + +Pros and cons for each approach. + +A. + - straightforward but highly depends upon VFS internal. + - the atomic behavaiour is kept. + - some of parameters such as nameidata are hard to reproduce for + branch fs. + - large overhead. +B. + - easy to implement. + - the atomic behavaiour is lost. +C. + - the atomic behavaiour is kept. + - dirty and tricky. + - VFS checks whether the file is created correctly after calling + ->create(), which means this approach doesn't work. +D. + - easy to implement. + - the atomic behavaiour is lost. + - to open a file with superuser's credential and give it to a user + process is a bad idea, since the file object keeps the credential + in it. It may affect LSM or something. This approach doesn't work + either. + +The approach A is ideal, but it hard to implement. So here is a +variation of A, which is to be implemented. + +A-1. Introduce aufs_atomic_open() + - calls branch fs ->atomic_open() if exists. otherwise calls + vfs_create() and finish_open(). + - the demerit is that the several checks after branch fs + ->atomic_open() are lost. in the ordinary case, the checks are + done by VFS:do_last(), lookup_open() and atomic_open(). some can + be implemented in aufs, but not all I am afraid. diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt new file mode 100644 index 000000000000..5c3c97f11c57 --- /dev/null +++ b/Documentation/filesystems/aufs/design/03lookup.txt @@ -0,0 +1,113 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Lookup in a Branch +---------------------------------------------------------------------- +Since aufs has a character of sub-VFS (see Introduction), it operates +lookup for branches as VFS does. It may be a heavy work. But almost all +lookup operation in aufs is the simplest case, ie. lookup only an entry +directly connected to its parent. Digging down the directory hierarchy +is unnecessary. VFS has a function lookup_one_len() for that use, and +aufs calls it. + +When a branch is a remote filesystem, aufs basically relies upon its +->d_revalidate(), also aufs forces the hardest revalidate tests for +them. +For d_revalidate, aufs implements three levels of revalidate tests. See +"Revalidate Dentry and UDBA" in detail. + + +Test Only the Highest One for the Directory Permission (dirperm1 option) +---------------------------------------------------------------------- +Let's try case study. +- aufs has two branches, upper readwrite and lower readonly. + /au = /rw + /ro +- "dirA" exists under /ro, but /rw. and its mode is 0700. +- user invoked "chmod a+rx /au/dirA" +- the internal copy-up is activated and "/rw/dirA" is created and its + permission bits are set to world readable. +- then "/au/dirA" becomes world readable? + +In this case, /ro/dirA is still 0700 since it exists in readonly branch, +or it may be a natively readonly filesystem. If aufs respects the lower +branch, it should not respond readdir request from other users. But user +allowed it by chmod. Should really aufs rejects showing the entries +under /ro/dirA? + +To be honest, I don't have a good solution for this case. So aufs +implements 'dirperm1' and 'nodirperm1' mount options, and leave it to +users. +When dirperm1 is specified, aufs checks only the highest one for the +directory permission, and shows the entries. Otherwise, as usual, checks +every dir existing on all branches and rejects the request. + +As a side effect, dirperm1 option improves the performance of aufs +because the number of permission check is reduced when the number of +branch is many. + + +Revalidate Dentry and UDBA (User's Direct Branch Access) +---------------------------------------------------------------------- +Generally VFS helpers re-validate a dentry as a part of lookup. +0. digging down the directory hierarchy. +1. lock the parent dir by its i_mutex. +2. lookup the final (child) entry. +3. revalidate it. +4. call the actual operation (create, unlink, etc.) +5. unlock the parent dir + +If the filesystem implements its ->d_revalidate() (step 3), then it is +called. Actually aufs implements it and checks the dentry on a branch is +still valid. +But it is not enough. Because aufs has to release the lock for the +parent dir on a branch at the end of ->lookup() (step 2) and +->d_revalidate() (step 3) while the i_mutex of the aufs dir is still +held by VFS. +If the file on a branch is changed directly, eg. bypassing aufs, after +aufs released the lock, then the subsequent operation may cause +something unpleasant result. + +This situation is a result of VFS architecture, ->lookup() and +->d_revalidate() is separated. But I never say it is wrong. It is a good +design from VFS's point of view. It is just not suitable for sub-VFS +character in aufs. + +Aufs supports such case by three level of revalidation which is +selectable by user. +1. Simple Revalidate + Addition to the native flow in VFS's, confirm the child-parent + relationship on the branch just after locking the parent dir on the + branch in the "actual operation" (step 4). When this validation + fails, aufs returns EBUSY. ->d_revalidate() (step 3) in aufs still + checks the validation of the dentry on branches. +2. Monitor Changes Internally by Inotify/Fsnotify + Addition to above, in the "actual operation" (step 4) aufs re-lookup + the dentry on the branch, and returns EBUSY if it finds different + dentry. + Additionally, aufs sets the inotify/fsnotify watch for every dir on branches + during it is in cache. When the event is notified, aufs registers a + function to kernel 'events' thread by schedule_work(). And the + function sets some special status to the cached aufs dentry and inode + private data. If they are not cached, then aufs has nothing to + do. When the same file is accessed through aufs (step 0-3) later, + aufs will detect the status and refresh all necessary data. + In this mode, aufs has to ignore the event which is fired by aufs + itself. +3. No Extra Validation + This is the simplest test and doesn't add any additional revalidation + test, and skip the revalidation in step 4. It is useful and improves + aufs performance when system surely hide the aufs branches from user, + by over-mounting something (or another method). diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt new file mode 100644 index 000000000000..da5200be41a9 --- /dev/null +++ b/Documentation/filesystems/aufs/design/04branch.txt @@ -0,0 +1,74 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Branch Manipulation + +Since aufs supports dynamic branch manipulation, ie. add/remove a branch +and changing its permission/attribute, there are a lot of works to do. + + +Add a Branch +---------------------------------------------------------------------- +o Confirm the adding dir exists outside of aufs, including loopback + mount, and its various attributes. +o Initialize the xino file and whiteout bases if necessary. + See struct.txt. + +o Check the owner/group/mode of the directory + When the owner/group/mode of the adding directory differs from the + existing branch, aufs issues a warning because it may impose a + security risk. + For example, when a upper writable branch has a world writable empty + top directory, a malicious user can create any files on the writable + branch directly, like copy-up and modify manually. If something like + /etc/{passwd,shadow} exists on the lower readonly branch but the upper + writable branch, and the writable branch is world-writable, then a + malicious guy may create /etc/passwd on the writable branch directly + and the infected file will be valid in aufs. + I am afraid it can be a security issue, but aufs can do nothing except + producing a warning. + + +Delete a Branch +---------------------------------------------------------------------- +o Confirm the deleting branch is not busy + To be general, there is one merit to adopt "remount" interface to + manipulate branches. It is to discard caches. At deleting a branch, + aufs checks the still cached (and connected) dentries and inodes. If + there are any, then they are all in-use. An inode without its + corresponding dentry can be alive alone (for example, inotify/fsnotify case). + + For the cached one, aufs checks whether the same named entry exists on + other branches. + If the cached one is a directory, because aufs provides a merged view + to users, as long as one dir is left on any branch aufs can show the + dir to users. In this case, the branch can be removed from aufs. + Otherwise aufs rejects deleting the branch. + + If any file on the deleting branch is opened by aufs, then aufs + rejects deleting. + + +Modify the Permission of a Branch +---------------------------------------------------------------------- +o Re-initialize or remove the xino file and whiteout bases if necessary. + See struct.txt. + +o rw --> ro: Confirm the modifying branch is not busy + Aufs rejects the request if any of these conditions are true. + - a file on the branch is mmap-ed. + - a regular file on the branch is opened for write and there is no + same named entry on the upper branch. diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt new file mode 100644 index 000000000000..0262084bf634 --- /dev/null +++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt @@ -0,0 +1,64 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Policies to Select One among Multiple Writable Branches +---------------------------------------------------------------------- +When the number of writable branch is more than one, aufs has to decide +the target branch for file creation or copy-up. By default, the highest +writable branch which has the parent (or ancestor) dir of the target +file is chosen (top-down-parent policy). +By user's request, aufs implements some other policies to select the +writable branch, for file creation several policies, round-robin, +most-free-space, and other policies. For copy-up, top-down-parent, +bottom-up-parent, bottom-up and others. + +As expected, the round-robin policy selects the branch in circular. When +you have two writable branches and creates 10 new files, 5 files will be +created for each branch. mkdir(2) systemcall is an exception. When you +create 10 new directories, all will be created on the same branch. +And the most-free-space policy selects the one which has most free +space among the writable branches. The amount of free space will be +checked by aufs internally, and users can specify its time interval. + +The policies for copy-up is more simple, +top-down-parent is equivalent to the same named on in create policy, +bottom-up-parent selects the writable branch where the parent dir +exists and the nearest upper one from the copyup-source, +bottom-up selects the nearest upper writable branch from the +copyup-source, regardless the existence of the parent dir. + +There are some rules or exceptions to apply these policies. +- If there is a readonly branch above the policy-selected branch and + the parent dir is marked as opaque (a variation of whiteout), or the + target (creating) file is whiteout-ed on the upper readonly branch, + then the result of the policy is ignored and the target file will be + created on the nearest upper writable branch than the readonly branch. +- If there is a writable branch above the policy-selected branch and + the parent dir is marked as opaque or the target file is whiteouted + on the branch, then the result of the policy is ignored and the target + file will be created on the highest one among the upper writable + branches who has diropq or whiteout. In case of whiteout, aufs removes + it as usual. +- link(2) and rename(2) systemcalls are exceptions in every policy. + They try selecting the branch where the source exists as possible + since copyup a large file will take long time. If it can't be, + ie. the branch where the source exists is readonly, then they will + follow the copyup policy. +- There is an exception for rename(2) when the target exists. + If the rename target exists, aufs compares the index of the branches + where the source and the target exists and selects the higher + one. If the selected branch is readonly, then aufs follows the + copyup policy. diff --git a/Documentation/filesystems/aufs/design/06dirren.dot b/Documentation/filesystems/aufs/design/06dirren.dot new file mode 100644 index 000000000000..2d62bb6dd55f --- /dev/null +++ b/Documentation/filesystems/aufs/design/06dirren.dot @@ -0,0 +1,31 @@ + +// to view this graph, run dot(1) command in GRAPHVIZ. + +digraph G { +node [shape=box]; +whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"]; + +node [shape=oval]; + +aufs_rename -> whinfo [label="store/remove"]; + +node [shape=oval]; +inode_list [label="h_inum list in branch\ncache"]; + +node [shape=box]; +whinode [label="h_inum list file"]; + +node [shape=oval]; +brmgmt [label="br_add/del/mod/umount"]; + +brmgmt -> inode_list [label="create/remove"]; +brmgmt -> whinode [label="load/store"]; + +inode_list -> whinode [style=dashed,dir=both]; + +aufs_rename -> inode_list [label="add/del"]; + +aufs_lookup -> inode_list [label="search"]; + +aufs_lookup -> whinfo [label="load/remove"]; +} diff --git a/Documentation/filesystems/aufs/design/06dirren.txt b/Documentation/filesystems/aufs/design/06dirren.txt new file mode 100644 index 000000000000..38ae77b2c842 --- /dev/null +++ b/Documentation/filesystems/aufs/design/06dirren.txt @@ -0,0 +1,102 @@ + +# Copyright (C) 2017-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Special handling for renaming a directory (DIRREN) +---------------------------------------------------------------------- +First, let's assume we have a simple usecase. + +- /u = /rw + /ro +- /rw/dirA exists +- /ro/dirA and /ro/dirA/file exist too +- there is no dirB on both branches +- a user issues rename("dirA", "dirB") + +Now, what should aufs behave against this rename(2)? +There are a few possible cases. + +A. returns EROFS. + since dirA exists on a readonly branch which cannot be renamed. +B. returns EXDEV. + it is possible to copy-up dirA (only the dir itself), but the child + entries ("file" in this case) should not be. it must be a bad + approach to copy-up recursively. +C. returns a success. + even the branch /ro is readonly, aufs tries renaming it. Obviously it + is a violation of aufs' policy. +D. construct an extra information which indicates that /ro/dirA should + be handled as the name of dirB. + overlayfs has a similar feature called REDIRECT. + +Until now, aufs implements the case B only which returns EXDEV, and +expects the userspace application behaves like mv(1) which tries +issueing rename(2) recursively. + +A new aufs feature called DIRREN is introduced which implements the case +D. There are several "extra information" added. + +1. detailed info per renamed directory + path: /rw/dirB/$AUFS_WH_DR_INFO_PFX.<lower branch-id> +2. the inode-number list of directories on a branch + path: /rw/dirB/$AUFS_WH_DR_BRHINO + +The filename of "detailed info per directory" represents the lower +branch, and its format is +- a type of the branch id + one of these. + + uuid (not implemented yet) + + fsid + + dev +- the inode-number of the branch root dir + +And it contains these info in a single regular file. +- magic number +- branch's inode-number of the logically renamed dir +- the name of the before-renamed dir + +The "detailed info per directory" file is created in aufs rename(2), and +loaded in any lookup. +The info is considered in lookup for the matching case only. Here +"matching" means that the root of branch (in the info filename) is same +to the current looking-up branch. After looking-up the before-renamed +name, the inode-number is compared. And the matched dentry is used. + +The "inode-number list of directories" is a regular file which contains +simply the inode-numbers on the branch. The file is created or updated +in removing the branch, and loaded in adding the branch. Its lifetime is +equal to the branch. +The list is refered in lookup, and when the current target inode is +found in the list, the aufs tries loading the "detailed info per +directory" and get the changed and valid name of the dir. + +Theoretically these "extra informaiton" may be able to be put into XATTR +in the dir inode. But aufs doesn't choose this way because +1. XATTR may not be supported by the branch (or its configuration) +2. XATTR may have its size limit. +3. XATTR may be less easy to convert than a regular file, when the + format of the info is changed in the future. +At the same time, I agree that the regular file approach is much slower +than XATTR approach. So, in the future, aufs may take the XATTR or other +better approach. + +This DIRREN feature is enabled by aufs configuration, and is activated +by a new mount option. + +For the more complicated case, there is a work with UDBA option, which +is to dected the direct access to the branches (by-passing aufs) and to +maintain the cashes in aufs. Since a single cached aufs dentry may +contains two names, before- and after-rename, the name comparision in +UDBA handler may not work correctly. In this case, the behaviour will be +equivalen to udba=reval case. diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt new file mode 100644 index 000000000000..df985662befb --- /dev/null +++ b/Documentation/filesystems/aufs/design/06fhsm.txt @@ -0,0 +1,120 @@ + +# Copyright (C) 2011-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + + +File-based Hierarchical Storage Management (FHSM) +---------------------------------------------------------------------- +Hierarchical Storage Management (or HSM) is a well-known feature in the +storage world. Aufs provides this feature as file-based with multiple +writable branches, based upon the principle of "Colder, the Lower". +Here the word "colder" means that the less used files, and "lower" means +that the position in the order of the stacked branches vertically. +These multiple writable branches are prioritized, ie. the topmost one +should be the fastest drive and be used heavily. + +o Characters in aufs FHSM story +- aufs itself and a new branch attribute. +- a new ioctl interface to move-down and to establish a connection with + the daemon ("move-down" is a converse of "copy-up"). +- userspace tool and daemon. + +The userspace daemon establishes a connection with aufs and waits for +the notification. The notified information is very similar to struct +statfs containing the number of consumed blocks and inodes. +When the consumed blocks/inodes of a branch exceeds the user-specified +upper watermark, the daemon activates its move-down process until the +consumed blocks/inodes reaches the user-specified lower watermark. + +The actual move-down is done by aufs based upon the request from +user-space since we need to maintain the inode number and the internal +pointer arrays in aufs. + +Currently aufs FHSM handles the regular files only. Additionally they +must not be hard-linked nor pseudo-linked. + + +o Cowork of aufs and the user-space daemon + During the userspace daemon established the connection, aufs sends a + small notification to it whenever aufs writes something into the + writable branch. But it may cost high since aufs issues statfs(2) + internally. So user can specify a new option to cache the + info. Actually the notification is controlled by these factors. + + the specified cache time. + + classified as "force" by aufs internally. + Until the specified time expires, aufs doesn't send the info + except the forced cases. When aufs decide forcing, the info is always + notified to userspace. + For example, the number of free inodes is generally large enough and + the shortage of it happens rarely. So aufs doesn't force the + notification when creating a new file, directory and others. This is + the typical case which aufs doesn't force. + When aufs writes the actual filedata and the files consumes any of new + blocks, the aufs forces notifying. + + +o Interfaces in aufs +- New branch attribute. + + fhsm + Specifies that the branch is managed by FHSM feature. In other word, + participant in the FHSM. + When nofhsm is set to the branch, it will not be the source/target + branch of the move-down operation. This attribute is set + independently from coo and moo attributes, and if you want full + FHSM, you should specify them as well. +- New mount option. + + fhsm_sec + Specifies a second to suppress many less important info to be + notified. +- New ioctl. + + AUFS_CTL_FHSM_FD + create a new file descriptor which userspace can read the notification + (a subset of struct statfs) from aufs. +- Module parameter 'brs' + It has to be set to 1. Otherwise the new mount option 'fhsm' will not + be set. +- mount helpers /sbin/mount.aufs and /sbin/umount.aufs + When there are two or more branches with fhsm attributes, + /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs + terminates it. As a result of remounting and branch-manipulation, the + number of branches with fhsm attribute can be one. In this case, + /sbin/mount.aufs will terminate the user-space daemon. + + +Finally the operation is done as these steps in kernel-space. +- make sure that, + + no one else is using the file. + + the file is not hard-linked. + + the file is not pseudo-linked. + + the file is a regular file. + + the parent dir is not opaqued. +- find the target writable branch. +- make sure the file is not whiteout-ed by the upper (than the target) + branch. +- make the parent dir on the target branch. +- mutex lock the inode on the branch. +- unlink the whiteout on the target branch (if exists). +- lookup and create the whiteout-ed temporary name on the target branch. +- copy the file as the whiteout-ed temporary name on the target branch. +- rename the whiteout-ed temporary name to the original name. +- unlink the file on the source branch. +- maintain the internal pointer array and the external inode number + table (XINO). +- maintain the timestamps and other attributes of the parent dir and the + file. + +And of course, in every step, an error may happen. So the operation +should restore the original file state after an error happens. diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt new file mode 100644 index 000000000000..9184f6710437 --- /dev/null +++ b/Documentation/filesystems/aufs/design/06mmap.txt @@ -0,0 +1,72 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +mmap(2) -- File Memory Mapping +---------------------------------------------------------------------- +In aufs, the file-mapped pages are handled by a branch fs directly, no +interaction with aufs. It means aufs_mmap() calls the branch fs's +->mmap(). +This approach is simple and good, but there is one problem. +Under /proc, several entries show the mmapped files by its path (with +device and inode number), and the printed path will be the path on the +branch fs's instead of virtual aufs's. +This is not a problem in most cases, but some utilities lsof(1) (and its +user) may expect the path on aufs. + +To address this issue, aufs adds a new member called vm_prfile in struct +vm_area_struct (and struct vm_region). The original vm_file points to +the file on the branch fs in order to handle everything correctly as +usual. The new vm_prfile points to a virtual file in aufs, and the +show-functions in procfs refers to vm_prfile if it is set. +Also we need to maintain several other places where touching vm_file +such like +- fork()/clone() copies vma and the reference count of vm_file is + incremented. +- merging vma maintains the ref count too. + +This is not a good approach. It just fakes the printed path. But it +leaves all behaviour around f_mapping unchanged. This is surely an +advantage. +Actually aufs had adopted another complicated approach which calls +generic_file_mmap() and handles struct vm_operations_struct. In this +approach, aufs met a hard problem and I could not solve it without +switching the approach. + +There may be one more another approach which is +- bind-mount the branch-root onto the aufs-root internally +- grab the new vfsmount (ie. struct mount) +- lazy-umount the branch-root internally +- in open(2) the aufs-file, open the branch-file with the hidden + vfsmount (instead of the original branch's vfsmount) +- ideally this "bind-mount and lazy-umount" should be done atomically, + but it may be possible from userspace by the mount helper. + +Adding the internal hidden vfsmount and using it in opening a file, the +file path under /proc will be printed correctly. This approach looks +smarter, but is not possible I am afraid. +- aufs-root may be bind-mount later. when it happens, another hidden + vfsmount will be required. +- it is hard to get the chance to bind-mount and lazy-umount + + in kernel-space, FS can have vfsmount in open(2) via + file->f_path, and aufs can know its vfsmount. But several locks are + already acquired, and if aufs tries to bind-mount and lazy-umount + here, then it may cause a deadlock. + + in user-space, bind-mount doesn't invoke the mount helper. +- since /proc shows dev and ino, aufs has to give vma these info. it + means a new member vm_prinode will be necessary. this is essentially + equivalent to vm_prfile described above. + +I have to give up this "looks-smater" approach. diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt new file mode 100644 index 000000000000..d0f6aedfe2d0 --- /dev/null +++ b/Documentation/filesystems/aufs/design/06xattr.txt @@ -0,0 +1,96 @@ + +# Copyright (C) 2014-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + + +Listing XATTR/EA and getting the value +---------------------------------------------------------------------- +For the inode standard attributes (owner, group, timestamps, etc.), aufs +shows the values from the topmost existing file. This behaviour is good +for the non-dir entries since the bahaviour exactly matches the shown +information. But for the directories, aufs considers all the same named +entries on the lower branches. Which means, if one of the lower entry +rejects readdir call, then aufs returns an error even if the topmost +entry allows it. This behaviour is necessary to respect the branch fs's +security, but can make users confused since the user-visible standard +attributes don't match the behaviour. +To address this issue, aufs has a mount option called dirperm1 which +checks the permission for the topmost entry only, and ignores the lower +entry's permission. + +A similar issue can happen around XATTR. +getxattr(2) and listxattr(2) families behave as if dirperm1 option is +always set. Otherwise these very unpleasant situation would happen. +- listxattr(2) may return the duplicated entries. +- users may not be able to remove or reset the XATTR forever, + + +XATTR/EA support in the internal (copy,move)-(up,down) +---------------------------------------------------------------------- +Generally the extended attributes of inode are categorized as these. +- "security" for LSM and capability. +- "system" for posix ACL, 'acl' mount option is required for the branch + fs generally. +- "trusted" for userspace, CAP_SYS_ADMIN is required. +- "user" for userspace, 'user_xattr' mount option is required for the + branch fs generally. + +Moreover there are some other categories. Aufs handles these rather +unpopular categories as the ordinary ones, ie. there is no special +condition nor exception. + +In copy-up, the support for XATTR on the dst branch may differ from the +src branch. In this case, the copy-up operation will get an error and +the original user operation which triggered the copy-up will fail. It +can happen that even all copy-up will fail. +When both of src and dst branches support XATTR and if an error occurs +during copying XATTR, then the copy-up should fail obviously. That is a +good reason and aufs should return an error to userspace. But when only +the src branch support that XATTR, aufs should not return an error. +For example, the src branch supports ACL but the dst branch doesn't +because the dst branch may natively un-support it or temporary +un-support it due to "noacl" mount option. Of course, the dst branch fs +may NOT return an error even if the XATTR is not supported. It is +totally up to the branch fs. + +Anyway when the aufs internal copy-up gets an error from the dst branch +fs, then aufs tries removing the just copied entry and returns the error +to the userspace. The worst case of this situation will be all copy-up +will fail. + +For the copy-up operation, there two basic approaches. +- copy the specified XATTR only (by category above), and return the + error unconditionally if it happens. +- copy all XATTR, and ignore the error on the specified category only. + +In order to support XATTR and to implement the correct behaviour, aufs +chooses the latter approach and introduces some new branch attributes, +"icexsec", "icexsys", "icextr", "icexusr", and "icexoth". +They correspond to the XATTR namespaces (see above). Additionally, to be +convenient, "icex" is also provided which means all "icex*" attributes +are set (here the word "icex" stands for "ignore copy-error on XATTR"). + +The meaning of these attributes is to ignore the error from setting +XATTR on that branch. +Note that aufs tries copying all XATTR unconditionally, and ignores the +error from the dst branch according to the specified attributes. + +Some XATTR may have its default value. The default value may come from +the parent dir or the environment. If the default value is set at the +file creating-time, it will be overwritten by copy-up. +Some contradiction may happen I am afraid. +Do we need another attribute to stop copying XATTR? I am unsure. For +now, aufs implements the branch attributes to ignore the error. diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt new file mode 100644 index 000000000000..6fcb00d7dbdb --- /dev/null +++ b/Documentation/filesystems/aufs/design/07export.txt @@ -0,0 +1,58 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Export Aufs via NFS +---------------------------------------------------------------------- +Here is an approach. +- like xino/xib, add a new file 'xigen' which stores aufs inode + generation. +- iget_locked(): initialize aufs inode generation for a new inode, and + store it in xigen file. +- destroy_inode(): increment aufs inode generation and store it in xigen + file. it is necessary even if it is not unlinked, because any data of + inode may be changed by UDBA. +- encode_fh(): for a root dir, simply return FILEID_ROOT. otherwise + build file handle by + + branch id (4 bytes) + + superblock generation (4 bytes) + + inode number (4 or 8 bytes) + + parent dir inode number (4 or 8 bytes) + + inode generation (4 bytes)) + + return value of exportfs_encode_fh() for the parent on a branch (4 + bytes) + + file handle for a branch (by exportfs_encode_fh()) +- fh_to_dentry(): + + find the index of a branch from its id in handle, and check it is + still exist in aufs. + + 1st level: get the inode number from handle and search it in cache. + + 2nd level: if not found in cache, get the parent inode number from + the handle and search it in cache. and then open the found parent + dir, find the matching inode number by vfs_readdir() and get its + name, and call lookup_one_len() for the target dentry. + + 3rd level: if the parent dir is not cached, call + exportfs_decode_fh() for a branch and get the parent on a branch, + build a pathname of it, convert it a pathname in aufs, call + path_lookup(). now aufs gets a parent dir dentry, then handle it as + the 2nd level. + + to open the dir, aufs needs struct vfsmount. aufs keeps vfsmount + for every branch, but not itself. to get this, (currently) aufs + searches in current->nsproxy->mnt_ns list. it may not be a good + idea, but I didn't get other approach. + + test the generation of the gotten inode. +- every inode operation: they may get EBUSY due to UDBA. in this case, + convert it into ESTALE for NFSD. +- readdir(): call lockdep_on/off() because filldir in NFSD calls + lookup_one_len(), vfs_getattr(), encode_fh() and others. diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt new file mode 100644 index 000000000000..d7e58319086b --- /dev/null +++ b/Documentation/filesystems/aufs/design/08shwh.txt @@ -0,0 +1,52 @@ + +# Copyright (C) 2005-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Show Whiteout Mode (shwh) +---------------------------------------------------------------------- +Generally aufs hides the name of whiteouts. But in some cases, to show +them is very useful for users. For instance, creating a new middle layer +(branch) by merging existing layers. + +(borrowing aufs1 HOW-TO from a user, Michael Towers) +When you have three branches, +- Bottom: 'system', squashfs (underlying base system), read-only +- Middle: 'mods', squashfs, read-only +- Top: 'overlay', ram (tmpfs), read-write + +The top layer is loaded at boot time and saved at shutdown, to preserve +the changes made to the system during the session. +When larger changes have been made, or smaller changes have accumulated, +the size of the saved top layer data grows. At this point, it would be +nice to be able to merge the two overlay branches ('mods' and 'overlay') +and rewrite the 'mods' squashfs, clearing the top layer and thus +restoring save and load speed. + +This merging is simplified by the use of another aufs mount, of just the +two overlay branches using the 'shwh' option. +# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \ + aufs /livesys/merge_union + +A merged view of these two branches is then available at +/livesys/merge_union, and the new feature is that the whiteouts are +visible! +Note that in 'shwh' mode the aufs mount must be 'ro', which will disable +writing to all branches. Also the default mode for all branches is 'ro'. +It is now possible to save the combined contents of the two overlay +branches to a new squashfs, e.g.: +# mksquashfs /livesys/merge_union /path/to/newmods.squash + +This new squashfs archive can be stored on the boot device and the +initramfs will use it to replace the old one at the next boot. diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt new file mode 100644 index 000000000000..d55cae285dff --- /dev/null +++ b/Documentation/filesystems/aufs/design/10dynop.txt @@ -0,0 +1,47 @@ + +# Copyright (C) 2010-2020 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Dynamically customizable FS operations +---------------------------------------------------------------------- +Generally FS operations (struct inode_operations, struct +address_space_operations, struct file_operations, etc.) are defined as +"static const", but it never means that FS have only one set of +operation. Some FS have multiple sets of them. For instance, ext2 has +three sets, one for XIP, for NOBH, and for normal. +Since aufs overrides and redirects these operations, sometimes aufs has +to change its behaviour according to the branch FS type. More importantly +VFS acts differently if a function (member in the struct) is set or +not. It means aufs should have several sets of operations and select one +among them according to the branch FS definition. + +In order to solve this problem and not to affect the behaviour of VFS, +aufs defines these operations dynamically. For instance, aufs defines +dummy direct_IO function for struct address_space_operations, but it may +not be set to the address_space_operations actually. When the branch FS +doesn't have it, aufs doesn't set it to its address_space_operations +while the function definition itself is still alive. So the behaviour +itself will not change, and it will return an error when direct_IO is +not set. + +The lifetime of these dynamically generated operation object is +maintained by aufs branch object. When the branch is removed from aufs, +the reference counter of the object is decremented. When it reaches +zero, the dynamically generated operation object will be freed. + +This approach is designed to support AIO (io_submit), Direct I/O and +XIP (DAX) mainly. +Currently this approach is applied to address_space_operations for +regular files only. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 837d51f9e1fa..25e6673a085a 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1142,13 +1142,15 @@ icmp_ratelimit - INTEGER icmp_msgs_per_sec - INTEGER Limit maximal number of ICMP packets sent per second from this host. Only messages whose type matches icmp_ratemask (see below) are - controlled by this limit. + controlled by this limit. For security reasons, the precise count + of messages per second is randomized. Default: 1000 icmp_msgs_burst - INTEGER icmp_msgs_per_sec controls number of ICMP packets sent per second, while icmp_msgs_burst controls the burst size of these packets. + For security reasons, the precise burst size is randomized. Default: 50 diff --git a/MAINTAINERS b/MAINTAINERS index 4e2698cc7e23..491f32f3b072 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2984,6 +2984,19 @@ F: include/linux/audit.h F: include/uapi/linux/audit.h F: kernel/audit* +AUFS (advanced multi layered unification filesystem) FILESYSTEM +M: "J. R. Okajima" <hooanon05g@gmail.com> +L: aufs-users@lists.sourceforge.net (members only) +L: linux-unionfs@vger.kernel.org +W: http://aufs.sourceforge.net +T: git://github.com/sfjro/aufs4-linux.git +S: Supported +F: Documentation/filesystems/aufs/ +F: Documentation/ABI/testing/debugfs-aufs +F: Documentation/ABI/testing/sysfs-aufs +F: fs/aufs/ +F: include/uapi/linux/aufs_type.h + AUXILIARY DISPLAY DRIVERS M: Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com> S: Maintained @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 8 -SUBLEVEL = 16 +SUBLEVEL = 18 EXTRAVERSION = NAME = Kleptomaniac Octopus @@ -525,7 +525,7 @@ export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL # Files to ignore in find ... statements export RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o \ - -name CVS -o -name .pc -o -name .hg -o -name .git \) \ + -name CVS -o -name .pc -o -name .hg -o -name .git -o -name meta \) \ -prune -o export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \ --exclude CVS --exclude .pc --exclude .hg --exclude .git diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index ce8101834518..6b5c54576f54 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -8,5 +8,6 @@ menuconfig ARC_SOC_HSDK select ARC_HAS_ACCL_REGS select ARC_IRQ_NO_AUTOSAVE select CLK_HSDK + select RESET_CONTROLLER select RESET_HSDK select HAVE_PCI diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 59fde2d598d8..928218cf22db 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -65,7 +65,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-ipa-sra) # macro, but instead defines a whole series of macros which makes # testing for a specific architecture or later rather impossible. arch-$(CONFIG_CPU_32v7M) =-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m -arch-$(CONFIG_CPU_32v7) =-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a) +arch-$(CONFIG_CPU_32v7) =-D__LINUX_ARM_ARCH__=7 -march=armv7-a -Wa$(comma)-march=armv7-a arch-$(CONFIG_CPU_32v6) =-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6) # Only override the compiler option if ARMv6. The ARMv6K extensions are # always available in ARMv7 @@ -339,6 +339,9 @@ PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS) bootpImage uImage: zImage zImage: Image +# These targets cannot be built in parallel +.NOTPARALLEL: $(BOOT_TARGETS) + $(BOOT_TARGETS): vmlinux $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@ @$(kecho) ' Kernel: $(boot)/$@ is ready' diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index 0b3cd7a33a26..67608510fad3 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -68,6 +68,10 @@ $(obj)/zImage: $(obj)/compressed/vmlinux FORCE endif +ifeq ($(CONFIG_ARCH_VEXPRESS), y) +LOADADDR=0x04080000 +endif + ifneq ($(LOADADDR),) UIMAGE_LOADADDR=$(LOADADDR) else diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 911d8cf77f2c..0339a46fa71c 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -939,8 +939,10 @@ }; rngb: rngb@21b4000 { + compatible = "fsl,imx6sl-rngb", "fsl,imx25-rngb"; reg = <0x021b4000 0x4000>; interrupts = <0 5 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX6SL_CLK_DUMMY>; }; weim: weim@21b8000 { diff --git a/arch/arm/boot/dts/iwg20d-q7-common.dtsi b/arch/arm/boot/dts/iwg20d-q7-common.dtsi index ebbe1518ef8a..63cafd220dba 100644 --- a/arch/arm/boot/dts/iwg20d-q7-common.dtsi +++ b/arch/arm/boot/dts/iwg20d-q7-common.dtsi @@ -57,7 +57,7 @@ lvds-receiver { compatible = "ti,ds90cf384a", "lvds-decoder"; - powerdown-gpios = <&gpio7 25 GPIO_ACTIVE_LOW>; + power-supply = <&vcc_3v3_tft1>; ports { #address-cells = <1>; @@ -81,6 +81,7 @@ panel { compatible = "edt,etm0700g0dh6"; backlight = <&lcd_backlight>; + power-supply = <&vcc_3v3_tft1>; port { panel_in: endpoint { @@ -113,6 +114,17 @@ }; }; + vcc_3v3_tft1: regulator-panel { + compatible = "regulator-fixed"; + + regulator-name = "vcc-3v3-tft1"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + enable-active-high; + startup-delay-us = <500>; + gpio = <&gpio7 25 GPIO_ACTIVE_HIGH>; + }; + vcc_sdhi1: regulator-vcc-sdhi1 { compatible = "regulator-fixed"; @@ -207,6 +219,7 @@ reg = <0x38>; interrupt-parent = <&gpio2>; interrupts = <12 IRQ_TYPE_EDGE_FALLING>; + vcc-supply = <&vcc_3v3_tft1>; }; }; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index eedb92526968..a4ab8b96d0eb 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -239,8 +239,6 @@ <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/owl-s500.dtsi b/arch/arm/boot/dts/owl-s500.dtsi index 5ceb6cc4451d..1dbe4e8b38ac 100644 --- a/arch/arm/boot/dts/owl-s500.dtsi +++ b/arch/arm/boot/dts/owl-s500.dtsi @@ -84,21 +84,21 @@ global_timer: timer@b0020200 { compatible = "arm,cortex-a9-global-timer"; reg = <0xb0020200 0x100>; - interrupts = <GIC_PPI 0 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_timer: timer@b0020600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xb0020600 0x20>; - interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; twd_wdt: wdt@b0020620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0xb0020620 0xe0>; - interrupts = <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts index 5700e6b700d3..b85025d00943 100644 --- a/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts +++ b/arch/arm/boot/dts/stm32mp157c-lxa-mc1.dts @@ -121,8 +121,6 @@ reset-gpios = <&gpiog 0 GPIO_ACTIVE_LOW>; /* ETH_RST# */ interrupt-parent = <&gpioa>; interrupts = <6 IRQ_TYPE_EDGE_FALLING>; /* ETH_MDINT# */ - rxc-skew-ps = <1860>; - txc-skew-ps = <1860>; reset-assert-us = <10000>; reset-deassert-us = <300>; micrel,force-master; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi index 7c4bd615b311..e4e3c92eb30d 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi @@ -11,7 +11,6 @@ serial0 = &uart4; serial1 = &usart3; serial2 = &uart8; - ethernet0 = ðernet0; }; chosen { @@ -26,23 +25,13 @@ display_bl: display-bl { compatible = "pwm-backlight"; - pwms = <&pwm2 0 500000 PWM_POLARITY_INVERTED>; + pwms = <&pwm2 3 500000 PWM_POLARITY_INVERTED>; brightness-levels = <0 16 22 30 40 55 75 102 138 188 255>; default-brightness-level = <8>; enable-gpios = <&gpioi 0 GPIO_ACTIVE_HIGH>; status = "okay"; }; - ethernet_vio: vioregulator { - compatible = "regulator-fixed"; - regulator-name = "vio"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; - regulator-always-on; - regulator-boot-on; - }; - gpio-keys-polled { compatible = "gpio-keys-polled"; #size-cells = <0>; @@ -141,28 +130,6 @@ status = "okay"; }; -ðernet0 { - status = "okay"; - pinctrl-0 = <ðernet0_rmii_pins_a>; - pinctrl-1 = <ðernet0_rmii_sleep_pins_a>; - pinctrl-names = "default", "sleep"; - phy-mode = "rmii"; - max-speed = <100>; - phy-handle = <&phy0>; - st,eth-ref-clk-sel; - phy-reset-gpios = <&gpioh 15 GPIO_ACTIVE_LOW>; - - mdio0 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "snps,dwmac-mdio"; - - phy0: ethernet-phy@1 { - reg = <1>; - }; - }; -}; - &i2c2 { /* Header X22 */ pinctrl-names = "default"; pinctrl-0 = <&i2c2_pins_a>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index ba905196fb54..a87ebc484396 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -9,6 +9,10 @@ #include <dt-bindings/mfd/st,stpmic1.h> / { + aliases { + ethernet0 = ðernet0; + }; + memory@c0000000 { device_type = "memory"; reg = <0xC0000000 0x40000000>; @@ -55,6 +59,16 @@ no-map; }; }; + + ethernet_vio: vioregulator { + compatible = "regulator-fixed"; + regulator-name = "vio"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpiog 3 GPIO_ACTIVE_LOW>; + regulator-always-on; + regulator-boot-on; + }; }; &adc { @@ -94,6 +108,28 @@ status = "okay"; }; +ðernet0 { + status = "okay"; + pinctrl-0 = <ðernet0_rmii_pins_a>; + pinctrl-1 = <ðernet0_rmii_sleep_pins_a>; + pinctrl-names = "default", "sleep"; + phy-mode = "rmii"; + max-speed = <100>; + phy-handle = <&phy0>; + st,eth-ref-clk-sel; + phy-reset-gpios = <&gpioh 3 GPIO_ACTIVE_LOW>; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@1 { + reg = <1>; + }; + }; +}; + &i2c4 { pinctrl-names = "default"; pinctrl-0 = <&i2c4_pins_a>; @@ -249,7 +285,7 @@ compatible = "ti,tsc2004"; reg = <0x49>; vio-supply = <&v3v3>; - interrupts-extended = <&gpioh 3 IRQ_TYPE_EDGE_FALLING>; + interrupts-extended = <&gpioh 15 IRQ_TYPE_EDGE_FALLING>; }; eeprom@50 { diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi index 930202742a3f..905cd7bb98cf 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi @@ -295,9 +295,9 @@ &sdmmc2 { pinctrl-names = "default", "opendrain", "sleep"; - pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_b>; - pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_b>; - pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_b>; + pinctrl-0 = <&sdmmc2_b4_pins_a &sdmmc2_d47_pins_c>; + pinctrl-1 = <&sdmmc2_b4_od_pins_a &sdmmc2_d47_pins_c>; + pinctrl-2 = <&sdmmc2_b4_sleep_pins_a &sdmmc2_d47_sleep_pins_c>; bus-width = <8>; mmc-ddr-1_8v; no-sd; diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts index 42d62d1ba1dc..ea15073f0c79 100644 --- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts +++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts @@ -223,16 +223,16 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-gmac-phy"; }; ®_dcdc1 { regulator-always-on; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; - regulator-name = "vcc-3v0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc-3v3"; }; ®_dcdc2 { diff --git a/arch/arm/configs/axm55xx_defconfig b/arch/arm/configs/axm55xx_defconfig index 46075216ee6d..c731d4ade857 100644 --- a/arch/arm/configs/axm55xx_defconfig +++ b/arch/arm/configs/axm55xx_defconfig @@ -88,7 +88,6 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_CFI_STAA=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_PHYSMAP_OF=y -CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index e849367c0566..4d8f6f647dc6 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -75,7 +75,6 @@ CONFIG_MTD_CFI=m CONFIG_MTD_CFI_INTELEXT=m CONFIG_MTD_CFI_AMDSTD=m CONFIG_MTD_PHYSMAP=m -CONFIG_MTD_M25P80=m CONFIG_MTD_RAW_NAND=m CONFIG_MTD_NAND_DAVINCI=m CONFIG_MTD_SPI_NOR=m diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig index e70c997d5f4c..546afafa63fb 100644 --- a/arch/arm/configs/dove_defconfig +++ b/arch/arm/configs/dove_defconfig @@ -44,7 +44,6 @@ CONFIG_MTD_CFI_GEOMETRY=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_STAA=y CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 87e6400c436b..5b5ae581ea22 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -110,7 +110,6 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_CFI_STAA=y CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_DATAFLASH=y -CONFIG_MTD_M25P80=y CONFIG_MTD_SST25L=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_GPMI_NAND=y diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 84a3b055f253..ddf84146a277 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -121,7 +121,6 @@ CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y CONFIG_MTD_PLATRAM=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_DAVINCI=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig index 226f2e97c6e2..18590973df12 100644 --- a/arch/arm/configs/mvebu_v5_defconfig +++ b/arch/arm/configs/mvebu_v5_defconfig @@ -75,7 +75,6 @@ CONFIG_MTD_CFI_GEOMETRY=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_STAA=y CONFIG_MTD_PHYSMAP=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_ORION=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig index cddce57fe4b9..c8f4723d99c7 100644 --- a/arch/arm/configs/mvebu_v7_defconfig +++ b/arch/arm/configs/mvebu_v7_defconfig @@ -50,7 +50,6 @@ CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_CFI_STAA=y CONFIG_MTD_PHYSMAP_OF=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_MARVELL=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index a9c6f32a9b1c..1322ebd3ccfd 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -46,7 +46,6 @@ CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y CONFIG_MTD_DATAFLASH=y -CONFIG_MTD_M25P80=y CONFIG_MTD_SST25L=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_GPMI_NAND=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index e6559e3350e6..10c1e1d2d39e 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -179,7 +179,6 @@ CONFIG_MTD_RAM=m CONFIG_MTD_ROM=m CONFIG_MTD_COMPLEX_MAPPINGS=y CONFIG_MTD_PXA2XX=m -CONFIG_MTD_M25P80=m CONFIG_MTD_BLOCK2MTD=y CONFIG_MTD_DOCG3=m CONFIG_MTD_RAW_NAND=m diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig index c882167e1496..0a90c8ded4e2 100644 --- a/arch/arm/configs/qcom_defconfig +++ b/arch/arm/configs/qcom_defconfig @@ -62,7 +62,6 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_QCOM=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 8e1f78c19920..95c38b1e4a8b 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -63,7 +63,6 @@ CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_ATMEL=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig index e73c97b0f5b0..04c8bd301a72 100644 --- a/arch/arm/configs/socfpga_defconfig +++ b/arch/arm/configs/socfpga_defconfig @@ -48,7 +48,6 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y -CONFIG_MTD_M25P80=y CONFIG_MTD_RAW_NAND=y CONFIG_MTD_NAND_DENALI_DT=y CONFIG_MTD_SPI_NOR=y diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index aa94369bdd0f..6a7988a51e38 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -76,7 +76,6 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_TEGRA_GMI=y CONFIG_MTD=y -CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_AD525X_DPOT=y diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 271cb8a1eba1..e4ce46a398e4 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -349,7 +349,8 @@ ENTRY(\sym) */ syscall_table_start sys_call_table #define COMPAT(nr, native, compat) syscall nr, native -#ifdef CONFIG_AEABI + +#if defined(CONFIG_AEABI) && !defined(CONFIG_OABI_COMPAT) #include <calls-eabi.S> #else #include <calls-oabi.S> diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 2aab043441e8..eae8aaaadc3b 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -800,6 +800,7 @@ static void __init at91_pm_init(void (*pm_idle)(void)) pmc_np = of_find_matching_node_and_match(NULL, atmel_pmc_ids, &of_id); soc_pm.data.pmc = of_iomap(pmc_np, 0); + of_node_put(pmc_np); if (!soc_pm.data.pmc) { pr_err("AT91: PM not supported, PMC not found\n"); return; diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index 6f5f89711f25..a92d277f81a0 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -174,8 +174,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, */ if (mpuss_can_lose_context) { error = cpu_cluster_pm_enter(); - if (error) + if (error) { + omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON); goto cpu_cluster_pm_out; + } } } diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c index 58c5ef3cf1d7..2d370f7f75fa 100644 --- a/arch/arm/mach-s3c24xx/mach-at2440evb.c +++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c @@ -143,7 +143,7 @@ static struct gpiod_lookup_table at2440evb_mci_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPG(10) */ - GPIO_LOOKUP("GPG", 10, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 10, "cd", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c index e1c372e5447b..82cc37513779 100644 --- a/arch/arm/mach-s3c24xx/mach-h1940.c +++ b/arch/arm/mach-s3c24xx/mach-h1940.c @@ -468,9 +468,9 @@ static struct gpiod_lookup_table h1940_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(5) */ - GPIO_LOOKUP("GPF", 5, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c index 9035f868fb34..3a5b1124037b 100644 --- a/arch/arm/mach-s3c24xx/mach-mini2440.c +++ b/arch/arm/mach-s3c24xx/mach-mini2440.c @@ -244,9 +244,9 @@ static struct gpiod_lookup_table mini2440_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPG(8) */ - GPIO_LOOKUP("GPG", 8, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 8, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_HIGH), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c index d856f23939af..ffa20f52aa83 100644 --- a/arch/arm/mach-s3c24xx/mach-n30.c +++ b/arch/arm/mach-s3c24xx/mach-n30.c @@ -359,9 +359,9 @@ static struct gpiod_lookup_table n30_mci_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(1) */ - GPIO_LOOKUP("GPF", 1, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 1, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPG(10) */ - GPIO_LOOKUP("GPG", 10, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOG", 10, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c index fde98b175c75..c0a06f123cfe 100644 --- a/arch/arm/mach-s3c24xx/mach-rx1950.c +++ b/arch/arm/mach-s3c24xx/mach-rx1950.c @@ -571,9 +571,9 @@ static struct gpiod_lookup_table rx1950_mmc_gpio_table = { .dev_id = "s3c2410-sdi", .table = { /* Card detect S3C2410_GPF(5) */ - GPIO_LOOKUP("GPF", 5, "cd", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW), /* Write protect S3C2410_GPH(8) */ - GPIO_LOOKUP("GPH", 8, "wp", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW), { }, }, }; diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 12c26eb88afb..43d91bfd2360 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1249,20 +1249,28 @@ static void __init l2c310_of_parse(const struct device_node *np, ret = of_property_read_u32(np, "prefetch-data", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_DATA_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_DATA_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_DATA_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-data property value is missing\n"); } ret = of_property_read_u32(np, "prefetch-instr", &val); if (ret == 0) { - if (val) + if (val) { prefetch |= L310_PREFETCH_CTRL_INSTR_PREFETCH; - else + *aux_val |= L310_PREFETCH_CTRL_INSTR_PREFETCH; + } else { prefetch &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + *aux_val &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; + } + *aux_mask &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH; } else if (ret != -EINVAL) { pr_err("L2C-310 OF prefetch-instr property value is missing\n"); } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c6550eddfce1..f9d7b60de351 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -434,8 +434,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr, if (pud_none(*pud_k)) goto bad_area; - if (!pud_present(*pud)) + if (!pud_present(*pud)) { set_pud(pud, *pud_k); + /* + * There is a small window during free_pgtables() where the + * user *pud entry is 0 but the TLB has not been invalidated + * and we get a level 2 (pmd) translation fault caused by the + * intermediate TLB caching of the old level 1 (pud) entry. + */ + flush_tlb_kernel_page(addr); + } pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); @@ -458,8 +466,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, #endif if (pmd_none(pmd_k[index])) goto bad_area; + if (!pmd_present(pmd[index])) + copy_pmd(pmd, pmd_k); - copy_pmd(pmd, pmd_k); return 0; bad_area: diff --git a/arch/arm/tools/gen-mach-types b/arch/arm/tools/gen-mach-types index cbe1c33bb871..cb2b69f2a39d 100644 --- a/arch/arm/tools/gen-mach-types +++ b/arch/arm/tools/gen-mach-types @@ -1,4 +1,4 @@ -#!/bin/awk +#!/usr/bin/awk # SPDX-License-Identifier: GPL-2.0 # # Awk script to generate include/generated/mach-types.h diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index d5fe7c9e0be1..5a3442346418 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,14 +10,14 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X -z norelro CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour # for relative relocs, since this leads to better Image compression # with the relocation offsets always being zero. -LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro \ +LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \ $(call ld-option, --no-apply-dynamic-relocs) endif diff --git a/arch/arm64/boot/dts/actions/s700.dtsi b/arch/arm64/boot/dts/actions/s700.dtsi index 2006ad5424fa..f8eb72bb4125 100644 --- a/arch/arm64/boot/dts/actions/s700.dtsi +++ b/arch/arm64/boot/dts/actions/s700.dtsi @@ -231,7 +231,7 @@ pinctrl: pinctrl@e01b0000 { compatible = "actions,s700-pinctrl"; - reg = <0x0 0xe01b0000 0x0 0x1000>; + reg = <0x0 0xe01b0000 0x0 0x100>; clocks = <&cmu CLK_GPIO>; gpio-controller; gpio-ranges = <&pinctrl 0 0 136>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi index 4462a68c0681..cdc4209f94d0 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi @@ -125,8 +125,7 @@ <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>; + <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "gp", "gpmmu", "pp", @@ -137,8 +136,7 @@ "pp2", "ppmmu2", "pp3", - "ppmmu3", - "pmu"; + "ppmmu3"; clocks = <&ccu CLK_BUS_GPU>, <&ccu CLK_GPU>; clock-names = "bus", "core"; resets = <&ccu RST_BUS_GPU>; diff --git a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi index ff5ba85b7562..833bbc3359c4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi @@ -41,13 +41,13 @@ led-white { label = "vim3:white:sys"; - gpios = <&gpio_ao GPIOAO_4 GPIO_ACTIVE_LOW>; + gpios = <&gpio_ao GPIOAO_4 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; led-red { label = "vim3:red"; - gpios = <&gpio_expander 5 GPIO_ACTIVE_LOW>; + gpios = <&gpio_expander 5 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 66ac66856e7e..077e12a0de3f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -614,6 +614,7 @@ gpc: gpc@303a0000 { compatible = "fsl,imx8mq-gpc"; reg = <0x303a0000 0x10000>; + interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; interrupt-controller; #interrupt-cells = <3>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi index a5a12b2599a4..01522dd10603 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi @@ -431,12 +431,11 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&nor_gpio1_pins>; - bus-width = <8>; - max-frequency = <50000000>; - non-removable; + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; + spi-max-frequency = <50000000>; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 32bd140ac9fd..103d2226c579 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -228,14 +228,14 @@ }; thermal-zones { - cpu0_1-thermal { + cpu0-1-thermal { polling-delay-passive = <250>; polling-delay = <1000>; thermal-sensors = <&tsens 5>; trips { - cpu0_1_alert0: trip-point@0 { + cpu0_1_alert0: trip-point0 { temperature = <75000>; hysteresis = <2000>; type = "passive"; @@ -258,7 +258,7 @@ }; }; - cpu2_3-thermal { + cpu2-3-thermal { polling-delay-passive = <250>; polling-delay = <1000>; @@ -1021,7 +1021,7 @@ reg-names = "mdp_phys"; interrupt-parent = <&mdss>; - interrupts = <0 0>; + interrupts = <0>; clocks = <&gcc GCC_MDSS_AHB_CLK>, <&gcc GCC_MDSS_AXI_CLK>, @@ -1053,7 +1053,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 0>; + interrupts = <4>; assigned-clocks = <&gcc BYTE0_CLK_SRC>, <&gcc PCLK0_CLK_SRC>; diff --git a/arch/arm64/boot/dts/qcom/pm8916.dtsi b/arch/arm64/boot/dts/qcom/pm8916.dtsi index 0bcdf0471107..adf9a5988cdc 100644 --- a/arch/arm64/boot/dts/qcom/pm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8916.dtsi @@ -119,7 +119,7 @@ wcd_codec: codec@f000 { compatible = "qcom,pm8916-wcd-analog-codec"; - reg = <0xf000 0x200>; + reg = <0xf000>; reg-names = "pmic-codec-core"; clocks = <&gcc GCC_CODEC_DIGCODEC_CLK>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index 31b9217bb5bf..7f1b75b2bcee 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2193,7 +2193,7 @@ system-cache-controller@9200000 { compatible = "qcom,sc7180-llcc"; - reg = <0 0x09200000 0 0x200000>, <0 0x09600000 0 0x50000>; + reg = <0 0x09200000 0 0x50000>, <0 0x09600000 0 0x50000>; reg-names = "llcc_base", "llcc_broadcast_base"; interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH>; }; @@ -2357,7 +2357,7 @@ <19200000>; interrupt-parent = <&mdss>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <0>; status = "disabled"; @@ -2380,7 +2380,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <4>; clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK>, <&dispcc DISP_CC_MDSS_BYTE0_INTF_CLK>, diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi index 42171190cce4..065e8fe3a071 100644 --- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi @@ -1214,9 +1214,8 @@ reg = <0 0xe6ea0000 0 0x0064>; interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 210>; - dmas = <&dmac1 0x43>, <&dmac1 0x42>, - <&dmac2 0x43>, <&dmac2 0x42>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x43>, <&dmac0 0x42>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>; resets = <&cpg 210>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi index 1991bdc36792..27f74df8efbd 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi @@ -1192,9 +1192,8 @@ reg = <0 0xe6ea0000 0 0x0064>; interrupts = <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 210>; - dmas = <&dmac1 0x43>, <&dmac1 0x42>, - <&dmac2 0x43>, <&dmac2 0x42>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x43>, <&dmac0 0x42>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A77990_PD_ALWAYS_ON>; resets = <&cpg 210>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 9174ddc76bdc..b8d04c5748bf 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -500,7 +500,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -511,7 +511,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 2ca7ba69c318..644be5612768 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -705,7 +705,6 @@ CONFIG_USB_TEGRA_XUDC=m CONFIG_TYPEC=m CONFIG_TYPEC_TCPM=m CONFIG_TYPEC_FUSB302=m -CONFIG_TYPEC_HD3SS3220=m CONFIG_MMC=y CONFIG_MMC_BLOCK_MINORS=32 CONFIG_MMC_ARMMMCI=y diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 0bc46149e491..4b39293d0f72 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -359,9 +359,13 @@ __AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000) __AARCH64_INSN_FUNCS(exception, 0xFF000000, 0xD4000000) __AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F) __AARCH64_INSN_FUNCS(br, 0xFFFFFC1F, 0xD61F0000) +__AARCH64_INSN_FUNCS(br_auth, 0xFEFFF800, 0xD61F0800) __AARCH64_INSN_FUNCS(blr, 0xFFFFFC1F, 0xD63F0000) +__AARCH64_INSN_FUNCS(blr_auth, 0xFEFFF800, 0xD63F0800) __AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000) +__AARCH64_INSN_FUNCS(ret_auth, 0xFFFFFBFF, 0xD65F0BFF) __AARCH64_INSN_FUNCS(eret, 0xFFFFFFFF, 0xD69F03E0) +__AARCH64_INSN_FUNCS(eret_auth, 0xFFFFFBFF, 0xD69F0BFF) __AARCH64_INSN_FUNCS(mrs, 0xFFF00000, 0xD5300000) __AARCH64_INSN_FUNCS(msr_imm, 0xFFF8F01F, 0xD500401F) __AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a1871bb32bb1..d207f63eb68e 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -163,7 +163,6 @@ extern u64 vabits_actual; #include <linux/bitops.h> #include <linux/mmdebug.h> -extern s64 physvirt_offset; extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) @@ -239,7 +238,7 @@ static inline const void *__tag_set(const void *addr, u8 tag) */ #define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) -#define __lm_to_phys(addr) (((addr) + physvirt_offset)) +#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ @@ -257,7 +256,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) #endif /* CONFIG_DEBUG_VIRTUAL */ -#define __phys_to_virt(x) ((unsigned long)((x) - physvirt_offset)) +#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 758e2d1577d0..a1745d6ea4b5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -23,6 +23,8 @@ #define VMALLOC_START (MODULES_END) #define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) + #define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ @@ -33,8 +35,6 @@ #include <linux/mm_types.h> #include <linux/sched.h> -extern struct page *vmemmap; - extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 422ed2e38a6c..d8a2bacf4e0a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -234,14 +234,17 @@ static int detect_harden_bp_fw(void) smccc_end = NULL; break; -#if IS_ENABLED(CONFIG_KVM) case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; +#if IS_ENABLED(CONFIG_KVM) smccc_start = __smccc_workaround_1_smc; smccc_end = __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ; - break; +#else + smccc_start = NULL; + smccc_end = NULL; #endif + break; default: return -1; @@ -454,6 +457,12 @@ out_printmsg: return required; } +static void cpu_enable_ssbd_mitigation(const struct arm64_cpu_capabilities *cap) +{ + if (ssbd_state != ARM64_SSBD_FORCE_DISABLE) + cap->matches(cap, SCOPE_LOCAL_CPU); +} + /* known invulnerable cores */ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), @@ -596,6 +605,12 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } +static void +cpu_enable_branch_predictor_hardening(const struct arm64_cpu_capabilities *cap) +{ + cap->matches(cap, SCOPE_LOCAL_CPU); +} + static const __maybe_unused struct midr_range tx2_family_cpus[] = { MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), @@ -887,9 +902,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #endif { + .desc = "Branch predictor hardening", .capability = ARM64_HARDEN_BRANCH_PREDICTOR, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = check_branch_predictor, + .cpu_enable = cpu_enable_branch_predictor_hardening, }, #ifdef CONFIG_HARDEN_EL2_VECTORS { @@ -903,6 +920,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_SSBD, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = has_ssbd_mitigation, + .cpu_enable = cpu_enable_ssbd_mitigation, .midr_range_list = arm64_ssb_cpus, }, #ifdef CONFIG_ARM64_ERRATUM_1418040 diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index a107375005bc..ccc8c9e22b25 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -176,7 +176,7 @@ bool __kprobes aarch64_insn_uses_literal(u32 insn) bool __kprobes aarch64_insn_is_branch(u32 insn) { - /* b, bl, cb*, tb*, b.cond, br, blr */ + /* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */ return aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) || @@ -185,8 +185,11 @@ bool __kprobes aarch64_insn_is_branch(u32 insn) aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) || aarch64_insn_is_ret(insn) || + aarch64_insn_is_ret_auth(insn) || aarch64_insn_is_br(insn) || + aarch64_insn_is_br_auth(insn) || aarch64_insn_is_blr(insn) || + aarch64_insn_is_blr_auth(insn) || aarch64_insn_is_bcond(insn); } diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index b0e03e052dd1..a4b0864c4e32 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -54,16 +54,22 @@ user_backtrace(struct frame_tail __user *tail, #ifdef CONFIG_COMPAT /* - * The registers we're interested in are at the end of the variable - * length saved register structure. The fp points at the end of this - * structure so the address of this struct is: - * (struct compat_frame_tail *)(xxx->fp)-1 + * The AAPCS ABI, the most current replacing the obsolete APCS ABI, + * does not specifically describe the stack frame with respect to the + * frame pointer. However, the examination of emitted prologue + * instructions for ARM implies that with -fno-omit-framepointer, + * register R11 is used as the frame pointer register and saved on the + * stack, with LR. * - * This code has been adapted from the ARM OProfile support. + * After the prolog, the FP points to the location of the saved LR and + * FP+4 points to the previous frames FP as shown below: + * Stack Hi Mem + * (Value of FP)+4 Saved FP for caller + * (Value of FP) LR set by caller + * Stack Lo Mem */ struct compat_frame_tail { compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */ - u32 sp; u32 lr; } __attribute__((packed)); @@ -91,11 +97,10 @@ compat_user_backtrace(struct compat_frame_tail __user *tail, * Frame pointers should strictly progress back up the stack * (towards higher addresses). */ - if (tail + 1 >= (struct compat_frame_tail __user *) - compat_ptr(buftail.fp)) + if ((u64)tail + 4 >= (u64)buftail.fp) return NULL; - return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; + return (struct compat_frame_tail __user *)((u64)buftail.fp - 4); } #endif /* CONFIG_COMPAT */ @@ -123,7 +128,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, /* AARCH32 compat mode */ struct compat_frame_tail __user *tail; - tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; + tail = (struct compat_frame_tail __user *)(regs->compat_fp - 4); while ((entry->nr < entry->max_stack) && tail && !((unsigned long)tail & 0x3)) diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 581602413a13..c26d84ff0e22 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -510,6 +510,11 @@ static u32 armv8pmu_event_cnten_mask(struct perf_event *event) static inline void armv8pmu_enable_counter(u32 mask) { + /* + * Make sure event configuration register writes are visible before we + * enable the counter. + * */ + isb(); write_sysreg(mask, pmcntenset_el0); } diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 666b225aeb3a..7a13195bb662 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -51,6 +51,10 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) if ((u32)idx == PERF_REG_ARM64_PC) return regs->pc; + if (perf_reg_abi(current) == PERF_SAMPLE_REGS_ABI_32 + && idx == 15) + return regs->regs[PERF_REG_ARM64_PC]; + return regs->regs[idx]; } diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 263d5fba4c8a..c541fb48886e 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -29,7 +29,8 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn) aarch64_insn_is_msr_imm(insn) || aarch64_insn_is_msr_reg(insn) || aarch64_insn_is_exception(insn) || - aarch64_insn_is_eret(insn)) + aarch64_insn_is_eret(insn) || + aarch64_insn_is_eret_auth(insn)) return false; /* diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 1e93cfc7c47a..ca4410eb230a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -54,12 +54,6 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -s64 physvirt_offset __ro_after_init; -EXPORT_SYMBOL(physvirt_offset); - -struct page *vmemmap __ro_after_init; -EXPORT_SYMBOL(vmemmap); - /* * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of * memory as some devices, namely the Raspberry Pi 4, have peripherals with @@ -290,20 +284,6 @@ void __init arm64_memblock_init(void) memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); - physvirt_offset = PHYS_OFFSET - PAGE_OFFSET; - - vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)); - - /* - * If we are running with a 52-bit kernel VA config on a system that - * does not support it, we have to offset our vmemmap and physvirt_offset - * s.t. we avoid the 52-bit portion of the direct linear map - */ - if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) { - vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT; - physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48); - } - /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be @@ -319,6 +299,16 @@ void __init arm64_memblock_init(void) } /* + * If we are running with a 52-bit kernel VA config on a system that + * does not support it, we have to place the available physical + * memory in the 48-bit addressable part of the linear region, i.e., + * we have to move it upward. Since memstart_addr represents the + * physical address of PAGE_OFFSET, we have to *subtract* from it. + */ + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) + memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + + /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible * via the linear mapping. diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c index 9ef4ec0aea00..59f7dfe50a4d 100644 --- a/arch/m68k/coldfire/device.c +++ b/arch/m68k/coldfire/device.c @@ -554,7 +554,7 @@ static struct platform_device mcf_edma = { }; #endif /* IS_ENABLED(CONFIG_MCF_EDMA) */ -#if IS_ENABLED(CONFIG_MMC) +#ifdef MCFSDHC_BASE static struct mcf_esdhc_platform_data mcf_esdhc_data = { .max_bus_width = 4, .cd_type = ESDHC_CD_NONE, @@ -579,7 +579,7 @@ static struct platform_device mcf_esdhc = { .resource = mcf_esdhc_resources, .dev.platform_data = &mcf_esdhc_data, }; -#endif /* IS_ENABLED(CONFIG_MMC) */ +#endif /* MCFSDHC_BASE */ static struct platform_device *mcf_devices[] __initdata = { &mcf_uart, @@ -613,7 +613,7 @@ static struct platform_device *mcf_devices[] __initdata = { #if IS_ENABLED(CONFIG_MCF_EDMA) &mcf_edma, #endif -#if IS_ENABLED(CONFIG_MMC) +#ifdef MCFSDHC_BASE &mcf_esdhc, #endif }; diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 2e87a9b6d312..63bce836b9f1 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h generic-y += extable.h -generic-y += hw_irq.h generic-y += kvm_para.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index daa24f1e1483..bfc3cf9aafb4 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -94,6 +94,10 @@ config MIPS config MIPS_FIXUP_BIGPHYS_ADDR bool +config QEMUMIPS64 + bool "Enable for qemumips64 specific configurations" + default n + menu "Machine selection" choice @@ -105,17 +109,17 @@ config MIPS_GENERIC select BOOT_RAW select BUILTIN_DTB select CEVT_R4K - select CLKSRC_MIPS_GIC select COMMON_CLK select CPU_MIPSR2_IRQ_EI select CPU_MIPSR2_IRQ_VI - select CSRC_R4K select DMA_PERDEV_COHERENT select HAVE_PCI select IRQ_MIPS_CPU select MIPS_AUTO_PFN_OFFSET select MIPS_CPU_SCACHE select MIPS_GIC + select CLKSRC_MIPS_GIC if !QEMUMIPS64 + select CSRC_R4K if !QEMUMIPS64 select MIPS_L1_CACHE_SHIFT_7 select NO_EXCEPT_FILL select PCI_DRIVERS_GENERIC @@ -524,9 +528,9 @@ config MIPS_MALTA select BOOT_RAW select BUILTIN_DTB select CEVT_R4K - select CLKSRC_MIPS_GIC + select CLKSRC_MIPS_GIC if !QEMUMIPS64 + select CSRC_R4K if !QEMUMIPS64 select COMMON_CLK - select CSRC_R4K select DMA_MAYBE_COHERENT select GENERIC_ISA_DMA select HAVE_PCSPKR_PLATFORM diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 14f8ba93367f..f0a341c30b89 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -485,6 +485,7 @@ static void __maybe_unused build_tlb_probe_entry(u32 **p) case CPU_R4700: case CPU_R5000: case CPU_NEVADA: + case CPU_4KC: uasm_i_nop(p); uasm_i_tlbp(p); break; @@ -533,6 +534,7 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l, case CPU_R4600: case CPU_R4700: + case CPU_4KC: uasm_i_nop(p); tlbw(p); uasm_i_nop(p); @@ -557,7 +559,6 @@ void build_tlb_write_entry(u32 **p, struct uasm_label **l, case CPU_R12000: case CPU_R14000: case CPU_R16000: - case CPU_4KC: case CPU_4KEC: case CPU_M14KC: case CPU_M14KEC: diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 2e64c7600eea..377dc6e7ef1c 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -36,7 +36,9 @@ cflags-vdso := $(ccflags-vdso) \ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ - $(call cc-option, -fno-stack-protector) + $(call cc-option, -fno-stack-protector) \ + $(call cc-option, -mrelax-pic-calls) \ + $(call cc-option, -mexplicit-relocs) aflags-vdso := $(ccflags-vdso) \ -D__ASSEMBLY__ -Wa,-gdwarf-2 diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index 17c24f14615f..6839f8fcf76b 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -164,19 +164,19 @@ struct __large_struct { #define __get_user_nocheck(x, ptr, size) \ ({ \ - long __gu_err, __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + long __gu_err; \ + __get_user_size((x), (ptr), (size), __gu_err); \ __gu_err; \ }) #define __get_user_check(x, ptr, size) \ ({ \ - long __gu_err = -EFAULT, __gu_val = 0; \ - const __typeof__(*(ptr)) * __gu_addr = (ptr); \ - if (access_ok(__gu_addr, size)) \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + long __gu_err = -EFAULT; \ + const __typeof__(*(ptr)) *__gu_addr = (ptr); \ + if (access_ok(__gu_addr, size)) \ + __get_user_size((x), __gu_addr, (size), __gu_err); \ + else \ + (x) = (__typeof__(*(ptr))) 0; \ __gu_err; \ }) @@ -190,11 +190,13 @@ do { \ case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break; \ case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break; \ case 8: __get_user_asm2(x, ptr, retval); break; \ - default: (x) = __get_user_bad(); \ + default: (x) = (__typeof__(*(ptr)))__get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, op) \ +{ \ + unsigned long __gu_tmp; \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ "2:\n" \ @@ -208,10 +210,14 @@ do { \ " .align 2\n" \ " .long 1b,3b\n" \ ".previous" \ - : "=r"(err), "=r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))__gu_tmp; \ +} #define __get_user_asm2(x, addr, err) \ +{ \ + unsigned long long __gu_tmp; \ __asm__ __volatile__( \ "1: l.lwz %1,0(%2)\n" \ "2: l.lwz %H1,4(%2)\n" \ @@ -228,8 +234,11 @@ do { \ " .long 1b,4b\n" \ " .long 2b,4b\n" \ ".previous" \ - : "=r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT), "0"(err)) + : "=r"(err), "=&r"(__gu_tmp) \ + : "r"(addr), "i"(-EFAULT), "0"(err)); \ + (x) = (__typeof__(*(addr)))( \ + (__typeof__((x)-(x)))__gu_tmp); \ +} /* more complex routines */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9fa23eb320ff..cf78ad7ff0b7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -135,7 +135,7 @@ config PPC select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE - select ARCH_HAS_UACCESS_MCSAFE if PPC64 + select ARCH_HAS_COPY_MC if PPC64 select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index f310c32e88a4..03c32b1a57f8 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -290,6 +290,9 @@ PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2) boot := arch/$(ARCH)/boot +# These targets cannot be built in parallel +.NOTPARALLEL: $(BOOT_TARGETS) + $(BOOT_TARGETS1): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@) $(BOOT_TARGETS2): vmlinux @@ -418,7 +421,10 @@ endif archclean: $(Q)$(MAKE) $(clean)=$(boot) -archprepare: checkbin +arch/powerpc/lib/crtsavres.o: arch/powerpc/lib/crtsavres.S + $(Q)$(MAKE) $(build)=arch/powerpc/lib arch/powerpc/lib/crtsavres.o + +archprepare: checkbin arch/powerpc/lib/crtsavres.o archheaders: $(Q)$(MAKE) $(build)=arch/powerpc/kernel/syscalls all diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 3f9ae3585ab9..80c953414882 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,19 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 -#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) /* - * Our page table limit us to 64TB. Hence for the kernel mapping, - * each MAP area is limited to 16 TB. - * The four map areas are: linear mapping, vmap, IO and vmemmap + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. */ +#define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Define the address range of the kernel non-linear virtual area (61TB) */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 414d209f45bb..c711fe890110 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,14 +8,13 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include <linux/sched.h> + struct drmem_lmb { u64 base_addr; u32 drc_index; u32 aa_index; u32 flags; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; -#endif }; struct drmem_lmb_info { @@ -26,8 +25,22 @@ struct drmem_lmb_info { extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) < (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ @@ -104,22 +117,4 @@ static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) lmb->aa_index = 0xffffffff; } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ - lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr); -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ - lmb->nid = -1; -} -#else -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ -} -#endif - #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index cb424799da0d..5a00da670a40 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -40,6 +40,7 @@ struct arch_hw_breakpoint { #else #define HW_BREAKPOINT_SIZE 0x8 #endif +#define HW_BREAKPOINT_SIZE_QUADWORD 0x10 #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 88e6c78100d9..c750afc62887 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -815,7 +815,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index b72692702f35..9bf6dffb4090 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -53,9 +53,7 @@ void *__memmove(void *to, const void *from, __kernel_size_t n); #ifndef CONFIG_KASAN #define __HAVE_ARCH_MEMSET32 #define __HAVE_ARCH_MEMSET64 -#define __HAVE_ARCH_MEMCPY_MCSAFE -extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz); extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t); extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t); diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h index 85580b30aba4..7546402d796a 100644 --- a/arch/powerpc/include/asm/svm.h +++ b/arch/powerpc/include/asm/svm.h @@ -15,6 +15,8 @@ static inline bool is_secure_guest(void) return mfmsr() & MSR_S; } +void __init svm_swiotlb_init(void); + void dtl_cache_ctor(void *addr); #define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL) @@ -25,6 +27,8 @@ static inline bool is_secure_guest(void) return false; } +static inline void svm_swiotlb_init(void) {} + #define get_dtl_cache_ctor() NULL #endif /* CONFIG_PPC_SVM */ diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 862985cf5180..cf87bbdcfdcb 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -67,19 +67,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 64c04ab09112..97506441c15b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -436,6 +436,32 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_generic(void *to, const void *from, unsigned long size); + +static inline unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned long size) +{ + return copy_mc_generic(to, from, size); +} +#define copy_mc_to_kernel copy_mc_to_kernel + +static inline unsigned long __must_check +copy_mc_to_user(void __user *to, const void *from, unsigned long n) +{ + if (likely(check_copy_size(from, n, true))) { + if (access_ok(to, n)) { + allow_write_to_user(to, n); + n = copy_mc_generic((void *)to, from, n); + prevent_write_to_user(to, n); + } + } + + return n; +} +#endif + #ifdef __powerpc64__ static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) @@ -524,20 +550,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) return ret; } -static __always_inline unsigned long __must_check -copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) -{ - if (likely(check_copy_size(from, n, true))) { - if (access_ok(to, n)) { - allow_write_to_user(to, n); - n = memcpy_mcsafe((void *)to, from, n); - prevent_write_to_user(to, n); - } - } - - return n; -} - unsigned long __arch_clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 244542ae2a91..53484600855a 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -4,7 +4,9 @@ # ifdef CONFIG_PPC64 -CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) +CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) $(call cc-disable-warning, attribute-alias) +CFLAGS_ptrace.o += $(call cc-disable-warning, array-bounds) +CFLAGS_syscalls.o += $(call cc-disable-warning, attribute-alias) endif ifdef CONFIG_PPC32 CFLAGS_prom_init.o += -fPIC diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index c55e67bab271..2190be70c7fd 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -519,9 +519,17 @@ static bool ea_hw_range_overlaps(unsigned long ea, int size, struct arch_hw_breakpoint *info) { unsigned long hw_start_addr, hw_end_addr; + unsigned long align_size = HW_BREAKPOINT_SIZE; - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); + /* + * On p10 predecessors, quadword is handle differently then + * other instructions. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) + align_size = HW_BREAKPOINT_SIZE_QUADWORD; + + hw_start_addr = ALIGN_DOWN(info->address, align_size); + hw_end_addr = ALIGN(info->address + info->len, align_size); return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); } @@ -635,6 +643,8 @@ static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, if (*type == CACHEOP) { *size = cache_op_size(); *ea &= ~(*size - 1); + } else if (*type == LOAD_VMX || *type == STORE_VMX) { + *ea &= ~(*size - 1); } } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 05b1cc0e009e..3a22281a8264 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -214,7 +214,7 @@ void replay_soft_interrupts(void) struct pt_regs regs; ppc_save_regs(®s); - regs.softe = IRQS_ALL_DISABLED; + regs.softe = IRQS_ENABLED; again: if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) @@ -368,6 +368,12 @@ notrace void arch_local_irq_restore(unsigned long mask) } } + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); @@ -377,6 +383,7 @@ notrace void arch_local_irq_restore(unsigned long mask) trace_hardirqs_on(); irq_soft_mask_set(IRQS_ENABLED); __hard_irq_enable(); + preempt_enable(); } EXPORT_SYMBOL(arch_local_irq_restore); diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 697c7e4b5877..8bd8d8de5c40 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -219,6 +219,7 @@ long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_inf brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE); brk.type = HW_BRK_TYPE_TRANSLATE; brk.len = DABR_MAX_LEN; + brk.hw_len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index e2ab8a111b69..0b4694b8d248 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -13,13 +13,14 @@ */ #include <linux/errno.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/init.h> +#include <linux/delay.h> +#include <linux/workqueue.h> #include <asm/io.h> #include <asm/reg.h> @@ -39,9 +40,7 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; -struct timer_list tau_timer; - -#undef DEBUG +static bool tau_int_enable; /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ @@ -50,72 +49,49 @@ struct timer_list tau_timer; #define step_size 2 /* step size when temp goes out of range */ #define window_expand 1 /* expand the window by this much */ /* configurable values for shrinking the window */ -#define shrink_timer 2*HZ /* period between shrinking the window */ +#define shrink_timer 2000 /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ static void set_thresholds(unsigned long cpu) { -#ifdef CONFIG_TAU_INT - /* - * setup THRM1, - * threshold, valid bit, enable interrupts, interrupt when below threshold - */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID); + u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0; - /* setup THRM2, - * threshold, valid bit, enable interrupts, interrupt when above threshold - */ - mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE); -#else - /* same thing but don't enable interrupts */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID); - mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V); -#endif + /* setup THRM1, threshold, valid bit, interrupt when below threshold */ + mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID); + + /* setup THRM2, threshold, valid bit, interrupt when above threshold */ + mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie); } static void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -140,17 +116,16 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); -#ifndef CONFIG_TAU_INT - TAUupdate(cpu); -#endif + if (!tau_int_enable) + TAUupdate(cpu); + + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { @@ -173,32 +148,26 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } -static void tau_timeout_smp(struct timer_list *unused) -{ +static struct workqueue_struct *tau_workq; - /* schedule ourselves to be run again */ - mod_timer(&tau_timer, jiffies + shrink_timer) ; +static void tau_work_func(struct work_struct *work) +{ + msleep(shrink_timer); on_each_cpu(tau_timeout, NULL, 0); + /* schedule ourselves to be run again */ + queue_work(tau_workq, work); } +DECLARE_WORK(tau_work, tau_work_func); + /* * setup the TAU * @@ -231,21 +200,19 @@ static int __init TAU_init(void) return 1; } + tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && + !strcmp(cur_cpu_spec->platform, "ppc750"); - /* first, set up the window shrinking timer */ - timer_setup(&tau_timer, tau_timeout_smp, 0); - tau_timer.expires = jiffies + shrink_timer; - add_timer(&tau_timer); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1, 0); + if (!tau_workq) + return -ENOMEM; on_each_cpu(TAU_init_smp, NULL, 0); - printk("Thermal assist unit "); -#ifdef CONFIG_TAU_INT - printk("using interrupts, "); -#else - printk("using timers, "); -#endif - printk("shrink_timer: %d jiffies\n", shrink_timer); + queue_work(tau_workq, &tau_work); + + pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", + tau_int_enable ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S index 0bcc5e5fe789..de401e6ee9c8 100644 --- a/arch/powerpc/kernel/vdso32/sigtramp.S +++ b/arch/powerpc/kernel/vdso32/sigtramp.S @@ -247,6 +247,40 @@ V_FUNCTION_END(__kernel_sigtramp_rt32) vsave_msr1 (31); \ vsave_msr2 (33, 32*16+12); \ vsave (32, 32*16) +#elif defined(CONFIG_SPE) +#define EH_FRAME_VMX \ + rsave (113, VREGS); \ + rsave (114, VREGS + 1*4); \ + rsave (115, VREGS + 2*4); \ + rsave (116, VREGS + 3*4); \ + rsave (117, VREGS + 4*4); \ + rsave (118, VREGS + 5*4); \ + rsave (119, VREGS + 6*4); \ + rsave (120, VREGS + 7*4); \ + rsave (121, VREGS + 8*4); \ + rsave (122, VREGS + 9*4); \ + rsave (123, VREGS + 10*4); \ + rsave (124, VREGS + 11*4); \ + rsave (125, VREGS + 12*4); \ + rsave (126, VREGS + 13*4); \ + rsave (127, VREGS + 14*4); \ + rsave (128, VREGS + 15*4); \ + rsave (129, VREGS + 16*4); \ + rsave (130, VREGS + 17*4); \ + rsave (131, VREGS + 18*4); \ + rsave (132, VREGS + 19*4); \ + rsave (133, VREGS + 20*4); \ + rsave (134, VREGS + 21*4); \ + rsave (135, VREGS + 22*4); \ + rsave (136, VREGS + 23*4); \ + rsave (137, VREGS + 24*4); \ + rsave (138, VREGS + 25*4); \ + rsave (139, VREGS + 26*4); \ + rsave (140, VREGS + 27*4); \ + rsave (141, VREGS + 28*4); \ + rsave (142, VREGS + 29*4); \ + rsave (143, VREGS + 30*4); \ + rsave (144, VREGS + 31*4); #else #define EH_FRAME_VMX #endif diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 5e994cda8e40..c254f5f733a8 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ memcpy_power7.o obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ - memcpy_64.o memcpy_mcsafe_64.o + memcpy_64.o copy_mc_64.o obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/copy_mc_64.S index cb882d9a6d8a..88d46c471493 100644 --- a/arch/powerpc/lib/memcpy_mcsafe_64.S +++ b/arch/powerpc/lib/copy_mc_64.S @@ -50,7 +50,7 @@ err3; stb r0,0(r3) blr -_GLOBAL(memcpy_mcsafe) +_GLOBAL(copy_mc_generic) mr r7,r5 cmpldi r5,16 blt .Lshort_copy @@ -239,4 +239,4 @@ err1; stb r0,0(r3) 15: li r3,0 blr -EXPORT_SYMBOL_GPL(memcpy_mcsafe); +EXPORT_SYMBOL_GPL(copy_mc_generic); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index b5cc9b23cf02..277a07772e7d 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -644,19 +644,29 @@ static void do_exit_flush_lazy_tlb(void *arg) struct mm_struct *mm = arg; unsigned long pid = mm->context.id; + /* + * A kthread could have done a mmget_not_zero() after the flushing CPU + * checked mm_is_singlethreaded, and be in the process of + * kthread_use_mm when interrupted here. In that case, current->mm will + * be set to mm, because kthread_use_mm() setting ->mm and switching to + * the mm is done with interrupts off. + */ if (current->mm == mm) - return; /* Local CPU */ + goto out_flush; if (current->active_mm == mm) { - /* - * Must be a kernel thread because sender is single-threaded. - */ - BUG_ON(current->mm); + WARN_ON_ONCE(current->mm != NULL); + /* Is a kernel thread and is using mm as the lazy tlb */ mmgrab(&init_mm); - switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); mmdrop(mm); } + + atomic_dec(&mm->context.active_cpus); + cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm)); + +out_flush: _tlbiel_pid(pid, RIC_FLUSH_ALL); } @@ -671,7 +681,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm) */ smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb, (void *)mm, 1); - mm_reset_thread_local(mm); } void radix__flush_tlb_mm(struct mm_struct *mm) diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 156c38f89511..e7ebc845f786 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -598,6 +598,7 @@ void slb_initialize(void) asm volatile("isync":::"memory"); asm volatile("slbmte %0,%0"::"r" (0) : "memory"); asm volatile("isync; slbia; isync":::"memory"); + mb(); create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX); /* diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 59327cefbc6a..873fcfc7b875 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -362,10 +362,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) if (!drmem_info->lmbs) return; - for_each_drmem_lmb(lmb) { + for_each_drmem_lmb(lmb) read_drconf_v1_cell(lmb, &prop); - lmb_set_nid(lmb); - } } static void __init init_drmem_v2_lmbs(const __be32 *prop) @@ -410,8 +408,6 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) lmb->aa_index = dr_cell.aa_index; lmb->flags = dr_cell.flags; - - lmb_set_nid(lmb); } } } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 019b0c0bbbf3..ca91d04d0a7a 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -121,8 +121,7 @@ void __init kasan_mmu_init(void) { int ret; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || - IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -133,11 +132,11 @@ void __init kasan_mmu_init(void) void __init kasan_init(void) { struct memblock_region *reg; + int ret; for_each_memblock(memory, reg) { phys_addr_t base = reg->base; phys_addr_t top = min(base + reg->size, total_lowmem); - int ret; if (base >= top) continue; @@ -147,6 +146,13 @@ void __init kasan_init(void) panic("kasan: kasan_init_region() failed"); } + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } + kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c2c11eb8dcfc..0f21bcb16405 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -50,6 +50,7 @@ #include <asm/swiotlb.h> #include <asm/rtas.h> #include <asm/kasan.h> +#include <asm/svm.h> #include <mm/mmu_decl.h> @@ -290,7 +291,10 @@ void __init mem_init(void) * back to to-down. */ memblock_set_bottom_up(true); - swiotlb_init(0); + if (is_secure_guest()) + svm_swiotlb_init(); + else + swiotlb_init(0); #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index e608f9db12dd..8965b4463d43 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -95,7 +95,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -223,7 +223,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -234,7 +234,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 4c86da5eb28a..0b5c8f4fbdbf 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -269,6 +269,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) mask |= CNST_PMC_MASK(pmc); value |= CNST_PMC_VAL(pmc); + + /* + * PMC5 and PMC6 are used to count cycles and instructions and + * they do not support most of the constraint bits. Add a check + * to exclude PMC5/6 from most of the constraints except for + * EBB/BHRB. + */ + if (pmc >= 5) + goto ebb_bhrb; } if (pmc <= 4) { @@ -335,6 +344,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } } +ebb_bhrb: if (!pmc && ebb) /* EBB events must specify the PMC */ return -1; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index fb7515b4fa9c..b439b027a42f 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -223,12 +223,11 @@ config TAU temperature within 2-4 degrees Celsius. This option shows the current on-die temperature in /proc/cpuinfo if the cpu supports it. - Unfortunately, on some chip revisions, this sensor is very inaccurate - and in many cases, does not work at all, so don't assume the cpu - temp is actually what /proc/cpuinfo says it is. + Unfortunately, this sensor is very inaccurate when uncalibrated, so + don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU help The TAU supports an interrupt driven mode which causes an interrupt @@ -236,12 +235,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 543c816fa99e..0e6693bacb7e 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -318,15 +318,14 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct dump_obj *create_dump_obj(uint32_t id, size_t size, - uint32_t type) +static void create_dump_obj(uint32_t id, size_t size, uint32_t type) { struct dump_obj *dump; int rc; dump = kzalloc(sizeof(*dump), GFP_KERNEL); if (!dump) - return NULL; + return; dump->kobj.kset = dump_kset; @@ -346,21 +345,39 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size, rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); if (rc) { kobject_put(&dump->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this dump is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the dump before kobject_uevent() is called. If that + * happens then there is a potential race between + * dump_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&dump->kobj); rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&dump->kobj, KOBJ_ADD); + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + } else { + /* Drop reference count taken for bin file */ kobject_put(&dump->kobj); - return NULL; } - pr_info("%s: New platform dump. ID = 0x%x Size %u\n", - __func__, dump->id, dump->size); - - kobject_uevent(&dump->kobj, KOBJ_ADD); - - return dump; + /* Drop our reference */ + kobject_put(&dump->kobj); + return; } static irqreturn_t process_dump(int irq, void *data) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 8b748690dac2..9f236149b402 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -356,25 +356,32 @@ static int dlpar_add_lmb(struct drmem_lmb *); static int dlpar_remove_lmb(struct drmem_lmb *lmb) { + struct memory_block *mem_block; unsigned long block_sz; int rc; if (!lmb_is_removable(lmb)) return -EINVAL; + mem_block = lmb_to_memblock(lmb); + if (mem_block == NULL) + return -EINVAL; + rc = dlpar_offline_lmb(lmb); - if (rc) + if (rc) { + put_device(&mem_block->dev); return rc; + } block_sz = pseries_memory_block_size(); - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + put_device(&mem_block->dev); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); lmb->flags &= ~DRCONF_MEM_ASSIGNED; return 0; @@ -631,7 +638,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) static int dlpar_add_lmb(struct drmem_lmb *lmb) { unsigned long block_sz; - int rc; + int nid, rc; if (lmb->flags & DRCONF_MEM_ASSIGNED) return -EINVAL; @@ -642,11 +649,13 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) return rc; } - lmb_set_nid(lmb); block_sz = memory_block_size_bytes(); + /* Find the node id for this address. */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + /* Add the memory */ - rc = __add_memory(lmb->nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; @@ -654,9 +663,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; } diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 9c569078a09f..6c2c66450dac 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -702,6 +702,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.of_node = p->pdev->dev.of_node; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); + /* Set the dimm command family mask to accept PDSMs */ + set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask); + if (!p->bus_desc.provider_name) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 13c86a292c6d..b2b245b25edb 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -521,18 +521,55 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +static int mce_handle_err_realmode(int disposition, u8 error_type) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (disposition == RTAS_DISP_NOT_RECOVERED) { + switch (error_type) { + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + /* + * Store the old slb content in paca before flushing. + * Print this when we go to virtual mode. + * There are chances that we may hit MCE again if there + * is a parity error on the SLB entry we trying to read + * for saving. Hence limit the slb saving to single + * level of recursion. + */ + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); + flush_and_reload_slb(); + disposition = RTAS_DISP_FULLY_RECOVERED; + break; + default: + break; + } + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { + /* Platform corrected itself but could be degraded */ + pr_err("MCE: limited recovery, system may be degraded\n"); + disposition = RTAS_DISP_FULLY_RECOVERED; + } +#endif + return disposition; +} -static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +static int mce_handle_err_virtmode(struct pt_regs *regs, + struct rtas_error_log *errp, + struct pseries_mc_errorlog *mce_log, + int disposition) { struct mce_error_info mce_err = { 0 }; - unsigned long eaddr = 0, paddr = 0; - struct pseries_errorlog *pseries_log; - struct pseries_mc_errorlog *mce_log; - int disposition = rtas_error_disposition(errp); int initiator = rtas_error_initiator(errp); int severity = rtas_error_severity(errp); + unsigned long eaddr = 0, paddr = 0; u8 error_type, err_sub_type; + if (!mce_log) + goto out; + + error_type = mce_log->error_type; + err_sub_type = rtas_mc_error_sub_type(mce_log); + if (initiator == RTAS_INITIATOR_UNKNOWN) mce_err.initiator = MCE_INITIATOR_UNKNOWN; else if (initiator == RTAS_INITIATOR_CPU) @@ -571,18 +608,7 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; mce_err.error_class = MCE_ECLASS_UNKNOWN; - if (!rtas_error_extended(errp)) - goto out; - - pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); - if (pseries_log == NULL) - goto out; - - mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - error_type = mce_log->error_type; - err_sub_type = rtas_mc_error_sub_type(mce_log); - - switch (mce_log->error_type) { + switch (error_type) { case MC_ERROR_TYPE_UE: mce_err.error_type = MCE_ERROR_TYPE_UE; mce_common_process_ue(regs, &mce_err); @@ -682,37 +708,31 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; break; } +out: + save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, + &mce_err, regs->nip, eaddr, paddr); + return disposition; +} -#ifdef CONFIG_PPC_BOOK3S_64 - if (disposition == RTAS_DISP_NOT_RECOVERED) { - switch (error_type) { - case MC_ERROR_TYPE_SLB: - case MC_ERROR_TYPE_ERAT: - /* - * Store the old slb content in paca before flushing. - * Print this when we go to virtual mode. - * There are chances that we may hit MCE again if there - * is a parity error on the SLB entry we trying to read - * for saving. Hence limit the slb saving to single - * level of recursion. - */ - if (local_paca->in_mce == 1) - slb_save_contents(local_paca->mce_faulty_slbs); - flush_and_reload_slb(); - disposition = RTAS_DISP_FULLY_RECOVERED; - break; - default: - break; - } - } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { - /* Platform corrected itself but could be degraded */ - printk(KERN_ERR "MCE: limited recovery, system may " - "be degraded\n"); - disposition = RTAS_DISP_FULLY_RECOVERED; - } -#endif +static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +{ + struct pseries_errorlog *pseries_log; + struct pseries_mc_errorlog *mce_log = NULL; + int disposition = rtas_error_disposition(errp); + u8 error_type; + + if (!rtas_error_extended(errp)) + goto out; + + pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); + if (!pseries_log) + goto out; + + mce_log = (struct pseries_mc_errorlog *)pseries_log->data; + error_type = mce_log->error_type; + + disposition = mce_handle_err_realmode(disposition, error_type); -out: /* * Enable translation as we will be accessing per-cpu variables * in save_mce_event() which may fall outside RMO region, also @@ -723,10 +743,10 @@ out: * Note: All the realmode handling like flushing SLB entries for * SLB multihit is done by now. */ +out: mtmsr(mfmsr() | MSR_IR | MSR_DR); - save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, - &mce_err, regs->nip, eaddr, paddr); - + disposition = mce_handle_err_virtmode(regs, errp, mce_log, + disposition); return disposition; } diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index bbb97169bf63..6268545947b8 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -36,6 +36,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 40c0637203d5..81085eb8f225 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -7,6 +7,7 @@ */ #include <linux/mm.h> +#include <linux/memblock.h> #include <asm/machdep.h> #include <asm/svm.h> #include <asm/swiotlb.h> @@ -34,6 +35,31 @@ static int __init init_svm(void) } machine_early_initcall(pseries, init_svm); +/* + * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it + * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have + * any addressing limitation, we don't need to allocate it in low addresses. + */ +void __init svm_swiotlb_init(void) +{ + unsigned char *vstart; + unsigned long bytes, io_tlb_nslabs; + + io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + panic("SVM: Cannot allocate SWIOTLB buffer"); +} + int set_memory_encrypted(unsigned long addr, int numpages) { if (!PAGE_ALIGNED(addr)) diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index ad8117148ea3..21b9d1bf39ff 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -174,6 +174,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 7efe4bc3ccf6..ac5862cee142 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -962,6 +962,7 @@ static void insert_cpu_bpts(void) brk.address = dabr[i].address; brk.type = (dabr[i].enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; + brk.hw_len = 8; __set_breakpoint(i, &brk); } } diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 5967f3014156..c93486a9989b 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -197,9 +197,10 @@ void pcibios_bus_add_device(struct pci_dev *pdev) * With pdev->no_vf_scan the common PCI probing code does not * perform PF/VF linking. */ - if (zdev->vfn) + if (zdev->vfn) { zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); - + pdev->no_command_memory = 1; + } } static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) diff --git a/arch/sh/tools/gen-mach-types b/arch/sh/tools/gen-mach-types index 6d7c2d8eaf55..2a4a42a6d70c 100644 --- a/arch/sh/tools/gen-mach-types +++ b/arch/sh/tools/gen-mach-types @@ -1,4 +1,4 @@ -#!/bin/awk +#!/usr/bin/awk # SPDX-License-Identifier: GPL-2.0 # # Awk script to generate include/generated/machtypes.h diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 8735c468230a..555203e3e7b4 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1403,7 +1403,7 @@ static int vector_net_load_bpf_flash(struct net_device *dev, kfree(vp->bpf->filter); vp->bpf->filter = NULL; } else { - vp->bpf = kmalloc(sizeof(struct sock_fprog), GFP_KERNEL); + vp->bpf = kmalloc(sizeof(struct sock_fprog), GFP_ATOMIC); if (vp->bpf == NULL) { netdev_err(dev, "failed to allocate memory for firmware\n"); goto flash_fail; @@ -1415,7 +1415,7 @@ static int vector_net_load_bpf_flash(struct net_device *dev, if (request_firmware(&fw, efl->data, &vdevice->pdev.dev)) goto flash_fail; - vp->bpf->filter = kmemdup(fw->data, fw->size, GFP_KERNEL); + vp->bpf->filter = kmemdup(fw->data, fw->size, GFP_ATOMIC); if (!vp->bpf->filter) goto free_buffer; diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 25eaa6a0c658..c07436e89e59 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -70,13 +70,17 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, * read of the message and write of the ACK. */ if (mode != TTMH_READ) { + bool disabled = irqs_disabled(); + + BUG_ON(mode == TTMH_IDLE && !disabled); + + if (disabled) + local_irq_enable(); while (os_poll(1, &time_travel_ext_fd) != 0) { - if (mode == TTMH_IDLE) { - BUG_ON(!irqs_disabled()); - local_irq_enable(); - local_irq_disable(); - } + /* nothing */ } + if (disabled) + local_irq_disable(); } ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 883da0abf779..1f4104f8852b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -75,7 +75,7 @@ config X86 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE + select ARCH_HAS_COPY_MC if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 0dd319e6e5b4..ec98b400e38f 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -59,7 +59,7 @@ config EARLY_PRINTK_USB_XDBC You should normally say N here, unless you want to debug early crashes or need a very simple printk logging facility. -config MCSAFE_TEST +config COPY_MC_TEST def_bool n config EFI_PGT_DUMP diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index c8862696a47b..077d19268b0b 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -12,7 +12,9 @@ * It is not referenced from the code, but GCC < 5 with -fPIE would fail * due to an undefined symbol. Define it to make these ancient GCCs work. */ +#ifndef CONFIG_RANDOMIZE_BASE unsigned long __force_order; +#endif #define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ #define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 26c36357c4c9..a023cbe21230 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -89,6 +89,7 @@ struct perf_ibs { u64 max_period; unsigned long offset_mask[1]; int offset_max; + unsigned int fetch_count_reset_broken : 1; struct cpu_perf_ibs __percpu *pcpu; struct attribute **format_attrs; @@ -363,7 +364,12 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event, static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { - wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask); + u64 tmp = hwc->config | config; + + if (perf_ibs->fetch_count_reset_broken) + wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask); + + wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask); } /* @@ -733,6 +739,13 @@ static __init void perf_event_ibs_init(void) { struct attribute **attr = ibs_op_format_attrs; + /* + * Some chips fail to reset the fetch count when it is written; instead + * they need a 0-1 transition of IbsFetchEn. + */ + if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18) + perf_ibs_fetch.fetch_count_reset_broken = 1; + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); if (ibs_caps & IBS_CAPS_OPCNT) { diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index fb616203ce42..be50ef8572cc 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -379,7 +379,7 @@ static __init int _init_events_attrs(void) while (amd_iommu_v2_event_descs[i].attr.attr.name) i++; - attrs = kcalloc(i + 1, sizeof(struct attribute **), GFP_KERNEL); + attrs = kcalloc(i + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 4103665c6e03..29640b4079af 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1087,8 +1087,10 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, cpuc->event_list[n] = event; n++; - if (is_counter_pair(&event->hw)) + if (is_counter_pair(&event->hw)) { cpuc->n_pair++; + cpuc->n_txn_pair++; + } } return n; } @@ -1953,6 +1955,7 @@ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); + __this_cpu_write(cpu_hw_events.n_txn_pair, 0); } /* @@ -1978,6 +1981,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); + __this_cpu_sub(cpu_hw_events.n_pair, __this_cpu_read(cpu_hw_events.n_txn_pair)); perf_pmu_enable(pmu); } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index dc43cc124e09..221d1766d6e6 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -670,9 +670,7 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - struct pt_regs regs; - - x86_pmu.drain_pebs(®s); + x86_pmu.drain_pebs(NULL); } /* @@ -1737,6 +1735,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); + struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1749,6 +1748,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } else if (!intel_pmu_save_and_restart(event)) return; + if (!iregs) + iregs = &dummy_iregs; + while (count > 1) { setup_sample(event, iregs, at, &data, regs); perf_event_output(event, &data, regs); @@ -1758,16 +1760,22 @@ static void __intel_pmu_pebs_event(struct perf_event *event, } setup_sample(event, iregs, at, &data, regs); - - /* - * All but the last records are processed. - * The last one is left to be able to call the overflow handler. - */ - if (perf_event_overflow(event, &data, regs)) { - x86_pmu_stop(event, 0); - return; + if (iregs == &dummy_iregs) { + /* + * The PEBS records may be drained in the non-overflow context, + * e.g., large PEBS + context switch. Perf should treat the + * last record the same as other PEBS records, and doesn't + * invoke the generic overflow handler. + */ + perf_event_output(event, &data, regs); + } else { + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, regs)) + x86_pmu_stop(event, 0); } - } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 1038e9f1e354..3b70c2ff177c 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -115,6 +115,10 @@ #define ICL_UNC_CBO_0_PER_CTR0 0x702 #define ICL_UNC_CBO_MSR_OFFSET 0x8 +/* ICL ARB register */ +#define ICL_UNC_ARB_PER_CTR 0x3b1 +#define ICL_UNC_ARB_PERFEVTSEL 0x3b3 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); @@ -302,15 +306,21 @@ void skl_uncore_cpu_init(void) snb_uncore_arb.ops = &skl_uncore_msr_ops; } +static struct intel_uncore_ops icl_uncore_msr_ops = { + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + static struct intel_uncore_type icl_uncore_cbox = { .name = "cbox", - .num_counters = 4, + .num_counters = 2, .perf_ctr_bits = 44, .perf_ctr = ICL_UNC_CBO_0_PER_CTR0, .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, .event_mask = SNB_UNC_RAW_EVENT_MASK, .msr_offset = ICL_UNC_CBO_MSR_OFFSET, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .format_group = &snb_uncore_format_group, }; @@ -339,13 +349,25 @@ static struct intel_uncore_type icl_uncore_clockbox = { .single_fixed = 1, .event_mask = SNB_UNC_CTL_EV_SEL_MASK, .format_group = &icl_uncore_clock_format_group, - .ops = &skl_uncore_msr_ops, + .ops = &icl_uncore_msr_ops, .event_descs = icl_uncore_events, }; +static struct intel_uncore_type icl_uncore_arb = { + .name = "arb", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 44, + .perf_ctr = ICL_UNC_ARB_PER_CTR, + .event_ctl = ICL_UNC_ARB_PERFEVTSEL, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .ops = &icl_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + static struct intel_uncore_type *icl_msr_uncores[] = { &icl_uncore_cbox, - &snb_uncore_arb, + &icl_uncore_arb, &icl_uncore_clockbox, NULL, }; @@ -363,7 +385,6 @@ void icl_uncore_cpu_init(void) { uncore_msr_uncores = icl_msr_uncores; icl_uncore_cbox.num_boxes = icl_get_cbox_num(); - snb_uncore_arb.ops = &skl_uncore_msr_ops; } enum { diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 07652fa20ebb..6a03fe8054a8 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4550,10 +4550,10 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -5009,17 +5009,17 @@ static struct uncore_event_desc icx_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_read, "event=0xff,umask=0x30"), - INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(ddrt_write, "event=0xff,umask=0x31"), - INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(ddrt_write.unit, "MiB"), { /* end: all zeroes */ }, }; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e17a3d8a47ed..d4d482d16fe1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -198,6 +198,7 @@ struct cpu_hw_events { they've never been enabled yet */ int n_txn; /* the # last events in the below arrays; added in the current transaction */ + int n_txn_pair; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; diff --git a/arch/x86/include/asm/copy_mc_test.h b/arch/x86/include/asm/copy_mc_test.h new file mode 100644 index 000000000000..e4991ba96726 --- /dev/null +++ b/arch/x86/include/asm/copy_mc_test.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _COPY_MC_TEST_H_ +#define _COPY_MC_TEST_H_ + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_COPY_MC_TEST +extern unsigned long copy_mc_test_src; +extern unsigned long copy_mc_test_dst; + +static inline void copy_mc_inject_src(void *addr) +{ + if (addr) + copy_mc_test_src = (unsigned long) addr; + else + copy_mc_test_src = ~0UL; +} + +static inline void copy_mc_inject_dst(void *addr) +{ + if (addr) + copy_mc_test_dst = (unsigned long) addr; + else + copy_mc_test_dst = ~0UL; +} +#else /* CONFIG_COPY_MC_TEST */ +static inline void copy_mc_inject_src(void *addr) +{ +} + +static inline void copy_mc_inject_dst(void *addr) +{ +} +#endif /* CONFIG_COPY_MC_TEST */ + +#else /* __ASSEMBLY__ */ +#include <asm/export.h> + +#ifdef CONFIG_COPY_MC_TEST +.macro COPY_MC_TEST_CTL + .pushsection .data + .align 8 + .globl copy_mc_test_src + copy_mc_test_src: + .quad 0 + EXPORT_SYMBOL_GPL(copy_mc_test_src) + .globl copy_mc_test_dst + copy_mc_test_dst: + .quad 0 + EXPORT_SYMBOL_GPL(copy_mc_test_dst) + .popsection +.endm + +.macro COPY_MC_TEST_SRC reg count target + leaq \count(\reg), %r9 + cmp copy_mc_test_src, %r9 + ja \target +.endm + +.macro COPY_MC_TEST_DST reg count target + leaq \count(\reg), %r9 + cmp copy_mc_test_dst, %r9 + ja \target +.endm +#else +.macro COPY_MC_TEST_CTL +.endm + +.macro COPY_MC_TEST_SRC reg count target +.endm + +.macro COPY_MC_TEST_DST reg count target +.endm +#endif /* CONFIG_COPY_MC_TEST */ +#endif /* __ASSEMBLY__ */ +#endif /* _COPY_MC_TEST_H_ */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cf503824529c..9b9112e4379a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -174,6 +174,15 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb); extern int mce_p5_enabled; +#ifdef CONFIG_ARCH_HAS_COPY_MC +extern void enable_copy_mc_fragile(void); +unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt); +#else +static inline void enable_copy_mc_fragile(void) +{ +} +#endif + #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/mcsafe_test.h b/arch/x86/include/asm/mcsafe_test.h deleted file mode 100644 index eb59804b6201..000000000000 --- a/arch/x86/include/asm/mcsafe_test.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MCSAFE_TEST_H_ -#define _MCSAFE_TEST_H_ - -#ifndef __ASSEMBLY__ -#ifdef CONFIG_MCSAFE_TEST -extern unsigned long mcsafe_test_src; -extern unsigned long mcsafe_test_dst; - -static inline void mcsafe_inject_src(void *addr) -{ - if (addr) - mcsafe_test_src = (unsigned long) addr; - else - mcsafe_test_src = ~0UL; -} - -static inline void mcsafe_inject_dst(void *addr) -{ - if (addr) - mcsafe_test_dst = (unsigned long) addr; - else - mcsafe_test_dst = ~0UL; -} -#else /* CONFIG_MCSAFE_TEST */ -static inline void mcsafe_inject_src(void *addr) -{ -} - -static inline void mcsafe_inject_dst(void *addr) -{ -} -#endif /* CONFIG_MCSAFE_TEST */ - -#else /* __ASSEMBLY__ */ -#include <asm/export.h> - -#ifdef CONFIG_MCSAFE_TEST -.macro MCSAFE_TEST_CTL - .pushsection .data - .align 8 - .globl mcsafe_test_src - mcsafe_test_src: - .quad 0 - EXPORT_SYMBOL_GPL(mcsafe_test_src) - .globl mcsafe_test_dst - mcsafe_test_dst: - .quad 0 - EXPORT_SYMBOL_GPL(mcsafe_test_dst) - .popsection -.endm - -.macro MCSAFE_TEST_SRC reg count target - leaq \count(\reg), %r9 - cmp mcsafe_test_src, %r9 - ja \target -.endm - -.macro MCSAFE_TEST_DST reg count target - leaq \count(\reg), %r9 - cmp mcsafe_test_dst, %r9 - ja \target -.endm -#else -.macro MCSAFE_TEST_CTL -.endm - -.macro MCSAFE_TEST_SRC reg count target -.endm - -.macro MCSAFE_TEST_DST reg count target -.endm -#endif /* CONFIG_MCSAFE_TEST */ -#endif /* __ASSEMBLY__ */ -#endif /* _MCSAFE_TEST_H_ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index eb8e781c4353..b8f7c9659ef6 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -11,45 +11,47 @@ #include <linux/jump_label.h> /* - * Volatile isn't enough to prevent the compiler from reordering the - * read/write functions for the control registers and messing everything up. - * A memory clobber would solve the problem, but would prevent reordering of - * all loads stores around it, which can hurt performance. Solution is to - * use a variable and mimic reads and writes to it to enforce serialization + * The compiler should not reorder volatile asm statements with respect to each + * other: they should execute in program order. However GCC 4.9.x and 5.x have + * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder + * volatile asm. The write functions are not affected since they have memory + * clobbers preventing reordering. To prevent reads from being reordered with + * respect to writes, use a dummy memory operand. */ -extern unsigned long __force_order; + +#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; - asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; - asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { - asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); + asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; - asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { - asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); + asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) @@ -64,10 +66,10 @@ static inline unsigned long native_read_cr4(void) asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) - : "=r" (val), "=m" (__force_order) : "0" (0)); + : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); + asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 75314c3dbe47..6e450827f677 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -82,38 +82,6 @@ int strcmp(const char *cs, const char *ct); #endif -#define __HAVE_ARCH_MEMCPY_MCSAFE 1 -__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src, - size_t cnt); -DECLARE_STATIC_KEY_FALSE(mcsafe_key); - -/** - * memcpy_mcsafe - copy memory with indication if a machine check happened - * - * @dst: destination address - * @src: source address - * @cnt: number of bytes to copy - * - * Low level memory copy function that catches machine checks - * We only call into the "safe" function on systems that can - * actually do machine check recovery. Everyone else can just - * use memcpy(). - * - * Return 0 for success, or number of bytes not copied if there was an - * exception. - */ -static __always_inline __must_check unsigned long -memcpy_mcsafe(void *dst, const void *src, size_t cnt) -{ -#ifdef CONFIG_X86_MCE - if (static_branch_unlikely(&mcsafe_key)) - return __memcpy_mcsafe(dst, src, cnt); - else -#endif - memcpy(dst, src, cnt); - return 0; -} - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 void __memcpy_flushcache(void *dst, const void *src, size_t cnt); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 2f3e8f2a958f..9bfca52b4641 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -455,6 +455,15 @@ extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned len); +#define copy_mc_to_kernel copy_mc_to_kernel + +unsigned long __must_check +copy_mc_to_user(void *to, const void *from, unsigned len); +#endif + /* * movsl can be slow when source and dest are not both 8-byte aligned */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index bc10e3dc64fe..e7265a552f4f 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -47,22 +47,6 @@ copy_user_generic(void *to, const void *from, unsigned len) } static __always_inline __must_check unsigned long -copy_to_user_mcsafe(void *to, const void *from, unsigned len) -{ - unsigned long ret; - - __uaccess_begin(); - /* - * Note, __memcpy_mcsafe() is explicitly used since it can - * handle exceptions / faults. memcpy_mcsafe() may fall back to - * memcpy() which lacks this handling. - */ - ret = __memcpy_mcsafe(to, from, len); - __uaccess_end(); - return ret; -} - -static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); @@ -102,8 +86,4 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } - -unsigned long -mcsafe_handle_tail(char *to, char *from, unsigned len); - #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 95c090a45b4b..d8ef789e00c1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -358,7 +358,7 @@ void native_write_cr0(unsigned long val) unsigned long bits_missing = 0; set_register: - asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order)); + asm volatile("mov %0,%%cr0": "+r" (val) : : "memory"); if (static_branch_likely(&cr_pinning)) { if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) { @@ -377,7 +377,7 @@ void native_write_cr4(unsigned long val) unsigned long bits_changed = 0; set_register: - asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); + asm volatile("mov %0,%%cr4": "+r" (val) : : "memory"); if (static_branch_likely(&cr_pinning)) { if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 14e4b4d17ee5..69b2bb305a5a 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -40,7 +40,6 @@ #include <linux/debugfs.h> #include <linux/irq_work.h> #include <linux/export.h> -#include <linux/jump_label.h> #include <linux/set_memory.h> #include <linux/task_work.h> #include <linux/hardirq.h> @@ -370,42 +369,105 @@ static int msr_to_offset(u32 msr) return -1; } +__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr) +{ + pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, regs->ip, (void *)regs->ip); + + show_stack_regs(regs); + + panic("MCA architectural violation!\n"); + + while (true) + cpu_relax(); + + return true; +} + /* MSR access wrappers used for error injection */ -static u64 mce_rdmsrl(u32 msr) +static noinstr u64 mce_rdmsrl(u32 msr) { - u64 v; + DECLARE_ARGS(val, low, high); if (__this_cpu_read(injectm.finished)) { - int offset = msr_to_offset(msr); + int offset; + u64 ret; + + instrumentation_begin(); + offset = msr_to_offset(msr); if (offset < 0) - return 0; - return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); - } + ret = 0; + else + ret = *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); - if (rdmsrl_safe(msr, &v)) { - WARN_ONCE(1, "mce: Unable to read MSR 0x%x!\n", msr); - /* - * Return zero in case the access faulted. This should - * not happen normally but can happen if the CPU does - * something weird, or if the code is buggy. - */ - v = 0; + instrumentation_end(); + + return ret; } - return v; + /* + * RDMSR on MCA MSRs should not fault. If they do, this is very much an + * architectural violation and needs to be reported to hw vendor. Panic + * the box to not allow any further progress. + */ + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_fault) + : EAX_EDX_RET(val, low, high) : "c" (msr)); + + + return EAX_EDX_VAL(val, low, high); +} + +__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr) +{ + pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, + regs->ip, (void *)regs->ip); + + show_stack_regs(regs); + + panic("MCA architectural violation!\n"); + + while (true) + cpu_relax(); + + return true; } -static void mce_wrmsrl(u32 msr, u64 v) +static noinstr void mce_wrmsrl(u32 msr, u64 v) { + u32 low, high; + if (__this_cpu_read(injectm.finished)) { - int offset = msr_to_offset(msr); + int offset; + instrumentation_begin(); + + offset = msr_to_offset(msr); if (offset >= 0) *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v; + + instrumentation_end(); + return; } - wrmsrl(msr, v); + + low = (u32)v; + high = (u32)(v >> 32); + + /* See comment in mce_rdmsrl() */ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_fault) + : : "c" (msr), "a"(low), "d" (high) : "memory"); } /* @@ -2059,7 +2121,7 @@ void mce_disable_bank(int bank) and older. * mce=nobootlog Don't log MCEs from before booting. * mce=bios_cmci_threshold Don't program the CMCI threshold - * mce=recovery force enable memcpy_mcsafe() + * mce=recovery force enable copy_mc_fragile() */ static int __init mcheck_enable(char *str) { @@ -2667,13 +2729,10 @@ static void __init mcheck_debugfs_init(void) static void __init mcheck_debugfs_init(void) { } #endif -DEFINE_STATIC_KEY_FALSE(mcsafe_key); -EXPORT_SYMBOL_GPL(mcsafe_key); - static int __init mcheck_late_init(void) { if (mca_cfg.recovery) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); mcheck_debugfs_init(); diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 6473070b5da4..b122610e9046 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -185,4 +185,14 @@ extern bool amd_filter_mce(struct mce *m); static inline bool amd_filter_mce(struct mce *m) { return false; }; #endif +__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr); + +__visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr); + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index e1da619add19..567ce09a0286 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -9,9 +9,11 @@ #include <linux/seq_file.h> #include <linux/init.h> #include <linux/debugfs.h> -#include <asm/mce.h> #include <linux/uaccess.h> +#include <asm/mce.h> +#include <asm/intel-family.h> + #include "internal.h" /* @@ -40,9 +42,14 @@ static struct severity { unsigned char context; unsigned char excp; unsigned char covered; + unsigned char cpu_model; + unsigned char cpu_minstepping; + unsigned char bank_lo, bank_hi; char *msg; } severities[] = { #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } +#define BANK_RANGE(l, h) .bank_lo = l, .bank_hi = h +#define MODEL_STEPPING(m, s) .cpu_model = m, .cpu_minstepping = s #define KERNEL .context = IN_KERNEL #define USER .context = IN_USER #define KERNEL_RECOV .context = IN_KERNEL_RECOV @@ -97,7 +104,6 @@ static struct severity { KEEP, "Corrected error", NOSER, BITCLR(MCI_STATUS_UC) ), - /* * known AO MCACODs reported via MCE or CMC: * @@ -113,6 +119,18 @@ static struct severity { AO, "Action optional: last level cache writeback error", SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) ), + /* + * Quirk for Skylake/Cascade Lake. Patrol scrubber may be configured + * to report uncorrected errors using CMCI with a special signature. + * UC=0, MSCOD=0x0010, MCACOD=binary(000X 0000 1100 XXXX) reported + * in one of the memory controller banks. + * Set severity to "AO" for same action as normal patrol scrub error. + */ + MCESEV( + AO, "Uncorrected Patrol Scrub Error", + SER, MASK(MCI_STATUS_UC|MCI_ADDR|0xffffeff0, MCI_ADDR|0x001000c0), + MODEL_STEPPING(INTEL_FAM6_SKYLAKE_X, 4), BANK_RANGE(13, 18) + ), /* ignore OVER for UCNA */ MCESEV( @@ -324,6 +342,12 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e continue; if (s->excp && excp != s->excp) continue; + if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model) + continue; + if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping) + continue; + if (s->bank_lo && (m->bank < s->bank_lo || m->bank > s->bank_hi)) + continue; if (msg) *msg = s->msg; s->covered = 1; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 9b6fafa69be9..d9473d86a075 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -21,6 +21,7 @@ * */ +#include <linux/jiffies.h> #include <linux/dmi.h> #include <linux/init.h> #include <linux/export.h> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 7401cc12c3cc..42679610c9be 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -115,7 +115,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) unsigned long prologue = regs->ip - PROLOGUE_SIZE; if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Bad RIP value.\n", loglvl); + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 61ddc3a5e5c2..f8ff895aaf7e 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -243,9 +243,9 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { - char arg[32]; + char arg[128]; char *argptr = arg; - int bit; + int arglen, res, bit; #ifdef CONFIG_X86_32 if (cmdline_find_option_bool(boot_command_line, "no387")) @@ -268,12 +268,26 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); - if (cmdline_find_option(boot_command_line, "clearcpuid", arg, - sizeof(arg)) && - get_option(&argptr, &bit) && - bit >= 0 && - bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); + if (arglen <= 0) + return; + + pr_info("Clearing CPUID bits:"); + do { + res = get_option(&argptr, &bit); + if (res == 0 || res == 3) + break; + + /* If the argument was too long, the last bit may be cut off */ + if (res == 1 && arglen >= sizeof(arg)) + break; + + if (bit >= 0 && bit < NCAPINTS * 32) { + pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit)); + setup_clear_cpu_cap(bit); + } + } while (res == 2); + pr_cont("\n"); } /* diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index d7c5e44b26f7..091752c3a19e 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -102,7 +102,6 @@ fs_initcall(nmi_warning_debugfs); static void nmi_check_duration(struct nmiaction *action, u64 duration) { - u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; if (duration < nmi_longest_ns || duration < action->max_duration) @@ -110,12 +109,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration) action->max_duration = duration; - remainder_ns = do_div(whole_msecs, (1000 * 1000)); + remainder_ns = do_div(duration, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - action->handler, whole_msecs, decimal_msecs); + action->handler, duration, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 896d74cb5081..e0296983a238 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -8,6 +8,7 @@ #include <asm/hpet.h> #include <asm/setup.h> +#include <asm/mce.h> #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) @@ -624,10 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); -#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) -#include <linux/jump_label.h> -#include <asm/string_64.h> - /* Ivy Bridge, Haswell, Broadwell */ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) { @@ -636,7 +633,7 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) pci_read_config_dword(pdev, 0x84, &capid0); if (capid0 & 0x10) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); } /* Skylake */ @@ -653,7 +650,7 @@ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) * enabled, so memory machine check recovery is also enabled. */ if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0)) - static_branch_inc(&mcsafe_key); + enable_copy_mc_fragile(); } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); @@ -661,7 +658,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif -#endif bool x86_apple_machine; EXPORT_SYMBOL(x86_apple_machine); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 69cc82310974..d43df8de75a6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -196,7 +196,7 @@ static __always_inline void __user *error_get_trap_addr(struct pt_regs *regs) DEFINE_IDTENTRY(exc_divide_error) { - do_error_trap(regs, 0, "divide_error", X86_TRAP_DE, SIGFPE, + do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, FPE_INTDIV, error_get_trap_addr(regs)); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d0e2825ae617..571cb8657e53 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3594,7 +3594,7 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) u64 tsc_aux = 0; if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) - return emulate_gp(ctxt, 0); + return emulate_ud(ctxt); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d057376bd3d3..698969e18fe3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -197,12 +197,9 @@ static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) /* * If no longer has pending EOI in LAPICs, update - * EOI for this vetor. + * EOI for this vector. */ rtc_irq_eoi(ioapic, vcpu, entry->fields.vector); - kvm_ioapic_update_eoi_one(vcpu, ioapic, - entry->fields.trig_mode, - irq); break; } } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index cfe83d4ae625..ca0781b41df9 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) + | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4ce2ddd26c0b..ccb72af1bcb5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -490,6 +490,12 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) } } +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec) +{ + apic_clear_irr(vec, vcpu->arch.apic); +} +EXPORT_SYMBOL_GPL(kvm_apic_clear_irr); + static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { struct kvm_vcpu *vcpu; @@ -2462,6 +2468,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) __apic_update_ppr(apic, &ppr); return apic_has_interrupt_for_ppr(apic, ppr); } +EXPORT_SYMBOL_GPL(kvm_apic_has_interrupt); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 754f29beb83e..4fb86e3a9dd3 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -89,6 +89,7 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1e6724c30cc0..57cd70801216 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6341,6 +6341,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) cond_resched_lock(&kvm->mmu_lock); } } + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index e80daa98682f..b74722e0abb5 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -868,6 +868,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * - Tell IOMMU to use legacy mode for this interrupt. * - Retrieve ga_tag of prior interrupt remapping data. */ + pi.prev_ga_tag = 0; pi.is_guest_mode = false; ret = irq_set_vcpu_affinity(host_irq, &pi); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index a5810928b011..27e41fac9196 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2402,6 +2402,8 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); + + vmx->segment_cache.bitmask = 0; } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -3295,8 +3297,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - if (unlikely(!nested_get_vmcs12_pages(vcpu))) + if (unlikely(!nested_get_vmcs12_pages(vcpu))) { + vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_KVM_INTERNAL_ERROR; + } if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); @@ -3480,6 +3484,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; + /* Emulate processing of posted interrupts on VM-Enter. */ + if (nested_cpu_has_posted_intr(vmcs12) && + kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); + } + /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6110bce7237b..02c3cec7e515 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o +lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c new file mode 100644 index 000000000000..c13e8c9ee926 --- /dev/null +++ b/arch/x86/lib/copy_mc.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ + +#include <linux/jump_label.h> +#include <linux/uaccess.h> +#include <linux/export.h> +#include <linux/string.h> +#include <linux/types.h> + +#include <asm/mce.h> + +#ifdef CONFIG_X86_MCE +/* + * See COPY_MC_TEST for self-test of the copy_mc_fragile() + * implementation. + */ +static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key); + +void enable_copy_mc_fragile(void) +{ + static_branch_inc(©_mc_fragile_key); +} +#define copy_mc_fragile_enabled (static_branch_unlikely(©_mc_fragile_key)) + +/* + * Similar to copy_user_handle_tail, probe for the write fault point, or + * source exception point. + */ +__visible notrace unsigned long +copy_mc_fragile_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) + if (copy_mc_fragile(to, from, 1)) + break; + return len; +} +#else +/* + * No point in doing careful copying, or consulting a static key when + * there is no #MC handler in the CONFIG_X86_MCE=n case. + */ +void enable_copy_mc_fragile(void) +{ +} +#define copy_mc_fragile_enabled (0) +#endif + +unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned len); + +/** + * copy_mc_to_kernel - memory copy that handles source exceptions + * + * @dst: destination address + * @src: source address + * @len: number of bytes to copy + * + * Call into the 'fragile' version on systems that benefit from avoiding + * corner case poison consumption scenarios, For example, accessing + * poison across 2 cachelines with a single instruction. Almost all + * other uses case can use copy_mc_enhanced_fast_string() for a fast + * recoverable copy, or fallback to plain memcpy. + * + * Return 0 for success, or number of bytes not copied if there was an + * exception. + */ +unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) +{ + if (copy_mc_fragile_enabled) + return copy_mc_fragile(dst, src, len); + if (static_cpu_has(X86_FEATURE_ERMS)) + return copy_mc_enhanced_fast_string(dst, src, len); + memcpy(dst, src, len); + return 0; +} +EXPORT_SYMBOL_GPL(copy_mc_to_kernel); + +unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len) +{ + unsigned long ret; + + if (copy_mc_fragile_enabled) { + __uaccess_begin(); + ret = copy_mc_fragile(dst, src, len); + __uaccess_end(); + return ret; + } + + if (static_cpu_has(X86_FEATURE_ERMS)) { + __uaccess_begin(); + ret = copy_mc_enhanced_fast_string(dst, src, len); + __uaccess_end(); + return ret; + } + + return copy_user_generic(dst, src, len); +} diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S new file mode 100644 index 000000000000..892d8915f609 --- /dev/null +++ b/arch/x86/lib/copy_mc_64.S @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ + +#include <linux/linkage.h> +#include <asm/copy_mc_test.h> +#include <asm/export.h> +#include <asm/asm.h> + +#ifndef CONFIG_UML + +#ifdef CONFIG_X86_MCE +COPY_MC_TEST_CTL + +/* + * copy_mc_fragile - copy memory with indication if an exception / fault happened + * + * The 'fragile' version is opted into by platform quirks and takes + * pains to avoid unrecoverable corner cases like 'fast-string' + * instruction sequences, and consuming poison across a cacheline + * boundary. The non-fragile version is equivalent to memcpy() + * regardless of CPU machine-check-recovery capability. + */ +SYM_FUNC_START(copy_mc_fragile) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_read_leading_bytes: + movb (%rsi), %al + COPY_MC_TEST_SRC %rsi 1 .E_leading_bytes + COPY_MC_TEST_DST %rdi 1 .E_leading_bytes +.L_write_leading_bytes: + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_read_leading_bytes + +.L_8byte_aligned: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + +.L_read_words: + movq (%rsi), %r8 + COPY_MC_TEST_SRC %rsi 8 .E_read_words + COPY_MC_TEST_DST %rdi 8 .E_write_words +.L_write_words: + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi + decl %ecx + jnz .L_read_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_read_trailing_bytes: + movb (%rsi), %al + COPY_MC_TEST_SRC %rsi 1 .E_trailing_bytes + COPY_MC_TEST_DST %rdi 1 .E_trailing_bytes +.L_write_trailing_bytes: + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_read_trailing_bytes + + /* Copy successful. Return zero */ +.L_done_memcpy_trap: + xorl %eax, %eax +.L_done: + ret +SYM_FUNC_END(copy_mc_fragile) +EXPORT_SYMBOL_GPL(copy_mc_fragile) + + .section .fixup, "ax" + /* + * Return number of bytes not copied for any failure. Note that + * there is no "tail" handling since the source buffer is 8-byte + * aligned and poison is cacheline aligned. + */ +.E_read_words: + shll $3, %ecx +.E_leading_bytes: + addl %edx, %ecx +.E_trailing_bytes: + mov %ecx, %eax + jmp .L_done + + /* + * For write fault handling, given the destination is unaligned, + * we handle faults on multi-byte writes with a byte-by-byte + * copy up to the write-protected page. + */ +.E_write_words: + shll $3, %ecx + addl %edx, %ecx + movl %ecx, %edx + jmp copy_mc_fragile_handle_tail + + .previous + + _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) + _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE(.L_write_words, .E_write_words) + _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) +#endif /* CONFIG_X86_MCE */ + +/* + * copy_mc_enhanced_fast_string - memory copy with exception handling + * + * Fast string copy + fault / exception handling. If the CPU does + * support machine check exception recovery, but does not support + * recovering from fast-string exceptions then this CPU needs to be + * added to the copy_mc_fragile_key set of quirks. Otherwise, absent any + * machine check recovery support this version should be no slower than + * standard memcpy. + */ +SYM_FUNC_START(copy_mc_enhanced_fast_string) + movq %rdi, %rax + movq %rdx, %rcx +.L_copy: + rep movsb + /* Copy successful. Return zero */ + xorl %eax, %eax + ret +SYM_FUNC_END(copy_mc_enhanced_fast_string) + + .section .fixup, "ax" +.E_copy: + /* + * On fault %rcx is updated such that the copy instruction could + * optionally be restarted at the fault position, i.e. it + * contains 'bytes remaining'. A non-zero return indicates error + * to copy_mc_generic() users, or indicate short transfers to + * user-copy routines. + */ + movq %rcx, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy, .E_copy) +#endif /* !CONFIG_UML */ diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index bbcc05bcefad..037faac46b0c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -4,7 +4,6 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -187,117 +186,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig) SYM_FUNC_END(memcpy_orig) .popsection - -#ifndef CONFIG_UML - -MCSAFE_TEST_CTL - -/* - * __memcpy_mcsafe - memory copy with machine check exception handling - * Note that we only catch machine checks when reading the source addresses. - * Writes to target are posted and don't generate machine checks. - */ -SYM_FUNC_START(__memcpy_mcsafe) - cmpl $8, %edx - /* Less than 8 bytes? Go to byte copy loop */ - jb .L_no_whole_words - - /* Check for bad alignment of source */ - testl $7, %esi - /* Already aligned */ - jz .L_8byte_aligned - - /* Copy one byte at a time until source is 8-byte aligned */ - movl %esi, %ecx - andl $7, %ecx - subl $8, %ecx - negl %ecx - subl %ecx, %edx -.L_read_leading_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes - MCSAFE_TEST_DST %rdi 1 .E_leading_bytes -.L_write_leading_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_leading_bytes - -.L_8byte_aligned: - movl %edx, %ecx - andl $7, %edx - shrl $3, %ecx - jz .L_no_whole_words - -.L_read_words: - movq (%rsi), %r8 - MCSAFE_TEST_SRC %rsi 8 .E_read_words - MCSAFE_TEST_DST %rdi 8 .E_write_words -.L_write_words: - movq %r8, (%rdi) - addq $8, %rsi - addq $8, %rdi - decl %ecx - jnz .L_read_words - - /* Any trailing bytes? */ -.L_no_whole_words: - andl %edx, %edx - jz .L_done_memcpy_trap - - /* Copy trailing bytes */ - movl %edx, %ecx -.L_read_trailing_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes - MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes -.L_write_trailing_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_trailing_bytes - - /* Copy successful. Return zero */ -.L_done_memcpy_trap: - xorl %eax, %eax -.L_done: - ret -SYM_FUNC_END(__memcpy_mcsafe) -EXPORT_SYMBOL_GPL(__memcpy_mcsafe) - - .section .fixup, "ax" - /* - * Return number of bytes not copied for any failure. Note that - * there is no "tail" handling since the source buffer is 8-byte - * aligned and poison is cacheline aligned. - */ -.E_read_words: - shll $3, %ecx -.E_leading_bytes: - addl %edx, %ecx -.E_trailing_bytes: - mov %ecx, %eax - jmp .L_done - - /* - * For write fault handling, given the destination is unaligned, - * we handle faults on multi-byte writes with a byte-by-byte - * copy up to the write-protected page. - */ -.E_write_words: - shll $3, %ecx - addl %edx, %ecx - movl %ecx, %edx - jmp mcsafe_handle_tail - - .previous - - _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) - _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) - _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE(.L_write_words, .E_write_words) - _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) -#endif diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 1847e993ac63..508c81e97ab1 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -56,27 +56,6 @@ unsigned long clear_user(void __user *to, unsigned long n) } EXPORT_SYMBOL(clear_user); -/* - * Similar to copy_user_handle_tail, probe for the write fault point, - * but reuse __memcpy_mcsafe in case a new read error is encountered. - * clac() is handled in _copy_to_iter_mcsafe(). - */ -__visible notrace unsigned long -mcsafe_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++, from++) { - /* - * Call the assembly routine back directly since - * memcpy_mcsafe() may silently fallback to memcpy. - */ - unsigned long rem = __memcpy_mcsafe(to, from, 1); - - if (rem) - break; - } - return len; -} - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 00c62115f39c..0aaf31917061 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -33,6 +33,7 @@ #include <asm/hw_irq.h> #include <asm/io_apic.h> #include <asm/intel-mid.h> +#include <asm/acpi.h> #define PCIE_CAP_OFFSET 0x100 diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..1c2832e9f77d 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -1,4 +1,4 @@ -#!/bin/awk -f +#!/usr/bin/awk -f # SPDX-License-Identifier: GPL-2.0 # gen-insn-attr-x86.awk: Instruction attribute table generator # Written by Masami Hiramatsu <mhiramat@redhat.com> diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c46b9f2e732f..6e39eda00c2c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1438,6 +1438,15 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; xen_boot_params_init_edd(); + +#ifdef CONFIG_ACPI + /* + * Disable selecting "Firmware First mode" for correctable + * memory errors, as this is the duty of the hypervisor to + * decide. + */ + acpi_disable_cmcff = 1; +#endif } if (!boot_params.screen_info.orig_video_isVGA) diff --git a/block/blk-core.c b/block/blk-core.c index 619a3dcd3f5e..8d6435b73118 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -798,11 +798,10 @@ static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; - printk(KERN_INFO "attempt to access beyond end of device\n"); - printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n", - bio_devname(bio, b), bio->bi_opf, - (unsigned long long)bio_end_sector(bio), - (long long)maxsector); + pr_info_ratelimited("attempt to access beyond end of device\n" + "%s: rw=%d, want=%llu, limit=%llu\n", + bio_devname(bio, b), bio->bi_opf, + bio_end_sector(bio), maxsector); } #ifdef CONFIG_FAIL_MAKE_REQUEST diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 062229395a50..7b52e7657b2d 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -36,8 +36,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj) struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); - cancel_delayed_work_sync(&hctx->run_work); - if (hctx->flags & BLK_MQ_F_BLOCKING) cleanup_srcu_struct(hctx->srcu); blk_free_flush_queue(hctx->fq); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 02643e149d5e..95fea6c18baf 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -896,9 +896,16 @@ static void __blk_release_queue(struct work_struct *work) blk_free_queue_stats(q->stats); - if (queue_is_mq(q)) + if (queue_is_mq(q)) { + struct blk_mq_hw_ctx *hctx; + int i; + cancel_delayed_work_sync(&q->requeue_work); + queue_for_each_hw_ctx(q, hctx, i) + cancel_delayed_work_sync(&hctx->run_work); + } + blk_exit_queue(q); blk_queue_free_zone_bitmaps(q); diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 43c6aa784858..e62d735ed266 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -78,7 +78,7 @@ static int crypto_aead_copy_sgl(struct crypto_sync_skcipher *null_tfm, SYNC_SKCIPHER_REQUEST_ON_STACK(skreq, null_tfm); skcipher_request_set_sync_tfm(skreq, null_tfm); - skcipher_request_set_callback(skreq, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_request_set_callback(skreq, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); skcipher_request_set_crypt(skreq, src, dst, len, NULL); @@ -291,19 +291,20 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, areq->outlen = outlen; aead_request_set_callback(&areq->cra_u.aead_req, - CRYPTO_TFM_REQ_MAY_BACKLOG, + CRYPTO_TFM_REQ_MAY_SLEEP, af_alg_async_cb, areq); err = ctx->enc ? crypto_aead_encrypt(&areq->cra_u.aead_req) : crypto_aead_decrypt(&areq->cra_u.aead_req); /* AIO operation in progress */ - if (err == -EINPROGRESS || err == -EBUSY) + if (err == -EINPROGRESS) return -EIOCBQUEUED; sock_put(sk); } else { /* Synchronous operation */ aead_request_set_callback(&areq->cra_u.aead_req, + CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &ctx->wait); err = crypto_wait_req(ctx->enc ? diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 81c4022285a7..30069a92a9b2 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -123,7 +123,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, crypto_skcipher_decrypt(&areq->cra_u.skcipher_req); /* AIO operation in progress */ - if (err == -EINPROGRESS || err == -EBUSY) + if (err == -EINPROGRESS) return -EIOCBQUEUED; sock_put(sk); diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 5b310eea9e52..adab46ca5dff 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -223,7 +223,7 @@ static struct binder_transaction_log_entry *binder_transaction_log_add( struct binder_work { struct list_head entry; - enum { + enum binder_work_type { BINDER_WORK_TRANSACTION = 1, BINDER_WORK_TRANSACTION_COMPLETE, BINDER_WORK_RETURN_ERROR, @@ -885,27 +885,6 @@ static struct binder_work *binder_dequeue_work_head_ilocked( return w; } -/** - * binder_dequeue_work_head() - Dequeues the item at head of list - * @proc: binder_proc associated with list - * @list: list to dequeue head - * - * Removes the head of the list if there are items on the list - * - * Return: pointer dequeued binder_work, NULL if list was empty - */ -static struct binder_work *binder_dequeue_work_head( - struct binder_proc *proc, - struct list_head *list) -{ - struct binder_work *w; - - binder_inner_proc_lock(proc); - w = binder_dequeue_work_head_ilocked(list); - binder_inner_proc_unlock(proc); - return w; -} - static void binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer); static void binder_free_thread(struct binder_thread *thread); @@ -2345,8 +2324,6 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, * file is done when the transaction is torn * down. */ - WARN_ON(failed_at && - proc->tsk == current->group_leader); } break; case BINDER_TYPE_PTR: /* @@ -4589,13 +4566,17 @@ static void binder_release_work(struct binder_proc *proc, struct list_head *list) { struct binder_work *w; + enum binder_work_type wtype; while (1) { - w = binder_dequeue_work_head(proc, list); + binder_inner_proc_lock(proc); + w = binder_dequeue_work_head_ilocked(list); + wtype = w ? w->type : 0; + binder_inner_proc_unlock(proc); if (!w) return; - switch (w->type) { + switch (wtype) { case BINDER_WORK_TRANSACTION: { struct binder_transaction *t; @@ -4629,9 +4610,11 @@ static void binder_release_work(struct binder_proc *proc, kfree(death); binder_stats_deleted(BINDER_STAT_DEATH); } break; + case BINDER_WORK_NODE: + break; default: pr_err("unexpected work type, %d, not freed\n", - w->type); + wtype); break; } } diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index d991dd46e89c..98b8baa47dc5 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -240,6 +240,8 @@ enum { as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ + AHCI_HFLAG_IGN_NOTSUPP_POWER_ON = (1 << 27), /* ignore -EOPNOTSUPP + from phy_power_on() */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index d4bba3ace45d..3ad46d26d9d5 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -227,7 +227,7 @@ static const struct ahci_mvebu_plat_data ahci_mvebu_armada_380_plat_data = { static const struct ahci_mvebu_plat_data ahci_mvebu_armada_3700_plat_data = { .plat_config = ahci_mvebu_armada_3700_config, - .flags = AHCI_HFLAG_SUSPEND_PHYS, + .flags = AHCI_HFLAG_SUSPEND_PHYS | AHCI_HFLAG_IGN_NOTSUPP_POWER_ON, }; static const struct of_device_id ahci_mvebu_of_match[] = { diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 129556fcf6be..a1cbb894e5f0 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -59,7 +59,7 @@ int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) } rc = phy_power_on(hpriv->phys[i]); - if (rc) { + if (rc && !(rc == -EOPNOTSUPP && (hpriv->flags & AHCI_HFLAG_IGN_NOTSUPP_POWER_ON))) { phy_exit(hpriv->phys[i]); goto disable_phys; } diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 141ac600b64c..44b0ed8f6bb8 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -120,7 +120,7 @@ /* Descriptor table word 0 bit (when DTA32M = 1) */ #define SATA_RCAR_DTEND BIT(0) -#define SATA_RCAR_DMA_BOUNDARY 0x1FFFFFFEUL +#define SATA_RCAR_DMA_BOUNDARY 0x1FFFFFFFUL /* Gen2 Physical Layer Control Registers */ #define RCAR_GEN2_PHY_CTL1_REG 0x1704 diff --git a/drivers/base/firmware_loader/fallback_platform.c b/drivers/base/firmware_loader/fallback_platform.c index 685edb7dd05a..6958ab1a8059 100644 --- a/drivers/base/firmware_loader/fallback_platform.c +++ b/drivers/base/firmware_loader/fallback_platform.c @@ -17,7 +17,7 @@ int firmware_fallback_platform(struct fw_priv *fw_priv, u32 opt_flags) if (!(opt_flags & FW_OPT_FALLBACK_PLATFORM)) return -ENOENT; - rc = security_kernel_load_data(LOADING_FIRMWARE_EFI_EMBEDDED); + rc = security_kernel_load_data(LOADING_FIRMWARE); if (rc) return rc; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index dfc66038bef9..6fa16886aeda 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -763,6 +763,24 @@ out_err: return error; } +/* + * for AUFS + * no get/put for file. + */ +struct file *loop_backing_file(struct super_block *sb) +{ + struct file *ret; + struct loop_device *l; + + ret = NULL; + if (MAJOR(sb->s_dev) == LOOP_MAJOR) { + l = sb->s_bdev->bd_disk->private_data; + ret = l->lo_backing_file; + } + return ret; +} +EXPORT_SYMBOL_GPL(loop_backing_file); + /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a5fef9aa419f..91a0c84d55c9 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2849,6 +2849,7 @@ static int btusb_mtk_submit_wmt_recv_urb(struct hci_dev *hdev) buf = kmalloc(size, GFP_KERNEL); if (!buf) { kfree(dr); + usb_free_urb(urb); return -ENOMEM; } diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 85a30fb9177b..f83d67eafc9f 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -538,6 +538,7 @@ static void hci_uart_tty_close(struct tty_struct *tty) clear_bit(HCI_UART_PROTO_READY, &hu->flags); percpu_up_write(&hu->proto_lock); + cancel_work_sync(&hu->init_ready); cancel_work_sync(&hu->write_work); if (hdev) { diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 7b233312e723..3977bba485c2 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -355,6 +355,8 @@ void hci_uart_unregister_device(struct hci_uart *hu) struct hci_dev *hdev = hu->hdev; clear_bit(HCI_UART_PROTO_READY, &hu->flags); + + cancel_work_sync(&hu->init_ready); if (test_bit(HCI_UART_REGISTERED, &hu->flags)) hci_unregister_dev(hdev); hci_free_dev(hdev); diff --git a/drivers/bus/mhi/core/Makefile b/drivers/bus/mhi/core/Makefile index 66e2700c9032..bc1469778cf8 100644 --- a/drivers/bus/mhi/core/Makefile +++ b/drivers/bus/mhi/core/Makefile @@ -1,3 +1,3 @@ -obj-$(CONFIG_MHI_BUS) := mhi.o +obj-$(CONFIG_MHI_BUS) += mhi.o mhi-y := init.o main.o pm.o boot.o diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 77b8d551ae7f..dd559661c15b 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1963,7 +1963,7 @@ static int try_smi_init(struct smi_info *new_smi) /* Do this early so it's available for logs. */ if (!new_smi->io.dev) { pr_err("IPMI interface added with no device\n"); - rv = EIO; + rv = -EIO; goto out_err; } diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c index 37c22667e831..4313ecb2af5b 100644 --- a/drivers/clk/at91/clk-main.c +++ b/drivers/clk/at91/clk-main.c @@ -437,12 +437,17 @@ static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index) return -EINVAL; regmap_read(regmap, AT91_CKGR_MOR, &tmp); - tmp &= ~MOR_KEY_MASK; if (index && !(tmp & AT91_PMC_MOSCSEL)) - regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL); + tmp = AT91_PMC_MOSCSEL; else if (!index && (tmp & AT91_PMC_MOSCSEL)) - regmap_write(regmap, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL); + tmp = 0; + else + return 0; + + regmap_update_bits(regmap, AT91_CKGR_MOR, + AT91_PMC_MOSCSEL | MOR_KEY_MASK, + tmp | AT91_PMC_KEY); while (!clk_sam9x5_main_ready(regmap)) cpu_relax(); diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 011802f1a6df..f18b4d9e9455 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -1337,8 +1337,10 @@ static struct clk_hw *bcm2835_register_pll(struct bcm2835_cprman *cprman, pll->hw.init = &init; ret = devm_clk_hw_register(cprman->dev, &pll->hw); - if (ret) + if (ret) { + kfree(pll); return NULL; + } return &pll->hw; } diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index a64aace213c2..7762c5825e77 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -157,10 +157,10 @@ static const char * const imx8mq_qspi_sels[] = {"osc_25m", "sys1_pll_400m", "sys "audio_pll2_out", "sys1_pll_266m", "sys3_pll_out", "sys1_pll_100m", }; static const char * const imx8mq_usdhc1_sels[] = {"osc_25m", "sys1_pll_400m", "sys1_pll_800m", "sys2_pll_500m", - "audio_pll2_out", "sys1_pll_266m", "sys3_pll_out", "sys1_pll_100m", }; + "sys3_pll_out", "sys1_pll_266m", "audio_pll2_out", "sys1_pll_100m", }; static const char * const imx8mq_usdhc2_sels[] = {"osc_25m", "sys1_pll_400m", "sys1_pll_800m", "sys2_pll_500m", - "audio_pll2_out", "sys1_pll_266m", "sys3_pll_out", "sys1_pll_100m", }; + "sys3_pll_out", "sys1_pll_266m", "audio_pll2_out", "sys1_pll_100m", }; static const char * const imx8mq_i2c1_sels[] = {"osc_25m", "sys1_pll_160m", "sys2_pll_50m", "sys3_pll_out", "audio_pll1_out", "video_pll1_out", "audio_pll2_out", "sys1_pll_133m", }; diff --git a/drivers/clk/keystone/sci-clk.c b/drivers/clk/keystone/sci-clk.c index 7edf8c8432b6..64ea895f1a7d 100644 --- a/drivers/clk/keystone/sci-clk.c +++ b/drivers/clk/keystone/sci-clk.c @@ -522,7 +522,7 @@ static int ti_sci_scan_clocks_from_dt(struct sci_clk_provider *provider) np = of_find_node_with_property(np, *clk_name); if (!np) { clk_name++; - break; + continue; } if (!of_device_is_available(np)) diff --git a/drivers/clk/mediatek/clk-mt6779.c b/drivers/clk/mediatek/clk-mt6779.c index 9766cccf5844..6e0d3a166729 100644 --- a/drivers/clk/mediatek/clk-mt6779.c +++ b/drivers/clk/mediatek/clk-mt6779.c @@ -919,6 +919,8 @@ static const struct mtk_gate infra_clks[] = { "pwm_sel", 19), GATE_INFRA0(CLK_INFRA_PWM, "infra_pwm", "pwm_sel", 21), + GATE_INFRA0(CLK_INFRA_UART0, "infra_uart0", + "uart_sel", 22), GATE_INFRA0(CLK_INFRA_UART1, "infra_uart1", "uart_sel", 23), GATE_INFRA0(CLK_INFRA_UART2, "infra_uart2", diff --git a/drivers/clk/meson/axg-audio.c b/drivers/clk/meson/axg-audio.c index 53715e36326c..9918cb375de3 100644 --- a/drivers/clk/meson/axg-audio.c +++ b/drivers/clk/meson/axg-audio.c @@ -1209,12 +1209,7 @@ static struct clk_hw_onecell_data sm1_audio_hw_onecell_data = { }; -/* Convenience table to populate regmap in .probe() - * Note that this table is shared between both AXG and G12A, - * with spdifout_b clocks being exclusive to G12A. Since those - * clocks are not declared within the AXG onecell table, we do not - * feel the need to have separate AXG/G12A regmap tables. - */ +/* Convenience table to populate regmap in .probe(). */ static struct clk_regmap *const axg_clk_regmaps[] = { &ddr_arb, &pdm, @@ -1236,6 +1231,130 @@ static struct clk_regmap *const axg_clk_regmaps[] = { &spdifout, &resample, &power_detect, + &mst_a_mclk_sel, + &mst_b_mclk_sel, + &mst_c_mclk_sel, + &mst_d_mclk_sel, + &mst_e_mclk_sel, + &mst_f_mclk_sel, + &mst_a_mclk_div, + &mst_b_mclk_div, + &mst_c_mclk_div, + &mst_d_mclk_div, + &mst_e_mclk_div, + &mst_f_mclk_div, + &mst_a_mclk, + &mst_b_mclk, + &mst_c_mclk, + &mst_d_mclk, + &mst_e_mclk, + &mst_f_mclk, + &spdifout_clk_sel, + &spdifout_clk_div, + &spdifout_clk, + &spdifin_clk_sel, + &spdifin_clk_div, + &spdifin_clk, + &pdm_dclk_sel, + &pdm_dclk_div, + &pdm_dclk, + &pdm_sysclk_sel, + &pdm_sysclk_div, + &pdm_sysclk, + &mst_a_sclk_pre_en, + &mst_b_sclk_pre_en, + &mst_c_sclk_pre_en, + &mst_d_sclk_pre_en, + &mst_e_sclk_pre_en, + &mst_f_sclk_pre_en, + &mst_a_sclk_div, + &mst_b_sclk_div, + &mst_c_sclk_div, + &mst_d_sclk_div, + &mst_e_sclk_div, + &mst_f_sclk_div, + &mst_a_sclk_post_en, + &mst_b_sclk_post_en, + &mst_c_sclk_post_en, + &mst_d_sclk_post_en, + &mst_e_sclk_post_en, + &mst_f_sclk_post_en, + &mst_a_sclk, + &mst_b_sclk, + &mst_c_sclk, + &mst_d_sclk, + &mst_e_sclk, + &mst_f_sclk, + &mst_a_lrclk_div, + &mst_b_lrclk_div, + &mst_c_lrclk_div, + &mst_d_lrclk_div, + &mst_e_lrclk_div, + &mst_f_lrclk_div, + &mst_a_lrclk, + &mst_b_lrclk, + &mst_c_lrclk, + &mst_d_lrclk, + &mst_e_lrclk, + &mst_f_lrclk, + &tdmin_a_sclk_sel, + &tdmin_b_sclk_sel, + &tdmin_c_sclk_sel, + &tdmin_lb_sclk_sel, + &tdmout_a_sclk_sel, + &tdmout_b_sclk_sel, + &tdmout_c_sclk_sel, + &tdmin_a_sclk_pre_en, + &tdmin_b_sclk_pre_en, + &tdmin_c_sclk_pre_en, + &tdmin_lb_sclk_pre_en, + &tdmout_a_sclk_pre_en, + &tdmout_b_sclk_pre_en, + &tdmout_c_sclk_pre_en, + &tdmin_a_sclk_post_en, + &tdmin_b_sclk_post_en, + &tdmin_c_sclk_post_en, + &tdmin_lb_sclk_post_en, + &tdmout_a_sclk_post_en, + &tdmout_b_sclk_post_en, + &tdmout_c_sclk_post_en, + &tdmin_a_sclk, + &tdmin_b_sclk, + &tdmin_c_sclk, + &tdmin_lb_sclk, + &tdmout_a_sclk, + &tdmout_b_sclk, + &tdmout_c_sclk, + &tdmin_a_lrclk, + &tdmin_b_lrclk, + &tdmin_c_lrclk, + &tdmin_lb_lrclk, + &tdmout_a_lrclk, + &tdmout_b_lrclk, + &tdmout_c_lrclk, +}; + +static struct clk_regmap *const g12a_clk_regmaps[] = { + &ddr_arb, + &pdm, + &tdmin_a, + &tdmin_b, + &tdmin_c, + &tdmin_lb, + &tdmout_a, + &tdmout_b, + &tdmout_c, + &frddr_a, + &frddr_b, + &frddr_c, + &toddr_a, + &toddr_b, + &toddr_c, + &loopback, + &spdifin, + &spdifout, + &resample, + &power_detect, &spdifout_b, &mst_a_mclk_sel, &mst_b_mclk_sel, @@ -1713,8 +1832,8 @@ static const struct audioclk_data axg_audioclk_data = { }; static const struct audioclk_data g12a_audioclk_data = { - .regmap_clks = axg_clk_regmaps, - .regmap_clk_num = ARRAY_SIZE(axg_clk_regmaps), + .regmap_clks = g12a_clk_regmaps, + .regmap_clk_num = ARRAY_SIZE(g12a_clk_regmaps), .hw_onecell_data = &g12a_audio_hw_onecell_data, .reset_offset = AUDIO_SW_RESET, .reset_num = 26, diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index 30c15766ebb1..05d032be15c8 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -298,6 +298,17 @@ static struct clk_regmap g12a_fclk_div2 = { &g12a_fclk_div2_div.hw }, .num_parents = 1, + /* + * Similar to fclk_div3, it seems that this clock is used by + * the resident firmware and is required by the platform to + * operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) Mark the clock used by a firmware resource, if possible + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c index c6fb57cd576f..aa5c0c6ead01 100644 --- a/drivers/clk/qcom/gcc-sdm660.c +++ b/drivers/clk/qcom/gcc-sdm660.c @@ -666,7 +666,7 @@ static struct clk_rcg2 hmss_rbcpr_clk_src = { .cmd_rcgr = 0x48044, .mnd_width = 0, .hid_width = 5, - .parent_map = gcc_parent_map_xo_gpll0_gpll0_early_div, + .parent_map = gcc_parent_map_xo_gpll0, .freq_tbl = ftbl_hmss_rbcpr_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "hmss_rbcpr_clk_src", diff --git a/drivers/clk/rockchip/clk-half-divider.c b/drivers/clk/rockchip/clk-half-divider.c index b333fc28c94b..37c858d689e0 100644 --- a/drivers/clk/rockchip/clk-half-divider.c +++ b/drivers/clk/rockchip/clk-half-divider.c @@ -166,7 +166,7 @@ struct clk *rockchip_clk_register_halfdiv(const char *name, unsigned long flags, spinlock_t *lock) { - struct clk *clk; + struct clk *clk = ERR_PTR(-ENOMEM); struct clk_mux *mux = NULL; struct clk_gate *gate = NULL; struct clk_divider *div = NULL; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 09aa44cb8a91..ba04cb381cd3 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -341,7 +341,7 @@ static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg) return read_hv_clock_tsc(); } -static u64 read_hv_sched_clock_tsc(void) +static u64 notrace read_hv_sched_clock_tsc(void) { return (read_hv_clock_tsc() - hv_sched_clock_offset) * (NSEC_PER_SEC / HV_CLOCK_HZ); @@ -404,7 +404,7 @@ static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg) return read_hv_clock_msr(); } -static u64 read_hv_sched_clock_msr(void) +static u64 notrace read_hv_sched_clock_msr(void) { return (read_hv_clock_msr() - hv_sched_clock_offset) * (NSEC_PER_SEC / HV_CLOCK_HZ); diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index df1c941260d1..b4af4094309b 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -484,6 +484,12 @@ remove_opp: /* late_initcall, to guarantee the driver is loaded after A37xx clock driver */ late_initcall(armada37xx_cpufreq_driver_init); +static const struct of_device_id __maybe_unused armada37xx_cpufreq_of_match[] = { + { .compatible = "marvell,armada-3700-nb-pm" }, + { }, +}; +MODULE_DEVICE_TABLE(of, armada37xx_cpufreq_of_match); + MODULE_AUTHOR("Gregory CLEMENT <gregory.clement@free-electrons.com>"); MODULE_DESCRIPTION("Armada 37xx cpufreq driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 8646eb197cd9..31f5c4ebbac9 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -884,12 +884,15 @@ static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { int cpu; - struct cpufreq_policy cpu_policy; + struct cpufreq_policy *cpu_policy; rebooting = true; for_each_online_cpu(cpu) { - cpufreq_get_policy(&cpu_policy, cpu); - powernv_cpufreq_target_index(&cpu_policy, get_nominal_index()); + cpu_policy = cpufreq_cpu_get(cpu); + if (!cpu_policy) + continue; + powernv_cpufreq_target_index(cpu_policy, get_nominal_index()); + cpufreq_cpu_put(cpu_policy); } return NOTIFY_DONE; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c index b957061424a1..8f3d6d31da52 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c @@ -120,7 +120,10 @@ int sun8i_ce_run_task(struct sun8i_ce_dev *ce, int flow, const char *name) /* Be sure all data is written before enabling the task */ wmb(); - v = 1 | (ce->chanlist[flow].tl->t_common_ctl & 0x7F) << 8; + /* Only H6 needs to write a part of t_common_ctl along with "1", but since it is ignored + * on older SoCs, we have no reason to complicate things. + */ + v = 1 | ((le32_to_cpu(ce->chanlist[flow].tl->t_common_ctl) & 0x7F) << 8); writel(v, ce->base + CE_TLR); mutex_unlock(&ce->mlock); diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig index bc35aa0ec07a..d7f2840cf0a9 100644 --- a/drivers/crypto/caam/Kconfig +++ b/drivers/crypto/caam/Kconfig @@ -114,6 +114,7 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API_QI select CRYPTO_AUTHENC select CRYPTO_SKCIPHER select CRYPTO_DES + select CRYPTO_XTS help Selecting this will use CAAM Queue Interface (QI) for sending & receiving crypto jobs to/from CAAM. This gives better performance diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c index 315d53499ce8..829d41a1e5da 100644 --- a/drivers/crypto/caam/caamalg_qi.c +++ b/drivers/crypto/caam/caamalg_qi.c @@ -18,6 +18,8 @@ #include "qi.h" #include "jr.h" #include "caamalg_desc.h" +#include <crypto/xts.h> +#include <asm/unaligned.h> /* * crypto alg @@ -67,6 +69,12 @@ struct caam_ctx { struct device *qidev; spinlock_t lock; /* Protects multiple init of driver context */ struct caam_drv_ctx *drv_ctx[NUM_OP]; + bool xts_key_fallback; + struct crypto_skcipher *fallback; +}; + +struct caam_skcipher_req_ctx { + struct skcipher_request fallback_req; }; static int aead_set_sh_desc(struct crypto_aead *aead) @@ -726,12 +734,21 @@ static int xts_skcipher_setkey(struct crypto_skcipher *skcipher, const u8 *key, struct caam_ctx *ctx = crypto_skcipher_ctx(skcipher); struct device *jrdev = ctx->jrdev; int ret = 0; + int err; - if (keylen != 2 * AES_MIN_KEY_SIZE && keylen != 2 * AES_MAX_KEY_SIZE) { + err = xts_verify_key(skcipher, key, keylen); + if (err) { dev_dbg(jrdev, "key size mismatch\n"); - return -EINVAL; + return err; } + if (keylen != 2 * AES_KEYSIZE_128 && keylen != 2 * AES_KEYSIZE_256) + ctx->xts_key_fallback = true; + + err = crypto_skcipher_setkey(ctx->fallback, key, keylen); + if (err) + return err; + ctx->cdata.keylen = keylen; ctx->cdata.key_virt = key; ctx->cdata.key_inline = true; @@ -1373,6 +1390,14 @@ static struct skcipher_edesc *skcipher_edesc_alloc(struct skcipher_request *req, return edesc; } +static inline bool xts_skcipher_ivsize(struct skcipher_request *req) +{ + struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); + unsigned int ivsize = crypto_skcipher_ivsize(skcipher); + + return !!get_unaligned((u64 *)(req->iv + (ivsize / 2))); +} + static inline int skcipher_crypt(struct skcipher_request *req, bool encrypt) { struct skcipher_edesc *edesc; @@ -1383,6 +1408,22 @@ static inline int skcipher_crypt(struct skcipher_request *req, bool encrypt) if (!req->cryptlen) return 0; + if (ctx->fallback && (xts_skcipher_ivsize(req) || + ctx->xts_key_fallback)) { + struct caam_skcipher_req_ctx *rctx = skcipher_request_ctx(req); + + skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); + skcipher_request_set_callback(&rctx->fallback_req, + req->base.flags, + req->base.complete, + req->base.data); + skcipher_request_set_crypt(&rctx->fallback_req, req->src, + req->dst, req->cryptlen, req->iv); + + return encrypt ? crypto_skcipher_encrypt(&rctx->fallback_req) : + crypto_skcipher_decrypt(&rctx->fallback_req); + } + if (unlikely(caam_congested)) return -EAGAIN; @@ -1507,6 +1548,7 @@ static struct caam_skcipher_alg driver_algs[] = { .base = { .cra_name = "xts(aes)", .cra_driver_name = "xts-aes-caam-qi", + .cra_flags = CRYPTO_ALG_NEED_FALLBACK, .cra_blocksize = AES_BLOCK_SIZE, }, .setkey = xts_skcipher_setkey, @@ -2440,9 +2482,32 @@ static int caam_cra_init(struct crypto_skcipher *tfm) struct skcipher_alg *alg = crypto_skcipher_alg(tfm); struct caam_skcipher_alg *caam_alg = container_of(alg, typeof(*caam_alg), skcipher); + struct caam_ctx *ctx = crypto_skcipher_ctx(tfm); + u32 alg_aai = caam_alg->caam.class1_alg_type & OP_ALG_AAI_MASK; + int ret = 0; + + if (alg_aai == OP_ALG_AAI_XTS) { + const char *tfm_name = crypto_tfm_alg_name(&tfm->base); + struct crypto_skcipher *fallback; + + fallback = crypto_alloc_skcipher(tfm_name, 0, + CRYPTO_ALG_NEED_FALLBACK); + if (IS_ERR(fallback)) { + dev_err(ctx->jrdev, "Failed to allocate %s fallback: %ld\n", + tfm_name, PTR_ERR(fallback)); + return PTR_ERR(fallback); + } + + ctx->fallback = fallback; + crypto_skcipher_set_reqsize(tfm, sizeof(struct caam_skcipher_req_ctx) + + crypto_skcipher_reqsize(fallback)); + } + + ret = caam_init_common(ctx, &caam_alg->caam, false); + if (ret && ctx->fallback) + crypto_free_skcipher(ctx->fallback); - return caam_init_common(crypto_skcipher_ctx(tfm), &caam_alg->caam, - false); + return ret; } static int caam_aead_init(struct crypto_aead *tfm) @@ -2468,7 +2533,11 @@ static void caam_exit_common(struct caam_ctx *ctx) static void caam_cra_exit(struct crypto_skcipher *tfm) { - caam_exit_common(crypto_skcipher_ctx(tfm)); + struct caam_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (ctx->fallback) + crypto_free_skcipher(ctx->fallback); + caam_exit_common(ctx); } static void caam_aead_exit(struct crypto_aead *tfm) @@ -2502,7 +2571,7 @@ static void caam_skcipher_alg_init(struct caam_skcipher_alg *t_alg) alg->base.cra_module = THIS_MODULE; alg->base.cra_priority = CAAM_CRA_PRIORITY; alg->base.cra_ctxsize = sizeof(struct caam_ctx); - alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY; + alg->base.cra_flags |= CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY; alg->init = caam_cra_init; alg->exit = caam_cra_exit; diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index 64112c736810..7234b95241e9 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -1746,7 +1746,7 @@ ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) break; default: ret = -EINVAL; - goto e_ctx; + goto e_data; } } else { /* Stash the context */ diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c index d39e1664fc7e..3c65bf070c90 100644 --- a/drivers/crypto/ccree/cc_pm.c +++ b/drivers/crypto/ccree/cc_pm.c @@ -65,8 +65,12 @@ const struct dev_pm_ops ccree_pm = { int cc_pm_get(struct device *dev) { int rc = pm_runtime_get_sync(dev); + if (rc < 0) { + pm_runtime_put_noidle(dev); + return rc; + } - return (rc == 1 ? 0 : rc); + return 0; } void cc_pm_put_suspend(struct device *dev) diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index 54093115eb95..62fbc7df022b 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -92,11 +92,13 @@ static void chtls_sock_release(struct kref *ref) static struct net_device *chtls_find_netdev(struct chtls_dev *cdev, struct sock *sk) { + struct adapter *adap = pci_get_drvdata(cdev->pdev); struct net_device *ndev = cdev->ports[0]; #if IS_ENABLED(CONFIG_IPV6) struct net_device *temp; int addr_type; #endif + int i; switch (sk->sk_family) { case PF_INET: @@ -127,8 +129,12 @@ static struct net_device *chtls_find_netdev(struct chtls_dev *cdev, return NULL; if (is_vlan_dev(ndev)) - return vlan_dev_real_dev(ndev); - return ndev; + ndev = vlan_dev_real_dev(ndev); + + for_each_port(adap, i) + if (cdev->ports[i] == ndev) + return ndev; + return NULL; } static void assign_rxopt(struct sock *sk, unsigned int opt) @@ -477,7 +483,6 @@ void chtls_destroy_sock(struct sock *sk) chtls_purge_write_queue(sk); free_tls_keyid(sk); kref_put(&csk->kref, chtls_sock_release); - csk->cdev = NULL; if (sk->sk_family == AF_INET) sk->sk_prot = &tcp_prot; #if IS_ENABLED(CONFIG_IPV6) @@ -736,14 +741,13 @@ void chtls_listen_stop(struct chtls_dev *cdev, struct sock *sk) #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { - struct chtls_sock *csk; + struct net_device *ndev = chtls_find_netdev(cdev, sk); int addr_type = 0; - csk = rcu_dereference_sk_user_data(sk); addr_type = ipv6_addr_type((const struct in6_addr *) &sk->sk_v6_rcv_saddr); if (addr_type != IPV6_ADDR_ANY) - cxgb4_clip_release(csk->egress_dev, (const u32 *) + cxgb4_clip_release(ndev, (const u32 *) &sk->sk_v6_rcv_saddr, 1); } #endif @@ -768,14 +772,13 @@ static int chtls_pass_open_rpl(struct chtls_dev *cdev, struct sk_buff *skb) if (rpl->status != CPL_ERR_NONE) { pr_info("Unexpected PASS_OPEN_RPL status %u for STID %u\n", rpl->status, stid); - return CPL_RET_BUF_DONE; + } else { + cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); + sock_put(listen_ctx->lsk); + kfree(listen_ctx); + module_put(THIS_MODULE); } - cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); - sock_put(listen_ctx->lsk); - kfree(listen_ctx); - module_put(THIS_MODULE); - - return 0; + return CPL_RET_BUF_DONE; } static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb) @@ -792,15 +795,13 @@ static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb) if (rpl->status != CPL_ERR_NONE) { pr_info("Unexpected CLOSE_LISTSRV_RPL status %u for STID %u\n", rpl->status, stid); - return CPL_RET_BUF_DONE; + } else { + cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); + sock_put(listen_ctx->lsk); + kfree(listen_ctx); + module_put(THIS_MODULE); } - - cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family); - sock_put(listen_ctx->lsk); - kfree(listen_ctx); - module_put(THIS_MODULE); - - return 0; + return CPL_RET_BUF_DONE; } static void chtls_purge_wr_queue(struct sock *sk) @@ -1156,6 +1157,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk, ndev = n->dev; if (!ndev) goto free_dst; + if (is_vlan_dev(ndev)) + ndev = vlan_dev_real_dev(ndev); + port_id = cxgb4_port_idx(ndev); csk = chtls_sock_create(cdev); @@ -1506,7 +1510,6 @@ static void add_to_reap_list(struct sock *sk) struct chtls_sock *csk = sk->sk_user_data; local_bh_disable(); - bh_lock_sock(sk); release_tcp_port(sk); /* release the port immediately */ spin_lock(&reap_list_lock); @@ -1515,7 +1518,6 @@ static void add_to_reap_list(struct sock *sk) if (!csk->passive_reap_next) schedule_work(&reap_task); spin_unlock(&reap_list_lock); - bh_unlock_sock(sk); local_bh_enable(); } diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index 2e9acae1cba3..188d871f6b8c 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -902,9 +902,9 @@ static int chtls_skb_copy_to_page_nocache(struct sock *sk, return 0; } -static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk) +static bool csk_mem_free(struct chtls_dev *cdev, struct sock *sk) { - return (cdev->max_host_sndbuf - sk->sk_wmem_queued); + return (cdev->max_host_sndbuf - sk->sk_wmem_queued > 0); } static int csk_wait_memory(struct chtls_dev *cdev, @@ -1240,6 +1240,7 @@ int chtls_sendpage(struct sock *sk, struct page *page, copied = 0; csk = rcu_dereference_sk_user_data(sk); cdev = csk->cdev; + lock_sock(sk); timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); err = sk_stream_wait_connect(sk, &timeo); @@ -1584,6 +1585,7 @@ skip_copy: tp->urg_data = 0; if ((avail + offset) >= skb->len) { + struct sk_buff *next_skb; if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) { tp->copied_seq += skb->len; hws->rcvpld = skb->hdr_len; @@ -1594,8 +1596,10 @@ skip_copy: chtls_free_skb(sk, skb); buffers_freed++; hws->copied_seq = 0; - if (copied >= target && - !skb_peek(&sk->sk_receive_queue)) + next_skb = skb_peek(&sk->sk_receive_queue); + if (copied >= target && !next_skb) + break; + if (ULP_SKB_CB(next_skb)->flags & ULPCB_FLAG_TLS_HDR) break; } } while (len > 0); diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 64614a9bdf21..047826f18bd3 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -332,11 +332,14 @@ static int sec_alg_resource_alloc(struct sec_ctx *ctx, ret = sec_alloc_pbuf_resource(dev, res); if (ret) { dev_err(dev, "fail to alloc pbuf dma resource!\n"); - goto alloc_fail; + goto alloc_pbuf_fail; } } return 0; +alloc_pbuf_fail: + if (ctx->alg_type == SEC_AEAD) + sec_free_mac_resource(dev, qp_ctx->res); alloc_fail: sec_free_civ_resource(dev, res); @@ -447,8 +450,10 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) ctx->fake_req_limit = QM_Q_DEPTH >> 1; ctx->qp_ctx = kcalloc(sec->ctx_q_num, sizeof(struct sec_qp_ctx), GFP_KERNEL); - if (!ctx->qp_ctx) - return -ENOMEM; + if (!ctx->qp_ctx) { + ret = -ENOMEM; + goto err_destroy_qps; + } for (i = 0; i < sec->ctx_q_num; i++) { ret = sec_create_qp_ctx(&sec->qm, ctx, i, 0); @@ -457,12 +462,15 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) } return 0; + err_sec_release_qp_ctx: for (i = i - 1; i >= 0; i--) sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]); - sec_destroy_qps(ctx->qps, sec->ctx_q_num); kfree(ctx->qp_ctx); +err_destroy_qps: + sec_destroy_qps(ctx->qps, sec->ctx_q_num); + return ret; } diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index ad73fc946682..3be6e0db0f9f 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -528,7 +528,7 @@ static void release_ixp_crypto(struct device *dev) if (crypt_virt) { dma_free_coherent(dev, - NPE_QLEN_TOTAL * sizeof( struct crypt_ctl), + NPE_QLEN * sizeof(struct crypt_ctl), crypt_virt, crypt_phys); } } diff --git a/drivers/crypto/mediatek/mtk-platform.c b/drivers/crypto/mediatek/mtk-platform.c index 7e3ad085b5bd..efce3a83b35a 100644 --- a/drivers/crypto/mediatek/mtk-platform.c +++ b/drivers/crypto/mediatek/mtk-platform.c @@ -442,7 +442,7 @@ static void mtk_desc_dma_free(struct mtk_cryp *cryp) static int mtk_desc_ring_alloc(struct mtk_cryp *cryp) { struct mtk_ring **ring = cryp->ring; - int i, err = ENOMEM; + int i; for (i = 0; i < MTK_RING_MAX; i++) { ring[i] = kzalloc(sizeof(**ring), GFP_KERNEL); @@ -469,14 +469,14 @@ static int mtk_desc_ring_alloc(struct mtk_cryp *cryp) return 0; err_cleanup: - for (; i--; ) { + do { dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ, ring[i]->res_base, ring[i]->res_dma); dma_free_coherent(cryp->dev, MTK_DESC_RING_SZ, ring[i]->cmd_base, ring[i]->cmd_dma); kfree(ring[i]); - } - return err; + } while (i--); + return -ENOMEM; } static int mtk_crypto_probe(struct platform_device *pdev) diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c index 82691a057d2a..bc956dfb34de 100644 --- a/drivers/crypto/omap-sham.c +++ b/drivers/crypto/omap-sham.c @@ -456,6 +456,9 @@ static void omap_sham_write_ctrl_omap4(struct omap_sham_dev *dd, size_t length, struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req); u32 val, mask; + if (likely(ctx->digcnt)) + omap_sham_write(dd, SHA_REG_DIGCNT(dd), ctx->digcnt); + /* * Setting ALGO_CONST only for the first iteration and * CLOSE_HASH only for the last one. Note that flags mode bits diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c index 7384e91c8b32..0d32b641a7f9 100644 --- a/drivers/crypto/picoxcell_crypto.c +++ b/drivers/crypto/picoxcell_crypto.c @@ -1666,11 +1666,6 @@ static int spacc_probe(struct platform_device *pdev) goto err_clk_put; } - ret = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh); - if (ret) - goto err_clk_disable; - - /* * Use an IRQ threshold of 50% as a default. This seems to be a * reasonable trade off of latency against throughput but can be @@ -1678,6 +1673,10 @@ static int spacc_probe(struct platform_device *pdev) */ engine->stat_irq_thresh = (engine->fifo_sz / 2); + ret = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh); + if (ret) + goto err_clk_disable; + /* * Configure the interrupts. We only use the STAT_CNT interrupt as we * only submit a new packet for processing when we complete another in diff --git a/drivers/crypto/stm32/Kconfig b/drivers/crypto/stm32/Kconfig index 4ef3eb11361c..4a4c3284ae1f 100644 --- a/drivers/crypto/stm32/Kconfig +++ b/drivers/crypto/stm32/Kconfig @@ -3,6 +3,7 @@ config CRYPTO_DEV_STM32_CRC tristate "Support for STM32 crc accelerators" depends on ARCH_STM32 select CRYPTO_HASH + select CRC32 help This enables support for the CRC32 hw accelerator which can be found on STMicroelectronics STM32 SOC. diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index 3ba41148c2a4..2c13f5214d2c 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -6,6 +6,7 @@ #include <linux/bitrev.h> #include <linux/clk.h> +#include <linux/crc32.h> #include <linux/crc32poly.h> #include <linux/module.h> #include <linux/mod_devicetable.h> @@ -147,7 +148,6 @@ static int burst_update(struct shash_desc *desc, const u8 *d8, struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc); struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm); struct stm32_crc *crc; - unsigned long flags; crc = stm32_crc_get_next_crc(); if (!crc) @@ -155,7 +155,15 @@ static int burst_update(struct shash_desc *desc, const u8 *d8, pm_runtime_get_sync(crc->dev); - spin_lock_irqsave(&crc->lock, flags); + if (!spin_trylock(&crc->lock)) { + /* Hardware is busy, calculate crc32 by software */ + if (mctx->poly == CRC32_POLY_LE) + ctx->partial = crc32_le(ctx->partial, d8, length); + else + ctx->partial = __crc32c_le(ctx->partial, d8, length); + + goto pm_out; + } /* * Restore previously calculated CRC for this context as init value @@ -195,8 +203,9 @@ static int burst_update(struct shash_desc *desc, const u8 *d8, /* Store partial result */ ctx->partial = readl_relaxed(crc->regs + CRC_DR); - spin_unlock_irqrestore(&crc->lock, flags); + spin_unlock(&crc->lock); +pm_out: pm_runtime_mark_last_busy(crc->dev); pm_runtime_put_autosuspend(crc->dev); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 323822372b4c..7480fc104209 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -1240,15 +1240,14 @@ static int dmatest_chan_set(const char *val, const struct kernel_param *kp) add_threaded_test(info); /* Check if channel was added successfully */ - dtc = list_last_entry(&info->channels, struct dmatest_chan, node); - - if (dtc->chan) { + if (!list_empty(&info->channels)) { /* * if new channel was not successfully added, revert the * "test_channel" string to the name of the last successfully * added channel. exception for when users issues empty string * to channel parameter. */ + dtc = list_last_entry(&info->channels, struct dmatest_chan, node); if ((strcmp(dma_chan_name(dtc->chan), strim(test_channel)) != 0) && (strcmp("", strim(test_channel)) != 0)) { ret = -EINVAL; diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index a1b56f52db2f..5e7fdc0b6e3d 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -772,6 +772,10 @@ bool dw_dma_filter(struct dma_chan *chan, void *param) if (dws->dma_dev != chan->device->dev) return false; + /* permit channels in accordance with the channels mask */ + if (dws->channels && !(dws->channels & dwc->mask)) + return false; + /* We have to copy data since dws can be temporary storage */ memcpy(&dwc->dws, dws, sizeof(struct dw_dma_slave)); diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c index 7a085b3c1854..d9810980920a 100644 --- a/drivers/dma/dw/dw.c +++ b/drivers/dma/dw/dw.c @@ -14,7 +14,7 @@ static void dw_dma_initialize_chan(struct dw_dma_chan *dwc) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); - u32 cfghi = DWC_CFGH_FIFO_MODE; + u32 cfghi = is_slave_direction(dwc->direction) ? 0 : DWC_CFGH_FIFO_MODE; u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority); bool hs_polarity = dwc->dws.hs_polarity; diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c index 9e27831dee32..43e975fb6714 100644 --- a/drivers/dma/dw/of.c +++ b/drivers/dma/dw/of.c @@ -22,18 +22,21 @@ static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec, }; dma_cap_mask_t cap; - if (dma_spec->args_count != 3) + if (dma_spec->args_count < 3 || dma_spec->args_count > 4) return NULL; slave.src_id = dma_spec->args[0]; slave.dst_id = dma_spec->args[0]; slave.m_master = dma_spec->args[1]; slave.p_master = dma_spec->args[2]; + if (dma_spec->args_count >= 4) + slave.channels = dma_spec->args[3]; if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS || slave.dst_id >= DW_DMA_MAX_NR_REQUESTS || slave.m_master >= dw->pdata->nr_masters || - slave.p_master >= dw->pdata->nr_masters)) + slave.p_master >= dw->pdata->nr_masters || + slave.channels >= BIT(dw->pdata->nr_channels))) return NULL; dma_cap_zero(cap); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index fd782aee02d9..98c56606ab1a 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -389,7 +389,7 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags) struct ioat_descs *descs = &ioat_chan->descs[i]; descs->virt = dma_alloc_coherent(to_dev(ioat_chan), - SZ_2M, &descs->hw, flags); + IOAT_CHUNK_SIZE, &descs->hw, flags); if (!descs->virt) { int idx; diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index b194658b8b5c..fbec28dc661d 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -209,8 +209,8 @@ static int config_irq(void *ctx, struct platform_device *pdev) /* register interrupt handler */ irq = platform_get_irq(pdev, 0); dev_dbg(&pdev->dev, "got irq %d\n", irq); - if (!irq) - return -ENODEV; + if (irq < 0) + return irq; rc = devm_request_irq(&pdev->dev, irq, mcr_isr, IRQF_TRIGGER_HIGH, DRV_NAME, ctx); diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 191aa7c19ded..324a46b8479b 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -1061,16 +1061,15 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) PCI_DEVICE_ID_INTEL_5100_19, 0); if (!einj) { ret = -ENODEV; - goto bail_einj; + goto bail_mc_free; } rc = pci_enable_device(einj); if (rc < 0) { ret = rc; - goto bail_disable_einj; + goto bail_einj; } - mci->pdev = &pdev->dev; priv = mci->pvt_info; @@ -1136,14 +1135,14 @@ static int i5100_init_one(struct pci_dev *pdev, const struct pci_device_id *id) bail_scrub: priv->scrub_enable = 0; cancel_delayed_work_sync(&(priv->i5100_scrubbing)); - edac_mc_free(mci); - -bail_disable_einj: pci_disable_device(einj); bail_einj: pci_dev_put(einj); +bail_mc_free: + edac_mc_free(mci); + bail_disable_ch1: pci_disable_device(ch1mm); diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c index 8be3e89a510e..d7419a90a2f5 100644 --- a/drivers/edac/ti_edac.c +++ b/drivers/edac/ti_edac.c @@ -278,7 +278,8 @@ static int ti_edac_probe(struct platform_device *pdev) /* add EMIF ECC error handler */ error_irq = platform_get_irq(pdev, 0); - if (!error_irq) { + if (error_irq < 0) { + ret = error_irq; edac_printk(KERN_ERR, EDAC_MOD_NAME, "EMIF irq number not defined.\n"); goto err; diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 6998dc86b5ce..b797a713c331 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -110,7 +110,7 @@ static int mailbox_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_mailbox *smbox = cinfo->transport_info; - if (!IS_ERR(smbox->chan)) { + if (smbox && !IS_ERR(smbox->chan)) { mbox_free_channel(smbox->chan); cinfo->transport_info = NULL; smbox->chan = NULL; diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index e5bfac79e5ac..04f5d79d4265 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -62,10 +62,12 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, status = efi_get_random_bytes(sizeof(phys_seed), (u8 *)&phys_seed); if (status == EFI_NOT_FOUND) { - efi_info("EFI_RNG_PROTOCOL unavailable, no randomness supplied\n"); + efi_info("EFI_RNG_PROTOCOL unavailable, KASLR will be disabled\n"); + efi_nokaslr = true; } else if (status != EFI_SUCCESS) { - efi_err("efi_get_random_bytes() failed\n"); - return status; + efi_err("efi_get_random_bytes() failed (0x%lx), KASLR will be disabled\n", + status); + efi_nokaslr = true; } } else { efi_info("KASLR disabled on kernel command line\n"); diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 11ecf3c4640e..368cd60000ee 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -136,7 +136,7 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size, if (status) goto fdt_set_fail; - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { efi_status_t efi_status; efi_status = efi_get_random_bytes(sizeof(fdt_val64), @@ -145,8 +145,6 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size, status = fdt_setprop_var(fdt, node, "kaslr-seed", fdt_val64); if (status) goto fdt_set_fail; - } else if (efi_status != EFI_NOT_FOUND) { - return efi_status; } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7c1cc0ba30a5..78cf9e4fddbd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8178,8 +8178,7 @@ static int dm_update_plane_state(struct dc *dc, dm_old_plane_state->dc_state, dm_state->context)) { - ret = EINVAL; - return ret; + return -EINVAL; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d016f50e187c..d261f425b80e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2538,7 +2538,7 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_stream_update_to_stream(dc, context, stream, stream_update); - if (update_type > UPDATE_TYPE_FAST) { + if (update_type >= UPDATE_TYPE_FULL) { if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { DC_ERROR("Mode validation failed for stream update!\n"); dc_release_state(context); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c index ebff9b1e312e..124c081a0f2c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c @@ -75,7 +75,7 @@ static unsigned int calculate_16_bit_backlight_from_pwm(struct dce_panel_cntl *d else bl_pwm &= 0xFFFF; - current_backlight = bl_pwm << (1 + bl_int_count); + current_backlight = (uint64_t)bl_pwm << (1 + bl_int_count); if (bl_period == 0) bl_period = 0xFFFF; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 20bdabebbc43..76cd4f3de4ea 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3165,6 +3165,9 @@ static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive = dc->debug.enable_dram_clock_change_one_display_vactive; + /*Unsafe due to current pipe merge and split logic*/ + ASSERT(context != dc->current_state); + if (fast_validate) { return dcn20_validate_bandwidth_internal(dc, context, true); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index f00a56835084..c6ab3dee4fd6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -1184,6 +1184,9 @@ bool dcn21_validate_bandwidth(struct dc *dc, struct dc_state *context, BW_VAL_TRACE_COUNT(); + /*Unsafe due to current pipe merge and split logic*/ + ASSERT(context != dc->current_state); + out = dcn20_fast_validate_bw(dc, context, pipes, &pipe_cnt, pipe_split_from, &vlevel); if (pipe_cnt == 0) diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c index 5d67a41f7c3a..3dd70d813f69 100644 --- a/drivers/gpu/drm/drm_debugfs_crc.c +++ b/drivers/gpu/drm/drm_debugfs_crc.c @@ -144,8 +144,10 @@ static ssize_t crc_control_write(struct file *file, const char __user *ubuf, source[len - 1] = '\0'; ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt); - if (ret) + if (ret) { + kfree(source); return ret; + } spin_lock_irq(&crc->lock); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 8b2d5c945c95..1d85af9a481a 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -175,6 +175,10 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo, } } +/* + * Note that on error, drm_gem_vram_init will free the buffer object. + */ + static int drm_gem_vram_init(struct drm_device *dev, struct drm_gem_vram_object *gbo, size_t size, unsigned long pg_align) @@ -184,15 +188,19 @@ static int drm_gem_vram_init(struct drm_device *dev, int ret; size_t acc_size; - if (WARN_ONCE(!vmm, "VRAM MM not initialized")) + if (WARN_ONCE(!vmm, "VRAM MM not initialized")) { + kfree(gbo); return -EINVAL; + } bdev = &vmm->bdev; gbo->bo.base.funcs = &drm_gem_vram_object_funcs; ret = drm_gem_object_init(dev, &gbo->bo.base, size); - if (ret) + if (ret) { + kfree(gbo); return ret; + } acc_size = ttm_bo_dma_acc_size(bdev, size, sizeof(*gbo)); @@ -203,13 +211,13 @@ static int drm_gem_vram_init(struct drm_device *dev, &gbo->placement, pg_align, false, acc_size, NULL, NULL, ttm_buffer_object_destroy); if (ret) - goto err_drm_gem_object_release; + /* + * A failing ttm_bo_init will call ttm_buffer_object_destroy + * to release gbo->bo.base and kfree gbo. + */ + return ret; return 0; - -err_drm_gem_object_release: - drm_gem_object_release(&gbo->bo.base); - return ret; } /** @@ -243,13 +251,9 @@ struct drm_gem_vram_object *drm_gem_vram_create(struct drm_device *dev, ret = drm_gem_vram_init(dev, gbo, size, pg_align); if (ret < 0) - goto err_kfree; + return ERR_PTR(ret); return gbo; - -err_kfree: - kfree(gbo); - return ERR_PTR(ret); } EXPORT_SYMBOL(drm_gem_vram_create); diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index f41cbb753bb4..720a767118c9 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -2078,7 +2078,7 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev intel_dp->dpcd, sizeof(intel_dp->dpcd)); cdv_intel_edp_panel_vdd_off(gma_encoder); - if (ret == 0) { + if (ret <= 0) { /* if this fails, presume the device is a ghost */ DRM_INFO("failed to retrieve link info, disabling eDP\n"); drm_encoder_cleanup(encoder); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index e7532e7d74e9..0e1f11669b07 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -323,6 +323,7 @@ static void print_context_stats(struct seq_file *m, } i915_gem_context_unlock_engines(ctx); + mutex_lock(&ctx->mutex); if (!IS_ERR_OR_NULL(ctx->file_priv)) { struct file_stats stats = { .vm = rcu_access_pointer(ctx->vm), @@ -343,6 +344,7 @@ static void print_context_stats(struct seq_file *m, print_file_stats(m, name, stats); } + mutex_unlock(&ctx->mutex); spin_lock(&i915->gem.contexts.lock); list_safe_reset_next(ctx, cn, link); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index d8b43500f12d..2d01a293aa78 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -485,7 +485,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc) mbox_flush(mtk_crtc->cmdq_client->chan, 2000); cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE); cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event); - cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event); + cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false); mtk_crtc_ddp_config(crtc, cmdq_handle); cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index d6023ba8033c..3bb567812b99 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -864,7 +864,7 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu, int i; a6xx_state->indexed_regs = state_kcalloc(a6xx_state, count, - sizeof(a6xx_state->indexed_regs)); + sizeof(*a6xx_state->indexed_regs)); if (!a6xx_state->indexed_regs) return; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index a74ccc5b8220..5b5809c0e44b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -189,10 +189,16 @@ struct msm_gem_address_space * adreno_iommu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) { - struct iommu_domain *iommu = iommu_domain_alloc(&platform_bus_type); - struct msm_mmu *mmu = msm_iommu_new(&pdev->dev, iommu); + struct iommu_domain *iommu; + struct msm_mmu *mmu; struct msm_gem_address_space *aspace; + iommu = iommu_domain_alloc(&platform_bus_type); + if (!iommu) + return NULL; + + mmu = msm_iommu_new(&pdev->dev, iommu); + aspace = msm_gem_address_space_create(mmu, "gpu", SZ_16M, 0xffffffff - SZ_16M); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 1026e1e5bec1..4d81a0c73616 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -881,7 +881,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_plane *plane; struct drm_display_mode *mode; - int cnt = 0, rc = 0, mixer_width, i, z_pos; + int cnt = 0, rc = 0, mixer_width = 0, i, z_pos; struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2]; int multirect_count = 0; @@ -914,9 +914,11 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, memset(pipe_staged, 0, sizeof(pipe_staged)); - mixer_width = mode->hdisplay / cstate->num_mixers; + if (cstate->num_mixers) { + mixer_width = mode->hdisplay / cstate->num_mixers; - _dpu_crtc_setup_lm_bounds(crtc, state); + _dpu_crtc_setup_lm_bounds(crtc, state); + } crtc_rect.x2 = mode->hdisplay; crtc_rect.y2 = mode->vdisplay; diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index 497cf443a9af..0b02e65a89e7 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -26,6 +26,7 @@ #include <drm/drm_drv.h> #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fb_helper.h> +#include <drm/drm_fourcc.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_irq.h> @@ -87,8 +88,26 @@ void mxsfb_disable_axi_clk(struct mxsfb_drm_private *mxsfb) clk_disable_unprepare(mxsfb->clk_axi); } +static struct drm_framebuffer * +mxsfb_fb_create(struct drm_device *dev, struct drm_file *file_priv, + const struct drm_mode_fb_cmd2 *mode_cmd) +{ + const struct drm_format_info *info; + + info = drm_get_format_info(dev, mode_cmd); + if (!info) + return ERR_PTR(-EINVAL); + + if (mode_cmd->width * info->cpp[0] != mode_cmd->pitches[0]) { + dev_dbg(dev->dev, "Invalid pitch: fb width must match pitch\n"); + return ERR_PTR(-EINVAL); + } + + return drm_gem_fb_create(dev, file_priv, mode_cmd); +} + static const struct drm_mode_config_funcs mxsfb_mode_config_funcs = { - .fb_create = drm_gem_fb_create, + .fb_create = mxsfb_fb_create, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 7debf2ca4252..4b4ca31a2d57 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2862,12 +2862,12 @@ static const struct drm_display_mode ortustech_com43h4m85ulc_mode = { static const struct panel_desc ortustech_com43h4m85ulc = { .modes = &ortustech_com43h4m85ulc_mode, .num_modes = 1, - .bpc = 8, + .bpc = 6, .size = { .width = 56, .height = 93, }, - .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .bus_format = MEDIA_BUS_FMT_RGB666_1X18, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, .connector_type = DRM_MODE_CONNECTOR_DPI, }; diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index c30c719a8059..3c4a85213c15 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -69,6 +69,9 @@ struct panfrost_compatible { int num_pm_domains; /* Only required if num_pm_domains > 1. */ const char * const *pm_domain_names; + + /* Vendor implementation quirks callback */ + void (*vendor_quirk)(struct panfrost_device *pfdev); }; struct panfrost_device { diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 882fecc33fdb..6e11a73e81aa 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -667,7 +667,18 @@ static const struct panfrost_compatible default_data = { .pm_domain_names = NULL, }; +static const struct panfrost_compatible amlogic_data = { + .num_supplies = ARRAY_SIZE(default_supplies), + .supply_names = default_supplies, + .vendor_quirk = panfrost_gpu_amlogic_quirk, +}; + static const struct of_device_id dt_match[] = { + /* Set first to probe before the generic compatibles */ + { .compatible = "amlogic,meson-gxm-mali", + .data = &amlogic_data, }, + { .compatible = "amlogic,meson-g12a-mali", + .data = &amlogic_data, }, { .compatible = "arm,mali-t604", .data = &default_data, }, { .compatible = "arm,mali-t624", .data = &default_data, }, { .compatible = "arm,mali-t628", .data = &default_data, }, diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index f2c1ddc41a9b..165403878ad9 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -75,6 +75,17 @@ int panfrost_gpu_soft_reset(struct panfrost_device *pfdev) return 0; } +void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev) +{ + /* + * The Amlogic integrated Mali-T820, Mali-G31 & Mali-G52 needs + * these undocumented bits in GPU_PWR_OVERRIDE1 to be set in order + * to operate correctly. + */ + gpu_write(pfdev, GPU_PWR_KEY, GPU_PWR_KEY_UNLOCK); + gpu_write(pfdev, GPU_PWR_OVERRIDE1, 0xfff | (0x20 << 16)); +} + static void panfrost_gpu_init_quirks(struct panfrost_device *pfdev) { u32 quirks = 0; @@ -135,6 +146,10 @@ static void panfrost_gpu_init_quirks(struct panfrost_device *pfdev) if (quirks) gpu_write(pfdev, GPU_JM_CONFIG, quirks); + + /* Here goes platform specific quirks */ + if (pfdev->comp->vendor_quirk) + pfdev->comp->vendor_quirk(pfdev); } #define MAX_HW_REVS 6 @@ -304,16 +319,18 @@ void panfrost_gpu_power_on(struct panfrost_device *pfdev) int ret; u32 val; + panfrost_gpu_init_quirks(pfdev); + /* Just turn on everything for now */ gpu_write(pfdev, L2_PWRON_LO, pfdev->features.l2_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + L2_READY_LO, - val, val == pfdev->features.l2_present, 100, 1000); + val, val == pfdev->features.l2_present, 100, 20000); if (ret) dev_err(pfdev->dev, "error powering up gpu L2"); gpu_write(pfdev, SHADER_PWRON_LO, pfdev->features.shader_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_READY_LO, - val, val == pfdev->features.shader_present, 100, 1000); + val, val == pfdev->features.shader_present, 100, 20000); if (ret) dev_err(pfdev->dev, "error powering up gpu shader"); @@ -355,7 +372,6 @@ int panfrost_gpu_init(struct panfrost_device *pfdev) return err; } - panfrost_gpu_init_quirks(pfdev); panfrost_gpu_power_on(pfdev); return 0; diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.h b/drivers/gpu/drm/panfrost/panfrost_gpu.h index 4112412087b2..468c51e7e46d 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.h +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.h @@ -16,4 +16,6 @@ int panfrost_gpu_soft_reset(struct panfrost_device *pfdev); void panfrost_gpu_power_on(struct panfrost_device *pfdev); void panfrost_gpu_power_off(struct panfrost_device *pfdev); +void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev); + #endif diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h index ea38ac60581c..eddaa62ad8b0 100644 --- a/drivers/gpu/drm/panfrost/panfrost_regs.h +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h @@ -51,6 +51,10 @@ #define GPU_STATUS 0x34 #define GPU_STATUS_PRFCNT_ACTIVE BIT(2) #define GPU_LATEST_FLUSH_ID 0x38 +#define GPU_PWR_KEY 0x50 /* (WO) Power manager key register */ +#define GPU_PWR_KEY_UNLOCK 0x2968A819 +#define GPU_PWR_OVERRIDE0 0x54 /* (RW) Power manager override settings */ +#define GPU_PWR_OVERRIDE1 0x58 /* (RW) Power manager override settings */ #define GPU_FAULT_STATUS 0x3C #define GPU_FAULT_ADDRESS_LO 0x40 #define GPU_FAULT_ADDRESS_HI 0x44 diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index f1a81c9b184d..fa09b3ae8b9d 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -13,6 +13,7 @@ #include <drm/drm_fourcc.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_plane_helper.h> #include <drm/drm_vblank.h> @@ -341,6 +342,13 @@ static const struct drm_plane_funcs rcar_du_vsp_plane_funcs = { .atomic_destroy_state = rcar_du_vsp_plane_atomic_destroy_state, }; +static void rcar_du_vsp_cleanup(struct drm_device *dev, void *res) +{ + struct rcar_du_vsp *vsp = res; + + put_device(vsp->vsp); +} + int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, unsigned int crtcs) { @@ -357,6 +365,10 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, vsp->vsp = &pdev->dev; + ret = drmm_add_action(rcdu->ddev, rcar_du_vsp_cleanup, vsp); + if (ret < 0) + return ret; + ret = vsp1_du_init(vsp->vsp); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index fa39d140adc6..94825ec3a09d 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -471,8 +471,8 @@ static int __init vgem_init(void) out_put: drm_dev_put(&vgem_device->drm); + platform_device_unregister(vgem_device->platform); return ret; - out_unregister: platform_device_unregister(vgem_device->platform); out_free: diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 0a5c8cf409fb..dc8cb8dfce58 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -80,8 +80,10 @@ static void virtio_gpu_get_capsets(struct virtio_gpu_device *vgdev, vgdev->capsets[i].id > 0, 5 * HZ); if (ret == 0) { DRM_ERROR("timed out waiting for cap set %d\n", i); + spin_lock(&vgdev->display_info_lock); kfree(vgdev->capsets); vgdev->capsets = NULL; + spin_unlock(&vgdev->display_info_lock); return; } DRM_INFO("cap set %d: id %d, max-version %d, max-size %d\n", diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 9e663a5d9952..2517450bf46b 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -684,9 +684,13 @@ static void virtio_gpu_cmd_get_capset_info_cb(struct virtio_gpu_device *vgdev, int i = le32_to_cpu(cmd->capset_index); spin_lock(&vgdev->display_info_lock); - vgdev->capsets[i].id = le32_to_cpu(resp->capset_id); - vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version); - vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size); + if (vgdev->capsets) { + vgdev->capsets[i].id = le32_to_cpu(resp->capset_id); + vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version); + vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size); + } else { + DRM_ERROR("invalid capset memory."); + } spin_unlock(&vgdev->display_info_lock); wake_up(&vgdev->resp_wq); } diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c index 4af2f19480f4..b8b060354667 100644 --- a/drivers/gpu/drm/vkms/vkms_composer.c +++ b/drivers/gpu/drm/vkms/vkms_composer.c @@ -33,7 +33,7 @@ static uint32_t compute_crc(void *vaddr_out, struct vkms_composer *composer) + (i * composer->pitch) + (j * composer->cpp); /* XRGB format ignores Alpha channel */ - memset(vaddr_out + src_offset + 24, 0, 8); + bitmap_clear(vaddr_out + src_offset, 24, 8); crc = crc32_le(crc, vaddr_out + src_offset, sizeof(u32)); } diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 1e8b2169d834..e6a3ea1b399a 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -188,8 +188,8 @@ static int __init vkms_init(void) out_put: drm_dev_put(&vkms_device->drm); + platform_device_unregister(vkms_device->platform); return ret; - out_unregister: platform_device_unregister(vkms_device->platform); out_free: diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b49ec7dde645..b269c792d25d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -726,6 +726,7 @@ #define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL 0x6049 #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 +#define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E 0x602e @@ -1122,6 +1123,7 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 +#define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index e3d475f4baf6..b2bff932c524 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -797,7 +797,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x3b: /* Battery Strength */ hidinput_setup_battery(device, HID_INPUT_REPORT, field); usage->type = EV_PWR; - goto ignore; + return; case 0x3c: /* Invert */ map_key_clear(BTN_TOOL_RUBBER); @@ -1059,7 +1059,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case HID_DC_BATTERYSTRENGTH: hidinput_setup_battery(device, HID_INPUT_REPORT, field); usage->type = EV_PWR; - goto ignore; + return; } goto unknown; diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 6c55682c5974..044a93f3c117 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -44,6 +44,10 @@ static const struct hid_device_id ite_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index e3152155c4b8..99f041afd5c0 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1973,6 +1973,12 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC, USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) }, + /* Lenovo X1 TAB Gen 3 */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X1_TAB3) }, + /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, MT_USB_DEVICE(USB_VENDOR_ID_ASUS, diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index 1a6e600197d0..509b9bb1362c 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -294,31 +294,40 @@ static ssize_t kone_sysfs_write_settings(struct file *fp, struct kobject *kobj, struct kone_device *kone = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval = 0, difference, old_profile; + struct kone_settings *settings = (struct kone_settings *)buf; /* I need to get my data in one piece */ if (off != 0 || count != sizeof(struct kone_settings)) return -EINVAL; mutex_lock(&kone->kone_lock); - difference = memcmp(buf, &kone->settings, sizeof(struct kone_settings)); + difference = memcmp(settings, &kone->settings, + sizeof(struct kone_settings)); if (difference) { - retval = kone_set_settings(usb_dev, - (struct kone_settings const *)buf); - if (retval) { - mutex_unlock(&kone->kone_lock); - return retval; + if (settings->startup_profile < 1 || + settings->startup_profile > 5) { + retval = -EINVAL; + goto unlock; } + retval = kone_set_settings(usb_dev, settings); + if (retval) + goto unlock; + old_profile = kone->settings.startup_profile; - memcpy(&kone->settings, buf, sizeof(struct kone_settings)); + memcpy(&kone->settings, settings, sizeof(struct kone_settings)); kone_profile_activated(kone, kone->settings.startup_profile); if (kone->settings.startup_profile != old_profile) kone_profile_report(kone, kone->settings.startup_profile); } +unlock: mutex_unlock(&kone->kone_lock); + if (retval) + return retval; + return sizeof(struct kone_settings); } static BIN_ATTR(settings, 0660, kone_sysfs_read_settings, diff --git a/drivers/hwmon/bt1-pvt.c b/drivers/hwmon/bt1-pvt.c index 94698cae0497..3e1d56585b91 100644 --- a/drivers/hwmon/bt1-pvt.c +++ b/drivers/hwmon/bt1-pvt.c @@ -13,6 +13,7 @@ #include <linux/bitops.h> #include <linux/clk.h> #include <linux/completion.h> +#include <linux/delay.h> #include <linux/device.h> #include <linux/hwmon-sysfs.h> #include <linux/hwmon.h> @@ -476,6 +477,7 @@ static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type, long *val) { struct pvt_cache *cache = &pvt->cache[type]; + unsigned long timeout; u32 data; int ret; @@ -499,7 +501,14 @@ static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type, pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID, 0); pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, PVT_CTRL_EN); - wait_for_completion(&cache->conversion); + /* + * Wait with timeout since in case if the sensor is suddenly powered + * down the request won't be completed and the caller will hang up on + * this procedure until the power is back up again. Multiply the + * timeout by the factor of two to prevent a false timeout. + */ + timeout = 2 * usecs_to_jiffies(ktime_to_us(pvt->timeout)); + ret = wait_for_completion_timeout(&cache->conversion, timeout); pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0); pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID, @@ -509,6 +518,9 @@ static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type, mutex_unlock(&pvt->iface_mtx); + if (!ret) + return -ETIMEDOUT; + if (type == PVT_TEMP) *val = pvt_calc_poly(&poly_N_to_temp, data); else @@ -654,44 +666,16 @@ static int pvt_write_trim(struct pvt_hwmon *pvt, long val) static int pvt_read_timeout(struct pvt_hwmon *pvt, long *val) { - unsigned long rate; - ktime_t kt; - u32 data; - - rate = clk_get_rate(pvt->clks[PVT_CLOCK_REF].clk); - if (!rate) - return -ENODEV; - - /* - * Don't bother with mutex here, since we just read data from MMIO. - * We also have to scale the ticks timeout up to compensate the - * ms-ns-data translations. - */ - data = readl(pvt->regs + PVT_TTIMEOUT) + 1; + int ret; - /* - * Calculate ref-clock based delay (Ttotal) between two consecutive - * data samples of the same sensor. So we first must calculate the - * delay introduced by the internal ref-clock timer (Tref * Fclk). - * Then add the constant timeout cuased by each conversion latency - * (Tmin). The basic formulae for each conversion is following: - * Ttotal = Tref * Fclk + Tmin - * Note if alarms are enabled the sensors are polled one after - * another, so in order to have the delay being applicable for each - * sensor the requested value must be equally redistirbuted. - */ -#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS) - kt = ktime_set(PVT_SENSORS_NUM * (u64)data, 0); - kt = ktime_divns(kt, rate); - kt = ktime_add_ns(kt, PVT_SENSORS_NUM * PVT_TOUT_MIN); -#else - kt = ktime_set(data, 0); - kt = ktime_divns(kt, rate); - kt = ktime_add_ns(kt, PVT_TOUT_MIN); -#endif + ret = mutex_lock_interruptible(&pvt->iface_mtx); + if (ret) + return ret; /* Return the result in msec as hwmon sysfs interface requires. */ - *val = ktime_to_ms(kt); + *val = ktime_to_ms(pvt->timeout); + + mutex_unlock(&pvt->iface_mtx); return 0; } @@ -699,7 +683,7 @@ static int pvt_read_timeout(struct pvt_hwmon *pvt, long *val) static int pvt_write_timeout(struct pvt_hwmon *pvt, long val) { unsigned long rate; - ktime_t kt; + ktime_t kt, cache; u32 data; int ret; @@ -712,7 +696,7 @@ static int pvt_write_timeout(struct pvt_hwmon *pvt, long val) * between all available sensors to have the requested delay * applicable to each individual sensor. */ - kt = ms_to_ktime(val); + cache = kt = ms_to_ktime(val); #if defined(CONFIG_SENSORS_BT1_PVT_ALARMS) kt = ktime_divns(kt, PVT_SENSORS_NUM); #endif @@ -741,6 +725,7 @@ static int pvt_write_timeout(struct pvt_hwmon *pvt, long val) return ret; pvt_set_tout(pvt, data); + pvt->timeout = cache; mutex_unlock(&pvt->iface_mtx); @@ -982,10 +967,52 @@ static int pvt_request_clks(struct pvt_hwmon *pvt) return 0; } -static void pvt_init_iface(struct pvt_hwmon *pvt) +static int pvt_check_pwr(struct pvt_hwmon *pvt) { + unsigned long tout; + int ret = 0; + u32 data; + + /* + * Test out the sensor conversion functionality. If it is not done on + * time then the domain must have been unpowered and we won't be able + * to use the device later in this driver. + * Note If the power source is lost during the normal driver work the + * data read procedure will either return -ETIMEDOUT (for the + * alarm-less driver configuration) or just stop the repeated + * conversion. In the later case alas we won't be able to detect the + * problem. + */ + pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_ALL, PVT_INTR_ALL); + pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, PVT_CTRL_EN); + pvt_set_tout(pvt, 0); + readl(pvt->regs + PVT_DATA); + + tout = PVT_TOUT_MIN / NSEC_PER_USEC; + usleep_range(tout, 2 * tout); + + data = readl(pvt->regs + PVT_DATA); + if (!(data & PVT_DATA_VALID)) { + ret = -ENODEV; + dev_err(pvt->dev, "Sensor is powered down\n"); + } + + pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0); + + return ret; +} + +static int pvt_init_iface(struct pvt_hwmon *pvt) +{ + unsigned long rate; u32 trim, temp; + rate = clk_get_rate(pvt->clks[PVT_CLOCK_REF].clk); + if (!rate) { + dev_err(pvt->dev, "Invalid reference clock rate\n"); + return -ENODEV; + } + /* * Make sure all interrupts and controller are disabled so not to * accidentally have ISR executed before the driver data is fully @@ -1000,12 +1027,37 @@ static void pvt_init_iface(struct pvt_hwmon *pvt) pvt_set_mode(pvt, pvt_info[pvt->sensor].mode); pvt_set_tout(pvt, PVT_TOUT_DEF); + /* + * Preserve the current ref-clock based delay (Ttotal) between the + * sensors data samples in the driver data so not to recalculate it + * each time on the data requests and timeout reads. It consists of the + * delay introduced by the internal ref-clock timer (N / Fclk) and the + * constant timeout caused by each conversion latency (Tmin): + * Ttotal = N / Fclk + Tmin + * If alarms are enabled the sensors are polled one after another and + * in order to get the next measurement of a particular sensor the + * caller will have to wait for at most until all the others are + * polled. In that case the formulae will look a bit different: + * Ttotal = 5 * (N / Fclk + Tmin) + */ +#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS) + pvt->timeout = ktime_set(PVT_SENSORS_NUM * PVT_TOUT_DEF, 0); + pvt->timeout = ktime_divns(pvt->timeout, rate); + pvt->timeout = ktime_add_ns(pvt->timeout, PVT_SENSORS_NUM * PVT_TOUT_MIN); +#else + pvt->timeout = ktime_set(PVT_TOUT_DEF, 0); + pvt->timeout = ktime_divns(pvt->timeout, rate); + pvt->timeout = ktime_add_ns(pvt->timeout, PVT_TOUT_MIN); +#endif + trim = PVT_TRIM_DEF; if (!of_property_read_u32(pvt->dev->of_node, "baikal,pvt-temp-offset-millicelsius", &temp)) trim = pvt_calc_trim(temp); pvt_set_trim(pvt, trim); + + return 0; } static int pvt_request_irq(struct pvt_hwmon *pvt) @@ -1109,7 +1161,13 @@ static int pvt_probe(struct platform_device *pdev) if (ret) return ret; - pvt_init_iface(pvt); + ret = pvt_check_pwr(pvt); + if (ret) + return ret; + + ret = pvt_init_iface(pvt); + if (ret) + return ret; ret = pvt_request_irq(pvt); if (ret) diff --git a/drivers/hwmon/bt1-pvt.h b/drivers/hwmon/bt1-pvt.h index 5eac73e94885..93b8dd5e7c94 100644 --- a/drivers/hwmon/bt1-pvt.h +++ b/drivers/hwmon/bt1-pvt.h @@ -10,6 +10,7 @@ #include <linux/completion.h> #include <linux/hwmon.h> #include <linux/kernel.h> +#include <linux/ktime.h> #include <linux/mutex.h> #include <linux/seqlock.h> @@ -201,6 +202,7 @@ struct pvt_cache { * if alarms are disabled). * @sensor: current PVT sensor the data conversion is being performed for. * @cache: data cache descriptor. + * @timeout: conversion timeout cache. */ struct pvt_hwmon { struct device *dev; @@ -214,6 +216,7 @@ struct pvt_hwmon { struct mutex iface_mtx; enum pvt_sensor_type sensor; struct pvt_cache cache[PVT_SENSORS_NUM]; + ktime_t timeout; }; /* diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c index 18b4e071067f..de04dff28945 100644 --- a/drivers/hwmon/pmbus/max34440.c +++ b/drivers/hwmon/pmbus/max34440.c @@ -388,7 +388,6 @@ static struct pmbus_driver_info max34440_info[] = { .func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, - .read_byte_data = max34440_read_byte_data, .read_word_data = max34440_read_word_data, .write_word_data = max34440_write_word_data, }, @@ -419,7 +418,6 @@ static struct pmbus_driver_info max34440_info[] = { .func[15] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, - .read_byte_data = max34440_read_byte_data, .read_word_data = max34440_read_word_data, .write_word_data = max34440_write_word_data, }, @@ -455,7 +453,6 @@ static struct pmbus_driver_info max34440_info[] = { .func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, .func[21] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP, - .read_byte_data = max34440_read_byte_data, .read_word_data = max34440_read_word_data, .write_word_data = max34440_write_word_data, }, diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 5a5120121e50..3964ceab2817 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1951,8 +1951,12 @@ static int w83627ehf_probe(struct platform_device *pdev) data, &w83627ehf_chip_info, w83627ehf_groups); + if (IS_ERR(hwmon_dev)) { + err = PTR_ERR(hwmon_dev); + goto exit_release; + } - return PTR_ERR_OR_ZERO(hwmon_dev); + return 0; exit_release: release_region(res->start, IOREGION_LENGTH); diff --git a/drivers/hwtracing/coresight/coresight-cti.c b/drivers/hwtracing/coresight/coresight-cti.c index 3ccc703dc940..167fbc2e7033 100644 --- a/drivers/hwtracing/coresight/coresight-cti.c +++ b/drivers/hwtracing/coresight/coresight-cti.c @@ -86,22 +86,16 @@ void cti_write_all_hw_regs(struct cti_drvdata *drvdata) CS_LOCK(drvdata->base); } -static void cti_enable_hw_smp_call(void *info) -{ - struct cti_drvdata *drvdata = info; - - cti_write_all_hw_regs(drvdata); -} - /* write regs to hardware and enable */ static int cti_enable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; struct device *dev = &drvdata->csdev->dev; + unsigned long flags; int rc = 0; pm_runtime_get_sync(dev->parent); - spin_lock(&drvdata->spinlock); + spin_lock_irqsave(&drvdata->spinlock, flags); /* no need to do anything if enabled or unpowered*/ if (config->hw_enabled || !config->hw_powered) @@ -112,19 +106,11 @@ static int cti_enable_hw(struct cti_drvdata *drvdata) if (rc) goto cti_err_not_enabled; - if (drvdata->ctidev.cpu >= 0) { - rc = smp_call_function_single(drvdata->ctidev.cpu, - cti_enable_hw_smp_call, - drvdata, 1); - if (rc) - goto cti_err_not_enabled; - } else { - cti_write_all_hw_regs(drvdata); - } + cti_write_all_hw_regs(drvdata); config->hw_enabled = true; atomic_inc(&drvdata->config.enable_req_count); - spin_unlock(&drvdata->spinlock); + spin_unlock_irqrestore(&drvdata->spinlock, flags); return rc; cti_state_unchanged: @@ -132,7 +118,7 @@ cti_state_unchanged: /* cannot enable due to error */ cti_err_not_enabled: - spin_unlock(&drvdata->spinlock); + spin_unlock_irqrestore(&drvdata->spinlock, flags); pm_runtime_put(dev->parent); return rc; } @@ -141,9 +127,7 @@ cti_err_not_enabled: static void cti_cpuhp_enable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; - struct device *dev = &drvdata->csdev->dev; - pm_runtime_get_sync(dev->parent); spin_lock(&drvdata->spinlock); config->hw_powered = true; @@ -163,7 +147,6 @@ static void cti_cpuhp_enable_hw(struct cti_drvdata *drvdata) /* did not re-enable due to no claim / no request */ cti_hp_not_enabled: spin_unlock(&drvdata->spinlock); - pm_runtime_put(dev->parent); } /* disable hardware */ @@ -511,12 +494,15 @@ static bool cti_add_sysfs_link(struct cti_drvdata *drvdata, return !link_err; } -static void cti_remove_sysfs_link(struct cti_trig_con *tc) +static void cti_remove_sysfs_link(struct cti_drvdata *drvdata, + struct cti_trig_con *tc) { struct coresight_sysfs_link link_info; + link_info.orig = drvdata->csdev; link_info.orig_name = tc->con_dev_name; link_info.target = tc->con_dev; + link_info.target_name = dev_name(&drvdata->csdev->dev); coresight_remove_sysfs_link(&link_info); } @@ -606,8 +592,8 @@ void cti_remove_assoc_from_csdev(struct coresight_device *csdev) ctidrv = csdev_to_cti_drvdata(csdev->ect_dev); ctidev = &ctidrv->ctidev; list_for_each_entry(tc, &ctidev->trig_cons, node) { - if (tc->con_dev == csdev->ect_dev) { - cti_remove_sysfs_link(tc); + if (tc->con_dev == csdev) { + cti_remove_sysfs_link(ctidrv, tc); tc->con_dev = NULL; break; } @@ -651,7 +637,7 @@ static void cti_remove_conn_xrefs(struct cti_drvdata *drvdata) if (tc->con_dev) { coresight_set_assoc_ectdev_mutex(tc->con_dev, NULL); - cti_remove_sysfs_link(tc); + cti_remove_sysfs_link(drvdata, tc); tc->con_dev = NULL; } } @@ -742,7 +728,8 @@ static int cti_dying_cpu(unsigned int cpu) spin_lock(&drvdata->spinlock); drvdata->config.hw_powered = false; - coresight_disclaim_device(drvdata->base); + if (drvdata->config.hw_enabled) + coresight_disclaim_device(drvdata->base); spin_unlock(&drvdata->spinlock); return 0; } diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 84f1dcb69827..9b0c5d719232 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -126,10 +126,10 @@ static void free_sink_buffer(struct etm_event_data *event_data) cpumask_t *mask = &event_data->mask; struct coresight_device *sink; - if (WARN_ON(cpumask_empty(mask))) + if (!event_data->snk_config) return; - if (!event_data->snk_config) + if (WARN_ON(cpumask_empty(mask))) return; cpu = cpumask_first(mask); @@ -310,6 +310,16 @@ static void etm_event_start(struct perf_event *event, int flags) if (!event_data) goto fail; + /* + * Check if this ETM is allowed to trace, as decided + * at etm_setup_aux(). This could be due to an unreachable + * sink from this ETM. We can't do much in this case if + * the sink was specified or hinted to the driver. For + * now, simply don't record anything on this ETM. + */ + if (!cpumask_test_cpu(cpu, &event_data->mask)) + goto fail_end_stop; + path = etm_event_cpu_path(event_data, cpu); /* We need a sink, no need to continue without one */ sink = coresight_get_sink(path); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index b673e738bc9a..a588cd6de01c 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -206,7 +206,7 @@ static ssize_t reset_store(struct device *dev, * each trace run. */ config->vinst_ctrl = BIT(0); - if (drvdata->nr_addr_cmp == true) { + if (drvdata->nr_addr_cmp > 0) { config->mode |= ETM_MODE_VIEWINST_STARTSTOP; /* SSSTATUS, bit[9] */ config->vinst_ctrl |= BIT(9); diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index 6089c481f8f1..d4e74b03c1e0 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -48,12 +48,11 @@ module_param(pm_save_enable, int, 0444); MODULE_PARM_DESC(pm_save_enable, "Save/restore state on power down: 1 = never, 2 = self-hosted"); -/* The number of ETMv4 currently registered */ -static int etm4_count; static struct etmv4_drvdata *etmdrvdata[NR_CPUS]; static void etm4_set_default_config(struct etmv4_config *config); static int etm4_set_event_filters(struct etmv4_drvdata *drvdata, struct perf_event *event); +static u64 etm4_get_access_type(struct etmv4_config *config); static enum cpuhp_state hp_online; @@ -781,6 +780,22 @@ static void etm4_init_arch_data(void *info) CS_LOCK(drvdata->base); } +/* Set ELx trace filter access in the TRCVICTLR register */ +static void etm4_set_victlr_access(struct etmv4_config *config) +{ + u64 access_type; + + config->vinst_ctrl &= ~(ETM_EXLEVEL_S_VICTLR_MASK | ETM_EXLEVEL_NS_VICTLR_MASK); + + /* + * TRCVICTLR::EXLEVEL_NS:EXLEVELS: Set kernel / user filtering + * bits in vinst_ctrl, same bit pattern as TRCACATRn values returned by + * etm4_get_access_type() but with a relative shift in this register. + */ + access_type = etm4_get_access_type(config) << ETM_EXLEVEL_LSHIFT_TRCVICTLR; + config->vinst_ctrl |= (u32)access_type; +} + static void etm4_set_default_config(struct etmv4_config *config) { /* disable all events tracing */ @@ -798,6 +813,9 @@ static void etm4_set_default_config(struct etmv4_config *config) /* TRCVICTLR::EVENT = 0x01, select the always on logic */ config->vinst_ctrl = BIT(0); + + /* TRCVICTLR::EXLEVEL_NS:EXLEVELS: Set kernel / user filtering */ + etm4_set_victlr_access(config); } static u64 etm4_get_ns_access_type(struct etmv4_config *config) @@ -1062,7 +1080,7 @@ out: void etm4_config_trace_mode(struct etmv4_config *config) { - u32 addr_acc, mode; + u32 mode; mode = config->mode; mode &= (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER); @@ -1074,15 +1092,7 @@ void etm4_config_trace_mode(struct etmv4_config *config) if (!(mode & ETM_MODE_EXCL_KERN) && !(mode & ETM_MODE_EXCL_USER)) return; - addr_acc = config->addr_acc[ETM_DEFAULT_ADDR_COMP]; - /* clear default config */ - addr_acc &= ~(ETM_EXLEVEL_NS_APP | ETM_EXLEVEL_NS_OS | - ETM_EXLEVEL_NS_HYP); - - addr_acc |= etm4_get_ns_access_type(config); - - config->addr_acc[ETM_DEFAULT_ADDR_COMP] = addr_acc; - config->addr_acc[ETM_DEFAULT_ADDR_COMP + 1] = addr_acc; + etm4_set_victlr_access(config); } static int etm4_online_cpu(unsigned int cpu) @@ -1179,7 +1189,7 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trcvdsacctlr = readl(drvdata->base + TRCVDSACCTLR); state->trcvdarcctlr = readl(drvdata->base + TRCVDARCCTLR); - for (i = 0; i < drvdata->nrseqstate; i++) + for (i = 0; i < drvdata->nrseqstate - 1; i++) state->trcseqevr[i] = readl(drvdata->base + TRCSEQEVRn(i)); state->trcseqrstevr = readl(drvdata->base + TRCSEQRSTEVR); @@ -1223,7 +1233,7 @@ static int etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trccidcctlr1 = readl(drvdata->base + TRCCIDCCTLR1); state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR0); - state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR1); + state->trcvmidcctlr1 = readl(drvdata->base + TRCVMIDCCTLR1); state->trcclaimset = readl(drvdata->base + TRCCLAIMCLR); @@ -1284,7 +1294,7 @@ static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) writel_relaxed(state->trcvdsacctlr, drvdata->base + TRCVDSACCTLR); writel_relaxed(state->trcvdarcctlr, drvdata->base + TRCVDARCCTLR); - for (i = 0; i < drvdata->nrseqstate; i++) + for (i = 0; i < drvdata->nrseqstate - 1; i++) writel_relaxed(state->trcseqevr[i], drvdata->base + TRCSEQEVRn(i)); @@ -1333,7 +1343,7 @@ static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) writel_relaxed(state->trccidcctlr1, drvdata->base + TRCCIDCCTLR1); writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR0); - writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR1); + writel_relaxed(state->trcvmidcctlr1, drvdata->base + TRCVMIDCCTLR1); writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET); @@ -1394,28 +1404,25 @@ static struct notifier_block etm4_cpu_pm_nb = { .notifier_call = etm4_cpu_pm_notify, }; -/* Setup PM. Called with cpus locked. Deals with error conditions and counts */ -static int etm4_pm_setup_cpuslocked(void) +/* Setup PM. Deals with error conditions and counts */ +static int __init etm4_pm_setup(void) { int ret; - if (etm4_count++) - return 0; - ret = cpu_pm_register_notifier(&etm4_cpu_pm_nb); if (ret) - goto reduce_count; + return ret; - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING, - "arm/coresight4:starting", - etm4_starting_cpu, etm4_dying_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING, + "arm/coresight4:starting", + etm4_starting_cpu, etm4_dying_cpu); if (ret) goto unregister_notifier; - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, - "arm/coresight4:online", - etm4_online_cpu, NULL); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "arm/coresight4:online", + etm4_online_cpu, NULL); /* HP dyn state ID returned in ret on success */ if (ret > 0) { @@ -1424,21 +1431,15 @@ static int etm4_pm_setup_cpuslocked(void) } /* failed dyn state - remove others */ - cpuhp_remove_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING); + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); unregister_notifier: cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); - -reduce_count: - --etm4_count; return ret; } -static void etm4_pm_clear(void) +static void __init etm4_pm_clear(void) { - if (--etm4_count != 0) - return; - cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); if (hp_online) { @@ -1491,22 +1492,12 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) if (!desc.name) return -ENOMEM; - cpus_read_lock(); etmdrvdata[drvdata->cpu] = drvdata; if (smp_call_function_single(drvdata->cpu, etm4_init_arch_data, drvdata, 1)) dev_err(dev, "ETM arch init failed\n"); - ret = etm4_pm_setup_cpuslocked(); - cpus_read_unlock(); - - /* etm4_pm_setup_cpuslocked() does its own cleanup - exit on error */ - if (ret) { - etmdrvdata[drvdata->cpu] = NULL; - return ret; - } - if (etm4_arch_supported(drvdata->arch) == false) { ret = -EINVAL; goto err_arch_supported; @@ -1553,7 +1544,6 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) err_arch_supported: etmdrvdata[drvdata->cpu] = NULL; - etm4_pm_clear(); return ret; } @@ -1591,4 +1581,23 @@ static struct amba_driver etm4x_driver = { .probe = etm4_probe, .id_table = etm4_ids, }; -builtin_amba_driver(etm4x_driver); + +static int __init etm4x_init(void) +{ + int ret; + + ret = etm4_pm_setup(); + + /* etm4_pm_setup() does its own cleanup - exit on error */ + if (ret) + return ret; + + ret = amba_driver_register(&etm4x_driver); + if (ret) { + pr_err("Error registering etm4x driver\n"); + etm4_pm_clear(); + } + + return ret; +} +device_initcall(etm4x_init); diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 47729e04aac7..ab38f9afd821 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -192,6 +192,9 @@ #define ETM_EXLEVEL_NS_HYP BIT(14) #define ETM_EXLEVEL_NS_NA BIT(15) +/* access level control in TRCVICTLR - same bits as TRCACATRn but shifted */ +#define ETM_EXLEVEL_LSHIFT_TRCVICTLR 8 + /* secure / non secure masks - TRCVICTLR, IDR3 */ #define ETM_EXLEVEL_S_VICTLR_MASK GENMASK(19, 16) /* NS MON (EL3) mode never implemented */ diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c index e4912abda3aa..85a6c099ddeb 100644 --- a/drivers/hwtracing/coresight/coresight-platform.c +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -712,11 +712,11 @@ static int acpi_coresight_parse_graph(struct acpi_device *adev, return dir; if (dir == ACPI_CORESIGHT_LINK_MASTER) { - if (ptr->outport > pdata->nr_outport) - pdata->nr_outport = ptr->outport; + if (ptr->outport >= pdata->nr_outport) + pdata->nr_outport = ptr->outport + 1; ptr++; } else { - WARN_ON(pdata->nr_inport == ptr->child_port); + WARN_ON(pdata->nr_inport == ptr->child_port + 1); /* * We do not track input port connections for a device. * However we need the highest port number described, @@ -724,8 +724,8 @@ static int acpi_coresight_parse_graph(struct acpi_device *adev, * record for an output connection. Hence, do not move * the ptr for input connections */ - if (ptr->child_port > pdata->nr_inport) - pdata->nr_inport = ptr->child_port; + if (ptr->child_port >= pdata->nr_inport) + pdata->nr_inport = ptr->child_port + 1; } } diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index f3efbb3b2b4d..cf03af09c6ce 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -1023,7 +1023,6 @@ static void coresight_device_release(struct device *dev) { struct coresight_device *csdev = to_coresight_device(dev); - cti_remove_assoc_from_csdev(csdev); fwnode_handle_put(csdev->dev.fwnode); kfree(csdev->refcnt); kfree(csdev); @@ -1357,6 +1356,7 @@ void coresight_unregister(struct coresight_device *csdev) { etm_perf_del_symlink_sink(csdev); /* Remove references of that device in the topology */ + cti_remove_assoc_from_csdev(csdev); coresight_remove_conns(csdev); coresight_release_platform_data(csdev, csdev->pdata); device_unregister(&csdev->dev); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 735bf31a3fdf..6546d6cf3c24 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -1191,6 +1191,7 @@ config I2C_RCAR tristate "Renesas R-Car I2C Controller" depends on ARCH_RENESAS || COMPILE_TEST select I2C_SLAVE + select RESET_CONTROLLER if ARCH_RCAR_GEN3 help If you say yes to this option, support will be included for the R-Car I2C controller. diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 2ade99b105b9..bbf8dd491d24 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -264,6 +264,7 @@ static acpi_status i2c_acpi_add_device(acpi_handle handle, u32 level, void i2c_acpi_register_devices(struct i2c_adapter *adap) { acpi_status status; + acpi_handle handle; if (!has_acpi_companion(&adap->dev)) return; @@ -274,6 +275,15 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap) adap, NULL); if (ACPI_FAILURE(status)) dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); + + if (!adap->dev.parent) + return; + + handle = ACPI_HANDLE(adap->dev.parent); + if (!handle) + return; + + acpi_walk_dep_device_list(handle); } const struct acpi_device_id * @@ -729,7 +739,6 @@ int i2c_acpi_install_space_handler(struct i2c_adapter *adapter) return -ENOMEM; } - acpi_walk_dep_device_list(handle); return 0; } diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 97f2e29265da..cc7564446ccd 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1782,6 +1782,21 @@ static void i3c_master_bus_cleanup(struct i3c_master_controller *master) i3c_master_detach_free_devs(master); } +static void i3c_master_attach_boardinfo(struct i3c_dev_desc *i3cdev) +{ + struct i3c_master_controller *master = i3cdev->common.master; + struct i3c_dev_boardinfo *i3cboardinfo; + + list_for_each_entry(i3cboardinfo, &master->boardinfo.i3c, node) { + if (i3cdev->info.pid != i3cboardinfo->pid) + continue; + + i3cdev->boardinfo = i3cboardinfo; + i3cdev->info.static_addr = i3cboardinfo->static_addr; + return; + } +} + static struct i3c_dev_desc * i3c_master_search_i3c_dev_duplicate(struct i3c_dev_desc *refdev) { @@ -1837,10 +1852,10 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, if (ret) goto err_detach_dev; + i3c_master_attach_boardinfo(newdev); + olddev = i3c_master_search_i3c_dev_duplicate(newdev); if (olddev) { - newdev->boardinfo = olddev->boardinfo; - newdev->info.static_addr = olddev->info.static_addr; newdev->dev = olddev->dev; if (newdev->dev) newdev->dev->desc = newdev; diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 3fee8bd7fe20..3f2226928fe0 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -1635,8 +1635,10 @@ static int cdns_i3c_master_probe(struct platform_device *pdev) master->ibi.slots = devm_kcalloc(&pdev->dev, master->ibi.num_slots, sizeof(*master->ibi.slots), GFP_KERNEL); - if (!master->ibi.slots) + if (!master->ibi.slots) { + ret = -ENOMEM; goto err_disable_sysclk; + } writel(IBIR_THR(1), master->regs + CMD_IBI_THR_CTRL); writel(MST_INT_IBIR_THR, master->regs + MST_IER); diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index 0e2068ec068b..358636954619 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -794,6 +794,13 @@ static int stm32_adc_core_runtime_resume(struct device *dev) { return stm32_adc_core_hw_start(dev); } + +static int stm32_adc_core_runtime_idle(struct device *dev) +{ + pm_runtime_mark_last_busy(dev); + + return 0; +} #endif static const struct dev_pm_ops stm32_adc_core_pm_ops = { @@ -801,7 +808,7 @@ static const struct dev_pm_ops stm32_adc_core_pm_ops = { pm_runtime_force_resume) SET_RUNTIME_PM_OPS(stm32_adc_core_runtime_suspend, stm32_adc_core_runtime_resume, - NULL) + stm32_adc_core_runtime_idle) }; static const struct stm32_adc_priv_cfg stm32f4_adc_priv_cfg = { diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 3a98439bba83..0abce004a959 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -647,13 +647,12 @@ static void process_one_req(struct work_struct *_work) req->callback = NULL; spin_lock_bh(&lock); + /* + * Although the work will normally have been canceled by the workqueue, + * it can still be requeued as long as it is on the req_list. + */ + cancel_delayed_work(&req->work); if (!list_empty(&req->list)) { - /* - * Although the work will normally have been canceled by the - * workqueue, it can still be requeued as long as it is on the - * req_list. - */ - cancel_delayed_work(&req->work); list_del_init(&req->list); kfree(req); } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 26de0dab60bb..d28c7c6940b0 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -68,6 +68,9 @@ static const char * const cma_events[] = { [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; +static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, + union ib_gid *mgid); + const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; @@ -345,13 +348,10 @@ struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) struct cma_multicast { struct rdma_id_private *id_priv; - union { - struct ib_sa_multicast *ib; - } multicast; + struct ib_sa_multicast *sa_mc; struct list_head list; void *context; struct sockaddr_storage addr; - struct kref mcref; u8 join_state; }; @@ -363,18 +363,6 @@ struct cma_work { struct rdma_cm_event event; }; -struct cma_ndev_work { - struct work_struct work; - struct rdma_id_private *id; - struct rdma_cm_event event; -}; - -struct iboe_mcast_work { - struct work_struct work; - struct rdma_id_private *id; - struct cma_multicast *mc; -}; - union cma_ip_addr { struct in6_addr ip6; struct { @@ -483,14 +471,6 @@ static void cma_attach_to_dev(struct rdma_id_private *id_priv, rdma_start_port(cma_dev->device)]; } -static inline void release_mc(struct kref *kref) -{ - struct cma_multicast *mc = container_of(kref, struct cma_multicast, mcref); - - kfree(mc->multicast.ib); - kfree(mc); -} - static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); @@ -1783,19 +1763,30 @@ static void cma_release_port(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -static void cma_leave_roce_mc_group(struct rdma_id_private *id_priv, - struct cma_multicast *mc) +static void destroy_mc(struct rdma_id_private *id_priv, + struct cma_multicast *mc) { - struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; - struct net_device *ndev = NULL; + if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) + ib_sa_free_multicast(mc->sa_mc); - if (dev_addr->bound_dev_if) - ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); - if (ndev) { - cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid, false); - dev_put(ndev); + if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { + struct rdma_dev_addr *dev_addr = + &id_priv->id.route.addr.dev_addr; + struct net_device *ndev = NULL; + + if (dev_addr->bound_dev_if) + ndev = dev_get_by_index(dev_addr->net, + dev_addr->bound_dev_if); + if (ndev) { + union ib_gid mgid; + + cma_set_mgid(id_priv, (struct sockaddr *)&mc->addr, + &mgid); + cma_igmp_send(ndev, &mgid, false); + dev_put(ndev); + } } - kref_put(&mc->mcref, release_mc); + kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) @@ -1803,16 +1794,10 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv) struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { - mc = container_of(id_priv->mc_list.next, - struct cma_multicast, list); + mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, + list); list_del(&mc->list); - if (rdma_cap_ib_mcast(id_priv->cma_dev->device, - id_priv->id.port_num)) { - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); - } else { - cma_leave_roce_mc_group(id_priv, mc); - } + destroy_mc(id_priv, mc); } } @@ -2646,32 +2631,14 @@ static void cma_work_handler(struct work_struct *_work) struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); - if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) + if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || + READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; - - if (cma_cm_event_handler(id_priv, &work->event)) { - cma_id_put(id_priv); - destroy_id_handler_unlock(id_priv); - goto out_free; + if (work->old_state != 0 || work->new_state != 0) { + if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) + goto out_unlock; } -out_unlock: - mutex_unlock(&id_priv->handler_mutex); - cma_id_put(id_priv); -out_free: - kfree(work); -} - -static void cma_ndev_work_handler(struct work_struct *_work) -{ - struct cma_ndev_work *work = container_of(_work, struct cma_ndev_work, work); - struct rdma_id_private *id_priv = work->id; - - mutex_lock(&id_priv->handler_mutex); - if (id_priv->state == RDMA_CM_DESTROYING || - id_priv->state == RDMA_CM_DEVICE_REMOVAL) - goto out_unlock; - if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); @@ -2682,6 +2649,8 @@ out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: + if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) + rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } @@ -4295,63 +4264,66 @@ out: } EXPORT_SYMBOL(rdma_disconnect); -static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) +static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, + struct ib_sa_multicast *multicast, + struct rdma_cm_event *event, + struct cma_multicast *mc) { - struct rdma_id_private *id_priv; - struct cma_multicast *mc = multicast->context; - struct rdma_cm_event event = {}; - int ret = 0; - - id_priv = mc->id_priv; - mutex_lock(&id_priv->handler_mutex); - if (id_priv->state != RDMA_CM_ADDR_BOUND && - id_priv->state != RDMA_CM_ADDR_RESOLVED) - goto out; + struct rdma_dev_addr *dev_addr; + enum ib_gid_type gid_type; + struct net_device *ndev; if (!status) status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); else pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); - mutex_lock(&id_priv->qp_mutex); - if (!status && id_priv->id.qp) { - status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid, - be16_to_cpu(multicast->rec.mlid)); - if (status) - pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to attach QP. status %d\n", - status); + + event->status = status; + event->param.ud.private_data = mc->context; + if (status) { + event->event = RDMA_CM_EVENT_MULTICAST_ERROR; + return; } - mutex_unlock(&id_priv->qp_mutex); - event.status = status; - event.param.ud.private_data = mc->context; - if (!status) { - struct rdma_dev_addr *dev_addr = - &id_priv->id.route.addr.dev_addr; - struct net_device *ndev = - dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); - enum ib_gid_type gid_type = - id_priv->cma_dev->default_gid_type[id_priv->id.port_num - - rdma_start_port(id_priv->cma_dev->device)]; - - event.event = RDMA_CM_EVENT_MULTICAST_JOIN; - ret = ib_init_ah_from_mcmember(id_priv->id.device, - id_priv->id.port_num, - &multicast->rec, - ndev, gid_type, - &event.param.ud.ah_attr); - if (ret) - event.event = RDMA_CM_EVENT_MULTICAST_ERROR; + dev_addr = &id_priv->id.route.addr.dev_addr; + ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); + gid_type = + id_priv->cma_dev + ->default_gid_type[id_priv->id.port_num - + rdma_start_port( + id_priv->cma_dev->device)]; + + event->event = RDMA_CM_EVENT_MULTICAST_JOIN; + if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, + &multicast->rec, ndev, gid_type, + &event->param.ud.ah_attr)) { + event->event = RDMA_CM_EVENT_MULTICAST_ERROR; + goto out; + } - event.param.ud.qp_num = 0xFFFFFF; - event.param.ud.qkey = be32_to_cpu(multicast->rec.qkey); - if (ndev) - dev_put(ndev); - } else - event.event = RDMA_CM_EVENT_MULTICAST_ERROR; + event->param.ud.qp_num = 0xFFFFFF; + event->param.ud.qkey = be32_to_cpu(multicast->rec.qkey); - ret = cma_cm_event_handler(id_priv, &event); +out: + if (ndev) + dev_put(ndev); +} +static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) +{ + struct cma_multicast *mc = multicast->context; + struct rdma_id_private *id_priv = mc->id_priv; + struct rdma_cm_event event = {}; + int ret = 0; + + mutex_lock(&id_priv->handler_mutex); + if (id_priv->state != RDMA_CM_ADDR_BOUND && + id_priv->state != RDMA_CM_ADDR_RESOLVED) + goto out; + + cma_make_mc_event(status, id_priv, multicast, &event, mc); + ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { destroy_id_handler_unlock(id_priv); @@ -4441,23 +4413,10 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; - mc->multicast.ib = ib_sa_join_multicast(&sa_client, id_priv->id.device, - id_priv->id.port_num, &rec, - comp_mask, GFP_KERNEL, - cma_ib_mc_handler, mc); - return PTR_ERR_OR_ZERO(mc->multicast.ib); -} - -static void iboe_mcast_work_handler(struct work_struct *work) -{ - struct iboe_mcast_work *mw = container_of(work, struct iboe_mcast_work, work); - struct cma_multicast *mc = mw->mc; - struct ib_sa_multicast *m = mc->multicast.ib; - - mc->multicast.ib->context = mc; - cma_ib_mc_handler(0, m); - kref_put(&mc->mcref, release_mc); - kfree(mw); + mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, + id_priv->id.port_num, &rec, comp_mask, + GFP_KERNEL, cma_ib_mc_handler, mc); + return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, @@ -4492,52 +4451,47 @@ static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { - struct iboe_mcast_work *work; + struct cma_work *work; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; + struct ib_sa_multicast ib; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); - if (cma_zero_addr((struct sockaddr *)&mc->addr)) + if (cma_zero_addr(addr)) return -EINVAL; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; - mc->multicast.ib = kzalloc(sizeof(struct ib_sa_multicast), GFP_KERNEL); - if (!mc->multicast.ib) { - err = -ENOMEM; - goto out1; - } - gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; - cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid, gid_type); + cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); - mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff); + ib.rec.pkey = cpu_to_be16(0xffff); if (id_priv->id.ps == RDMA_PS_UDP) - mc->multicast.ib->rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); + ib.rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) { err = -ENODEV; - goto out2; + goto err_free; } - mc->multicast.ib->rec.rate = iboe_get_rate(ndev); - mc->multicast.ib->rec.hop_limit = 1; - mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu); + ib.rec.rate = iboe_get_rate(ndev); + ib.rec.hop_limit = 1; + ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { - mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; + ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { - err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid, + err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } @@ -4546,24 +4500,22 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, err = -ENOTSUPP; } dev_put(ndev); - if (err || !mc->multicast.ib->rec.mtu) { + if (err || !ib.rec.mtu) { if (!err) err = -EINVAL; - goto out2; + goto err_free; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, - &mc->multicast.ib->rec.port_gid); + &ib.rec.port_gid); work->id = id_priv; - work->mc = mc; - INIT_WORK(&work->work, iboe_mcast_work_handler); - kref_get(&mc->mcref); + INIT_WORK(&work->work, cma_work_handler); + cma_make_mc_event(0, id_priv, &ib, &work->event, mc); + /* Balances with cma_id_put() in cma_work_handler */ + cma_id_get(id_priv); queue_work(cma_wq, &work->work); - return 0; -out2: - kfree(mc->multicast.ib); -out1: +err_free: kfree(work); return err; } @@ -4575,6 +4527,10 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, struct cma_multicast *mc; int ret; + /* Not supported for kernel QPs */ + if (WARN_ON(id->qp)) + return -EINVAL; + if (!id->device) return -EINVAL; @@ -4583,7 +4539,7 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, !cma_comp(id_priv, RDMA_CM_ADDR_RESOLVED)) return -EINVAL; - mc = kmalloc(sizeof *mc, GFP_KERNEL); + mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; @@ -4593,7 +4549,6 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { - kref_init(&mc->mcref); ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; @@ -4625,25 +4580,14 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { - if (!memcmp(&mc->addr, addr, rdma_addr_size(addr))) { - list_del(&mc->list); - spin_unlock_irq(&id_priv->lock); - - if (id->qp) - ib_detach_mcast(id->qp, - &mc->multicast.ib->rec.mgid, - be16_to_cpu(mc->multicast.ib->rec.mlid)); - - BUG_ON(id_priv->cma_dev->device != id->device); - - if (rdma_cap_ib_mcast(id->device, id->port_num)) { - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); - } else if (rdma_protocol_roce(id->device, id->port_num)) { - cma_leave_roce_mc_group(id_priv, mc); - } - return; - } + if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) + continue; + list_del(&mc->list); + spin_unlock_irq(&id_priv->lock); + + WARN_ON(id_priv->cma_dev->device != id->device); + destroy_mc(id_priv, mc); + return; } spin_unlock_irq(&id_priv->lock); } @@ -4652,7 +4596,7 @@ EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; - struct cma_ndev_work *work; + struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; @@ -4665,7 +4609,7 @@ static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id if (!work) return -ENOMEM; - INIT_WORK(&work->work, cma_ndev_work_handler); + INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index a92fc3f90bb5..19e36e52181b 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -197,24 +197,22 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private) } /** - * __ib_alloc_cq_user - allocate a completion queue + * __ib_alloc_cq allocate a completion queue * @dev: device to allocate the CQ for * @private: driver private data, accessible from cq->cq_context * @nr_cqe: number of CQEs to allocate * @comp_vector: HCA completion vectors for this CQ * @poll_ctx: context to poll the CQ from. * @caller: module owner name. - * @udata: Valid user data or NULL for kernel object * * This is the proper interface to allocate a CQ for in-kernel users. A * CQ allocated with this interface will automatically be polled from the * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id * to use this CQ abstraction. */ -struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, - int nr_cqe, int comp_vector, - enum ib_poll_context poll_ctx, - const char *caller, struct ib_udata *udata) +struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, + int comp_vector, enum ib_poll_context poll_ctx, + const char *caller) { struct ib_cq_init_attr cq_attr = { .cqe = nr_cqe, @@ -277,7 +275,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, out_destroy_cq: rdma_dim_destroy(cq); rdma_restrack_del(&cq->res); - cq->device->ops.destroy_cq(cq, udata); + cq->device->ops.destroy_cq(cq, NULL); out_free_wc: kfree(cq->wc); out_free_cq: @@ -285,7 +283,7 @@ out_free_cq: trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret); return ERR_PTR(ret); } -EXPORT_SYMBOL(__ib_alloc_cq_user); +EXPORT_SYMBOL(__ib_alloc_cq); /** * __ib_alloc_cq_any - allocate a completion queue @@ -310,18 +308,19 @@ struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, atomic_inc_return(&counter) % min_t(int, dev->num_comp_vectors, num_online_cpus()); - return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx, - caller, NULL); + return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, + caller); } EXPORT_SYMBOL(__ib_alloc_cq_any); /** - * ib_free_cq_user - free a completion queue + * ib_free_cq - free a completion queue * @cq: completion queue to free. - * @udata: User data or NULL for kernel object */ -void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata) +void ib_free_cq(struct ib_cq *cq) { + int ret; + if (WARN_ON_ONCE(atomic_read(&cq->usecnt))) return; if (WARN_ON_ONCE(cq->cqe_used)) @@ -343,12 +342,13 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata) rdma_dim_destroy(cq); trace_cq_free(cq); + ret = cq->device->ops.destroy_cq(cq, NULL); + WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); rdma_restrack_del(&cq->res); - cq->device->ops.destroy_cq(cq, udata); kfree(cq->wc); kfree(cq); } -EXPORT_SYMBOL(ib_free_cq_user); +EXPORT_SYMBOL(ib_free_cq); void ib_cq_pool_init(struct ib_device *dev) { diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index d03dacaef788..2643d5dbe1da 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -586,6 +586,7 @@ static int ucma_free_ctx(struct ucma_context *ctx) list_move_tail(&uevent->list, &list); } list_del(&ctx->list); + events_reported = ctx->events_reported; mutex_unlock(&ctx->file->mut); list_for_each_entry_safe(uevent, tmp, &list, list) { @@ -595,7 +596,6 @@ static int ucma_free_ctx(struct ucma_context *ctx) kfree(uevent); } - events_reported = ctx->events_reported; mutex_destroy(&ctx->mutex); kfree(ctx); return events_reported; @@ -1512,7 +1512,9 @@ static ssize_t ucma_process_join(struct ucma_file *file, return 0; err3: + mutex_lock(&ctx->mutex); rdma_leave_multicast(ctx->cm_id, (struct sockaddr *) &mc->addr); + mutex_unlock(&ctx->mutex); ucma_cleanup_mc_events(mc); err2: xa_erase(&multicast_table, mc->id); @@ -1678,7 +1680,9 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, cur_file = ctx->file; if (cur_file == new_file) { + mutex_lock(&cur_file->mut); resp.events_reported = ctx->events_reported; + mutex_unlock(&cur_file->mut); goto response; } diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 82455a1392f1..7e765fe21160 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -151,13 +151,24 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, dma_addr_t mask; int i; + /* rdma_for_each_block() has a bug if the page size is smaller than the + * page size used to build the umem. For now prevent smaller page sizes + * from being returned. + */ + pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); + /* At minimum, drivers must support PAGE_SIZE or smaller */ if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0)))) return 0; va = virt; - /* max page size not to exceed MR length */ - mask = roundup_pow_of_two(umem->length); + /* The best result is the smallest page size that results in the minimum + * number of required pages. Compute the largest page size that could + * work based on VA address bits that don't change. + */ + mask = pgsz_bitmap & + GENMASK(BITS_PER_LONG - 1, + bits_per((umem->length - 1 + virt) ^ virt)); /* offset into first SGL */ pgoff = umem->address & ~PAGE_MASK; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 1b0ea945756f..2e397d18dbf4 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2016,16 +2016,21 @@ EXPORT_SYMBOL(rdma_set_cq_moderation); int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata) { + int ret; + if (WARN_ON_ONCE(cq->shared)) return -EOPNOTSUPP; if (atomic_read(&cq->usecnt)) return -EBUSY; + ret = cq->device->ops.destroy_cq(cq, udata); + if (ret) + return ret; + rdma_restrack_del(&cq->res); - cq->device->ops.destroy_cq(cq, udata); kfree(cq); - return 0; + return ret; } EXPORT_SYMBOL(ib_destroy_cq_user); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index cb6e873039df..9f69abf01d33 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2714,7 +2714,7 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr, } /* Completion Queues */ -void bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) +int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) { struct bnxt_re_cq *cq; struct bnxt_qplib_nq *nq; @@ -2730,6 +2730,7 @@ void bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) atomic_dec(&rdev->cq_count); nq->budget--; kfree(cq->cql); + return 0; } int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index e5fbbeba6d28..f4a0ded67a8a 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -193,7 +193,7 @@ int bnxt_re_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int bnxt_re_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int bnxt_re_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *pd, int mr_access_flags); diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index b1bb61c65f4f..7b076fc23cf3 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -967,7 +967,7 @@ int c4iw_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return !err || err == -ENODATA ? npolled : err; } -void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) +int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) { struct c4iw_cq *chp; struct c4iw_ucontext *ucontext; @@ -985,6 +985,7 @@ void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) ucontext ? &ucontext->uctx : &chp->cq.rdev->uctx, chp->destroy_skb, chp->wr_waitp); c4iw_put_wr_wait(chp->wr_waitp); + return 0; } int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index e8e11bd95e42..de0f278e3150 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -992,7 +992,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, struct ib_udata *udata); struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc); int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata); -void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata); +int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata); int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags); diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h index 1889dd172a25..05f593940e7b 100644 --- a/drivers/infiniband/hw/efa/efa.h +++ b/drivers/infiniband/hw/efa/efa.h @@ -139,7 +139,7 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata); struct ib_qp *efa_create_qp(struct ib_pd *ibpd, struct ib_qp_init_attr *init_attr, struct ib_udata *udata); -void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); +int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 7dd082441333..bd2caa2353c7 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -843,7 +843,7 @@ static int efa_destroy_cq_idx(struct efa_dev *dev, int cq_idx) return efa_com_destroy_cq(&dev->edev, ¶ms); } -void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct efa_dev *dev = to_edev(ibcq->device); struct efa_cq *cq = to_ecq(ibcq); @@ -856,6 +856,7 @@ void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) efa_destroy_cq_idx(dev, cq->cq_idx); efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size, DMA_FROM_DEVICE); + return 0; } static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq, diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index e87d616f7988..c5acf3332519 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -311,7 +311,7 @@ err_cq_buf: return ret; } -void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) +int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device); struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq); @@ -322,6 +322,7 @@ void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) free_cq_buf(hr_dev, hr_cq); free_cq_db(hr_dev, hr_cq, udata); free_cqc(hr_dev, hr_cq); + return 0; } void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index c69453a62767..77ca55b559a0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -929,7 +929,7 @@ struct hns_roce_hw { int (*poll_cq)(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int (*dereg_mr)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr, struct ib_udata *udata); - void (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata); + int (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*init_eq)(struct hns_roce_dev *hr_dev); void (*cleanup_eq)(struct hns_roce_dev *hr_dev); @@ -1246,7 +1246,7 @@ int to_hr_qp_type(int qp_type); int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata); +int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata); int hns_roce_db_map_user(struct hns_roce_ucontext *context, struct ib_udata *udata, unsigned long virt, struct hns_roce_db *db); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index cf39f560b800..5a0c90e0b367 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -271,7 +271,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, ps_opcode = HNS_ROCE_WQE_OPCODE_SEND; break; case IB_WR_LOCAL_INV: - break; case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_LSO: @@ -3573,7 +3572,7 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) return 0; } -static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +static int hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device); struct hns_roce_cq *hr_cq = to_hr_cq(ibcq); @@ -3604,6 +3603,7 @@ static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) } wait_time++; } + return 0; } static void set_eq_cons_index_v1(struct hns_roce_eq *eq, int req_not) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 38a48ab3e1d0..37809a0b50e2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1770,9 +1770,9 @@ static void calc_pg_sz(int obj_num, int obj_size, int hop_num, int ctx_bt_num, int *buf_page_size, int *bt_page_size, u32 hem_type) { u64 obj_per_chunk; - int bt_chunk_size = 1 << PAGE_SHIFT; - int buf_chunk_size = 1 << PAGE_SHIFT; - int obj_per_chunk_default = buf_chunk_size / obj_size; + u64 bt_chunk_size = PAGE_SIZE; + u64 buf_chunk_size = PAGE_SIZE; + u64 obj_per_chunk_default = buf_chunk_size / obj_size; *buf_page_size = 0; *bt_page_size = 0; @@ -3640,9 +3640,6 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp, V2_QPC_BYTE_76_SRQ_EN_S, 1); } - roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_ACK_REQ_FREQ_M, - V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 4); - roce_set_bit(context->byte_172_sq_psn, V2_QPC_BYTE_172_FRE_S, 1); hr_qp->access_flags = attr->qp_access_flags; @@ -3983,6 +3980,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, dma_addr_t trrl_ba; dma_addr_t irrl_ba; enum ib_mtu mtu; + u8 lp_pktn_ini; u8 port_num; u64 *mtts; u8 *dmac; @@ -4090,13 +4088,21 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, } #define MAX_LP_MSG_LEN 65536 - /* MTU*(2^LP_PKTN_INI) shouldn't be bigger than 64kb */ + /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */ + lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / ib_mtu_enum_to_int(mtu)); + roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, - V2_QPC_BYTE_56_LP_PKTN_INI_S, - ilog2(MAX_LP_MSG_LEN / ib_mtu_enum_to_int(mtu))); + V2_QPC_BYTE_56_LP_PKTN_INI_S, lp_pktn_ini); roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, V2_QPC_BYTE_56_LP_PKTN_INI_S, 0); + /* ACK_REQ_FREQ should be larger than or equal to LP_PKTN_INI */ + roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_ACK_REQ_FREQ_M, + V2_QPC_BYTE_172_ACK_REQ_FREQ_S, lp_pktn_ini); + roce_set_field(qpc_mask->byte_172_sq_psn, + V2_QPC_BYTE_172_ACK_REQ_FREQ_M, + V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 0); + roce_set_bit(qpc_mask->byte_108_rx_reqepsn, V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S, 0); roce_set_field(qpc_mask->byte_96_rx_reqmsn, V2_QPC_BYTE_96_RX_REQ_MSN_M, @@ -4287,11 +4293,19 @@ static int hns_roce_v2_set_path(struct ib_qp *ibqp, V2_QPC_BYTE_28_FL_S, 0); memcpy(context->dgid, grh->dgid.raw, sizeof(grh->dgid.raw)); memset(qpc_mask->dgid, 0, sizeof(grh->dgid.raw)); + + hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); + if (unlikely(hr_qp->sl > MAX_SERVICE_LEVEL)) { + ibdev_err(ibdev, + "failed to fill QPC, sl (%d) shouldn't be larger than %d.\n", + hr_qp->sl, MAX_SERVICE_LEVEL); + return -EINVAL; + } + roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, - V2_QPC_BYTE_28_SL_S, rdma_ah_get_sl(&attr->ah_attr)); + V2_QPC_BYTE_28_SL_S, hr_qp->sl); roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_SL_M, V2_QPC_BYTE_28_SL_S, 0); - hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr); return 0; } @@ -4787,7 +4801,9 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn, V2_QPC_BYTE_212_RETRY_CNT_M, V2_QPC_BYTE_212_RETRY_CNT_S); - qp_attr->rnr_retry = le32_to_cpu(context.rq_rnr_timer); + qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack, + V2_QPC_BYTE_244_RNR_CNT_M, + V2_QPC_BYTE_244_RNR_CNT_S); done: qp_attr->cur_qp_state = qp_attr->qp_state; @@ -4803,6 +4819,7 @@ done: } qp_init_attr->cap = qp_attr->cap; + qp_init_attr->sq_sig_type = hr_qp->sq_signal_bits; out: mutex_unlock(&hr_qp->mutex); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 4f840997c6c7..c6a280bdbfaa 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -1957,6 +1957,8 @@ struct hns_roce_eq_context { #define HNS_ROCE_V2_AEQE_EVENT_QUEUE_NUM_S 0 #define HNS_ROCE_V2_AEQE_EVENT_QUEUE_NUM_M GENMASK(23, 0) +#define MAX_SERVICE_LEVEL 0x7 + struct hns_roce_wqe_atomic_seg { __le64 fetchadd_swap_data; __le64 cmp_data; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 4edea397b6b8..4486c9b7c3e4 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -1171,8 +1171,10 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, mutex_lock(&hr_qp->mutex); - cur_state = attr_mask & IB_QP_CUR_STATE ? - attr->cur_qp_state : (enum ib_qp_state)hr_qp->state; + if (attr_mask & IB_QP_CUR_STATE && attr->cur_qp_state != hr_qp->state) + goto out; + + cur_state = hr_qp->state; new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state; if (ibqp->uobject && diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 49d92638e0db..9a2b87cc3d30 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -409,8 +409,8 @@ static inline struct i40iw_qp *to_iwqp(struct ib_qp *ibqp) } /* i40iw.c */ -void i40iw_add_ref(struct ib_qp *); -void i40iw_rem_ref(struct ib_qp *); +void i40iw_qp_add_ref(struct ib_qp *ibqp); +void i40iw_qp_rem_ref(struct ib_qp *ibqp); struct ib_qp *i40iw_get_qp(struct ib_device *, int); void i40iw_flush_wqes(struct i40iw_device *iwdev, @@ -554,9 +554,8 @@ enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev, bool wait); void i40iw_receive_ilq(struct i40iw_sc_vsi *vsi, struct i40iw_puda_buf *rbuf); void i40iw_free_sqbuf(struct i40iw_sc_vsi *vsi, void *bufp); -void i40iw_free_qp_resources(struct i40iw_device *iwdev, - struct i40iw_qp *iwqp, - u32 qp_num); +void i40iw_free_qp_resources(struct i40iw_qp *iwqp); + enum i40iw_status_code i40iw_obj_aligned_mem(struct i40iw_device *iwdev, struct i40iw_dma_mem *memptr, u32 size, u32 mask); diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index fa7a5ff498c7..56c1e9abc52d 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -2322,7 +2322,7 @@ static void i40iw_rem_ref_cm_node(struct i40iw_cm_node *cm_node) iwqp = cm_node->iwqp; if (iwqp) { iwqp->cm_node = NULL; - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); cm_node->iwqp = NULL; } else if (cm_node->qhash_set) { i40iw_get_addr_info(cm_node, &nfo); @@ -3452,7 +3452,7 @@ void i40iw_cm_disconn(struct i40iw_qp *iwqp) kfree(work); return; } - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); spin_unlock_irqrestore(&iwdev->qptable_lock, flags); work->iwqp = iwqp; @@ -3623,7 +3623,7 @@ static void i40iw_disconnect_worker(struct work_struct *work) kfree(dwork); i40iw_cm_disconn_true(iwqp); - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** @@ -3745,7 +3745,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_node->lsmm_size = accept.size + conn_param->private_data_len; i40iw_cm_init_tsa_conn(iwqp, cm_node); cm_id->add_ref(cm_id); - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); attr.qp_state = IB_QPS_RTS; cm_node->qhash_set = false; @@ -3908,7 +3908,7 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) iwqp->cm_node = cm_node; cm_node->iwqp = iwqp; iwqp->cm_id = cm_id; - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); if (cm_node->state != I40IW_CM_STATE_OFFLOADED) { cm_node->state = I40IW_CM_STATE_SYN_SENT; diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index ae8b97c30665..a7512508f7e6 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -313,7 +313,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) __func__, info->qp_cq_id); continue; } - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); spin_unlock_irqrestore(&iwdev->qptable_lock, flags); qp = &iwqp->sc_qp; spin_lock_irqsave(&iwqp->lock, flags); @@ -427,7 +427,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) break; } if (info->qp) - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } while (1); if (aeqcnt) diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 016524683e17..72db7c1dc299 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -480,25 +480,6 @@ void i40iw_cleanup_pending_cqp_op(struct i40iw_device *iwdev) } /** - * i40iw_free_qp - callback after destroy cqp completes - * @cqp_request: cqp request for destroy qp - * @num: not used - */ -static void i40iw_free_qp(struct i40iw_cqp_request *cqp_request, u32 num) -{ - struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)cqp_request->param; - struct i40iw_qp *iwqp = (struct i40iw_qp *)qp->back_qp; - struct i40iw_device *iwdev; - u32 qp_num = iwqp->ibqp.qp_num; - - iwdev = iwqp->iwdev; - - i40iw_rem_pdusecount(iwqp->iwpd, iwdev); - i40iw_free_qp_resources(iwdev, iwqp, qp_num); - i40iw_rem_devusecount(iwdev); -} - -/** * i40iw_wait_event - wait for completion * @iwdev: iwarp device * @cqp_request: cqp request to wait @@ -618,26 +599,23 @@ void i40iw_rem_pdusecount(struct i40iw_pd *iwpd, struct i40iw_device *iwdev) } /** - * i40iw_add_ref - add refcount for qp + * i40iw_qp_add_ref - add refcount for qp * @ibqp: iqarp qp */ -void i40iw_add_ref(struct ib_qp *ibqp) +void i40iw_qp_add_ref(struct ib_qp *ibqp) { struct i40iw_qp *iwqp = (struct i40iw_qp *)ibqp; - atomic_inc(&iwqp->refcount); + refcount_inc(&iwqp->refcount); } /** - * i40iw_rem_ref - rem refcount for qp and free if 0 + * i40iw_qp_rem_ref - rem refcount for qp and free if 0 * @ibqp: iqarp qp */ -void i40iw_rem_ref(struct ib_qp *ibqp) +void i40iw_qp_rem_ref(struct ib_qp *ibqp) { struct i40iw_qp *iwqp; - enum i40iw_status_code status; - struct i40iw_cqp_request *cqp_request; - struct cqp_commands_info *cqp_info; struct i40iw_device *iwdev; u32 qp_num; unsigned long flags; @@ -645,7 +623,7 @@ void i40iw_rem_ref(struct ib_qp *ibqp) iwqp = to_iwqp(ibqp); iwdev = iwqp->iwdev; spin_lock_irqsave(&iwdev->qptable_lock, flags); - if (!atomic_dec_and_test(&iwqp->refcount)) { + if (!refcount_dec_and_test(&iwqp->refcount)) { spin_unlock_irqrestore(&iwdev->qptable_lock, flags); return; } @@ -653,25 +631,8 @@ void i40iw_rem_ref(struct ib_qp *ibqp) qp_num = iwqp->ibqp.qp_num; iwdev->qp_table[qp_num] = NULL; spin_unlock_irqrestore(&iwdev->qptable_lock, flags); - cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false); - if (!cqp_request) - return; - - cqp_request->callback_fcn = i40iw_free_qp; - cqp_request->param = (void *)&iwqp->sc_qp; - cqp_info = &cqp_request->info; - cqp_info->cqp_cmd = OP_QP_DESTROY; - cqp_info->post_sq = 1; - cqp_info->in.u.qp_destroy.qp = &iwqp->sc_qp; - cqp_info->in.u.qp_destroy.scratch = (uintptr_t)cqp_request; - cqp_info->in.u.qp_destroy.remove_hash_idx = true; - status = i40iw_handle_cqp_op(iwdev, cqp_request); - if (!status) - return; + complete(&iwqp->free_qp); - i40iw_rem_pdusecount(iwqp->iwpd, iwdev); - i40iw_free_qp_resources(iwdev, iwqp, qp_num); - i40iw_rem_devusecount(iwdev); } /** @@ -938,7 +899,7 @@ static void i40iw_terminate_timeout(struct timer_list *t) struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)&iwqp->sc_qp; i40iw_terminate_done(qp, 1); - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** @@ -950,7 +911,7 @@ void i40iw_terminate_start_timer(struct i40iw_sc_qp *qp) struct i40iw_qp *iwqp; iwqp = (struct i40iw_qp *)qp->back_qp; - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); timer_setup(&iwqp->terminate_timer, i40iw_terminate_timeout, 0); iwqp->terminate_timer.expires = jiffies + HZ; add_timer(&iwqp->terminate_timer); @@ -966,7 +927,7 @@ void i40iw_terminate_del_timer(struct i40iw_sc_qp *qp) iwqp = (struct i40iw_qp *)qp->back_qp; if (del_timer(&iwqp->terminate_timer)) - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 19af29a48c55..2419de36e943 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -364,11 +364,11 @@ static struct i40iw_pbl *i40iw_get_pbl(unsigned long va, * @iwqp: qp ptr (user or kernel) * @qp_num: qp number assigned */ -void i40iw_free_qp_resources(struct i40iw_device *iwdev, - struct i40iw_qp *iwqp, - u32 qp_num) +void i40iw_free_qp_resources(struct i40iw_qp *iwqp) { struct i40iw_pbl *iwpbl = &iwqp->iwpbl; + struct i40iw_device *iwdev = iwqp->iwdev; + u32 qp_num = iwqp->ibqp.qp_num; i40iw_ieq_cleanup_qp(iwdev->vsi.ieq, &iwqp->sc_qp); i40iw_dealloc_push_page(iwdev, &iwqp->sc_qp); @@ -402,6 +402,10 @@ static void i40iw_clean_cqes(struct i40iw_qp *iwqp, struct i40iw_cq *iwcq) static int i40iw_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) { struct i40iw_qp *iwqp = to_iwqp(ibqp); + struct ib_qp_attr attr; + struct i40iw_device *iwdev = iwqp->iwdev; + + memset(&attr, 0, sizeof(attr)); iwqp->destroyed = 1; @@ -416,7 +420,15 @@ static int i40iw_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) } } - i40iw_rem_ref(&iwqp->ibqp); + attr.qp_state = IB_QPS_ERR; + i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL); + i40iw_qp_rem_ref(&iwqp->ibqp); + wait_for_completion(&iwqp->free_qp); + i40iw_cqp_qp_destroy_cmd(&iwdev->sc_dev, &iwqp->sc_qp); + i40iw_rem_pdusecount(iwqp->iwpd, iwdev); + i40iw_free_qp_resources(iwqp); + i40iw_rem_devusecount(iwdev); + return 0; } @@ -577,6 +589,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, qp->back_qp = (void *)iwqp; qp->push_idx = I40IW_INVALID_PUSH_PAGE_INDEX; + iwqp->iwdev = iwdev; iwqp->ctx_info.iwarp_info = &iwqp->iwarp_info; if (i40iw_allocate_dma_mem(dev->hw, @@ -601,7 +614,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, goto error; } - iwqp->iwdev = iwdev; iwqp->iwpd = iwpd; iwqp->ibqp.qp_num = qp_num; qp = &iwqp->sc_qp; @@ -715,7 +727,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, goto error; } - i40iw_add_ref(&iwqp->ibqp); + refcount_set(&iwqp->refcount, 1); spin_lock_init(&iwqp->lock); iwqp->sig_all = (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) ? 1 : 0; iwdev->qp_table[qp_num] = iwqp; @@ -737,10 +749,11 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, } init_completion(&iwqp->sq_drained); init_completion(&iwqp->rq_drained); + init_completion(&iwqp->free_qp); return &iwqp->ibqp; error: - i40iw_free_qp_resources(iwdev, iwqp, qp_num); + i40iw_free_qp_resources(iwqp); return ERR_PTR(err_code); } @@ -1053,7 +1066,7 @@ void i40iw_cq_wq_destroy(struct i40iw_device *iwdev, struct i40iw_sc_cq *cq) * @ib_cq: cq pointer * @udata: user data or NULL for kernel object */ -static void i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) +static int i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) { struct i40iw_cq *iwcq; struct i40iw_device *iwdev; @@ -1065,6 +1078,7 @@ static void i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata) i40iw_cq_wq_destroy(iwdev, cq); cq_free_resources(iwdev, iwcq); i40iw_rem_devusecount(iwdev); + return 0; } /** @@ -2656,13 +2670,13 @@ static const struct ib_device_ops i40iw_dev_ops = { .get_hw_stats = i40iw_get_hw_stats, .get_port_immutable = i40iw_port_immutable, .iw_accept = i40iw_accept, - .iw_add_ref = i40iw_add_ref, + .iw_add_ref = i40iw_qp_add_ref, .iw_connect = i40iw_connect, .iw_create_listen = i40iw_create_listen, .iw_destroy_listen = i40iw_destroy_listen, .iw_get_qp = i40iw_get_qp, .iw_reject = i40iw_reject, - .iw_rem_ref = i40iw_rem_ref, + .iw_rem_ref = i40iw_qp_rem_ref, .map_mr_sg = i40iw_map_mr_sg, .mmap = i40iw_mmap, .modify_qp = i40iw_modify_qp, diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.h b/drivers/infiniband/hw/i40iw/i40iw_verbs.h index 331bc21cbcc7..bab71f3e5637 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.h +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.h @@ -139,7 +139,7 @@ struct i40iw_qp { struct i40iw_qp_host_ctx_info ctx_info; struct i40iwarp_offload_info iwarp_info; void *allocated_buffer; - atomic_t refcount; + refcount_t refcount; struct iw_cm_id *cm_id; void *cm_node; struct ib_mr *lsmm_mr; @@ -174,5 +174,6 @@ struct i40iw_qp { struct i40iw_dma_mem ietf_mem; struct completion sq_drained; struct completion rq_drained; + struct completion free_qp; }; #endif diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c index b591861934b3..81d6a3460b55 100644 --- a/drivers/infiniband/hw/mlx4/cm.c +++ b/drivers/infiniband/hw/mlx4/cm.c @@ -280,6 +280,9 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id) if (!sriov->is_going_down && !id->scheduled_delete) { id->scheduled_delete = 1; schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT); + } else if (id->scheduled_delete) { + /* Adjust timeout if already scheduled */ + mod_delayed_work(system_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT); } spin_unlock_irqrestore(&sriov->going_down_lock, flags); spin_unlock(&sriov->id_map_lock); diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index f8b936b76dcd..3851316407ce 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -475,7 +475,7 @@ out: return err; } -void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { struct mlx4_ib_dev *dev = to_mdev(cq->device); struct mlx4_ib_cq *mcq = to_mcq(cq); @@ -495,6 +495,7 @@ void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) mlx4_db_free(dev->dev, &mcq->db); } ib_umem_release(mcq->umem); + return 0; } static void dump_cqe(void *cqe) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index abe68708d6d6..2cbdba4da9df 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -1299,6 +1299,18 @@ static void mlx4_ib_tunnel_comp_handler(struct ib_cq *cq, void *arg) spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); } +static void mlx4_ib_wire_comp_handler(struct ib_cq *cq, void *arg) +{ + unsigned long flags; + struct mlx4_ib_demux_pv_ctx *ctx = cq->cq_context; + struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev); + + spin_lock_irqsave(&dev->sriov.going_down_lock, flags); + if (!dev->sriov.is_going_down && ctx->state == DEMUX_PV_STATE_ACTIVE) + queue_work(ctx->wi_wq, &ctx->work); + spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); +} + static int mlx4_ib_post_pv_qp_buf(struct mlx4_ib_demux_pv_ctx *ctx, struct mlx4_ib_demux_pv_qp *tun_qp, int index) @@ -2001,7 +2013,8 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port, cq_size *= 2; cq_attr.cqe = cq_size; - ctx->cq = ib_create_cq(ctx->ib_dev, mlx4_ib_tunnel_comp_handler, + ctx->cq = ib_create_cq(ctx->ib_dev, + create_tun ? mlx4_ib_tunnel_comp_handler : mlx4_ib_wire_comp_handler, NULL, ctx, &cq_attr); if (IS_ERR(ctx->cq)) { ret = PTR_ERR(ctx->cq); @@ -2038,6 +2051,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port, INIT_WORK(&ctx->work, mlx4_ib_sqp_comp_worker); ctx->wq = to_mdev(ibdev)->sriov.demux[port - 1].wq; + ctx->wi_wq = to_mdev(ibdev)->sriov.demux[port - 1].wi_wq; ret = ib_req_notify_cq(ctx->cq, IB_CQ_NEXT_COMP); if (ret) { @@ -2181,7 +2195,7 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev, goto err_mcg; } - snprintf(name, sizeof name, "mlx4_ibt%d", port); + snprintf(name, sizeof(name), "mlx4_ibt%d", port); ctx->wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM); if (!ctx->wq) { pr_err("Failed to create tunnelling WQ for port %d\n", port); @@ -2189,7 +2203,15 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev, goto err_wq; } - snprintf(name, sizeof name, "mlx4_ibud%d", port); + snprintf(name, sizeof(name), "mlx4_ibwi%d", port); + ctx->wi_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM); + if (!ctx->wi_wq) { + pr_err("Failed to create wire WQ for port %d\n", port); + ret = -ENOMEM; + goto err_wiwq; + } + + snprintf(name, sizeof(name), "mlx4_ibud%d", port); ctx->ud_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM); if (!ctx->ud_wq) { pr_err("Failed to create up/down WQ for port %d\n", port); @@ -2200,6 +2222,10 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev, return 0; err_udwq: + destroy_workqueue(ctx->wi_wq); + ctx->wi_wq = NULL; + +err_wiwq: destroy_workqueue(ctx->wq); ctx->wq = NULL; @@ -2247,12 +2273,14 @@ static void mlx4_ib_free_demux_ctx(struct mlx4_ib_demux_ctx *ctx) ctx->tun[i]->state = DEMUX_PV_STATE_DOWNING; } flush_workqueue(ctx->wq); + flush_workqueue(ctx->wi_wq); for (i = 0; i < dev->dev->caps.sqp_demux; i++) { destroy_pv_resources(dev, i, ctx->port, ctx->tun[i], 0); free_pv_object(dev, i, ctx->port); } kfree(ctx->tun); destroy_workqueue(ctx->ud_wq); + destroy_workqueue(ctx->wi_wq); destroy_workqueue(ctx->wq); } } diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6f4ea1067095..bac526a70317 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -454,6 +454,7 @@ struct mlx4_ib_demux_pv_ctx { struct ib_pd *pd; struct work_struct work; struct workqueue_struct *wq; + struct workqueue_struct *wi_wq; struct mlx4_ib_demux_pv_qp qp[2]; }; @@ -461,6 +462,7 @@ struct mlx4_ib_demux_ctx { struct ib_device *ib_dev; int port; struct workqueue_struct *wq; + struct workqueue_struct *wi_wq; struct workqueue_struct *ud_wq; spinlock_t ud_lock; atomic64_t subnet_prefix; @@ -736,7 +738,7 @@ int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period); int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata); int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 0c18cb6a2f14..ec634085e1d9 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -168,7 +168,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, { enum rdma_link_layer ll = rdma_port_get_link_layer(qp->ibqp.device, 1); struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device); - struct mlx5_ib_srq *srq; + struct mlx5_ib_srq *srq = NULL; struct mlx5_ib_wq *wq; u16 wqe_ctr; u8 roce_packet_type; @@ -180,7 +180,8 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, if (qp->ibqp.xrcd) { msrq = mlx5_cmd_get_srq(dev, be32_to_cpu(cqe->srqn)); - srq = to_mibsrq(msrq); + if (msrq) + srq = to_mibsrq(msrq); } else { srq = to_msrq(qp->ibqp.srq); } @@ -1023,16 +1024,21 @@ err_cqb: return err; } -void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(cq->device); struct mlx5_ib_cq *mcq = to_mcq(cq); + int ret; + + ret = mlx5_core_destroy_cq(dev->mdev, &mcq->mcq); + if (ret) + return ret; - mlx5_core_destroy_cq(dev->mdev, &mcq->mcq); if (udata) destroy_cq_user(mcq, udata); else destroy_cq_kernel(dev, mcq); + return 0; } static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 6f99ed03d88e..1f4aa2647a6f 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -867,7 +867,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, /* We support 'Gappy' memory registration too */ props->device_cap_flags |= IB_DEVICE_SG_GAPS_REG; } - props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; + /* IB_WR_REG_MR always requires changing the entity size with UMR */ + if (!MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled)) + props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; if (MLX5_CAP_GEN(mdev, sho)) { props->device_cap_flags |= IB_DEVICE_INTEGRITY_HANDOVER; /* At this stage no support for signature handover */ diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 5dbe3eb0d9cb..3825cdec6ac6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1180,7 +1180,7 @@ int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer, size_t buflen, size_t *bc); int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags); int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 44683073be0c..85c9a1ffdbb6 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -50,6 +50,29 @@ enum { static void create_mkey_callback(int status, struct mlx5_async_work *context); +static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, + struct ib_pd *pd) +{ + struct mlx5_ib_dev *dev = to_mdev(pd->device); + + MLX5_SET(mkc, mkc, a, !!(acc & IB_ACCESS_REMOTE_ATOMIC)); + MLX5_SET(mkc, mkc, rw, !!(acc & IB_ACCESS_REMOTE_WRITE)); + MLX5_SET(mkc, mkc, rr, !!(acc & IB_ACCESS_REMOTE_READ)); + MLX5_SET(mkc, mkc, lw, !!(acc & IB_ACCESS_LOCAL_WRITE)); + MLX5_SET(mkc, mkc, lr, 1); + + if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) + MLX5_SET(mkc, mkc, relaxed_ordering_write, + !!(acc & IB_ACCESS_RELAXED_ORDERING)); + if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read)) + MLX5_SET(mkc, mkc, relaxed_ordering_read, + !!(acc & IB_ACCESS_RELAXED_ORDERING)); + + MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET64(mkc, mkc, start_addr, start_addr); +} + static void assign_mkey_variant(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, u32 *in) @@ -152,12 +175,12 @@ static struct mlx5_ib_mr *alloc_cache_mr(struct mlx5_cache_ent *ent, void *mkc) mr->cache_ent = ent; mr->dev = ent->dev; + set_mkc_access_pd_addr_fields(mkc, 0, 0, ent->dev->umrc.pd); MLX5_SET(mkc, mkc, free, 1); MLX5_SET(mkc, mkc, umr_en, 1); MLX5_SET(mkc, mkc, access_mode_1_0, ent->access_mode & 0x3); MLX5_SET(mkc, mkc, access_mode_4_2, (ent->access_mode >> 2) & 0x7); - MLX5_SET(mkc, mkc, qpn, 0xffffff); MLX5_SET(mkc, mkc, translations_octword_size, ent->xlt); MLX5_SET(mkc, mkc, log_page_size, ent->page); return mr; @@ -774,29 +797,6 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) return 0; } -static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, - struct ib_pd *pd) -{ - struct mlx5_ib_dev *dev = to_mdev(pd->device); - - MLX5_SET(mkc, mkc, a, !!(acc & IB_ACCESS_REMOTE_ATOMIC)); - MLX5_SET(mkc, mkc, rw, !!(acc & IB_ACCESS_REMOTE_WRITE)); - MLX5_SET(mkc, mkc, rr, !!(acc & IB_ACCESS_REMOTE_READ)); - MLX5_SET(mkc, mkc, lw, !!(acc & IB_ACCESS_LOCAL_WRITE)); - MLX5_SET(mkc, mkc, lr, 1); - - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) - MLX5_SET(mkc, mkc, relaxed_ordering_write, - !!(acc & IB_ACCESS_RELAXED_ORDERING)); - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read)) - MLX5_SET(mkc, mkc, relaxed_ordering_read, - !!(acc & IB_ACCESS_RELAXED_ORDERING)); - - MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); - MLX5_SET(mkc, mkc, qpn, 0xffffff); - MLX5_SET64(mkc, mkc, start_addr, start_addr); -} - struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc) { struct mlx5_ib_dev *dev = to_mdev(pd->device); @@ -1190,29 +1190,17 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd, MLX5_SET(create_mkey_in, in, pg_access, !!(pg_cap)); mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + set_mkc_access_pd_addr_fields(mkc, access_flags, virt_addr, + populate ? pd : dev->umrc.pd); MLX5_SET(mkc, mkc, free, !populate); MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT); - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) - MLX5_SET(mkc, mkc, relaxed_ordering_write, - !!(access_flags & IB_ACCESS_RELAXED_ORDERING)); - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read)) - MLX5_SET(mkc, mkc, relaxed_ordering_read, - !!(access_flags & IB_ACCESS_RELAXED_ORDERING)); - MLX5_SET(mkc, mkc, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC)); - MLX5_SET(mkc, mkc, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE)); - MLX5_SET(mkc, mkc, rr, !!(access_flags & IB_ACCESS_REMOTE_READ)); - MLX5_SET(mkc, mkc, lw, !!(access_flags & IB_ACCESS_LOCAL_WRITE)); - MLX5_SET(mkc, mkc, lr, 1); MLX5_SET(mkc, mkc, umr_en, 1); - MLX5_SET64(mkc, mkc, start_addr, virt_addr); MLX5_SET64(mkc, mkc, len, length); - MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); MLX5_SET(mkc, mkc, bsf_octword_size, 0); MLX5_SET(mkc, mkc, translations_octword_size, get_octo_len(virt_addr, length, page_shift)); MLX5_SET(mkc, mkc, log_page_size, page_shift); - MLX5_SET(mkc, mkc, qpn, 0xffffff); if (populate) { MLX5_SET(create_mkey_in, in, translations_octword_actual_size, get_octo_len(virt_addr, length, page_shift)); diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 9fa2f9164a47..2ad15adf304e 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -789,7 +789,7 @@ out: return ret; } -static void mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +static int mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { if (udata) { struct mthca_ucontext *context = @@ -808,6 +808,7 @@ static void mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) to_mcq(cq)->set_ci_db_index); } mthca_free_cq(to_mdev(cq->device), to_mcq(cq)); + return 0; } static inline u32 convert_access(int acc) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index d11c74390a12..927c70d1ffbc 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -1056,7 +1056,7 @@ static void ocrdma_flush_cq(struct ocrdma_cq *cq) spin_unlock_irqrestore(&cq->cq_lock, flags); } -void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +int ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct ocrdma_cq *cq = get_ocrdma_cq(ibcq); struct ocrdma_eq *eq = NULL; @@ -1081,6 +1081,7 @@ void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) ocrdma_get_db_addr(dev, pdid), dev->nic_info.db_page_size); } + return 0; } static int ocrdma_add_qpn_map(struct ocrdma_dev *dev, struct ocrdma_qp *qp) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h index 3a5010881be5..c46412dff924 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h @@ -72,7 +72,7 @@ void ocrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata); int ocrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *); -void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); +int ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); struct ib_qp *ocrdma_create_qp(struct ib_pd *, struct ib_qp_init_attr *attrs, diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index ccaedfd53e49..679766abb436 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -601,7 +601,7 @@ static int qedr_set_device_attr(struct qedr_dev *dev) qed_attr = dev->ops->rdma_query_device(dev->rdma_ctx); /* Part 2 - check capabilities */ - page_size = ~dev->attr.page_size_caps + 1; + page_size = ~qed_attr->page_size_caps + 1; if (page_size > PAGE_SIZE) { DP_ERR(dev, "Kernel PAGE_SIZE is %ld which is smaller than minimum page size (%d) required by qedr\n", diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 97fc7dd353b0..c7169d2c69e5 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -736,7 +736,7 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) struct qedr_dev *dev = ep->dev; struct qedr_qp *qp; struct qed_iwarp_accept_in params; - int rc = 0; + int rc; DP_DEBUG(dev, QEDR_MSG_IWARP, "Accept on qpid=%d\n", conn_param->qpn); @@ -759,8 +759,10 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) params.ord = conn_param->ord; if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_CONNECT, - &qp->iwarp_cm_flags)) + &qp->iwarp_cm_flags)) { + rc = -EINVAL; goto err; /* QP already destroyed */ + } rc = dev->ops->iwarp_accept(dev->rdma_ctx, ¶ms); if (rc) { diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 1a7f1f805be3..41813e9d771f 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -998,7 +998,7 @@ int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, /* Generate doorbell address. */ cq->db.data.icid = cq->icid; cq->db_addr = dev->db_addr + db_offset; - cq->db.data.params = DB_AGG_CMD_SET << + cq->db.data.params = DB_AGG_CMD_MAX << RDMA_PWM_VAL32_DATA_AGG_CMD_SHIFT; /* point to the very last element, passing it we will toggle */ @@ -1050,7 +1050,7 @@ int qedr_resize_cq(struct ib_cq *ibcq, int new_cnt, struct ib_udata *udata) #define QEDR_DESTROY_CQ_MAX_ITERATIONS (10) #define QEDR_DESTROY_CQ_ITER_DURATION (10) -void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +int qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct qedr_dev *dev = get_qedr_dev(ibcq->device); struct qed_rdma_destroy_cq_out_params oparams; @@ -1065,7 +1065,7 @@ void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) /* GSIs CQs are handled by driver, so they don't exist in the FW */ if (cq->cq_type == QEDR_CQ_TYPE_GSI) { qedr_db_recovery_del(dev, cq->db_addr, &cq->db.data); - return; + return 0; } iparams.icid = cq->icid; @@ -1113,6 +1113,7 @@ void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) * Since the destroy CQ ramrod has also been received on the EQ we can * be certain that there's no event handler in process. */ + return 0; } static inline int get_gid_info_from_table(struct ib_qp *ibqp, @@ -2112,6 +2113,28 @@ static int qedr_create_kernel_qp(struct qedr_dev *dev, return rc; } +static int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp, + struct ib_udata *udata) +{ + struct qedr_ucontext *ctx = + rdma_udata_to_drv_context(udata, struct qedr_ucontext, + ibucontext); + int rc; + + if (qp->qp_type != IB_QPT_GSI) { + rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp); + if (rc) + return rc; + } + + if (qp->create_type == QEDR_QP_CREATE_USER) + qedr_cleanup_user(dev, ctx, qp); + else + qedr_cleanup_kernel(dev, qp); + + return 0; +} + struct ib_qp *qedr_create_qp(struct ib_pd *ibpd, struct ib_qp_init_attr *attrs, struct ib_udata *udata) @@ -2158,19 +2181,21 @@ struct ib_qp *qedr_create_qp(struct ib_pd *ibpd, rc = qedr_create_kernel_qp(dev, qp, ibpd, attrs); if (rc) - goto err; + goto out_free_qp; qp->ibqp.qp_num = qp->qp_id; if (rdma_protocol_iwarp(&dev->ibdev, 1)) { rc = xa_insert(&dev->qps, qp->qp_id, qp, GFP_KERNEL); if (rc) - goto err; + goto out_free_qp_resources; } return &qp->ibqp; -err: +out_free_qp_resources: + qedr_free_qp_resources(dev, qp, udata); +out_free_qp: kfree(qp); return ERR_PTR(-EFAULT); @@ -2636,7 +2661,7 @@ int qedr_query_qp(struct ib_qp *ibqp, qp_attr->cap.max_recv_wr = qp->rq.max_wr; qp_attr->cap.max_send_sge = qp->sq.max_sges; qp_attr->cap.max_recv_sge = qp->rq.max_sges; - qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE; + qp_attr->cap.max_inline_data = dev->attr.max_inline; qp_init_attr->cap = qp_attr->cap; qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; @@ -2671,28 +2696,6 @@ err: return rc; } -static int qedr_free_qp_resources(struct qedr_dev *dev, struct qedr_qp *qp, - struct ib_udata *udata) -{ - struct qedr_ucontext *ctx = - rdma_udata_to_drv_context(udata, struct qedr_ucontext, - ibucontext); - int rc; - - if (qp->qp_type != IB_QPT_GSI) { - rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp); - if (rc) - return rc; - } - - if (qp->create_type == QEDR_QP_CREATE_USER) - qedr_cleanup_user(dev, ctx, qp); - else - qedr_cleanup_kernel(dev, qp); - - return 0; -} - int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) { struct qedr_qp *qp = get_qedr_qp(ibqp); @@ -2752,6 +2755,8 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) if (rdma_protocol_iwarp(&dev->ibdev, 1)) qedr_iw_qp_rem_ref(&qp->ibqp); + else + kfree(qp); return 0; } diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h index 5e02387e068d..e0db3bc1653e 100644 --- a/drivers/infiniband/hw/qedr/verbs.h +++ b/drivers/infiniband/hw/qedr/verbs.h @@ -52,7 +52,7 @@ void qedr_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata); int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int qedr_resize_cq(struct ib_cq *, int cqe, struct ib_udata *); -void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); +int qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags); struct ib_qp *qedr_create_qp(struct ib_pd *, struct ib_qp_init_attr *attrs, struct ib_udata *); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index b8a77ce11590..586ff16be1bb 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -596,9 +596,9 @@ int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, return 0; } -void usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { - return; + return 0; } struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length, diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h index 2aedf78c13cf..f13b08c59b9a 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h @@ -60,7 +60,7 @@ int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int access_flags, struct ib_udata *udata); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index 4f6cc0de7ef9..6d3e6389e47d 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -235,7 +235,7 @@ static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq) * @cq: the completion queue to destroy. * @udata: user data or null for kernel object */ -void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { struct pvrdma_cq *vcq = to_vcq(cq); union pvrdma_cmd_req req; @@ -261,6 +261,7 @@ void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) pvrdma_free_cq(dev, vcq); atomic_dec(&dev->num_cqs); + return 0; } static inline struct pvrdma_cqe *get_cqe(struct pvrdma_cq *cq, int i) diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h index 267702226f10..af36e9f767ee 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h @@ -411,7 +411,7 @@ int pvrdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int pvrdma_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); int pvrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c index 04d2e72017fe..19248be14093 100644 --- a/drivers/infiniband/sw/rdmavt/cq.c +++ b/drivers/infiniband/sw/rdmavt/cq.c @@ -315,7 +315,7 @@ bail_wc: * * Called by ib_destroy_cq() in the generic verbs code. */ -void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +int rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct rvt_cq *cq = ibcq_to_rvtcq(ibcq); struct rvt_dev_info *rdi = cq->rdi; @@ -328,6 +328,7 @@ void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) kref_put(&cq->ip->ref, rvt_release_mmap_info); else vfree(cq->kqueue); + return 0; } /** diff --git a/drivers/infiniband/sw/rdmavt/cq.h b/drivers/infiniband/sw/rdmavt/cq.h index 5e26a2eb19a4..feb01e7ee004 100644 --- a/drivers/infiniband/sw/rdmavt/cq.h +++ b/drivers/infiniband/sw/rdmavt/cq.h @@ -53,7 +53,7 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); -void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); +int rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata); int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags); int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata); int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry); diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index f904bb34477a..2d534c450f3c 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -95,9 +95,7 @@ struct rvt_dev_info *rvt_alloc_device(size_t size, int nports) if (!rdi) return rdi; - rdi->ports = kcalloc(nports, - sizeof(struct rvt_ibport **), - GFP_KERNEL); + rdi->ports = kcalloc(nports, sizeof(*rdi->ports), GFP_KERNEL); if (!rdi->ports) ib_dealloc_device(&rdi->ibdev); diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 46e111c218fd..9bfb98056fc2 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -281,6 +281,8 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb) struct rxe_mc_elem *mce; struct rxe_qp *qp; union ib_gid dgid; + struct sk_buff *per_qp_skb; + struct rxe_pkt_info *per_qp_pkt; int err; if (skb->protocol == htons(ETH_P_IP)) @@ -309,21 +311,29 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb) if (err) continue; - /* if *not* the last qp in the list - * increase the users of the skb then post to the next qp + /* for all but the last qp create a new clone of the + * skb and pass to the qp. */ if (mce->qp_list.next != &mcg->qp_list) - skb_get(skb); + per_qp_skb = skb_clone(skb, GFP_ATOMIC); + else + per_qp_skb = skb; + + if (unlikely(!per_qp_skb)) + continue; - pkt->qp = qp; + per_qp_pkt = SKB_TO_PKT(per_qp_skb); + per_qp_pkt->qp = qp; rxe_add_ref(qp); - rxe_rcv_pkt(pkt, skb); + rxe_rcv_pkt(per_qp_pkt, per_qp_skb); } spin_unlock_bh(&mcg->mcg_lock); rxe_drop_ref(mcg); /* drop ref from rxe_pool_get_key. */ + return; + err1: kfree_skb(skb); } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 00ba6fb1e676..452748b3854b 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -816,13 +816,14 @@ static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, return rxe_add_to_pool(&rxe->cq_pool, &cq->pelem); } -static void rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) { struct rxe_cq *cq = to_rcq(ibcq); rxe_cq_disable(cq); rxe_drop_ref(cq); + return 0; } static int rxe_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata) diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 987e2ba05dbc..7e657f90ca4f 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -1064,7 +1064,7 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr, return rv > 0 ? 0 : rv; } -void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata) +int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata) { struct siw_cq *cq = to_siw_cq(base_cq); struct siw_device *sdev = to_siw_dev(base_cq->device); @@ -1082,6 +1082,7 @@ void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata) atomic_dec(&sdev->num_cq); vfree(cq->queue); + return 0; } /* diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h index 1a731989fad6..b0b748886910 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.h +++ b/drivers/infiniband/sw/siw/siw_verbs.h @@ -63,7 +63,7 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr); int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr); -void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata); +int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata); int siw_poll_cq(struct ib_cq *base_cq, int num_entries, struct ib_wc *wc); int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags); struct ib_mr *siw_reg_user_mr(struct ib_pd *base_pd, u64 start, u64 len, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index ef60e8e4ae67..7c0bb2642d23 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2470,6 +2470,8 @@ static struct net_device *ipoib_add_port(const char *format, /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); + ndev->rtnl_link_ops = ipoib_get_link_ops(); + result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 38c984d16996..d5a90a66b45c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -144,6 +144,16 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, return 0; } +static void ipoib_del_child_link(struct net_device *dev, struct list_head *head) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + if (!priv->parent) + return; + + unregister_netdevice_queue(dev, head); +} + static size_t ipoib_get_size(const struct net_device *dev) { return nla_total_size(2) + /* IFLA_IPOIB_PKEY */ @@ -158,6 +168,7 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .priv_size = sizeof(struct ipoib_dev_priv), .setup = ipoib_setup_common, .newlink = ipoib_new_child_link, + .dellink = ipoib_del_child_link, .changelink = ipoib_changelink, .get_size = ipoib_get_size, .fill_info = ipoib_fill_info, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 30865605e098..4c50a87ed7cc 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -195,6 +195,8 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) } priv = ipoib_priv(ndev); + ndev->rtnl_link_ops = ipoib_get_link_ops(); + result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD); if (result && ndev->reg_state == NETREG_UNINITIALIZED) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 28f6414dfa3d..d6f93601712e 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -16,6 +16,7 @@ #include "rtrs-srv.h" #include "rtrs-log.h" #include <rdma/ib_cm.h> +#include <rdma/ib_verbs.h> MODULE_DESCRIPTION("RDMA Transport Server"); MODULE_LICENSE("GPL"); @@ -31,6 +32,7 @@ MODULE_LICENSE("GPL"); static struct rtrs_rdma_dev_pd dev_pd; static mempool_t *chunk_pool; struct class *rtrs_dev_class; +static struct rtrs_srv_ib_ctx ib_ctx; static int __read_mostly max_chunk_size = DEFAULT_MAX_CHUNK_SIZE; static int __read_mostly sess_queue_depth = DEFAULT_SESS_QUEUE_DEPTH; @@ -2042,6 +2044,70 @@ static void free_srv_ctx(struct rtrs_srv_ctx *ctx) kfree(ctx); } +static int rtrs_srv_add_one(struct ib_device *device) +{ + struct rtrs_srv_ctx *ctx; + int ret = 0; + + mutex_lock(&ib_ctx.ib_dev_mutex); + if (ib_ctx.ib_dev_count) + goto out; + + /* + * Since our CM IDs are NOT bound to any ib device we will create them + * only once + */ + ctx = ib_ctx.srv_ctx; + ret = rtrs_srv_rdma_init(ctx, ib_ctx.port); + if (ret) { + /* + * We errored out here. + * According to the ib code, if we encounter an error here then the + * error code is ignored, and no more calls to our ops are made. + */ + pr_err("Failed to initialize RDMA connection"); + goto err_out; + } + +out: + /* + * Keep a track on the number of ib devices added + */ + ib_ctx.ib_dev_count++; + +err_out: + mutex_unlock(&ib_ctx.ib_dev_mutex); + return ret; +} + +static void rtrs_srv_remove_one(struct ib_device *device, void *client_data) +{ + struct rtrs_srv_ctx *ctx; + + mutex_lock(&ib_ctx.ib_dev_mutex); + ib_ctx.ib_dev_count--; + + if (ib_ctx.ib_dev_count) + goto out; + + /* + * Since our CM IDs are NOT bound to any ib device we will remove them + * only once, when the last device is removed + */ + ctx = ib_ctx.srv_ctx; + rdma_destroy_id(ctx->cm_id_ip); + rdma_destroy_id(ctx->cm_id_ib); + +out: + mutex_unlock(&ib_ctx.ib_dev_mutex); +} + +static struct ib_client rtrs_srv_client = { + .name = "rtrs_server", + .add = rtrs_srv_add_one, + .remove = rtrs_srv_remove_one +}; + /** * rtrs_srv_open() - open RTRS server context * @ops: callback functions @@ -2060,7 +2126,11 @@ struct rtrs_srv_ctx *rtrs_srv_open(struct rtrs_srv_ops *ops, u16 port) if (!ctx) return ERR_PTR(-ENOMEM); - err = rtrs_srv_rdma_init(ctx, port); + mutex_init(&ib_ctx.ib_dev_mutex); + ib_ctx.srv_ctx = ctx; + ib_ctx.port = port; + + err = ib_register_client(&rtrs_srv_client); if (err) { free_srv_ctx(ctx); return ERR_PTR(err); @@ -2099,8 +2169,8 @@ static void close_ctx(struct rtrs_srv_ctx *ctx) */ void rtrs_srv_close(struct rtrs_srv_ctx *ctx) { - rdma_destroy_id(ctx->cm_id_ip); - rdma_destroy_id(ctx->cm_id_ib); + ib_unregister_client(&rtrs_srv_client); + mutex_destroy(&ib_ctx.ib_dev_mutex); close_ctx(ctx); free_srv_ctx(ctx); } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.h b/drivers/infiniband/ulp/rtrs/rtrs-srv.h index dc95b0932f0d..08b0b8a6eebe 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.h +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.h @@ -118,6 +118,13 @@ struct rtrs_srv_ctx { struct list_head srv_list; }; +struct rtrs_srv_ib_ctx { + struct rtrs_srv_ctx *srv_ctx; + u16 port; + struct mutex ib_dev_mutex; + int ib_dev_count; +}; + extern struct class *rtrs_dev_class; void close_sess(struct rtrs_srv_sess *sess); diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c index 7c70492d9d6b..f831f01501d5 100644 --- a/drivers/input/keyboard/ep93xx_keypad.c +++ b/drivers/input/keyboard/ep93xx_keypad.c @@ -250,8 +250,8 @@ static int ep93xx_keypad_probe(struct platform_device *pdev) } keypad->irq = platform_get_irq(pdev, 0); - if (!keypad->irq) { - err = -ENXIO; + if (keypad->irq < 0) { + err = keypad->irq; goto failed_free; } diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 94c94d7f5155..d6c924032aaa 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -240,10 +240,8 @@ static int omap4_keypad_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (!irq) { - dev_err(&pdev->dev, "no keyboard irq assigned\n"); - return -EINVAL; - } + if (irq < 0) + return irq; keypad_data = kzalloc(sizeof(struct omap4_keypad), GFP_KERNEL); if (!keypad_data) { diff --git a/drivers/input/keyboard/twl4030_keypad.c b/drivers/input/keyboard/twl4030_keypad.c index af3a6824f1a4..77e0743a3cf8 100644 --- a/drivers/input/keyboard/twl4030_keypad.c +++ b/drivers/input/keyboard/twl4030_keypad.c @@ -50,7 +50,7 @@ struct twl4030_keypad { bool autorepeat; unsigned int n_rows; unsigned int n_cols; - unsigned int irq; + int irq; struct device *dbg_dev; struct input_dev *input; @@ -376,10 +376,8 @@ static int twl4030_kp_probe(struct platform_device *pdev) } kp->irq = platform_get_irq(pdev, 0); - if (!kp->irq) { - dev_err(&pdev->dev, "no keyboard irq assigned\n"); - return -EINVAL; - } + if (kp->irq < 0) + return kp->irq; error = matrix_keypad_build_keymap(keymap_data, NULL, TWL4030_MAX_ROWS, diff --git a/drivers/input/serio/sun4i-ps2.c b/drivers/input/serio/sun4i-ps2.c index a681a2c04e39..f15ed3dcdb9b 100644 --- a/drivers/input/serio/sun4i-ps2.c +++ b/drivers/input/serio/sun4i-ps2.c @@ -211,7 +211,6 @@ static int sun4i_ps2_probe(struct platform_device *pdev) struct sun4i_ps2data *drvdata; struct serio *serio; struct device *dev = &pdev->dev; - unsigned int irq; int error; drvdata = kzalloc(sizeof(struct sun4i_ps2data), GFP_KERNEL); @@ -264,14 +263,12 @@ static int sun4i_ps2_probe(struct platform_device *pdev) writel(0, drvdata->reg_base + PS2_REG_GCTL); /* Get IRQ for the device */ - irq = platform_get_irq(pdev, 0); - if (!irq) { - dev_err(dev, "no IRQ found\n"); - error = -ENXIO; + drvdata->irq = platform_get_irq(pdev, 0); + if (drvdata->irq < 0) { + error = drvdata->irq; goto err_disable_clk; } - drvdata->irq = irq; drvdata->serio = serio; drvdata->dev = dev; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 5477a5718202..db7f27d4734a 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -90,7 +90,7 @@ /* FW read command, 0x53 0x?? 0x0, 0x01 */ #define E_ELAN_INFO_FW_VER 0x00 #define E_ELAN_INFO_BC_VER 0x10 -#define E_ELAN_INFO_REK 0xE0 +#define E_ELAN_INFO_REK 0xD0 #define E_ELAN_INFO_TEST_VER 0xE0 #define E_ELAN_INFO_FW_ID 0xF0 #define E_INFO_OSR 0xD6 diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c index 9ed258854349..5e6ba5c4eca2 100644 --- a/drivers/input/touchscreen/imx6ul_tsc.c +++ b/drivers/input/touchscreen/imx6ul_tsc.c @@ -530,20 +530,25 @@ static int __maybe_unused imx6ul_tsc_resume(struct device *dev) mutex_lock(&input_dev->mutex); - if (input_dev->users) { - retval = clk_prepare_enable(tsc->adc_clk); - if (retval) - goto out; - - retval = clk_prepare_enable(tsc->tsc_clk); - if (retval) { - clk_disable_unprepare(tsc->adc_clk); - goto out; - } + if (!input_dev->users) + goto out; - retval = imx6ul_tsc_init(tsc); + retval = clk_prepare_enable(tsc->adc_clk); + if (retval) + goto out; + + retval = clk_prepare_enable(tsc->tsc_clk); + if (retval) { + clk_disable_unprepare(tsc->adc_clk); + goto out; } + retval = imx6ul_tsc_init(tsc); + if (retval) { + clk_disable_unprepare(tsc->tsc_clk); + clk_disable_unprepare(tsc->adc_clk); + goto out; + } out: mutex_unlock(&input_dev->mutex); return retval; diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index b54cc64e4ea6..389356332c54 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -479,7 +479,7 @@ static ssize_t stmfts_sysfs_hover_enable_write(struct device *dev, mutex_lock(&sdata->mutex); - if (value & sdata->hover_enabled) + if (value && sdata->hover_enabled) goto out; if (sdata->running) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index d176df569af8..78d813bd0dcc 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -578,8 +578,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) * index into qcom_iommu->ctxs: */ if (WARN_ON(asid < 1) || - WARN_ON(asid > qcom_iommu->num_ctxs)) + WARN_ON(asid > qcom_iommu->num_ctxs)) { + put_device(&iommu_pdev->dev); return -EINVAL; + } if (!dev_iommu_priv_get(dev)) { dev_iommu_priv_set(dev, qcom_iommu); @@ -588,8 +590,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) * multiple different iommu devices. Multiple context * banks are ok, but multiple devices are not: */ - if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) + if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) { + put_device(&iommu_pdev->dev); return -EINVAL; + } } return iommu_fwspec_add_ids(dev, &asid, 1); diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index db38a68abb6c..a6f4ca438bca 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -1315,8 +1315,9 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg) strlcpy(info->bmname, "gennvm", sizeof(info->bmname)); i++; - if (i > 31) { - pr_err("max 31 devices can be reported.\n"); + if (i >= ARRAY_SIZE(devices->info)) { + pr_err("max %zd devices can be reported.\n", + ARRAY_SIZE(devices->info)); break; } } diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 0b821a5b2db8..3e7d4b20ab34 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -82,9 +82,12 @@ static void msg_submit(struct mbox_chan *chan) exit: spin_unlock_irqrestore(&chan->lock, flags); - if (!err && (chan->txdone_method & TXDONE_BY_POLL)) - /* kick start the timer immediately to avoid delays */ - hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL); + /* kick start the timer immediately to avoid delays */ + if (!err && (chan->txdone_method & TXDONE_BY_POLL)) { + /* but only if not already active */ + if (!hrtimer_active(&chan->mbox->poll_hrt)) + hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL); + } } static void tx_tick(struct mbox_chan *chan, int r) @@ -122,11 +125,10 @@ static enum hrtimer_restart txdone_hrtimer(struct hrtimer *hrtimer) struct mbox_chan *chan = &mbox->chans[i]; if (chan->active_req && chan->cl) { + resched = true; txdone = chan->mbox->ops->last_tx_done(chan); if (txdone) tx_tick(chan, 0); - else - resched = true; } } diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index b24822ad8409..9963bb9cd74f 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -69,7 +69,7 @@ struct cmdq_task { struct cmdq { struct mbox_controller mbox; void __iomem *base; - u32 irq; + int irq; u32 thread_nr; u32 irq_mask; struct cmdq_thread *thread; @@ -466,10 +466,8 @@ static int cmdq_probe(struct platform_device *pdev) } cmdq->irq = platform_get_irq(pdev, 0); - if (!cmdq->irq) { - dev_err(dev, "failed to get irq\n"); - return -EINVAL; - } + if (cmdq->irq < 0) + return cmdq->irq; cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev); cmdq->irq_mask = GENMASK(cmdq->thread_nr - 1, 0); diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 1533419f1875..de467a1303db 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -49,7 +49,7 @@ do { \ #define pmem_assign(dest, src) ((dest) = (src)) #endif -#if defined(__HAVE_ARCH_MEMCPY_MCSAFE) && defined(DM_WRITECACHE_HAS_PMEM) +#if IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC) && defined(DM_WRITECACHE_HAS_PMEM) #define DM_WRITECACHE_HANDLE_HARDWARE_ERRORS #endif @@ -992,7 +992,8 @@ static void writecache_resume(struct dm_target *ti) } wc->freelist_size = 0; - r = memcpy_mcsafe(&sb_seq_count, &sb(wc)->seq_count, sizeof(uint64_t)); + r = copy_mc_to_kernel(&sb_seq_count, &sb(wc)->seq_count, + sizeof(uint64_t)); if (r) { writecache_error(wc, r, "hardware memory error when reading superblock: %d", r); sb_seq_count = cpu_to_le64(0); @@ -1008,7 +1009,8 @@ static void writecache_resume(struct dm_target *ti) e->seq_count = -1; continue; } - r = memcpy_mcsafe(&wme, memory_entry(wc, e), sizeof(struct wc_memory_entry)); + r = copy_mc_to_kernel(&wme, memory_entry(wc, e), + sizeof(struct wc_memory_entry)); if (r) { writecache_error(wc, r, "hardware memory error when reading metadata entry %lu: %d", (unsigned long)b, r); @@ -1206,7 +1208,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data if (rw == READ) { int r; - r = memcpy_mcsafe(buf, data, size); + r = copy_mc_to_kernel(buf, data, size); flush_dcache_page(bio_page(bio)); if (unlikely(r)) { writecache_error(wc, r, "hardware memory error when reading data: %d", r); @@ -2349,7 +2351,7 @@ invalid_optional: } } - r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock)); + r = copy_mc_to_kernel(&s, sb(wc), sizeof(struct wc_memory_superblock)); if (r) { ti->error = "Hardware memory error when reading superblock"; goto bad; @@ -2360,7 +2362,8 @@ invalid_optional: ti->error = "Unable to initialize device"; goto bad; } - r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock)); + r = copy_mc_to_kernel(&s, sb(wc), + sizeof(struct wc_memory_superblock)); if (r) { ti->error = "Hardware memory error when reading superblock"; goto bad; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 95a5f3757fa3..19b2601be3c5 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1949,6 +1949,7 @@ out: } EXPORT_SYMBOL_GPL(md_bitmap_load); +/* caller need to free returned bitmap with md_bitmap_free() */ struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot) { int rv = 0; @@ -2012,6 +2013,7 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot, md_bitmap_unplug(mddev->bitmap); *low = lo; *high = hi; + md_bitmap_free(bitmap); return rv; } @@ -2615,4 +2617,3 @@ struct attribute_group md_bitmap_group = { .name = "bitmap", .attrs = md_bitmap_attrs, }; - diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index d50737ec4039..afbbc552c327 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1166,6 +1166,7 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz * can't resize bitmap */ goto out; + md_bitmap_free(bitmap); } return 0; diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c index 3f1ca40b9b98..8a8585261bb8 100644 --- a/drivers/media/firewire/firedtv-fw.c +++ b/drivers/media/firewire/firedtv-fw.c @@ -272,8 +272,10 @@ static int node_probe(struct fw_unit *unit, const struct ieee1394_device_id *id) name_len = fw_csr_string(unit->directory, CSR_MODEL, name, sizeof(name)); - if (name_len < 0) - return name_len; + if (name_len < 0) { + err = name_len; + goto fail_free; + } for (i = ARRAY_SIZE(model_names); --i; ) if (strlen(model_names[i]) <= name_len && strncmp(name, model_names[i], name_len) == 0) diff --git a/drivers/media/i2c/m5mols/m5mols_core.c b/drivers/media/i2c/m5mols/m5mols_core.c index de295114ca48..21666d705e37 100644 --- a/drivers/media/i2c/m5mols/m5mols_core.c +++ b/drivers/media/i2c/m5mols/m5mols_core.c @@ -764,7 +764,8 @@ static int m5mols_sensor_power(struct m5mols_info *info, bool enable) ret = regulator_bulk_enable(ARRAY_SIZE(supplies), supplies); if (ret) { - info->set_power(&client->dev, 0); + if (info->set_power) + info->set_power(&client->dev, 0); return ret; } diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c index 2fe4a7ac0592..3a4268aa5f02 100644 --- a/drivers/media/i2c/ov5640.c +++ b/drivers/media/i2c/ov5640.c @@ -34,6 +34,8 @@ #define OV5640_REG_SYS_RESET02 0x3002 #define OV5640_REG_SYS_CLOCK_ENABLE02 0x3006 #define OV5640_REG_SYS_CTRL0 0x3008 +#define OV5640_REG_SYS_CTRL0_SW_PWDN 0x42 +#define OV5640_REG_SYS_CTRL0_SW_PWUP 0x02 #define OV5640_REG_CHIP_ID 0x300a #define OV5640_REG_IO_MIPI_CTRL00 0x300e #define OV5640_REG_PAD_OUTPUT_ENABLE01 0x3017 @@ -274,8 +276,7 @@ static inline struct v4l2_subdev *ctrl_to_sd(struct v4l2_ctrl *ctrl) /* YUV422 UYVY VGA@30fps */ static const struct reg_value ov5640_init_setting_30fps_VGA[] = { {0x3103, 0x11, 0, 0}, {0x3008, 0x82, 0, 5}, {0x3008, 0x42, 0, 0}, - {0x3103, 0x03, 0, 0}, {0x3017, 0x00, 0, 0}, {0x3018, 0x00, 0, 0}, - {0x3630, 0x36, 0, 0}, + {0x3103, 0x03, 0, 0}, {0x3630, 0x36, 0, 0}, {0x3631, 0x0e, 0, 0}, {0x3632, 0xe2, 0, 0}, {0x3633, 0x12, 0, 0}, {0x3621, 0xe0, 0, 0}, {0x3704, 0xa0, 0, 0}, {0x3703, 0x5a, 0, 0}, {0x3715, 0x78, 0, 0}, {0x3717, 0x01, 0, 0}, {0x370b, 0x60, 0, 0}, @@ -751,7 +752,7 @@ static int ov5640_mod_reg(struct ov5640_dev *sensor, u16 reg, * +->| PLL Root Div | - reg 0x3037, bit 4 * +-+------------+ * | +---------+ - * +->| Bit Div | - reg 0x3035, bits 0-3 + * +->| Bit Div | - reg 0x3034, bits 0-3 * +-+-------+ * | +-------------+ * +->| SCLK Div | - reg 0x3108, bits 0-1 @@ -1120,6 +1121,12 @@ static int ov5640_load_regs(struct ov5640_dev *sensor, val = regs->val; mask = regs->mask; + /* remain in power down mode for DVP */ + if (regs->reg_addr == OV5640_REG_SYS_CTRL0 && + val == OV5640_REG_SYS_CTRL0_SW_PWUP && + sensor->ep.bus_type != V4L2_MBUS_CSI2_DPHY) + continue; + if (mask) ret = ov5640_mod_reg(sensor, reg_addr, mask, val); else @@ -1275,31 +1282,9 @@ static int ov5640_set_stream_dvp(struct ov5640_dev *sensor, bool on) if (ret) return ret; - /* - * enable VSYNC/HREF/PCLK DVP control lines - * & D[9:6] DVP data lines - * - * PAD OUTPUT ENABLE 01 - * - 6: VSYNC output enable - * - 5: HREF output enable - * - 4: PCLK output enable - * - [3:0]: D[9:6] output enable - */ - ret = ov5640_write_reg(sensor, - OV5640_REG_PAD_OUTPUT_ENABLE01, - on ? 0x7f : 0); - if (ret) - return ret; - - /* - * enable D[5:0] DVP data lines - * - * PAD OUTPUT ENABLE 02 - * - [7:2]: D[5:0] output enable - */ - return ov5640_write_reg(sensor, - OV5640_REG_PAD_OUTPUT_ENABLE02, - on ? 0xfc : 0); + return ov5640_write_reg(sensor, OV5640_REG_SYS_CTRL0, on ? + OV5640_REG_SYS_CTRL0_SW_PWUP : + OV5640_REG_SYS_CTRL0_SW_PWDN); } static int ov5640_set_stream_mipi(struct ov5640_dev *sensor, bool on) @@ -2001,6 +1986,95 @@ static void ov5640_set_power_off(struct ov5640_dev *sensor) clk_disable_unprepare(sensor->xclk); } +static int ov5640_set_power_mipi(struct ov5640_dev *sensor, bool on) +{ + int ret; + + if (!on) { + /* Reset MIPI bus settings to their default values. */ + ov5640_write_reg(sensor, OV5640_REG_IO_MIPI_CTRL00, 0x58); + ov5640_write_reg(sensor, OV5640_REG_MIPI_CTRL00, 0x04); + ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT00, 0x00); + return 0; + } + + /* + * Power up MIPI HS Tx and LS Rx; 2 data lanes mode + * + * 0x300e = 0x40 + * [7:5] = 010 : 2 data lanes mode (see FIXME note in + * "ov5640_set_stream_mipi()") + * [4] = 0 : Power up MIPI HS Tx + * [3] = 0 : Power up MIPI LS Rx + * [2] = 0 : MIPI interface disabled + */ + ret = ov5640_write_reg(sensor, OV5640_REG_IO_MIPI_CTRL00, 0x40); + if (ret) + return ret; + + /* + * Gate clock and set LP11 in 'no packets mode' (idle) + * + * 0x4800 = 0x24 + * [5] = 1 : Gate clock when 'no packets' + * [2] = 1 : MIPI bus in LP11 when 'no packets' + */ + ret = ov5640_write_reg(sensor, OV5640_REG_MIPI_CTRL00, 0x24); + if (ret) + return ret; + + /* + * Set data lanes and clock in LP11 when 'sleeping' + * + * 0x3019 = 0x70 + * [6] = 1 : MIPI data lane 2 in LP11 when 'sleeping' + * [5] = 1 : MIPI data lane 1 in LP11 when 'sleeping' + * [4] = 1 : MIPI clock lane in LP11 when 'sleeping' + */ + ret = ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT00, 0x70); + if (ret) + return ret; + + /* Give lanes some time to coax into LP11 state. */ + usleep_range(500, 1000); + + return 0; +} + +static int ov5640_set_power_dvp(struct ov5640_dev *sensor, bool on) +{ + int ret; + + if (!on) { + /* Reset settings to their default values. */ + ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT_ENABLE01, 0x00); + ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT_ENABLE02, 0x00); + return 0; + } + + /* + * enable VSYNC/HREF/PCLK DVP control lines + * & D[9:6] DVP data lines + * + * PAD OUTPUT ENABLE 01 + * - 6: VSYNC output enable + * - 5: HREF output enable + * - 4: PCLK output enable + * - [3:0]: D[9:6] output enable + */ + ret = ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT_ENABLE01, 0x7f); + if (ret) + return ret; + + /* + * enable D[5:0] DVP data lines + * + * PAD OUTPUT ENABLE 02 + * - [7:2]: D[5:0] output enable + */ + return ov5640_write_reg(sensor, OV5640_REG_PAD_OUTPUT_ENABLE02, 0xfc); +} + static int ov5640_set_power(struct ov5640_dev *sensor, bool on) { int ret = 0; @@ -2013,67 +2087,17 @@ static int ov5640_set_power(struct ov5640_dev *sensor, bool on) ret = ov5640_restore_mode(sensor); if (ret) goto power_off; + } - /* We're done here for DVP bus, while CSI-2 needs setup. */ - if (sensor->ep.bus_type != V4L2_MBUS_CSI2_DPHY) - return 0; - - /* - * Power up MIPI HS Tx and LS Rx; 2 data lanes mode - * - * 0x300e = 0x40 - * [7:5] = 010 : 2 data lanes mode (see FIXME note in - * "ov5640_set_stream_mipi()") - * [4] = 0 : Power up MIPI HS Tx - * [3] = 0 : Power up MIPI LS Rx - * [2] = 0 : MIPI interface disabled - */ - ret = ov5640_write_reg(sensor, - OV5640_REG_IO_MIPI_CTRL00, 0x40); - if (ret) - goto power_off; - - /* - * Gate clock and set LP11 in 'no packets mode' (idle) - * - * 0x4800 = 0x24 - * [5] = 1 : Gate clock when 'no packets' - * [2] = 1 : MIPI bus in LP11 when 'no packets' - */ - ret = ov5640_write_reg(sensor, - OV5640_REG_MIPI_CTRL00, 0x24); - if (ret) - goto power_off; - - /* - * Set data lanes and clock in LP11 when 'sleeping' - * - * 0x3019 = 0x70 - * [6] = 1 : MIPI data lane 2 in LP11 when 'sleeping' - * [5] = 1 : MIPI data lane 1 in LP11 when 'sleeping' - * [4] = 1 : MIPI clock lane in LP11 when 'sleeping' - */ - ret = ov5640_write_reg(sensor, - OV5640_REG_PAD_OUTPUT00, 0x70); - if (ret) - goto power_off; - - /* Give lanes some time to coax into LP11 state. */ - usleep_range(500, 1000); - - } else { - if (sensor->ep.bus_type == V4L2_MBUS_CSI2_DPHY) { - /* Reset MIPI bus settings to their default values. */ - ov5640_write_reg(sensor, - OV5640_REG_IO_MIPI_CTRL00, 0x58); - ov5640_write_reg(sensor, - OV5640_REG_MIPI_CTRL00, 0x04); - ov5640_write_reg(sensor, - OV5640_REG_PAD_OUTPUT00, 0x00); - } + if (sensor->ep.bus_type == V4L2_MBUS_CSI2_DPHY) + ret = ov5640_set_power_mipi(sensor, on); + else + ret = ov5640_set_power_dvp(sensor, on); + if (ret) + goto power_off; + if (!on) ov5640_set_power_off(sensor); - } return 0; diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c index dbbab75f135e..cff99cf61ed4 100644 --- a/drivers/media/i2c/tc358743.c +++ b/drivers/media/i2c/tc358743.c @@ -919,8 +919,8 @@ static const struct cec_adap_ops tc358743_cec_adap_ops = { .adap_monitor_all_enable = tc358743_cec_adap_monitor_all_enable, }; -static void tc358743_cec_isr(struct v4l2_subdev *sd, u16 intstatus, - bool *handled) +static void tc358743_cec_handler(struct v4l2_subdev *sd, u16 intstatus, + bool *handled) { struct tc358743_state *state = to_state(sd); unsigned int cec_rxint, cec_txint; @@ -953,7 +953,8 @@ static void tc358743_cec_isr(struct v4l2_subdev *sd, u16 intstatus, cec_transmit_attempt_done(state->cec_adap, CEC_TX_STATUS_ERROR); } - *handled = true; + if (handled) + *handled = true; } if ((intstatus & MASK_CEC_RINT) && (cec_rxint & MASK_CECRIEND)) { @@ -968,7 +969,8 @@ static void tc358743_cec_isr(struct v4l2_subdev *sd, u16 intstatus, msg.msg[i] = v & 0xff; } cec_received_msg(state->cec_adap, &msg); - *handled = true; + if (handled) + *handled = true; } i2c_wr16(sd, INTSTATUS, intstatus & (MASK_CEC_RINT | MASK_CEC_TINT)); @@ -1432,7 +1434,7 @@ static int tc358743_isr(struct v4l2_subdev *sd, u32 status, bool *handled) #ifdef CONFIG_VIDEO_TC358743_CEC if (intstatus & (MASK_CEC_RINT | MASK_CEC_TINT)) { - tc358743_cec_isr(sd, intstatus, handled); + tc358743_cec_handler(sd, intstatus, handled); i2c_wr16(sd, INTSTATUS, intstatus & (MASK_CEC_RINT | MASK_CEC_TINT)); intstatus &= ~(MASK_CEC_RINT | MASK_CEC_TINT); @@ -1461,7 +1463,7 @@ static int tc358743_isr(struct v4l2_subdev *sd, u32 status, bool *handled) static irqreturn_t tc358743_irq_handler(int irq, void *dev_id) { struct tc358743_state *state = dev_id; - bool handled; + bool handled = false; tc358743_isr(&state->sd, 0, &handled); diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c index 9144f795fb93..b721720f9845 100644 --- a/drivers/media/pci/bt8xx/bttv-driver.c +++ b/drivers/media/pci/bt8xx/bttv-driver.c @@ -4013,11 +4013,13 @@ static int bttv_probe(struct pci_dev *dev, const struct pci_device_id *pci_id) btv->id = dev->device; if (pci_enable_device(dev)) { pr_warn("%d: Can't enable device\n", btv->c.nr); - return -EIO; + result = -EIO; + goto free_mem; } if (pci_set_dma_mask(dev, DMA_BIT_MASK(32))) { pr_warn("%d: No suitable DMA available\n", btv->c.nr); - return -EIO; + result = -EIO; + goto free_mem; } if (!request_mem_region(pci_resource_start(dev,0), pci_resource_len(dev,0), @@ -4025,7 +4027,8 @@ static int bttv_probe(struct pci_dev *dev, const struct pci_device_id *pci_id) pr_warn("%d: can't request iomem (0x%llx)\n", btv->c.nr, (unsigned long long)pci_resource_start(dev, 0)); - return -EBUSY; + result = -EBUSY; + goto free_mem; } pci_set_master(dev); pci_set_command(dev); @@ -4211,6 +4214,10 @@ fail0: release_mem_region(pci_resource_start(btv->c.pci,0), pci_resource_len(btv->c.pci,0)); pci_disable_device(btv->c.pci); + +free_mem: + bttvs[btv->c.nr] = NULL; + kfree(btv); return result; } diff --git a/drivers/media/pci/saa7134/saa7134-tvaudio.c b/drivers/media/pci/saa7134/saa7134-tvaudio.c index 79e1afb71075..5cc4ef21f9d3 100644 --- a/drivers/media/pci/saa7134/saa7134-tvaudio.c +++ b/drivers/media/pci/saa7134/saa7134-tvaudio.c @@ -683,7 +683,8 @@ int saa_dsp_writel(struct saa7134_dev *dev, int reg, u32 value) { int err; - audio_dbg(2, "dsp write reg 0x%x = 0x%06x\n", reg << 2, value); + audio_dbg(2, "dsp write reg 0x%x = 0x%06x\n", + (reg << 2) & 0xffffffff, value); err = saa_dsp_wait_bit(dev,SAA7135_DSP_RWSTATE_WRR); if (err < 0) return err; diff --git a/drivers/media/platform/exynos4-is/fimc-isp.c b/drivers/media/platform/exynos4-is/fimc-isp.c index cde0d254ec1c..a77c49b18511 100644 --- a/drivers/media/platform/exynos4-is/fimc-isp.c +++ b/drivers/media/platform/exynos4-is/fimc-isp.c @@ -305,8 +305,10 @@ static int fimc_isp_subdev_s_power(struct v4l2_subdev *sd, int on) if (on) { ret = pm_runtime_get_sync(&is->pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put(&is->pdev->dev); return ret; + } set_bit(IS_ST_PWR_ON, &is->state); ret = fimc_is_start_firmware(is); diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c index 394e0818f2d5..92130d779137 100644 --- a/drivers/media/platform/exynos4-is/fimc-lite.c +++ b/drivers/media/platform/exynos4-is/fimc-lite.c @@ -470,7 +470,7 @@ static int fimc_lite_open(struct file *file) set_bit(ST_FLITE_IN_USE, &fimc->state); ret = pm_runtime_get_sync(&fimc->pdev->dev); if (ret < 0) - goto unlock; + goto err_pm; ret = v4l2_fh_open(file); if (ret < 0) diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index 9c31d950cddf..a07d796f63df 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -484,8 +484,10 @@ static int fimc_md_register_sensor_entities(struct fimc_md *fmd) return -ENXIO; ret = pm_runtime_get_sync(fmd->pmf); - if (ret < 0) + if (ret < 0) { + pm_runtime_put(fmd->pmf); return ret; + } fmd->num_sensors = 0; @@ -1268,11 +1270,9 @@ static int fimc_md_get_pinctrl(struct fimc_md *fmd) if (IS_ERR(pctl->state_default)) return PTR_ERR(pctl->state_default); + /* PINCTRL_STATE_IDLE is optional */ pctl->state_idle = pinctrl_lookup_state(pctl->pinctrl, PINCTRL_STATE_IDLE); - if (IS_ERR(pctl->state_idle)) - return PTR_ERR(pctl->state_idle); - return 0; } diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c index 540151bbf58f..1aac167abb17 100644 --- a/drivers/media/platform/exynos4-is/mipi-csis.c +++ b/drivers/media/platform/exynos4-is/mipi-csis.c @@ -510,8 +510,10 @@ static int s5pcsis_s_stream(struct v4l2_subdev *sd, int enable) if (enable) { s5pcsis_clear_counters(state); ret = pm_runtime_get_sync(&state->pdev->dev); - if (ret && ret != 1) + if (ret && ret != 1) { + pm_runtime_put_noidle(&state->pdev->dev); return ret; + } } mutex_lock(&state->lock); diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c index df78df59da45..08a5473b5610 100644 --- a/drivers/media/platform/mx2_emmaprp.c +++ b/drivers/media/platform/mx2_emmaprp.c @@ -852,8 +852,11 @@ static int emmaprp_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pcdev); irq = platform_get_irq(pdev, 0); - if (irq < 0) - return irq; + if (irq < 0) { + ret = irq; + goto rel_vdev; + } + ret = devm_request_irq(&pdev->dev, irq, emmaprp_irq, 0, dev_name(&pdev->dev), pcdev); if (ret) diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c index b91e472ee764..de066757726d 100644 --- a/drivers/media/platform/omap3isp/isp.c +++ b/drivers/media/platform/omap3isp/isp.c @@ -2328,8 +2328,10 @@ static int isp_probe(struct platform_device *pdev) mem = platform_get_resource(pdev, IORESOURCE_MEM, i); isp->mmio_base[map_idx] = devm_ioremap_resource(isp->dev, mem); - if (IS_ERR(isp->mmio_base[map_idx])) - return PTR_ERR(isp->mmio_base[map_idx]); + if (IS_ERR(isp->mmio_base[map_idx])) { + ret = PTR_ERR(isp->mmio_base[map_idx]); + goto error; + } } ret = isp_get_clocks(isp); diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c index 008afb85023b..3c5b9082ad72 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c @@ -176,8 +176,10 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on) int ret; ret = pm_runtime_get_sync(dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_sync(dev); return ret; + } ret = csiphy_set_clock_rates(csiphy); if (ret < 0) { diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index 203c6538044f..321ad77cb6cf 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -224,13 +224,15 @@ static int venus_probe(struct platform_device *pdev) ret = dma_set_mask_and_coherent(dev, core->res->dma_mask); if (ret) - return ret; + goto err_core_put; if (!dev->dma_parms) { dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; + if (!dev->dma_parms) { + ret = -ENOMEM; + goto err_core_put; + } } dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); @@ -242,11 +244,11 @@ static int venus_probe(struct platform_device *pdev) IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "venus", core); if (ret) - return ret; + goto err_core_put; ret = hfi_create(core, &venus_core_ops); if (ret) - return ret; + goto err_core_put; pm_runtime_enable(dev); @@ -287,8 +289,10 @@ static int venus_probe(struct platform_device *pdev) goto err_core_deinit; ret = pm_runtime_put_sync(dev); - if (ret) + if (ret) { + pm_runtime_get_noresume(dev); goto err_dev_unregister; + } return 0; @@ -299,9 +303,13 @@ err_core_deinit: err_venus_shutdown: venus_shutdown(core); err_runtime_disable: + pm_runtime_put_noidle(dev); pm_runtime_set_suspended(dev); pm_runtime_disable(dev); hfi_destroy(core); +err_core_put: + if (core->pm_ops->core_put) + core->pm_ops->core_put(dev); return ret; } diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 7c4c483d5438..76be14efbfb0 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -1088,8 +1088,6 @@ static int vdec_stop_capture(struct venus_inst *inst) break; } - INIT_LIST_HEAD(&inst->registeredbufs); - return ret; } @@ -1189,6 +1187,14 @@ static int vdec_buf_init(struct vb2_buffer *vb) static void vdec_buf_cleanup(struct vb2_buffer *vb) { struct venus_inst *inst = vb2_get_drv_priv(vb->vb2_queue); + struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); + struct venus_buffer *buf = to_venus_buffer(vbuf); + + mutex_lock(&inst->lock); + if (vb->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) + if (!list_empty(&inst->registeredbufs)) + list_del_init(&buf->reg_list); + mutex_unlock(&inst->lock); inst->buf_count--; if (!inst->buf_count) diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c index 5c6b00737fe7..05c712e00a2a 100644 --- a/drivers/media/platform/rcar-fcp.c +++ b/drivers/media/platform/rcar-fcp.c @@ -103,8 +103,10 @@ int rcar_fcp_enable(struct rcar_fcp_device *fcp) return 0; ret = pm_runtime_get_sync(fcp->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(fcp->dev); return ret; + } return 0; } diff --git a/drivers/media/platform/rcar-vin/rcar-csi2.c b/drivers/media/platform/rcar-vin/rcar-csi2.c index 151e6a90c5fb..d9bc8cef7db5 100644 --- a/drivers/media/platform/rcar-vin/rcar-csi2.c +++ b/drivers/media/platform/rcar-vin/rcar-csi2.c @@ -361,7 +361,6 @@ struct rcar_csi2 { struct media_pad pads[NR_OF_RCAR_CSI2_PAD]; struct v4l2_async_notifier notifier; - struct v4l2_async_subdev asd; struct v4l2_subdev *remote; struct v4l2_mbus_framefmt mf; @@ -810,6 +809,8 @@ static int rcsi2_parse_v4l2(struct rcar_csi2 *priv, static int rcsi2_parse_dt(struct rcar_csi2 *priv) { + struct v4l2_async_subdev *asd; + struct fwnode_handle *fwnode; struct device_node *ep; struct v4l2_fwnode_endpoint v4l2_ep = { .bus_type = 0 }; int ret; @@ -833,24 +834,19 @@ static int rcsi2_parse_dt(struct rcar_csi2 *priv) return ret; } - priv->asd.match.fwnode = - fwnode_graph_get_remote_endpoint(of_fwnode_handle(ep)); - priv->asd.match_type = V4L2_ASYNC_MATCH_FWNODE; - + fwnode = fwnode_graph_get_remote_endpoint(of_fwnode_handle(ep)); of_node_put(ep); - v4l2_async_notifier_init(&priv->notifier); - - ret = v4l2_async_notifier_add_subdev(&priv->notifier, &priv->asd); - if (ret) { - fwnode_handle_put(priv->asd.match.fwnode); - return ret; - } + dev_dbg(priv->dev, "Found '%pOF'\n", to_of_node(fwnode)); + v4l2_async_notifier_init(&priv->notifier); priv->notifier.ops = &rcar_csi2_notify_ops; - dev_dbg(priv->dev, "Found '%pOF'\n", - to_of_node(priv->asd.match.fwnode)); + asd = v4l2_async_notifier_add_fwnode_subdev(&priv->notifier, fwnode, + sizeof(*asd)); + fwnode_handle_put(fwnode); + if (IS_ERR(asd)) + return PTR_ERR(asd); ret = v4l2_async_subdev_notifier_register(&priv->subdev, &priv->notifier); diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c index 1a30cd036371..95bc9e0e8792 100644 --- a/drivers/media/platform/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/rcar-vin/rcar-dma.c @@ -1392,8 +1392,10 @@ int rvin_set_channel_routing(struct rvin_dev *vin, u8 chsel) int ret; ret = pm_runtime_get_sync(vin->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(vin->dev); return ret; + } /* Make register writes take effect immediately. */ vnmc = rvin_read(vin, VNMC_REG); diff --git a/drivers/media/platform/rcar_drif.c b/drivers/media/platform/rcar_drif.c index 3d2451ac347d..f318cd4b8086 100644 --- a/drivers/media/platform/rcar_drif.c +++ b/drivers/media/platform/rcar_drif.c @@ -185,7 +185,6 @@ struct rcar_drif_frame_buf { /* OF graph endpoint's V4L2 async data */ struct rcar_drif_graph_ep { struct v4l2_subdev *subdev; /* Async matched subdev */ - struct v4l2_async_subdev asd; /* Async sub-device descriptor */ }; /* DMA buffer */ @@ -1109,12 +1108,6 @@ static int rcar_drif_notify_bound(struct v4l2_async_notifier *notifier, struct rcar_drif_sdr *sdr = container_of(notifier, struct rcar_drif_sdr, notifier); - if (sdr->ep.asd.match.fwnode != - of_fwnode_handle(subdev->dev->of_node)) { - rdrif_err(sdr, "subdev %s cannot bind\n", subdev->name); - return -EINVAL; - } - v4l2_set_subdev_hostdata(subdev, sdr); sdr->ep.subdev = subdev; rdrif_dbg(sdr, "bound asd %s\n", subdev->name); @@ -1218,7 +1211,7 @@ static int rcar_drif_parse_subdevs(struct rcar_drif_sdr *sdr) { struct v4l2_async_notifier *notifier = &sdr->notifier; struct fwnode_handle *fwnode, *ep; - int ret; + struct v4l2_async_subdev *asd; v4l2_async_notifier_init(notifier); @@ -1227,26 +1220,21 @@ static int rcar_drif_parse_subdevs(struct rcar_drif_sdr *sdr) if (!ep) return 0; + /* Get the endpoint properties */ + rcar_drif_get_ep_properties(sdr, ep); + fwnode = fwnode_graph_get_remote_port_parent(ep); + fwnode_handle_put(ep); if (!fwnode) { dev_warn(sdr->dev, "bad remote port parent\n"); - fwnode_handle_put(ep); return -EINVAL; } - sdr->ep.asd.match.fwnode = fwnode; - sdr->ep.asd.match_type = V4L2_ASYNC_MATCH_FWNODE; - ret = v4l2_async_notifier_add_subdev(notifier, &sdr->ep.asd); - if (ret) { - fwnode_handle_put(fwnode); - return ret; - } - - /* Get the endpoint properties */ - rcar_drif_get_ep_properties(sdr, ep); - + asd = v4l2_async_notifier_add_fwnode_subdev(notifier, fwnode, + sizeof(*asd)); fwnode_handle_put(fwnode); - fwnode_handle_put(ep); + if (IS_ERR(asd)) + return PTR_ERR(asd); return 0; } diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c index 36b821ccc1db..bf9a75b75083 100644 --- a/drivers/media/platform/rockchip/rga/rga-buf.c +++ b/drivers/media/platform/rockchip/rga/rga-buf.c @@ -81,6 +81,7 @@ static int rga_buf_start_streaming(struct vb2_queue *q, unsigned int count) ret = pm_runtime_get_sync(rga->dev); if (ret < 0) { + pm_runtime_put_noidle(rga->dev); rga_buf_return_buffers(q, VB2_BUF_STATE_QUEUED); return ret; } diff --git a/drivers/media/platform/s3c-camif/camif-core.c b/drivers/media/platform/s3c-camif/camif-core.c index c6fbcd7036d6..ee624804862e 100644 --- a/drivers/media/platform/s3c-camif/camif-core.c +++ b/drivers/media/platform/s3c-camif/camif-core.c @@ -464,7 +464,7 @@ static int s3c_camif_probe(struct platform_device *pdev) ret = camif_media_dev_init(camif); if (ret < 0) - goto err_alloc; + goto err_pm; ret = camif_register_sensor(camif); if (ret < 0) @@ -498,10 +498,9 @@ err_sens: media_device_unregister(&camif->media_dev); media_device_cleanup(&camif->media_dev); camif_unregister_media_entities(camif); -err_alloc: +err_pm: pm_runtime_put(dev); pm_runtime_disable(dev); -err_pm: camif_clk_put(camif); err_clk: s3c_camif_unregister_subdev(camif); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c index 7d52431c2c83..62d2320a7218 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c @@ -79,8 +79,10 @@ int s5p_mfc_power_on(void) int i, ret = 0; ret = pm_runtime_get_sync(pm->device); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(pm->device); return ret; + } /* clock control */ for (i = 0; i < pm->num_clocks; i++) { diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c index af2d5eb782ce..e1d150584bdc 100644 --- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c +++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c @@ -1371,7 +1371,7 @@ static int bdisp_probe(struct platform_device *pdev) ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "failed to set PM\n"); - goto err_dbg; + goto err_pm; } /* Filters */ @@ -1399,7 +1399,6 @@ err_filter: bdisp_hw_free_filters(bdisp->dev); err_pm: pm_runtime_put(dev); -err_dbg: bdisp_debugfs_remove(bdisp); err_v4l2: v4l2_device_unregister(&bdisp->v4l2_dev); diff --git a/drivers/media/platform/sti/delta/delta-v4l2.c b/drivers/media/platform/sti/delta/delta-v4l2.c index 2503224eeee5..c691b3d81549 100644 --- a/drivers/media/platform/sti/delta/delta-v4l2.c +++ b/drivers/media/platform/sti/delta/delta-v4l2.c @@ -954,8 +954,10 @@ static void delta_run_work(struct work_struct *work) /* enable the hardware */ if (!dec->pm) { ret = delta_get_sync(ctx); - if (ret) + if (ret) { + delta_put_autosuspend(ctx); goto err; + } } /* decode this access unit */ diff --git a/drivers/media/platform/sti/hva/hva-hw.c b/drivers/media/platform/sti/hva/hva-hw.c index 401aaafa1710..43f279e2a6a3 100644 --- a/drivers/media/platform/sti/hva/hva-hw.c +++ b/drivers/media/platform/sti/hva/hva-hw.c @@ -272,6 +272,7 @@ static unsigned long int hva_hw_get_ip_version(struct hva_dev *hva) if (pm_runtime_get_sync(dev) < 0) { dev_err(dev, "%s failed to get pm_runtime\n", HVA_PREFIX); + pm_runtime_put_noidle(dev); mutex_unlock(&hva->protect_mutex); return -EFAULT; } @@ -388,7 +389,7 @@ int hva_hw_probe(struct platform_device *pdev, struct hva_dev *hva) ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "%s failed to set PM\n", HVA_PREFIX); - goto err_clk; + goto err_pm; } /* check IP hardware version */ @@ -553,6 +554,7 @@ void hva_hw_dump_regs(struct hva_dev *hva, struct seq_file *s) if (pm_runtime_get_sync(dev) < 0) { seq_puts(s, "Cannot wake up IP\n"); + pm_runtime_put_noidle(dev); mutex_unlock(&hva->protect_mutex); return; } diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c index b8931490b83b..fd1c41cba52f 100644 --- a/drivers/media/platform/stm32/stm32-dcmi.c +++ b/drivers/media/platform/stm32/stm32-dcmi.c @@ -733,7 +733,7 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count) if (ret < 0) { dev_err(dcmi->dev, "%s: Failed to start streaming, cannot get sync (%d)\n", __func__, ret); - goto err_release_buffers; + goto err_pm_put; } ret = media_pipeline_start(&dcmi->vdev->entity, &dcmi->pipeline); @@ -837,8 +837,6 @@ err_media_pipeline_stop: err_pm_put: pm_runtime_put(dcmi->dev); - -err_release_buffers: spin_lock_irq(&dcmi->irqlock); /* * Return all buffers to vb2 in QUEUED state. diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c index cff2fcd6d812..82d3ee45e2e9 100644 --- a/drivers/media/platform/ti-vpe/vpe.c +++ b/drivers/media/platform/ti-vpe/vpe.c @@ -2475,6 +2475,8 @@ static int vpe_runtime_get(struct platform_device *pdev) r = pm_runtime_get_sync(&pdev->dev); WARN_ON(r < 0); + if (r) + pm_runtime_put_noidle(&pdev->dev); return r < 0 ? r : 0; } diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c index c650e45bb0ad..dc62533cf32c 100644 --- a/drivers/media/platform/vsp1/vsp1_drv.c +++ b/drivers/media/platform/vsp1/vsp1_drv.c @@ -562,7 +562,12 @@ int vsp1_device_get(struct vsp1_device *vsp1) int ret; ret = pm_runtime_get_sync(vsp1->dev); - return ret < 0 ? ret : 0; + if (ret < 0) { + pm_runtime_put_noidle(vsp1->dev); + return ret; + } + + return 0; } /* @@ -845,12 +850,12 @@ static int vsp1_probe(struct platform_device *pdev) /* Configure device parameters based on the version register. */ pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = vsp1_device_get(vsp1); if (ret < 0) goto done; vsp1->version = vsp1_read(vsp1, VI6_IP_VERSION); - pm_runtime_put_sync(&pdev->dev); + vsp1_device_put(vsp1); for (i = 0; i < ARRAY_SIZE(vsp1_device_infos); ++i) { if ((vsp1->version & VI6_IP_VERSION_MODEL_MASK) == diff --git a/drivers/media/rc/ati_remote.c b/drivers/media/rc/ati_remote.c index 9cdef17b4793..c12dda73cdd5 100644 --- a/drivers/media/rc/ati_remote.c +++ b/drivers/media/rc/ati_remote.c @@ -835,6 +835,10 @@ static int ati_remote_probe(struct usb_interface *interface, err("%s: endpoint_in message size==0? \n", __func__); return -ENODEV; } + if (!usb_endpoint_is_int_out(endpoint_out)) { + err("%s: Unexpected endpoint_out\n", __func__); + return -ENODEV; + } ati_remote = kzalloc(sizeof (struct ati_remote), GFP_KERNEL); rc_dev = rc_allocate_device(RC_DRIVER_SCANCODE); diff --git a/drivers/media/test-drivers/vivid/vivid-meta-out.c b/drivers/media/test-drivers/vivid/vivid-meta-out.c index ff8a039aba72..95835b52b58f 100644 --- a/drivers/media/test-drivers/vivid/vivid-meta-out.c +++ b/drivers/media/test-drivers/vivid/vivid-meta-out.c @@ -164,10 +164,11 @@ void vivid_meta_out_process(struct vivid_dev *dev, { struct vivid_meta_out_buf *meta = vb2_plane_vaddr(&buf->vb.vb2_buf, 0); - tpg_s_brightness(&dev->tpg, meta->brightness); - tpg_s_contrast(&dev->tpg, meta->contrast); - tpg_s_saturation(&dev->tpg, meta->saturation); - tpg_s_hue(&dev->tpg, meta->hue); + v4l2_ctrl_s_ctrl(dev->brightness, meta->brightness); + v4l2_ctrl_s_ctrl(dev->contrast, meta->contrast); + v4l2_ctrl_s_ctrl(dev->saturation, meta->saturation); + v4l2_ctrl_s_ctrl(dev->hue, meta->hue); + dprintk(dev, 2, " %s brightness %u contrast %u saturation %u hue %d\n", __func__, meta->brightness, meta->contrast, meta->saturation, meta->hue); diff --git a/drivers/media/tuners/tuner-simple.c b/drivers/media/tuners/tuner-simple.c index b6e70fada3fb..8fb186b25d6a 100644 --- a/drivers/media/tuners/tuner-simple.c +++ b/drivers/media/tuners/tuner-simple.c @@ -500,7 +500,7 @@ static int simple_radio_bandswitch(struct dvb_frontend *fe, u8 *buffer) case TUNER_TENA_9533_DI: case TUNER_YMEC_TVF_5533MF: tuner_dbg("This tuner doesn't have FM. Most cards have a TEA5767 for FM\n"); - return 0; + return -EINVAL; case TUNER_PHILIPS_FM1216ME_MK3: case TUNER_PHILIPS_FM1236_MK3: case TUNER_PHILIPS_FMD1216ME_MK3: @@ -702,7 +702,8 @@ static int simple_set_radio_freq(struct dvb_frontend *fe, TUNER_RATIO_SELECT_50; /* 50 kHz step */ /* Bandswitch byte */ - simple_radio_bandswitch(fe, &buffer[0]); + if (simple_radio_bandswitch(fe, &buffer[0])) + return 0; /* Convert from 1/16 kHz V4L steps to 1/20 MHz (=50 kHz) PLL steps freq * (1 Mhz / 16000 V4L steps) * (20 PLL steps / 1 MHz) = diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index e399b9fad757..a30a8a731eda 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -773,12 +773,16 @@ static s32 uvc_get_le_value(struct uvc_control_mapping *mapping, offset &= 7; mask = ((1LL << bits) - 1) << offset; - for (; bits > 0; data++) { + while (1) { u8 byte = *data & mask; value |= offset > 0 ? (byte >> offset) : (byte << (-offset)); bits -= 8 - (offset > 0 ? offset : 0); + if (bits <= 0) + break; + offset -= 8; mask = (1 << bits) - 1; + data++; } /* Sign-extend the value if needed. */ diff --git a/drivers/media/usb/uvc/uvc_entity.c b/drivers/media/usb/uvc/uvc_entity.c index b4499cddeffe..ca3a9c2eec27 100644 --- a/drivers/media/usb/uvc/uvc_entity.c +++ b/drivers/media/usb/uvc/uvc_entity.c @@ -73,10 +73,45 @@ static int uvc_mc_init_entity(struct uvc_video_chain *chain, int ret; if (UVC_ENTITY_TYPE(entity) != UVC_TT_STREAMING) { + u32 function; + v4l2_subdev_init(&entity->subdev, &uvc_subdev_ops); strscpy(entity->subdev.name, entity->name, sizeof(entity->subdev.name)); + switch (UVC_ENTITY_TYPE(entity)) { + case UVC_VC_SELECTOR_UNIT: + function = MEDIA_ENT_F_VID_MUX; + break; + case UVC_VC_PROCESSING_UNIT: + case UVC_VC_EXTENSION_UNIT: + /* For lack of a better option. */ + function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER; + break; + case UVC_COMPOSITE_CONNECTOR: + case UVC_COMPONENT_CONNECTOR: + function = MEDIA_ENT_F_CONN_COMPOSITE; + break; + case UVC_SVIDEO_CONNECTOR: + function = MEDIA_ENT_F_CONN_SVIDEO; + break; + case UVC_ITT_CAMERA: + function = MEDIA_ENT_F_CAM_SENSOR; + break; + case UVC_TT_VENDOR_SPECIFIC: + case UVC_ITT_VENDOR_SPECIFIC: + case UVC_ITT_MEDIA_TRANSPORT_INPUT: + case UVC_OTT_VENDOR_SPECIFIC: + case UVC_OTT_DISPLAY: + case UVC_OTT_MEDIA_TRANSPORT_OUTPUT: + case UVC_EXTERNAL_VENDOR_SPECIFIC: + default: + function = MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN; + break; + } + + entity->subdev.entity.function = function; + ret = media_entity_pads_init(&entity->subdev.entity, entity->num_pads, entity->pads); diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c index 0335e69b70ab..5e6f3153b5ff 100644 --- a/drivers/media/usb/uvc/uvc_v4l2.c +++ b/drivers/media/usb/uvc/uvc_v4l2.c @@ -247,11 +247,41 @@ static int uvc_v4l2_try_format(struct uvc_streaming *stream, if (ret < 0) goto done; + /* After the probe, update fmt with the values returned from + * negotiation with the device. + */ + for (i = 0; i < stream->nformats; ++i) { + if (probe->bFormatIndex == stream->format[i].index) { + format = &stream->format[i]; + break; + } + } + + if (i == stream->nformats) { + uvc_trace(UVC_TRACE_FORMAT, "Unknown bFormatIndex %u\n", + probe->bFormatIndex); + return -EINVAL; + } + + for (i = 0; i < format->nframes; ++i) { + if (probe->bFrameIndex == format->frame[i].bFrameIndex) { + frame = &format->frame[i]; + break; + } + } + + if (i == format->nframes) { + uvc_trace(UVC_TRACE_FORMAT, "Unknown bFrameIndex %u\n", + probe->bFrameIndex); + return -EINVAL; + } + fmt->fmt.pix.width = frame->wWidth; fmt->fmt.pix.height = frame->wHeight; fmt->fmt.pix.field = V4L2_FIELD_NONE; fmt->fmt.pix.bytesperline = uvc_v4l2_get_bytesperline(format, frame); fmt->fmt.pix.sizeimage = probe->dwMaxVideoFrameSize; + fmt->fmt.pix.pixelformat = format->fcc; fmt->fmt.pix.colorspace = format->colorspace; if (uvc_format != NULL) diff --git a/drivers/memory/fsl-corenet-cf.c b/drivers/memory/fsl-corenet-cf.c index 0b0ed72016da..0309bd5a1800 100644 --- a/drivers/memory/fsl-corenet-cf.c +++ b/drivers/memory/fsl-corenet-cf.c @@ -211,10 +211,8 @@ static int ccf_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, ccf); irq = platform_get_irq(pdev, 0); - if (!irq) { - dev_err(&pdev->dev, "%s: no irq\n", __func__); - return -ENXIO; - } + if (irq < 0) + return irq; ret = devm_request_irq(&pdev->dev, irq, ccf_irq, 0, pdev->name, ccf); if (ret) { diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index eff26c1b1394..27bc417029e1 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -949,7 +949,7 @@ static int gpmc_cs_remap(int cs, u32 base) int ret; u32 old_base, size; - if (cs > gpmc_cs_num) { + if (cs >= gpmc_cs_num) { pr_err("%s: requested chip-select is disabled\n", __func__); return -ENODEV; } @@ -984,7 +984,7 @@ int gpmc_cs_request(int cs, unsigned long size, unsigned long *base) struct resource *res = &gpmc->mem; int r = -1; - if (cs > gpmc_cs_num) { + if (cs >= gpmc_cs_num) { pr_err("%s: requested chip-select is disabled\n", __func__); return -ENODEV; } @@ -2274,6 +2274,10 @@ static void gpmc_probe_dt_children(struct platform_device *pdev) } } #else +void gpmc_read_settings_dt(struct device_node *np, struct gpmc_settings *p) +{ + memset(p, 0, sizeof(*p)); +} static int gpmc_probe_dt(struct platform_device *pdev) { return 0; diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index ccd62b963952..6d2f4a0a901d 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -1415,8 +1415,14 @@ static int sm501_plat_probe(struct platform_device *dev) goto err_claim; } - return sm501_init_dev(sm); + ret = sm501_init_dev(sm); + if (ret) + goto err_unmap; + + return 0; + err_unmap: + iounmap(sm->regs); err_claim: release_mem_region(sm->io_res->start, 0x100); err_res: diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 0d5928bc1b6d..e39b118b945f 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1172,10 +1172,6 @@ void rtsx_pci_init_ocp(struct rtsx_pcr *pcr) rtsx_pci_write_register(pcr, REG_OCPGLITCH, SD_OCP_GLITCH_MASK, pcr->hw_param.ocp_glitch); rtsx_pci_enable_ocp(pcr); - } else { - /* OC power down */ - rtsx_pci_write_register(pcr, FPDCTL, OC_POWER_DOWN, - OC_POWER_DOWN); } } } @@ -1536,12 +1532,14 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, ret = mfd_add_devices(&pcidev->dev, pcr->id, rtsx_pcr_cells, ARRAY_SIZE(rtsx_pcr_cells), NULL, 0, NULL); if (ret < 0) - goto disable_irq; + goto free_slots; schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200)); return 0; +free_slots: + kfree(pcr->slots); disable_irq: free_irq(pcr->irq, (void *)pcr); disable_msi: diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 25a9dd9c0c1b..2ba899f5659f 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -393,8 +393,8 @@ int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid, *capp_unit_id = get_capp_unit_id(np, *phb_index); of_node_put(np); if (!*capp_unit_id) { - pr_err("cxl: invalid capp unit id (phb_index: %d)\n", - *phb_index); + pr_err("cxl: No capp unit found for PHB[%lld,%d]. Make sure the adapter is on a capi-compatible slot\n", + *chipid, *phb_index); return -ENODEV; } diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index cde9a2fc1325..490ff49d11ed 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -358,7 +358,7 @@ static int at25_probe(struct spi_device *spi) at25->nvmem_config.reg_read = at25_ee_read; at25->nvmem_config.reg_write = at25_ee_write; at25->nvmem_config.priv = at25; - at25->nvmem_config.stride = 4; + at25->nvmem_config.stride = 1; at25->nvmem_config.word_size = 1; at25->nvmem_config.size = chip.byte_len; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index ca183733847b..bcc45bf7af2c 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -6285,7 +6285,7 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << + *mask |= ((u64) !is_eng_idle) << (GAUDI_ENGINE_ID_DMA_0 + dma_id); if (s) seq_printf(s, fmt, dma_id, @@ -6308,7 +6308,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << (GAUDI_ENGINE_ID_TPC_0 + i); + *mask |= ((u64) !is_eng_idle) << + (GAUDI_ENGINE_ID_TPC_0 + i); if (s) seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N", @@ -6336,7 +6337,8 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << (GAUDI_ENGINE_ID_MME_0 + i); + *mask |= ((u64) !is_eng_idle) << + (GAUDI_ENGINE_ID_MME_0 + i); if (s) { if (!is_slave) seq_printf(s, fmt, i, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c179085ced7b..a8041a39fae3 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -5098,7 +5098,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << (GOYA_ENGINE_ID_DMA_0 + i); + *mask |= ((u64) !is_eng_idle) << + (GOYA_ENGINE_ID_DMA_0 + i); if (s) seq_printf(s, dma_fmt, i, is_eng_idle ? "Y" : "N", qm_glbl_sts0, dma_core_sts0); @@ -5121,7 +5122,8 @@ static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << (GOYA_ENGINE_ID_TPC_0 + i); + *mask |= ((u64) !is_eng_idle) << + (GOYA_ENGINE_ID_TPC_0 + i); if (s) seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N", qm_glbl_sts0, cmdq_glbl_sts0, tpc_cfg_sts); @@ -5141,7 +5143,7 @@ static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, is_idle &= is_eng_idle; if (mask) - *mask |= !is_eng_idle << GOYA_ENGINE_ID_MME_0; + *mask |= ((u64) !is_eng_idle) << GOYA_ENGINE_ID_MME_0; if (s) { seq_printf(s, fmt, 0, is_eng_idle ? "Y" : "N", qm_glbl_sts0, cmdq_glbl_sts0, mme_arch_sts); diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c index 406cd5abfa72..56c784699eb8 100644 --- a/drivers/misc/mic/scif/scif_rma.c +++ b/drivers/misc/mic/scif/scif_rma.c @@ -1384,6 +1384,8 @@ retry: (prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0, pinned_pages->pages); if (nr_pages != pinned_pages->nr_pages) { + if (pinned_pages->nr_pages < 0) + pinned_pages->nr_pages = 0; if (try_upgrade) { if (ulimit) __scif_dec_pinned_vm_lock(mm, nr_pages); @@ -1400,7 +1402,6 @@ retry: if (pinned_pages->nr_pages < nr_pages) { err = -EFAULT; - pinned_pages->nr_pages = nr_pages; goto dec_pinned; } @@ -1413,7 +1414,6 @@ dec_pinned: __scif_dec_pinned_vm_lock(mm, nr_pages); /* Something went wrong! Rollback */ error_unmap: - pinned_pages->nr_pages = nr_pages; scif_destroy_pinned_pages(pinned_pages); *pages = NULL; dev_dbg(scif_info.mdev.this_device, diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 85942f6717c5..8aadc6055df1 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -320,7 +320,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, /* First assign the vring's allocated in host memory */ vqconfig = _vop_vq_config(vdev->desc) + index; memcpy_fromio(&config, vqconfig, sizeof(config)); - _vr_size = vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN); + _vr_size = round_up(vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN), 4); vr_size = PAGE_ALIGN(_vr_size + sizeof(struct _mic_vring_info)); va = vpdev->hw_ops->remap(vpdev, le64_to_cpu(config.address), vr_size); if (!va) diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c index 30eac172f017..7014ffe88632 100644 --- a/drivers/misc/mic/vop/vop_vringh.c +++ b/drivers/misc/mic/vop/vop_vringh.c @@ -296,7 +296,7 @@ static int vop_virtio_add_device(struct vop_vdev *vdev, num = le16_to_cpu(vqconfig[i].num); mutex_init(&vvr->vr_mutex); - vr_size = PAGE_ALIGN(vring_size(num, MIC_VIRTIO_RING_ALIGN) + + vr_size = PAGE_ALIGN(round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4) + sizeof(struct _mic_vring_info)); vr->va = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, @@ -308,7 +308,7 @@ static int vop_virtio_add_device(struct vop_vdev *vdev, goto err; } vr->len = vr_size; - vr->info = vr->va + vring_size(num, MIC_VIRTIO_RING_ALIGN); + vr->info = vr->va + round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4); vr->info->magic = cpu_to_le32(MIC_MAGIC + vdev->virtio_id + i); vr_addr = dma_map_single(&vpdev->dev, vr->va, vr_size, DMA_BIDIRECTIONAL); @@ -602,6 +602,7 @@ static int vop_virtio_copy_from_user(struct vop_vdev *vdev, void __user *ubuf, size_t partlen; bool dma = VOP_USE_DMA && vi->dma_ch; int err = 0; + size_t offset = 0; if (dma) { dma_alignment = 1 << vi->dma_ch->device->copy_align; @@ -655,13 +656,20 @@ memcpy: * We are copying to IO below and should ideally use something * like copy_from_user_toio(..) if it existed. */ - if (copy_from_user((void __force *)dbuf, ubuf, len)) { - err = -EFAULT; - dev_err(vop_dev(vdev), "%s %d err %d\n", - __func__, __LINE__, err); - goto err; + while (len) { + partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE); + + if (copy_from_user(vvr->buf, ubuf + offset, partlen)) { + err = -EFAULT; + dev_err(vop_dev(vdev), "%s %d err %d\n", + __func__, __LINE__, err); + goto err; + } + memcpy_toio(dbuf + offset, vvr->buf, partlen); + offset += partlen; + vdev->out_bytes += partlen; + len -= partlen; } - vdev->out_bytes += len; err = 0; err: vpdev->hw_ops->unmap(vpdev, dbuf); diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig index 2d2266c1439e..51b51f377470 100644 --- a/drivers/misc/ocxl/Kconfig +++ b/drivers/misc/ocxl/Kconfig @@ -9,9 +9,8 @@ config OCXL_BASE config OCXL tristate "OpenCAPI coherent accelerator support" - depends on PPC_POWERNV && PCI && EEH + depends on PPC_POWERNV && PCI && EEH && HOTPLUG_PCI_POWERNV select OCXL_BASE - select HOTPLUG_PCI_POWERNV default m help Select this option to enable the ocxl driver for Open diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index 8531ae781195..c49065887e8f 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -657,8 +657,9 @@ static int qp_host_get_user_memory(u64 produce_uva, if (retval < (int)produce_q->kernel_if->num_pages) { pr_debug("get_user_pages_fast(produce) failed (retval=%d)", retval); - qp_release_pages(produce_q->kernel_if->u.h.header_page, - retval, false); + if (retval > 0) + qp_release_pages(produce_q->kernel_if->u.h.header_page, + retval, false); err = VMCI_ERROR_NO_MEM; goto out; } @@ -670,8 +671,9 @@ static int qp_host_get_user_memory(u64 produce_uva, if (retval < (int)consume_q->kernel_if->num_pages) { pr_debug("get_user_pages_fast(consume) failed (retval=%d)", retval); - qp_release_pages(consume_q->kernel_if->u.h.header_page, - retval, false); + if (retval > 0) + qp_release_pages(consume_q->kernel_if->u.h.header_page, + retval, false); qp_release_pages(produce_q->kernel_if->u.h.header_page, produce_q->kernel_if->num_pages, false); err = VMCI_ERROR_NO_MEM; diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index e0655278c5c3..3efaa9534a77 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -26,6 +26,9 @@ static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func, unsigned i, nr_strings; char **buffer, *string; + if (size < 2) + return 0; + /* Find all null-terminated (including zero length) strings in the TPLLV1_INFO field. Trailing garbage is ignored. */ buf += 2; diff --git a/drivers/mtd/hyperbus/hbmc-am654.c b/drivers/mtd/hyperbus/hbmc-am654.c index f350a0809f88..a808fa28cd9a 100644 --- a/drivers/mtd/hyperbus/hbmc-am654.c +++ b/drivers/mtd/hyperbus/hbmc-am654.c @@ -70,7 +70,8 @@ static int am654_hbmc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv); - ret = of_address_to_resource(np, 0, &res); + priv->hbdev.np = of_get_next_child(np, NULL); + ret = of_address_to_resource(priv->hbdev.np, 0, &res); if (ret) return ret; @@ -103,7 +104,6 @@ static int am654_hbmc_probe(struct platform_device *pdev) priv->ctlr.dev = dev; priv->ctlr.ops = &am654_hbmc_ops; priv->hbdev.ctlr = &priv->ctlr; - priv->hbdev.np = of_get_next_child(dev->of_node, NULL); ret = hyperbus_register_device(&priv->hbdev); if (ret) { dev_err(dev, "failed to register controller\n"); diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c index 0f1547f09d08..72f5c7b30079 100644 --- a/drivers/mtd/lpddr/lpddr2_nvm.c +++ b/drivers/mtd/lpddr/lpddr2_nvm.c @@ -393,6 +393,17 @@ static int lpddr2_nvm_lock(struct mtd_info *mtd, loff_t start_add, return lpddr2_nvm_do_block_op(mtd, start_add, len, LPDDR2_NVM_LOCK); } +static const struct mtd_info lpddr2_nvm_mtd_info = { + .type = MTD_RAM, + .writesize = 1, + .flags = (MTD_CAP_NVRAM | MTD_POWERUP_LOCK), + ._read = lpddr2_nvm_read, + ._write = lpddr2_nvm_write, + ._erase = lpddr2_nvm_erase, + ._unlock = lpddr2_nvm_unlock, + ._lock = lpddr2_nvm_lock, +}; + /* * lpddr2_nvm driver probe method */ @@ -433,6 +444,7 @@ static int lpddr2_nvm_probe(struct platform_device *pdev) .pfow_base = OW_BASE_ADDRESS, .fldrv_priv = pcm_data, }; + if (IS_ERR(map->virt)) return PTR_ERR(map->virt); @@ -444,22 +456,13 @@ static int lpddr2_nvm_probe(struct platform_device *pdev) return PTR_ERR(pcm_data->ctl_regs); /* Populate mtd_info data structure */ - *mtd = (struct mtd_info) { - .dev = { .parent = &pdev->dev }, - .name = pdev->dev.init_name, - .type = MTD_RAM, - .priv = map, - .size = resource_size(add_range), - .erasesize = ERASE_BLOCKSIZE * pcm_data->bus_width, - .writesize = 1, - .writebufsize = WRITE_BUFFSIZE * pcm_data->bus_width, - .flags = (MTD_CAP_NVRAM | MTD_POWERUP_LOCK), - ._read = lpddr2_nvm_read, - ._write = lpddr2_nvm_write, - ._erase = lpddr2_nvm_erase, - ._unlock = lpddr2_nvm_unlock, - ._lock = lpddr2_nvm_lock, - }; + *mtd = lpddr2_nvm_mtd_info; + mtd->dev.parent = &pdev->dev; + mtd->name = pdev->dev.init_name; + mtd->priv = map; + mtd->size = resource_size(add_range); + mtd->erasesize = ERASE_BLOCKSIZE * pcm_data->bus_width; + mtd->writebufsize = WRITE_BUFFSIZE * pcm_data->bus_width; /* Verify the presence of the device looking for PFOW string */ if (!lpddr2_nvm_pfow_present(map)) { diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index 4ced68be7ed7..774970bfcf85 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -279,12 +279,13 @@ static void mtdoops_do_dump(struct kmsg_dumper *dumper, kmsg_dump_get_buffer(dumper, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, record_size - MTDOOPS_HEADER_SIZE, NULL); - /* Panics must be written immediately */ - if (reason != KMSG_DUMP_OOPS) + if (reason != KMSG_DUMP_OOPS) { + /* Panics must be written immediately */ mtdoops_write(cxt, 1); - - /* For other cases, schedule work to write it "nicely" */ - schedule_work(&cxt->work_write); + } else { + /* For other cases, schedule work to write it "nicely" */ + schedule_work(&cxt->work_write); + } } static void mtdoops_notify_add(struct mtd_info *mtd) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 3711e7a0436c..b3390028c6bf 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -400,12 +400,14 @@ static int gpio_nand_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_OF static const struct of_device_id gpio_nand_of_id_table[] = { { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, gpio_nand_of_id_table); +#endif static const struct platform_device_id gpio_nand_plat_id_table[] = { { diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 65c9d17b25a3..dce6d7a10a36 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1791,7 +1791,7 @@ static int stm32_fmc2_nfc_parse_child(struct stm32_fmc2_nfc *nfc, return ret; } - if (cs > FMC2_MAX_CE) { + if (cs >= FMC2_MAX_CE) { dev_err(nfc->dev, "invalid reg value: %d\n", cs); return -EINVAL; } diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 7248c5901183..fcca45e2abe2 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -852,8 +852,10 @@ static int vf610_nfc_probe(struct platform_device *pdev) } of_id = of_match_device(vf610_nfc_dt_ids, &pdev->dev); - if (!of_id) - return -ENODEV; + if (!of_id) { + err = -ENODEV; + goto err_disable_clk; + } nfc->variant = (enum vf610_nfc_variant)of_id->data; diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index d219c970042a..0b7667e60780 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -21,7 +21,7 @@ #define GD5FXGQ4UXFXXG_STATUS_ECC_UNCOR_ERROR (7 << 4) static SPINAND_OP_VARIANTS(read_cache_variants, - SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), @@ -29,7 +29,7 @@ static SPINAND_OP_VARIANTS(read_cache_variants, SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); static SPINAND_OP_VARIANTS(read_cache_variants_f, - SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X4_OP_3A(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_X2_OP_3A(0, 1, NULL, 0), @@ -202,7 +202,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants, &write_cache_variants, &update_cache_variants), - 0, + SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, gd5fxgq4xa_ecc_get_status)), SPINAND_INFO("GD5F2GQ4xA", @@ -212,7 +212,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants, &write_cache_variants, &update_cache_variants), - 0, + SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, gd5fxgq4xa_ecc_get_status)), SPINAND_INFO("GD5F4GQ4xA", @@ -222,7 +222,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants, &write_cache_variants, &update_cache_variants), - 0, + SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, gd5fxgq4xa_ecc_get_status)), SPINAND_INFO("GD5F1GQ4UExxG", @@ -232,7 +232,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants, &write_cache_variants, &update_cache_variants), - 0, + SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgq4_variant2_ooblayout, gd5fxgq4uexxg_ecc_get_status)), SPINAND_INFO("GD5F1GQ4UFxxG", @@ -242,7 +242,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants_f, &write_cache_variants, &update_cache_variants), - 0, + SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&gd5fxgq4_variant2_ooblayout, gd5fxgq4ufxxg_ecc_get_status)), }; diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 94d10ec954a0..2ac7a667bde3 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1260,18 +1260,23 @@ static int flexcan_chip_start(struct net_device *dev) return err; } -/* flexcan_chip_stop +/* __flexcan_chip_stop * - * this functions is entered with clocks enabled + * this function is entered with clocks enabled */ -static void flexcan_chip_stop(struct net_device *dev) +static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error) { struct flexcan_priv *priv = netdev_priv(dev); struct flexcan_regs __iomem *regs = priv->regs; + int err; /* freeze + disable module */ - flexcan_chip_freeze(priv); - flexcan_chip_disable(priv); + err = flexcan_chip_freeze(priv); + if (err && !disable_on_error) + return err; + err = flexcan_chip_disable(priv); + if (err && !disable_on_error) + goto out_chip_unfreeze; /* Disable all interrupts */ priv->write(0, ®s->imask2); @@ -1281,6 +1286,23 @@ static void flexcan_chip_stop(struct net_device *dev) flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; + + return 0; + + out_chip_unfreeze: + flexcan_chip_unfreeze(priv); + + return err; +} + +static inline int flexcan_chip_stop_disable_on_error(struct net_device *dev) +{ + return __flexcan_chip_stop(dev, true); +} + +static inline int flexcan_chip_stop(struct net_device *dev) +{ + return __flexcan_chip_stop(dev, false); } static int flexcan_open(struct net_device *dev) @@ -1362,7 +1384,7 @@ static int flexcan_close(struct net_device *dev) netif_stop_queue(dev); can_rx_offload_disable(&priv->offload); - flexcan_chip_stop(dev); + flexcan_chip_stop_disable_on_error(dev); can_rx_offload_del(&priv->offload); free_irq(dev->irq, dev); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 38ea5e600fb8..e6d0cb9ee02f 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -144,8 +144,6 @@ static int __maybe_unused m_can_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct m_can_classdev *mcan_class = netdev_priv(ndev); - m_can_class_suspend(dev); - clk_disable_unprepare(mcan_class->cclk); clk_disable_unprepare(mcan_class->hclk); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7b6c0dce7536..ee433abc2d4b 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -103,14 +103,8 @@ void ksz_init_mib_timer(struct ksz_device *dev) INIT_DELAYED_WORK(&dev->mib_read, ksz_mib_read_work); - /* Read MIB counters every 30 seconds to avoid overflow. */ - dev->mib_read_interval = msecs_to_jiffies(30000); - for (i = 0; i < dev->mib_port_cnt; i++) dev->dev_ops->port_init_cnt(dev, i); - - /* Start the timer 2 seconds later. */ - schedule_delayed_work(&dev->mib_read, msecs_to_jiffies(2000)); } EXPORT_SYMBOL_GPL(ksz_init_mib_timer); @@ -144,7 +138,9 @@ void ksz_adjust_link(struct dsa_switch *ds, int port, /* Read all MIB counters when the link is going down. */ if (!phydev->link) { p->read = true; - schedule_delayed_work(&dev->mib_read, 0); + /* timer started */ + if (dev->mib_read_interval) + schedule_delayed_work(&dev->mib_read, 0); } mutex_lock(&dev->dev_mutex); if (!phydev->link) @@ -460,6 +456,12 @@ int ksz_switch_register(struct ksz_device *dev, return ret; } + /* Read MIB counters every 30 seconds to avoid overflow. */ + dev->mib_read_interval = msecs_to_jiffies(30000); + + /* Start the MIB timer. */ + schedule_delayed_work(&dev->mib_read, 0); + return 0; } EXPORT_SYMBOL(ksz_switch_register); diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h index 9a63b51e1d82..6f2dab7e33d6 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek-smi-core.h @@ -25,6 +25,9 @@ struct rtl8366_mib_counter { const char *name; }; +/** + * struct rtl8366_vlan_mc - Virtual LAN member configuration + */ struct rtl8366_vlan_mc { u16 vid; u16 untag; @@ -119,7 +122,6 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi); int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used); int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, u32 untag, u32 fid); -int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val); int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, unsigned int vid); int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable); diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 99cdb2f18fa2..49c626a33680 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -36,12 +36,113 @@ int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used) } EXPORT_SYMBOL_GPL(rtl8366_mc_is_used); +/** + * rtl8366_obtain_mc() - retrieve or allocate a VLAN member configuration + * @smi: the Realtek SMI device instance + * @vid: the VLAN ID to look up or allocate + * @vlanmc: the pointer will be assigned to a pointer to a valid member config + * if successful + * @return: index of a new member config or negative error number + */ +static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, + struct rtl8366_vlan_mc *vlanmc) +{ + struct rtl8366_vlan_4k vlan4k; + int ret; + int i; + + /* Try to find an existing member config entry for this VID */ + for (i = 0; i < smi->num_vlan_mc; i++) { + ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + if (vid == vlanmc->vid) + return i; + } + + /* We have no MC entry for this VID, try to find an empty one */ + for (i = 0; i < smi->num_vlan_mc; i++) { + ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + if (vlanmc->vid == 0 && vlanmc->member == 0) { + /* Update the entry from the 4K table */ + ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + if (ret) { + dev_err(smi->dev, "error looking for 4K VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + vlanmc->vid = vid; + vlanmc->member = vlan4k.member; + vlanmc->untag = vlan4k.untag; + vlanmc->fid = vlan4k.fid; + ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + + dev_dbg(smi->dev, "created new MC at index %d for VID %d\n", + i, vid); + return i; + } + } + + /* MC table is full, try to find an unused entry and replace it */ + for (i = 0; i < smi->num_vlan_mc; i++) { + int used; + + ret = rtl8366_mc_is_used(smi, i, &used); + if (ret) + return ret; + + if (!used) { + /* Update the entry from the 4K table */ + ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + if (ret) + return ret; + + vlanmc->vid = vid; + vlanmc->member = vlan4k.member; + vlanmc->untag = vlan4k.untag; + vlanmc->fid = vlan4k.fid; + ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + if (ret) { + dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + i, vid); + return ret; + } + dev_dbg(smi->dev, "recycled MC at index %i for VID %d\n", + i, vid); + return i; + } + } + + dev_err(smi->dev, "all VLAN member configurations are in use\n"); + return -ENOSPC; +} + int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, u32 untag, u32 fid) { + struct rtl8366_vlan_mc vlanmc; struct rtl8366_vlan_4k vlan4k; + int mc; int ret; - int i; + + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; dev_dbg(smi->dev, "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", @@ -63,133 +164,58 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, "resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, vlan4k.member, vlan4k.untag); - /* Try to find an existing MC entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - struct rtl8366_vlan_mc vlanmc; - - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vid == vlanmc.vid) { - /* update the MC entry */ - vlanmc.member |= member; - vlanmc.untag |= untag; - vlanmc.fid = fid; - - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + /* Find or allocate a member config for this VID */ + ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + if (ret < 0) + return ret; + mc = ret; - dev_dbg(smi->dev, - "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", - vid, vlanmc.member, vlanmc.untag); + /* Update the MC entry */ + vlanmc.member |= member; + vlanmc.untag |= untag; + vlanmc.fid = fid; - break; - } - } + /* Commit updates to the MC entry */ + ret = smi->ops->set_vlan_mc(smi, mc, &vlanmc); + if (ret) + dev_err(smi->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", + mc, vid); + else + dev_dbg(smi->dev, + "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", + vid, vlanmc.member, vlanmc.untag); return ret; } EXPORT_SYMBOL_GPL(rtl8366_set_vlan); -int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val) -{ - struct rtl8366_vlan_mc vlanmc; - int ret; - int index; - - ret = smi->ops->get_mc_index(smi, port, &index); - if (ret) - return ret; - - ret = smi->ops->get_vlan_mc(smi, index, &vlanmc); - if (ret) - return ret; - - *val = vlanmc.vid; - return 0; -} -EXPORT_SYMBOL_GPL(rtl8366_get_pvid); - int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, unsigned int vid) { struct rtl8366_vlan_mc vlanmc; - struct rtl8366_vlan_4k vlan4k; + int mc; int ret; - int i; - - /* Try to find an existing MC entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vid == vlanmc.vid) { - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } - } - - /* We have no MC entry for this VID, try to find an empty one */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - if (vlanmc.vid == 0 && vlanmc.member == 0) { - /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); - if (ret) - return ret; - vlanmc.vid = vid; - vlanmc.member = vlan4k.member; - vlanmc.untag = vlan4k.untag; - vlanmc.fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; - - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } - } - - /* MC table is full, try to find an unused entry and replace it */ - for (i = 0; i < smi->num_vlan_mc; i++) { - int used; - - ret = rtl8366_mc_is_used(smi, i, &used); - if (ret) - return ret; - - if (!used) { - /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); - if (ret) - return ret; + if (!smi->ops->is_vlan_valid(smi, vid)) + return -EINVAL; - vlanmc.vid = vid; - vlanmc.member = vlan4k.member; - vlanmc.untag = vlan4k.untag; - vlanmc.fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); - if (ret) - return ret; + /* Find or allocate a member config for this VID */ + ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + if (ret < 0) + return ret; + mc = ret; - ret = smi->ops->set_mc_index(smi, port, i); - return ret; - } + ret = smi->ops->set_mc_index(smi, port, mc); + if (ret) { + dev_err(smi->dev, "set PVID: failed to set MC index %d for port %d\n", + mc, port); + return ret; } - dev_err(smi->dev, - "all VLAN member configurations are in use\n"); + dev_dbg(smi->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", + port, vid, mc); - return -ENOSPC; + return 0; } EXPORT_SYMBOL_GPL(rtl8366_set_pvid); @@ -389,7 +415,8 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (!smi->ops->is_vlan_valid(smi, vid)) return; - dev_info(smi->dev, "add VLAN on port %d, %s, %s\n", + dev_info(smi->dev, "add VLAN %d on port %d, %s, %s\n", + vlan->vid_begin, port, untagged ? "untagged" : "tagged", pvid ? " PVID" : "no PVID"); @@ -398,34 +425,29 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, dev_err(smi->dev, "port is DSA or CPU port\n"); for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { - int pvid_val = 0; - - dev_info(smi->dev, "add VLAN %04x\n", vid); member |= BIT(port); if (untagged) untag |= BIT(port); - /* To ensure that we have a valid MC entry for this VLAN, - * initialize the port VLAN ID here. - */ - ret = rtl8366_get_pvid(smi, port, &pvid_val); - if (ret < 0) { - dev_err(smi->dev, "could not lookup PVID for port %d\n", - port); - return; - } - if (pvid_val == 0) { - ret = rtl8366_set_pvid(smi, port, vid); - if (ret < 0) - return; - } - ret = rtl8366_set_vlan(smi, vid, member, untag, 0); if (ret) dev_err(smi->dev, "failed to set up VLAN %04x", vid); + + if (!pvid) + continue; + + ret = rtl8366_set_pvid(smi, port, vid); + if (ret) + dev_err(smi->dev, + "failed to set PVID on port %d to VLAN %04x", + port, vid); + + if (!ret) + dev_dbg(smi->dev, "VLAN add: added VLAN %d with PVID on port %d\n", + vid, port); } } EXPORT_SYMBOL_GPL(rtl8366_vlan_add); diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index fd1977590cb4..c83b332656a4 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -1270,7 +1270,7 @@ static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) if (smi->vlan4k_enabled) max = RTL8366RB_NUM_VIDS - 1; - if (vlan == 0 || vlan >= max) + if (vlan == 0 || vlan > max) return false; return true; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index dd07db656a5c..f3c125d50d7a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1158,16 +1158,6 @@ static void bnxt_queue_sp_work(struct bnxt *bp) schedule_work(&bp->sp_task); } -static void bnxt_cancel_sp_work(struct bnxt *bp) -{ - if (BNXT_PF(bp)) { - flush_workqueue(bnxt_pf_wq); - } else { - cancel_work_sync(&bp->sp_task); - cancel_delayed_work_sync(&bp->fw_reset_task); - } -} - static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { if (!rxr->bnapi->in_reset) { @@ -4198,7 +4188,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; - if (BNXT_NO_FW_ACCESS(bp)) + if (BNXT_NO_FW_ACCESS(bp) && + le16_to_cpu(req->req_type) != HWRM_FUNC_RESET) return -EBUSY; if (msg_len > BNXT_HWRM_MAX_REQ_LEN) { @@ -9247,7 +9238,10 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { int rc = 0; - rc = __bnxt_open_nic(bp, irq_re_init, link_re_init); + if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) + rc = -EIO; + if (!rc) + rc = __bnxt_open_nic(bp, irq_re_init, link_re_init); if (rc) { netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc); dev_close(bp->dev); @@ -11505,15 +11499,17 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_cancel_sp_work(bp); - bp->sp_event = 0; - - bnxt_dl_fw_reporters_destroy(bp, true); if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + /* Flush any pending tasks */ + cancel_work_sync(&bp->sp_task); + cancel_delayed_work_sync(&bp->fw_reset_task); + bp->sp_event = 0; + + bnxt_dl_fw_reporters_destroy(bp, true); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); @@ -12238,6 +12234,9 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_DISCONNECT; } + if (state == pci_channel_io_frozen) + set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state); + if (netif_running(netdev)) bnxt_close(netdev); @@ -12264,7 +12263,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); - int err = 0; + int err = 0, off; pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; netdev_info(bp->dev, "PCI Slot Reset\n"); @@ -12276,6 +12275,20 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) "Cannot re-enable PCI device after reset.\n"); } else { pci_set_master(pdev); + /* Upon fatal error, our device internal logic that latches to + * BAR value is getting reset and will restore only upon + * rewritting the BARs. + * + * As pci_restore_state() does not re-write the BARs if the + * value is same as saved value earlier, driver needs to + * write the BARs to 0 to force restore, in case of fatal error. + */ + if (test_and_clear_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, + &bp->state)) { + for (off = PCI_BASE_ADDRESS_0; + off <= PCI_BASE_ADDRESS_5; off += 4) + pci_write_config_dword(bp->pdev, off, 0); + } pci_restore_state(pdev); pci_save_state(pdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 440b43c8068f..a80ac2ae57a6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1672,6 +1672,7 @@ struct bnxt { #define BNXT_STATE_ABORT_ERR 5 #define BNXT_STATE_FW_FATAL_COND 6 #define BNXT_STATE_DRV_REGISTERED 7 +#define BNXT_STATE_PCI_CHANNEL_IO_FROZEN 8 #define BNXT_NO_FW_ACCESS(bp) \ (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index ff0d82e2535d..fd33c888046b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -145,13 +145,13 @@ static int configure_filter_smac(struct adapter *adap, struct filter_entry *f) int err; /* do a set-tcb for smac-sel and CWR bit.. */ - err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1); - if (err) - goto smac_err; - err = set_tcb_field(adap, f, f->tid, TCB_SMAC_SEL_W, TCB_SMAC_SEL_V(TCB_SMAC_SEL_M), TCB_SMAC_SEL_V(f->smt->idx), 1); + if (err) + goto smac_err; + + err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1); if (!err) return 0; @@ -865,6 +865,7 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) | FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) | FW_FILTER_WR_DMAC_V(f->fs.newdmac) | + FW_FILTER_WR_SMAC_V(f->fs.newsmac) | FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT || f->fs.newvlan == VLAN_REWRITE) | FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE || @@ -882,7 +883,7 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) | FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) | FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld)); - fwr->smac_sel = 0; + fwr->smac_sel = f->smt->idx; fwr->rx_chan_rx_rpl_iq = htons(FW_FILTER_WR_RX_CHAN_V(0) | FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id)); @@ -1321,11 +1322,8 @@ static void mk_act_open_req6(struct filter_entry *f, struct sk_buff *skb, TX_QUEUE_V(f->fs.nat_mode) | T5_OPT_2_VALID_F | RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) | - CONG_CNTRL_V((f->fs.action == FILTER_DROP) | - (f->fs.dirsteer << 1)) | PACE_V((f->fs.maskhash) | - ((f->fs.dirsteerhash) << 1)) | - CCTRL_ECN_V(f->fs.action == FILTER_SWITCH)); + ((f->fs.dirsteerhash) << 1))); } static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb, @@ -1361,11 +1359,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb, TX_QUEUE_V(f->fs.nat_mode) | T5_OPT_2_VALID_F | RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) | - CONG_CNTRL_V((f->fs.action == FILTER_DROP) | - (f->fs.dirsteer << 1)) | PACE_V((f->fs.maskhash) | - ((f->fs.dirsteerhash) << 1)) | - CCTRL_ECN_V(f->fs.action == FILTER_SWITCH)); + ((f->fs.dirsteerhash) << 1))); } static int cxgb4_set_hash_filter(struct net_device *dev, @@ -2037,6 +2032,20 @@ void hash_filter_rpl(struct adapter *adap, const struct cpl_act_open_rpl *rpl) } return; } + switch (f->fs.action) { + case FILTER_PASS: + if (f->fs.dirsteer) + set_tcb_tflag(adap, f, tid, + TF_DIRECT_STEER_S, 1, 1); + break; + case FILTER_DROP: + set_tcb_tflag(adap, f, tid, TF_DROP_S, 1, 1); + break; + case FILTER_SWITCH: + set_tcb_tflag(adap, f, tid, TF_LPBK_S, 1, 1); + break; + } + break; default: @@ -2104,22 +2113,11 @@ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl) if (ctx) ctx->result = 0; } else if (ret == FW_FILTER_WR_FLT_ADDED) { - int err = 0; - - if (f->fs.newsmac) - err = configure_filter_smac(adap, f); - - if (!err) { - f->pending = 0; /* async setup completed */ - f->valid = 1; - if (ctx) { - ctx->result = 0; - ctx->tid = idx; - } - } else { - clear_filter(adap, f); - if (ctx) - ctx->result = err; + f->pending = 0; /* async setup completed */ + f->valid = 1; + if (ctx) { + ctx->result = 0; + ctx->tid = idx; } } else { /* Something went wrong. Issue a warning about the diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 59b65d4db086..dff564e1cfc7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -60,6 +60,89 @@ static struct ch_tc_pedit_fields pedits[] = { PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12), }; +static const struct cxgb4_natmode_config cxgb4_natmode_config_array[] = { + /* Default supported NAT modes */ + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_NONE, + .natmode = NAT_MODE_NONE, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP, + .natmode = NAT_MODE_DIP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_DPORT, + .natmode = NAT_MODE_DIP_DP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_DPORT | + CXGB4_ACTION_NATMODE_SIP, + .natmode = NAT_MODE_DIP_DP_SIP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_DPORT | + CXGB4_ACTION_NATMODE_SPORT, + .natmode = NAT_MODE_DIP_DP_SP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_SIP | CXGB4_ACTION_NATMODE_SPORT, + .natmode = NAT_MODE_SIP_SP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_SIP | + CXGB4_ACTION_NATMODE_SPORT, + .natmode = NAT_MODE_DIP_SIP_SP, + }, + { + .chip = CHELSIO_T5, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_SIP | + CXGB4_ACTION_NATMODE_DPORT | + CXGB4_ACTION_NATMODE_SPORT, + .natmode = NAT_MODE_ALL, + }, + /* T6+ can ignore L4 ports when they're disabled. */ + { + .chip = CHELSIO_T6, + .flags = CXGB4_ACTION_NATMODE_SIP, + .natmode = NAT_MODE_SIP_SP, + }, + { + .chip = CHELSIO_T6, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_SPORT, + .natmode = NAT_MODE_DIP_DP_SP, + }, + { + .chip = CHELSIO_T6, + .flags = CXGB4_ACTION_NATMODE_DIP | CXGB4_ACTION_NATMODE_SIP, + .natmode = NAT_MODE_ALL, + }, +}; + +static void cxgb4_action_natmode_tweak(struct ch_filter_specification *fs, + u8 natmode_flags) +{ + u8 i = 0; + + /* Translate the enabled NAT 4-tuple fields to one of the + * hardware supported NAT mode configurations. This ensures + * that we pick a valid combination, where the disabled fields + * do not get overwritten to 0. + */ + for (i = 0; i < ARRAY_SIZE(cxgb4_natmode_config_array); i++) { + if (cxgb4_natmode_config_array[i].flags == natmode_flags) { + fs->nat_mode = cxgb4_natmode_config_array[i].natmode; + return; + } + } +} + static struct ch_tc_flower_entry *allocate_flower_entry(void) { struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL); @@ -287,7 +370,8 @@ static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask, } static void process_pedit_field(struct ch_filter_specification *fs, u32 val, - u32 mask, u32 offset, u8 htype) + u32 mask, u32 offset, u8 htype, + u8 *natmode_flags) { switch (htype) { case FLOW_ACT_MANGLE_HDR_TYPE_ETH: @@ -312,60 +396,94 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, switch (offset) { case PEDIT_IP4_SRC: offload_pedit(fs, val, mask, IP4_SRC); + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; break; case PEDIT_IP4_DST: offload_pedit(fs, val, mask, IP4_DST); + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; } - fs->nat_mode = NAT_MODE_ALL; break; case FLOW_ACT_MANGLE_HDR_TYPE_IP6: switch (offset) { case PEDIT_IP6_SRC_31_0: offload_pedit(fs, val, mask, IP6_SRC_31_0); + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; break; case PEDIT_IP6_SRC_63_32: offload_pedit(fs, val, mask, IP6_SRC_63_32); + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; break; case PEDIT_IP6_SRC_95_64: offload_pedit(fs, val, mask, IP6_SRC_95_64); + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; break; case PEDIT_IP6_SRC_127_96: offload_pedit(fs, val, mask, IP6_SRC_127_96); + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; break; case PEDIT_IP6_DST_31_0: offload_pedit(fs, val, mask, IP6_DST_31_0); + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; break; case PEDIT_IP6_DST_63_32: offload_pedit(fs, val, mask, IP6_DST_63_32); + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; break; case PEDIT_IP6_DST_95_64: offload_pedit(fs, val, mask, IP6_DST_95_64); + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; break; case PEDIT_IP6_DST_127_96: offload_pedit(fs, val, mask, IP6_DST_127_96); + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; } - fs->nat_mode = NAT_MODE_ALL; break; case FLOW_ACT_MANGLE_HDR_TYPE_TCP: switch (offset) { case PEDIT_TCP_SPORT_DPORT: - if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) { fs->nat_fport = val; - else + *natmode_flags |= CXGB4_ACTION_NATMODE_SPORT; + } else { fs->nat_lport = val >> 16; + *natmode_flags |= CXGB4_ACTION_NATMODE_DPORT; + } } - fs->nat_mode = NAT_MODE_ALL; break; case FLOW_ACT_MANGLE_HDR_TYPE_UDP: switch (offset) { case PEDIT_UDP_SPORT_DPORT: - if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) { fs->nat_fport = val; - else + *natmode_flags |= CXGB4_ACTION_NATMODE_SPORT; + } else { fs->nat_lport = val >> 16; + *natmode_flags |= CXGB4_ACTION_NATMODE_DPORT; + } } - fs->nat_mode = NAT_MODE_ALL; + break; + } +} + +static int cxgb4_action_natmode_validate(struct adapter *adap, u8 natmode_flags, + struct netlink_ext_ack *extack) +{ + u8 i = 0; + + /* Extract the NAT mode to enable based on what 4-tuple fields + * are enabled to be overwritten. This ensures that the + * disabled fields don't get overwritten to 0. + */ + for (i = 0; i < ARRAY_SIZE(cxgb4_natmode_config_array); i++) { + const struct cxgb4_natmode_config *c; + + c = &cxgb4_natmode_config_array[i]; + if (CHELSIO_CHIP_VERSION(adap->params.chip) >= c->chip && + natmode_flags == c->flags) + return 0; } + NL_SET_ERR_MSG_MOD(extack, "Unsupported NAT mode 4-tuple combination"); + return -EOPNOTSUPP; } void cxgb4_process_flow_actions(struct net_device *in, @@ -373,6 +491,7 @@ void cxgb4_process_flow_actions(struct net_device *in, struct ch_filter_specification *fs) { struct flow_action_entry *act; + u8 natmode_flags = 0; int i; flow_action_for_each(i, act, actions) { @@ -423,13 +542,17 @@ void cxgb4_process_flow_actions(struct net_device *in, val = act->mangle.val; offset = act->mangle.offset; - process_pedit_field(fs, val, mask, offset, htype); + process_pedit_field(fs, val, mask, offset, htype, + &natmode_flags); } break; default: break; } } + if (natmode_flags) + cxgb4_action_natmode_tweak(fs, natmode_flags); + } static bool valid_l4_mask(u32 mask) @@ -446,7 +569,8 @@ static bool valid_l4_mask(u32 mask) } static bool valid_pedit_action(struct net_device *dev, - const struct flow_action_entry *act) + const struct flow_action_entry *act, + u8 *natmode_flags) { u32 mask, offset; u8 htype; @@ -471,7 +595,10 @@ static bool valid_pedit_action(struct net_device *dev, case FLOW_ACT_MANGLE_HDR_TYPE_IP4: switch (offset) { case PEDIT_IP4_SRC: + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; + break; case PEDIT_IP4_DST: + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; break; default: netdev_err(dev, "%s: Unsupported pedit field\n", @@ -485,10 +612,13 @@ static bool valid_pedit_action(struct net_device *dev, case PEDIT_IP6_SRC_63_32: case PEDIT_IP6_SRC_95_64: case PEDIT_IP6_SRC_127_96: + *natmode_flags |= CXGB4_ACTION_NATMODE_SIP; + break; case PEDIT_IP6_DST_31_0: case PEDIT_IP6_DST_63_32: case PEDIT_IP6_DST_95_64: case PEDIT_IP6_DST_127_96: + *natmode_flags |= CXGB4_ACTION_NATMODE_DIP; break; default: netdev_err(dev, "%s: Unsupported pedit field\n", @@ -504,6 +634,10 @@ static bool valid_pedit_action(struct net_device *dev, __func__); return false; } + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + *natmode_flags |= CXGB4_ACTION_NATMODE_SPORT; + else + *natmode_flags |= CXGB4_ACTION_NATMODE_DPORT; break; default: netdev_err(dev, "%s: Unsupported pedit field\n", @@ -519,6 +653,10 @@ static bool valid_pedit_action(struct net_device *dev, __func__); return false; } + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + *natmode_flags |= CXGB4_ACTION_NATMODE_SPORT; + else + *natmode_flags |= CXGB4_ACTION_NATMODE_DPORT; break; default: netdev_err(dev, "%s: Unsupported pedit field\n", @@ -537,10 +675,12 @@ int cxgb4_validate_flow_actions(struct net_device *dev, struct flow_action *actions, struct netlink_ext_ack *extack) { + struct adapter *adap = netdev2adap(dev); struct flow_action_entry *act; bool act_redir = false; bool act_pedit = false; bool act_vlan = false; + u8 natmode_flags = 0; int i; if (!flow_action_basic_hw_stats_check(actions, extack)) @@ -553,7 +693,6 @@ int cxgb4_validate_flow_actions(struct net_device *dev, /* Do nothing */ break; case FLOW_ACTION_REDIRECT: { - struct adapter *adap = netdev2adap(dev); struct net_device *n_dev, *target_dev; unsigned int i; bool found = false; @@ -603,7 +742,8 @@ int cxgb4_validate_flow_actions(struct net_device *dev, } break; case FLOW_ACTION_MANGLE: { - bool pedit_valid = valid_pedit_action(dev, act); + bool pedit_valid = valid_pedit_action(dev, act, + &natmode_flags); if (!pedit_valid) return -EOPNOTSUPP; @@ -622,6 +762,15 @@ int cxgb4_validate_flow_actions(struct net_device *dev, return -EINVAL; } + if (act_pedit) { + int ret; + + ret = cxgb4_action_natmode_validate(adap, natmode_flags, + extack); + if (ret) + return ret; + } + return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h index 0a30c96b81ff..95142b1a88af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h @@ -108,6 +108,21 @@ struct ch_tc_pedit_fields { #define PEDIT_TCP_SPORT_DPORT 0x0 #define PEDIT_UDP_SPORT_DPORT 0x0 +enum cxgb4_action_natmode_flags { + CXGB4_ACTION_NATMODE_NONE = 0, + CXGB4_ACTION_NATMODE_DIP = (1 << 0), + CXGB4_ACTION_NATMODE_SIP = (1 << 1), + CXGB4_ACTION_NATMODE_DPORT = (1 << 2), + CXGB4_ACTION_NATMODE_SPORT = (1 << 3), +}; + +/* TC PEDIT action to NATMODE translation entry */ +struct cxgb4_natmode_config { + enum chip_type chip; + u8 flags; + u8 natmode; +}; + void cxgb4_process_flow_actions(struct net_device *in, struct flow_action *actions, struct ch_filter_specification *fs); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h index 50232e063f49..92473dda55d9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h @@ -50,6 +50,10 @@ #define TCB_T_FLAGS_M 0xffffffffffffffffULL #define TCB_T_FLAGS_V(x) ((__u64)(x) << TCB_T_FLAGS_S) +#define TF_DROP_S 22 +#define TF_DIRECT_STEER_S 23 +#define TF_LPBK_S 59 + #define TF_CCTRL_ECE_S 60 #define TF_CCTRL_CWR_S 61 #define TF_CCTRL_RFR_S 62 diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 18f3aeb88f22..c67a16a48d62 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -169,6 +169,7 @@ struct enic { u16 num_vfs; #endif spinlock_t enic_api_lock; + bool enic_api_busy; struct enic_port_profile *pp; /* work queue cache line section */ diff --git a/drivers/net/ethernet/cisco/enic/enic_api.c b/drivers/net/ethernet/cisco/enic/enic_api.c index b161f24522b8..b028ea2dec2b 100644 --- a/drivers/net/ethernet/cisco/enic/enic_api.c +++ b/drivers/net/ethernet/cisco/enic/enic_api.c @@ -34,6 +34,12 @@ int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf, struct vnic_dev *vdev = enic->vdev; spin_lock(&enic->enic_api_lock); + while (enic->enic_api_busy) { + spin_unlock(&enic->enic_api_lock); + cpu_relax(); + spin_lock(&enic->enic_api_lock); + } + spin_lock_bh(&enic->devcmd_lock); vnic_dev_cmd_proxy_by_index_start(vdev, vf); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index cd5fe4f6b54c..21093f33d2d7 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2140,8 +2140,6 @@ static int enic_dev_wait(struct vnic_dev *vdev, int done; int err; - BUG_ON(in_interrupt()); - err = start(vdev, arg); if (err) return err; @@ -2329,6 +2327,13 @@ static int enic_set_rss_nic_cfg(struct enic *enic) rss_hash_bits, rss_base_cpu, rss_enable); } +static void enic_set_api_busy(struct enic *enic, bool busy) +{ + spin_lock(&enic->enic_api_lock); + enic->enic_api_busy = busy; + spin_unlock(&enic->enic_api_lock); +} + static void enic_reset(struct work_struct *work) { struct enic *enic = container_of(work, struct enic, reset); @@ -2338,7 +2343,9 @@ static void enic_reset(struct work_struct *work) rtnl_lock(); - spin_lock(&enic->enic_api_lock); + /* Stop any activity from infiniband */ + enic_set_api_busy(enic, true); + enic_stop(enic->netdev); enic_dev_soft_reset(enic); enic_reset_addr_lists(enic); @@ -2346,7 +2353,10 @@ static void enic_reset(struct work_struct *work) enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); enic_open(enic->netdev); - spin_unlock(&enic->enic_api_lock); + + /* Allow infiniband to fiddle with the device again */ + enic_set_api_busy(enic, false); + call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev); rtnl_unlock(); @@ -2358,7 +2368,9 @@ static void enic_tx_hang_reset(struct work_struct *work) rtnl_lock(); - spin_lock(&enic->enic_api_lock); + /* Stop any activity from infiniband */ + enic_set_api_busy(enic, true); + enic_dev_hang_notify(enic); enic_stop(enic->netdev); enic_dev_hang_reset(enic); @@ -2367,7 +2379,10 @@ static void enic_tx_hang_reset(struct work_struct *work) enic_set_rss_nic_cfg(enic); enic_dev_set_ig_vlan_rewrite_mode(enic); enic_open(enic->netdev); - spin_unlock(&enic->enic_api_lock); + + /* Allow infiniband to fiddle with the device again */ + enic_set_api_busy(enic, false); + call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev); rtnl_unlock(); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 87236206366f..00024dd41147 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1817,6 +1817,11 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; + /* Disable ast2600 problematic HW arbitration */ + if (of_device_is_compatible(np, "aspeed,ast2600-mac")) { + iowrite32(FTGMAC100_TM_DEFAULT, + priv->base + FTGMAC100_OFFSET_TM); + } } else { priv->rxdes0_edorr_mask = BIT(15); priv->txdes0_edotr_mask = BIT(15); diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h index e5876a3fda91..63b3e02fab16 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.h +++ b/drivers/net/ethernet/faraday/ftgmac100.h @@ -170,6 +170,14 @@ #define FTGMAC100_MACCR_SW_RST (1 << 31) /* + * test mode control register + */ +#define FTGMAC100_TM_RQ_TX_VALID_DIS (1 << 28) +#define FTGMAC100_TM_RQ_RR_IDLE_PREV (1 << 27) +#define FTGMAC100_TM_DEFAULT \ + (FTGMAC100_TM_RQ_TX_VALID_DIS | FTGMAC100_TM_RQ_RR_IDLE_PREV) + +/* * PHY control register */ #define FTGMAC100_PHYCR_MDC_CYCTHR_MASK 0x3f diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 534fcc71a2a5..e1cd79555629 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1913,6 +1913,27 @@ out: return ret; } +static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + struct phy_device *phy_dev = ndev->phydev; + + if (phy_dev) { + phy_reset_after_clk_enable(phy_dev); + } else if (fep->phy_node) { + /* + * If the PHY still is not bound to the MAC, but there is + * OF PHY node and a matching PHY device instance already, + * use the OF PHY node to obtain the PHY device instance, + * and then use that PHY device instance when triggering + * the PHY reset. + */ + phy_dev = of_phy_find_device(fep->phy_node); + phy_reset_after_clk_enable(phy_dev); + put_device(&phy_dev->mdio.dev); + } +} + static int fec_enet_clk_enable(struct net_device *ndev, bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); @@ -1939,7 +1960,7 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) if (ret) goto failed_clk_ref; - phy_reset_after_clk_enable(ndev->phydev); + fec_enet_phy_reset_after_clk_enable(ndev); } else { clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { @@ -2985,16 +3006,16 @@ fec_enet_open(struct net_device *ndev) /* Init MAC prior to mii bus probe */ fec_restart(ndev); - /* Probe and connect to PHY when open the interface */ - ret = fec_enet_mii_probe(ndev); - if (ret) - goto err_enet_mii_probe; - /* Call phy_reset_after_clk_enable() again if it failed during * phy_reset_after_clk_enable() before because the PHY wasn't probed. */ if (reset_again) - phy_reset_after_clk_enable(ndev->phydev); + fec_enet_phy_reset_after_clk_enable(ndev); + + /* Probe and connect to PHY when open the interface */ + ret = fec_enet_mii_probe(ndev); + if (ret) + goto err_enet_mii_probe; if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_used(); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 9162856de1b1..ab15f1c588b3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3146,8 +3146,8 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev) hclgevf_uninit_msi(hdev); } - hclgevf_pci_uninit(hdev); hclgevf_cmd_uninit(hdev); + hclgevf_pci_uninit(hdev); hclgevf_uninit_mac_list(hdev); } diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index c5c732601e35..c3ec9ceed833 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1031,12 +1031,6 @@ static int ibmveth_is_packet_unsupported(struct sk_buff *skb, ret = -EOPNOTSUPP; } - if (!ether_addr_equal(ether_header->h_source, netdev->dev_addr)) { - netdev_dbg(netdev, "source packet MAC address does not match veth device's, dropping packet.\n"); - netdev->stats.tx_dropped++; - ret = -EOPNOTSUPP; - } - return ret; } @@ -1349,6 +1343,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) int offset = ibmveth_rxq_frame_offset(adapter); int csum_good = ibmveth_rxq_csum_good(adapter); int lrg_pkt = ibmveth_rxq_large_packet(adapter); + __sum16 iph_check = 0; skb = ibmveth_rxq_get_buffer(adapter); @@ -1385,16 +1380,26 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) skb_put(skb, length); skb->protocol = eth_type_trans(skb, netdev); - if (csum_good) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - ibmveth_rx_csum_helper(skb, adapter); + /* PHYP without PLSO support places a -1 in the ip + * checksum for large send frames. + */ + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + iph_check = iph->check; } - if (length > netdev->mtu + ETH_HLEN) { + if ((length > netdev->mtu + ETH_HLEN) || + lrg_pkt || iph_check == 0xffff) { ibmveth_rx_mss_helper(skb, mss, lrg_pkt); adapter->rx_large_packets++; } + if (csum_good) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + ibmveth_rx_csum_helper(skb, adapter); + } + napi_gro_receive(napi, skb); /* send it up */ netdev->stats.rx_packets++; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1b702a43a5d0..f96bb3dab5a8 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1828,9 +1828,13 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) int rc; rc = 0; - ether_addr_copy(adapter->mac_addr, addr->sa_data); - if (adapter->state != VNIC_PROBED) + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (adapter->state != VNIC_PROBED) { + ether_addr_copy(adapter->mac_addr, addr->sa_data); rc = __ibmvnic_set_mac(netdev, addr->sa_data); + } return rc; } @@ -4194,8 +4198,13 @@ static int handle_change_mac_rsp(union ibmvnic_crq *crq, dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc); goto out; } + /* crq->change_mac_addr.mac_addr is the requested one + * crq->change_mac_addr_rsp.mac_addr is the returned valid one. + */ ether_addr_copy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0]); + ether_addr_copy(adapter->mac_addr, + &crq->change_mac_addr_rsp.mac_addr[0]); out: complete(&adapter->fw_done); return rc; @@ -4605,7 +4614,7 @@ static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq, case IBMVNIC_1GBPS: adapter->speed = SPEED_1000; break; - case IBMVNIC_10GBP: + case IBMVNIC_10GBPS: adapter->speed = SPEED_10000; break; case IBMVNIC_25GBPS: @@ -4620,6 +4629,9 @@ static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq, case IBMVNIC_100GBPS: adapter->speed = SPEED_100000; break; + case IBMVNIC_200GBPS: + adapter->speed = SPEED_200000; + break; default: if (netif_carrier_ok(netdev)) netdev_warn(netdev, "Unknown speed 0x%08x\n", rspeed); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index f8416e1d4cf0..43feb96b0a68 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -373,7 +373,7 @@ struct ibmvnic_phys_parms { #define IBMVNIC_10MBPS 0x40000000 #define IBMVNIC_100MBPS 0x20000000 #define IBMVNIC_1GBPS 0x10000000 -#define IBMVNIC_10GBP 0x08000000 +#define IBMVNIC_10GBPS 0x08000000 #define IBMVNIC_40GBPS 0x04000000 #define IBMVNIC_100GBPS 0x02000000 #define IBMVNIC_25GBPS 0x01000000 diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 03e034918d14..bf48f0ded9c7 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1113,7 +1113,7 @@ out: return rc; probe_err_register: - kfree(lp->td_ring); + kfree((struct dma_desc *)KSEG0ADDR(lp->td_ring)); probe_err_td_ring: iounmap(lp->tx_dma_regs); probe_err_dma_tx: @@ -1133,6 +1133,7 @@ static int korina_remove(struct platform_device *pdev) iounmap(lp->eth_regs); iounmap(lp->rx_dma_regs); iounmap(lp->tx_dma_regs); + kfree((struct dma_desc *)KSEG0ADDR(lp->td_ring)); unregister_netdev(bif->dev); free_netdev(bif->dev); diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 62a820b1eb16..3362b148de23 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -17,6 +17,7 @@ config NET_MEDIATEK_SOC config NET_MEDIATEK_STAR_EMAC tristate "MediaTek STAR Ethernet MAC support" select PHYLIB + select REGMAP_MMIO help This driver supports the ethernet MAC IP first used on MediaTek MT85** SoCs. diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 8a10285b0e10..89edcb5fca4f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -943,6 +943,9 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget) bool clean_complete = true; int done; + if (!budget) + return 0; + if (priv->tx_ring_num[TX_XDP]) { xdp_tx_cq = priv->tx_cq[TX_XDP][cq->ring]; if (xdp_tx_cq->xdp_busy) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 9dff7b086c9f..1f11379ad5b6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -350,7 +350,7 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, .dma = tx_info->map0_dma, }; - if (!mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { + if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { dma_unmap_page(priv->ddev, tx_info->map0_dma, PAGE_SIZE, priv->dma_dir); put_page(tx_info->page); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 7283443868f3..13c87ab50b26 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -212,8 +212,8 @@ static int mlx5e_health_rsc_fmsg_binary(struct devlink_fmsg *fmsg, { u32 data_size; + int err = 0; u32 offset; - int err; for (offset = 0; offset < value_len; offset += data_size) { data_size = value_len - offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 2d55b7c22c03..4e7cfa22b3d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -550,8 +550,9 @@ static int mlx5_pps_event(struct notifier_block *nb, switch (clock->ptp_info.pin_config[pin].func) { case PTP_PF_EXTTS: ptp_event.index = pin; - ptp_event.timestamp = timecounter_cyc2time(&clock->tc, - be64_to_cpu(eqe->data.pps.time_stamp)); + ptp_event.timestamp = + mlx5_timecounter_cyc2time(clock, + be64_to_cpu(eqe->data.pps.time_stamp)); if (clock->pps_info.enabled) { ptp_event.type = PTP_CLOCK_PPSUSR; ptp_event.pps_times.ts_real = diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 71b6185b4904..42726fdf5a3a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1483,6 +1483,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, if (!reload) devlink_resources_unregister(devlink, NULL); mlxsw_core->bus->fini(mlxsw_core->bus_priv); + if (!reload) + devlink_free(devlink); return; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index fe173ea894e2..ed89e669ddd5 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4559,7 +4559,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) } rtl_irq_disable(tp); - napi_schedule_irqoff(&tp->napi); + napi_schedule(&tp->napi); out: rtl_ack_events(tp, status); @@ -4675,7 +4675,7 @@ static int rtl8169_close(struct net_device *dev) phy_disconnect(tp->phydev); - pci_free_irq(pdev, 0, tp); + free_irq(pci_irq_vector(pdev, 0), tp); dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray, tp->RxPhyAddr); @@ -4726,8 +4726,8 @@ static int rtl_open(struct net_device *dev) rtl_request_firmware(tp); - retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, tp, - dev->name); + retval = request_irq(pci_irq_vector(pdev, 0), rtl8169_interrupt, + IRQF_SHARED, dev->name, tp); if (retval < 0) goto err_release_fw_2; @@ -4759,7 +4759,7 @@ out: return retval; err_free_irq: - pci_free_irq(pdev, 0, tp); + free_irq(pci_irq_vector(pdev, 0), tp); err_release_fw_2: rtl_release_firmware(tp); rtl8169_rx_clear(tp); @@ -4871,6 +4871,10 @@ static int __maybe_unused rtl8169_resume(struct device *device) if (netif_running(tp->dev)) __rtl8169_resume(tp); + /* Reportedly at least Asus X453MA truncates packets otherwise */ + if (tp->mac_version == RTL_GIGA_MAC_VER_37) + rtl_init_rxcfg(tp); + return 0; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 99f7aae102ce..6c58ba186b2c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1747,12 +1747,16 @@ static int ravb_hwtstamp_get(struct net_device *ndev, struct ifreq *req) config.flags = 0; config.tx_type = priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_V2_L2_EVENT) + switch (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE) { + case RAVB_RXTSTAMP_TYPE_V2_L2_EVENT: config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; - else if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_ALL) + break; + case RAVB_RXTSTAMP_TYPE_ALL: config.rx_filter = HWTSTAMP_FILTER_ALL; - else + break; + default: config.rx_filter = HWTSTAMP_FILTER_NONE; + } return copy_to_user(req->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 0f366cc50b74..7f8be61a3708 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -6,6 +6,7 @@ #include <linux/pm_runtime.h> #include <linux/acpi.h> #include <linux/of_mdio.h> +#include <linux/of_net.h> #include <linux/etherdevice.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -1836,6 +1837,14 @@ static const struct net_device_ops netsec_netdev_ops = { static int netsec_of_probe(struct platform_device *pdev, struct netsec_priv *priv, u32 *phy_addr) { + int err; + + err = of_get_phy_mode(pdev->dev.of_node, &priv->phy_interface); + if (err) { + dev_err(&pdev->dev, "missing required property 'phy-mode'\n"); + return err; + } + priv->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!priv->phy_np) { dev_err(&pdev->dev, "missing required property 'phy-handle'\n"); @@ -1862,6 +1871,14 @@ static int netsec_acpi_probe(struct platform_device *pdev, if (!IS_ENABLED(CONFIG_ACPI)) return -ENODEV; + /* ACPI systems are assumed to configure the PHY in firmware, so + * there is really no need to discover the PHY mode from the DSDT. + * Since firmware is known to exist in the field that configures the + * PHY correctly but passes the wrong mode string in the phy-mode + * device property, we have no choice but to ignore it. + */ + priv->phy_interface = PHY_INTERFACE_MODE_NA; + ret = device_property_read_u32(&pdev->dev, "phy-channel", phy_addr); if (ret) { dev_err(&pdev->dev, @@ -1998,13 +2015,6 @@ static int netsec_probe(struct platform_device *pdev) priv->msg_enable = NETIF_MSG_TX_ERR | NETIF_MSG_HW | NETIF_MSG_DRV | NETIF_MSG_LINK | NETIF_MSG_PROBE; - priv->phy_interface = device_get_phy_mode(&pdev->dev); - if ((int)priv->phy_interface < 0) { - dev_err(&pdev->dev, "missing required property 'phy-mode'\n"); - ret = -ENODEV; - goto free_ndev; - } - priv->ioaddr = devm_ioremap(&pdev->dev, mmio_res->start, resource_size(mmio_res)); if (!priv->ioaddr) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 73465e5f5a41..d4be2559bb73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -176,32 +176,6 @@ static void stmmac_enable_all_queues(struct stmmac_priv *priv) } } -/** - * stmmac_stop_all_queues - Stop all queues - * @priv: driver private structure - */ -static void stmmac_stop_all_queues(struct stmmac_priv *priv) -{ - u32 tx_queues_cnt = priv->plat->tx_queues_to_use; - u32 queue; - - for (queue = 0; queue < tx_queues_cnt; queue++) - netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); -} - -/** - * stmmac_start_all_queues - Start all queues - * @priv: driver private structure - */ -static void stmmac_start_all_queues(struct stmmac_priv *priv) -{ - u32 tx_queues_cnt = priv->plat->tx_queues_to_use; - u32 queue; - - for (queue = 0; queue < tx_queues_cnt; queue++) - netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue)); -} - static void stmmac_service_event_schedule(struct stmmac_priv *priv) { if (!test_bit(STMMAC_DOWN, &priv->state) && @@ -2736,6 +2710,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_enable_tbs(priv, priv->ioaddr, enable, chan); } + /* Configure real RX and TX queues */ + netif_set_real_num_rx_queues(dev, priv->plat->rx_queues_to_use); + netif_set_real_num_tx_queues(dev, priv->plat->tx_queues_to_use); + /* Start the ball rolling... */ stmmac_start_all_dma(priv); @@ -2862,7 +2840,7 @@ static int stmmac_open(struct net_device *dev) } stmmac_enable_all_queues(priv); - stmmac_start_all_queues(priv); + netif_tx_start_all_queues(priv->dev); return 0; @@ -2903,8 +2881,6 @@ static int stmmac_release(struct net_device *dev) phylink_stop(priv->phylink); phylink_disconnect_phy(priv->phylink); - stmmac_stop_all_queues(priv); - stmmac_disable_all_queues(priv); for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) @@ -4819,10 +4795,6 @@ int stmmac_dvr_probe(struct device *device, stmmac_check_ether_addr(priv); - /* Configure real RX and TX queues */ - netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use); - netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use); - ndev->netdev_ops = &stmmac_netdev_ops; ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -5078,7 +5050,6 @@ int stmmac_suspend(struct device *dev) mutex_lock(&priv->lock); netif_device_detach(ndev); - stmmac_stop_all_queues(priv); stmmac_disable_all_queues(priv); @@ -5203,8 +5174,6 @@ int stmmac_resume(struct device *dev) stmmac_enable_all_queues(priv); - stmmac_start_all_queues(priv); - mutex_unlock(&priv->lock); if (!device_may_wakeup(priv->device)) { diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 8e47d0112e5d..10f910f8cbe5 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -663,10 +663,6 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gtp = netdev_priv(dev); - err = gtp_encap_enable(gtp, data); - if (err < 0) - return err; - if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; } else { @@ -677,12 +673,16 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, err = gtp_hashtable_new(gtp, hashsize); if (err < 0) - goto out_encap; + return err; + + err = gtp_encap_enable(gtp, data); + if (err < 0) + goto out_hashtable; err = register_netdevice(dev); if (err < 0) { netdev_dbg(dev, "failed to register new netdev %d\n", err); - goto out_hashtable; + goto out_encap; } gn = net_generic(dev_net(dev), gtp_net_id); @@ -693,11 +693,11 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, return 0; +out_encap: + gtp_encap_disable(gtp); out_hashtable: kfree(gtp->addr_hash); kfree(gtp->tid_hash); -out_encap: - gtp_encap_disable(gtp); return err; } diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index bdbfeed359db..41e9af35a582 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -398,15 +398,24 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size, /* assert(which < trans->tre_count); */ - /* Set the page information for the buffer. We also need to fill in - * the DMA address and length for the buffer (something dma_map_sg() - * normally does). + /* Commands are quite different from data transfer requests. + * Their payloads come from a pool whose memory is allocated + * using dma_alloc_coherent(). We therefore do *not* map them + * for DMA (unlike what we do for pages and skbs). + * + * When a transaction completes, the SGL is normally unmapped. + * A command transaction has direction DMA_NONE, which tells + * gsi_trans_complete() to skip the unmapping step. + * + * The only things we use directly in a command scatter/gather + * entry are the DMA address and length. We still need the SG + * table flags to be maintained though, so assign a NULL page + * pointer for that purpose. */ sg = &trans->sgl[which]; - - sg_set_buf(sg, buf, size); + sg_assign_page(sg, NULL); sg_dma_address(sg) = addr; - sg_dma_len(sg) = sg->length; + sg_dma_len(sg) = size; info = &trans->info[which]; info->opcode = opcode; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 9e58e495d373..bb46741fbe47 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1447,6 +1447,9 @@ void ipa_endpoint_resume_one(struct ipa_endpoint *endpoint) void ipa_endpoint_suspend(struct ipa *ipa) { + if (!ipa->setup_complete) + return; + if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); @@ -1458,6 +1461,9 @@ void ipa_endpoint_suspend(struct ipa *ipa) void ipa_endpoint_resume(struct ipa *ipa) { + if (!ipa->setup_complete) + return; + ipa_endpoint_resume_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); ipa_endpoint_resume_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 07c42c0719f5..5ca1356b8656 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1375,6 +1375,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ + {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index 9b00708676cf..1bdd3df0867a 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -46,7 +46,15 @@ static struct hdlc_proto *first_proto; static int hdlc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *p, struct net_device *orig_dev) { - struct hdlc_device *hdlc = dev_to_hdlc(dev); + struct hdlc_device *hdlc; + + /* First make sure "dev" is an HDLC device */ + if (!(dev->priv_flags & IFF_WAN_HDLC)) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + + hdlc = dev_to_hdlc(dev); if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(skb); diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c index 08e0a46501de..c70a518b8b47 100644 --- a/drivers/net/wan/hdlc_raw_eth.c +++ b/drivers/net/wan/hdlc_raw_eth.c @@ -99,6 +99,7 @@ static int raw_eth_ioctl(struct net_device *dev, struct ifreq *ifr) old_qlen = dev->tx_queue_len; ether_setup(dev); dev->tx_queue_len = old_qlen; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; eth_hw_addr_random(dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_off(dev); diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c index 294fbc1e89ab..e6e0284e4783 100644 --- a/drivers/net/wireless/ath/ath10k/ce.c +++ b/drivers/net/wireless/ath/ath10k/ce.c @@ -1555,7 +1555,7 @@ ath10k_ce_alloc_src_ring(struct ath10k *ar, unsigned int ce_id, ret = ath10k_ce_alloc_shadow_base(ar, src_ring, nentries); if (ret) { dma_free_coherent(ar->dev, - (nentries * sizeof(struct ce_desc_64) + + (nentries * sizeof(struct ce_desc) + CE_DESC_RING_ALIGN), src_ring->base_addr_owner_space_unaligned, base_addr); diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index d787cbead56a..215ade6faf32 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -142,6 +142,14 @@ static int __ath10k_htt_rx_ring_fill_n(struct ath10k_htt *htt, int num) BUILD_BUG_ON(HTT_RX_RING_FILL_LEVEL >= HTT_RX_RING_SIZE / 2); idx = __le32_to_cpu(*htt->rx_ring.alloc_idx.vaddr); + + if (idx < 0 || idx >= htt->rx_ring.size) { + ath10k_err(htt->ar, "rx ring index is not valid, firmware malfunctioning?\n"); + idx &= htt->rx_ring.size_mask; + ret = -ENOMEM; + goto fail; + } + while (num > 0) { skb = dev_alloc_skb(HTT_RX_BUF_SIZE + HTT_RX_DESC_ALIGN); if (!skb) { diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 919d15584d4a..77daca67a8e1 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -7283,7 +7283,7 @@ ath10k_mac_update_bss_chan_survey(struct ath10k *ar, struct ieee80211_channel *channel) { int ret; - enum wmi_bss_survey_req_type type = WMI_BSS_SURVEY_REQ_TYPE_READ_CLEAR; + enum wmi_bss_survey_req_type type = WMI_BSS_SURVEY_REQ_TYPE_READ; lockdep_assert_held(&ar->conf_mutex); diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c index 30092841ac46..a0314c1c8465 100644 --- a/drivers/net/wireless/ath/ath11k/ahb.c +++ b/drivers/net/wireless/ath/ath11k/ahb.c @@ -981,12 +981,16 @@ err_core_free: static int ath11k_ahb_remove(struct platform_device *pdev) { struct ath11k_base *ab = platform_get_drvdata(pdev); + unsigned long left; reinit_completion(&ab->driver_recovery); - if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags)) - wait_for_completion_timeout(&ab->driver_recovery, - ATH11K_AHB_RECOVERY_TIMEOUT); + if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags)) { + left = wait_for_completion_timeout(&ab->driver_recovery, + ATH11K_AHB_RECOVERY_TIMEOUT); + if (!left) + ath11k_warn(ab, "failed to receive recovery response completion\n"); + } set_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags); cancel_work_sync(&ab->restart_work); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 2836a0f197ab..fc5be7e8c043 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -5824,7 +5824,7 @@ static int __ath11k_mac_register(struct ath11k *ar) ret = ath11k_mac_setup_channels_rates(ar, cap->supported_bands); if (ret) - goto err_free; + goto err; ath11k_mac_setup_ht_vht_cap(ar, cap, &ht_cap); ath11k_mac_setup_he_cap(ar, cap); @@ -5938,7 +5938,9 @@ static int __ath11k_mac_register(struct ath11k *ar) err_free: kfree(ar->mac.sbands[NL80211_BAND_2GHZ].channels); kfree(ar->mac.sbands[NL80211_BAND_5GHZ].channels); + kfree(ar->mac.sbands[NL80211_BAND_6GHZ].channels); +err: SET_IEEE80211_DEV(ar->hw, NULL); return ret; } diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index c00a99ad8dbc..497cff7e64cc 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -2419,6 +2419,7 @@ int ath11k_qmi_init_service(struct ath11k_base *ab) ATH11K_QMI_WLFW_SERVICE_INS_ID_V01); if (ret < 0) { ath11k_warn(ab, "failed to add qmi lookup\n"); + destroy_workqueue(ab->qmi.event_wq); return ret; } diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c index 5e7ea838a921..814131a0680a 100644 --- a/drivers/net/wireless/ath/ath6kl/main.c +++ b/drivers/net/wireless/ath/ath6kl/main.c @@ -430,6 +430,9 @@ void ath6kl_connect_ap_mode_sta(struct ath6kl_vif *vif, u16 aid, u8 *mac_addr, ath6kl_dbg(ATH6KL_DBG_TRC, "new station %pM aid=%d\n", mac_addr, aid); + if (aid < 1 || aid > AP_MAX_NUM_STA) + return; + if (assoc_req_len > sizeof(struct ieee80211_hdr_3addr)) { struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) assoc_info; diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c index 6885d2ded53a..3d5db84d6465 100644 --- a/drivers/net/wireless/ath/ath6kl/wmi.c +++ b/drivers/net/wireless/ath/ath6kl/wmi.c @@ -2645,6 +2645,11 @@ int ath6kl_wmi_delete_pstream_cmd(struct wmi *wmi, u8 if_idx, u8 traffic_class, return -EINVAL; } + if (tsid >= 16) { + ath6kl_err("invalid tsid: %d\n", tsid); + return -EINVAL; + } + skb = ath6kl_wmi_get_new_buf(sizeof(*cmd)); if (!skb) return -ENOMEM; diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 3f563e02d17d..2ed98aaed6fb 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -449,10 +449,19 @@ static void hif_usb_stop(void *hif_handle) spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); /* The pending URBs have to be canceled. */ + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_pending, list) { + usb_get_urb(tx_buf->urb); + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_urb(tx_buf->urb); + list_del(&tx_buf->list); + usb_free_urb(tx_buf->urb); + kfree(tx_buf->buf); + kfree(tx_buf); + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_anchored_urbs(&hif_dev->mgmt_submitted); } @@ -762,27 +771,37 @@ static void ath9k_hif_usb_dealloc_tx_urbs(struct hif_device_usb *hif_dev) struct tx_buf *tx_buf = NULL, *tx_buf_tmp = NULL; unsigned long flags; + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_buf, list) { + usb_get_urb(tx_buf->urb); + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_urb(tx_buf->urb); list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); hif_dev->tx.flags |= HIF_USB_TX_FLUSH; spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_pending, list) { + usb_get_urb(tx_buf->urb); + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_urb(tx_buf->urb); list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); + spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } + spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_anchored_urbs(&hif_dev->mgmt_submitted); } diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index d2e062eaf561..510e61e97dbc 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -339,6 +339,8 @@ void ath9k_htc_txcompletion_cb(struct htc_target *htc_handle, if (skb) { htc_hdr = (struct htc_frame_hdr *) skb->data; + if (htc_hdr->endpoint_id >= ARRAY_SIZE(htc_handle->endpoint)) + goto ret; endpoint = &htc_handle->endpoint[htc_hdr->endpoint_id]; skb_pull(skb, sizeof(struct htc_frame_hdr)); diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 702b689c06df..f3ea629764fa 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -163,7 +163,7 @@ static struct ieee80211_supported_band wcn_band_5ghz = { .ampdu_density = IEEE80211_HT_MPDU_DENSITY_16, .mcs = { .rx_mask = { 0xff, 0, 0, 0, 0, 0, 0, 0, 0, 0, }, - .rx_highest = cpu_to_le16(72), + .rx_highest = cpu_to_le16(150), .tx_params = IEEE80211_HT_MCS_TX_DEFINED, } } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index c88655acc78c..76b478f70b4b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -483,7 +483,7 @@ static int brcmf_rx_hdrpull(struct brcmf_pub *drvr, struct sk_buff *skb, ret = brcmf_proto_hdrpull(drvr, true, skb, ifp); if (ret || !(*ifp) || !(*ifp)->ndev) { - if (ret != -ENODATA && *ifp) + if (ret != -ENODATA && *ifp && (*ifp)->ndev) (*ifp)->ndev->stats.rx_errors++; brcmu_pkt_buf_free_skb(skb); return -ENODATA; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c index 8bb4f1fa790e..1bb270e782ff 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c @@ -1619,6 +1619,8 @@ fail: BRCMF_TX_IOCTL_MAX_MSG_SIZE, msgbuf->ioctbuf, msgbuf->ioctbuf_handle); + if (msgbuf->txflow_wq) + destroy_workqueue(msgbuf->txflow_wq); kfree(msgbuf); } return -ENOMEM; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c index 7ef36234a25d..66797dc5e90d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c @@ -5065,8 +5065,10 @@ bool wlc_phy_attach_lcnphy(struct brcms_phy *pi) pi->pi_fptr.radioloftget = wlc_lcnphy_get_radio_loft; pi->pi_fptr.detach = wlc_phy_detach_lcnphy; - if (!wlc_phy_txpwr_srom_read_lcnphy(pi)) + if (!wlc_phy_txpwr_srom_read_lcnphy(pi)) { + kfree(pi->u.pi_lcnphy); return false; + } if (LCNREV_IS(pi->pubpi.phy_rev, 1)) { if (pi_lcn->lcnphy_tempsense_option == 3) { diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 27116c7d3f4f..48269a4cf896 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -947,9 +947,8 @@ static bool iwl_dbg_tlv_check_fw_pkt(struct iwl_fw_runtime *fwrt, struct iwl_rx_packet *pkt = tp_data->fw_pkt; struct iwl_cmd_header *wanted_hdr = (void *)&trig_data; - if (pkt && ((wanted_hdr->cmd == 0 && wanted_hdr->group_id == 0) || - (pkt->hdr.cmd == wanted_hdr->cmd && - pkt->hdr.group_id == wanted_hdr->group_id))) { + if (pkt && (pkt->hdr.cmd == wanted_hdr->cmd && + pkt->hdr.group_id == wanted_hdr->group_id)) { struct iwl_rx_packet *fw_pkt = kmemdup(pkt, sizeof(*pkt) + iwl_rx_packet_payload_len(pkt), @@ -1012,6 +1011,9 @@ static void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt) enum iwl_fw_ini_buffer_location *ini_dest = &fwrt->trans->dbg.ini_dest; int ret, i; + if (*ini_dest != IWL_FW_INI_LOCATION_INVALID) + return; + IWL_DEBUG_FW(fwrt, "WRT: Generating active triggers list, domain 0x%x\n", fwrt->trans->dbg.domains_bitmap); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 77916231ff7d..03b73003b009 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3685,9 +3685,12 @@ static int iwl_mvm_send_aux_roc_cmd(struct iwl_mvm *mvm, tail->apply_time_max_delay = cpu_to_le32(delay); IWL_DEBUG_TE(mvm, - "ROC: Requesting to remain on channel %u for %ums (requested = %ums, max_delay = %ums, dtim_interval = %ums)\n", - channel->hw_value, req_dur, duration, delay, - dtim_interval); + "ROC: Requesting to remain on channel %u for %ums\n", + channel->hw_value, req_dur); + IWL_DEBUG_TE(mvm, + "\t(requested = %ums, max_delay = %ums, dtim_interval = %ums)\n", + duration, delay, dtim_interval); + /* Set the node address */ memcpy(tail->node_addr, vif->addr, ETH_ALEN); diff --git a/drivers/net/wireless/intersil/p54/p54pci.c b/drivers/net/wireless/intersil/p54/p54pci.c index 80ad0b7eaef4..f8c6027cab6b 100644 --- a/drivers/net/wireless/intersil/p54/p54pci.c +++ b/drivers/net/wireless/intersil/p54/p54pci.c @@ -329,10 +329,12 @@ static void p54p_tx(struct ieee80211_hw *dev, struct sk_buff *skb) struct p54p_desc *desc; dma_addr_t mapping; u32 idx, i; + __le32 device_addr; spin_lock_irqsave(&priv->lock, flags); idx = le32_to_cpu(ring_control->host_idx[1]); i = idx % ARRAY_SIZE(ring_control->tx_data); + device_addr = ((struct p54_hdr *)skb->data)->req_id; mapping = pci_map_single(priv->pdev, skb->data, skb->len, PCI_DMA_TODEVICE); @@ -346,7 +348,7 @@ static void p54p_tx(struct ieee80211_hw *dev, struct sk_buff *skb) desc = &ring_control->tx_data[i]; desc->host_addr = cpu_to_le32(mapping); - desc->device_addr = ((struct p54_hdr *)skb->data)->req_id; + desc->device_addr = device_addr; desc->len = cpu_to_le16(skb->len); desc->flags = 0; diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index ff932627a46c..2fb69a590bd8 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -1889,7 +1889,7 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info, chan, CFG80211_BSS_FTYPE_UNKNOWN, bssid, timestamp, cap_info_bitmap, beacon_period, - ie_buf, ie_len, rssi, GFP_KERNEL); + ie_buf, ie_len, rssi, GFP_ATOMIC); if (bss) { bss_priv = (struct mwifiex_bss_priv *)bss->priv; bss_priv->band = band; diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index a042965962a2..1b6bee546528 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -1976,6 +1976,8 @@ error: kfree(card->mpa_rx.buf); card->mpa_tx.buf_size = 0; card->mpa_rx.buf_size = 0; + card->mpa_tx.buf = NULL; + card->mpa_rx.buf = NULL; } return ret; diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c index 6f3cfde4654c..426e39d4ccf0 100644 --- a/drivers/net/wireless/marvell/mwifiex/usb.c +++ b/drivers/net/wireless/marvell/mwifiex/usb.c @@ -1353,7 +1353,8 @@ static void mwifiex_usb_cleanup_tx_aggr(struct mwifiex_adapter *adapter) skb_dequeue(&port->tx_aggr.aggr_list))) mwifiex_write_data_complete(adapter, skb_tmp, 0, -1); - del_timer_sync(&port->tx_aggr.timer_cnxt.hold_timer); + if (port->tx_aggr.timer_cnxt.hold_timer.function) + del_timer_sync(&port->tx_aggr.timer_cnxt.hold_timer); port->tx_aggr.timer_cnxt.is_hold_timer_set = false; port->tx_aggr.timer_cnxt.hold_tmo_msecs = 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 8fb8255650a7..6969579e6b1d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -2267,14 +2267,6 @@ int mt7915_mcu_add_beacon(struct ieee80211_hw *hw, struct bss_info_bcn *bcn; int len = MT7915_BEACON_UPDATE_SIZE + MAX_BEACON_SIZE; - rskb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len); - if (IS_ERR(rskb)) - return PTR_ERR(rskb); - - tlv = mt7915_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn)); - bcn = (struct bss_info_bcn *)tlv; - bcn->enable = en; - skb = ieee80211_beacon_get_template(hw, vif, &offs); if (!skb) return -EINVAL; @@ -2285,6 +2277,16 @@ int mt7915_mcu_add_beacon(struct ieee80211_hw *hw, return -EINVAL; } + rskb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len); + if (IS_ERR(rskb)) { + dev_kfree_skb(skb); + return PTR_ERR(rskb); + } + + tlv = mt7915_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn)); + bcn = (struct bss_info_bcn *)tlv; + bcn->enable = en; + if (mvif->band_idx) { info = IEEE80211_SKB_CB(skb); info->hw_queue |= MT_TX_HW_QUEUE_EXT_PHY; diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index f40d8c3c3d9e..f3ccbd2b1084 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -869,6 +869,7 @@ int qtnf_cmd_send_del_intf(struct qtnf_vif *vif) default: pr_warn("VIF%u.%u: unsupported iftype %d\n", vif->mac->macid, vif->vifid, vif->wdev.iftype); + dev_kfree_skb(cmd_skb); ret = -EINVAL; goto out; } @@ -1924,6 +1925,7 @@ int qtnf_cmd_send_change_sta(struct qtnf_vif *vif, const u8 *mac, break; default: pr_err("unsupported iftype %d\n", vif->wdev.iftype); + dev_kfree_skb(cmd_skb); ret = -EINVAL; goto out; } diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 19efae462a24..5cd7ef3625c5 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5795,7 +5795,6 @@ static int rtl8xxxu_submit_int_urb(struct ieee80211_hw *hw) ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { usb_unanchor_urb(urb); - usb_free_urb(urb); goto error; } @@ -5804,6 +5803,7 @@ static int rtl8xxxu_submit_int_urb(struct ieee80211_hw *hw) rtl8xxxu_write32(priv, REG_USB_HIMR, val32); error: + usb_free_urb(urb); return ret; } @@ -6318,6 +6318,7 @@ static int rtl8xxxu_start(struct ieee80211_hw *hw) struct rtl8xxxu_priv *priv = hw->priv; struct rtl8xxxu_rx_urb *rx_urb; struct rtl8xxxu_tx_urb *tx_urb; + struct sk_buff *skb; unsigned long flags; int ret, i; @@ -6368,6 +6369,13 @@ static int rtl8xxxu_start(struct ieee80211_hw *hw) rx_urb->hw = hw; ret = rtl8xxxu_submit_rx_urb(priv, rx_urb); + if (ret) { + if (ret != -ENOMEM) { + skb = (struct sk_buff *)rx_urb->urb.context; + dev_kfree_skb(skb); + } + rtl8xxxu_queue_rx_urb(priv, rx_urb); + } } schedule_delayed_work(&priv->ra_watchdog, 2 * HZ); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 665d4bbdee6a..6a881d0be9bf 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -1465,6 +1465,9 @@ int rtw_core_init(struct rtw_dev *rtwdev) ret = rtw_load_firmware(rtwdev, RTW_WOWLAN_FW); if (ret) { rtw_warn(rtwdev, "no wow firmware loaded\n"); + wait_for_completion(&rtwdev->fw.completion); + if (rtwdev->fw.firmware) + release_firmware(rtwdev->fw.firmware); return ret; } } @@ -1479,6 +1482,8 @@ void rtw_core_deinit(struct rtw_dev *rtwdev) struct rtw_rsvd_page *rsvd_pkt, *tmp; unsigned long flags; + rtw_wait_firmware_completion(rtwdev); + if (fw->firmware) release_firmware(fw->firmware); diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c index 3413973bc475..7f1f5073b9f4 100644 --- a/drivers/net/wireless/realtek/rtw88/pci.c +++ b/drivers/net/wireless/realtek/rtw88/pci.c @@ -1599,6 +1599,8 @@ void rtw_pci_shutdown(struct pci_dev *pdev) if (chip->ops->shutdown) chip->ops->shutdown(rtwdev); + + pci_set_power_state(pdev, PCI_D3hot); } EXPORT_SYMBOL(rtw_pci_shutdown); diff --git a/drivers/net/wireless/realtek/rtw88/pci.h b/drivers/net/wireless/realtek/rtw88/pci.h index 024c2bc275cb..ca17aa9cf7dc 100644 --- a/drivers/net/wireless/realtek/rtw88/pci.h +++ b/drivers/net/wireless/realtek/rtw88/pci.h @@ -9,8 +9,8 @@ #define RTK_BEQ_TX_DESC_NUM 256 #define RTK_MAX_RX_DESC_NUM 512 -/* 8K + rx desc size */ -#define RTK_PCI_RX_BUF_SIZE (8192 + 24) +/* 11K + rx desc size */ +#define RTK_PCI_RX_BUF_SIZE (11454 + 24) #define RTK_PCI_CTRL 0x300 #define BIT_RST_TRXDMA_INTF BIT(20) diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c index 8d93f3159746..9687b376d221 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.c +++ b/drivers/net/wireless/realtek/rtw88/phy.c @@ -147,12 +147,13 @@ void rtw_phy_dig_write(struct rtw_dev *rtwdev, u8 igi) { struct rtw_chip_info *chip = rtwdev->chip; struct rtw_hal *hal = &rtwdev->hal; - const struct rtw_hw_reg *dig_cck = &chip->dig_cck[0]; u32 addr, mask; u8 path; - if (dig_cck) + if (chip->dig_cck) { + const struct rtw_hw_reg *dig_cck = &chip->dig_cck[0]; rtw_write32_mask(rtwdev, dig_cck->addr, dig_cck->mask, igi >> 1); + } for (path = 0; path < hal->rf_path_num; path++) { addr = chip->dig[path].addr; diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 88e1db65be02..71428d8cbcfc 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -1203,6 +1203,7 @@ static int amd_ntb_init_pci(struct amd_ntb_dev *ndev, err_dma_mask: pci_clear_master(pdev); + pci_release_regions(pdev); err_pci_regions: pci_disable_device(pdev); err_pci_enable: diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c index 423f9b8fbbcf..fa561d455f7c 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen1.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c @@ -1893,7 +1893,7 @@ static int intel_ntb_pci_probe(struct pci_dev *pdev, goto err_init_dev; } else { rc = -EINVAL; - goto err_ndev; + goto err_init_pci; } ndev_reset_unsafe_flags(ndev); diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index 45964acba944..22d865ba6353 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -268,7 +268,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns, if (rw == READ) { if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) return -EIO; - if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0) + if (copy_mc_to_kernel(buf, nsio->addr + offset, size) != 0) return -EIO; return 0; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d25e66fd942d..5a4f588605ca 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -125,7 +125,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off, while (len) { mem = kmap_atomic(page); chunk = min_t(unsigned int, len, PAGE_SIZE - off); - rem = memcpy_mcsafe(mem + off, pmem_addr, chunk); + rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk); kunmap_atomic(mem); if (rem) return BLK_STS_IOERR; @@ -305,7 +305,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev, /* * Use the 'no check' versions of copy_from_iter_flushcache() and - * copy_to_iter_mcsafe() to bypass HARDENED_USERCOPY overhead. Bounds + * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds * checking, both file offset and device offset, is handled by * dax_iomap_actor() */ @@ -318,7 +318,7 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { - return _copy_to_iter_mcsafe(addr, bytes, i); + return _copy_mc_to_iter(addr, bytes, i); } static const struct dax_operations pmem_dax_ops = { diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 58b035cc67a0..75ed95a250fb 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1142,7 +1142,8 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) * in case a host died before it enabled the controller. Hence, simply * reset the keep alive timer when the controller is enabled. */ - mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ); + if (ctrl->kato) + mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ); } static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 927eb5f6003f..4aca5b4a87d7 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -355,16 +355,14 @@ static void nvmem_cell_add(struct nvmem_cell *cell) blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_ADD, cell); } -static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - struct nvmem_cell *cell) +static int nvmem_cell_info_to_nvmem_cell_nodup(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info, + struct nvmem_cell *cell) { cell->nvmem = nvmem; cell->offset = info->offset; cell->bytes = info->bytes; - cell->name = kstrdup_const(info->name, GFP_KERNEL); - if (!cell->name) - return -ENOMEM; + cell->name = info->name; cell->bit_offset = info->bit_offset; cell->nbits = info->nbits; @@ -376,13 +374,30 @@ static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem, if (!IS_ALIGNED(cell->offset, nvmem->stride)) { dev_err(&nvmem->dev, "cell %s unaligned to nvmem stride %d\n", - cell->name, nvmem->stride); + cell->name ?: "<unknown>", nvmem->stride); return -EINVAL; } return 0; } +static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem, + const struct nvmem_cell_info *info, + struct nvmem_cell *cell) +{ + int err; + + err = nvmem_cell_info_to_nvmem_cell_nodup(nvmem, info, cell); + if (err) + return err; + + cell->name = kstrdup_const(info->name, GFP_KERNEL); + if (!cell->name) + return -ENOMEM; + + return 0; +} + /** * nvmem_add_cells() - Add cell information to an nvmem device * @@ -823,6 +838,7 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id) { struct device_node *nvmem_np; + struct nvmem_device *nvmem; int index = 0; if (id) @@ -832,7 +848,9 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-ENOENT); - return __nvmem_device_get(nvmem_np, device_match_of_node); + nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); + of_node_put(nvmem_np); + return nvmem; } EXPORT_SYMBOL_GPL(of_nvmem_device_get); #endif @@ -1433,7 +1451,7 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, if (!nvmem) return -EINVAL; - rc = nvmem_cell_info_to_nvmem_cell(nvmem, info, &cell); + rc = nvmem_cell_info_to_nvmem_cell_nodup(nvmem, info, &cell); if (rc) return rc; @@ -1463,7 +1481,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem, if (!nvmem) return -EINVAL; - rc = nvmem_cell_info_to_nvmem_cell(nvmem, info, &cell); + rc = nvmem_cell_info_to_nvmem_cell_nodup(nvmem, info, &cell); if (rc) return rc; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 91dcad982d36..11d192fb2e81 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -1918,6 +1918,9 @@ static void _opp_detach_genpd(struct opp_table *opp_table) { int index; + if (!opp_table->genpd_virt_devs) + return; + for (index = 0; index < opp_table->required_opp_count; index++) { if (!opp_table->genpd_virt_devs[index]) continue; @@ -1964,6 +1967,9 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, if (!opp_table) return ERR_PTR(-ENOMEM); + if (opp_table->genpd_virt_devs) + return opp_table; + /* * If the genpd's OPP table isn't already initialized, parsing of the * required-opps fail for dev. We should retry this after genpd's OPP diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 5e5b8821bed8..ce1c00ea5fdc 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -505,7 +505,8 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) u32 reg; int i; - hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE); + hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE) & + PCI_HEADER_TYPE_MASK; if (hdr_type != PCI_HEADER_TYPE_NORMAL) { dev_err(pci->dev, "PCIe controller is not set to EP mode (hdr_type:0x%x)!\n", diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 90ff291c24f0..c79326e699e8 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -9,7 +9,7 @@ */ #include <linux/delay.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> @@ -608,7 +608,7 @@ static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = { * Initialize the configuration space of the PCI-to-PCI bridge * associated with the given PCIe interface. */ -static void advk_sw_pci_bridge_init(struct advk_pcie *pcie) +static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) { struct pci_bridge_emul *bridge = &pcie->bridge; @@ -634,8 +634,7 @@ static void advk_sw_pci_bridge_init(struct advk_pcie *pcie) bridge->data = pcie; bridge->ops = &advk_pci_bridge_emul_ops; - pci_bridge_emul_init(bridge, 0); - + return pci_bridge_emul_init(bridge, 0); } static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, @@ -1069,7 +1068,9 @@ static int advk_pcie_enable_phy(struct advk_pcie *pcie) } ret = phy_power_on(pcie->phy); - if (ret) { + if (ret == -EOPNOTSUPP) { + dev_warn(&pcie->pdev->dev, "PHY unsupported by firmware\n"); + } else if (ret) { phy_exit(pcie->phy); return ret; } @@ -1169,7 +1170,11 @@ static int advk_pcie_probe(struct platform_device *pdev) advk_pcie_setup_hw(pcie); - advk_sw_pci_bridge_init(pcie); + ret = advk_sw_pci_bridge_init(pcie); + if (ret) { + dev_err(dev, "Failed to register emulated root PCI bridge\n"); + return ret; + } ret = advk_pcie_init_irq_domain(pcie); if (ret) { diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index bf40ff09c99d..95c04b0ffeb1 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1275,11 +1275,25 @@ static void hv_irq_unmask(struct irq_data *data) exit_unlock: spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags); - if (res) { + /* + * During hibernation, when a CPU is offlined, the kernel tries + * to move the interrupt to the remaining CPUs that haven't + * been offlined yet. In this case, the below hv_do_hypercall() + * always fails since the vmbus channel has been closed: + * refer to cpu_disable_common() -> fixup_irqs() -> + * irq_migrate_all_off_this_cpu() -> migrate_one_irq(). + * + * Suppress the error message for hibernation because the failure + * during hibernation does not matter (at this time all the devices + * have been frozen). Note: the correct affinity info is still updated + * into the irqdata data structure in migrate_one_irq() -> + * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM + * resumes, hv_pci_restore_msi_state() is able to correctly restore + * the interrupt with the correct affinity. + */ + if (res && hbus->state != hv_pcibus_removing) dev_err(&hbus->hdev->device, "%s() failed: %#llx", __func__, res); - return; - } pci_msi_unmask_irq(data); } @@ -3368,6 +3382,34 @@ static int hv_pci_suspend(struct hv_device *hdev) return 0; } +static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg) +{ + struct msi_desc *entry; + struct irq_data *irq_data; + + for_each_pci_msi_entry(entry, pdev) { + irq_data = irq_get_irq_data(entry->irq); + if (WARN_ON_ONCE(!irq_data)) + return -EINVAL; + + hv_compose_msi_msg(irq_data, &entry->msg); + } + + return 0; +} + +/* + * Upon resume, pci_restore_msi_state() -> ... -> __pci_write_msi_msg() + * directly writes the MSI/MSI-X registers via MMIO, but since Hyper-V + * doesn't trap and emulate the MMIO accesses, here hv_compose_msi_msg() + * must be used to ask Hyper-V to re-create the IOMMU Interrupt Remapping + * Table entries. + */ +static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus) +{ + pci_walk_bus(hbus->pci_bus, hv_pci_restore_msi_msg, NULL); +} + static int hv_pci_resume(struct hv_device *hdev) { struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); @@ -3401,6 +3443,8 @@ static int hv_pci_resume(struct hv_device *hdev) prepopulate_bars(hbus); + hv_pci_restore_msi_state(hbus); + hbus->state = hv_pcibus_installed; return 0; out: diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c index 3176ad3ab0e5..908475d27e0e 100644 --- a/drivers/pci/controller/pcie-iproc-msi.c +++ b/drivers/pci/controller/pcie-iproc-msi.c @@ -209,15 +209,20 @@ static int iproc_msi_irq_set_affinity(struct irq_data *data, struct iproc_msi *msi = irq_data_get_irq_chip_data(data); int target_cpu = cpumask_first(mask); int curr_cpu; + int ret; curr_cpu = hwirq_to_cpu(msi, data->hwirq); if (curr_cpu == target_cpu) - return IRQ_SET_MASK_OK_DONE; + ret = IRQ_SET_MASK_OK_DONE; + else { + /* steer MSI to the target CPU */ + data->hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq) + target_cpu; + ret = IRQ_SET_MASK_OK; + } - /* steer MSI to the target CPU */ - data->hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq) + target_cpu; + irq_data_update_effective_affinity(data, cpumask_of(target_cpu)); - return IRQ_SET_MASK_OK; + return ret; } static void iproc_msi_irq_compose_msi_msg(struct irq_data *data, diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index b37e08c4f9d1..4afd4ee4f7f0 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -180,6 +180,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id) virtfn->device = iov->vf_device; virtfn->is_virtfn = 1; virtfn->physfn = pci_dev_get(dev); + virtfn->no_command_memory = 1; if (id == 0) pci_read_vf_config_common(virtfn); diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c index aac9823b0c6b..e116815fa809 100644 --- a/drivers/perf/thunderx2_pmu.c +++ b/drivers/perf/thunderx2_pmu.c @@ -805,14 +805,17 @@ static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev, list_for_each_entry(rentry, &list, node) { if (resource_type(rentry->res) == IORESOURCE_MEM) { res = *rentry->res; + rentry = NULL; break; } } + acpi_dev_free_resource_list(&list); - if (!rentry->res) + if (rentry) { + dev_err(dev, "PMU type %d: Fail to find resource\n", type); return NULL; + } - acpi_dev_free_resource_list(&list); base = devm_ioremap_resource(dev, &res); if (IS_ERR(base)) { dev_err(dev, "PMU type %d: Fail to map resource\n", type); diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c index edac28cd25dd..633cf07ba672 100644 --- a/drivers/perf/xgene_pmu.c +++ b/drivers/perf/xgene_pmu.c @@ -1453,17 +1453,6 @@ static char *xgene_pmu_dev_name(struct device *dev, u32 type, int id) } #if defined(CONFIG_ACPI) -static int acpi_pmu_dev_add_resource(struct acpi_resource *ares, void *data) -{ - struct resource *res = data; - - if (ares->type == ACPI_RESOURCE_TYPE_FIXED_MEMORY32) - acpi_dev_resource_memory(ares, res); - - /* Always tell the ACPI core to skip this resource */ - return 1; -} - static struct xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu, struct acpi_device *adev, u32 type) @@ -1475,6 +1464,7 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu, struct hw_pmu_info *inf; void __iomem *dev_csr; struct resource res; + struct resource_entry *rentry; int enable_bit; int rc; @@ -1483,11 +1473,23 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu, return NULL; INIT_LIST_HEAD(&resource_list); - rc = acpi_dev_get_resources(adev, &resource_list, - acpi_pmu_dev_add_resource, &res); + rc = acpi_dev_get_resources(adev, &resource_list, NULL, NULL); + if (rc <= 0) { + dev_err(dev, "PMU type %d: No resources found\n", type); + return NULL; + } + + list_for_each_entry(rentry, &resource_list, node) { + if (resource_type(rentry->res) == IORESOURCE_MEM) { + res = *rentry->res; + rentry = NULL; + break; + } + } acpi_dev_free_resource_list(&resource_list); - if (rc < 0) { - dev_err(dev, "PMU type %d: No resource address found\n", type); + + if (rentry) { + dev_err(dev, "PMU type %d: No memory resource found\n", type); return NULL; } diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c index 1a138be8bd6a..810f25a47632 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -26,7 +26,6 @@ #define COMPHY_SIP_POWER_ON 0x82000001 #define COMPHY_SIP_POWER_OFF 0x82000002 #define COMPHY_SIP_PLL_LOCK 0x82000003 -#define COMPHY_FW_NOT_SUPPORTED (-1) #define COMPHY_FW_MODE_SATA 0x1 #define COMPHY_FW_MODE_SGMII 0x2 @@ -112,10 +111,19 @@ static int mvebu_a3700_comphy_smc(unsigned long function, unsigned long lane, unsigned long mode) { struct arm_smccc_res res; + s32 ret; arm_smccc_smc(function, lane, mode, 0, 0, 0, 0, 0, &res); + ret = res.a0; - return res.a0; + switch (ret) { + case SMCCC_RET_SUCCESS: + return 0; + case SMCCC_RET_NOT_SUPPORTED: + return -EOPNOTSUPP; + default: + return -EINVAL; + } } static int mvebu_a3700_comphy_get_fw_mode(int lane, int port, @@ -220,7 +228,7 @@ static int mvebu_a3700_comphy_power_on(struct phy *phy) } ret = mvebu_a3700_comphy_smc(COMPHY_SIP_POWER_ON, lane->id, fw_param); - if (ret == COMPHY_FW_NOT_SUPPORTED) + if (ret == -EOPNOTSUPP) dev_err(lane->dev, "unsupported SMC call, try updating your firmware\n"); diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c index e41367f36ee1..53ad127b100f 100644 --- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c @@ -123,7 +123,6 @@ #define COMPHY_SIP_POWER_ON 0x82000001 #define COMPHY_SIP_POWER_OFF 0x82000002 -#define COMPHY_FW_NOT_SUPPORTED (-1) /* * A lane is described by the following bitfields: @@ -273,10 +272,19 @@ static int mvebu_comphy_smc(unsigned long function, unsigned long phys, unsigned long lane, unsigned long mode) { struct arm_smccc_res res; + s32 ret; arm_smccc_smc(function, phys, lane, mode, 0, 0, 0, 0, &res); + ret = res.a0; - return res.a0; + switch (ret) { + case SMCCC_RET_SUCCESS: + return 0; + case SMCCC_RET_NOT_SUPPORTED: + return -EOPNOTSUPP; + default: + return -EINVAL; + } } static int mvebu_comphy_get_mode(bool fw_mode, int lane, int port, @@ -819,7 +827,7 @@ static int mvebu_comphy_power_on(struct phy *phy) if (!ret) return ret; - if (ret == COMPHY_FW_NOT_SUPPORTED) + if (ret == -EOPNOTSUPP) dev_err(priv->dev, "unsupported SMC call, try updating your firmware\n"); diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index b625a657171e..11e27136032b 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -515,7 +515,7 @@ int aspeed_pin_config_set(struct pinctrl_dev *pctldev, unsigned int offset, val = pmap->val << __ffs(pconf->mask); rc = regmap_update_bits(pdata->scu, pconf->reg, - pmap->mask, val); + pconf->mask, val); if (rc < 0) return rc; diff --git a/drivers/pinctrl/bcm/Kconfig b/drivers/pinctrl/bcm/Kconfig index dcf7df797af7..0ed14de0134c 100644 --- a/drivers/pinctrl/bcm/Kconfig +++ b/drivers/pinctrl/bcm/Kconfig @@ -23,6 +23,7 @@ config PINCTRL_BCM2835 select PINMUX select PINCONF select GENERIC_PINCONF + select GPIOLIB select GPIOLIB_IRQCHIP default ARCH_BCM2835 || ARCH_BRCMSTB help diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index c6fe7d64c913..c7448be64d07 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -129,9 +129,8 @@ static int dt_to_map_one_config(struct pinctrl *p, if (!np_pctldev || of_node_is_root(np_pctldev)) { of_node_put(np_pctldev); ret = driver_deferred_probe_check_state(p->dev); - /* keep deferring if modules are enabled unless we've timed out */ - if (IS_ENABLED(CONFIG_MODULES) && !allow_default && - (ret == -ENODEV)) + /* keep deferring if modules are enabled */ + if (IS_ENABLED(CONFIG_MODULES) && !allow_default && ret < 0) ret = -EPROBE_DEFER; return ret; } diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 151931b593f6..235a141182bf 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -87,7 +87,7 @@ const struct regmap_config mcp23x08_regmap = { }; EXPORT_SYMBOL_GPL(mcp23x08_regmap); -static const struct reg_default mcp23x16_defaults[] = { +static const struct reg_default mcp23x17_defaults[] = { {.reg = MCP_IODIR << 1, .def = 0xffff}, {.reg = MCP_IPOL << 1, .def = 0x0000}, {.reg = MCP_GPINTEN << 1, .def = 0x0000}, @@ -98,23 +98,23 @@ static const struct reg_default mcp23x16_defaults[] = { {.reg = MCP_OLAT << 1, .def = 0x0000}, }; -static const struct regmap_range mcp23x16_volatile_range = { +static const struct regmap_range mcp23x17_volatile_range = { .range_min = MCP_INTF << 1, .range_max = MCP_GPIO << 1, }; -static const struct regmap_access_table mcp23x16_volatile_table = { - .yes_ranges = &mcp23x16_volatile_range, +static const struct regmap_access_table mcp23x17_volatile_table = { + .yes_ranges = &mcp23x17_volatile_range, .n_yes_ranges = 1, }; -static const struct regmap_range mcp23x16_precious_range = { - .range_min = MCP_GPIO << 1, +static const struct regmap_range mcp23x17_precious_range = { + .range_min = MCP_INTCAP << 1, .range_max = MCP_GPIO << 1, }; -static const struct regmap_access_table mcp23x16_precious_table = { - .yes_ranges = &mcp23x16_precious_range, +static const struct regmap_access_table mcp23x17_precious_table = { + .yes_ranges = &mcp23x17_precious_range, .n_yes_ranges = 1, }; @@ -124,10 +124,10 @@ const struct regmap_config mcp23x17_regmap = { .reg_stride = 2, .max_register = MCP_OLAT << 1, - .volatile_table = &mcp23x16_volatile_table, - .precious_table = &mcp23x16_precious_table, - .reg_defaults = mcp23x16_defaults, - .num_reg_defaults = ARRAY_SIZE(mcp23x16_defaults), + .volatile_table = &mcp23x17_volatile_table, + .precious_table = &mcp23x17_precious_table, + .reg_defaults = mcp23x17_defaults, + .num_reg_defaults = ARRAY_SIZE(mcp23x17_defaults), .cache_type = REGCACHE_FLAT, .val_format_endian = REGMAP_ENDIAN_LITTLE, }; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index c322f30a2064..22283ba797cd 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1060,12 +1060,10 @@ static int msm_gpio_irq_set_wake(struct irq_data *d, unsigned int on) * when TLMM is powered on. To allow that, enable the GPIO * summary line to be wakeup capable at GIC. */ - if (d->parent_data) - irq_chip_set_wake_parent(d, on); - - irq_set_irq_wake(pctrl->irq, on); + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return irq_chip_set_wake_parent(d, on); - return 0; + return irq_set_irq_wake(pctrl->irq, on); } static int msm_gpio_irq_reqres(struct irq_data *d) @@ -1226,6 +1224,8 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; pctrl->irq_chip.irq_set_affinity = msm_gpio_irq_set_affinity; pctrl->irq_chip.irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity; + pctrl->irq_chip.flags = IRQCHIP_MASK_ON_SUSPEND | + IRQCHIP_SET_TYPE_MASKED; np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); if (np) { diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c index b59180bff5a3..ef61298c30bd 100644 --- a/drivers/platform/chrome/cros_ec_lightbar.c +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -116,6 +116,8 @@ static int get_lightbar_version(struct cros_ec_dev *ec, param = (struct ec_params_lightbar *)msg->data; param->cmd = LIGHTBAR_CMD_VERSION; + msg->outsize = sizeof(param->cmd); + msg->result = sizeof(resp->version); ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) { ret = 0; diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index c27548fd386a..0d2ed6d1f9c7 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -319,15 +319,6 @@ static struct i2c_board_info mlxplat_mlxcpld_psu[] = { }, }; -static struct i2c_board_info mlxplat_mlxcpld_ng_psu[] = { - { - I2C_BOARD_INFO("24c32", 0x51), - }, - { - I2C_BOARD_INFO("24c32", 0x50), - }, -}; - static struct i2c_board_info mlxplat_mlxcpld_pwr[] = { { I2C_BOARD_INFO("dps460", 0x59), @@ -752,15 +743,13 @@ static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_psu_items_data[] = { .label = "psu1", .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, .mask = BIT(0), - .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[0], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, }, { .label = "psu2", .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, .mask = BIT(1), - .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[1], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, }, }; diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index d88f388a3450..d5e84946a1da 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1347,7 +1347,7 @@ static int acpi_wmi_remove(struct platform_device *device) acpi_remove_address_space_handler(acpi_device->handle, ACPI_ADR_SPACE_EC, &acpi_wmi_ec_space_handler); wmi_free_devices(acpi_device); - device_destroy(&wmi_bus_class, MKDEV(0, 0)); + device_unregister((struct device *)dev_get_drvdata(&device->dev)); return 0; } @@ -1401,7 +1401,7 @@ static int acpi_wmi_probe(struct platform_device *device) return 0; err_remove_busdev: - device_destroy(&wmi_bus_class, MKDEV(0, 0)); + device_unregister(wmi_bus_dev); err_remove_notify_handler: acpi_remove_notify_handler(acpi_device->handle, ACPI_DEVICE_NOTIFY, diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c index 599a0f66a384..a34d95ed70b2 100644 --- a/drivers/pwm/pwm-img.c +++ b/drivers/pwm/pwm-img.c @@ -277,6 +277,8 @@ static int img_pwm_probe(struct platform_device *pdev) return PTR_ERR(pwm->pwm_clk); } + platform_set_drvdata(pdev, pwm); + pm_runtime_set_autosuspend_delay(&pdev->dev, IMG_PWM_PM_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_enable(&pdev->dev); @@ -313,7 +315,6 @@ static int img_pwm_probe(struct platform_device *pdev) goto err_suspend; } - platform_set_drvdata(pdev, pwm); return 0; err_suspend: diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c index 9d965ffe66d1..da9bc3d10104 100644 --- a/drivers/pwm/pwm-lpss.c +++ b/drivers/pwm/pwm-lpss.c @@ -93,10 +93,12 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, * The equation is: * base_unit = round(base_unit_range * freq / c) */ - base_unit_range = BIT(lpwm->info->base_unit_bits) - 1; + base_unit_range = BIT(lpwm->info->base_unit_bits); freq *= base_unit_range; base_unit = DIV_ROUND_CLOSEST_ULL(freq, c); + /* base_unit must not be 0 and we also want to avoid overflowing it */ + base_unit = clamp_val(base_unit, 1, base_unit_range - 1); on_time_div = 255ULL * duty_ns; do_div(on_time_div, period_ns); @@ -104,8 +106,7 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, orig_ctrl = ctrl = pwm_lpss_read(pwm); ctrl &= ~PWM_ON_TIME_DIV_MASK; - ctrl &= ~(base_unit_range << PWM_BASE_UNIT_SHIFT); - base_unit &= base_unit_range; + ctrl &= ~((base_unit_range - 1) << PWM_BASE_UNIT_SHIFT); ctrl |= (u32) base_unit << PWM_BASE_UNIT_SHIFT; ctrl |= on_time_div; diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c index eb8c9cb645a6..098e94335cb5 100644 --- a/drivers/pwm/pwm-rockchip.c +++ b/drivers/pwm/pwm-rockchip.c @@ -288,6 +288,7 @@ static int rockchip_pwm_probe(struct platform_device *pdev) const struct of_device_id *id; struct rockchip_pwm_chip *pc; struct resource *r; + u32 enable_conf, ctrl; int ret, count; id = of_match_device(rockchip_pwm_dt_ids, &pdev->dev); @@ -362,7 +363,9 @@ static int rockchip_pwm_probe(struct platform_device *pdev) } /* Keep the PWM clk enabled if the PWM appears to be up and running. */ - if (!pwm_is_enabled(pc->chip.pwms)) + enable_conf = pc->data->enable_conf; + ctrl = readl_relaxed(pc->base + pc->data->regs.ctrl); + if ((ctrl & enable_conf) != enable_conf) clk_disable(pc->clk); return 0; diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 451608e960a1..152946e033d1 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -871,15 +871,16 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, rmcd_error("pin_user_pages_fast err=%ld", pinned); nr_pages = 0; - } else + } else { rmcd_error("pinned %ld out of %ld pages", pinned, nr_pages); + /* + * Set nr_pages up to mean "how many pages to unpin, in + * the error handler: + */ + nr_pages = pinned; + } ret = -EFAULT; - /* - * Set nr_pages up to mean "how many pages to unpin, in - * the error handler: - */ - nr_pages = pinned; goto err_pg; } @@ -1679,6 +1680,7 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv, struct rio_dev *rdev; struct rio_switch *rswitch = NULL; struct rio_mport *mport; + struct device *dev; size_t size; u32 rval; u32 swpinfo = 0; @@ -1693,8 +1695,10 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv, rmcd_debug(RDEV, "name:%s ct:0x%x did:0x%x hc:0x%x", dev_info.name, dev_info.comptag, dev_info.destid, dev_info.hopcount); - if (bus_find_device_by_name(&rio_bus_type, NULL, dev_info.name)) { + dev = bus_find_device_by_name(&rio_bus_type, NULL, dev_info.name); + if (dev) { rmcd_debug(RDEV, "device %s already exists", dev_info.name); + put_device(dev); return -EEXIST; } diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index 569d9ad2c594..6939aa5b3dc7 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -553,20 +553,20 @@ static struct notifier_block cec_nb = { .priority = MCE_PRIO_CEC, }; -static void __init cec_init(void) +static int __init cec_init(void) { if (ce_arr.disabled) - return; + return -ENODEV; ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL); if (!ce_arr.array) { pr_err("Error allocating CE array page!\n"); - return; + return -ENOMEM; } if (create_debugfs_nodes()) { free_page((unsigned long)ce_arr.array); - return; + return -ENOMEM; } INIT_DELAYED_WORK(&cec_work, cec_work_fn); @@ -575,6 +575,7 @@ static void __init cec_init(void) mce_register_decode_chain(&cec_nb); pr_info("Correctable Errors collector initialized.\n"); + return 0; } late_initcall(cec_init); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index be8c709a7488..25e601bf9383 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5187,15 +5187,20 @@ regulator_register(const struct regulator_desc *regulator_desc, else if (regulator_desc->supply_name) rdev->supply_name = regulator_desc->supply_name; - /* - * Attempt to resolve the regulator supply, if specified, - * but don't return an error if we fail because we will try - * to resolve it again later as more regulators are added. - */ - if (regulator_resolve_supply(rdev)) - rdev_dbg(rdev, "unable to resolve supply\n"); - ret = set_machine_constraints(rdev, constraints); + if (ret == -EPROBE_DEFER) { + /* Regulator might be in bypass mode and so needs its supply + * to set the constraints */ + /* FIXME: this currently triggers a chicken-and-egg problem + * when creating -SUPPLY symlink in sysfs to a regulator + * that is just being created */ + ret = regulator_resolve_supply(rdev); + if (!ret) + ret = set_machine_constraints(rdev, constraints); + else + rdev_dbg(rdev, "unable to resolve supply early: %pe\n", + ERR_PTR(ret)); + } if (ret < 0) goto wash; diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c index 3d3d87210ef2..58d1d7e571d6 100644 --- a/drivers/remoteproc/mtk_scp_ipi.c +++ b/drivers/remoteproc/mtk_scp_ipi.c @@ -30,10 +30,8 @@ int scp_ipi_register(struct mtk_scp *scp, scp_ipi_handler_t handler, void *priv) { - if (!scp) { - dev_err(scp->dev, "scp device is not ready\n"); + if (!scp) return -EPROBE_DEFER; - } if (WARN_ON(id >= SCP_IPI_MAX) || WARN_ON(handler == NULL)) return -EINVAL; diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c index 83f2b8804ee9..96a17ec29140 100644 --- a/drivers/rpmsg/mtk_rpmsg.c +++ b/drivers/rpmsg/mtk_rpmsg.c @@ -200,7 +200,6 @@ static int mtk_rpmsg_register_device(struct mtk_rpmsg_rproc_subdev *mtk_subdev, struct rpmsg_device *rpdev; struct mtk_rpmsg_device *mdev; struct platform_device *pdev = mtk_subdev->pdev; - int ret; mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) @@ -219,13 +218,7 @@ static int mtk_rpmsg_register_device(struct mtk_rpmsg_rproc_subdev *mtk_subdev, rpdev->dev.parent = &pdev->dev; rpdev->dev.release = mtk_rpmsg_release_device; - ret = rpmsg_register_device(rpdev); - if (ret) { - kfree(mdev); - return ret; - } - - return 0; + return rpmsg_register_device(rpdev); } static void mtk_register_device_work_function(struct work_struct *register_work) diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c index 4abbeea782fa..19903de6268d 100644 --- a/drivers/rpmsg/qcom_smd.c +++ b/drivers/rpmsg/qcom_smd.c @@ -1338,7 +1338,7 @@ static int qcom_smd_parse_edge(struct device *dev, ret = of_property_read_u32(node, key, &edge->edge_id); if (ret) { dev_err(dev, "edge missing %s property\n", key); - return -EINVAL; + goto put_node; } edge->remote_pid = QCOM_SMEM_HOST_ANY; @@ -1349,32 +1349,37 @@ static int qcom_smd_parse_edge(struct device *dev, edge->mbox_client.knows_txdone = true; edge->mbox_chan = mbox_request_channel(&edge->mbox_client, 0); if (IS_ERR(edge->mbox_chan)) { - if (PTR_ERR(edge->mbox_chan) != -ENODEV) - return PTR_ERR(edge->mbox_chan); + if (PTR_ERR(edge->mbox_chan) != -ENODEV) { + ret = PTR_ERR(edge->mbox_chan); + goto put_node; + } edge->mbox_chan = NULL; syscon_np = of_parse_phandle(node, "qcom,ipc", 0); if (!syscon_np) { dev_err(dev, "no qcom,ipc node\n"); - return -ENODEV; + ret = -ENODEV; + goto put_node; } edge->ipc_regmap = syscon_node_to_regmap(syscon_np); - if (IS_ERR(edge->ipc_regmap)) - return PTR_ERR(edge->ipc_regmap); + if (IS_ERR(edge->ipc_regmap)) { + ret = PTR_ERR(edge->ipc_regmap); + goto put_node; + } key = "qcom,ipc"; ret = of_property_read_u32_index(node, key, 1, &edge->ipc_offset); if (ret < 0) { dev_err(dev, "no offset in %s\n", key); - return -EINVAL; + goto put_node; } ret = of_property_read_u32_index(node, key, 2, &edge->ipc_bit); if (ret < 0) { dev_err(dev, "no bit in %s\n", key); - return -EINVAL; + goto put_node; } } @@ -1385,7 +1390,8 @@ static int qcom_smd_parse_edge(struct device *dev, irq = irq_of_parse_and_map(node, 0); if (irq < 0) { dev_err(dev, "required smd interrupt missing\n"); - return -EINVAL; + ret = irq; + goto put_node; } ret = devm_request_irq(dev, irq, @@ -1393,12 +1399,18 @@ static int qcom_smd_parse_edge(struct device *dev, node->name, edge); if (ret) { dev_err(dev, "failed to request smd irq\n"); - return ret; + goto put_node; } edge->irq = irq; return 0; + +put_node: + of_node_put(node); + edge->of_node = NULL; + + return ret; } /* diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 49702942bb08..70b198423deb 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -352,6 +352,10 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) regmap_update_bits(ds1307->regmap, DS1340_REG_FLAG, DS1340_BIT_OSF, 0); break; + case ds_1388: + regmap_update_bits(ds1307->regmap, DS1388_REG_FLAG, + DS1388_BIT_OSF, 0); + break; case mcp794xx: /* * these bits were cleared when preparing the date/time diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 51ea56b73a97..4e30047d76c4 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -680,6 +680,11 @@ struct qeth_card_blkt { int inter_packet_jumbo; }; +enum qeth_pnso_mode { + QETH_PNSO_NONE, + QETH_PNSO_BRIDGEPORT, +}; + #define QETH_BROADCAST_WITH_ECHO 0x01 #define QETH_BROADCAST_WITHOUT_ECHO 0x02 struct qeth_card_info { @@ -696,6 +701,7 @@ struct qeth_card_info { /* no bitfield, we take a pointer on these two: */ u8 has_lp2lp_cso_v6; u8 has_lp2lp_cso_v4; + enum qeth_pnso_mode pnso_mode; enum qeth_card_types type; enum qeth_link_types link_type; int broadcast_capable; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index b4e06aeb6dc1..7c6f6a09b99e 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -273,6 +273,17 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, return qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN); } +static void qeth_l2_set_pnso_mode(struct qeth_card *card, + enum qeth_pnso_mode mode) +{ + spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card))); + WRITE_ONCE(card->info.pnso_mode, mode); + spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card))); + + if (mode == QETH_PNSO_NONE) + drain_workqueue(card->event_wq); +} + static void qeth_l2_stop_card(struct qeth_card *card) { QETH_CARD_TEXT(card, 2, "stopcard"); @@ -291,7 +302,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) qeth_qdio_clear_card(card, 0); qeth_clear_working_pool_list(card); - flush_workqueue(card->event_wq); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); qeth_flush_local_addrs(card); card->info.promisc_mode = 0; } @@ -1111,12 +1122,6 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) NULL }; - /* Role should not change by itself, but if it did, */ - /* information from the hardware is authoritative. */ - mutex_lock(&data->card->sbp_lock); - data->card->options.sbp.role = entry->role; - mutex_unlock(&data->card->sbp_lock); - snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); snprintf(env_role, sizeof(env_role), "ROLE=%s", (entry->role == QETH_SBP_ROLE_NONE) ? "none" : @@ -1165,19 +1170,34 @@ static void qeth_bridge_state_change(struct qeth_card *card, } struct qeth_addr_change_data { - struct work_struct worker; + struct delayed_work dwork; struct qeth_card *card; struct qeth_ipacmd_addr_change ac_event; }; static void qeth_addr_change_event_worker(struct work_struct *work) { - struct qeth_addr_change_data *data = - container_of(work, struct qeth_addr_change_data, worker); + struct delayed_work *dwork = to_delayed_work(work); + struct qeth_addr_change_data *data; + struct qeth_card *card; int i; + data = container_of(dwork, struct qeth_addr_change_data, dwork); + card = data->card; + QETH_CARD_TEXT(data->card, 4, "adrchgew"); + + if (READ_ONCE(card->info.pnso_mode) == QETH_PNSO_NONE) + goto free; + if (data->ac_event.lost_event_mask) { + /* Potential re-config in progress, try again later: */ + if (!mutex_trylock(&card->sbp_lock)) { + queue_delayed_work(card->event_wq, dwork, + msecs_to_jiffies(100)); + return; + } + dev_info(&data->card->gdev->dev, "Address change notification stopped on %s (%s)\n", data->card->dev->name, @@ -1186,8 +1206,9 @@ static void qeth_addr_change_event_worker(struct work_struct *work) : (data->ac_event.lost_event_mask == 0x02) ? "Bridge port state change" : "Unknown reason"); - mutex_lock(&data->card->sbp_lock); + data->card->options.sbp.hostnotification = 0; + card->info.pnso_mode = QETH_PNSO_NONE; mutex_unlock(&data->card->sbp_lock); qeth_bridge_emit_host_event(data->card, anev_abort, 0, NULL, NULL); @@ -1201,6 +1222,8 @@ static void qeth_addr_change_event_worker(struct work_struct *work) &entry->token, &entry->addr_lnid); } + +free: kfree(data); } @@ -1212,6 +1235,9 @@ static void qeth_addr_change_event(struct qeth_card *card, struct qeth_addr_change_data *data; int extrasize; + if (card->info.pnso_mode == QETH_PNSO_NONE) + return; + QETH_CARD_TEXT(card, 4, "adrchgev"); if (cmd->hdr.return_code != 0x0000) { if (cmd->hdr.return_code == 0x0010) { @@ -1231,11 +1257,11 @@ static void qeth_addr_change_event(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "ACNalloc"); return; } - INIT_WORK(&data->worker, qeth_addr_change_event_worker); + INIT_DELAYED_WORK(&data->dwork, qeth_addr_change_event_worker); data->card = card; memcpy(&data->ac_event, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(card->event_wq, &data->worker); + queue_delayed_work(card->event_wq, &data->dwork, 0); } /* SETBRIDGEPORT support; sending commands */ @@ -1556,9 +1582,14 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable) if (enable) { qeth_bridge_emit_host_event(card, anev_reset, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_BRIDGEPORT); rc = qeth_l2_pnso(card, 1, qeth_bridgeport_an_set_cb, card); - } else + if (rc) + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } else { rc = qeth_l2_pnso(card, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } return rc; } diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 86bcae992f72..4695d25e54f2 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -157,6 +157,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, rc = -EBUSY; else if (qeth_card_hw_is_reachable(card)) { rc = qeth_bridgeport_an_set(card, enable); + /* sbp_lock ensures ordering vs notifications-stopped events */ if (!rc) card->options.sbp.hostnotification = enable; } else diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 9b81cfbbc5c5..239e04c03cf9 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -3020,6 +3020,7 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } + mem->dma = paddr; mem->va = eq_vaddress; ret = be_fill_queue(eq, phba->params.num_eq_entries, sizeof(struct be_eq_entry), eq_vaddress); @@ -3029,7 +3030,6 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba, goto create_eq_error; } - mem->dma = paddr; ret = beiscsi_cmd_eq_create(&phba->ctrl, eq, BEISCSI_EQ_DELAY_DEF); if (ret) { @@ -3086,6 +3086,7 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } + mem->dma = paddr; ret = be_fill_queue(cq, phba->params.num_cq_entries, sizeof(struct sol_cqe), cq_vaddress); if (ret) { @@ -3095,7 +3096,6 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba, goto create_cq_error; } - mem->dma = paddr; ret = beiscsi_cmd_cq_create(&phba->ctrl, cq, eq, false, false, 0); if (ret) { diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c index bc5d84f87d8f..440ef32be048 100644 --- a/drivers/scsi/bfa/bfad.c +++ b/drivers/scsi/bfa/bfad.c @@ -749,6 +749,7 @@ bfad_pci_init(struct pci_dev *pdev, struct bfad_s *bfad) if (bfad->pci_bar0_kva == NULL) { printk(KERN_ERR "Fail to map bar0\n"); + rc = -ENODEV; goto out_release_region; } diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 950f9cdf0577..5d0f42031d12 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -2384,7 +2384,7 @@ static int csio_hw_prep_fw(struct csio_hw *hw, struct fw_info *fw_info, FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c), FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k), FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k)); - ret = EINVAL; + ret = -EINVAL; goto bye; } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 635f6f9cffc4..ef91f3d01f98 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4928,6 +4928,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id) if (IS_ERR(vhost->work_thread)) { dev_err(dev, "Couldn't create kernel thread: %ld\n", PTR_ERR(vhost->work_thread)); + rc = PTR_ERR(vhost->work_thread); goto free_host_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index a85c9672c6ea..a67749c8f4ab 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -1808,18 +1808,22 @@ mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc) /* TMs are on msix_index == 0 */ if (reply_q->msix_index == 0) continue; + synchronize_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index)); if (reply_q->irq_poll_scheduled) { /* Calling irq_poll_disable will wait for any pending * callbacks to have completed. */ irq_poll_disable(&reply_q->irqpoll); irq_poll_enable(&reply_q->irqpoll); - reply_q->irq_poll_scheduled = false; - reply_q->irq_line_enable = true; - enable_irq(reply_q->os_irq); - continue; + /* check how the scheduled poll has ended, + * clean up only if necessary + */ + if (reply_q->irq_poll_scheduled) { + reply_q->irq_poll_scheduled = false; + reply_q->irq_line_enable = true; + enable_irq(reply_q->os_irq); + } } - synchronize_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index)); } } diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c index 8906aceda4c4..0354898d7cac 100644 --- a/drivers/scsi/mvumi.c +++ b/drivers/scsi/mvumi.c @@ -2425,6 +2425,7 @@ static int mvumi_io_attach(struct mvumi_hba *mhba) if (IS_ERR(mhba->dm_thread)) { dev_err(&mhba->pdev->dev, "failed to create device scan thread\n"); + ret = PTR_ERR(mhba->dm_thread); mutex_unlock(&mhba->sas_discovery_mutex); goto fail_create_thread; } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 51cfab9d1afd..ed3054fffa34 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -704,7 +704,7 @@ static int qedf_eh_abort(struct scsi_cmnd *sc_cmd) rdata = fcport->rdata; if (!rdata || !kref_get_unless_zero(&rdata->kref)) { QEDF_ERR(&qedf->dbg_ctx, "stale rport, sc_cmd=%p\n", sc_cmd); - rc = 1; + rc = SUCCESS; goto out; } diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 946cebc4c932..90aa64604ad7 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -59,6 +59,7 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi, "Freeing tid=0x%x for cid=0x%x\n", cmd->task_id, qedi_conn->iscsi_conn_id); + spin_lock(&qedi_conn->list_lock); if (likely(cmd->io_cmd_in_list)) { cmd->io_cmd_in_list = false; list_del_init(&cmd->io_cmd); @@ -69,6 +70,7 @@ static void qedi_process_logout_resp(struct qedi_ctx *qedi, cmd->task_id, qedi_conn->iscsi_conn_id, &cmd->io_cmd); } + spin_unlock(&qedi_conn->list_lock); cmd->state = RESPONSE_RECEIVED; qedi_clear_task_idx(qedi, cmd->task_id); @@ -122,6 +124,7 @@ static void qedi_process_text_resp(struct qedi_ctx *qedi, "Freeing tid=0x%x for cid=0x%x\n", cmd->task_id, qedi_conn->iscsi_conn_id); + spin_lock(&qedi_conn->list_lock); if (likely(cmd->io_cmd_in_list)) { cmd->io_cmd_in_list = false; list_del_init(&cmd->io_cmd); @@ -132,6 +135,7 @@ static void qedi_process_text_resp(struct qedi_ctx *qedi, cmd->task_id, qedi_conn->iscsi_conn_id, &cmd->io_cmd); } + spin_unlock(&qedi_conn->list_lock); cmd->state = RESPONSE_RECEIVED; qedi_clear_task_idx(qedi, cmd->task_id); @@ -222,11 +226,13 @@ static void qedi_process_tmf_resp(struct qedi_ctx *qedi, tmf_hdr = (struct iscsi_tm *)qedi_cmd->task->hdr; + spin_lock(&qedi_conn->list_lock); if (likely(qedi_cmd->io_cmd_in_list)) { qedi_cmd->io_cmd_in_list = false; list_del_init(&qedi_cmd->io_cmd); qedi_conn->active_cmd_count--; } + spin_unlock(&qedi_conn->list_lock); if (((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) == ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) || @@ -288,11 +294,13 @@ static void qedi_process_login_resp(struct qedi_ctx *qedi, ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK; qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf + pld_len; + spin_lock(&qedi_conn->list_lock); if (likely(cmd->io_cmd_in_list)) { cmd->io_cmd_in_list = false; list_del_init(&cmd->io_cmd); qedi_conn->active_cmd_count--; } + spin_unlock(&qedi_conn->list_lock); memset(task_ctx, '\0', sizeof(*task_ctx)); @@ -817,8 +825,11 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi, qedi_clear_task_idx(qedi_conn->qedi, rtid); spin_lock(&qedi_conn->list_lock); - list_del_init(&dbg_cmd->io_cmd); - qedi_conn->active_cmd_count--; + if (likely(dbg_cmd->io_cmd_in_list)) { + dbg_cmd->io_cmd_in_list = false; + list_del_init(&dbg_cmd->io_cmd); + qedi_conn->active_cmd_count--; + } spin_unlock(&qedi_conn->list_lock); qedi_cmd->state = CLEANUP_RECV; wake_up_interruptible(&qedi_conn->wait_queue); @@ -1236,6 +1247,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, qedi_conn->cmd_cleanup_req++; qedi_iscsi_cleanup_task(ctask, true); + cmd->io_cmd_in_list = false; list_del_init(&cmd->io_cmd); qedi_conn->active_cmd_count--; QEDI_WARN(&qedi->dbg_ctx, @@ -1447,8 +1459,11 @@ ldel_exit: spin_unlock_bh(&qedi_conn->tmf_work_lock); spin_lock(&qedi_conn->list_lock); - list_del_init(&cmd->io_cmd); - qedi_conn->active_cmd_count--; + if (likely(cmd->io_cmd_in_list)) { + cmd->io_cmd_in_list = false; + list_del_init(&cmd->io_cmd); + qedi_conn->active_cmd_count--; + } spin_unlock(&qedi_conn->list_lock); clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags); diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 425e665ec08b..6e92625df4b7 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -975,11 +975,13 @@ static void qedi_cleanup_active_cmd_list(struct qedi_conn *qedi_conn) { struct qedi_cmd *cmd, *cmd_tmp; + spin_lock(&qedi_conn->list_lock); list_for_each_entry_safe(cmd, cmd_tmp, &qedi_conn->active_cmd_list, io_cmd) { list_del_init(&cmd->io_cmd); qedi_conn->active_cmd_count--; } + spin_unlock(&qedi_conn->list_lock); } static void qedi_ep_disconnect(struct iscsi_endpoint *ep) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 81a307695cc9..569fa4b28e4e 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1127,6 +1127,15 @@ static void qedi_schedule_recovery_handler(void *dev) schedule_delayed_work(&qedi->recovery_work, 0); } +static void qedi_set_conn_recovery(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *session = cls_session->dd_data; + struct iscsi_conn *conn = session->leadconn; + struct qedi_conn *qedi_conn = conn->dd_data; + + qedi_start_conn_recovery(qedi_conn->qedi, qedi_conn); +} + static void qedi_link_update(void *dev, struct qed_link_output *link) { struct qedi_ctx *qedi = (struct qedi_ctx *)dev; @@ -1138,6 +1147,7 @@ static void qedi_link_update(void *dev, struct qed_link_output *link) QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Link Down event.\n"); atomic_set(&qedi->link_state, QEDI_LINK_DOWN); + iscsi_host_for_each_session(qedi->shost, qedi_set_conn_recovery); } } diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 2861c636dd65..f17ab22ad0e4 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -63,6 +63,16 @@ void qla2x00_sp_free(srb_t *sp) qla2x00_rel_sp(sp); } +void qla2xxx_rel_done_warning(srb_t *sp, int res) +{ + WARN_ONCE(1, "Calling done() of an already freed srb %p object\n", sp); +} + +void qla2xxx_rel_free_warning(srb_t *sp) +{ + WARN_ONCE(1, "Calling free() of an already freed srb %p object\n", sp); +} + /* Asynchronous Login/Logout Routines -------------------------------------- */ unsigned long diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 1fb6ccac07cc..26d9c78d4c52 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -207,10 +207,15 @@ qla2xxx_get_qpair_sp(scsi_qla_host_t *vha, struct qla_qpair *qpair, return sp; } +void qla2xxx_rel_done_warning(srb_t *sp, int res); +void qla2xxx_rel_free_warning(srb_t *sp); + static inline void qla2xxx_rel_qpair_sp(struct qla_qpair *qpair, srb_t *sp) { sp->qpair = NULL; + sp->done = qla2xxx_rel_done_warning; + sp->free = qla2xxx_rel_free_warning; mempool_free(sp, qpair->srb_mempool); QLA_QPAIR_MARK_NOT_BUSY(qpair); } diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index fdb2ce7acb91..9f5d3aa1d874 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4908,7 +4908,7 @@ qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha) "Done %s.\n", __func__); } - dma_free_coherent(&ha->pdev->dev, DMA_POOL_SIZE, + dma_free_coherent(&ha->pdev->dev, ELS_CMD_MAP_SIZE, els_cmd_map, els_cmd_map_dma); return rval; diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 262dfd7635a4..7b14fd1cb030 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -683,7 +683,7 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha) struct nvme_fc_port_template *tmpl; struct qla_hw_data *ha; struct nvme_fc_port_info pinfo; - int ret = EINVAL; + int ret = -EINVAL; if (!IS_ENABLED(CONFIG_NVME_FC)) return ret; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 90289162dbd4..a034e9caa299 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -5668,7 +5668,7 @@ static int qlt_chk_unresolv_exchg(struct scsi_qla_host *vha, /* found existing exchange */ qpair->retry_term_cnt++; if (qpair->retry_term_cnt >= 5) { - rc = EIO; + rc = -EIO; qpair->retry_term_cnt = 0; ql_log(ql_log_warn, vha, 0xffff, "Unable to send ABTS Respond. Dumping firmware.\n"); diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 5dc697ce8b5d..4a6b15dc36aa 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -1220,7 +1220,7 @@ static int qla4xxx_get_host_stats(struct Scsi_Host *shost, char *buf, int len) le64_to_cpu(ql_iscsi_stats->iscsi_sequence_error); exit_host_stats: if (ql_iscsi_stats) - dma_free_coherent(&ha->pdev->dev, host_stats_size, + dma_free_coherent(&ha->pdev->dev, stats_size, ql_iscsi_stats, iscsi_stats_dma); ql4_printk(KERN_INFO, ha, "%s: Get host stats done\n", diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h index 1129fe7a27ed..ee069a8b442a 100644 --- a/drivers/scsi/smartpqi/smartpqi.h +++ b/drivers/scsi/smartpqi/smartpqi.h @@ -359,7 +359,7 @@ struct pqi_event_response { struct pqi_iu_header header; u8 event_type; u8 reserved2 : 7; - u8 request_acknowlege : 1; + u8 request_acknowledge : 1; __le16 event_id; __le32 additional_event_id; union { diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index cd157f11eb22..10afbaaa4a82 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -542,8 +542,7 @@ static int pqi_build_raid_path_request(struct pqi_ctrl_info *ctrl_info, put_unaligned_be16(cdb_length, &cdb[7]); break; default: - dev_err(&ctrl_info->pci_dev->dev, "unknown command 0x%c\n", - cmd); + dev_err(&ctrl_info->pci_dev->dev, "unknown command 0x%c\n", cmd); break; } @@ -2462,7 +2461,6 @@ static int pqi_raid_bypass_submit_scsi_cmd(struct pqi_ctrl_info *ctrl_info, offload_to_mirror = (offload_to_mirror >= layout_map_count - 1) ? 0 : offload_to_mirror + 1; - WARN_ON(offload_to_mirror >= layout_map_count); device->offload_to_mirror = offload_to_mirror; /* * Avoid direct use of device->offload_to_mirror within this @@ -2915,10 +2913,14 @@ static int pqi_interpret_task_management_response( return rc; } -static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, - struct pqi_queue_group *queue_group) +static inline void pqi_invalid_response(struct pqi_ctrl_info *ctrl_info) +{ + pqi_take_ctrl_offline(ctrl_info); +} + +static int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, struct pqi_queue_group *queue_group) { - unsigned int num_responses; + int num_responses; pqi_index_t oq_pi; pqi_index_t oq_ci; struct pqi_io_request *io_request; @@ -2930,6 +2932,13 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, while (1) { oq_pi = readl(queue_group->oq_pi); + if (oq_pi >= ctrl_info->num_elements_per_oq) { + pqi_invalid_response(ctrl_info); + dev_err(&ctrl_info->pci_dev->dev, + "I/O interrupt: producer index (%u) out of range (0-%u): consumer index: %u\n", + oq_pi, ctrl_info->num_elements_per_oq - 1, oq_ci); + return -1; + } if (oq_pi == oq_ci) break; @@ -2938,10 +2947,22 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, (oq_ci * PQI_OPERATIONAL_OQ_ELEMENT_LENGTH); request_id = get_unaligned_le16(&response->request_id); - WARN_ON(request_id >= ctrl_info->max_io_slots); + if (request_id >= ctrl_info->max_io_slots) { + pqi_invalid_response(ctrl_info); + dev_err(&ctrl_info->pci_dev->dev, + "request ID in response (%u) out of range (0-%u): producer index: %u consumer index: %u\n", + request_id, ctrl_info->max_io_slots - 1, oq_pi, oq_ci); + return -1; + } io_request = &ctrl_info->io_request_pool[request_id]; - WARN_ON(atomic_read(&io_request->refcount) == 0); + if (atomic_read(&io_request->refcount) == 0) { + pqi_invalid_response(ctrl_info); + dev_err(&ctrl_info->pci_dev->dev, + "request ID in response (%u) does not match an outstanding I/O request: producer index: %u consumer index: %u\n", + request_id, oq_pi, oq_ci); + return -1; + } switch (response->header.iu_type) { case PQI_RESPONSE_IU_RAID_PATH_IO_SUCCESS: @@ -2971,24 +2992,22 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info, io_request->error_info = ctrl_info->error_buffer + (get_unaligned_le16(&response->error_index) * PQI_ERROR_BUFFER_ELEMENT_LENGTH); - pqi_process_io_error(response->header.iu_type, - io_request); + pqi_process_io_error(response->header.iu_type, io_request); break; default: + pqi_invalid_response(ctrl_info); dev_err(&ctrl_info->pci_dev->dev, - "unexpected IU type: 0x%x\n", - response->header.iu_type); - break; + "unexpected IU type: 0x%x: producer index: %u consumer index: %u\n", + response->header.iu_type, oq_pi, oq_ci); + return -1; } - io_request->io_complete_callback(io_request, - io_request->context); + io_request->io_complete_callback(io_request, io_request->context); /* * Note that the I/O request structure CANNOT BE TOUCHED after * returning from the I/O completion callback! */ - oq_ci = (oq_ci + 1) % ctrl_info->num_elements_per_oq; } @@ -3301,9 +3320,9 @@ static void pqi_ofa_capture_event_payload(struct pqi_event *event, } } -static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info) +static int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info) { - unsigned int num_events; + int num_events; pqi_index_t oq_pi; pqi_index_t oq_ci; struct pqi_event_queue *event_queue; @@ -3317,26 +3336,31 @@ static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info) while (1) { oq_pi = readl(event_queue->oq_pi); + if (oq_pi >= PQI_NUM_EVENT_QUEUE_ELEMENTS) { + pqi_invalid_response(ctrl_info); + dev_err(&ctrl_info->pci_dev->dev, + "event interrupt: producer index (%u) out of range (0-%u): consumer index: %u\n", + oq_pi, PQI_NUM_EVENT_QUEUE_ELEMENTS - 1, oq_ci); + return -1; + } + if (oq_pi == oq_ci) break; num_events++; - response = event_queue->oq_element_array + - (oq_ci * PQI_EVENT_OQ_ELEMENT_LENGTH); + response = event_queue->oq_element_array + (oq_ci * PQI_EVENT_OQ_ELEMENT_LENGTH); event_index = pqi_event_type_to_event_index(response->event_type); - if (event_index >= 0) { - if (response->request_acknowlege) { - event = &ctrl_info->events[event_index]; - event->pending = true; - event->event_type = response->event_type; - event->event_id = response->event_id; - event->additional_event_id = - response->additional_event_id; + if (event_index >= 0 && response->request_acknowledge) { + event = &ctrl_info->events[event_index]; + event->pending = true; + event->event_type = response->event_type; + event->event_id = response->event_id; + event->additional_event_id = response->additional_event_id; + if (event->event_type == PQI_EVENT_TYPE_OFA) pqi_ofa_capture_event_payload(event, response); - } } oq_ci = (oq_ci + 1) % PQI_NUM_EVENT_QUEUE_ELEMENTS; @@ -3451,7 +3475,8 @@ static irqreturn_t pqi_irq_handler(int irq, void *data) { struct pqi_ctrl_info *ctrl_info; struct pqi_queue_group *queue_group; - unsigned int num_responses_handled; + int num_io_responses_handled; + int num_events_handled; queue_group = data; ctrl_info = queue_group->ctrl_info; @@ -3459,17 +3484,25 @@ static irqreturn_t pqi_irq_handler(int irq, void *data) if (!pqi_is_valid_irq(ctrl_info)) return IRQ_NONE; - num_responses_handled = pqi_process_io_intr(ctrl_info, queue_group); + num_io_responses_handled = pqi_process_io_intr(ctrl_info, queue_group); + if (num_io_responses_handled < 0) + goto out; - if (irq == ctrl_info->event_irq) - num_responses_handled += pqi_process_event_intr(ctrl_info); + if (irq == ctrl_info->event_irq) { + num_events_handled = pqi_process_event_intr(ctrl_info); + if (num_events_handled < 0) + goto out; + } else { + num_events_handled = 0; + } - if (num_responses_handled) + if (num_io_responses_handled + num_events_handled > 0) atomic_inc(&ctrl_info->num_interrupts); pqi_start_io(ctrl_info, queue_group, RAID_PATH, NULL); pqi_start_io(ctrl_info, queue_group, AIO_PATH, NULL); +out: return IRQ_HANDLED; } diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index d56ce8d97d4e..7ad127f21397 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -585,13 +585,7 @@ static int ufs_mtk_apply_dev_quirks(struct ufs_hba *hba) static void ufs_mtk_fixup_dev_quirks(struct ufs_hba *hba) { - struct ufs_dev_info *dev_info = &hba->dev_info; - u16 mid = dev_info->wmanufacturerid; - ufshcd_fixup_dev_quirks(hba, ufs_mtk_dev_fixups); - - if (mid == UFS_VENDOR_SAMSUNG) - hba->dev_quirks &= ~UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE; } /** diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 2e6ddb5cdfc2..7da27eed1fe7 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -1604,9 +1604,6 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host) */ } mask <<= offset; - - pm_runtime_get_sync(host->hba->dev); - ufshcd_hold(host->hba, false); ufshcd_rmwl(host->hba, TEST_BUS_SEL, (u32)host->testbus.select_major << 19, REG_UFS_CFG1); @@ -1619,8 +1616,6 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host) * committed before returning. */ mb(); - ufshcd_release(host->hba); - pm_runtime_put_sync(host->hba->dev); return 0; } diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 8bc8e4e62c04..e5f75b2e07e2 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -484,6 +484,9 @@ void ufshcd_print_trs(struct ufs_hba *hba, unsigned long bitmap, bool pr_prdt) prdt_length = le16_to_cpu( lrbp->utr_descriptor_ptr->prd_table_length); + if (hba->quirks & UFSHCD_QUIRK_PRDT_BYTE_GRAN) + prdt_length /= sizeof(struct ufshcd_sg_entry); + dev_err(hba->dev, "UPIU[%d] - PRDT - %d entries phys@0x%llx\n", tag, prdt_length, diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index ae1e248a8fb8..1d2bc181da05 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -301,8 +301,6 @@ int slim_unregister_controller(struct slim_controller *ctrl) { /* Remove all clients */ device_for_each_child(ctrl->dev, NULL, slim_ctrl_remove_device); - /* Enter Clock Pause */ - slim_ctrl_clk_pause(ctrl, false, 0); ida_simple_remove(&ctrl_ida, ctrl->id); return 0; @@ -326,8 +324,8 @@ void slim_report_absent(struct slim_device *sbdev) mutex_lock(&ctrl->lock); sbdev->is_laddr_valid = false; mutex_unlock(&ctrl->lock); - - ida_simple_remove(&ctrl->laddr_ida, sbdev->laddr); + if (!ctrl->get_laddr) + ida_simple_remove(&ctrl->laddr_ida, sbdev->laddr); slim_device_update_status(sbdev, SLIM_DEVICE_STATUS_DOWN); } EXPORT_SYMBOL_GPL(slim_report_absent); diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index 743ee7b4e63f..218aefc3531c 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1277,9 +1277,13 @@ static void qcom_slim_ngd_qmi_del_server(struct qmi_handle *hdl, { struct qcom_slim_ngd_qmi *qmi = container_of(hdl, struct qcom_slim_ngd_qmi, svc_event_hdl); + struct qcom_slim_ngd_ctrl *ctrl = + container_of(qmi, struct qcom_slim_ngd_ctrl, qmi); qmi->svc_info.sq_node = 0; qmi->svc_info.sq_port = 0; + + qcom_slim_ngd_enable(ctrl, false); } static struct qmi_ops qcom_slim_ngd_qmi_svc_event_ops = { diff --git a/drivers/soc/fsl/qbman/bman.c b/drivers/soc/fsl/qbman/bman.c index f4fb527d8301..c5dd026fe889 100644 --- a/drivers/soc/fsl/qbman/bman.c +++ b/drivers/soc/fsl/qbman/bman.c @@ -660,7 +660,7 @@ int bm_shutdown_pool(u32 bpid) } done: put_affine_portal(); - return 0; + return err; } struct gen_pool *bm_bpalloc; diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c index 87ee9f767b7a..d8ace96832ba 100644 --- a/drivers/soc/mediatek/mtk-cmdq-helper.c +++ b/drivers/soc/mediatek/mtk-cmdq-helper.c @@ -213,15 +213,16 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, } EXPORT_SYMBOL(cmdq_pkt_write_mask); -int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event) +int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear) { struct cmdq_instruction inst = { {0} }; + u32 clear_option = clear ? CMDQ_WFE_UPDATE : 0; if (event >= CMDQ_MAX_EVENT) return -EINVAL; inst.op = CMDQ_CODE_WFE; - inst.value = CMDQ_WFE_OPTION; + inst.value = CMDQ_WFE_OPTION | clear_option; inst.event = event; return cmdq_pkt_append_command(pkt, inst); diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 1f35b097c635..7abfc8c4fdc7 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -328,7 +328,7 @@ static int of_apr_add_pd_lookups(struct device *dev) pds = pdr_add_lookup(apr->pdr, service_name, service_path); if (IS_ERR(pds) && PTR_ERR(pds) != -EALREADY) { - dev_err(dev, "pdr add lookup failed: %d\n", ret); + dev_err(dev, "pdr add lookup failed: %ld\n", PTR_ERR(pds)); return PTR_ERR(pds); } } diff --git a/drivers/soc/qcom/pdr_internal.h b/drivers/soc/qcom/pdr_internal.h index 15b5002e4127..ab9ae8cdfa54 100644 --- a/drivers/soc/qcom/pdr_internal.h +++ b/drivers/soc/qcom/pdr_internal.h @@ -185,7 +185,7 @@ struct qmi_elem_info servreg_get_domain_list_resp_ei[] = { .data_type = QMI_STRUCT, .elem_len = SERVREG_DOMAIN_LIST_LENGTH, .elem_size = sizeof(struct servreg_location_entry), - .array_type = NO_ARRAY, + .array_type = VAR_LEN_ARRAY, .tlv_type = 0x12, .offset = offsetof(struct servreg_get_domain_list_resp, domain_list), diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c index 31ff49fcd078..c556623dae02 100644 --- a/drivers/soc/xilinx/zynqmp_power.c +++ b/drivers/soc/xilinx/zynqmp_power.c @@ -205,7 +205,7 @@ static int zynqmp_pm_probe(struct platform_device *pdev) rx_chan = mbox_request_channel_byname(client, "rx"); if (IS_ERR(rx_chan)) { dev_err(&pdev->dev, "Failed to request rx channel\n"); - return IS_ERR(rx_chan); + return PTR_ERR(rx_chan); } } else if (of_find_property(pdev->dev.of_node, "interrupts", NULL)) { irq = platform_get_irq(pdev, 0); diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c index 2ea73809ca34..271839a8add0 100644 --- a/drivers/spi/spi-dw-pci.c +++ b/drivers/spi/spi-dw-pci.c @@ -127,18 +127,16 @@ static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (desc->setup) { ret = desc->setup(dws); if (ret) - return ret; + goto err_free_irq_vectors; } } else { - pci_free_irq_vectors(pdev); - return -ENODEV; + ret = -ENODEV; + goto err_free_irq_vectors; } ret = dw_spi_add_host(&pdev->dev, dws); - if (ret) { - pci_free_irq_vectors(pdev); - return ret; - } + if (ret) + goto err_free_irq_vectors; /* PCI hook and SPI hook use the same drv data */ pci_set_drvdata(pdev, dws); @@ -152,6 +150,10 @@ static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pm_runtime_allow(&pdev->dev); return 0; + +err_free_irq_vectors: + pci_free_irq_vectors(pdev); + return ret; } static void spi_pci_remove(struct pci_dev *pdev) diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c index 37a3e0f8e752..a702e9d7d68c 100644 --- a/drivers/spi/spi-fsi.c +++ b/drivers/spi/spi-fsi.c @@ -24,11 +24,16 @@ #define SPI_FSI_BASE 0x70000 #define SPI_FSI_INIT_TIMEOUT_MS 1000 -#define SPI_FSI_MAX_TRANSFER_SIZE 2048 +#define SPI_FSI_MAX_XFR_SIZE 2048 +#define SPI_FSI_MAX_XFR_SIZE_RESTRICTED 32 #define SPI_FSI_ERROR 0x0 #define SPI_FSI_COUNTER_CFG 0x1 #define SPI_FSI_COUNTER_CFG_LOOPS(x) (((u64)(x) & 0xffULL) << 32) +#define SPI_FSI_COUNTER_CFG_N2_RX BIT_ULL(8) +#define SPI_FSI_COUNTER_CFG_N2_TX BIT_ULL(9) +#define SPI_FSI_COUNTER_CFG_N2_IMPLICIT BIT_ULL(10) +#define SPI_FSI_COUNTER_CFG_N2_RELOAD BIT_ULL(11) #define SPI_FSI_CFG1 0x2 #define SPI_FSI_CLOCK_CFG 0x3 #define SPI_FSI_CLOCK_CFG_MM_ENABLE BIT_ULL(32) @@ -61,7 +66,7 @@ #define SPI_FSI_STATUS_RDR_OVERRUN BIT_ULL(62) #define SPI_FSI_STATUS_RDR_FULL BIT_ULL(63) #define SPI_FSI_STATUS_ANY_ERROR \ - (SPI_FSI_STATUS_ERROR | SPI_FSI_STATUS_TDR_UNDERRUN | \ + (SPI_FSI_STATUS_ERROR | \ SPI_FSI_STATUS_TDR_OVERRUN | SPI_FSI_STATUS_RDR_UNDERRUN | \ SPI_FSI_STATUS_RDR_OVERRUN) #define SPI_FSI_PORT_CTRL 0x9 @@ -70,6 +75,8 @@ struct fsi_spi { struct device *dev; /* SPI controller device */ struct fsi_device *fsi; /* FSI2SPI CFAM engine device */ u32 base; + size_t max_xfr_size; + bool restricted; }; struct fsi_spi_sequence { @@ -205,8 +212,12 @@ static int fsi_spi_reset(struct fsi_spi *ctx) if (rc) return rc; - return fsi_spi_write_reg(ctx, SPI_FSI_CLOCK_CFG, - SPI_FSI_CLOCK_CFG_RESET2); + rc = fsi_spi_write_reg(ctx, SPI_FSI_CLOCK_CFG, + SPI_FSI_CLOCK_CFG_RESET2); + if (rc) + return rc; + + return fsi_spi_write_reg(ctx, SPI_FSI_STATUS, 0ULL); } static int fsi_spi_sequence_add(struct fsi_spi_sequence *seq, u8 val) @@ -214,8 +225,8 @@ static int fsi_spi_sequence_add(struct fsi_spi_sequence *seq, u8 val) /* * Add the next byte of instruction to the 8-byte sequence register. * Then decrement the counter so that the next instruction will go in - * the right place. Return the number of "slots" left in the sequence - * register. + * the right place. Return the index of the slot we just filled in the + * sequence register. */ seq->data |= (u64)val << seq->bit; seq->bit -= 8; @@ -233,40 +244,71 @@ static int fsi_spi_sequence_transfer(struct fsi_spi *ctx, struct fsi_spi_sequence *seq, struct spi_transfer *transfer) { + bool docfg = false; int loops; int idx; int rc; + u8 val = 0; u8 len = min(transfer->len, 8U); u8 rem = transfer->len % len; + u64 cfg = 0ULL; loops = transfer->len / len; if (transfer->tx_buf) { - idx = fsi_spi_sequence_add(seq, - SPI_FSI_SEQUENCE_SHIFT_OUT(len)); + val = SPI_FSI_SEQUENCE_SHIFT_OUT(len); + idx = fsi_spi_sequence_add(seq, val); + if (rem) rem = SPI_FSI_SEQUENCE_SHIFT_OUT(rem); } else if (transfer->rx_buf) { - idx = fsi_spi_sequence_add(seq, - SPI_FSI_SEQUENCE_SHIFT_IN(len)); + val = SPI_FSI_SEQUENCE_SHIFT_IN(len); + idx = fsi_spi_sequence_add(seq, val); + if (rem) rem = SPI_FSI_SEQUENCE_SHIFT_IN(rem); } else { return -EINVAL; } + if (ctx->restricted) { + const int eidx = rem ? 5 : 6; + + while (loops > 1 && idx <= eidx) { + idx = fsi_spi_sequence_add(seq, val); + loops--; + docfg = true; + } + + if (loops > 1) { + dev_warn(ctx->dev, "No sequencer slots; aborting.\n"); + return -EINVAL; + } + } + if (loops > 1) { fsi_spi_sequence_add(seq, SPI_FSI_SEQUENCE_BRANCH(idx)); + docfg = true; + } - if (rem) - fsi_spi_sequence_add(seq, rem); + if (docfg) { + cfg = SPI_FSI_COUNTER_CFG_LOOPS(loops - 1); + if (transfer->rx_buf) + cfg |= SPI_FSI_COUNTER_CFG_N2_RX | + SPI_FSI_COUNTER_CFG_N2_TX | + SPI_FSI_COUNTER_CFG_N2_IMPLICIT | + SPI_FSI_COUNTER_CFG_N2_RELOAD; - rc = fsi_spi_write_reg(ctx, SPI_FSI_COUNTER_CFG, - SPI_FSI_COUNTER_CFG_LOOPS(loops - 1)); + rc = fsi_spi_write_reg(ctx, SPI_FSI_COUNTER_CFG, cfg); if (rc) return rc; + } else { + fsi_spi_write_reg(ctx, SPI_FSI_COUNTER_CFG, 0ULL); } + if (rem) + fsi_spi_sequence_add(seq, rem); + return 0; } @@ -275,6 +317,7 @@ static int fsi_spi_transfer_data(struct fsi_spi *ctx, { int rc = 0; u64 status = 0ULL; + u64 cfg = 0ULL; if (transfer->tx_buf) { int nb; @@ -312,6 +355,16 @@ static int fsi_spi_transfer_data(struct fsi_spi *ctx, u64 in = 0ULL; u8 *rx = transfer->rx_buf; + rc = fsi_spi_read_reg(ctx, SPI_FSI_COUNTER_CFG, &cfg); + if (rc) + return rc; + + if (cfg & SPI_FSI_COUNTER_CFG_N2_IMPLICIT) { + rc = fsi_spi_write_reg(ctx, SPI_FSI_DATA_TX, 0); + if (rc) + return rc; + } + while (transfer->len > recv) { do { rc = fsi_spi_read_reg(ctx, SPI_FSI_STATUS, @@ -350,7 +403,7 @@ static int fsi_spi_transfer_init(struct fsi_spi *ctx) u64 status = 0ULL; u64 wanted_clock_cfg = SPI_FSI_CLOCK_CFG_ECC_DISABLE | SPI_FSI_CLOCK_CFG_SCK_NO_DEL | - FIELD_PREP(SPI_FSI_CLOCK_CFG_SCK_DIV, 4); + FIELD_PREP(SPI_FSI_CLOCK_CFG_SCK_DIV, 19); end = jiffies + msecs_to_jiffies(SPI_FSI_INIT_TIMEOUT_MS); do { @@ -407,7 +460,7 @@ static int fsi_spi_transfer_one_message(struct spi_controller *ctlr, /* Sequencer must do shift out (tx) first. */ if (!transfer->tx_buf || - transfer->len > SPI_FSI_MAX_TRANSFER_SIZE) { + transfer->len > (ctx->max_xfr_size + 8)) { rc = -EINVAL; goto error; } @@ -431,7 +484,7 @@ static int fsi_spi_transfer_one_message(struct spi_controller *ctlr, /* Sequencer can only do shift in (rx) after tx. */ if (next->rx_buf) { - if (next->len > SPI_FSI_MAX_TRANSFER_SIZE) { + if (next->len > ctx->max_xfr_size) { rc = -EINVAL; goto error; } @@ -476,7 +529,9 @@ error: static size_t fsi_spi_max_transfer_size(struct spi_device *spi) { - return SPI_FSI_MAX_TRANSFER_SIZE; + struct fsi_spi *ctx = spi_controller_get_devdata(spi->controller); + + return ctx->max_xfr_size; } static int fsi_spi_probe(struct device *dev) @@ -524,6 +579,14 @@ static int fsi_spi_probe(struct device *dev) ctx->fsi = fsi; ctx->base = base + SPI_FSI_BASE; + if (of_device_is_compatible(np, "ibm,fsi2spi-restricted")) { + ctx->restricted = true; + ctx->max_xfr_size = SPI_FSI_MAX_XFR_SIZE_RESTRICTED; + } else { + ctx->restricted = false; + ctx->max_xfr_size = SPI_FSI_MAX_XFR_SIZE; + } + rc = devm_spi_register_controller(dev, ctlr); if (rc) spi_controller_put(ctlr); diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index e9e256718ef4..10d8a722b083 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/gcd.h> -#include <linux/iopoll.h> #include <linux/spi/spi.h> #include <linux/gpio.h> @@ -349,9 +348,19 @@ disable_fifo: static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit) { - u32 val; - - return readl_poll_timeout(reg, val, val & bit, 1, MSEC_PER_SEC); + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(1000); + while (!(readl_relaxed(reg) & bit)) { + if (time_after(jiffies, timeout)) { + if (!(readl_relaxed(reg) & bit)) + return -ETIMEDOUT; + else + return 0; + } + cpu_relax(); + } + return 0; } static int mcspi_wait_for_completion(struct omap2_mcspi *mcspi, diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index cf67ea60dc0e..6587a7dc3f5b 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -122,6 +122,7 @@ struct s3c64xx_spi_dma_data { struct dma_chan *ch; + dma_cookie_t cookie; enum dma_transfer_direction direction; }; @@ -264,12 +265,13 @@ static void s3c64xx_spi_dmacb(void *data) spin_unlock_irqrestore(&sdd->lock, flags); } -static void prepare_dma(struct s3c64xx_spi_dma_data *dma, +static int prepare_dma(struct s3c64xx_spi_dma_data *dma, struct sg_table *sgt) { struct s3c64xx_spi_driver_data *sdd; struct dma_slave_config config; struct dma_async_tx_descriptor *desc; + int ret; memset(&config, 0, sizeof(config)); @@ -293,12 +295,24 @@ static void prepare_dma(struct s3c64xx_spi_dma_data *dma, desc = dmaengine_prep_slave_sg(dma->ch, sgt->sgl, sgt->nents, dma->direction, DMA_PREP_INTERRUPT); + if (!desc) { + dev_err(&sdd->pdev->dev, "unable to prepare %s scatterlist", + dma->direction == DMA_DEV_TO_MEM ? "rx" : "tx"); + return -ENOMEM; + } desc->callback = s3c64xx_spi_dmacb; desc->callback_param = dma; - dmaengine_submit(desc); + dma->cookie = dmaengine_submit(desc); + ret = dma_submit_error(dma->cookie); + if (ret) { + dev_err(&sdd->pdev->dev, "DMA submission failed"); + return -EIO; + } + dma_async_issue_pending(dma->ch); + return 0; } static void s3c64xx_spi_set_cs(struct spi_device *spi, bool enable) @@ -348,11 +362,12 @@ static bool s3c64xx_spi_can_dma(struct spi_master *master, return xfer->len > (FIFO_LVL_MASK(sdd) >> 1) + 1; } -static void s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd, +static int s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd, struct spi_transfer *xfer, int dma_mode) { void __iomem *regs = sdd->regs; u32 modecfg, chcfg; + int ret = 0; modecfg = readl(regs + S3C64XX_SPI_MODE_CFG); modecfg &= ~(S3C64XX_SPI_MODE_TXDMA_ON | S3C64XX_SPI_MODE_RXDMA_ON); @@ -378,7 +393,7 @@ static void s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd, chcfg |= S3C64XX_SPI_CH_TXCH_ON; if (dma_mode) { modecfg |= S3C64XX_SPI_MODE_TXDMA_ON; - prepare_dma(&sdd->tx_dma, &xfer->tx_sg); + ret = prepare_dma(&sdd->tx_dma, &xfer->tx_sg); } else { switch (sdd->cur_bpw) { case 32: @@ -410,12 +425,17 @@ static void s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd, writel(((xfer->len * 8 / sdd->cur_bpw) & 0xffff) | S3C64XX_SPI_PACKET_CNT_EN, regs + S3C64XX_SPI_PACKET_CNT); - prepare_dma(&sdd->rx_dma, &xfer->rx_sg); + ret = prepare_dma(&sdd->rx_dma, &xfer->rx_sg); } } + if (ret) + return ret; + writel(modecfg, regs + S3C64XX_SPI_MODE_CFG); writel(chcfg, regs + S3C64XX_SPI_CH_CFG); + + return 0; } static u32 s3c64xx_spi_wait_for_timeout(struct s3c64xx_spi_driver_data *sdd, @@ -548,9 +568,10 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd, return 0; } -static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd) +static int s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd) { void __iomem *regs = sdd->regs; + int ret; u32 val; /* Disable Clock */ @@ -598,7 +619,9 @@ static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd) if (sdd->port_conf->clk_from_cmu) { /* The src_clk clock is divided internally by 2 */ - clk_set_rate(sdd->src_clk, sdd->cur_speed * 2); + ret = clk_set_rate(sdd->src_clk, sdd->cur_speed * 2); + if (ret) + return ret; } else { /* Configure Clock */ val = readl(regs + S3C64XX_SPI_CLK_CFG); @@ -612,6 +635,8 @@ static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd) val |= S3C64XX_SPI_ENCLK_ENABLE; writel(val, regs + S3C64XX_SPI_CLK_CFG); } + + return 0; } #define XFER_DMAADDR_INVALID DMA_BIT_MASK(32) @@ -654,7 +679,9 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master, sdd->cur_bpw = bpw; sdd->cur_speed = speed; sdd->cur_mode = spi->mode; - s3c64xx_spi_config(sdd); + status = s3c64xx_spi_config(sdd); + if (status) + return status; } if (!is_polling(sdd) && (xfer->len > fifo_len) && @@ -678,13 +705,18 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master, sdd->state &= ~RXBUSY; sdd->state &= ~TXBUSY; - s3c64xx_enable_datapath(sdd, xfer, use_dma); - /* Start the signals */ s3c64xx_spi_set_cs(spi, true); + status = s3c64xx_enable_datapath(sdd, xfer, use_dma); + spin_unlock_irqrestore(&sdd->lock, flags); + if (status) { + dev_err(&spi->dev, "failed to enable data path for transfer: %d\n", status); + break; + } + if (use_dma) status = s3c64xx_wait_for_dma(sdd, xfer); else diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index 03929b9d3a8b..d0725bc8b48a 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -2593,7 +2593,7 @@ static int nbu2ss_ep_queue(struct usb_ep *_ep, if (req->unaligned) { if (!ep->virt_buf) - ep->virt_buf = dma_alloc_coherent(NULL, PAGE_SIZE, + ep->virt_buf = dma_alloc_coherent(udc->dev, PAGE_SIZE, &ep->phys_buf, GFP_ATOMIC | GFP_DMA); if (ep->epnum > 0) { @@ -3148,7 +3148,7 @@ static int nbu2ss_drv_remove(struct platform_device *pdev) for (i = 0; i < NUM_ENDPOINTS; i++) { ep = &udc->ep[i]; if (ep->virt_buf) - dma_free_coherent(NULL, PAGE_SIZE, (void *)ep->virt_buf, + dma_free_coherent(udc->dev, PAGE_SIZE, (void *)ep->virt_buf, ep->phys_buf); } diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index 54434c2dbaf9..8473e1437074 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -9521,7 +9521,7 @@ ia_css_stream_create(const struct ia_css_stream_config *stream_config, if (err) { IA_CSS_LEAVE_ERR(err); - return err; + goto ERR; } #endif for (i = 0; i < num_pipes; i++) diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c index d561f125085a..d72ebbd17a69 100644 --- a/drivers/staging/media/hantro/hantro_h264.c +++ b/drivers/staging/media/hantro/hantro_h264.c @@ -327,7 +327,7 @@ dma_addr_t hantro_h264_get_ref_buf(struct hantro_ctx *ctx, */ dst_buf = hantro_get_dst_buf(ctx); buf = &dst_buf->vb2_buf; - dma_addr = vb2_dma_contig_plane_dma_addr(buf, 0); + dma_addr = hantro_get_dec_buf_addr(ctx, buf); } return dma_addr; diff --git a/drivers/staging/media/hantro/hantro_postproc.c b/drivers/staging/media/hantro/hantro_postproc.c index 44062ffceaea..6d2a8f2a8f0b 100644 --- a/drivers/staging/media/hantro/hantro_postproc.c +++ b/drivers/staging/media/hantro/hantro_postproc.c @@ -118,7 +118,9 @@ int hantro_postproc_alloc(struct hantro_ctx *ctx) unsigned int num_buffers = cap_queue->num_buffers; unsigned int i, buf_size; - buf_size = ctx->dst_fmt.plane_fmt[0].sizeimage; + buf_size = ctx->dst_fmt.plane_fmt[0].sizeimage + + hantro_h264_mv_size(ctx->dst_fmt.width, + ctx->dst_fmt.height); for (i = 0; i < num_buffers; ++i) { struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i]; diff --git a/drivers/staging/media/ipu3/ipu3-css-params.c b/drivers/staging/media/ipu3/ipu3-css-params.c index fbd53d7c097c..e9d6bd9e9332 100644 --- a/drivers/staging/media/ipu3/ipu3-css-params.c +++ b/drivers/staging/media/ipu3/ipu3-css-params.c @@ -159,7 +159,7 @@ imgu_css_scaler_calc(u32 input_width, u32 input_height, u32 target_width, memset(&cfg->scaler_coeffs_chroma, 0, sizeof(cfg->scaler_coeffs_chroma)); - memset(&cfg->scaler_coeffs_luma, 0, sizeof(*cfg->scaler_coeffs_luma)); + memset(&cfg->scaler_coeffs_luma, 0, sizeof(cfg->scaler_coeffs_luma)); do { phase_step_correction++; diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c b/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c index 7c4df6d48c43..4df9476ef2a9 100644 --- a/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c +++ b/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c @@ -16,6 +16,7 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/io.h> #include <linux/mfd/syscon.h> #include <linux/module.h> diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c index 195d963c4fbb..b6fee7230ce0 100644 --- a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c +++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c @@ -597,7 +597,7 @@ static void RxReorderIndicatePacket(struct ieee80211_device *ieee, prxbIndicateArray = kmalloc_array(REORDER_WIN_SIZE, sizeof(struct ieee80211_rxb *), - GFP_KERNEL); + GFP_ATOMIC); if (!prxbIndicateArray) return; diff --git a/drivers/staging/wfx/data_rx.c b/drivers/staging/wfx/data_rx.c index 0e959ebc38b5..a9fb5165b33d 100644 --- a/drivers/staging/wfx/data_rx.c +++ b/drivers/staging/wfx/data_rx.c @@ -80,7 +80,7 @@ void wfx_rx_cb(struct wfx_vif *wvif, goto drop; if (arg->status == HIF_STATUS_RX_FAIL_MIC) - hdr->flag |= RX_FLAG_MMIC_ERROR; + hdr->flag |= RX_FLAG_MMIC_ERROR | RX_FLAG_IV_STRIPPED; else if (arg->status) goto drop; diff --git a/drivers/staging/wilc1000/mon.c b/drivers/staging/wilc1000/mon.c index 60331417bd98..66f1c870f4f6 100644 --- a/drivers/staging/wilc1000/mon.c +++ b/drivers/staging/wilc1000/mon.c @@ -236,11 +236,10 @@ struct net_device *wilc_wfi_init_mon_interface(struct wilc *wl, if (register_netdevice(wl->monitor_dev)) { netdev_err(real_dev, "register_netdevice failed\n"); + free_netdev(wl->monitor_dev); return NULL; } priv = netdev_priv(wl->monitor_dev); - if (!priv) - return NULL; priv->real_ndev = real_dev; diff --git a/drivers/staging/wilc1000/sdio.c b/drivers/staging/wilc1000/sdio.c index 36eb589263bf..b14e4ed6134f 100644 --- a/drivers/staging/wilc1000/sdio.c +++ b/drivers/staging/wilc1000/sdio.c @@ -151,9 +151,10 @@ static int wilc_sdio_probe(struct sdio_func *func, wilc->dev = &func->dev; wilc->rtc_clk = devm_clk_get(&func->card->dev, "rtc"); - if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) + if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) { + kfree(sdio_priv); return -EPROBE_DEFER; - else if (!IS_ERR(wilc->rtc_clk)) + } else if (!IS_ERR(wilc->rtc_clk)) clk_prepare_enable(wilc->rtc_clk); dev_info(&func->dev, "Driver Initializing success\n"); diff --git a/drivers/staging/wilc1000/spi.c b/drivers/staging/wilc1000/spi.c index 3f19e3f38a39..a18dac0aa6b6 100644 --- a/drivers/staging/wilc1000/spi.c +++ b/drivers/staging/wilc1000/spi.c @@ -112,9 +112,10 @@ static int wilc_bus_probe(struct spi_device *spi) wilc->dev_irq_num = spi->irq; wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc_clk"); - if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) + if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) { + kfree(spi_priv); return -EPROBE_DEFER; - else if (!IS_ERR(wilc->rtc_clk)) + } else if (!IS_ERR(wilc->rtc_clk)) clk_prepare_enable(wilc->rtc_clk); return 0; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 0209bc23e631..13a280c780c3 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -669,7 +669,7 @@ static void scatter_data_area(struct tcmu_dev *udev, void *from, *to = NULL; size_t copy_bytes, to_offset, offset; struct scatterlist *sg; - struct page *page; + struct page *page = NULL; for_each_sg(data_sg, sg, data_nents, i) { int sg_remaining = sg->length; diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig index d1b27b0522a3..8d60e0ff67b4 100644 --- a/drivers/tty/hvc/Kconfig +++ b/drivers/tty/hvc/Kconfig @@ -81,6 +81,7 @@ config HVC_DCC bool "ARM JTAG DCC console" depends on ARM || ARM64 select HVC_DRIVER + select SERIAL_CORE_CONSOLE help This console uses the JTAG DCC on ARM to create a console under the HVC driver. This console is used through a JTAG only on ARM. If you don't have diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c index 55105ac38f89..509d1042825a 100644 --- a/drivers/tty/hvc/hvcs.c +++ b/drivers/tty/hvc/hvcs.c @@ -1216,13 +1216,6 @@ static void hvcs_close(struct tty_struct *tty, struct file *filp) tty_wait_until_sent(tty, HVCS_CLOSE_WAIT); - /* - * This line is important because it tells hvcs_open that this - * device needs to be re-configured the next time hvcs_open is - * called. - */ - tty->driver_data = NULL; - free_irq(irq, hvcsd); return; } else if (hvcsd->port.count < 0) { @@ -1237,6 +1230,13 @@ static void hvcs_cleanup(struct tty_struct * tty) { struct hvcs_struct *hvcsd = tty->driver_data; + /* + * This line is important because it tells hvcs_open that this + * device needs to be re-configured the next time hvcs_open is + * called. + */ + tty->driver_data = NULL; + tty_port_put(&hvcsd->port); } diff --git a/drivers/tty/ipwireless/network.c b/drivers/tty/ipwireless/network.c index cf20616340a1..fe569f6294a2 100644 --- a/drivers/tty/ipwireless/network.c +++ b/drivers/tty/ipwireless/network.c @@ -117,7 +117,7 @@ static int ipwireless_ppp_start_xmit(struct ppp_channel *ppp_channel, skb->len, notify_packet_sent, network); - if (ret == -1) { + if (ret < 0) { skb_pull(skb, 2); return 0; } @@ -134,7 +134,7 @@ static int ipwireless_ppp_start_xmit(struct ppp_channel *ppp_channel, notify_packet_sent, network); kfree(buf); - if (ret == -1) + if (ret < 0) return 0; } kfree_skb(skb); diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c index fad3401e604d..23584769fc29 100644 --- a/drivers/tty/ipwireless/tty.c +++ b/drivers/tty/ipwireless/tty.c @@ -218,7 +218,7 @@ static int ipw_write(struct tty_struct *linux_tty, ret = ipwireless_send_packet(tty->hardware, IPW_CHANNEL_RAS, buf, count, ipw_write_packet_sent_callback, tty); - if (ret == -1) { + if (ret < 0) { mutex_unlock(&tty->ipw_tty_mutex); return 0; } diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 00099a8439d2..c6a1d8c4e689 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -120,10 +120,10 @@ static int pty_write(struct tty_struct *tty, const unsigned char *buf, int c) spin_lock_irqsave(&to->port->lock, flags); /* Stuff the data into the input queue of the other end */ c = tty_insert_flip_string(to->port, buf, c); + spin_unlock_irqrestore(&to->port->lock, flags); /* And shovel */ if (c) tty_flip_buffer_push(to->port); - spin_unlock_irqrestore(&to->port->lock, flags); } return c; } diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 780908d43557..896b9c77117d 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -8,6 +8,7 @@ menu "Serial drivers" config SERIAL_EARLYCON bool + depends on SERIAL_CORE help Support for early consoles with the earlycon parameter. This enables the console before standard serial driver is probed. The console is diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index a8d1edcf252c..64e801a3a020 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -308,8 +308,9 @@ static void pl011_write(unsigned int val, const struct uart_amba_port *uap, */ static int pl011_fifo_to_tty(struct uart_amba_port *uap) { - u16 status; unsigned int ch, flag, fifotaken; + int sysrq; + u16 status; for (fifotaken = 0; fifotaken != 256; fifotaken++) { status = pl011_read(uap, REG_FR); @@ -344,10 +345,12 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap) flag = TTY_FRAME; } - if (uart_handle_sysrq_char(&uap->port, ch & 255)) - continue; + spin_unlock(&uap->port.lock); + sysrq = uart_handle_sysrq_char(&uap->port, ch & 255); + spin_lock(&uap->port.lock); - uart_insert_char(&uap->port, ch, UART011_DR_OE, ch, flag); + if (!sysrq) + uart_insert_char(&uap->port, ch, UART011_DR_OE, ch, flag); } return fifotaken; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 90298c403042..f8ba7690efe3 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -649,26 +649,24 @@ static int lpuart32_poll_init(struct uart_port *port) spin_lock_irqsave(&sport->port.lock, flags); /* Disable Rx & Tx */ - lpuart32_write(&sport->port, UARTCTRL, 0); + lpuart32_write(&sport->port, 0, UARTCTRL); temp = lpuart32_read(&sport->port, UARTFIFO); /* Enable Rx and Tx FIFO */ - lpuart32_write(&sport->port, UARTFIFO, - temp | UARTFIFO_RXFE | UARTFIFO_TXFE); + lpuart32_write(&sport->port, temp | UARTFIFO_RXFE | UARTFIFO_TXFE, UARTFIFO); /* flush Tx and Rx FIFO */ - lpuart32_write(&sport->port, UARTFIFO, - UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH); + lpuart32_write(&sport->port, UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH, UARTFIFO); /* explicitly clear RDRF */ if (lpuart32_read(&sport->port, UARTSTAT) & UARTSTAT_RDRF) { lpuart32_read(&sport->port, UARTDATA); - lpuart32_write(&sport->port, UARTFIFO, UARTFIFO_RXUF); + lpuart32_write(&sport->port, UARTFIFO_RXUF, UARTFIFO); } /* Enable Rx and Tx */ - lpuart32_write(&sport->port, UARTCTRL, UARTCTRL_RE | UARTCTRL_TE); + lpuart32_write(&sport->port, UARTCTRL_RE | UARTCTRL_TE, UARTCTRL); spin_unlock_irqrestore(&sport->port.lock, flags); return 0; @@ -677,12 +675,12 @@ static int lpuart32_poll_init(struct uart_port *port) static void lpuart32_poll_put_char(struct uart_port *port, unsigned char c) { lpuart32_wait_bit_set(port, UARTSTAT, UARTSTAT_TDRE); - lpuart32_write(port, UARTDATA, c); + lpuart32_write(port, c, UARTDATA); } static int lpuart32_poll_get_char(struct uart_port *port) { - if (!(lpuart32_read(port, UARTSTAT) & UARTSTAT_RDRF)) + if (!(lpuart32_read(port, UARTWATER) >> UARTWATER_RXCNT_OFF)) return NO_POLL_CHAR; return lpuart32_read(port, UARTDATA); diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index ffdf6da016c2..2bb800ca5f0c 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -954,7 +954,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport, sampling_rate = UART_OVERSAMPLING; /* Sampling rate is halved for IP versions >= 2.5 */ ver = geni_se_get_qup_hw_version(&port->se); - if (GENI_SE_VERSION_MAJOR(ver) >= 2 && GENI_SE_VERSION_MINOR(ver) >= 5) + if (ver >= QUP_SE_VERSION_2_5) sampling_rate /= 2; clk_rate = get_clk_div_rate(baud, sampling_rate, &clk_div); diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 37ae7fc5f8dd..7bac485b49ba 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -2988,12 +2988,12 @@ void cdns3_gadget_exit(struct cdns3 *cdns) priv_dev = cdns->gadget_dev; - devm_free_irq(cdns->dev, cdns->dev_irq, priv_dev); pm_runtime_mark_last_busy(cdns->dev); pm_runtime_put_autosuspend(cdns->dev); usb_del_gadget_udc(&priv_dev->gadget); + devm_free_irq(cdns->dev, cdns->dev_irq, priv_dev); cdns3_free_all_eps(priv_dev); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 7499ba118665..808722b8294a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1243,9 +1243,21 @@ static int acm_probe(struct usb_interface *intf, } } } else { + int class = -1; + data_intf_num = union_header->bSlaveInterface0; control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0); data_interface = usb_ifnum_to_if(usb_dev, data_intf_num); + + if (control_interface) + class = control_interface->cur_altsetting->desc.bInterfaceClass; + + if (class != USB_CLASS_COMM && class != USB_CLASS_CDC_DATA) { + dev_dbg(&intf->dev, "Broken union descriptor, assuming single interface\n"); + combined_interfaces = 1; + control_interface = data_interface = intf; + goto look_for_collapsed_interface; + } } if (!control_interface || !data_interface) { @@ -1900,6 +1912,17 @@ static const struct usb_device_id acm_ids[] = { .driver_info = IGNORE_DEVICE, }, + /* Exclude ETAS ES58x */ + { USB_DEVICE(0x108c, 0x0159), /* ES581.4 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x108c, 0x0168), /* ES582.1 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x108c, 0x0169), /* ES584.1 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x1bc7, 0x0021), /* Telit 3G ACM only composition */ .driver_info = SEND_ZERO_PACKET, }, diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index e3db6fbeadef..0c7a0adfd1e1 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -58,6 +58,9 @@ MODULE_DEVICE_TABLE (usb, wdm_ids); #define WDM_MAX 16 +/* we cannot wait forever at flush() */ +#define WDM_FLUSH_TIMEOUT (30 * HZ) + /* CDC-WMC r1.1 requires wMaxCommand to be "at least 256 decimal (0x100)" */ #define WDM_DEFAULT_BUFSIZE 256 @@ -151,7 +154,7 @@ static void wdm_out_callback(struct urb *urb) kfree(desc->outbuf); desc->outbuf = NULL; clear_bit(WDM_IN_USE, &desc->flags); - wake_up(&desc->wait); + wake_up_all(&desc->wait); } static void wdm_in_callback(struct urb *urb) @@ -393,6 +396,9 @@ static ssize_t wdm_write if (test_bit(WDM_RESETTING, &desc->flags)) r = -EIO; + if (test_bit(WDM_DISCONNECTING, &desc->flags)) + r = -ENODEV; + if (r < 0) { rv = r; goto out_free_mem_pm; @@ -424,6 +430,7 @@ static ssize_t wdm_write if (rv < 0) { desc->outbuf = NULL; clear_bit(WDM_IN_USE, &desc->flags); + wake_up_all(&desc->wait); /* for wdm_wait_for_response() */ dev_err(&desc->intf->dev, "Tx URB error: %d\n", rv); rv = usb_translate_errors(rv); goto out_free_mem_pm; @@ -583,28 +590,58 @@ err: return rv; } -static int wdm_flush(struct file *file, fl_owner_t id) +static int wdm_wait_for_response(struct file *file, long timeout) { struct wdm_device *desc = file->private_data; + long rv; /* Use long here because (int) MAX_SCHEDULE_TIMEOUT < 0. */ + + /* + * Needs both flags. We cannot do with one because resetting it would + * cause a race with write() yet we need to signal a disconnect. + */ + rv = wait_event_interruptible_timeout(desc->wait, + !test_bit(WDM_IN_USE, &desc->flags) || + test_bit(WDM_DISCONNECTING, &desc->flags), + timeout); - wait_event(desc->wait, - /* - * needs both flags. We cannot do with one - * because resetting it would cause a race - * with write() yet we need to signal - * a disconnect - */ - !test_bit(WDM_IN_USE, &desc->flags) || - test_bit(WDM_DISCONNECTING, &desc->flags)); - - /* cannot dereference desc->intf if WDM_DISCONNECTING */ + /* + * To report the correct error. This is best effort. + * We are inevitably racing with the hardware. + */ if (test_bit(WDM_DISCONNECTING, &desc->flags)) return -ENODEV; - if (desc->werr < 0) - dev_err(&desc->intf->dev, "Error in flush path: %d\n", - desc->werr); + if (!rv) + return -EIO; + if (rv < 0) + return -EINTR; + + spin_lock_irq(&desc->iuspin); + rv = desc->werr; + desc->werr = 0; + spin_unlock_irq(&desc->iuspin); + + return usb_translate_errors(rv); + +} + +/* + * You need to send a signal when you react to malicious or defective hardware. + * Also, don't abort when fsync() returned -EINVAL, for older kernels which do + * not implement wdm_flush() will return -EINVAL. + */ +static int wdm_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + return wdm_wait_for_response(file, MAX_SCHEDULE_TIMEOUT); +} - return usb_translate_errors(desc->werr); +/* + * Same with wdm_fsync(), except it uses finite timeout in order to react to + * malicious or defective hardware which ceased communication after close() was + * implicitly called due to process termination. + */ +static int wdm_flush(struct file *file, fl_owner_t id) +{ + return wdm_wait_for_response(file, WDM_FLUSH_TIMEOUT); } static __poll_t wdm_poll(struct file *file, struct poll_table_struct *wait) @@ -729,6 +766,7 @@ static const struct file_operations wdm_fops = { .owner = THIS_MODULE, .read = wdm_read, .write = wdm_write, + .fsync = wdm_fsync, .open = wdm_open, .flush = wdm_flush, .release = wdm_release, diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index da923ec17612..31ca5abb4c12 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -772,11 +772,12 @@ void usb_block_urb(struct urb *urb) EXPORT_SYMBOL_GPL(usb_block_urb); /** - * usb_kill_anchored_urbs - cancel transfer requests en masse + * usb_kill_anchored_urbs - kill all URBs associated with an anchor * @anchor: anchor the requests are bound to * - * this allows all outstanding URBs to be killed starting - * from the back of the queue + * This kills all outstanding URBs starting from the back of the queue, + * with guarantee that no completer callbacks will take place from the + * anchor after this function returns. * * This routine should not be called by a driver after its disconnect * method has returned. @@ -784,20 +785,26 @@ EXPORT_SYMBOL_GPL(usb_block_urb); void usb_kill_anchored_urbs(struct usb_anchor *anchor) { struct urb *victim; + int surely_empty; - spin_lock_irq(&anchor->lock); - while (!list_empty(&anchor->urb_list)) { - victim = list_entry(anchor->urb_list.prev, struct urb, - anchor_list); - /* we must make sure the URB isn't freed before we kill it*/ - usb_get_urb(victim); - spin_unlock_irq(&anchor->lock); - /* this will unanchor the URB */ - usb_kill_urb(victim); - usb_put_urb(victim); + do { spin_lock_irq(&anchor->lock); - } - spin_unlock_irq(&anchor->lock); + while (!list_empty(&anchor->urb_list)) { + victim = list_entry(anchor->urb_list.prev, + struct urb, anchor_list); + /* make sure the URB isn't freed before we kill it */ + usb_get_urb(victim); + spin_unlock_irq(&anchor->lock); + /* this will unanchor the URB */ + usb_kill_urb(victim); + usb_put_urb(victim); + spin_lock_irq(&anchor->lock); + } + surely_empty = usb_anchor_check_wakeup(anchor); + + spin_unlock_irq(&anchor->lock); + cpu_relax(); + } while (!surely_empty); } EXPORT_SYMBOL_GPL(usb_kill_anchored_urbs); @@ -816,21 +823,27 @@ EXPORT_SYMBOL_GPL(usb_kill_anchored_urbs); void usb_poison_anchored_urbs(struct usb_anchor *anchor) { struct urb *victim; + int surely_empty; - spin_lock_irq(&anchor->lock); - anchor->poisoned = 1; - while (!list_empty(&anchor->urb_list)) { - victim = list_entry(anchor->urb_list.prev, struct urb, - anchor_list); - /* we must make sure the URB isn't freed before we kill it*/ - usb_get_urb(victim); - spin_unlock_irq(&anchor->lock); - /* this will unanchor the URB */ - usb_poison_urb(victim); - usb_put_urb(victim); + do { spin_lock_irq(&anchor->lock); - } - spin_unlock_irq(&anchor->lock); + anchor->poisoned = 1; + while (!list_empty(&anchor->urb_list)) { + victim = list_entry(anchor->urb_list.prev, + struct urb, anchor_list); + /* make sure the URB isn't freed before we kill it */ + usb_get_urb(victim); + spin_unlock_irq(&anchor->lock); + /* this will unanchor the URB */ + usb_poison_urb(victim); + usb_put_urb(victim); + spin_lock_irq(&anchor->lock); + } + surely_empty = usb_anchor_check_wakeup(anchor); + + spin_unlock_irq(&anchor->lock); + cpu_relax(); + } while (!surely_empty); } EXPORT_SYMBOL_GPL(usb_poison_anchored_urbs); @@ -970,14 +983,20 @@ void usb_scuttle_anchored_urbs(struct usb_anchor *anchor) { struct urb *victim; unsigned long flags; + int surely_empty; + + do { + spin_lock_irqsave(&anchor->lock, flags); + while (!list_empty(&anchor->urb_list)) { + victim = list_entry(anchor->urb_list.prev, + struct urb, anchor_list); + __usb_unanchor_urb(victim, anchor); + } + surely_empty = usb_anchor_check_wakeup(anchor); - spin_lock_irqsave(&anchor->lock, flags); - while (!list_empty(&anchor->urb_list)) { - victim = list_entry(anchor->urb_list.prev, struct urb, - anchor_list); - __usb_unanchor_urb(victim, anchor); - } - spin_unlock_irqrestore(&anchor->lock, flags); + spin_unlock_irqrestore(&anchor->lock, flags); + cpu_relax(); + } while (!surely_empty); } EXPORT_SYMBOL_GPL(usb_scuttle_anchored_urbs); diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 7faf5f8c056d..642926f9670e 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -712,8 +712,11 @@ static u32 dwc2_hsotg_read_frameno(struct dwc2_hsotg *hsotg) */ static unsigned int dwc2_gadget_get_chain_limit(struct dwc2_hsotg_ep *hs_ep) { + const struct usb_endpoint_descriptor *ep_desc = hs_ep->ep.desc; int is_isoc = hs_ep->isochronous; unsigned int maxsize; + u32 mps = hs_ep->ep.maxpacket; + int dir_in = hs_ep->dir_in; if (is_isoc) maxsize = (hs_ep->dir_in ? DEV_DMA_ISOC_TX_NBYTES_LIMIT : @@ -722,6 +725,11 @@ static unsigned int dwc2_gadget_get_chain_limit(struct dwc2_hsotg_ep *hs_ep) else maxsize = DEV_DMA_NBYTES_LIMIT * MAX_DMA_DESC_NUM_GENERIC; + /* Interrupt OUT EP with mps not multiple of 4 */ + if (hs_ep->index) + if (usb_endpoint_xfer_int(ep_desc) && !dir_in && (mps % 4)) + maxsize = mps * MAX_DMA_DESC_NUM_GENERIC; + return maxsize; } @@ -737,11 +745,14 @@ static unsigned int dwc2_gadget_get_chain_limit(struct dwc2_hsotg_ep *hs_ep) * Isochronous - descriptor rx/tx bytes bitfield limit, * Control In/Bulk/Interrupt - multiple of mps. This will allow to not * have concatenations from various descriptors within one packet. + * Interrupt OUT - if mps not multiple of 4 then a single packet corresponds + * to a single descriptor. * * Selects corresponding mask for RX/TX bytes as well. */ static u32 dwc2_gadget_get_desc_params(struct dwc2_hsotg_ep *hs_ep, u32 *mask) { + const struct usb_endpoint_descriptor *ep_desc = hs_ep->ep.desc; u32 mps = hs_ep->ep.maxpacket; int dir_in = hs_ep->dir_in; u32 desc_size = 0; @@ -765,6 +776,13 @@ static u32 dwc2_gadget_get_desc_params(struct dwc2_hsotg_ep *hs_ep, u32 *mask) desc_size -= desc_size % mps; } + /* Interrupt OUT EP with mps not multiple of 4 */ + if (hs_ep->index) + if (usb_endpoint_xfer_int(ep_desc) && !dir_in && (mps % 4)) { + desc_size = mps; + *mask = DEV_DMA_NBYTES_MASK; + } + return desc_size; } @@ -1123,13 +1141,7 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg, length += (mps - (length % mps)); } - /* - * If more data to send, adjust DMA for EP0 out data stage. - * ureq->dma stays unchanged, hence increment it by already - * passed passed data count before starting new transaction. - */ - if (!index && hsotg->ep0_state == DWC2_EP0_DATA_OUT && - continuing) + if (continuing) offset = ureq->actual; /* Fill DDMA chain entries */ @@ -2320,22 +2332,36 @@ static void dwc2_hsotg_change_ep_iso_parity(struct dwc2_hsotg *hsotg, */ static unsigned int dwc2_gadget_get_xfersize_ddma(struct dwc2_hsotg_ep *hs_ep) { + const struct usb_endpoint_descriptor *ep_desc = hs_ep->ep.desc; struct dwc2_hsotg *hsotg = hs_ep->parent; unsigned int bytes_rem = 0; + unsigned int bytes_rem_correction = 0; struct dwc2_dma_desc *desc = hs_ep->desc_list; int i; u32 status; + u32 mps = hs_ep->ep.maxpacket; + int dir_in = hs_ep->dir_in; if (!desc) return -EINVAL; + /* Interrupt OUT EP with mps not multiple of 4 */ + if (hs_ep->index) + if (usb_endpoint_xfer_int(ep_desc) && !dir_in && (mps % 4)) + bytes_rem_correction = 4 - (mps % 4); + for (i = 0; i < hs_ep->desc_count; ++i) { status = desc->status; bytes_rem += status & DEV_DMA_NBYTES_MASK; + bytes_rem -= bytes_rem_correction; if (status & DEV_DMA_STS_MASK) dev_err(hsotg->dev, "descriptor %d closed with %x\n", i, status & DEV_DMA_STS_MASK); + + if (status & DEV_DMA_L) + break; + desc++; } diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index ce736d67c7c3..fd73ddd8eb75 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -860,7 +860,7 @@ int dwc2_get_hwparams(struct dwc2_hsotg *hsotg) int dwc2_init_params(struct dwc2_hsotg *hsotg) { const struct of_device_id *match; - void (*set_params)(void *data); + void (*set_params)(struct dwc2_hsotg *data); dwc2_set_default_params(hsotg); dwc2_get_device_properties(hsotg); diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index db9fd4bd1a38..b28e90e0b685 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -584,12 +584,16 @@ static int dwc2_driver_probe(struct platform_device *dev) if (retval) { hsotg->gadget.udc = NULL; dwc2_hsotg_remove(hsotg); - goto error_init; + goto error_debugfs; } } #endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */ return 0; +error_debugfs: + dwc2_debugfs_exit(hsotg); + if (hsotg->hcd_enabled) + dwc2_hcd_remove(hsotg); error_init: if (hsotg->params.activate_stm_id_vb_detection) regulator_disable(hsotg->usb33d); diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 25c686a752b0..928a85b0d1cd 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -119,6 +119,7 @@ static void __dwc3_set_mode(struct work_struct *work) struct dwc3 *dwc = work_to_dwc(work); unsigned long flags; int ret; + u32 reg; if (dwc->dr_mode != USB_DR_MODE_OTG) return; @@ -172,6 +173,11 @@ static void __dwc3_set_mode(struct work_struct *work) otg_set_vbus(dwc->usb2_phy->otg, true); phy_set_mode(dwc->usb2_generic_phy, PHY_MODE_USB_HOST); phy_set_mode(dwc->usb3_generic_phy, PHY_MODE_USB_HOST); + if (dwc->dis_split_quirk) { + reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg |= DWC3_GUCTL3_SPLITDISABLE; + dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + } } break; case DWC3_GCTL_PRTCAP_DEVICE: @@ -930,13 +936,6 @@ static int dwc3_core_init(struct dwc3 *dwc) */ dwc3_writel(dwc->regs, DWC3_GUID, LINUX_VERSION_CODE); - /* Handle USB2.0-only core configuration */ - if (DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3) == - DWC3_GHWPARAMS3_SSPHY_IFC_DIS) { - if (dwc->maximum_speed == USB_SPEED_SUPER) - dwc->maximum_speed = USB_SPEED_HIGH; - } - ret = dwc3_phy_setup(dwc); if (ret) goto err0; @@ -1357,6 +1356,9 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->dis_metastability_quirk = device_property_read_bool(dev, "snps,dis_metastability_quirk"); + dwc->dis_split_quirk = device_property_read_bool(dev, + "snps,dis-split-quirk"); + dwc->lpm_nyet_threshold = lpm_nyet_threshold; dwc->tx_de_emphasis = tx_de_emphasis; @@ -1382,6 +1384,8 @@ bool dwc3_has_imod(struct dwc3 *dwc) static void dwc3_check_params(struct dwc3 *dwc) { struct device *dev = dwc->dev; + unsigned int hwparam_gen = + DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3); /* Check for proper value of imod_interval */ if (dwc->imod_interval && !dwc3_has_imod(dwc)) { @@ -1413,17 +1417,23 @@ static void dwc3_check_params(struct dwc3 *dwc) dwc->maximum_speed); /* fall through */ case USB_SPEED_UNKNOWN: - /* default to superspeed */ - dwc->maximum_speed = USB_SPEED_SUPER; - - /* - * default to superspeed plus if we are capable. - */ - if ((DWC3_IP_IS(DWC31) || DWC3_IP_IS(DWC32)) && - (DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3) == - DWC3_GHWPARAMS3_SSPHY_IFC_GEN2)) + switch (hwparam_gen) { + case DWC3_GHWPARAMS3_SSPHY_IFC_GEN2: dwc->maximum_speed = USB_SPEED_SUPER_PLUS; - + break; + case DWC3_GHWPARAMS3_SSPHY_IFC_GEN1: + if (DWC3_IP_IS(DWC32)) + dwc->maximum_speed = USB_SPEED_SUPER_PLUS; + else + dwc->maximum_speed = USB_SPEED_SUPER; + break; + case DWC3_GHWPARAMS3_SSPHY_IFC_DIS: + dwc->maximum_speed = USB_SPEED_HIGH; + break; + default: + dwc->maximum_speed = USB_SPEED_SUPER; + break; + } break; } } @@ -1866,10 +1876,26 @@ static int dwc3_resume(struct device *dev) return 0; } + +static void dwc3_complete(struct device *dev) +{ + struct dwc3 *dwc = dev_get_drvdata(dev); + u32 reg; + + if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST && + dwc->dis_split_quirk) { + reg = dwc3_readl(dwc->regs, DWC3_GUCTL3); + reg |= DWC3_GUCTL3_SPLITDISABLE; + dwc3_writel(dwc->regs, DWC3_GUCTL3, reg); + } +} +#else +#define dwc3_complete NULL #endif /* CONFIG_PM_SLEEP */ static const struct dev_pm_ops dwc3_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_suspend, dwc3_resume) + .complete = dwc3_complete, SET_RUNTIME_PM_OPS(dwc3_runtime_suspend, dwc3_runtime_resume, dwc3_runtime_idle) }; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 013f42a2b5dc..af5533b09713 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -138,6 +138,7 @@ #define DWC3_GEVNTCOUNT(n) (0xc40c + ((n) * 0x10)) #define DWC3_GHWPARAMS8 0xc600 +#define DWC3_GUCTL3 0xc60c #define DWC3_GFLADJ 0xc630 /* Device Registers */ @@ -380,6 +381,9 @@ /* Global User Control Register 2 */ #define DWC3_GUCTL2_RST_ACTBITLATER BIT(14) +/* Global User Control Register 3 */ +#define DWC3_GUCTL3_SPLITDISABLE BIT(14) + /* Device Configuration Register */ #define DWC3_DCFG_DEVADDR(addr) ((addr) << 3) #define DWC3_DCFG_DEVADDR_MASK DWC3_DCFG_DEVADDR(0x7f) @@ -1052,6 +1056,7 @@ struct dwc3_scratchpad_array { * 2 - No de-emphasis * 3 - Reserved * @dis_metastability_quirk: set to disable metastability quirk. + * @dis_split_quirk: set to disable split boundary. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. */ @@ -1245,6 +1250,8 @@ struct dwc3 { unsigned dis_metastability_quirk:1; + unsigned dis_split_quirk:1; + u16 imod_interval; }; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 8852fbfdead4..336253ff5574 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -176,6 +176,7 @@ static const struct of_device_id of_dwc3_simple_match[] = { { .compatible = "cavium,octeon-7130-usb-uctl" }, { .compatible = "sprd,sc9860-dwc3" }, { .compatible = "allwinner,sun50i-h6-dwc3" }, + { .compatible = "hisilicon,hi3670-dwc3" }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_dwc3_simple_match); diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 1f638759a953..92a7c3a83945 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -85,8 +85,10 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f) /* peak (theoretical) bulk transfer rate in bits-per-second */ static inline unsigned ncm_bitrate(struct usb_gadget *g) { - if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER) - return 13 * 1024 * 8 * 1000 * 8; + if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS) + return 4250000000U; + else if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER) + return 3750000000U; else if (gadget_is_dualspeed(g) && g->speed == USB_SPEED_HIGH) return 13 * 512 * 8 * 1000 * 8; else @@ -1534,7 +1536,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) fs_ncm_notify_desc.bEndpointAddress; status = usb_assign_descriptors(f, ncm_fs_function, ncm_hs_function, - ncm_ss_function, NULL); + ncm_ss_function, ncm_ss_function); if (status) goto fail; diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 9c7ed2539ff7..8ed1295d7e35 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -31,6 +31,7 @@ #include <linux/types.h> #include <linux/ctype.h> #include <linux/cdev.h> +#include <linux/kref.h> #include <asm/byteorder.h> #include <linux/io.h> @@ -64,7 +65,7 @@ struct printer_dev { struct usb_gadget *gadget; s8 interface; struct usb_ep *in_ep, *out_ep; - + struct kref kref; struct list_head rx_reqs; /* List of free RX structs */ struct list_head rx_reqs_active; /* List of Active RX xfers */ struct list_head rx_buffers; /* List of completed xfers */ @@ -218,6 +219,13 @@ static inline struct usb_endpoint_descriptor *ep_desc(struct usb_gadget *gadget, /*-------------------------------------------------------------------------*/ +static void printer_dev_free(struct kref *kref) +{ + struct printer_dev *dev = container_of(kref, struct printer_dev, kref); + + kfree(dev); +} + static struct usb_request * printer_req_alloc(struct usb_ep *ep, unsigned len, gfp_t gfp_flags) { @@ -348,6 +356,7 @@ printer_open(struct inode *inode, struct file *fd) spin_unlock_irqrestore(&dev->lock, flags); + kref_get(&dev->kref); DBG(dev, "printer_open returned %x\n", ret); return ret; } @@ -365,6 +374,7 @@ printer_close(struct inode *inode, struct file *fd) dev->printer_status &= ~PRINTER_SELECTED; spin_unlock_irqrestore(&dev->lock, flags); + kref_put(&dev->kref, printer_dev_free); DBG(dev, "printer_close\n"); return 0; @@ -1350,7 +1360,8 @@ static void gprinter_free(struct usb_function *f) struct f_printer_opts *opts; opts = container_of(f->fi, struct f_printer_opts, func_inst); - kfree(dev); + + kref_put(&dev->kref, printer_dev_free); mutex_lock(&opts->lock); --opts->refcnt; mutex_unlock(&opts->lock); @@ -1419,6 +1430,7 @@ static struct usb_function *gprinter_alloc(struct usb_function_instance *fi) return ERR_PTR(-ENOMEM); } + kref_init(&dev->kref); ++opts->refcnt; dev->minor = opts->minor; dev->pnp_string = opts->pnp_string; diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index fbe96ef1ac7a..891e9f7f40d5 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -93,7 +93,7 @@ struct eth_dev { static inline int qlen(struct usb_gadget *gadget, unsigned qmult) { if (gadget_is_dualspeed(gadget) && (gadget->speed == USB_SPEED_HIGH || - gadget->speed == USB_SPEED_SUPER)) + gadget->speed >= USB_SPEED_SUPER)) return qmult * DEFAULT_QLEN; else return DEFAULT_QLEN; diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 3cfc6e2eba71..e0e3cb2f6f3b 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1391,6 +1391,7 @@ void gserial_disconnect(struct gserial *gser) if (port->port.tty) tty_hangup(port->port.tty); } + port->suspended = false; spin_unlock_irqrestore(&port->port_lock, flags); /* disable endpoints, aborting down any active I/O */ diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c index 54501814dc3f..aebe11829baa 100644 --- a/drivers/usb/gadget/udc/bcm63xx_udc.c +++ b/drivers/usb/gadget/udc/bcm63xx_udc.c @@ -26,6 +26,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/usb.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> #include <linux/workqueue.h> diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 4de91653a2c7..5eb62240c7f8 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -673,20 +673,24 @@ retry: /* handle root hub init quirks ... */ val = roothub_a (ohci); - val &= ~(RH_A_PSM | RH_A_OCPM); + /* Configure for per-port over-current protection by default */ + val &= ~RH_A_NOCP; + val |= RH_A_OCPM; if (ohci->flags & OHCI_QUIRK_SUPERIO) { - /* NSC 87560 and maybe others */ + /* NSC 87560 and maybe others. + * Ganged power switching, no over-current protection. + */ val |= RH_A_NOCP; - val &= ~(RH_A_POTPGT | RH_A_NPS); - ohci_writel (ohci, val, &ohci->regs->roothub.a); + val &= ~(RH_A_POTPGT | RH_A_NPS | RH_A_PSM | RH_A_OCPM); } else if ((ohci->flags & OHCI_QUIRK_AMD756) || (ohci->flags & OHCI_QUIRK_HUB_POWER)) { /* hub power always on; required for AMD-756 and some - * Mac platforms. ganged overcurrent reporting, if any. + * Mac platforms. */ val |= RH_A_NPS; - ohci_writel (ohci, val, &ohci->regs->roothub.a); } + ohci_writel(ohci, val, &ohci->regs->roothub.a); + ohci_writel (ohci, RH_HS_LPSC, &ohci->regs->roothub.status); ohci_writel (ohci, (val & RH_A_NPS) ? 0 : RH_B_PPCM, &ohci->regs->roothub.b); diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 0b949acfa258..5d12204d470d 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -639,6 +639,9 @@ EXPORT_SYMBOL_GPL(usb_amd_pt_check_port); */ void uhci_reset_hc(struct pci_dev *pdev, unsigned long base) { +#ifdef CONFIG_MIPS_MALTA + int timeout = 10; +#endif /* Turn off PIRQ enable and SMI enable. (This also turns off the * BIOS's USB Legacy Support.) Turn off all the R/WC bits too. */ @@ -652,9 +655,16 @@ void uhci_reset_hc(struct pci_dev *pdev, unsigned long base) outw(UHCI_USBCMD_HCRESET, base + UHCI_USBCMD); mb(); udelay(5); - if (inw(base + UHCI_USBCMD) & UHCI_USBCMD_HCRESET) - dev_warn(&pdev->dev, "HCRESET not completed yet!\n"); +#ifdef CONFIG_MIPS_MALTA + while (inw(base + UHCI_USBCMD) & UHCI_USBCMD_HCRESET) { + if (--timeout < 0) { + dev_warn(&pdev->dev, "HCRESET timed out!\n"); + break; + } + udelay(5); + } +#endif /* Just to be safe, disable interrupt requests and * make sure the controller is stopped. */ diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c index 35fcb826152c..1cd2808eb455 100644 --- a/drivers/usb/host/uhci-q.c +++ b/drivers/usb/host/uhci-q.c @@ -72,7 +72,9 @@ static void uhci_fsbr_off(struct uhci_hcd *uhci) static void uhci_add_fsbr(struct uhci_hcd *uhci, struct urb *urb) { struct urb_priv *urbp = urb->hcpriv; - +#ifdef CONFIG_MIPS_MALTA + return; +#endif urbp->fsbr = 1; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 113ab5d3cbfe..f665da34a8f7 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1915,8 +1915,6 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->in_ctx, ep_index); trace_xhci_add_endpoint(ep_ctx); - xhci_debugfs_create_endpoint(xhci, virt_dev, ep_index); - xhci_dbg(xhci, "add ep 0x%x, slot id %d, new drop flags = %#x, new add flags = %#x\n", (unsigned int) ep->desc.bEndpointAddress, udev->slot_id, @@ -2949,6 +2947,7 @@ static int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) xhci_check_bw_drop_ep_streams(xhci, virt_dev, i); virt_dev->eps[i].ring = virt_dev->eps[i].new_ring; virt_dev->eps[i].new_ring = NULL; + xhci_debugfs_create_endpoint(xhci, virt_dev, i); } command_cleanup: kfree(command->completion); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index d98843feddce..5076d0155bc3 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -406,7 +406,7 @@ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) * PF SR-IOV capability, there's therefore no need to trigger * faults based on the virtual value. */ - return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); + return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY); } /* @@ -520,8 +520,8 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos, count = vfio_default_config_read(vdev, pos, count, perm, offset, val); - /* Mask in virtual memory enable for SR-IOV devices */ - if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) { + /* Mask in virtual memory enable */ + if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) { u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); u32 tmp_val = le32_to_cpu(*val); @@ -589,9 +589,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, * shows it disabled (phys_mem/io, then the device has * undergone some kind of backdoor reset and needs to be * restored before we allow it to enable the bars. - * SR-IOV devices will trigger this, but we catch them later + * SR-IOV devices will trigger this - for mem enable let's + * catch this now and for io enable it will be caught later */ - if ((new_mem && virt_mem && !phys_mem) || + if ((new_mem && virt_mem && !phys_mem && + !pdev->no_command_memory) || (new_io && virt_io && !phys_io) || vfio_need_bar_restore(vdev)) vfio_bar_restore(vdev); @@ -1734,12 +1736,14 @@ int vfio_config_init(struct vfio_pci_device *vdev) vconfig[PCI_INTERRUPT_PIN]); vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ - + } + if (pdev->no_command_memory) { /* - * VFs do no implement the memory enable bit of the COMMAND - * register therefore we'll not have it set in our initial - * copy of config space after pci_enable_device(). For - * consistency with PFs, set the virtual enable bit here. + * VFs and devices that set pdev->no_command_memory do not + * implement the memory enable bit of the COMMAND register + * therefore we'll not have it set in our initial copy of + * config space after pci_enable_device(). For consistency + * with PFs, set the virtual enable bit here. */ *(__le16 *)&vconfig[PCI_COMMAND] |= cpu_to_le16(PCI_COMMAND_MEMORY); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 1d9fb2592945..869dce5f134d 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -352,11 +352,13 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, vdev->ctx[vector].producer.token = trigger; vdev->ctx[vector].producer.irq = irq; ret = irq_bypass_register_producer(&vdev->ctx[vector].producer); - if (unlikely(ret)) + if (unlikely(ret)) { dev_info(&pdev->dev, "irq bypass producer (token %p) registration fails: %d\n", vdev->ctx[vector].producer.token, ret); + vdev->ctx[vector].producer.token = NULL; + } vdev->ctx[vector].trigger = trigger; return 0; diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 580099afeaff..fbff5c4743c5 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1948,8 +1948,10 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, if (!group) return -ENODEV; - if (group->dev_counter > 1) - return -EINVAL; + if (group->dev_counter > 1) { + ret = -EINVAL; + goto err_pin_pages; + } ret = vfio_group_add_container_user(group); if (ret) @@ -2050,6 +2052,9 @@ int vfio_group_pin_pages(struct vfio_group *group, if (!group || !user_iova_pfn || !phys_pfn || !npage) return -EINVAL; + if (group->dev_counter > 1) + return -EINVAL; + if (npage > VFIO_PIN_PAGES_MAX_ENTRIES) return -E2BIG; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index f48f0db908a4..00d3cf12e92c 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -693,7 +693,8 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]); if (ret) { - vfio_unpin_page_external(dma, iova, do_accounting); + if (put_pfn(phys_pfn[i], dma->prot) && do_accounting) + vfio_lock_acct(dma, -1, true); goto pin_unwind; } @@ -2899,7 +2900,8 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, * size */ bitmap_set(dma->bitmap, offset >> pgshift, - *copied >> pgshift); + ((offset + *copied - 1) >> pgshift) - + (offset >> pgshift) + 1); } } else *copied = copy_from_user(data, (void __user *)vaddr, diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 2355f00f5773..1f6301375fd3 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -196,6 +196,7 @@ static struct sky81452_bl_platform_data *sky81452_bl_parse_dt( num_entry); if (ret < 0) { dev_err(dev, "led-sources node is invalid.\n"); + of_node_put(np); return ERR_PTR(-EINVAL); } diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index e116a3f9ad56..687bd2c0d504 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -2311,7 +2311,7 @@ static int radeonfb_pci_register(struct pci_dev *pdev, ret = radeon_kick_out_firmware_fb(pdev); if (ret) - return ret; + goto err_release_fb; /* request the mem regions */ ret = pci_request_region(pdev, 0, "radeonfb framebuffer"); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index da7c88ffaa6a..1136b569ccb7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1006,6 +1006,10 @@ fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var) return 0; } + /* bitfill_aligned() assumes that it's at least 8x8 */ + if (var->xres < 8 || var->yres < 8) + return -EINVAL; + ret = info->fbops->fb_check_var(var, info); if (ret) diff --git a/drivers/video/fbdev/sis/init.c b/drivers/video/fbdev/sis/init.c index dfe3eb769638..fde27feae5d0 100644 --- a/drivers/video/fbdev/sis/init.c +++ b/drivers/video/fbdev/sis/init.c @@ -2428,6 +2428,11 @@ SiS_SetCRT1FIFO_630(struct SiS_Private *SiS_Pr, unsigned short ModeNo, i = 0; + if (SiS_Pr->ChipType == SIS_730) + queuedata = &FQBQData730[0]; + else + queuedata = &FQBQData[0]; + if(ModeNo > 0x13) { /* Get VCLK */ @@ -2445,12 +2450,6 @@ SiS_SetCRT1FIFO_630(struct SiS_Private *SiS_Pr, unsigned short ModeNo, /* Get half colordepth */ colorth = colortharray[(SiS_Pr->SiS_ModeType - ModeEGA)]; - if(SiS_Pr->ChipType == SIS_730) { - queuedata = &FQBQData730[0]; - } else { - queuedata = &FQBQData[0]; - } - do { templ = SiS_CalcDelay2(SiS_Pr, queuedata[i]) * VCLK * colorth; diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index def14ac0ebe1..4a2be5ce0b8e 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -44,6 +44,7 @@ static const struct fb_fix_screeninfo uvesafb_fix = { .visual = FB_VISUAL_TRUECOLOR, }; +static int task_timeout = UVESAFB_TIMEOUT; /* timeout [ms] of task execution */ static int mtrr = 3; /* enable mtrr by default */ static bool blank = true; /* enable blanking by default */ static int ypan = 1; /* 0: scroll, 1: ypan, 2: ywrap */ @@ -147,7 +148,9 @@ static int uvesafb_exec(struct uvesafb_ktask *task) struct cn_msg *m; int err; int len = sizeof(task->t) + task->t.buf_len; - + int forever_wait = task_timeout < 0 ? 1 : 0; + /* For infinite wait case, set interval to the legacy 5000 ms */ + int timeout = forever_wait ? 5000 : task_timeout; /* * Check whether the message isn't longer than the maximum * allowed by connector. @@ -213,9 +216,21 @@ static int uvesafb_exec(struct uvesafb_ktask *task) } else if (err == -ENOBUFS) err = 0; - if (!err && !(task->t.flags & TF_EXIT)) - err = !wait_for_completion_timeout(task->done, - msecs_to_jiffies(UVESAFB_TIMEOUT)); + if (!err && !(task->t.flags & TF_EXIT)) { + do { + err = !wait_for_completion_timeout(task->done, + msecs_to_jiffies(timeout)); + if (err) + printk_ratelimited( + KERN_WARNING + "uvesafb: %u ms task timeout%s\n", + timeout, + forever_wait ? + ", infinitely waiting." : "."); + else + break; + } while (forever_wait); + } mutex_lock(&uvfb_lock); uvfb_tasks[seq] = NULL; @@ -1817,6 +1832,8 @@ static int uvesafb_setup(char *options) while ((this_opt = strsep(&options, ",")) != NULL) { if (!*this_opt) continue; + if (!strncmp(this_opt, "task_timeout", 12)) + task_timeout = simple_strtol(this_opt+12, NULL, 0); if (!strcmp(this_opt, "redraw")) ypan = 0; else if (!strcmp(this_opt, "ypan")) @@ -1960,6 +1977,9 @@ static const struct kernel_param_ops param_ops_scroll = { }; #define param_check_scroll(name, p) __param_check(name, p, void) +module_param(task_timeout, int, 0400); +MODULE_PARM_DESC(task_timeout, + "Timeout [ms] of a task's completion, or set to any negative value to infinitely wait"); module_param_named(scroll, ypan, scroll, 0); MODULE_PARM_DESC(scroll, "Scrolling mode, set to 'redraw', 'ypan', or 'ywrap'"); diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c index 578d3541e3d6..1e8a38a7967d 100644 --- a/drivers/video/fbdev/vga16fb.c +++ b/drivers/video/fbdev/vga16fb.c @@ -243,7 +243,7 @@ static void vga16fb_update_fix(struct fb_info *info) } static void vga16fb_clock_chip(struct vga16fb_par *par, - unsigned int pixclock, + unsigned int *pixclock, const struct fb_info *info, int mul, int div) { @@ -259,14 +259,14 @@ static void vga16fb_clock_chip(struct vga16fb_par *par, { 0 /* bad */, 0x00, 0x00}}; int err; - pixclock = (pixclock * mul) / div; + *pixclock = (*pixclock * mul) / div; best = vgaclocks; - err = pixclock - best->pixclock; + err = *pixclock - best->pixclock; if (err < 0) err = -err; for (ptr = vgaclocks + 1; ptr->pixclock; ptr++) { int tmp; - tmp = pixclock - ptr->pixclock; + tmp = *pixclock - ptr->pixclock; if (tmp < 0) tmp = -tmp; if (tmp < err) { err = tmp; @@ -275,7 +275,7 @@ static void vga16fb_clock_chip(struct vga16fb_par *par, } par->misc |= best->misc; par->clkdiv = best->seq_clock_mode; - pixclock = (best->pixclock * div) / mul; + *pixclock = (best->pixclock * div) / mul; } #define FAIL(X) return -EINVAL @@ -497,10 +497,10 @@ static int vga16fb_check_var(struct fb_var_screeninfo *var, if (mode & MODE_8BPP) /* pixel clock == vga clock / 2 */ - vga16fb_clock_chip(par, var->pixclock, info, 1, 2); + vga16fb_clock_chip(par, &var->pixclock, info, 1, 2); else /* pixel clock == vga clock */ - vga16fb_clock_chip(par, var->pixclock, info, 1, 1); + vga16fb_clock_chip(par, &var->pixclock, info, 1, 1); var->red.offset = var->green.offset = var->blue.offset = var->transp.offset = 0; diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c index 1b0b11b55d2a..46ee0a0998b6 100644 --- a/drivers/virt/fsl_hypervisor.c +++ b/drivers/virt/fsl_hypervisor.c @@ -157,7 +157,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) unsigned int i; long ret = 0; - int num_pinned; /* return value from get_user_pages() */ + int num_pinned = 0; /* return value from get_user_pages_fast() */ phys_addr_t remote_paddr; /* The next address in the remote buffer */ uint32_t count; /* The number of bytes left to copy */ @@ -174,7 +174,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) return -EINVAL; /* - * The array of pages returned by get_user_pages() covers only + * The array of pages returned by get_user_pages_fast() covers only * page-aligned memory. Since the user buffer is probably not * page-aligned, we need to handle the discrepancy. * @@ -224,7 +224,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) /* * 'pages' is an array of struct page pointers that's initialized by - * get_user_pages(). + * get_user_pages_fast(). */ pages = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { @@ -241,7 +241,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) if (!sg_list_unaligned) { pr_debug("fsl-hv: could not allocate S/G list\n"); ret = -ENOMEM; - goto exit; + goto free_pages; } sg_list = PTR_ALIGN(sg_list_unaligned, sizeof(struct fh_sg_list)); @@ -250,7 +250,6 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) num_pages, param.source != -1 ? FOLL_WRITE : 0, pages); if (num_pinned != num_pages) { - /* get_user_pages() failed */ pr_debug("fsl-hv: could not lock source buffer\n"); ret = (num_pinned < 0) ? num_pinned : -EFAULT; goto exit; @@ -292,13 +291,13 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) virt_to_phys(sg_list), num_pages); exit: - if (pages) { - for (i = 0; i < num_pages; i++) - if (pages[i]) - put_page(pages[i]); + if (pages && (num_pinned > 0)) { + for (i = 0; i < num_pinned; i++) + put_page(pages[i]); } kfree(sg_list_unaligned); +free_pages: kfree(pages); if (!ret) diff --git a/drivers/watchdog/sp5100_tco.h b/drivers/watchdog/sp5100_tco.h index 87eaf357ae01..adf015aa4126 100644 --- a/drivers/watchdog/sp5100_tco.h +++ b/drivers/watchdog/sp5100_tco.h @@ -70,7 +70,7 @@ #define EFCH_PM_DECODEEN_WDT_TMREN BIT(7) -#define EFCH_PM_DECODEEN3 0x00 +#define EFCH_PM_DECODEEN3 0x03 #define EFCH_PM_DECODEEN_SECOND_RES GENMASK(1, 0) #define EFCH_PM_WATCHDOG_DISABLE ((u8)GENMASK(3, 2)) diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index b535f5fa279b..c2065615fd6c 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -991,8 +991,10 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) wd_data->wdd = wdd; wdd->wd_data = wd_data; - if (IS_ERR_OR_NULL(watchdog_kworker)) + if (IS_ERR_OR_NULL(watchdog_kworker)) { + kfree(wd_data); return -ENODEV; + } device_initialize(&wd_data->dev); wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id); @@ -1018,7 +1020,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) pr_err("%s: a legacy watchdog module is probably present.\n", wdd->info->identity); old_wd_data = NULL; - kfree(wd_data); + put_device(&wd_data->dev); return err; } } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 64a9025a87be..1f32db7b72b2 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -720,17 +720,18 @@ struct gntdev_copy_batch { s16 __user *status[GNTDEV_COPY_BATCH]; unsigned int nr_ops; unsigned int nr_pages; + bool writeable; }; static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt, - bool writeable, unsigned long *gfn) + unsigned long *gfn) { unsigned long addr = (unsigned long)virt; struct page *page; unsigned long xen_pfn; int ret; - ret = get_user_pages_fast(addr, 1, writeable ? FOLL_WRITE : 0, &page); + ret = get_user_pages_fast(addr, 1, batch->writeable ? FOLL_WRITE : 0, &page); if (ret < 0) return ret; @@ -746,9 +747,13 @@ static void gntdev_put_pages(struct gntdev_copy_batch *batch) { unsigned int i; - for (i = 0; i < batch->nr_pages; i++) + for (i = 0; i < batch->nr_pages; i++) { + if (batch->writeable && !PageDirty(batch->pages[i])) + set_page_dirty_lock(batch->pages[i]); put_page(batch->pages[i]); + } batch->nr_pages = 0; + batch->writeable = false; } static int gntdev_copy(struct gntdev_copy_batch *batch) @@ -837,8 +842,9 @@ static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch, virt = seg->source.virt + copied; off = (unsigned long)virt & ~XEN_PAGE_MASK; len = min(len, (size_t)XEN_PAGE_SIZE - off); + batch->writeable = false; - ret = gntdev_get_page(batch, virt, false, &gfn); + ret = gntdev_get_page(batch, virt, &gfn); if (ret < 0) return ret; @@ -856,8 +862,9 @@ static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch, virt = seg->dest.virt + copied; off = (unsigned long)virt & ~XEN_PAGE_MASK; len = min(len, (size_t)XEN_PAGE_SIZE - off); + batch->writeable = true; - ret = gntdev_get_page(batch, virt, true, &gfn); + ret = gntdev_get_page(batch, virt, &gfn); if (ret < 0) return ret; diff --git a/fs/Kconfig b/fs/Kconfig index a88aa3af73c1..a92216bcbefb 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -250,6 +250,7 @@ source "fs/hfsplus/Kconfig" source "fs/befs/Kconfig" source "fs/bfs/Kconfig" source "fs/efs/Kconfig" +source "fs/yaffs2/Kconfig" source "fs/jffs2/Kconfig" # UBIFS File system configuration source "fs/ubifs/Kconfig" @@ -267,6 +268,7 @@ source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/erofs/Kconfig" source "fs/vboxsf/Kconfig" +source "fs/aufs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Makefile b/fs/Makefile index 2ce5112b02c8..a6e8da55723e 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -136,3 +136,5 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/ obj-$(CONFIG_EROFS_FS) += erofs/ obj-$(CONFIG_VBOXSF_FS) += vboxsf/ obj-$(CONFIG_ZONEFS_FS) += zonefs/ +obj-$(CONFIG_YAFFS_FS) += yaffs2/ +obj-$(CONFIG_AUFS_FS) += aufs/ diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 5b79cdceefa0..bc7ed46aaca9 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -19,7 +19,8 @@ static unsigned __read_mostly afs_cell_gc_delay = 10; static unsigned __read_mostly afs_cell_min_ttl = 10 * 60; static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60; -static void afs_manage_cell(struct work_struct *); +static void afs_queue_cell_manager(struct afs_net *); +static void afs_manage_cell_work(struct work_struct *); static void afs_dec_cells_outstanding(struct afs_net *net) { @@ -37,19 +38,21 @@ static void afs_set_cell_timer(struct afs_net *net, time64_t delay) atomic_inc(&net->cells_outstanding); if (timer_reduce(&net->cells_timer, jiffies + delay * HZ)) afs_dec_cells_outstanding(net); + } else { + afs_queue_cell_manager(net); } } /* - * Look up and get an activation reference on a cell record under RCU - * conditions. The caller must hold the RCU read lock. + * Look up and get an activation reference on a cell record. The caller must + * hold net->cells_lock at least read-locked. */ -struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, - const char *name, unsigned int namesz) +static struct afs_cell *afs_find_cell_locked(struct afs_net *net, + const char *name, unsigned int namesz) { struct afs_cell *cell = NULL; struct rb_node *p; - int n, seq = 0, ret = 0; + int n; _enter("%*.*s", namesz, namesz, name); @@ -58,61 +61,47 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, if (namesz > AFS_MAXCELLNAME) return ERR_PTR(-ENAMETOOLONG); - do { - /* Unfortunately, rbtree walking doesn't give reliable results - * under just the RCU read lock, so we have to check for - * changes. - */ - if (cell) - afs_put_cell(net, cell); - cell = NULL; - ret = -ENOENT; - - read_seqbegin_or_lock(&net->cells_lock, &seq); - - if (!name) { - cell = rcu_dereference_raw(net->ws_cell); - if (cell) { - afs_get_cell(cell); - ret = 0; - break; - } - ret = -EDESTADDRREQ; - continue; - } + if (!name) { + cell = net->ws_cell; + if (!cell) + return ERR_PTR(-EDESTADDRREQ); + goto found; + } - p = rcu_dereference_raw(net->cells.rb_node); - while (p) { - cell = rb_entry(p, struct afs_cell, net_node); - - n = strncasecmp(cell->name, name, - min_t(size_t, cell->name_len, namesz)); - if (n == 0) - n = cell->name_len - namesz; - if (n < 0) { - p = rcu_dereference_raw(p->rb_left); - } else if (n > 0) { - p = rcu_dereference_raw(p->rb_right); - } else { - if (atomic_inc_not_zero(&cell->usage)) { - ret = 0; - break; - } - /* We want to repeat the search, this time with - * the lock properly locked. - */ - } - cell = NULL; - } + p = net->cells.rb_node; + while (p) { + cell = rb_entry(p, struct afs_cell, net_node); + + n = strncasecmp(cell->name, name, + min_t(size_t, cell->name_len, namesz)); + if (n == 0) + n = cell->name_len - namesz; + if (n < 0) + p = p->rb_left; + else if (n > 0) + p = p->rb_right; + else + goto found; + } - } while (need_seqretry(&net->cells_lock, seq)); + return ERR_PTR(-ENOENT); - done_seqretry(&net->cells_lock, seq); +found: + return afs_use_cell(cell); +} - if (ret != 0 && cell) - afs_put_cell(net, cell); +/* + * Look up and get an activation reference on a cell record. + */ +struct afs_cell *afs_find_cell(struct afs_net *net, + const char *name, unsigned int namesz) +{ + struct afs_cell *cell; - return ret == 0 ? cell : ERR_PTR(ret); + down_read(&net->cells_lock); + cell = afs_find_cell_locked(net, name, namesz); + up_read(&net->cells_lock); + return cell; } /* @@ -166,8 +155,9 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, cell->name[i] = tolower(name[i]); cell->name[i] = 0; - atomic_set(&cell->usage, 2); - INIT_WORK(&cell->manager, afs_manage_cell); + atomic_set(&cell->ref, 1); + atomic_set(&cell->active, 0); + INIT_WORK(&cell->manager, afs_manage_cell_work); cell->volumes = RB_ROOT; INIT_HLIST_HEAD(&cell->proc_volumes); seqlock_init(&cell->volume_lock); @@ -206,6 +196,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, cell->dns_source = vllist->source; cell->dns_status = vllist->status; smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */ + atomic_inc(&net->cells_outstanding); _leave(" = %p", cell); return cell; @@ -245,9 +236,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, _enter("%s,%s", name, vllist); if (!excl) { - rcu_read_lock(); - cell = afs_lookup_cell_rcu(net, name, namesz); - rcu_read_unlock(); + cell = afs_find_cell(net, name, namesz); if (!IS_ERR(cell)) goto wait_for_cell; } @@ -268,7 +257,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, /* Find the insertion point and check to see if someone else added a * cell whilst we were allocating. */ - write_seqlock(&net->cells_lock); + down_write(&net->cells_lock); pp = &net->cells.rb_node; parent = NULL; @@ -290,23 +279,23 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, cell = candidate; candidate = NULL; + atomic_set(&cell->active, 2); rb_link_node_rcu(&cell->net_node, parent, pp); rb_insert_color(&cell->net_node, &net->cells); - atomic_inc(&net->cells_outstanding); - write_sequnlock(&net->cells_lock); + up_write(&net->cells_lock); - queue_work(afs_wq, &cell->manager); + afs_queue_cell(cell); wait_for_cell: _debug("wait_for_cell"); wait_var_event(&cell->state, ({ state = smp_load_acquire(&cell->state); /* vs error */ - state == AFS_CELL_ACTIVE || state == AFS_CELL_FAILED; + state == AFS_CELL_ACTIVE || state == AFS_CELL_REMOVED; })); /* Check the state obtained from the wait check. */ - if (state == AFS_CELL_FAILED) { + if (state == AFS_CELL_REMOVED) { ret = cell->error; goto error; } @@ -320,16 +309,17 @@ cell_already_exists: if (excl) { ret = -EEXIST; } else { - afs_get_cell(cursor); + afs_use_cell(cursor); ret = 0; } - write_sequnlock(&net->cells_lock); - kfree(candidate); + up_write(&net->cells_lock); + if (candidate) + afs_put_cell(candidate); if (ret == 0) goto wait_for_cell; goto error_noput; error: - afs_put_cell(net, cell); + afs_unuse_cell(net, cell); error_noput: _leave(" = %d [error]", ret); return ERR_PTR(ret); @@ -374,15 +364,15 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) } if (!test_and_set_bit(AFS_CELL_FL_NO_GC, &new_root->flags)) - afs_get_cell(new_root); + afs_use_cell(new_root); /* install the new cell */ - write_seqlock(&net->cells_lock); - old_root = rcu_access_pointer(net->ws_cell); - rcu_assign_pointer(net->ws_cell, new_root); - write_sequnlock(&net->cells_lock); + down_write(&net->cells_lock); + old_root = net->ws_cell; + net->ws_cell = new_root; + up_write(&net->cells_lock); - afs_put_cell(net, old_root); + afs_unuse_cell(net, old_root); _leave(" = 0"); return 0; } @@ -488,18 +478,21 @@ out_wake: static void afs_cell_destroy(struct rcu_head *rcu) { struct afs_cell *cell = container_of(rcu, struct afs_cell, rcu); + struct afs_net *net = cell->net; + int u; _enter("%p{%s}", cell, cell->name); - ASSERTCMP(atomic_read(&cell->usage), ==, 0); + u = atomic_read(&cell->ref); + ASSERTCMP(u, ==, 0); - afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root); - afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers)); - afs_put_cell(cell->net, cell->alias_of); + afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers)); + afs_unuse_cell(net, cell->alias_of); key_put(cell->anonymous_key); kfree(cell->name); kfree(cell); + afs_dec_cells_outstanding(net); _leave(" [destroyed]"); } @@ -534,16 +527,50 @@ void afs_cells_timer(struct timer_list *timer) */ struct afs_cell *afs_get_cell(struct afs_cell *cell) { - atomic_inc(&cell->usage); + if (atomic_read(&cell->ref) <= 0) + BUG(); + + atomic_inc(&cell->ref); return cell; } /* * Drop a reference on a cell record. */ -void afs_put_cell(struct afs_net *net, struct afs_cell *cell) +void afs_put_cell(struct afs_cell *cell) +{ + if (cell) { + unsigned int u, a; + + u = atomic_dec_return(&cell->ref); + if (u == 0) { + a = atomic_read(&cell->active); + WARN(a != 0, "Cell active count %u > 0\n", a); + call_rcu(&cell->rcu, afs_cell_destroy); + } + } +} + +/* + * Note a cell becoming more active. + */ +struct afs_cell *afs_use_cell(struct afs_cell *cell) +{ + if (atomic_read(&cell->ref) <= 0) + BUG(); + + atomic_inc(&cell->active); + return cell; +} + +/* + * Record a cell becoming less active. When the active counter reaches 1, it + * is scheduled for destruction, but may get reactivated. + */ +void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell) { time64_t now, expire_delay; + int a; if (!cell) return; @@ -556,11 +583,21 @@ void afs_put_cell(struct afs_net *net, struct afs_cell *cell) if (cell->vl_servers->nr_servers) expire_delay = afs_cell_gc_delay; - if (atomic_dec_return(&cell->usage) > 1) - return; + a = atomic_dec_return(&cell->active); + WARN_ON(a == 0); + if (a == 1) + /* 'cell' may now be garbage collected. */ + afs_set_cell_timer(net, expire_delay); +} - /* 'cell' may now be garbage collected. */ - afs_set_cell_timer(net, expire_delay); +/* + * Queue a cell for management, giving the workqueue a ref to hold. + */ +void afs_queue_cell(struct afs_cell *cell) +{ + afs_get_cell(cell); + if (!queue_work(afs_wq, &cell->manager)) + afs_put_cell(cell); } /* @@ -660,12 +697,10 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell) * Manage a cell record, initialising and destroying it, maintaining its DNS * records. */ -static void afs_manage_cell(struct work_struct *work) +static void afs_manage_cell(struct afs_cell *cell) { - struct afs_cell *cell = container_of(work, struct afs_cell, manager); struct afs_net *net = cell->net; - bool deleted; - int ret, usage; + int ret, active; _enter("%s", cell->name); @@ -674,14 +709,17 @@ again: switch (cell->state) { case AFS_CELL_INACTIVE: case AFS_CELL_FAILED: - write_seqlock(&net->cells_lock); - usage = 1; - deleted = atomic_try_cmpxchg_relaxed(&cell->usage, &usage, 0); - if (deleted) + down_write(&net->cells_lock); + active = 1; + if (atomic_try_cmpxchg_relaxed(&cell->active, &active, 0)) { rb_erase(&cell->net_node, &net->cells); - write_sequnlock(&net->cells_lock); - if (deleted) + smp_store_release(&cell->state, AFS_CELL_REMOVED); + } + up_write(&net->cells_lock); + if (cell->state == AFS_CELL_REMOVED) { + wake_up_var(&cell->state); goto final_destruction; + } if (cell->state == AFS_CELL_FAILED) goto done; smp_store_release(&cell->state, AFS_CELL_UNSET); @@ -703,7 +741,7 @@ again: goto again; case AFS_CELL_ACTIVE: - if (atomic_read(&cell->usage) > 1) { + if (atomic_read(&cell->active) > 1) { if (test_and_clear_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) { ret = afs_update_cell(cell); if (ret < 0) @@ -716,13 +754,16 @@ again: goto again; case AFS_CELL_DEACTIVATING: - if (atomic_read(&cell->usage) > 1) + if (atomic_read(&cell->active) > 1) goto reverse_deactivation; afs_deactivate_cell(net, cell); smp_store_release(&cell->state, AFS_CELL_INACTIVE); wake_up_var(&cell->state); goto again; + case AFS_CELL_REMOVED: + goto done; + default: break; } @@ -748,9 +789,18 @@ done: return; final_destruction: - call_rcu(&cell->rcu, afs_cell_destroy); - afs_dec_cells_outstanding(net); - _leave(" [destruct %d]", atomic_read(&net->cells_outstanding)); + /* The root volume is pinning the cell */ + afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root); + cell->root_volume = NULL; + afs_put_cell(cell); +} + +static void afs_manage_cell_work(struct work_struct *work) +{ + struct afs_cell *cell = container_of(work, struct afs_cell, manager); + + afs_manage_cell(cell); + afs_put_cell(cell); } /* @@ -779,26 +829,25 @@ void afs_manage_cells(struct work_struct *work) * lack of use and cells whose DNS results have expired and dispatch * their managers. */ - read_seqlock_excl(&net->cells_lock); + down_read(&net->cells_lock); for (cursor = rb_first(&net->cells); cursor; cursor = rb_next(cursor)) { struct afs_cell *cell = rb_entry(cursor, struct afs_cell, net_node); - unsigned usage; + unsigned active; bool sched_cell = false; - usage = atomic_read(&cell->usage); - _debug("manage %s %u", cell->name, usage); + active = atomic_read(&cell->active); + _debug("manage %s %u %u", cell->name, atomic_read(&cell->ref), active); - ASSERTCMP(usage, >=, 1); + ASSERTCMP(active, >=, 1); if (purging) { if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags)) - usage = atomic_dec_return(&cell->usage); - ASSERTCMP(usage, ==, 1); + atomic_dec(&cell->active); } - if (usage == 1) { + if (active == 1) { struct afs_vlserver_list *vllist; time64_t expire_at = cell->last_inactive; @@ -821,10 +870,10 @@ void afs_manage_cells(struct work_struct *work) } if (sched_cell) - queue_work(afs_wq, &cell->manager); + afs_queue_cell(cell); } - read_sequnlock_excl(&net->cells_lock); + up_read(&net->cells_lock); /* Update the timer on the way out. We have to pass an increment on * cells_outstanding in the namespace that we are in to the timer or @@ -854,11 +903,11 @@ void afs_cell_purge(struct afs_net *net) _enter(""); - write_seqlock(&net->cells_lock); - ws = rcu_access_pointer(net->ws_cell); - RCU_INIT_POINTER(net->ws_cell, NULL); - write_sequnlock(&net->cells_lock); - afs_put_cell(net, ws); + down_write(&net->cells_lock); + ws = net->ws_cell; + net->ws_cell = NULL; + up_write(&net->cells_lock); + afs_unuse_cell(net, ws); _debug("del timer"); if (del_timer_sync(&net->cells_timer)) diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 7b784af604fd..da32797dd425 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -123,9 +123,9 @@ static int afs_probe_cell_name(struct dentry *dentry) len--; } - cell = afs_lookup_cell_rcu(net, name, len); + cell = afs_find_cell(net, name, len); if (!IS_ERR(cell)) { - afs_put_cell(net, cell); + afs_unuse_cell(net, cell); return 0; } @@ -179,7 +179,6 @@ static struct dentry *afs_lookup_atcell(struct dentry *dentry) struct afs_cell *cell; struct afs_net *net = afs_d2net(dentry); struct dentry *ret; - unsigned int seq = 0; char *name; int len; @@ -191,17 +190,13 @@ static struct dentry *afs_lookup_atcell(struct dentry *dentry) if (!name) goto out_p; - rcu_read_lock(); - do { - read_seqbegin_or_lock(&net->cells_lock, &seq); - cell = rcu_dereference_raw(net->ws_cell); - if (cell) { - len = cell->name_len; - memcpy(name, cell->name, len + 1); - } - } while (need_seqretry(&net->cells_lock, seq)); - done_seqretry(&net->cells_lock, seq); - rcu_read_unlock(); + down_read(&net->cells_lock); + cell = net->ws_cell; + if (cell) { + len = cell->name_len; + memcpy(name, cell->name, len + 1); + } + up_read(&net->cells_lock); ret = ERR_PTR(-ENOENT); if (!cell) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index e1ebead2e505..7689f4535ef9 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -263,11 +263,11 @@ struct afs_net { /* Cell database */ struct rb_root cells; - struct afs_cell __rcu *ws_cell; + struct afs_cell *ws_cell; struct work_struct cells_manager; struct timer_list cells_timer; atomic_t cells_outstanding; - seqlock_t cells_lock; + struct rw_semaphore cells_lock; struct mutex cells_alias_lock; struct mutex proc_cells_lock; @@ -326,6 +326,7 @@ enum afs_cell_state { AFS_CELL_DEACTIVATING, AFS_CELL_INACTIVE, AFS_CELL_FAILED, + AFS_CELL_REMOVED, }; /* @@ -363,7 +364,8 @@ struct afs_cell { #endif time64_t dns_expiry; /* Time AFSDB/SRV record expires */ time64_t last_inactive; /* Time of last drop of usage count */ - atomic_t usage; + atomic_t ref; /* Struct refcount */ + atomic_t active; /* Active usage counter */ unsigned long flags; #define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ #define AFS_CELL_FL_DO_LOOKUP 1 /* DNS lookup requested */ @@ -915,11 +917,14 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, * cell.c */ extern int afs_cell_init(struct afs_net *, const char *); -extern struct afs_cell *afs_lookup_cell_rcu(struct afs_net *, const char *, unsigned); +extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned); extern struct afs_cell *afs_lookup_cell(struct afs_net *, const char *, unsigned, const char *, bool); +extern struct afs_cell *afs_use_cell(struct afs_cell *); +extern void afs_unuse_cell(struct afs_net *, struct afs_cell *); extern struct afs_cell *afs_get_cell(struct afs_cell *); -extern void afs_put_cell(struct afs_net *, struct afs_cell *); +extern void afs_put_cell(struct afs_cell *); +extern void afs_queue_cell(struct afs_cell *); extern void afs_manage_cells(struct work_struct *); extern void afs_cells_timer(struct timer_list *); extern void __net_exit afs_cell_purge(struct afs_net *); diff --git a/fs/afs/main.c b/fs/afs/main.c index 31b472f7c734..accdd8970e7c 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -78,7 +78,7 @@ static int __net_init afs_net_init(struct net *net_ns) mutex_init(&net->socket_mutex); net->cells = RB_ROOT; - seqlock_init(&net->cells_lock); + init_rwsem(&net->cells_lock); INIT_WORK(&net->cells_manager, afs_manage_cells); timer_setup(&net->cells_timer, afs_cells_timer, 0); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 79bc5f1338ed..c69a0282960c 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -88,7 +88,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) ctx->force = true; } if (ctx->cell) { - afs_put_cell(ctx->net, ctx->cell); + afs_unuse_cell(ctx->net, ctx->cell); ctx->cell = NULL; } if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) { @@ -124,7 +124,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) char *buf; if (src_as->cell) - ctx->cell = afs_get_cell(src_as->cell); + ctx->cell = afs_use_cell(src_as->cell); if (size < 2 || size > PAGE_SIZE - 1) return -EINVAL; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e817fc740ba0..855d7358933b 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -38,7 +38,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) if (v == SEQ_START_TOKEN) { /* display header on line 1 */ - seq_puts(m, "USE TTL SV ST NAME\n"); + seq_puts(m, "USE ACT TTL SV ST NAME\n"); return 0; } @@ -46,10 +46,11 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) vllist = rcu_dereference(cell->vl_servers); /* display one cell per line on subsequent lines */ - seq_printf(m, "%3u %6lld %2u %2u %s\n", - atomic_read(&cell->usage), + seq_printf(m, "%3u %3u %6lld %2u %2u %s\n", + atomic_read(&cell->ref), + atomic_read(&cell->active), cell->dns_expiry - ktime_get_real_seconds(), - vllist->nr_servers, + vllist ? vllist->nr_servers : 0, cell->state, cell->name); return 0; @@ -128,7 +129,7 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) } if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags)) - afs_put_cell(net, cell); + afs_unuse_cell(net, cell); } else { goto inval; } @@ -154,13 +155,11 @@ static int afs_proc_rootcell_show(struct seq_file *m, void *v) struct afs_net *net; net = afs_seq2net_single(m); - if (rcu_access_pointer(net->ws_cell)) { - rcu_read_lock(); - cell = rcu_dereference(net->ws_cell); - if (cell) - seq_printf(m, "%s\n", cell->name); - rcu_read_unlock(); - } + down_read(&net->cells_lock); + cell = net->ws_cell; + if (cell) + seq_printf(m, "%s\n", cell->name); + up_read(&net->cells_lock); return 0; } diff --git a/fs/afs/super.c b/fs/afs/super.c index b552357b1d13..e72c223f831d 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -294,7 +294,7 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) cellnamesz, cellnamesz, cellname ?: ""); return PTR_ERR(cell); } - afs_put_cell(ctx->net, ctx->cell); + afs_unuse_cell(ctx->net, ctx->cell); ctx->cell = cell; } @@ -389,8 +389,8 @@ static int afs_validate_fc(struct fs_context *fc) _debug("switch to alias"); key_put(ctx->key); ctx->key = NULL; - cell = afs_get_cell(ctx->cell->alias_of); - afs_put_cell(ctx->net, ctx->cell); + cell = afs_use_cell(ctx->cell->alias_of); + afs_unuse_cell(ctx->net, ctx->cell); ctx->cell = cell; goto reget_key; } @@ -508,7 +508,7 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) if (ctx->dyn_root) { as->dyn_root = true; } else { - as->cell = afs_get_cell(ctx->cell); + as->cell = afs_use_cell(ctx->cell); as->volume = afs_get_volume(ctx->volume, afs_volume_trace_get_alloc_sbi); } @@ -521,7 +521,7 @@ static void afs_destroy_sbi(struct afs_super_info *as) if (as) { struct afs_net *net = afs_net(as->net_ns); afs_put_volume(net, as->volume, afs_volume_trace_put_destroy_sbi); - afs_put_cell(net, as->cell); + afs_unuse_cell(net, as->cell); put_net(as->net_ns); kfree(as); } @@ -607,7 +607,7 @@ static void afs_free_fc(struct fs_context *fc) afs_destroy_sbi(fc->s_fs_info); afs_put_volume(ctx->net, ctx->volume, afs_volume_trace_put_free_fc); - afs_put_cell(ctx->net, ctx->cell); + afs_unuse_cell(ctx->net, ctx->cell); key_put(ctx->key); kfree(ctx); } @@ -634,9 +634,7 @@ static int afs_init_fs_context(struct fs_context *fc) ctx->net = afs_net(fc->net_ns); /* Default to the workstation cell. */ - rcu_read_lock(); - cell = afs_lookup_cell_rcu(ctx->net, NULL, 0); - rcu_read_unlock(); + cell = afs_find_cell(ctx->net, NULL, 0); if (IS_ERR(cell)) cell = NULL; ctx->cell = cell; diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 5082ef04e99c..ddb4cb67d0fd 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -177,7 +177,7 @@ static int afs_compare_cell_roots(struct afs_cell *cell) is_alias: rcu_read_unlock(); - cell->alias_of = afs_get_cell(p); + cell->alias_of = afs_use_cell(p); return 1; } @@ -247,18 +247,18 @@ static int afs_query_for_alias(struct afs_cell *cell, struct key *key) continue; if (p->root_volume) continue; /* Ignore cells that have a root.cell volume. */ - afs_get_cell(p); + afs_use_cell(p); mutex_unlock(&cell->net->proc_cells_lock); if (afs_query_for_alias_one(cell, key, p) != 0) goto is_alias; if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) { - afs_put_cell(cell->net, p); + afs_unuse_cell(cell->net, p); return -ERESTARTSYS; } - afs_put_cell(cell->net, p); + afs_unuse_cell(cell->net, p); } mutex_unlock(&cell->net->proc_cells_lock); diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index f405ca8b240a..750bd1579f21 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -45,7 +45,7 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) cell->dns_expiry <= ktime_get_real_seconds()) { dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count); set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); - queue_work(afs_wq, &cell->manager); + afs_queue_cell(cell); if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { if (wait_var_event_interruptible( diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 9bc0509e3634..a838030e9563 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -106,7 +106,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, return volume; error_1: - afs_put_cell(params->net, volume->cell); + afs_put_cell(volume->cell); kfree(volume); error_0: return ERR_PTR(ret); @@ -228,7 +228,7 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) afs_remove_volume_from_cell(volume); afs_put_serverlist(net, rcu_access_pointer(volume->servers)); - afs_put_cell(net, volume->cell); + afs_put_cell(volume->cell); trace_afs_volume(volume->vid, atomic_read(&volume->usage), afs_volume_trace_free); kfree_rcu(volume, rcu); diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig new file mode 100644 index 000000000000..9f436425716a --- /dev/null +++ b/fs/aufs/Kconfig @@ -0,0 +1,199 @@ +# SPDX-License-Identifier: GPL-2.0 +config AUFS_FS + tristate "Aufs (Advanced multi layered unification filesystem) support" + help + Aufs is a stackable unification filesystem such as Unionfs, + which unifies several directories and provides a merged single + directory. + In the early days, aufs was entirely re-designed and + re-implemented Unionfs Version 1.x series. Introducing many + original ideas, approaches and improvements, it becomes totally + different from Unionfs while keeping the basic features. + +if AUFS_FS +choice + prompt "Maximum number of branches" + default AUFS_BRANCH_MAX_127 + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_127 + bool "127" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_511 + bool "511" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_1023 + bool "1023" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_32767 + bool "32767" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +endchoice + +config AUFS_SBILIST + bool + depends on AUFS_MAGIC_SYSRQ || PROC_FS + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq or /proc, enabled automatically. + +config AUFS_HNOTIFY + bool "Detect direct branch access (bypassing aufs)" + help + If you want to modify files on branches directly, eg. bypassing aufs, + and want aufs to detect the changes of them fully, then enable this + option and use 'udba=notify' mount option. + Currently there is only one available configuration, "fsnotify". + It will have a negative impact to the performance. + See detail in aufs.5. + +choice + prompt "method" if AUFS_HNOTIFY + default AUFS_HFSNOTIFY +config AUFS_HFSNOTIFY + bool "fsnotify" + select FSNOTIFY +endchoice + +config AUFS_EXPORT + bool "NFS-exportable aufs" + depends on EXPORTFS + help + If you want to export your mounted aufs via NFS, then enable this + option. There are several requirements for this configuration. + See detail in aufs.5. + +config AUFS_INO_T_64 + bool + depends on AUFS_EXPORT + depends on 64BIT && !(ALPHA || S390) + default y + help + Automatic configuration for internal use. + /* typedef unsigned long/int __kernel_ino_t */ + /* alpha and s390x are int */ + +config AUFS_XATTR + bool "support for XATTR/EA (including Security Labels)" + help + If your branch fs supports XATTR/EA and you want to make them + available in aufs too, then enable this opsion and specify the + branch attributes for EA. + See detail in aufs.5. + +config AUFS_FHSM + bool "File-based Hierarchical Storage Management" + help + Hierarchical Storage Management (or HSM) is a well-known feature + in the storage world. Aufs provides this feature as file-based. + with multiple branches. + These multiple branches are prioritized, ie. the topmost one + should be the fastest drive and be used heavily. + +config AUFS_RDU + bool "Readdir in userspace" + help + Aufs has two methods to provide a merged view for a directory, + by a user-space library and by kernel-space natively. The latter + is always enabled but sometimes large and slow. + If you enable this option, install the library in aufs2-util + package, and set some environment variables for your readdir(3), + then the work will be handled in user-space which generally + shows better performance in most cases. + See detail in aufs.5. + +config AUFS_DIRREN + bool "Workaround for rename(2)-ing a directory" + help + By default, aufs returns EXDEV error in renameing a dir who has + his child on the lower branch, since it is a bad idea to issue + rename(2) internally for every lower branch. But user may not + accept this behaviour. So here is a workaround to allow such + rename(2) and store some extra infromation on the writable + branch. Obviously this costs high (and I don't like it). + To use this feature, you need to enable this configuration AND + to specify the mount option `dirren.' + See details in aufs.5 and the design documents. + +config AUFS_SHWH + bool "Show whiteouts" + help + If you want to make the whiteouts in aufs visible, then enable + this option and specify 'shwh' mount option. Although it may + sounds like philosophy or something, but in technically it + simply shows the name of whiteout with keeping its behaviour. + +config AUFS_BR_RAMFS + bool "Ramfs (initramfs/rootfs) as an aufs branch" + help + If you want to use ramfs as an aufs branch fs, then enable this + option. Generally tmpfs is recommended. + Aufs prohibited them to be a branch fs by default, because + initramfs becomes unusable after switch_root or something + generally. If you sets initramfs as an aufs branch and boot your + system by switch_root, you will meet a problem easily since the + files in initramfs may be inaccessible. + Unless you are going to use ramfs as an aufs branch fs without + switch_root or something, leave it N. + +config AUFS_BR_FUSE + bool "Fuse fs as an aufs branch" + depends on FUSE_FS + select AUFS_POLL + help + If you want to use fuse-based userspace filesystem as an aufs + branch fs, then enable this option. + It implements the internal poll(2) operation which is + implemented by fuse only (curretnly). + +config AUFS_POLL + bool + help + Automatic configuration for internal use. + +config AUFS_BR_HFSPLUS + bool "Hfsplus as an aufs branch" + depends on HFSPLUS_FS + default y + help + If you want to use hfsplus fs as an aufs branch fs, then enable + this option. This option introduces a small overhead at + copying-up a file on hfsplus. + +config AUFS_BDEV_LOOP + bool + depends on BLK_DEV_LOOP + default y + help + Automatic configuration for internal use. + Convert =[ym] into =y. + +config AUFS_DEBUG + bool "Debug aufs" + help + Enable this to compile aufs internal debug code. + It will have a negative impact to the performance. + +config AUFS_MAGIC_SYSRQ + bool + depends on AUFS_DEBUG && MAGIC_SYSRQ + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq, enabled automatically. +endif diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile new file mode 100644 index 000000000000..2c819a64935e --- /dev/null +++ b/fs/aufs/Makefile @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: GPL-2.0 + +include ${src}/magic.mk +ifeq (${CONFIG_AUFS_FS},m) +include ${src}/conf.mk +endif +-include ${src}/priv_def.mk + +# cf. include/linux/kernel.h +# enable pr_debug +ccflags-y += -DDEBUG +# sparse requires the full pathname +ifdef M +ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h +else +ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h +endif + +obj-$(CONFIG_AUFS_FS) += aufs.o +aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ + wkq.o vfsub.o dcsub.o \ + cpup.o whout.o wbr_policy.o \ + dinfo.o dentry.o \ + dynop.o \ + finfo.o file.o f_op.o \ + dir.o vdir.o \ + iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ + mvdown.o ioctl.o + +# all are boolean +aufs-$(CONFIG_PROC_FS) += procfs.o plink.o +aufs-$(CONFIG_SYSFS) += sysfs.o +aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o +aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o +aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o +aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o +aufs-$(CONFIG_AUFS_EXPORT) += export.o +aufs-$(CONFIG_AUFS_XATTR) += xattr.o +aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o +aufs-$(CONFIG_AUFS_DIRREN) += dirren.o +aufs-$(CONFIG_AUFS_FHSM) += fhsm.o +aufs-$(CONFIG_AUFS_POLL) += poll.o +aufs-$(CONFIG_AUFS_RDU) += rdu.o +aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o +aufs-$(CONFIG_AUFS_DEBUG) += debug.o +aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h new file mode 100644 index 000000000000..9a573445876f --- /dev/null +++ b/fs/aufs/aufs.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * all header files + */ + +#ifndef __AUFS_H__ +#define __AUFS_H__ + +#ifdef __KERNEL__ + +#define AuStub(type, name, body, ...) \ + static inline type name(__VA_ARGS__) { body; } + +#define AuStubVoid(name, ...) \ + AuStub(void, name, , __VA_ARGS__) +#define AuStubInt0(name, ...) \ + AuStub(int, name, return 0, __VA_ARGS__) + +#include "debug.h" + +#include "branch.h" +#include "cpup.h" +#include "dcsub.h" +#include "dbgaufs.h" +#include "dentry.h" +#include "dir.h" +#include "dirren.h" +#include "dynop.h" +#include "file.h" +#include "fstype.h" +#include "hbl.h" +#include "inode.h" +#include "lcnt.h" +#include "loop.h" +#include "module.h" +#include "opts.h" +#include "rwsem.h" +#include "super.h" +#include "sysaufs.h" +#include "vfsub.h" +#include "whout.h" +#include "wkq.h" + +#endif /* __KERNEL__ */ +#endif /* __AUFS_H__ */ diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c new file mode 100644 index 000000000000..26d41e1bc0c3 --- /dev/null +++ b/fs/aufs/branch.c @@ -0,0 +1,1427 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * branch management + */ + +#include <linux/compat.h> +#include <linux/statfs.h> +#include "aufs.h" + +/* + * free a single branch + */ +static void au_br_do_free(struct au_branch *br) +{ + int i; + struct au_wbr *wbr; + struct au_dykey **key; + + au_hnotify_fin_br(br); + /* always, regardless the mount option */ + au_dr_hino_free(&br->br_dirren); + au_xino_put(br); + + AuLCntZero(au_lcnt_read(&br->br_nfiles, /*do_rev*/0)); + au_lcnt_fin(&br->br_nfiles, /*do_sync*/0); + AuLCntZero(au_lcnt_read(&br->br_count, /*do_rev*/0)); + au_lcnt_fin(&br->br_count, /*do_sync*/0); + + wbr = br->br_wbr; + if (wbr) { + for (i = 0; i < AuBrWh_Last; i++) + dput(wbr->wbr_wh[i]); + AuDebugOn(atomic_read(&wbr->wbr_wh_running)); + AuRwDestroy(&wbr->wbr_wh_rwsem); + } + + if (br->br_fhsm) { + au_br_fhsm_fin(br->br_fhsm); + au_kfree_try_rcu(br->br_fhsm); + } + + key = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++, key++) + if (*key) + au_dy_put(*key); + else + break; + + /* recursive lock, s_umount of branch's */ + /* synchronize_rcu(); */ /* why? */ + lockdep_off(); + path_put(&br->br_path); + lockdep_on(); + au_kfree_rcu(wbr); + au_lcnt_wait_for_fin(&br->br_nfiles); + au_lcnt_wait_for_fin(&br->br_count); + /* I don't know why, but percpu_refcount requires this */ + /* synchronize_rcu(); */ + au_kfree_rcu(br); +} + +/* + * frees all branches + */ +void au_br_free(struct au_sbinfo *sbinfo) +{ + aufs_bindex_t bmax; + struct au_branch **br; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + bmax = sbinfo->si_bbot + 1; + br = sbinfo->si_branch; + while (bmax--) + au_br_do_free(*br++); +} + +/* + * find the index of a branch which is specified by @br_id. + */ +int au_br_index(struct super_block *sb, aufs_bindex_t br_id) +{ + aufs_bindex_t bindex, bbot; + + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) + if (au_sbr_id(sb, bindex) == br_id) + return bindex; + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * add a branch + */ + +static int test_overlap(struct super_block *sb, struct dentry *h_adding, + struct dentry *h_root) +{ + if (unlikely(h_adding == h_root + || au_test_loopback_overlap(sb, h_adding))) + return 1; + if (h_adding->d_sb != h_root->d_sb) + return 0; + return au_test_subdir(h_adding, h_root) + || au_test_subdir(h_root, h_adding); +} + +/* + * returns a newly allocated branch. @new_nbranch is a number of branches + * after adding a branch. + */ +static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch, + int perm) +{ + struct au_branch *add_branch; + struct dentry *root; + struct inode *inode; + int err; + + err = -ENOMEM; + add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS); + if (unlikely(!add_branch)) + goto out; + add_branch->br_xino = au_xino_alloc(/*nfile*/1); + if (unlikely(!add_branch->br_xino)) + goto out_br; + err = au_hnotify_init_br(add_branch, perm); + if (unlikely(err)) + goto out_xino; + + if (au_br_writable(perm)) { + /* may be freed separately at changing the branch permission */ + add_branch->br_wbr = kzalloc(sizeof(*add_branch->br_wbr), + GFP_NOFS); + if (unlikely(!add_branch->br_wbr)) + goto out_hnotify; + } + + if (au_br_fhsm(perm)) { + err = au_fhsm_br_alloc(add_branch); + if (unlikely(err)) + goto out_wbr; + } + + root = sb->s_root; + err = au_sbr_realloc(au_sbi(sb), new_nbranch, /*may_shrink*/0); + if (!err) + err = au_di_realloc(au_di(root), new_nbranch, /*may_shrink*/0); + if (!err) { + inode = d_inode(root); + err = au_hinode_realloc(au_ii(inode), new_nbranch, + /*may_shrink*/0); + } + if (!err) + return add_branch; /* success */ + +out_wbr: + au_kfree_rcu(add_branch->br_wbr); +out_hnotify: + au_hnotify_fin_br(add_branch); +out_xino: + au_xino_put(add_branch); +out_br: + au_kfree_rcu(add_branch); +out: + return ERR_PTR(err); +} + +/* + * test if the branch permission is legal or not. + */ +static int test_br(struct inode *inode, int brperm, char *path) +{ + int err; + + err = (au_br_writable(brperm) && IS_RDONLY(inode)); + if (!err) + goto out; + + err = -EINVAL; + pr_err("write permission for readonly mount or inode, %s\n", path); + +out: + return err; +} + +/* + * returns: + * 0: success, the caller will add it + * plus: success, it is already unified, the caller should ignore it + * minus: error + */ +static int test_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bbot, bindex; + struct dentry *root, *h_dentry; + struct inode *inode, *h_inode; + + root = sb->s_root; + bbot = au_sbbot(sb); + if (unlikely(bbot >= 0 + && au_find_dbindex(root, add->path.dentry) >= 0)) { + err = 1; + if (!remount) { + err = -EINVAL; + pr_err("%s duplicated\n", add->pathname); + } + goto out; + } + + err = -ENOSPC; /* -E2BIG; */ + if (unlikely(AUFS_BRANCH_MAX <= add->bindex + || AUFS_BRANCH_MAX - 1 <= bbot)) { + pr_err("number of branches exceeded %s\n", add->pathname); + goto out; + } + + err = -EDOM; + if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) { + pr_err("bad index %d\n", add->bindex); + goto out; + } + + inode = d_inode(add->path.dentry); + err = -ENOENT; + if (unlikely(!inode->i_nlink)) { + pr_err("no existence %s\n", add->pathname); + goto out; + } + + err = -EINVAL; + if (unlikely(inode->i_sb == sb)) { + pr_err("%s must be outside\n", add->pathname); + goto out; + } + + if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) { + pr_err("unsupported filesystem, %s (%s)\n", + add->pathname, au_sbtype(inode->i_sb)); + goto out; + } + + if (unlikely(inode->i_sb->s_stack_depth)) { + pr_err("already stacked, %s (%s)\n", + add->pathname, au_sbtype(inode->i_sb)); + goto out; + } + + err = test_br(d_inode(add->path.dentry), add->perm, add->pathname); + if (unlikely(err)) + goto out; + + if (bbot < 0) + return 0; /* success */ + + err = -EINVAL; + for (bindex = 0; bindex <= bbot; bindex++) + if (unlikely(test_overlap(sb, add->path.dentry, + au_h_dptr(root, bindex)))) { + pr_err("%s is overlapped\n", add->pathname); + goto out; + } + + err = 0; + if (au_opt_test(au_mntflags(sb), WARN_PERM)) { + h_dentry = au_h_dptr(root, 0); + h_inode = d_inode(h_dentry); + if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO) + || !uid_eq(h_inode->i_uid, inode->i_uid) + || !gid_eq(h_inode->i_gid, inode->i_gid)) + pr_warn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n", + add->pathname, + i_uid_read(inode), i_gid_read(inode), + (inode->i_mode & S_IALLUGO), + i_uid_read(h_inode), i_gid_read(h_inode), + (h_inode->i_mode & S_IALLUGO)); + } + +out: + return err; +} + +/* + * initialize or clean the whiteouts for an adding branch + */ +static int au_br_init_wh(struct super_block *sb, struct au_branch *br, + int new_perm) +{ + int err, old_perm; + aufs_bindex_t bindex; + struct inode *h_inode; + struct au_wbr *wbr; + struct au_hinode *hdir; + struct dentry *h_dentry; + + err = vfsub_mnt_want_write(au_br_mnt(br)); + if (unlikely(err)) + goto out; + + wbr = br->br_wbr; + old_perm = br->br_perm; + br->br_perm = new_perm; + hdir = NULL; + h_inode = NULL; + bindex = au_br_index(sb, br->br_id); + if (0 <= bindex) { + hdir = au_hi(d_inode(sb->s_root), bindex); + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + } else { + h_dentry = au_br_dentry(br); + h_inode = d_inode(h_dentry); + inode_lock_nested(h_inode, AuLsc_I_PARENT); + } + if (!wbr) + err = au_wh_init(br, sb); + else { + wbr_wh_write_lock(wbr); + err = au_wh_init(br, sb); + wbr_wh_write_unlock(wbr); + } + if (hdir) + au_hn_inode_unlock(hdir); + else + inode_unlock(h_inode); + vfsub_mnt_drop_write(au_br_mnt(br)); + br->br_perm = old_perm; + + if (!err && wbr && !au_br_writable(new_perm)) { + au_kfree_rcu(wbr); + br->br_wbr = NULL; + } + +out: + return err; +} + +static int au_wbr_init(struct au_branch *br, struct super_block *sb, + int perm) +{ + int err; + struct kstatfs kst; + struct au_wbr *wbr; + + wbr = br->br_wbr; + au_rw_init(&wbr->wbr_wh_rwsem); + atomic_set(&wbr->wbr_wh_running, 0); + + /* + * a limit for rmdir/rename a dir + * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h + */ + err = vfs_statfs(&br->br_path, &kst); + if (unlikely(err)) + goto out; + err = -EINVAL; + if (kst.f_namelen >= NAME_MAX) + err = au_br_init_wh(sb, br, perm); + else + pr_err("%pd(%s), unsupported namelen %ld\n", + au_br_dentry(br), + au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen); + +out: + return err; +} + +/* initialize a new branch */ +static int au_br_init(struct au_branch *br, struct super_block *sb, + struct au_opt_add *add) +{ + int err; + struct au_branch *brbase; + struct file *xf; + struct inode *h_inode; + + err = 0; + br->br_perm = add->perm; + br->br_path = add->path; /* set first, path_get() later */ + spin_lock_init(&br->br_dykey_lock); + au_lcnt_init(&br->br_nfiles, /*release*/NULL); + au_lcnt_init(&br->br_count, /*release*/NULL); + br->br_id = au_new_br_id(sb); + AuDebugOn(br->br_id < 0); + + /* always, regardless the given option */ + err = au_dr_br_init(sb, br, &add->path); + if (unlikely(err)) + goto out_err; + + if (au_br_writable(add->perm)) { + err = au_wbr_init(br, sb, add->perm); + if (unlikely(err)) + goto out_err; + } + + if (au_opt_test(au_mntflags(sb), XINO)) { + brbase = au_sbr(sb, 0); + xf = au_xino_file(brbase->br_xino, /*idx*/-1); + AuDebugOn(!xf); + h_inode = d_inode(add->path.dentry); + err = au_xino_init_br(sb, br, h_inode->i_ino, &xf->f_path); + if (unlikely(err)) { + AuDebugOn(au_xino_file(br->br_xino, /*idx*/-1)); + goto out_err; + } + } + + sysaufs_br_init(br); + path_get(&br->br_path); + goto out; /* success */ + +out_err: + memset(&br->br_path, 0, sizeof(br->br_path)); +out: + return err; +} + +static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex, + struct au_branch *br, aufs_bindex_t bbot, + aufs_bindex_t amount) +{ + struct au_branch **brp; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + memmove(brp + 1, brp, sizeof(*brp) * amount); + *brp = br; + sbinfo->si_bbot++; + if (unlikely(bbot < 0)) + sbinfo->si_bbot = 0; +} + +static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, + aufs_bindex_t bbot, aufs_bindex_t amount) +{ + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = au_hdentry(dinfo, bindex); + memmove(hdp + 1, hdp, sizeof(*hdp) * amount); + au_h_dentry_init(hdp); + dinfo->di_bbot++; + if (unlikely(bbot < 0)) + dinfo->di_btop = 0; +} + +static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, + aufs_bindex_t bbot, aufs_bindex_t amount) +{ + struct au_hinode *hip; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = au_hinode(iinfo, bindex); + memmove(hip + 1, hip, sizeof(*hip) * amount); + au_hinode_init(hip); + iinfo->ii_bbot++; + if (unlikely(bbot < 0)) + iinfo->ii_btop = 0; +} + +static void au_br_do_add(struct super_block *sb, struct au_branch *br, + aufs_bindex_t bindex) +{ + struct dentry *root, *h_dentry; + struct inode *root_inode, *h_inode; + aufs_bindex_t bbot, amount; + + root = sb->s_root; + root_inode = d_inode(root); + bbot = au_sbbot(sb); + amount = bbot + 1 - bindex; + h_dentry = au_br_dentry(br); + au_sbilist_lock(); + au_br_do_add_brp(au_sbi(sb), bindex, br, bbot, amount); + au_br_do_add_hdp(au_di(root), bindex, bbot, amount); + au_br_do_add_hip(au_ii(root_inode), bindex, bbot, amount); + au_set_h_dptr(root, bindex, dget(h_dentry)); + h_inode = d_inode(h_dentry); + au_set_h_iptr(root_inode, bindex, au_igrab(h_inode), /*flags*/0); + au_sbilist_unlock(); +} + +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bbot, add_bindex; + struct dentry *root, *h_dentry; + struct inode *root_inode; + struct au_branch *add_branch; + + root = sb->s_root; + root_inode = d_inode(root); + IMustLock(root_inode); + IiMustWriteLock(root_inode); + err = test_add(sb, add, remount); + if (unlikely(err < 0)) + goto out; + if (err) { + err = 0; + goto out; /* success */ + } + + bbot = au_sbbot(sb); + add_branch = au_br_alloc(sb, bbot + 2, add->perm); + err = PTR_ERR(add_branch); + if (IS_ERR(add_branch)) + goto out; + + err = au_br_init(add_branch, sb, add); + if (unlikely(err)) { + au_br_do_free(add_branch); + goto out; + } + + add_bindex = add->bindex; + sysaufs_brs_del(sb, add_bindex); /* remove successors */ + au_br_do_add(sb, add_branch, add_bindex); + sysaufs_brs_add(sb, add_bindex); /* append successors */ + dbgaufs_brs_add(sb, add_bindex, /*topdown*/0); /* rename successors */ + + h_dentry = add->path.dentry; + if (!add_bindex) { + au_cpup_attr_all(root_inode, /*force*/1); + sb->s_maxbytes = h_dentry->d_sb->s_maxbytes; + } else + au_add_nlink(root_inode, d_inode(h_dentry)); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static unsigned long long au_farray_cb(struct super_block *sb, void *a, + unsigned long long max __maybe_unused, + void *arg) +{ + unsigned long long n; + struct file **p, *f; + struct hlist_bl_head *files; + struct hlist_bl_node *pos; + struct au_finfo *finfo; + + n = 0; + p = a; + files = &au_sbi(sb)->si_files; + hlist_bl_lock(files); + hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { + f = finfo->fi_file; + if (file_count(f) + && !special_file(file_inode(f)->i_mode)) { + get_file(f); + *p++ = f; + n++; + AuDebugOn(n > max); + } + } + hlist_bl_unlock(files); + + return n; +} + +static struct file **au_farray_alloc(struct super_block *sb, + unsigned long long *max) +{ + struct au_sbinfo *sbi; + + sbi = au_sbi(sb); + *max = au_lcnt_read(&sbi->si_nfiles, /*do_rev*/1); + return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL); +} + +static void au_farray_free(struct file **a, unsigned long long max) +{ + unsigned long long ull; + + for (ull = 0; ull < max; ull++) + if (a[ull]) + fput(a[ull]); + kvfree(a); +} + +/* ---------------------------------------------------------------------- */ + +/* + * delete a branch + */ + +/* to show the line number, do not make it inlined function */ +#define AuVerbose(do_info, fmt, ...) do { \ + if (do_info) \ + pr_info(fmt, ##__VA_ARGS__); \ +} while (0) + +static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop, + aufs_bindex_t bbot) +{ + return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot; +} + +static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop, + aufs_bindex_t bbot) +{ + return au_test_ibusy(d_inode(dentry), btop, bbot); +} + +/* + * test if the branch is deletable or not. + */ +static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err, i, j, ndentry; + aufs_bindex_t btop, bbot; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *d; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, root, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; !err && i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = 0; !err && j < ndentry; j++) { + d = dpage->dentries[j]; + AuDebugOn(au_dcount(d) <= 0); + if (!au_digen_test(d, sigen)) { + di_read_lock_child(d, AuLock_IR); + if (unlikely(au_dbrange_test(d))) { + di_read_unlock(d, AuLock_IR); + continue; + } + } else { + di_write_lock_child(d); + if (unlikely(au_dbrange_test(d))) { + di_write_unlock(d); + continue; + } + err = au_reval_dpath(d, sigen); + if (!err) + di_downgrade_lock(d, AuLock_IR); + else { + di_write_unlock(d); + break; + } + } + + /* AuDbgDentry(d); */ + btop = au_dbtop(d); + bbot = au_dbbot(d); + if (btop <= bindex + && bindex <= bbot + && au_h_dptr(d, bindex) + && au_test_dbusy(d, btop, bbot)) { + err = -EBUSY; + AuVerbose(verbose, "busy %pd\n", d); + AuDbgDentry(d); + } + di_read_unlock(d, AuLock_IR); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err; + unsigned long long max, ull; + struct inode *i, **array; + aufs_bindex_t btop, bbot; + + array = au_iarray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + AuDbg("b%d\n", bindex); + for (ull = 0; !err && ull < max; ull++) { + i = array[ull]; + if (unlikely(!i)) + break; + if (i->i_ino == AUFS_ROOT_INO) + continue; + + /* AuDbgInode(i); */ + if (au_iigen(i, NULL) == sigen) + ii_read_lock_child(i); + else { + ii_write_lock_child(i); + err = au_refresh_hinode_self(i); + au_iigen_dec(i); + if (!err) + ii_downgrade_lock(i); + else { + ii_write_unlock(i); + break; + } + } + + btop = au_ibtop(i); + bbot = au_ibbot(i); + if (btop <= bindex + && bindex <= bbot + && au_h_iptr(i, bindex) + && au_test_ibusy(i, btop, bbot)) { + err = -EBUSY; + AuVerbose(verbose, "busy i%lu\n", i->i_ino); + AuDbgInode(i); + } + ii_read_unlock(i); + } + au_iarray_free(array, max); + +out: + return err; +} + +static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, + const unsigned int verbose) +{ + int err; + unsigned int sigen; + + sigen = au_sigen(root->d_sb); + DiMustNoWaiters(root); + IiMustNoWaiters(d_inode(root)); + di_write_unlock(root); + err = test_dentry_busy(root, bindex, sigen, verbose); + if (!err) + err = test_inode_busy(root->d_sb, bindex, sigen, verbose); + di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */ + + return err; +} + +static int test_dir_busy(struct file *file, aufs_bindex_t br_id, + struct file **to_free, int *idx) +{ + int err; + unsigned char matched, root; + aufs_bindex_t bindex, bbot; + struct au_fidir *fidir; + struct au_hfile *hfile; + + err = 0; + root = IS_ROOT(file->f_path.dentry); + if (root) { + get_file(file); + to_free[*idx] = file; + (*idx)++; + goto out; + } + + matched = 0; + fidir = au_fi(file)->fi_hdir; + AuDebugOn(!fidir); + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); bindex <= bbot; bindex++) { + hfile = fidir->fd_hfile + bindex; + if (!hfile->hf_file) + continue; + + if (hfile->hf_br->br_id == br_id) { + matched = 1; + break; + } + } + if (matched) + err = -EBUSY; + +out: + return err; +} + +static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id, + struct file **to_free, int opened) +{ + int err, idx; + unsigned long long ull, max; + aufs_bindex_t btop; + struct file *file, **array; + struct dentry *root; + struct au_hfile *hfile; + + array = au_farray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + idx = 0; + root = sb->s_root; + di_write_unlock(root); + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + fi_read_lock(file); + btop = au_fbtop(file); + if (!d_is_dir(file->f_path.dentry)) { + hfile = &au_fi(file)->fi_htop; + if (hfile->hf_br->br_id == br_id) + err = -EBUSY; + } else + err = test_dir_busy(file, br_id, to_free, &idx); + fi_read_unlock(file); + if (unlikely(err)) + break; + } + di_write_lock_child(root); + au_farray_free(array, max); + AuDebugOn(idx > opened); + +out: + return err; +} + +static void br_del_file(struct file **to_free, unsigned long long opened, + aufs_bindex_t br_id) +{ + unsigned long long ull; + aufs_bindex_t bindex, btop, bbot, bfound; + struct file *file; + struct au_fidir *fidir; + struct au_hfile *hfile; + + for (ull = 0; ull < opened; ull++) { + file = to_free[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + AuDebugOn(!d_is_dir(file->f_path.dentry)); + bfound = -1; + fidir = au_fi(file)->fi_hdir; + AuDebugOn(!fidir); + fi_write_lock(file); + btop = au_fbtop(file); + bbot = au_fbbot_dir(file); + for (bindex = btop; bindex <= bbot; bindex++) { + hfile = fidir->fd_hfile + bindex; + if (!hfile->hf_file) + continue; + + if (hfile->hf_br->br_id == br_id) { + bfound = bindex; + break; + } + } + AuDebugOn(bfound < 0); + au_set_h_fptr(file, bfound, NULL); + if (bfound == btop) { + for (btop++; btop <= bbot; btop++) + if (au_hf_dir(file, btop)) { + au_set_fbtop(file, btop); + break; + } + } + fi_write_unlock(file); + } +} + +static void au_br_do_del_brp(struct au_sbinfo *sbinfo, + const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_branch **brp, **p; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + if (bindex < bbot) + memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex)); + sbinfo->si_branch[0 + bbot] = NULL; + sbinfo->si_bbot--; + + p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + sbinfo->si_branch = p; + /* harmless error */ +} + +static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_hdentry *hdp, *p; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = au_hdentry(dinfo, bindex); + if (bindex < bbot) + memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex)); + /* au_h_dentry_init(au_hdentry(dinfo, bbot); */ + dinfo->di_bbot--; + + p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + dinfo->di_hdentry = p; + /* harmless error */ +} + +static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_hinode *hip, *p; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = au_hinode(iinfo, bindex); + if (bindex < bbot) + memmove(hip, hip + 1, sizeof(*hip) * (bbot - bindex)); + /* au_hinode_init(au_hinode(iinfo, bbot)); */ + iinfo->ii_bbot--; + + p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + iinfo->ii_hinode = p; + /* harmless error */ +} + +static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, + struct au_branch *br) +{ + aufs_bindex_t bbot; + struct au_sbinfo *sbinfo; + struct dentry *root, *h_root; + struct inode *inode, *h_inode; + struct au_hinode *hinode; + + SiMustWriteLock(sb); + + root = sb->s_root; + inode = d_inode(root); + sbinfo = au_sbi(sb); + bbot = sbinfo->si_bbot; + + h_root = au_h_dptr(root, bindex); + hinode = au_hi(inode, bindex); + h_inode = au_igrab(hinode->hi_inode); + au_hiput(hinode); + + au_sbilist_lock(); + au_br_do_del_brp(sbinfo, bindex, bbot); + au_br_do_del_hdp(au_di(root), bindex, bbot); + au_br_do_del_hip(au_ii(inode), bindex, bbot); + au_sbilist_unlock(); + + /* ignore an error */ + au_dr_br_fin(sb, br); /* always, regardless the mount option */ + + dput(h_root); + iput(h_inode); + au_br_do_free(br); +} + +static unsigned long long empty_cb(struct super_block *sb, void *array, + unsigned long long max, void *arg) +{ + return max; +} + +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) +{ + int err, rerr, i; + unsigned long long opened; + unsigned int mnt_flags; + aufs_bindex_t bindex, bbot, br_id; + unsigned char do_wh, verbose; + struct au_branch *br; + struct au_wbr *wbr; + struct dentry *root; + struct file **to_free; + + err = 0; + opened = 0; + to_free = NULL; + root = sb->s_root; + bindex = au_find_dbindex(root, del->h_path.dentry); + if (bindex < 0) { + if (remount) + goto out; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", del->pathname); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = -EBUSY; + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + bbot = au_sbbot(sb); + if (unlikely(!bbot)) { + AuVerbose(verbose, "no more branches left\n"); + goto out; + } + + br = au_sbr(sb, bindex); + AuDebugOn(!path_equal(&br->br_path, &del->h_path)); + if (unlikely(au_lcnt_read(&br->br_count, /*do_rev*/1))) { + AuVerbose(verbose, "br %pd2 is busy now\n", del->h_path.dentry); + goto out; + } + + br_id = br->br_id; + opened = au_lcnt_read(&br->br_nfiles, /*do_rev*/1); + if (unlikely(opened)) { + to_free = au_array_alloc(&opened, empty_cb, sb, NULL); + err = PTR_ERR(to_free); + if (IS_ERR(to_free)) + goto out; + + err = test_file_busy(sb, br_id, to_free, opened); + if (unlikely(err)) { + AuVerbose(verbose, "%llu file(s) opened\n", opened); + goto out; + } + } + + wbr = br->br_wbr; + do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph); + if (do_wh) { + /* instead of WbrWhMustWriteLock(wbr) */ + SiMustWriteLock(sb); + for (i = 0; i < AuBrWh_Last; i++) { + dput(wbr->wbr_wh[i]); + wbr->wbr_wh[i] = NULL; + } + } + + err = test_children_busy(root, bindex, verbose); + if (unlikely(err)) { + if (do_wh) + goto out_wh; + goto out; + } + + err = 0; + if (to_free) { + /* + * now we confirmed the branch is deletable. + * let's free the remaining opened dirs on the branch. + */ + di_write_unlock(root); + br_del_file(to_free, opened, br_id); + di_write_lock_child(root); + } + + sysaufs_brs_del(sb, bindex); /* remove successors */ + dbgaufs_xino_del(br); /* remove one */ + au_br_do_del(sb, bindex, br); + sysaufs_brs_add(sb, bindex); /* append successors */ + dbgaufs_brs_add(sb, bindex, /*topdown*/1); /* rename successors */ + + if (!bindex) { + au_cpup_attr_all(d_inode(root), /*force*/1); + sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes; + } else + au_sub_nlink(d_inode(root), d_inode(del->h_path.dentry)); + if (au_opt_test(mnt_flags, PLINK)) + au_plink_half_refresh(sb, br_id); + + goto out; /* success */ + +out_wh: + /* revert */ + rerr = au_br_init_wh(sb, br, br->br_perm); + if (rerr) + pr_warn("failed re-creating base whiteout, %s. (%d)\n", + del->pathname, rerr); +out: + if (to_free) + au_farray_free(to_free, opened); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg) +{ + int err; + aufs_bindex_t btop, bbot; + struct aufs_ibusy ibusy; + struct inode *inode, *h_inode; + + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = copy_from_user(&ibusy, arg, sizeof(ibusy)); + if (!err) + /* VERIFY_WRITE */ + err = !access_ok(&arg->h_ino, sizeof(arg->h_ino)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + + err = -EINVAL; + si_read_lock(sb, AuLock_FLUSH); + if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb))) + goto out_unlock; + + err = 0; + ibusy.h_ino = 0; /* invalid */ + inode = ilookup(sb, ibusy.ino); + if (!inode + || inode->i_ino == AUFS_ROOT_INO + || au_is_bad_inode(inode)) + goto out_unlock; + + ii_read_lock_child(inode); + btop = au_ibtop(inode); + bbot = au_ibbot(inode); + if (btop <= ibusy.bindex && ibusy.bindex <= bbot) { + h_inode = au_h_iptr(inode, ibusy.bindex); + if (h_inode && au_test_ibusy(inode, btop, bbot)) + ibusy.h_ino = h_inode->i_ino; + } + ii_read_unlock(inode); + iput(inode); + +out_unlock: + si_read_unlock(sb); + if (!err) { + err = __put_user(ibusy.h_ino, &arg->h_ino); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + } + } +out: + return err; +} + +long au_ibusy_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg); +} + +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg)); +} +#endif + +/* ---------------------------------------------------------------------- */ + +/* + * change a branch permission + */ + +static void au_warn_ima(void) +{ +#ifdef CONFIG_IMA + /* since it doesn't support mark_files_ro() */ + AuWarn1("RW -> RO makes IMA to produce wrong message\n"); +#endif +} + +static int do_need_sigen_inc(int a, int b) +{ + return au_br_whable(a) && !au_br_whable(b); +} + +static int need_sigen_inc(int old, int new) +{ + return do_need_sigen_inc(old, new) + || do_need_sigen_inc(new, old); +} + +static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex) +{ + int err, do_warn; + unsigned int mnt_flags; + unsigned long long ull, max; + aufs_bindex_t br_id; + unsigned char verbose, writer; + struct file *file, *hf, **array; + struct au_hfile *hfile; + struct inode *h_inode; + + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + + array = au_farray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + do_warn = 0; + br_id = au_sbr_id(sb, bindex); + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + fi_read_lock(file); + if (unlikely(au_test_mmapped(file))) { + err = -EBUSY; + AuVerbose(verbose, "mmapped %pD\n", file); + AuDbgFile(file); + FiMustNoWaiters(file); + fi_read_unlock(file); + goto out_array; + } + + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + if (!d_is_reg(file->f_path.dentry) + || !(file->f_mode & FMODE_WRITE) + || hfile->hf_br->br_id != br_id + || !(hf->f_mode & FMODE_WRITE)) + array[ull] = NULL; + else { + do_warn = 1; + get_file(file); + } + + FiMustNoWaiters(file); + fi_read_unlock(file); + fput(file); + } + + err = 0; + if (do_warn) + au_warn_ima(); + + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (!file) + continue; + + /* todo: already flushed? */ + /* + * fs/super.c:mark_files_ro() is gone, but aufs keeps its + * approach which resets f_mode and calls mnt_drop_write() and + * file_release_write() for each file, because the branch + * attribute in aufs world is totally different from the native + * fs rw/ro mode. + */ + /* fi_read_lock(file); */ + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + /* fi_read_unlock(file); */ + spin_lock(&hf->f_lock); + writer = !!(hf->f_mode & FMODE_WRITER); + hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER); + spin_unlock(&hf->f_lock); + if (writer) { + h_inode = file_inode(hf); + if (hf->f_mode & FMODE_READ) + i_readcount_inc(h_inode); + put_write_access(h_inode); + __mnt_drop_write(hf->f_path.mnt); + } + } + +out_array: + au_farray_free(array, max); +out: + AuTraceErr(err); + return err; +} + +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh) +{ + int err, rerr; + aufs_bindex_t bindex; + struct dentry *root; + struct au_branch *br; + struct au_br_fhsm *bf; + + root = sb->s_root; + bindex = au_find_dbindex(root, mod->h_root); + if (bindex < 0) { + if (remount) + return 0; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", mod->path); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = test_br(d_inode(mod->h_root), mod->perm, mod->path); + if (unlikely(err)) + goto out; + + br = au_sbr(sb, bindex); + AuDebugOn(mod->h_root != au_br_dentry(br)); + if (br->br_perm == mod->perm) + return 0; /* success */ + + /* pre-allocate for non-fhsm --> fhsm */ + bf = NULL; + if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) { + err = au_fhsm_br_alloc(br); + if (unlikely(err)) + goto out; + bf = br->br_fhsm; + br->br_fhsm = NULL; + } + + if (au_br_writable(br->br_perm)) { + /* remove whiteout base */ + err = au_br_init_wh(sb, br, mod->perm); + if (unlikely(err)) + goto out_bf; + + if (!au_br_writable(mod->perm)) { + /* rw --> ro, file might be mmapped */ + DiMustNoWaiters(root); + IiMustNoWaiters(d_inode(root)); + di_write_unlock(root); + err = au_br_mod_files_ro(sb, bindex); + /* aufs_write_lock() calls ..._child() */ + di_write_lock_child(root); + + if (unlikely(err)) { + rerr = -ENOMEM; + br->br_wbr = kzalloc(sizeof(*br->br_wbr), + GFP_NOFS); + if (br->br_wbr) + rerr = au_wbr_init(br, sb, br->br_perm); + if (unlikely(rerr)) { + AuIOErr("nested error %d (%d)\n", + rerr, err); + br->br_perm = mod->perm; + } + } + } + } else if (au_br_writable(mod->perm)) { + /* ro --> rw */ + err = -ENOMEM; + br->br_wbr = kzalloc(sizeof(*br->br_wbr), GFP_NOFS); + if (br->br_wbr) { + err = au_wbr_init(br, sb, mod->perm); + if (unlikely(err)) { + au_kfree_rcu(br->br_wbr); + br->br_wbr = NULL; + } + } + } + if (unlikely(err)) + goto out_bf; + + if (au_br_fhsm(br->br_perm)) { + if (!au_br_fhsm(mod->perm)) { + /* fhsm --> non-fhsm */ + au_br_fhsm_fin(br->br_fhsm); + au_kfree_rcu(br->br_fhsm); + br->br_fhsm = NULL; + } + } else if (au_br_fhsm(mod->perm)) + /* non-fhsm --> fhsm */ + br->br_fhsm = bf; + + *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); + br->br_perm = mod->perm; + goto out; /* success */ + +out_bf: + au_kfree_try_rcu(bf); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs) +{ + int err; + struct kstatfs kstfs; + + err = vfs_statfs(&br->br_path, &kstfs); + if (!err) { + stfs->f_blocks = kstfs.f_blocks; + stfs->f_bavail = kstfs.f_bavail; + stfs->f_files = kstfs.f_files; + stfs->f_ffree = kstfs.f_ffree; + } + + return err; +} diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h new file mode 100644 index 000000000000..594c8bd674b2 --- /dev/null +++ b/fs/aufs/branch.h @@ -0,0 +1,366 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * branch filesystems and xino for them + */ + +#ifndef __AUFS_BRANCH_H__ +#define __AUFS_BRANCH_H__ + +#ifdef __KERNEL__ + +#include <linux/mount.h> +#include "dirren.h" +#include "dynop.h" +#include "lcnt.h" +#include "rwsem.h" +#include "super.h" + +/* ---------------------------------------------------------------------- */ + +/* a xino file */ +struct au_xino { + struct file **xi_file; + unsigned int xi_nfile; + + struct { + spinlock_t spin; + ino_t *array; + int total; + /* reserved for future use */ + /* unsigned long *bitmap; */ + wait_queue_head_t wqh; + } xi_nondir; + + struct mutex xi_mtx; /* protects xi_file array */ + struct hlist_bl_head xi_writing; + + atomic_t xi_truncating; + + struct kref xi_kref; +}; + +/* File-based Hierarchical Storage Management */ +struct au_br_fhsm { +#ifdef CONFIG_AUFS_FHSM + struct mutex bf_lock; + unsigned long bf_jiffy; + struct aufs_stfs bf_stfs; + int bf_readable; +#endif +}; + +/* members for writable branch only */ +enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last}; +struct au_wbr { + struct au_rwsem wbr_wh_rwsem; + struct dentry *wbr_wh[AuBrWh_Last]; + atomic_t wbr_wh_running; +#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */ +#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */ +#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */ + + /* mfs mode */ + unsigned long long wbr_bytes; +}; + +/* ext2 has 3 types of operations at least, ext3 has 4 */ +#define AuBrDynOp (AuDyLast * 4) + +#ifdef CONFIG_AUFS_HFSNOTIFY +/* support for asynchronous destruction */ +struct au_br_hfsnotify { + struct fsnotify_group *hfsn_group; +}; +#endif + +/* sysfs entries */ +struct au_brsysfs { + char name[16]; + struct attribute attr; +}; + +enum { + AuBrSysfs_BR, + AuBrSysfs_BRID, + AuBrSysfs_Last +}; + +/* protected by superblock rwsem */ +struct au_branch { + struct au_xino *br_xino; + + aufs_bindex_t br_id; + + int br_perm; + struct path br_path; + spinlock_t br_dykey_lock; + struct au_dykey *br_dykey[AuBrDynOp]; + au_lcnt_t br_nfiles; /* opened files */ + au_lcnt_t br_count; /* in-use for other */ + + struct au_wbr *br_wbr; + struct au_br_fhsm *br_fhsm; + +#ifdef CONFIG_AUFS_HFSNOTIFY + struct au_br_hfsnotify *br_hfsn; +#endif + +#ifdef CONFIG_SYSFS + /* entries under sysfs per mount-point */ + struct au_brsysfs br_sysfs[AuBrSysfs_Last]; +#endif + +#ifdef CONFIG_DEBUG_FS + struct dentry *br_dbgaufs; /* xino */ +#endif + + struct au_dr_br br_dirren; +}; + +/* ---------------------------------------------------------------------- */ + +static inline struct vfsmount *au_br_mnt(struct au_branch *br) +{ + return br->br_path.mnt; +} + +static inline struct dentry *au_br_dentry(struct au_branch *br) +{ + return br->br_path.dentry; +} + +static inline struct super_block *au_br_sb(struct au_branch *br) +{ + return au_br_mnt(br)->mnt_sb; +} + +static inline int au_br_rdonly(struct au_branch *br) +{ + return (sb_rdonly(au_br_sb(br)) + || !au_br_writable(br->br_perm)) + ? -EROFS : 0; +} + +static inline int au_br_hnotifyable(int brperm __maybe_unused) +{ +#ifdef CONFIG_AUFS_HNOTIFY + return !(brperm & AuBrPerm_RR); +#else + return 0; +#endif +} + +static inline int au_br_test_oflag(int oflag, struct au_branch *br) +{ + int err, exec_flag; + + err = 0; + exec_flag = oflag & __FMODE_EXEC; + if (unlikely(exec_flag && path_noexec(&br->br_path))) + err = -EACCES; + + return err; +} + +static inline void au_xino_get(struct au_branch *br) +{ + struct au_xino *xi; + + xi = br->br_xino; + if (xi) + kref_get(&xi->xi_kref); +} + +static inline int au_xino_count(struct au_branch *br) +{ + int v; + struct au_xino *xi; + + v = 0; + xi = br->br_xino; + if (xi) + v = kref_read(&xi->xi_kref); + + return v; +} + +/* ---------------------------------------------------------------------- */ + +/* branch.c */ +struct au_sbinfo; +void au_br_free(struct au_sbinfo *sinfo); +int au_br_index(struct super_block *sb, aufs_bindex_t br_id); +struct au_opt_add; +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount); +struct au_opt_del; +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount); +long au_ibusy_ioctl(struct file *file, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg); +#endif +struct au_opt_mod; +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh); +struct aufs_stfs; +int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs); + +/* xino.c */ +static const loff_t au_loff_max = LLONG_MAX; + +aufs_bindex_t au_xi_root(struct super_block *sb, struct dentry *dentry); +struct file *au_xino_create(struct super_block *sb, char *fpath, int silent, + int wbrtop); +struct file *au_xino_create2(struct super_block *sb, struct path *base, + struct file *copy_src); +struct au_xi_new { + struct au_xino *xi; /* switch between xino and xigen */ + int idx; + struct path *base; + struct file *copy_src; +}; +struct file *au_xi_new(struct super_block *sb, struct au_xi_new *xinew); + +int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t *ino); +int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t ino); +ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size, + loff_t *pos); +ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, + size_t size, loff_t *pos); + +int au_xib_trunc(struct super_block *sb); +int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin); + +struct au_xino *au_xino_alloc(unsigned int nfile); +int au_xino_put(struct au_branch *br); +struct file *au_xino_file1(struct au_xino *xi); + +struct au_opt_xino; +void au_xino_clr(struct super_block *sb); +int au_xino_set(struct super_block *sb, struct au_opt_xino *xiopt, int remount); +struct file *au_xino_def(struct super_block *sb); +int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t hino, + struct path *base); + +ino_t au_xino_new_ino(struct super_block *sb); +void au_xino_delete_inode(struct inode *inode, const int unlinked); + +void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, + ino_t h_ino, int idx); +int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + int *idx); + +int au_xino_path(struct seq_file *seq, struct file *file); + +/* ---------------------------------------------------------------------- */ + +/* @idx is signed to accept -1 meaning the first file */ +static inline struct file *au_xino_file(struct au_xino *xi, int idx) +{ + struct file *file; + + file = NULL; + if (!xi) + goto out; + + if (idx >= 0) { + if (idx < xi->xi_nfile) + file = xi->xi_file[idx]; + } else + file = au_xino_file1(xi); + +out: + return file; +} + +/* ---------------------------------------------------------------------- */ + +/* Superblock to branch */ +static inline +aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_id; +} + +static inline +struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_mnt(au_sbr(sb, bindex)); +} + +static inline +struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_sb(au_sbr(sb, bindex)); +} + +static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_perm; +} + +static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_whable(au_sbr_perm(sb, bindex)); +} + +/* ---------------------------------------------------------------------- */ + +#define wbr_wh_read_lock(wbr) au_rw_read_lock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_lock(wbr) au_rw_write_lock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_read_trylock(wbr) au_rw_read_trylock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_trylock(wbr) au_rw_write_trylock(&(wbr)->wbr_wh_rwsem) +/* +#define wbr_wh_read_trylock_nested(wbr) \ + au_rw_read_trylock_nested(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_trylock_nested(wbr) \ + au_rw_write_trylock_nested(&(wbr)->wbr_wh_rwsem) +*/ + +#define wbr_wh_read_unlock(wbr) au_rw_read_unlock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_unlock(wbr) au_rw_write_unlock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_downgrade_lock(wbr) au_rw_dgrade_lock(&(wbr)->wbr_wh_rwsem) + +#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&(wbr)->wbr_wh_rwsem) +#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&(wbr)->wbr_wh_rwsem) +#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&(wbr)->wbr_wh_rwsem) + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_FHSM +static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm) +{ + mutex_init(&brfhsm->bf_lock); + brfhsm->bf_jiffy = 0; + brfhsm->bf_readable = 0; +} + +static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm) +{ + mutex_destroy(&brfhsm->bf_lock); +} +#else +AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm) +AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm) +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_BRANCH_H__ */ diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk new file mode 100644 index 000000000000..12782f8e0f38 --- /dev/null +++ b/fs/aufs/conf.mk @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 + +AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} + +define AuConf +ifdef ${1} +AuConfStr += ${1}=${${1}} +endif +endef + +AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ + SBILIST \ + HNOTIFY HFSNOTIFY \ + EXPORT INO_T_64 \ + XATTR \ + FHSM \ + RDU \ + DIRREN \ + SHWH \ + BR_RAMFS \ + BR_FUSE POLL \ + BR_HFSPLUS \ + BDEV_LOOP \ + DEBUG MAGIC_SYSRQ +$(foreach i, ${AuConfAll}, \ + $(eval $(call AuConf,CONFIG_AUFS_${i}))) + +AuConfName = ${obj}/conf.str +${AuConfName}.tmp: FORCE + @echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@ +${AuConfName}: ${AuConfName}.tmp + @diff -q $< $@ > /dev/null 2>&1 || { \ + echo ' GEN ' $@; \ + cp -p $< $@; \ + } +FORCE: +clean-files += ${AuConfName} ${AuConfName}.tmp +${obj}/sysfs.o: ${AuConfName} + +-include ${srctree}/${src}/conf_priv.mk diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c new file mode 100644 index 000000000000..492442339b6c --- /dev/null +++ b/fs/aufs/cpup.c @@ -0,0 +1,1458 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * copy-up functions, see wbr_policy.c for copy-down + */ + +#include <linux/fs_stack.h> +#include <linux/mm.h> +#include <linux/task_work.h> +#include "aufs.h" + +void au_cpup_attr_flags(struct inode *dst, unsigned int iflags) +{ + const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE + | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT; + + BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags)); + + dst->i_flags |= iflags & ~mask; + if (au_test_fs_notime(dst->i_sb)) + dst->i_flags |= S_NOATIME | S_NOCMTIME; +} + +void au_cpup_attr_timesizes(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + fsstack_copy_attr_times(inode, h_inode); + fsstack_copy_inode_size(inode, h_inode); +} + +void au_cpup_attr_nlink(struct inode *inode, int force) +{ + struct inode *h_inode; + struct super_block *sb; + aufs_bindex_t bindex, bbot; + + sb = inode->i_sb; + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (!force + && !S_ISDIR(h_inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode)) + return; + + /* + * 0 can happen in revalidating. + * h_inode->i_mutex may not be held here, but it is harmless since once + * i_nlink reaches 0, it will never become positive except O_TMPFILE + * case. + * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause + * the incorrect link count. + */ + set_nlink(inode, h_inode->i_nlink); + + /* + * fewer nlink makes find(1) noisy, but larger nlink doesn't. + * it may includes whplink directory. + */ + if (S_ISDIR(h_inode->i_mode)) { + bbot = au_ibbot(inode); + for (bindex++; bindex <= bbot; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) + au_add_nlink(inode, h_inode); + } + } +} + +void au_cpup_attr_changeable(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + inode->i_mode = h_inode->i_mode; + inode->i_uid = h_inode->i_uid; + inode->i_gid = h_inode->i_gid; + au_cpup_attr_timesizes(inode); + au_cpup_attr_flags(inode, h_inode->i_flags); +} + +void au_cpup_igen(struct inode *inode, struct inode *h_inode) +{ + struct au_iinfo *iinfo = au_ii(inode); + + IiMustWriteLock(inode); + + iinfo->ii_higen = h_inode->i_generation; + iinfo->ii_hsb1 = h_inode->i_sb; +} + +void au_cpup_attr_all(struct inode *inode, int force) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + au_cpup_attr_changeable(inode); + if (inode->i_nlink > 0) + au_cpup_attr_nlink(inode, force); + inode->i_rdev = h_inode->i_rdev; + inode->i_blkbits = h_inode->i_blkbits; + au_cpup_igen(inode, h_inode); +} + +/* ---------------------------------------------------------------------- */ + +/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ + +/* keep the timestamps of the parent dir when cpup */ +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path) +{ + struct inode *h_inode; + + dt->dt_dentry = dentry; + dt->dt_h_path = *h_path; + h_inode = d_inode(h_path->dentry); + dt->dt_atime = h_inode->i_atime; + dt->dt_mtime = h_inode->i_mtime; + /* smp_mb(); */ +} + +void au_dtime_revert(struct au_dtime *dt) +{ + struct iattr attr; + int err; + + attr.ia_atime = dt->dt_atime; + attr.ia_mtime = dt->dt_mtime; + attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET + | ATTR_ATIME | ATTR_ATIME_SET; + + /* no delegation since this is a directory */ + err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL); + if (unlikely(err)) + pr_warn("restoring timestamps failed(%d). ignored\n", err); +} + +/* ---------------------------------------------------------------------- */ + +/* internal use only */ +struct au_cpup_reg_attr { + int valid; + struct kstat st; + unsigned int iflags; /* inode->i_flags */ +}; + +static noinline_for_stack +int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src, + struct au_cpup_reg_attr *h_src_attr) +{ + int err, sbits, icex; + unsigned int mnt_flags; + unsigned char verbose; + struct iattr ia; + struct path h_path; + struct inode *h_isrc, *h_idst; + struct kstat *h_st; + struct au_branch *br; + + h_path.dentry = au_h_dptr(dst, bindex); + h_idst = d_inode(h_path.dentry); + br = au_sbr(dst->d_sb, bindex); + h_path.mnt = au_br_mnt(br); + h_isrc = d_inode(h_src); + ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID + | ATTR_ATIME | ATTR_MTIME + | ATTR_ATIME_SET | ATTR_MTIME_SET; + if (h_src_attr && h_src_attr->valid) { + h_st = &h_src_attr->st; + ia.ia_uid = h_st->uid; + ia.ia_gid = h_st->gid; + ia.ia_atime = h_st->atime; + ia.ia_mtime = h_st->mtime; + if (h_idst->i_mode != h_st->mode + && !S_ISLNK(h_idst->i_mode)) { + ia.ia_valid |= ATTR_MODE; + ia.ia_mode = h_st->mode; + } + sbits = !!(h_st->mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_idst, h_src_attr->iflags); + } else { + ia.ia_uid = h_isrc->i_uid; + ia.ia_gid = h_isrc->i_gid; + ia.ia_atime = h_isrc->i_atime; + ia.ia_mtime = h_isrc->i_mtime; + if (h_idst->i_mode != h_isrc->i_mode + && !S_ISLNK(h_idst->i_mode)) { + ia.ia_valid |= ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + } + sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_idst, h_isrc->i_flags); + } + /* no delegation since it is just created */ + err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); + + /* is this nfs only? */ + if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) { + ia.ia_valid = ATTR_FORCE | ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); + } + + icex = br->br_perm & AuBrAttr_ICEX; + if (!err) { + mnt_flags = au_mntflags(dst->d_sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, + char *buf, unsigned long blksize) +{ + int err; + size_t sz, rbytes, wbytes; + unsigned char all_zero; + char *p, *zp; + struct inode *h_inode; + /* reduce stack usage */ + struct iattr *ia; + + zp = page_address(ZERO_PAGE(0)); + if (unlikely(!zp)) + return -ENOMEM; /* possible? */ + + err = 0; + all_zero = 0; + while (len) { + AuDbg("len %lld\n", len); + sz = blksize; + if (len < blksize) + sz = len; + + rbytes = 0; + /* todo: signal_pending? */ + while (!rbytes || err == -EAGAIN || err == -EINTR) { + rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); + err = rbytes; + } + if (unlikely(err < 0)) + break; + + all_zero = 0; + if (len >= rbytes && rbytes == blksize) + all_zero = !memcmp(buf, zp, rbytes); + if (!all_zero) { + wbytes = rbytes; + p = buf; + while (wbytes) { + size_t b; + + b = vfsub_write_k(dst, p, wbytes, &dst->f_pos); + err = b; + /* todo: signal_pending? */ + if (unlikely(err == -EAGAIN || err == -EINTR)) + continue; + if (unlikely(err < 0)) + break; + wbytes -= b; + p += b; + } + if (unlikely(err < 0)) + break; + } else { + loff_t res; + + AuLabel(hole); + res = vfsub_llseek(dst, rbytes, SEEK_CUR); + err = res; + if (unlikely(res < 0)) + break; + } + len -= rbytes; + err = 0; + } + + /* the last block may be a hole */ + if (!err && all_zero) { + AuLabel(last hole); + + err = 1; + if (au_test_nfs(dst->f_path.dentry->d_sb)) { + /* nfs requires this step to make last hole */ + /* is this only nfs? */ + do { + /* todo: signal_pending? */ + err = vfsub_write_k(dst, "\0", 1, &dst->f_pos); + } while (err == -EAGAIN || err == -EINTR); + if (err == 1) + dst->f_pos--; + } + + if (err == 1) { + ia = (void *)buf; + ia->ia_size = dst->f_pos; + ia->ia_valid = ATTR_SIZE | ATTR_FILE; + ia->ia_file = dst; + h_inode = file_inode(dst); + inode_lock_nested(h_inode, AuLsc_I_CHILD2); + /* no delegation since it is just created */ + err = vfsub_notify_change(&dst->f_path, ia, + /*delegated*/NULL); + inode_unlock(h_inode); + } + } + + return err; +} + +int au_copy_file(struct file *dst, struct file *src, loff_t len) +{ + int err; + unsigned long blksize; + unsigned char do_kfree; + char *buf; + struct super_block *h_sb; + + err = -ENOMEM; + h_sb = file_inode(dst)->i_sb; + blksize = h_sb->s_blocksize; + if (!blksize || PAGE_SIZE < blksize) + blksize = PAGE_SIZE; + AuDbg("blksize %lu\n", blksize); + do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *)); + if (do_kfree) + buf = kmalloc(blksize, GFP_NOFS); + else + buf = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!buf)) + goto out; + + if (len > (1 << 22)) + AuDbg("copying a large file %lld\n", (long long)len); + + src->f_pos = 0; + dst->f_pos = 0; + err = au_do_copy_file(dst, src, len, buf, blksize); + if (do_kfree) { + AuDebugOn(!au_kfree_do_sz_test(blksize)); + au_kfree_do_rcu(buf); + } else + free_page((unsigned long)buf); + +out: + return err; +} + +static int au_do_copy(struct file *dst, struct file *src, loff_t len) +{ + int err; + struct super_block *h_src_sb; + struct inode *h_src_inode; + + h_src_inode = file_inode(src); + h_src_sb = h_src_inode->i_sb; + + /* XFS acquires inode_lock */ + if (!au_test_xfs(h_src_sb)) + err = au_copy_file(dst, src, len); + else { + inode_unlock_shared(h_src_inode); + err = au_copy_file(dst, src, len); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } + + return err; +} + +static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len) +{ + int err; + loff_t lo; + struct super_block *h_src_sb; + struct inode *h_src_inode; + + h_src_inode = file_inode(src); + h_src_sb = h_src_inode->i_sb; + if (h_src_sb != file_inode(dst)->i_sb + || !dst->f_op->remap_file_range) { + err = au_do_copy(dst, src, len); + goto out; + } + + if (!au_test_nfs(h_src_sb)) { + inode_unlock_shared(h_src_inode); + lo = vfsub_clone_file_range(src, dst, len); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } else + lo = vfsub_clone_file_range(src, dst, len); + if (lo == len) { + err = 0; + goto out; /* success */ + } else if (lo >= 0) + /* todo: possible? */ + /* paritially succeeded */ + AuDbg("lo %lld, len %lld. Retrying.\n", lo, len); + else if (lo != -EOPNOTSUPP) { + /* older XFS has a condition in cloning */ + err = lo; + goto out; + } + + /* the backend fs on NFS may not support cloning */ + err = au_do_copy(dst, src, len); + +out: + AuTraceErr(err); + return err; +} + +/* + * to support a sparse file which is opened with O_APPEND, + * we need to close the file. + */ +static int au_cp_regular(struct au_cp_generic *cpg) +{ + int err, i; + enum { SRC, DST }; + struct { + aufs_bindex_t bindex; + unsigned int flags; + struct dentry *dentry; + int force_wr; + struct file *file; + } *f, file[] = { + { + .bindex = cpg->bsrc, + .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, + }, + { + .bindex = cpg->bdst, + .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, + .force_wr = !!au_ftest_cpup(cpg->flags, RWDST), + } + }; + struct au_branch *br; + struct super_block *sb, *h_src_sb; + struct inode *h_src_inode; + struct task_struct *tsk = current; + + /* bsrc branch can be ro/rw. */ + sb = cpg->dentry->d_sb; + f = file; + for (i = 0; i < 2; i++, f++) { + f->dentry = au_h_dptr(cpg->dentry, f->bindex); + f->file = au_h_open(cpg->dentry, f->bindex, f->flags, + /*file*/NULL, f->force_wr); + if (IS_ERR(f->file)) { + err = PTR_ERR(f->file); + if (i == SRC) + goto out; + else + goto out_src; + } + } + + /* try stopping to update while we copyup */ + h_src_inode = d_inode(file[SRC].dentry); + h_src_sb = h_src_inode->i_sb; + if (!au_test_nfs(h_src_sb)) + IMustLock(h_src_inode); + err = au_clone_or_copy(file[DST].file, file[SRC].file, cpg->len); + + /* i wonder if we had O_NO_DELAY_FPUT flag */ + if (tsk->flags & PF_KTHREAD) + __fput_sync(file[DST].file); + else { + /* it happened actually */ + fput(file[DST].file); + /* + * too bad. + * we have to call both since we don't know which place the file + * was added to. + */ + task_work_run(); + flush_delayed_fput(); + } + br = au_sbr(sb, file[DST].bindex); + au_lcnt_dec(&br->br_nfiles); + +out_src: + fput(file[SRC].file); + br = au_sbr(sb, file[SRC].bindex); + au_lcnt_dec(&br->br_nfiles); +out: + return err; +} + +static int au_do_cpup_regular(struct au_cp_generic *cpg, + struct au_cpup_reg_attr *h_src_attr) +{ + int err, rerr; + loff_t l; + struct path h_path; + struct inode *h_src_inode, *h_dst_inode; + + err = 0; + h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc); + l = i_size_read(h_src_inode); + if (cpg->len == -1 || l < cpg->len) + cpg->len = l; + if (cpg->len) { + /* try stopping to update while we are referencing */ + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + au_pin_hdir_unlock(cpg->pin); + + h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc); + h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc); + h_src_attr->iflags = h_src_inode->i_flags; + if (!au_test_nfs(h_src_inode->i_sb)) + err = vfsub_getattr(&h_path, &h_src_attr->st); + else { + inode_unlock_shared(h_src_inode); + err = vfsub_getattr(&h_path, &h_src_attr->st); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } + if (unlikely(err)) { + inode_unlock_shared(h_src_inode); + goto out; + } + h_src_attr->valid = 1; + if (!au_test_nfs(h_src_inode->i_sb)) { + err = au_cp_regular(cpg); + inode_unlock_shared(h_src_inode); + } else { + inode_unlock_shared(h_src_inode); + err = au_cp_regular(cpg); + } + rerr = au_pin_hdir_relock(cpg->pin); + if (!err && rerr) + err = rerr; + } + if (!err && (h_src_inode->i_state & I_LINKABLE)) { + h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst); + h_dst_inode = d_inode(h_path.dentry); + spin_lock(&h_dst_inode->i_lock); + h_dst_inode->i_state |= I_LINKABLE; + spin_unlock(&h_dst_inode->i_lock); + } + +out: + return err; +} + +static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, + struct inode *h_dir) +{ + int err, symlen; + mm_segment_t old_fs; + union { + char *k; + char __user *u; + } sym; + + err = -ENOMEM; + sym.k = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!sym.k)) + goto out; + + /* unnecessary to support mmap_sem since symlink is not mmap-able */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + symlen = vfs_readlink(h_src, sym.u, PATH_MAX); + err = symlen; + set_fs(old_fs); + + if (symlen > 0) { + sym.k[symlen] = 0; + err = vfsub_symlink(h_dir, h_path, sym.k); + } + free_page((unsigned long)sym.k); + +out: + return err; +} + +/* + * regardless 'acl' option, reset all ACL. + * All ACL will be copied up later from the original entry on the lower branch. + */ +static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) +{ + int err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = h_path->dentry; + h_inode = d_inode(h_dentry); + /* forget_all_cached_acls(h_inode)); */ + err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); + AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; + if (!err) + err = vfsub_acl_chmod(h_inode, mode); + + AuTraceErr(err); + return err; +} + +static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent, + struct inode *h_dir, struct path *h_path) +{ + int err; + struct inode *dir, *inode; + + err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); + AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; + if (unlikely(err)) + goto out; + + /* + * strange behaviour from the users view, + * particularly setattr case + */ + dir = d_inode(dst_parent); + if (au_ibtop(dir) == cpg->bdst) + au_cpup_attr_nlink(dir, /*force*/1); + inode = d_inode(cpg->dentry); + au_cpup_attr_nlink(inode, /*force*/1); + +out: + return err; +} + +static noinline_for_stack +int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, + struct au_cpup_reg_attr *h_src_attr) +{ + int err; + umode_t mode; + unsigned int mnt_flags; + unsigned char isdir, isreg, force; + const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME); + struct au_dtime dt; + struct path h_path; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *h_inode, *h_dir; + struct super_block *sb; + + /* bsrc branch can be ro/rw. */ + h_src = au_h_dptr(cpg->dentry, cpg->bsrc); + h_inode = d_inode(h_src); + AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc)); + + /* try stopping to be referenced while we are creating */ + h_dst = au_h_dptr(cpg->dentry, cpg->bdst); + if (au_ftest_cpup(cpg->flags, RENAME)) + AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX, + AUFS_WH_PFX_LEN)); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + AuDebugOn(h_parent != h_dst->d_parent); + + sb = cpg->dentry->d_sb; + h_path.mnt = au_sbr_mnt(sb, cpg->bdst); + if (do_dt) { + h_path.dentry = h_parent; + au_dtime_store(&dt, dst_parent, &h_path); + } + h_path.dentry = h_dst; + + isreg = 0; + isdir = 0; + mode = h_inode->i_mode; + switch (mode & S_IFMT) { + case S_IFREG: + isreg = 1; + err = vfsub_create(h_dir, &h_path, 0600, /*want_excl*/true); + if (!err) + err = au_do_cpup_regular(cpg, h_src_attr); + break; + case S_IFDIR: + isdir = 1; + err = vfsub_mkdir(h_dir, &h_path, mode); + if (!err) + err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path); + break; + case S_IFLNK: + err = au_do_cpup_symlink(&h_path, h_src, h_dir); + break; + case S_IFCHR: + case S_IFBLK: + AuDebugOn(!capable(CAP_MKNOD)); + /*FALLTHROUGH*/ + case S_IFIFO: + case S_IFSOCK: + err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev); + break; + default: + AuIOErr("Unknown inode type 0%o\n", mode); + err = -EIO; + } + if (!err) + err = au_reset_acl(h_dir, &h_path, mode); + + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, UDBA_NONE) + && !isdir + && au_opt_test(mnt_flags, XINO) + && (h_inode->i_nlink == 1 + || (h_inode->i_state & I_LINKABLE)) + /* todo: unnecessary? */ + /* && d_inode(cpg->dentry)->i_nlink == 1 */ + && cpg->bdst < cpg->bsrc + && !au_ftest_cpup(cpg->flags, KEEPLINO)) + au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0); + /* ignore this error */ + + if (!err) { + force = 0; + if (isreg) { + force = !!cpg->len; + if (cpg->len == -1) + force = !!i_size_read(h_inode); + } + au_fhsm_wrote(sb, cpg->bdst, force); + } + + if (do_dt) + au_dtime_revert(&dt); + return err; +} + +static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path) +{ + int err; + struct dentry *dentry, *h_dentry, *h_parent, *parent; + struct inode *h_dir; + aufs_bindex_t bdst; + + dentry = cpg->dentry; + bdst = cpg->bdst; + h_dentry = au_h_dptr(dentry, bdst); + if (!au_ftest_cpup(cpg->flags, OVERWRITE)) { + dget(h_dentry); + au_set_h_dptr(dentry, bdst, NULL); + err = au_lkup_neg(dentry, bdst, /*wh*/0); + if (!err) + h_path->dentry = dget(au_h_dptr(dentry, bdst)); + au_set_h_dptr(dentry, bdst, h_dentry); + } else { + err = 0; + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + dput(parent); + h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent); + if (IS_ERR(h_path->dentry)) + err = PTR_ERR(h_path->dentry); + } + if (unlikely(err)) + goto out; + + h_parent = h_dentry->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + AuDbg("%pd %pd\n", h_dentry, h_path->dentry); + /* no delegation since it is just created */ + err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL, + /*flags*/0); + dput(h_path->dentry); + +out: + return err; +} + +/* + * copyup the @dentry from @bsrc to @bdst. + * the caller must set the both of lower dentries. + * @len is for truncating when it is -1 copyup the entire file. + * in link/rename cases, @dst_parent may be different from the real one. + * basic->bsrc can be larger than basic->bdst. + * aufs doesn't touch the credential so + * security_inode_copy_up{,_xattr}() are unnecessary. + */ +static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ + int err, rerr; + aufs_bindex_t old_ibtop; + unsigned char isdir, plink; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode; + struct super_block *sb; + struct au_branch *br; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct path h_path; + struct au_cpup_reg_attr h_src_attr; + } *a; + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + a->h_src_attr.valid = 0; + + sb = cpg->dentry->d_sb; + br = au_sbr(sb, cpg->bdst); + a->h_path.mnt = au_br_mnt(br); + h_dst = au_h_dptr(cpg->dentry, cpg->bdst); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + + h_src = au_h_dptr(cpg->dentry, cpg->bsrc); + inode = d_inode(cpg->dentry); + + if (!dst_parent) + dst_parent = dget_parent(cpg->dentry); + else + dget(dst_parent); + + plink = !!au_opt_test(au_mntflags(sb), PLINK); + dst_inode = au_h_iptr(inode, cpg->bdst); + if (dst_inode) { + if (unlikely(!plink)) { + err = -EIO; + AuIOErr("hi%lu(i%lu) exists on b%d " + "but plink is disabled\n", + dst_inode->i_ino, inode->i_ino, cpg->bdst); + goto out_parent; + } + + if (dst_inode->i_nlink) { + const int do_dt = au_ftest_cpup(cpg->flags, DTIME); + + h_src = au_plink_lkup(inode, cpg->bdst); + err = PTR_ERR(h_src); + if (IS_ERR(h_src)) + goto out_parent; + if (unlikely(d_is_negative(h_src))) { + err = -EIO; + AuIOErr("i%lu exists on b%d " + "but not pseudo-linked\n", + inode->i_ino, cpg->bdst); + dput(h_src); + goto out_parent; + } + + if (do_dt) { + a->h_path.dentry = h_parent; + au_dtime_store(&a->dt, dst_parent, &a->h_path); + } + + a->h_path.dentry = h_dst; + delegated = NULL; + err = vfsub_link(h_src, h_dir, &a->h_path, &delegated); + if (!err && au_ftest_cpup(cpg->flags, RENAME)) + err = au_do_ren_after_cpup(cpg, &a->h_path); + if (do_dt) + au_dtime_revert(&a->dt); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + dput(h_src); + goto out_parent; + } else + /* todo: cpup_wh_file? */ + /* udba work */ + au_update_ibrange(inode, /*do_put_zero*/1); + } + + isdir = S_ISDIR(inode->i_mode); + old_ibtop = au_ibtop(inode); + err = cpup_entry(cpg, dst_parent, &a->h_src_attr); + if (unlikely(err)) + goto out_rev; + dst_inode = d_inode(h_dst); + inode_lock_nested(dst_inode, AuLsc_I_CHILD2); + /* todo: necessary? */ + /* au_pin_hdir_unlock(cpg->pin); */ + + err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr); + if (unlikely(err)) { + /* todo: necessary? */ + /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */ + inode_unlock(dst_inode); + goto out_rev; + } + + if (cpg->bdst < old_ibtop) { + if (S_ISREG(inode->i_mode)) { + err = au_dy_iaop(inode, cpg->bdst, dst_inode); + if (unlikely(err)) { + /* ignore an error */ + /* au_pin_hdir_relock(cpg->pin); */ + inode_unlock(dst_inode); + goto out_rev; + } + } + au_set_ibtop(inode, cpg->bdst); + } else + au_set_ibbot(inode, cpg->bdst); + au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode), + au_hi_flags(inode, isdir)); + + /* todo: necessary? */ + /* err = au_pin_hdir_relock(cpg->pin); */ + inode_unlock(dst_inode); + if (unlikely(err)) + goto out_rev; + + src_inode = d_inode(h_src); + if (!isdir + && (src_inode->i_nlink > 1 + || src_inode->i_state & I_LINKABLE) + && plink) + au_plink_append(inode, cpg->bdst, h_dst); + + if (au_ftest_cpup(cpg->flags, RENAME)) { + a->h_path.dentry = h_dst; + err = au_do_ren_after_cpup(cpg, &a->h_path); + } + if (!err) + goto out_parent; /* success */ + + /* revert */ +out_rev: + a->h_path.dentry = h_parent; + au_dtime_store(&a->dt, dst_parent, &a->h_path); + a->h_path.dentry = h_dst; + rerr = 0; + if (d_is_positive(h_dst)) { + if (!isdir) { + /* no delegation since it is just created */ + rerr = vfsub_unlink(h_dir, &a->h_path, + /*delegated*/NULL, /*force*/0); + } else + rerr = vfsub_rmdir(h_dir, &a->h_path); + } + au_dtime_revert(&a->dt); + if (rerr) { + AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr); + err = -EIO; + } +out_parent: + dput(dst_parent); + au_kfree_rcu(a); +out: + return err; +} + +#if 0 /* reserved */ +struct au_cpup_single_args { + int *errp; + struct au_cp_generic *cpg; + struct dentry *dst_parent; +}; + +static void au_call_cpup_single(void *args) +{ + struct au_cpup_single_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_single(a->cpg, a->dst_parent); + au_pin_hdir_release(a->cpg->pin); +} +#endif + +/* + * prevent SIGXFSZ in copy-up. + * testing CAP_MKNOD is for generic fs, + * but CAP_FSETID is for xfs only, currently. + */ +static int au_cpup_sio_test(struct au_pin *pin, umode_t mode) +{ + int do_sio; + struct super_block *sb; + struct inode *h_dir; + + do_sio = 0; + sb = au_pinned_parent(pin)->d_sb; + if (!au_wkq_test() + && (!au_sbi(sb)->si_plink_maint_pid + || au_plink_maint(sb, AuLock_NOPLM))) { + switch (mode & S_IFMT) { + case S_IFREG: + /* no condition about RLIMIT_FSIZE and the file size */ + do_sio = 1; + break; + case S_IFCHR: + case S_IFBLK: + do_sio = !capable(CAP_MKNOD); + break; + } + if (!do_sio) + do_sio = ((mode & (S_ISUID | S_ISGID)) + && !capable(CAP_FSETID)); + /* this workaround may be removed in the future */ + if (!do_sio) { + h_dir = au_pinned_h_dir(pin); + do_sio = h_dir->i_mode & S_ISVTX; + } + } + + return do_sio; +} + +#if 0 /* reserved */ +int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ + int err, wkq_err; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc); + if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode)) + err = au_cpup_single(cpg, dst_parent); + else { + struct au_cpup_single_args args = { + .errp = &err, + .cpg = cpg, + .dst_parent = dst_parent + }; + wkq_err = au_wkq_wait(au_call_cpup_single, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} +#endif + +/* + * copyup the @dentry from the first active lower branch to @bdst, + * using au_cpup_single(). + */ +static int au_cpup_simple(struct au_cp_generic *cpg) +{ + int err; + unsigned int flags_orig; + struct dentry *dentry; + + AuDebugOn(cpg->bsrc < 0); + + dentry = cpg->dentry; + DiMustWriteLock(dentry); + + err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1); + if (!err) { + flags_orig = cpg->flags; + au_fset_cpup(cpg->flags, RENAME); + err = au_cpup_single(cpg, NULL); + cpg->flags = flags_orig; + if (!err) + return 0; /* success */ + + /* revert */ + au_set_h_dptr(dentry, cpg->bdst, NULL); + au_set_dbtop(dentry, cpg->bsrc); + } + + return err; +} + +struct au_cpup_simple_args { + int *errp; + struct au_cp_generic *cpg; +}; + +static void au_call_cpup_simple(void *args) +{ + struct au_cpup_simple_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_simple(a->cpg); + au_pin_hdir_release(a->cpg->pin); +} + +static int au_do_sio_cpup_simple(struct au_cp_generic *cpg) +{ + int err, wkq_err; + struct dentry *dentry, *parent; + struct file *h_file; + struct inode *h_dir; + + dentry = cpg->dentry; + h_file = NULL; + if (au_ftest_cpup(cpg->flags, HOPEN)) { + AuDebugOn(cpg->bsrc < 0); + h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + } + + parent = dget_parent(dentry); + h_dir = au_h_iptr(d_inode(parent), cpg->bdst); + if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) + err = au_cpup_simple(cpg); + else { + struct au_cpup_simple_args args = { + .errp = &err, + .cpg = cpg + }; + wkq_err = au_wkq_wait(au_call_cpup_simple, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + dput(parent); + if (h_file) + au_h_open_post(dentry, cpg->bsrc, h_file); + +out: + return err; +} + +int au_sio_cpup_simple(struct au_cp_generic *cpg) +{ + aufs_bindex_t bsrc, bbot; + struct dentry *dentry, *h_dentry; + + if (cpg->bsrc < 0) { + dentry = cpg->dentry; + bbot = au_dbbot(dentry); + for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) { + h_dentry = au_h_dptr(dentry, bsrc); + if (h_dentry) { + AuDebugOn(d_is_negative(h_dentry)); + break; + } + } + AuDebugOn(bsrc > bbot); + cpg->bsrc = bsrc; + } + AuDebugOn(cpg->bsrc <= cpg->bdst); + return au_do_sio_cpup_simple(cpg); +} + +int au_sio_cpdown_simple(struct au_cp_generic *cpg) +{ + AuDebugOn(cpg->bdst <= cpg->bsrc); + return au_do_sio_cpup_simple(cpg); +} + +/* ---------------------------------------------------------------------- */ + +/* + * copyup the deleted file for writing. + */ +static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry, + struct file *file) +{ + int err; + unsigned int flags_orig; + aufs_bindex_t bsrc_orig; + struct au_dinfo *dinfo; + struct { + struct au_hdentry *hd; + struct dentry *h_dentry; + } hdst, hsrc; + + dinfo = au_di(cpg->dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + bsrc_orig = cpg->bsrc; + cpg->bsrc = dinfo->di_btop; + hdst.hd = au_hdentry(dinfo, cpg->bdst); + hdst.h_dentry = hdst.hd->hd_dentry; + hdst.hd->hd_dentry = wh_dentry; + dinfo->di_btop = cpg->bdst; + + hsrc.h_dentry = NULL; + if (file) { + hsrc.hd = au_hdentry(dinfo, cpg->bsrc); + hsrc.h_dentry = hsrc.hd->hd_dentry; + hsrc.hd->hd_dentry = au_hf_top(file)->f_path.dentry; + } + flags_orig = cpg->flags; + cpg->flags = !AuCpup_DTIME; + err = au_cpup_single(cpg, /*h_parent*/NULL); + cpg->flags = flags_orig; + if (file) { + if (!err) + err = au_reopen_nondir(file); + hsrc.hd->hd_dentry = hsrc.h_dentry; + } + hdst.hd->hd_dentry = hdst.h_dentry; + dinfo->di_btop = cpg->bsrc; + cpg->bsrc = bsrc_orig; + + return err; +} + +static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ + int err; + aufs_bindex_t bdst; + struct au_dtime dt; + struct dentry *dentry, *parent, *h_parent, *wh_dentry; + struct au_branch *br; + struct path h_path; + + dentry = cpg->dentry; + bdst = cpg->bdst; + br = au_sbr(dentry->d_sb, bdst); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out; + + h_path.dentry = h_parent; + h_path.mnt = au_br_mnt(br); + au_dtime_store(&dt, parent, &h_path); + err = au_do_cpup_wh(cpg, wh_dentry, file); + if (unlikely(err)) + goto out_wh; + + dget(wh_dentry); + h_path.dentry = wh_dentry; + if (!d_is_dir(wh_dentry)) { + /* no delegation since it is just created */ + err = vfsub_unlink(d_inode(h_parent), &h_path, + /*delegated*/NULL, /*force*/0); + } else + err = vfsub_rmdir(d_inode(h_parent), &h_path); + if (unlikely(err)) { + AuIOErr("failed remove copied-up tmp file %pd(%d)\n", + wh_dentry, err); + err = -EIO; + } + au_dtime_revert(&dt); + au_set_hi_wh(d_inode(dentry), bdst, wh_dentry); + +out_wh: + dput(wh_dentry); +out: + dput(parent); + return err; +} + +struct au_cpup_wh_args { + int *errp; + struct au_cp_generic *cpg; + struct file *file; +}; + +static void au_call_cpup_wh(void *args) +{ + struct au_cpup_wh_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_wh(a->cpg, a->file); + au_pin_hdir_release(a->cpg->pin); +} + +int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ + int err, wkq_err; + aufs_bindex_t bdst; + struct dentry *dentry, *parent, *h_orph, *h_parent; + struct inode *dir, *h_dir, *h_tmpdir; + struct au_wbr *wbr; + struct au_pin wh_pin, *pin_orig; + + dentry = cpg->dentry; + bdst = cpg->bdst; + parent = dget_parent(dentry); + dir = d_inode(parent); + h_orph = NULL; + h_parent = NULL; + h_dir = au_igrab(au_h_iptr(dir, bdst)); + h_tmpdir = h_dir; + pin_orig = NULL; + if (!h_dir->i_nlink) { + wbr = au_sbr(dentry->d_sb, bdst)->br_wbr; + h_orph = wbr->wbr_orph; + + h_parent = dget(au_h_dptr(parent, bdst)); + au_set_h_dptr(parent, bdst, dget(h_orph)); + h_tmpdir = d_inode(h_orph); + au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); + + inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3); + /* todo: au_h_open_pre()? */ + + pin_orig = cpg->pin; + au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT, + AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED); + cpg->pin = &wh_pin; + } + + if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) + err = au_cpup_wh(cpg, file); + else { + struct au_cpup_wh_args args = { + .errp = &err, + .cpg = cpg, + .file = file + }; + wkq_err = au_wkq_wait(au_call_cpup_wh, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + if (h_orph) { + inode_unlock(h_tmpdir); + /* todo: au_h_open_post()? */ + au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); + au_set_h_dptr(parent, bdst, h_parent); + AuDebugOn(!pin_orig); + cpg->pin = pin_orig; + } + iput(h_dir); + dput(parent); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * generic routine for both of copy-up and copy-down. + */ +/* cf. revalidate function in file.c */ +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent, void *arg), + void *arg) +{ + int err; + struct au_pin pin; + struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry; + + err = 0; + parent = dget_parent(dentry); + if (IS_ROOT(parent)) + goto out; + + au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, + au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); + + /* do not use au_dpage */ + real_parent = parent; + while (1) { + dput(parent); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + if (h_parent) + goto out; /* success */ + + /* find top dir which is necessary to cpup */ + do { + d = parent; + dput(parent); + parent = dget_parent(d); + di_read_lock_parent3(parent, !AuLock_IR); + h_parent = au_h_dptr(parent, bdst); + di_read_unlock(parent, !AuLock_IR); + } while (!h_parent); + + if (d != real_parent) + di_write_lock_child3(d); + + /* somebody else might create while we were sleeping */ + h_dentry = au_h_dptr(d, bdst); + if (!h_dentry || d_is_negative(h_dentry)) { + if (h_dentry) + au_update_dbtop(d); + + au_pin_set_dentry(&pin, d); + err = au_do_pin(&pin); + if (!err) { + err = cp(d, bdst, &pin, h_parent, arg); + au_unpin(&pin); + } + } + + if (d != real_parent) + di_write_unlock(d); + if (unlikely(err)) + break; + } + +out: + dput(parent); + return err; +} + +static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent __maybe_unused, + void *arg __maybe_unused) +{ + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = bdst, + .bsrc = -1, + .len = 0, + .pin = pin, + .flags = AuCpup_DTIME + }; + return au_sio_cpup_simple(&cpg); +} + +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); +} + +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + int err; + struct dentry *parent; + struct inode *dir; + + parent = dget_parent(dentry); + dir = d_inode(parent); + err = 0; + if (au_h_iptr(dir, bdst)) + goto out; + + di_read_unlock(parent, AuLock_IR); + di_write_lock_parent(parent); + /* someone else might change our inode while we were sleeping */ + if (!au_h_iptr(dir, bdst)) + err = au_cpup_dirs(dentry, bdst); + di_downgrade_lock(parent, AuLock_IR); + +out: + dput(parent); + return err; +} diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h new file mode 100644 index 000000000000..d02f8150fa05 --- /dev/null +++ b/fs/aufs/cpup.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * copy-up/down functions + */ + +#ifndef __AUFS_CPUP_H__ +#define __AUFS_CPUP_H__ + +#ifdef __KERNEL__ + +#include <linux/path.h> + +struct inode; +struct file; +struct au_pin; + +void au_cpup_attr_flags(struct inode *dst, unsigned int iflags); +void au_cpup_attr_timesizes(struct inode *inode); +void au_cpup_attr_nlink(struct inode *inode, int force); +void au_cpup_attr_changeable(struct inode *inode); +void au_cpup_igen(struct inode *inode, struct inode *h_inode); +void au_cpup_attr_all(struct inode *inode, int force); + +/* ---------------------------------------------------------------------- */ + +struct au_cp_generic { + struct dentry *dentry; + aufs_bindex_t bdst, bsrc; + loff_t len; + struct au_pin *pin; + unsigned int flags; +}; + +/* cpup flags */ +#define AuCpup_DTIME 1 /* do dtime_store/revert */ +#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino, + for link(2) */ +#define AuCpup_RENAME (1 << 2) /* rename after cpup */ +#define AuCpup_HOPEN (1 << 3) /* call h_open_pre/post() in + cpup */ +#define AuCpup_OVERWRITE (1 << 4) /* allow overwriting the + existing entry */ +#define AuCpup_RWDST (1 << 5) /* force write target even if + the branch is marked as RO */ + +#ifndef CONFIG_AUFS_BR_HFSPLUS +#undef AuCpup_HOPEN +#define AuCpup_HOPEN 0 +#endif + +#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name) +#define au_fset_cpup(flags, name) \ + do { (flags) |= AuCpup_##name; } while (0) +#define au_fclr_cpup(flags, name) \ + do { (flags) &= ~AuCpup_##name; } while (0) + +int au_copy_file(struct file *dst, struct file *src, loff_t len); +int au_sio_cpup_simple(struct au_cp_generic *cpg); +int au_sio_cpdown_simple(struct au_cp_generic *cpg); +int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file); + +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent, void *arg), + void *arg); +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); + +/* ---------------------------------------------------------------------- */ + +/* keep timestamps when copyup */ +struct au_dtime { + struct dentry *dt_dentry; + struct path dt_h_path; + struct timespec64 dt_atime, dt_mtime; +}; +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path); +void au_dtime_revert(struct au_dtime *dt); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_CPUP_H__ */ diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c new file mode 100644 index 000000000000..80266f4fcf7d --- /dev/null +++ b/fs/aufs/dbgaufs.c @@ -0,0 +1,526 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debugfs interface + */ + +#include <linux/debugfs.h> +#include "aufs.h" + +#ifndef CONFIG_SYSFS +#error DEBUG_FS depends upon SYSFS +#endif + +static struct dentry *dbgaufs; +static const mode_t dbgaufs_mode = 0444; + +/* 20 is max digits length of ulong 64 */ +struct dbgaufs_arg { + int n; + char a[20 * 4]; +}; + +/* + * common function for all XINO files + */ +static int dbgaufs_xi_release(struct inode *inode __maybe_unused, + struct file *file) +{ + void *p; + + p = file->private_data; + if (p) { + /* this is struct dbgaufs_arg */ + AuDebugOn(!au_kfree_sz_test(p)); + au_kfree_do_rcu(p); + } + return 0; +} + +static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt, + int cnt) +{ + int err; + struct kstat st; + struct dbgaufs_arg *p; + + err = -ENOMEM; + p = kmalloc(sizeof(*p), GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = 0; + p->n = 0; + file->private_data = p; + if (!xf) + goto out; + + err = vfsub_getattr(&xf->f_path, &st); + if (!err) { + if (do_fcnt) + p->n = snprintf + (p->a, sizeof(p->a), "%d, %llux%u %lld\n", + cnt, st.blocks, st.blksize, + (long long)st.size); + else + p->n = snprintf(p->a, sizeof(p->a), "%llux%u %lld\n", + st.blocks, st.blksize, + (long long)st.size); + AuDebugOn(p->n >= sizeof(p->a)); + } else { + p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err); + err = 0; + } + +out: + return err; +} + +static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dbgaufs_arg *p; + + p = file->private_data; + return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + +/* ---------------------------------------------------------------------- */ + +struct dbgaufs_plink_arg { + int n; + char a[]; +}; + +static int dbgaufs_plink_release(struct inode *inode __maybe_unused, + struct file *file) +{ + free_page((unsigned long)file->private_data); + return 0; +} + +static int dbgaufs_plink_open(struct inode *inode, struct file *file) +{ + int err, i, limit; + unsigned long n, sum; + struct dbgaufs_plink_arg *p; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct hlist_bl_head *hbl; + + err = -ENOMEM; + p = (void *)get_zeroed_page(GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = -EFBIG; + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + if (au_opt_test(au_mntflags(sb), PLINK)) { + limit = PAGE_SIZE - sizeof(p->n); + + /* the number of buckets */ + n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH); + p->n += n; + limit -= n; + + sum = 0; + for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH; + i++, hbl++) { + n = au_hbl_count(hbl); + sum += n; + + n = snprintf(p->a + p->n, limit, "%lu ", n); + p->n += n; + limit -= n; + if (unlikely(limit <= 0)) + goto out_free; + } + p->a[p->n - 1] = '\n'; + + /* the sum of plinks */ + n = snprintf(p->a + p->n, limit, "%lu\n", sum); + p->n += n; + limit -= n; + if (unlikely(limit <= 0)) + goto out_free; + } else { +#define str "1\n0\n0\n" + p->n = sizeof(str) - 1; + strcpy(p->a, str); +#undef str + } + si_read_unlock(sb); + + err = 0; + file->private_data = p; + goto out; /* success */ + +out_free: + free_page((unsigned long)p); +out: + return err; +} + +static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dbgaufs_plink_arg *p; + + p = file->private_data; + return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + +static const struct file_operations dbgaufs_plink_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_plink_open, + .release = dbgaufs_plink_release, + .read = dbgaufs_plink_read +}; + +/* ---------------------------------------------------------------------- */ + +static int dbgaufs_xib_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0, /*cnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xib_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xib_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +/* ---------------------------------------------------------------------- */ + +#define DbgaufsXi_PREFIX "xi" + +static int dbgaufs_xino_open(struct inode *inode, struct file *file) +{ + int err, idx; + long l; + aufs_bindex_t bindex; + char *p, a[sizeof(DbgaufsXi_PREFIX) + 8]; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct au_xino *xi; + struct file *xf; + struct qstr *name; + struct au_branch *br; + + err = -ENOENT; + name = &file->f_path.dentry->d_name; + if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) + || memcmp(name->name, DbgaufsXi_PREFIX, + sizeof(DbgaufsXi_PREFIX) - 1))) + goto out; + + AuDebugOn(name->len >= sizeof(a)); + memcpy(a, name->name, name->len); + a[name->len] = '\0'; + p = strchr(a, '-'); + if (p) + *p = '\0'; + err = kstrtol(a + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); + if (unlikely(err)) + goto out; + bindex = l; + idx = 0; + if (p) { + err = kstrtol(p + 1, 10, &l); + if (unlikely(err)) + goto out; + idx = l; + } + + err = -ENOENT; + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + if (unlikely(bindex < 0 || bindex > au_sbbot(sb))) + goto out_si; + br = au_sbr(sb, bindex); + xi = br->br_xino; + if (unlikely(idx >= xi->xi_nfile)) + goto out_si; + xf = au_xino_file(xi, idx); + if (xf) + err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1, + au_xino_count(br)); + +out_si: + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +static const struct file_operations dbgaufs_xino_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xino_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +void dbgaufs_xino_del(struct au_branch *br) +{ + struct dentry *dbgaufs; + + dbgaufs = br->br_dbgaufs; + if (!dbgaufs) + return; + + br->br_dbgaufs = NULL; + /* debugfs acquires the parent i_mutex */ + lockdep_off(); + debugfs_remove(dbgaufs); + lockdep_on(); +} + +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ + aufs_bindex_t bbot; + struct au_branch *br; + + if (!au_sbi(sb)->si_dbgaufs) + return; + + bbot = au_sbbot(sb); + for (; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + dbgaufs_xino_del(br); + } +} + +static void dbgaufs_br_do_add(struct super_block *sb, aufs_bindex_t bindex, + unsigned int idx, struct dentry *parent, + struct au_sbinfo *sbinfo) +{ + struct au_branch *br; + struct dentry *d; + /* "xi" bindex(5) "-" idx(2) NULL */ + char name[sizeof(DbgaufsXi_PREFIX) + 8]; + + if (!idx) + snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); + else + snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d-%u", + bindex, idx); + br = au_sbr(sb, bindex); + if (br->br_dbgaufs) { + struct qstr qstr = QSTR_INIT(name, strlen(name)); + + if (!au_qstreq(&br->br_dbgaufs->d_name, &qstr)) { + /* debugfs acquires the parent i_mutex */ + lockdep_off(); + d = debugfs_rename(parent, br->br_dbgaufs, parent, + name); + lockdep_on(); + if (unlikely(!d)) + pr_warn("failed renaming %pd/%s, ignored.\n", + parent, name); + } + } else { + lockdep_off(); + br->br_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, + sbinfo, &dbgaufs_xino_fop); + lockdep_on(); + if (unlikely(!br->br_dbgaufs)) + pr_warn("failed creating %pd/%s, ignored.\n", + parent, name); + } +} + +static void dbgaufs_br_add(struct super_block *sb, aufs_bindex_t bindex, + struct dentry *parent, struct au_sbinfo *sbinfo) +{ + struct au_branch *br; + struct au_xino *xi; + unsigned int u; + + br = au_sbr(sb, bindex); + xi = br->br_xino; + for (u = 0; u < xi->xi_nfile; u++) + dbgaufs_br_do_add(sb, bindex, u, parent, sbinfo); +} + +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown) +{ + struct au_sbinfo *sbinfo; + struct dentry *parent; + aufs_bindex_t bbot; + + if (!au_opt_test(au_mntflags(sb), XINO)) + return; + + sbinfo = au_sbi(sb); + parent = sbinfo->si_dbgaufs; + if (!parent) + return; + + bbot = au_sbbot(sb); + if (topdown) + for (; bindex <= bbot; bindex++) + dbgaufs_br_add(sb, bindex, parent, sbinfo); + else + for (; bbot >= bindex; bbot--) + dbgaufs_br_add(sb, bbot, parent, sbinfo); +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_EXPORT +static int dbgaufs_xigen_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0, /*cnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xigen_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xigen_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + int err; + + /* + * This function is a dynamic '__init' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -EIO; + sbinfo->si_dbgaufs_xigen = debugfs_create_file + ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xigen_fop); + if (sbinfo->si_dbgaufs_xigen) + err = 0; + + return err; +} +#else +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + return 0; +} +#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_si_fin(struct au_sbinfo *sbinfo) +{ + /* + * This function is a dynamic '__fin' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + debugfs_remove_recursive(sbinfo->si_dbgaufs); + sbinfo->si_dbgaufs = NULL; +} + +int dbgaufs_si_init(struct au_sbinfo *sbinfo) +{ + int err; + char name[SysaufsSiNameLen]; + + /* + * This function is a dynamic '__init' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -ENOENT; + if (!dbgaufs) { + AuErr1("/debug/aufs is uninitialized\n"); + goto out; + } + + err = -EIO; + sysaufs_name(sbinfo, name); + sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); + if (unlikely(!sbinfo->si_dbgaufs)) + goto out; + + /* regardless plink/noplink option */ + sbinfo->si_dbgaufs_plink = debugfs_create_file + ("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_plink_fop); + if (unlikely(!sbinfo->si_dbgaufs_plink)) + goto out_dir; + + /* regardless xino/noxino option */ + sbinfo->si_dbgaufs_xib = debugfs_create_file + ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xib_fop); + if (unlikely(!sbinfo->si_dbgaufs_xib)) + goto out_dir; + + err = dbgaufs_xigen_init(sbinfo); + if (!err) + goto out; /* success */ + +out_dir: + dbgaufs_si_fin(sbinfo); +out: + if (unlikely(err)) + pr_err("debugfs/aufs failed\n"); + return err; +} + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_fin(void) +{ + debugfs_remove(dbgaufs); +} + +int __init dbgaufs_init(void) +{ + int err; + + err = -EIO; + dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); + if (dbgaufs) + err = 0; + return err; +} diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h new file mode 100644 index 000000000000..7b4ccdebb678 --- /dev/null +++ b/fs/aufs/dbgaufs.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debugfs interface + */ + +#ifndef __DBGAUFS_H__ +#define __DBGAUFS_H__ + +#ifdef __KERNEL__ + +struct super_block; +struct au_sbinfo; +struct au_branch; + +#ifdef CONFIG_DEBUG_FS +/* dbgaufs.c */ +void dbgaufs_xino_del(struct au_branch *br); +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown); +void dbgaufs_si_fin(struct au_sbinfo *sbinfo); +int dbgaufs_si_init(struct au_sbinfo *sbinfo); +void dbgaufs_fin(void); +int __init dbgaufs_init(void); +#else +AuStubVoid(dbgaufs_xino_del, struct au_branch *br) +AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex, + int topdown) +AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo) +AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo) +AuStubVoid(dbgaufs_fin, void) +AuStubInt0(__init dbgaufs_init, void) +#endif /* CONFIG_DEBUG_FS */ + +#endif /* __KERNEL__ */ +#endif /* __DBGAUFS_H__ */ diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c new file mode 100644 index 000000000000..0b9b1862b563 --- /dev/null +++ b/fs/aufs/dcsub.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for dentry cache + */ + +#include "aufs.h" + +static void au_dpage_free(struct au_dpage *dpage) +{ + int i; + struct dentry **p; + + p = dpage->dentries; + for (i = 0; i < dpage->ndentry; i++) + dput(*p++); + free_page((unsigned long)dpage->dentries); +} + +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) +{ + int err; + void *p; + + err = -ENOMEM; + dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); + if (unlikely(!dpages->dpages)) + goto out; + + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out_dpages; + + dpages->dpages[0].ndentry = 0; + dpages->dpages[0].dentries = p; + dpages->ndpage = 1; + return 0; /* success */ + +out_dpages: + au_kfree_try_rcu(dpages->dpages); +out: + return err; +} + +void au_dpages_free(struct au_dcsub_pages *dpages) +{ + int i; + struct au_dpage *p; + + p = dpages->dpages; + for (i = 0; i < dpages->ndpage; i++) + au_dpage_free(p++); + au_kfree_try_rcu(dpages->dpages); +} + +static int au_dpages_append(struct au_dcsub_pages *dpages, + struct dentry *dentry, gfp_t gfp) +{ + int err, sz; + struct au_dpage *dpage; + void *p; + + dpage = dpages->dpages + dpages->ndpage - 1; + sz = PAGE_SIZE / sizeof(dentry); + if (unlikely(dpage->ndentry >= sz)) { + AuLabel(new dpage); + err = -ENOMEM; + sz = dpages->ndpage * sizeof(*dpages->dpages); + p = au_kzrealloc(dpages->dpages, sz, + sz + sizeof(*dpages->dpages), gfp, + /*may_shrink*/0); + if (unlikely(!p)) + goto out; + + dpages->dpages = p; + dpage = dpages->dpages + dpages->ndpage; + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out; + + dpage->ndentry = 0; + dpage->dentries = p; + dpages->ndpage++; + } + + AuDebugOn(au_dcount(dentry) <= 0); + dpage->dentries[dpage->ndentry++] = dget_dlock(dentry); + return 0; /* success */ + +out: + return err; +} + +/* todo: BAD approach */ +/* copied from linux/fs/dcache.c */ +enum d_walk_ret { + D_WALK_CONTINUE, + D_WALK_QUIT, + D_WALK_NORETRY, + D_WALK_SKIP, +}; + +extern void d_walk(struct dentry *parent, void *data, + enum d_walk_ret (*enter)(void *, struct dentry *)); + +struct ac_dpages_arg { + int err; + struct au_dcsub_pages *dpages; + struct super_block *sb; + au_dpages_test test; + void *arg; +}; + +static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry) +{ + enum d_walk_ret ret; + struct ac_dpages_arg *arg = _arg; + + ret = D_WALK_CONTINUE; + if (dentry->d_sb == arg->sb + && !IS_ROOT(dentry) + && au_dcount(dentry) > 0 + && au_di(dentry) + && (!arg->test || arg->test(dentry, arg->arg))) { + arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC); + if (unlikely(arg->err)) + ret = D_WALK_QUIT; + } + + return ret; +} + +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg) +{ + struct ac_dpages_arg args = { + .err = 0, + .dpages = dpages, + .sb = root->d_sb, + .test = test, + .arg = arg + }; + + d_walk(root, &args, au_call_dpages_append); + + return args.err; +} + +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg) +{ + int err; + + err = 0; + write_seqlock(&rename_lock); + spin_lock(&dentry->d_lock); + if (do_include + && au_dcount(dentry) > 0 + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + goto out; + + /* + * RCU for vfsmount is unnecessary since this is a traverse in a single + * mount + */ + while (!IS_ROOT(dentry)) { + dentry = dentry->d_parent; /* rename_lock is locked */ + spin_lock(&dentry->d_lock); + if (au_dcount(dentry) > 0 + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + break; + } + +out: + write_sequnlock(&rename_lock); + return err; +} + +static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg) +{ + return au_di(dentry) && dentry->d_sb == arg; +} + +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include) +{ + return au_dcsub_pages_rev(dpages, dentry, do_include, + au_dcsub_dpages_aufs, dentry->d_sb); +} + +int au_test_subdir(struct dentry *d1, struct dentry *d2) +{ + struct path path[2] = { + { + .dentry = d1 + }, + { + .dentry = d2 + } + }; + + return path_is_under(path + 0, path + 1); +} diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h new file mode 100644 index 000000000000..36f7fcdd7f23 --- /dev/null +++ b/fs/aufs/dcsub.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for dentry cache + */ + +#ifndef __AUFS_DCSUB_H__ +#define __AUFS_DCSUB_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include <linux/fs.h> + +struct au_dpage { + int ndentry; + struct dentry **dentries; +}; + +struct au_dcsub_pages { + int ndpage; + struct au_dpage *dpages; +}; + +/* ---------------------------------------------------------------------- */ + +/* dcsub.c */ +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp); +void au_dpages_free(struct au_dcsub_pages *dpages); +typedef int (*au_dpages_test)(struct dentry *dentry, void *arg); +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg); +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg); +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include); +int au_test_subdir(struct dentry *d1, struct dentry *d2); + +/* ---------------------------------------------------------------------- */ + +/* + * todo: in linux-3.13, several similar (but faster) helpers are added to + * include/linux/dcache.h. Try them (in the future). + */ + +static inline int au_d_hashed_positive(struct dentry *d) +{ + int err; + struct inode *inode = d_inode(d); + + err = 0; + if (unlikely(d_unhashed(d) + || d_is_negative(d) + || !inode->i_nlink)) + err = -ENOENT; + return err; +} + +static inline int au_d_linkable(struct dentry *d) +{ + int err; + struct inode *inode = d_inode(d); + + err = au_d_hashed_positive(d); + if (err + && d_is_positive(d) + && (inode->i_state & I_LINKABLE)) + err = 0; + return err; +} + +static inline int au_d_alive(struct dentry *d) +{ + int err; + struct inode *inode; + + err = 0; + if (!IS_ROOT(d)) + err = au_d_hashed_positive(d); + else { + inode = d_inode(d); + if (unlikely(d_unlinked(d) + || d_is_negative(d) + || !inode->i_nlink)) + err = -ENOENT; + } + return err; +} + +static inline int au_alive_dir(struct dentry *d) +{ + int err; + + err = au_d_alive(d); + if (unlikely(err || IS_DEADDIR(d_inode(d)))) + err = -ENOENT; + return err; +} + +static inline int au_qstreq(struct qstr *a, struct qstr *b) +{ + return a->len == b->len + && !memcmp(a->name, b->name, a->len); +} + +/* + * by the commit + * 360f547 2015-01-25 dcache: let the dentry count go down to zero without + * taking d_lock + * the type of d_lockref.count became int, but the inlined function d_count() + * still returns unsigned int. + * I don't know why. Maybe it is for every d_count() users? + * Anyway au_dcount() lives on. + */ +static inline int au_dcount(struct dentry *d) +{ + return (int)d_count(d); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DCSUB_H__ */ diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c new file mode 100644 index 000000000000..f0c076c61252 --- /dev/null +++ b/fs/aufs/debug.c @@ -0,0 +1,441 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debug print functions + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* Returns 0, or -errno. arg is in kp->arg. */ +static int param_atomic_t_set(const char *val, const struct kernel_param *kp) +{ + int err, n; + + err = kstrtoint(val, 0, &n); + if (!err) { + if (n > 0) + au_debug_on(); + else + au_debug_off(); + } + return err; +} + +/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ +static int param_atomic_t_get(char *buffer, const struct kernel_param *kp) +{ + atomic_t *a; + + a = kp->arg; + return sprintf(buffer, "%d", atomic_read(a)); +} + +static struct kernel_param_ops param_ops_atomic_t = { + .set = param_atomic_t_set, + .get = param_atomic_t_get + /* void (*free)(void *arg) */ +}; + +atomic_t aufs_debug = ATOMIC_INIT(0); +MODULE_PARM_DESC(debug, "debug print"); +module_param_named(debug, aufs_debug, atomic_t, 0664); + +DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */ +char *au_plevel = KERN_DEBUG; +#define dpri(fmt, ...) do { \ + if ((au_plevel \ + && strcmp(au_plevel, KERN_DEBUG)) \ + || au_debug_test()) \ + printk("%s" fmt, au_plevel, ##__VA_ARGS__); \ +} while (0) + +/* ---------------------------------------------------------------------- */ + +void au_dpri_whlist(struct au_nhash *whlist) +{ + unsigned long ul, n; + struct hlist_head *head; + struct au_vdir_wh *pos; + + n = whlist->nh_num; + head = whlist->nh_head; + for (ul = 0; ul < n; ul++) { + hlist_for_each_entry(pos, head, wh_hash) + dpri("b%d, %.*s, %d\n", + pos->wh_bindex, + pos->wh_str.len, pos->wh_str.name, + pos->wh_str.len); + head++; + } +} + +void au_dpri_vdir(struct au_vdir *vdir) +{ + unsigned long ul; + union au_vdir_deblk_p p; + unsigned char *o; + + if (!vdir || IS_ERR(vdir)) { + dpri("err %ld\n", PTR_ERR(vdir)); + return; + } + + dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %llu\n", + vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk, + vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version); + for (ul = 0; ul < vdir->vd_nblk; ul++) { + p.deblk = vdir->vd_deblk[ul]; + o = p.deblk; + dpri("[%lu]: %p\n", ul, o); + } +} + +static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, + struct dentry *wh) +{ + char *n = NULL; + int l = 0; + + if (!inode || IS_ERR(inode)) { + dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); + return -1; + } + + /* the type of i_blocks depends upon CONFIG_LBDAF */ + BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) + && sizeof(inode->i_blocks) != sizeof(u64)); + if (wh) { + n = (void *)wh->d_name.name; + l = wh->d_name.len; + } + + dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," + " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", + bindex, inode, + inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", + atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, + i_size_read(inode), (unsigned long long)inode->i_blocks, + hn, (long long)timespec64_to_ns(&inode->i_ctime) & 0x0ffff, + inode->i_mapping ? inode->i_mapping->nrpages : 0, + inode->i_state, inode->i_flags, inode_peek_iversion(inode), + inode->i_generation, + l ? ", wh " : "", l, n); + return 0; +} + +void au_dpri_inode(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct au_hinode *hi; + aufs_bindex_t bindex; + int err, hn; + + err = do_pri_inode(-1, inode, -1, NULL); + if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode)) + return; + + iinfo = au_ii(inode); + dpri("i-1: btop %d, bbot %d, gen %d\n", + iinfo->ii_btop, iinfo->ii_bbot, au_iigen(inode, NULL)); + if (iinfo->ii_btop < 0) + return; + hn = 0; + for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; bindex++) { + hi = au_hinode(iinfo, bindex); + hn = !!au_hn(hi); + do_pri_inode(bindex, hi->hi_inode, hn, hi->hi_whdentry); + } +} + +void au_dpri_dalias(struct inode *inode) +{ + struct dentry *d; + + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) + au_dpri_dentry(d); + spin_unlock(&inode->i_lock); +} + +static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) +{ + struct dentry *wh = NULL; + int hn; + struct inode *inode; + struct au_iinfo *iinfo; + struct au_hinode *hi; + + if (!dentry || IS_ERR(dentry)) { + dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); + return -1; + } + /* do not call dget_parent() here */ + /* note: access d_xxx without d_lock */ + dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n", + bindex, dentry, dentry, + dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", + au_dcount(dentry), dentry->d_flags, + d_unhashed(dentry) ? "un" : ""); + hn = -1; + inode = NULL; + if (d_is_positive(dentry)) + inode = d_inode(dentry); + if (inode + && au_test_aufs(dentry->d_sb) + && bindex >= 0 + && !au_is_bad_inode(inode)) { + iinfo = au_ii(inode); + hi = au_hinode(iinfo, bindex); + hn = !!au_hn(hi); + wh = hi->hi_whdentry; + } + do_pri_inode(bindex, inode, hn, wh); + return 0; +} + +void au_dpri_dentry(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + aufs_bindex_t bindex; + int err; + + err = do_pri_dentry(-1, dentry); + if (err || !au_test_aufs(dentry->d_sb)) + return; + + dinfo = au_di(dentry); + if (!dinfo) + return; + dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n", + dinfo->di_btop, dinfo->di_bbot, + dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry), + dinfo->di_tmpfile); + if (dinfo->di_btop < 0) + return; + for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++) + do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry); +} + +static int do_pri_file(aufs_bindex_t bindex, struct file *file) +{ + char a[32]; + + if (!file || IS_ERR(file)) { + dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); + return -1; + } + a[0] = 0; + if (bindex < 0 + && !IS_ERR_OR_NULL(file->f_path.dentry) + && au_test_aufs(file->f_path.dentry->d_sb) + && au_fi(file)) + snprintf(a, sizeof(a), ", gen %d, mmapped %d", + au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); + dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", + bindex, file->f_mode, file->f_flags, (long)file_count(file), + file->f_version, file->f_pos, a); + if (!IS_ERR_OR_NULL(file->f_path.dentry)) + do_pri_dentry(bindex, file->f_path.dentry); + return 0; +} + +void au_dpri_file(struct file *file) +{ + struct au_finfo *finfo; + struct au_fidir *fidir; + struct au_hfile *hfile; + aufs_bindex_t bindex; + int err; + + err = do_pri_file(-1, file); + if (err + || IS_ERR_OR_NULL(file->f_path.dentry) + || !au_test_aufs(file->f_path.dentry->d_sb)) + return; + + finfo = au_fi(file); + if (!finfo) + return; + if (finfo->fi_btop < 0) + return; + fidir = finfo->fi_hdir; + if (!fidir) + do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file); + else + for (bindex = finfo->fi_btop; + bindex >= 0 && bindex <= fidir->fd_bbot; + bindex++) { + hfile = fidir->fd_hfile + bindex; + do_pri_file(bindex, hfile ? hfile->hf_file : NULL); + } +} + +static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) +{ + struct vfsmount *mnt; + struct super_block *sb; + + if (!br || IS_ERR(br)) + goto out; + mnt = au_br_mnt(br); + if (!mnt || IS_ERR(mnt)) + goto out; + sb = mnt->mnt_sb; + if (!sb || IS_ERR(sb)) + goto out; + + dpri("s%d: {perm 0x%x, id %d, wbr %p}, " + "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " + "xino %d\n", + bindex, br->br_perm, br->br_id, br->br_wbr, + au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev), + sb->s_flags, sb->s_count, + atomic_read(&sb->s_active), + !!au_xino_file(br->br_xino, /*idx*/-1)); + return 0; + +out: + dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); + return -1; +} + +void au_dpri_sb(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + aufs_bindex_t bindex; + int err; + /* to reduce stack size */ + struct { + struct vfsmount mnt; + struct au_branch fake; + } *a; + + /* this function can be called from magic sysrq */ + a = kzalloc(sizeof(*a), GFP_ATOMIC); + if (unlikely(!a)) { + dpri("no memory\n"); + return; + } + + a->mnt.mnt_sb = sb; + a->fake.br_path.mnt = &a->mnt; + err = do_pri_br(-1, &a->fake); + au_kfree_rcu(a); + dpri("dev 0x%x\n", sb->s_dev); + if (err || !au_test_aufs(sb)) + return; + + sbinfo = au_sbi(sb); + if (!sbinfo) + return; + dpri("nw %d, gen %u, kobj %d\n", + atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation, + kref_read(&sbinfo->si_kobj.kref)); + for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++) + do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); +} + +/* ---------------------------------------------------------------------- */ + +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) +{ + struct inode *h_inode, *inode = d_inode(dentry); + struct dentry *h_dentry; + aufs_bindex_t bindex, bbot, bi; + + if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) + return; + + bbot = au_dbbot(dentry); + bi = au_ibbot(inode); + if (bi < bbot) + bbot = bi; + bindex = au_dbtop(dentry); + bi = au_ibtop(inode); + if (bi > bindex) + bindex = bi; + + for (; bindex <= bbot; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_inode = au_h_iptr(inode, bindex); + if (unlikely(h_inode != d_inode(h_dentry))) { + au_debug_on(); + AuDbg("b%d, %s:%d\n", bindex, func, line); + AuDbgDentry(dentry); + AuDbgInode(inode); + au_debug_off(); + BUG(); + } + } +} + +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) +{ + int err, i, j; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + AuDebugOn(err); + err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1); + AuDebugOn(err); + for (i = dpages.ndpage - 1; !err && i >= 0; i--) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + for (j = dpage->ndentry - 1; !err && j >= 0; j--) + AuDebugOn(au_digen_test(dentries[j], sigen)); + } + au_dpages_free(&dpages); +} + +void au_dbg_verify_kthread(void) +{ + if (au_wkq_test()) { + au_dbg_blocked(); + /* + * It may be recursive, but udba=notify between two aufs mounts, + * where a single ro branch is shared, is not a problem. + */ + /* WARN_ON(1); */ + } +} + +/* ---------------------------------------------------------------------- */ + +int __init au_debug_init(void) +{ + aufs_bindex_t bindex; + struct au_vdir_destr destr; + + bindex = -1; + AuDebugOn(bindex >= 0); + + destr.len = -1; + AuDebugOn(destr.len < NAME_MAX); + +#ifdef CONFIG_4KSTACKS + pr_warn("CONFIG_4KSTACKS is defined.\n"); +#endif + + return 0; +} diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h new file mode 100644 index 000000000000..7e46953513f2 --- /dev/null +++ b/fs/aufs/debug.h @@ -0,0 +1,226 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debug print functions + */ + +#ifndef __AUFS_DEBUG_H__ +#define __AUFS_DEBUG_H__ + +#ifdef __KERNEL__ + +#include <linux/atomic.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/sysrq.h> + +#ifdef CONFIG_AUFS_DEBUG +#define AuDebugOn(a) BUG_ON(a) + +/* module parameter */ +extern atomic_t aufs_debug; +static inline void au_debug_on(void) +{ + atomic_inc(&aufs_debug); +} +static inline void au_debug_off(void) +{ + atomic_dec_if_positive(&aufs_debug); +} + +static inline int au_debug_test(void) +{ + return atomic_read(&aufs_debug) > 0; +} +#else +#define AuDebugOn(a) do {} while (0) +AuStubVoid(au_debug_on, void) +AuStubVoid(au_debug_off, void) +AuStubInt0(au_debug_test, void) +#endif /* CONFIG_AUFS_DEBUG */ + +#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t) + +/* ---------------------------------------------------------------------- */ + +/* debug print */ + +#define AuDbg(fmt, ...) do { \ + if (au_debug_test()) \ + pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \ +} while (0) +#define AuLabel(l) AuDbg(#l "\n") +#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__) +#define AuWarn1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_warn(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_err(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuIOErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + AuIOErr(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuUnsupportMsg "This operation is not supported." \ + " Please report this application to aufs-users ML." +#define AuUnsupport(fmt, ...) do { \ + pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \ + dump_stack(); \ +} while (0) + +#define AuTraceErr(e) do { \ + if (unlikely((e) < 0)) \ + AuDbg("err %d\n", (int)(e)); \ +} while (0) + +#define AuTraceErrPtr(p) do { \ + if (IS_ERR(p)) \ + AuDbg("err %ld\n", PTR_ERR(p)); \ +} while (0) + +/* dirty macros for debug print, use with "%.*s" and caution */ +#define AuLNPair(qstr) (qstr)->len, (qstr)->name + +/* ---------------------------------------------------------------------- */ + +struct dentry; +#ifdef CONFIG_AUFS_DEBUG +extern struct mutex au_dbg_mtx; +extern char *au_plevel; +struct au_nhash; +void au_dpri_whlist(struct au_nhash *whlist); +struct au_vdir; +void au_dpri_vdir(struct au_vdir *vdir); +struct inode; +void au_dpri_inode(struct inode *inode); +void au_dpri_dalias(struct inode *inode); +void au_dpri_dentry(struct dentry *dentry); +struct file; +void au_dpri_file(struct file *filp); +struct super_block; +void au_dpri_sb(struct super_block *sb); + +#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__) +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line); +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); +void au_dbg_verify_kthread(void); + +int __init au_debug_init(void); + +#define AuDbgWhlist(w) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#w "\n"); \ + au_dpri_whlist(w); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgVdir(v) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#v "\n"); \ + au_dpri_vdir(v); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgInode(i) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#i "\n"); \ + au_dpri_inode(i); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgDAlias(i) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#i "\n"); \ + au_dpri_dalias(i); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgDentry(d) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#d "\n"); \ + au_dpri_dentry(d); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgFile(f) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#f "\n"); \ + au_dpri_file(f); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgSb(sb) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#sb "\n"); \ + au_dpri_sb(sb); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgSym(addr) do { \ + char sym[KSYM_SYMBOL_LEN]; \ + sprint_symbol(sym, (unsigned long)addr); \ + AuDbg("%s\n", sym); \ +} while (0) +#else +AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry) +AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen) +AuStubVoid(au_dbg_verify_kthread, void) +AuStubInt0(__init au_debug_init, void) + +#define AuDbgWhlist(w) do {} while (0) +#define AuDbgVdir(v) do {} while (0) +#define AuDbgInode(i) do {} while (0) +#define AuDbgDAlias(i) do {} while (0) +#define AuDbgDentry(d) do {} while (0) +#define AuDbgFile(f) do {} while (0) +#define AuDbgSb(sb) do {} while (0) +#define AuDbgSym(addr) do {} while (0) +#endif /* CONFIG_AUFS_DEBUG */ + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +int __init au_sysrq_init(void); +void au_sysrq_fin(void); + +#ifdef CONFIG_HW_CONSOLE +#define au_dbg_blocked() do { \ + WARN_ON(1); \ + handle_sysrq('w'); \ +} while (0) +#else +AuStubVoid(au_dbg_blocked, void) +#endif + +#else +AuStubInt0(__init au_sysrq_init, void) +AuStubVoid(au_sysrq_fin, void) +AuStubVoid(au_dbg_blocked, void) +#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DEBUG_H__ */ diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c new file mode 100644 index 000000000000..50aaaa21d089 --- /dev/null +++ b/fs/aufs/dentry.c @@ -0,0 +1,1154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * lookup and dentry operations + */ + +#include <linux/iversion.h> +#include <linux/namei.h> +#include "aufs.h" + +/* + * returns positive/negative dentry, NULL or an error. + * NULL means whiteout-ed or not-found. + */ +static struct dentry* +au_do_lookup(struct dentry *h_parent, struct dentry *dentry, + aufs_bindex_t bindex, struct au_do_lookup_args *args) +{ + struct dentry *h_dentry; + struct inode *h_inode; + struct au_branch *br; + int wh_found, opq; + unsigned char wh_able; + const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); + const unsigned char ignore_perm = !!au_ftest_lkup(args->flags, + IGNORE_PERM); + + wh_found = 0; + br = au_sbr(dentry->d_sb, bindex); + wh_able = !!au_br_whable(br->br_perm); + if (wh_able) + wh_found = au_wh_test(h_parent, &args->whname, ignore_perm); + h_dentry = ERR_PTR(wh_found); + if (!wh_found) + goto real_lookup; + if (unlikely(wh_found < 0)) + goto out; + + /* We found a whiteout */ + /* au_set_dbbot(dentry, bindex); */ + au_set_dbwh(dentry, bindex); + if (!allow_neg) + return NULL; /* success */ + +real_lookup: + if (!ignore_perm) + h_dentry = vfsub_lkup_one(args->name, h_parent); + else + h_dentry = au_sio_lkup_one(args->name, h_parent); + if (IS_ERR(h_dentry)) { + if (PTR_ERR(h_dentry) == -ENAMETOOLONG + && !allow_neg) + h_dentry = NULL; + goto out; + } + + h_inode = d_inode(h_dentry); + if (d_is_negative(h_dentry)) { + if (!allow_neg) + goto out_neg; + } else if (wh_found + || (args->type && args->type != (h_inode->i_mode & S_IFMT))) + goto out_neg; + else if (au_ftest_lkup(args->flags, DIRREN) + /* && h_inode */ + && !au_dr_lkup_h_ino(args, bindex, h_inode->i_ino)) { + AuDbg("b%d %pd ignored hi%llu\n", bindex, h_dentry, + (unsigned long long)h_inode->i_ino); + goto out_neg; + } + + if (au_dbbot(dentry) <= bindex) + au_set_dbbot(dentry, bindex); + if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) + au_set_dbtop(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + + if (!d_is_dir(h_dentry) + || !wh_able + || (d_really_is_positive(dentry) && !d_is_dir(dentry))) + goto out; /* success */ + + inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); + opq = au_diropq_test(h_dentry); + inode_unlock_shared(h_inode); + if (opq > 0) + au_set_dbdiropq(dentry, bindex); + else if (unlikely(opq < 0)) { + au_set_h_dptr(dentry, bindex, NULL); + h_dentry = ERR_PTR(opq); + } + goto out; + +out_neg: + dput(h_dentry); + h_dentry = NULL; +out: + return h_dentry; +} + +static int au_test_shwh(struct super_block *sb, const struct qstr *name) +{ + if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) + && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) + return -EPERM; + return 0; +} + +/* + * returns the number of lower positive dentries, + * otherwise an error. + * can be called at unlinking with @type is zero. + */ +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, + unsigned int flags) +{ + int npositive, err; + aufs_bindex_t bindex, btail, bdiropq; + unsigned char isdir, dirperm1, dirren; + struct au_do_lookup_args args = { + .flags = flags, + .name = &dentry->d_name + }; + struct dentry *parent; + struct super_block *sb; + + sb = dentry->d_sb; + err = au_test_shwh(sb, args.name); + if (unlikely(err)) + goto out; + + err = au_wh_name_alloc(&args.whname, args.name); + if (unlikely(err)) + goto out; + + isdir = !!d_is_dir(dentry); + dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1); + dirren = !!au_opt_test(au_mntflags(sb), DIRREN); + if (dirren) + au_fset_lkup(args.flags, DIRREN); + + npositive = 0; + parent = dget_parent(dentry); + btail = au_dbtaildir(parent); + for (bindex = btop; bindex <= btail; bindex++) { + struct dentry *h_parent, *h_dentry; + struct inode *h_inode, *h_dir; + struct au_branch *br; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) { + if (d_is_positive(h_dentry)) + npositive++; + break; + } + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || !d_is_dir(h_parent)) + continue; + + if (dirren) { + /* if the inum matches, then use the prepared name */ + err = au_dr_lkup_name(&args, bindex); + if (unlikely(err)) + goto out_parent; + } + + h_dir = d_inode(h_parent); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + h_dentry = au_do_lookup(h_parent, dentry, bindex, &args); + inode_unlock_shared(h_dir); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out_parent; + if (h_dentry) + au_fclr_lkup(args.flags, ALLOW_NEG); + if (dirperm1) + au_fset_lkup(args.flags, IGNORE_PERM); + + if (au_dbwh(dentry) == bindex) + break; + if (!h_dentry) + continue; + if (d_is_negative(h_dentry)) + continue; + h_inode = d_inode(h_dentry); + npositive++; + if (!args.type) + args.type = h_inode->i_mode & S_IFMT; + if (args.type != S_IFDIR) + break; + else if (isdir) { + /* the type of lower may be different */ + bdiropq = au_dbdiropq(dentry); + if (bdiropq >= 0 && bdiropq <= bindex) + break; + } + br = au_sbr(sb, bindex); + if (dirren + && au_dr_hino_test_add(&br->br_dirren, h_inode->i_ino, + /*add_ent*/NULL)) { + /* prepare next name to lookup */ + err = au_dr_lkup(&args, dentry, bindex); + if (unlikely(err)) + goto out_parent; + } + } + + if (npositive) { + AuLabel(positive); + au_update_dbtop(dentry); + } + err = npositive; + if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE) + && au_dbtop(dentry) < 0)) { + err = -EIO; + AuIOErr("both of real entry and whiteout found, %pd, err %d\n", + dentry, err); + } + +out_parent: + dput(parent); + au_kfree_try_rcu(args.whname.name); + if (dirren) + au_dr_lkup_fin(&args); +out: + return err; +} + +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent) +{ + struct dentry *dentry; + int wkq_err; + + if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC)) + dentry = vfsub_lkup_one(name, parent); + else { + struct vfsub_lkup_one_args args = { + .errp = &dentry, + .name = name, + .parent = parent + }; + + wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args); + if (unlikely(wkq_err)) + dentry = ERR_PTR(wkq_err); + } + + return dentry; +} + +/* + * lookup @dentry on @bindex which should be negative. + */ +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh) +{ + int err; + struct dentry *parent, *h_parent, *h_dentry; + struct au_branch *br; + + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bindex); + br = au_sbr(dentry->d_sb, bindex); + if (wh) + h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); + else + h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out; + if (unlikely(d_is_positive(h_dentry))) { + err = -EIO; + AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex); + dput(h_dentry); + goto out; + } + + err = 0; + if (bindex < au_dbtop(dentry)) + au_set_dbtop(dentry, bindex); + if (au_dbbot(dentry) < bindex) + au_set_dbbot(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* subset of struct inode */ +struct au_iattr { + unsigned long i_ino; + /* unsigned int i_nlink; */ + kuid_t i_uid; + kgid_t i_gid; + u64 i_version; +/* + loff_t i_size; + blkcnt_t i_blocks; +*/ + umode_t i_mode; +}; + +static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) +{ + ia->i_ino = h_inode->i_ino; + /* ia->i_nlink = h_inode->i_nlink; */ + ia->i_uid = h_inode->i_uid; + ia->i_gid = h_inode->i_gid; + ia->i_version = inode_query_iversion(h_inode); +/* + ia->i_size = h_inode->i_size; + ia->i_blocks = h_inode->i_blocks; +*/ + ia->i_mode = (h_inode->i_mode & S_IFMT); +} + +static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode) +{ + return ia->i_ino != h_inode->i_ino + /* || ia->i_nlink != h_inode->i_nlink */ + || !uid_eq(ia->i_uid, h_inode->i_uid) + || !gid_eq(ia->i_gid, h_inode->i_gid) + || !inode_eq_iversion(h_inode, ia->i_version) +/* + || ia->i_size != h_inode->i_size + || ia->i_blocks != h_inode->i_blocks +*/ + || ia->i_mode != (h_inode->i_mode & S_IFMT); +} + +static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, + struct au_branch *br) +{ + int err; + struct au_iattr ia; + struct inode *h_inode; + struct dentry *h_d; + struct super_block *h_sb; + + err = 0; + memset(&ia, -1, sizeof(ia)); + h_sb = h_dentry->d_sb; + h_inode = NULL; + if (d_is_positive(h_dentry)) { + h_inode = d_inode(h_dentry); + au_iattr_save(&ia, h_inode); + } else if (au_test_nfs(h_sb) || au_test_fuse(h_sb)) + /* nfs d_revalidate may return 0 for negative dentry */ + /* fuse d_revalidate always return 0 for negative dentry */ + goto out; + + /* main purpose is namei.c:cached_lookup() and d_revalidate */ + h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent); + err = PTR_ERR(h_d); + if (IS_ERR(h_d)) + goto out; + + err = 0; + if (unlikely(h_d != h_dentry + || d_inode(h_d) != h_inode + || (h_inode && au_iattr_test(&ia, h_inode)))) + err = au_busy_or_stale(); + dput(h_d); + +out: + AuTraceErr(err); + return err; +} + +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br) +{ + int err; + + err = 0; + if (udba == AuOpt_UDBA_REVAL + && !au_test_fs_remote(h_dentry->d_sb)) { + IMustLock(h_dir); + err = (d_inode(h_dentry->d_parent) != h_dir); + } else if (udba != AuOpt_UDBA_NONE) + err = au_h_verify_dentry(h_dentry, h_parent, br); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) +{ + int err; + aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq; + struct au_hdentry tmp, *p, *q; + struct au_dinfo *dinfo; + struct super_block *sb; + + DiMustWriteLock(dentry); + + sb = dentry->d_sb; + dinfo = au_di(dentry); + bbot = dinfo->di_bbot; + bwh = dinfo->di_bwh; + bdiropq = dinfo->di_bdiropq; + bindex = dinfo->di_btop; + p = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, p++) { + if (!p->hd_dentry) + continue; + + new_bindex = au_br_index(sb, p->hd_id); + if (new_bindex == bindex) + continue; + + if (dinfo->di_bwh == bindex) + bwh = new_bindex; + if (dinfo->di_bdiropq == bindex) + bdiropq = new_bindex; + if (new_bindex < 0) { + au_hdput(p); + p->hd_dentry = NULL; + continue; + } + + /* swap two lower dentries, and loop again */ + q = au_hdentry(dinfo, new_bindex); + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hd_dentry) { + bindex--; + p--; + } + } + + dinfo->di_bwh = -1; + if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh)) + dinfo->di_bwh = bwh; + + dinfo->di_bdiropq = -1; + if (bdiropq >= 0 + && bdiropq <= au_sbbot(sb) + && au_sbr_whable(sb, bdiropq)) + dinfo->di_bdiropq = bdiropq; + + err = -EIO; + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + bbot = au_dbbot(parent); + bindex = 0; + p = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, p++) + if (p->hd_dentry) { + dinfo->di_btop = bindex; + break; + } + + if (dinfo->di_btop >= 0) { + bindex = bbot; + p = au_hdentry(dinfo, bindex); + for (; bindex >= 0; bindex--, p--) + if (p->hd_dentry) { + dinfo->di_bbot = bindex; + err = 0; + break; + } + } + + return err; +} + +static void au_do_hide(struct dentry *dentry) +{ + struct inode *inode; + + if (d_really_is_positive(dentry)) { + inode = d_inode(dentry); + if (!d_is_dir(dentry)) { + if (inode->i_nlink && !d_unhashed(dentry)) + drop_nlink(inode); + } else { + clear_nlink(inode); + /* stop next lookup */ + inode->i_flags |= S_DEAD; + } + smp_mb(); /* necessary? */ + } + d_drop(dentry); +} + +static int au_hide_children(struct dentry *parent) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *dentry; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, parent, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + /* in reverse order */ + for (i = dpages.ndpage - 1; i >= 0; i--) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = ndentry - 1; j >= 0; j--) { + dentry = dpage->dentries[j]; + if (dentry != parent) + au_do_hide(dentry); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static void au_hide(struct dentry *dentry) +{ + int err; + + AuDbgDentry(dentry); + if (d_is_dir(dentry)) { + /* shrink_dcache_parent(dentry); */ + err = au_hide_children(dentry); + if (unlikely(err)) + AuIOErr("%pd, failed hiding children, ignored %d\n", + dentry, err); + } + au_do_hide(dentry); +} + +/* + * By adding a dirty branch, a cached dentry may be affected in various ways. + * + * a dirty branch is added + * - on the top of layers + * - in the middle of layers + * - to the bottom of layers + * + * on the added branch there exists + * - a whiteout + * - a diropq + * - a same named entry + * + exist + * * negative --> positive + * * positive --> positive + * - type is unchanged + * - type is changed + * + doesn't exist + * * negative --> negative + * * positive --> negative (rejected by au_br_del() for non-dir case) + * - none + */ +static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo, + struct au_dinfo *tmp) +{ + int err; + aufs_bindex_t bindex, bbot; + struct { + struct dentry *dentry; + struct inode *inode; + mode_t mode; + } orig_h, tmp_h = { + .dentry = NULL + }; + struct au_hdentry *hd; + struct inode *inode, *h_inode; + struct dentry *h_dentry; + + err = 0; + AuDebugOn(dinfo->di_btop < 0); + orig_h.mode = 0; + orig_h.dentry = au_hdentry(dinfo, dinfo->di_btop)->hd_dentry; + orig_h.inode = NULL; + if (d_is_positive(orig_h.dentry)) { + orig_h.inode = d_inode(orig_h.dentry); + orig_h.mode = orig_h.inode->i_mode & S_IFMT; + } + if (tmp->di_btop >= 0) { + tmp_h.dentry = au_hdentry(tmp, tmp->di_btop)->hd_dentry; + if (d_is_positive(tmp_h.dentry)) { + tmp_h.inode = d_inode(tmp_h.dentry); + tmp_h.mode = tmp_h.inode->i_mode & S_IFMT; + } + } + + inode = NULL; + if (d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (!orig_h.inode) { + AuDbg("negative originally\n"); + if (inode) { + au_hide(dentry); + goto out; + } + AuDebugOn(inode); + AuDebugOn(dinfo->di_btop != dinfo->di_bbot); + AuDebugOn(dinfo->di_bdiropq != -1); + + if (!tmp_h.inode) { + AuDbg("negative --> negative\n"); + /* should have only one negative lower */ + if (tmp->di_btop >= 0 + && tmp->di_btop < dinfo->di_btop) { + AuDebugOn(tmp->di_btop != tmp->di_bbot); + AuDebugOn(dinfo->di_btop != dinfo->di_bbot); + au_set_h_dptr(dentry, dinfo->di_btop, NULL); + au_di_cp(dinfo, tmp); + hd = au_hdentry(tmp, tmp->di_btop); + au_set_h_dptr(dentry, tmp->di_btop, + dget(hd->hd_dentry)); + } + au_dbg_verify_dinode(dentry); + } else { + AuDbg("negative --> positive\n"); + /* + * similar to the behaviour of creating with bypassing + * aufs. + * unhash it in order to force an error in the + * succeeding create operation. + * we should not set S_DEAD here. + */ + d_drop(dentry); + /* au_di_swap(tmp, dinfo); */ + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive originally\n"); + /* inode may be NULL */ + AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode); + if (!tmp_h.inode) { + AuDbg("positive --> negative\n"); + /* or bypassing aufs */ + au_hide(dentry); + if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop) + dinfo->di_bwh = tmp->di_bwh; + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else if (orig_h.mode == tmp_h.mode) { + AuDbg("positive --> positive, same type\n"); + if (!S_ISDIR(orig_h.mode) + && dinfo->di_btop > tmp->di_btop) { + /* + * similar to the behaviour of removing and + * creating. + */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else { + /* fill empty slots */ + if (dinfo->di_btop > tmp->di_btop) + dinfo->di_btop = tmp->di_btop; + if (dinfo->di_bbot < tmp->di_bbot) + dinfo->di_bbot = tmp->di_bbot; + dinfo->di_bwh = tmp->di_bwh; + dinfo->di_bdiropq = tmp->di_bdiropq; + bbot = dinfo->di_bbot; + bindex = tmp->di_btop; + hd = au_hdentry(tmp, bindex); + for (; bindex <= bbot; bindex++, hd++) { + if (au_h_dptr(dentry, bindex)) + continue; + h_dentry = hd->hd_dentry; + if (!h_dentry) + continue; + AuDebugOn(d_is_negative(h_dentry)); + h_inode = d_inode(h_dentry); + AuDebugOn(orig_h.mode + != (h_inode->i_mode + & S_IFMT)); + au_set_h_dptr(dentry, bindex, + dget(h_dentry)); + } + if (inode) + err = au_refresh_hinode(inode, dentry); + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive --> positive, different type\n"); + /* similar to the behaviour of removing and creating */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } + } + +out: + return err; +} + +void au_refresh_dop(struct dentry *dentry, int force_reval) +{ + const struct dentry_operations *dop + = force_reval ? &aufs_dop : dentry->d_sb->s_d_op; + static const unsigned int mask + = DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE; + + BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags)); + + if (dentry->d_op == dop) + return; + + AuDbg("%pd\n", dentry); + spin_lock(&dentry->d_lock); + if (dop == &aufs_dop) + dentry->d_flags |= mask; + else + dentry->d_flags &= ~mask; + dentry->d_op = dop; + spin_unlock(&dentry->d_lock); +} + +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) +{ + int err, ebrange, nbr; + unsigned int sigen; + struct au_dinfo *dinfo, *tmp; + struct super_block *sb; + struct inode *inode; + + DiMustWriteLock(dentry); + AuDebugOn(IS_ROOT(dentry)); + AuDebugOn(d_really_is_negative(parent)); + + sb = dentry->d_sb; + sigen = au_sigen(sb); + err = au_digen_test(parent, sigen); + if (unlikely(err)) + goto out; + + nbr = au_sbbot(sb) + 1; + dinfo = au_di(dentry); + err = au_di_realloc(dinfo, nbr, /*may_shrink*/0); + if (unlikely(err)) + goto out; + ebrange = au_dbrange_test(dentry); + if (!ebrange) + ebrange = au_do_refresh_hdentry(dentry, parent); + + if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) { + AuDebugOn(au_dbtop(dentry) < 0 && au_dbbot(dentry) >= 0); + if (d_really_is_positive(dentry)) { + inode = d_inode(dentry); + err = au_refresh_hinode_self(inode); + } + au_dbg_verify_dinode(dentry); + if (!err) + goto out_dgen; /* success */ + goto out; + } + + /* temporary dinfo */ + AuDbgDentry(dentry); + err = -ENOMEM; + tmp = au_di_alloc(sb, AuLsc_DI_TMP); + if (unlikely(!tmp)) + goto out; + au_di_swap(tmp, dinfo); + /* returns the number of positive dentries */ + /* + * if current working dir is removed, it returns an error. + * but the dentry is legal. + */ + err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); + AuDbgDentry(dentry); + au_di_swap(tmp, dinfo); + if (err == -ENOENT) + err = 0; + if (err >= 0) { + /* compare/refresh by dinfo */ + AuDbgDentry(dentry); + err = au_refresh_by_dinfo(dentry, dinfo, tmp); + au_dbg_verify_dinode(dentry); + AuTraceErr(err); + } + au_di_realloc(dinfo, nbr, /*may_shrink*/1); /* harmless if err */ + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + if (unlikely(err)) + goto out; + +out_dgen: + au_update_digen(dentry); +out: + if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) { + AuIOErr("failed refreshing %pd, %d\n", dentry, err); + AuDbgDentry(dentry); + } + AuTraceErr(err); + return err; +} + +static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags, + struct dentry *dentry, aufs_bindex_t bindex) +{ + int err, valid; + + err = 0; + if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) + goto out; + + AuDbg("b%d\n", bindex); + /* + * gave up supporting LOOKUP_CREATE/OPEN for lower fs, + * due to whiteout and branch permission. + */ + flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE + | LOOKUP_FOLLOW | LOOKUP_EXCL); + /* it may return tri-state */ + valid = h_dentry->d_op->d_revalidate(h_dentry, flags); + + if (unlikely(valid < 0)) + err = valid; + else if (!valid) + err = -EINVAL; + +out: + AuTraceErr(err); + return err; +} + +/* todo: remove this */ +static int h_d_revalidate(struct dentry *dentry, struct inode *inode, + unsigned int flags, int do_udba, int dirren) +{ + int err; + umode_t mode, h_mode; + aufs_bindex_t bindex, btail, btop, ibs, ibe; + unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile; + struct inode *h_inode, *h_cached_inode; + struct dentry *h_dentry; + struct qstr *name, *h_name; + + err = 0; + plus = 0; + mode = 0; + ibs = -1; + ibe = -1; + unhashed = !!d_unhashed(dentry); + is_root = !!IS_ROOT(dentry); + name = &dentry->d_name; + tmpfile = au_di(dentry)->di_tmpfile; + + /* + * Theoretically, REVAL test should be unnecessary in case of + * {FS,I}NOTIFY. + * But {fs,i}notify doesn't fire some necessary events, + * IN_ATTRIB for atime/nlink/pageio + * Let's do REVAL test too. + */ + if (do_udba && inode) { + mode = (inode->i_mode & S_IFMT); + plus = (inode->i_nlink > 0); + ibs = au_ibtop(inode); + ibe = au_ibbot(inode); + } + + btop = au_dbtop(dentry); + btail = btop; + if (inode && S_ISDIR(inode->i_mode)) + btail = au_dbtaildir(dentry); + for (bindex = btop; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + AuDbg("b%d, %pd\n", bindex, h_dentry); + h_nfs = !!au_test_nfs(h_dentry->d_sb); + spin_lock(&h_dentry->d_lock); + h_name = &h_dentry->d_name; + if (unlikely(do_udba + && !is_root + && ((!h_nfs + && (unhashed != !!d_unhashed(h_dentry) + || (!tmpfile && !dirren + && !au_qstreq(name, h_name)) + )) + || (h_nfs + && !(flags & LOOKUP_OPEN) + && (h_dentry->d_flags + & DCACHE_NFSFS_RENAMED))) + )) { + int h_unhashed; + + h_unhashed = d_unhashed(h_dentry); + spin_unlock(&h_dentry->d_lock); + AuDbg("unhash 0x%x 0x%x, %pd %pd\n", + unhashed, h_unhashed, dentry, h_dentry); + goto err; + } + spin_unlock(&h_dentry->d_lock); + + err = au_do_h_d_reval(h_dentry, flags, dentry, bindex); + if (unlikely(err)) + /* do not goto err, to keep the errno */ + break; + + /* todo: plink too? */ + if (!do_udba) + continue; + + /* UDBA tests */ + if (unlikely(!!inode != d_is_positive(h_dentry))) + goto err; + + h_inode = NULL; + if (d_is_positive(h_dentry)) + h_inode = d_inode(h_dentry); + h_plus = plus; + h_mode = mode; + h_cached_inode = h_inode; + if (h_inode) { + h_mode = (h_inode->i_mode & S_IFMT); + h_plus = (h_inode->i_nlink > 0); + } + if (inode && ibs <= bindex && bindex <= ibe) + h_cached_inode = au_h_iptr(inode, bindex); + + if (!h_nfs) { + if (unlikely(plus != h_plus && !tmpfile)) + goto err; + } else { + if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED) + && !is_root + && !IS_ROOT(h_dentry) + && unhashed != d_unhashed(h_dentry))) + goto err; + } + if (unlikely(mode != h_mode + || h_cached_inode != h_inode)) + goto err; + continue; + +err: + err = -EINVAL; + break; + } + + AuTraceErr(err); + return err; +} + +/* todo: consolidate with do_refresh() and au_reval_for_attr() */ +static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *parent; + + if (!au_digen_test(dentry, sigen)) + return 0; + + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + AuDebugOn(au_digen_test(parent, sigen)); + au_dbg_verify_gen(parent, sigen); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + AuTraceErr(err); + return err; +} + +int au_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *d, *parent; + + if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) + return simple_reval_dpath(dentry, sigen); + + /* slow loop, keep it simple and stupid */ + /* cf: au_cpup_dirs() */ + err = 0; + parent = NULL; + while (au_digen_test(dentry, sigen)) { + d = dentry; + while (1) { + dput(parent); + parent = dget_parent(d); + if (!au_digen_test(parent, sigen)) + break; + d = parent; + } + + if (d != dentry) + di_write_lock_child2(d); + + /* someone might update our dentry while we were sleeping */ + if (au_digen_test(d, sigen)) { + /* + * todo: consolidate with simple_reval_dpath(), + * do_refresh() and au_reval_for_attr(). + */ + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(d, parent); + di_read_unlock(parent, AuLock_IR); + } + + if (d != dentry) + di_write_unlock(d); + dput(parent); + if (unlikely(err)) + break; + } + + return err; +} + +/* + * if valid returns 1, otherwise 0. + */ +static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + int valid, err; + unsigned int sigen; + unsigned char do_udba, dirren; + struct super_block *sb; + struct inode *inode; + + /* todo: support rcu-walk? */ + if (flags & LOOKUP_RCU) + return -ECHILD; + + valid = 0; + if (unlikely(!au_di(dentry))) + goto out; + + valid = 1; + sb = dentry->d_sb; + /* + * todo: very ugly + * i_mutex of parent dir may be held, + * but we should not return 'invalid' due to busy. + */ + err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM); + if (unlikely(err)) { + valid = err; + AuTraceErr(err); + goto out; + } + inode = NULL; + if (d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (unlikely(inode && au_is_bad_inode(inode))) { + err = -EINVAL; + AuTraceErr(err); + goto out_dgrade; + } + if (unlikely(au_dbrange_test(dentry))) { + err = -EINVAL; + AuTraceErr(err); + goto out_dgrade; + } + + sigen = au_sigen(sb); + if (au_digen_test(dentry, sigen)) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_dpath(dentry, sigen); + if (unlikely(err)) { + AuTraceErr(err); + goto out_dgrade; + } + } + di_downgrade_lock(dentry, AuLock_IR); + + err = -EINVAL; + if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY)) + && inode + && !(inode->i_state && I_LINKABLE) + && (IS_DEADDIR(inode) || !inode->i_nlink)) { + AuTraceErr(err); + goto out_inval; + } + + do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE); + if (do_udba && inode) { + aufs_bindex_t btop = au_ibtop(inode); + struct inode *h_inode; + + if (btop >= 0) { + h_inode = au_h_iptr(inode, btop); + if (h_inode && au_test_higen(inode, h_inode)) { + AuTraceErr(err); + goto out_inval; + } + } + } + + dirren = !!au_opt_test(au_mntflags(sb), DIRREN); + err = h_d_revalidate(dentry, inode, flags, do_udba, dirren); + if (unlikely(!err && do_udba && au_dbtop(dentry) < 0)) { + err = -EIO; + AuDbg("both of real entry and whiteout found, %p, err %d\n", + dentry, err); + } + goto out_inval; + +out_dgrade: + di_downgrade_lock(dentry, AuLock_IR); +out_inval: + aufs_read_unlock(dentry, AuLock_IR); + AuTraceErr(err); + valid = !err; +out: + if (!valid) { + AuDbg("%pd invalid, %d\n", dentry, valid); + d_drop(dentry); + } + return valid; +} + +static void aufs_d_release(struct dentry *dentry) +{ + if (au_di(dentry)) { + au_di_fin(dentry); + au_hn_di_reinit(dentry); + } +} + +const struct dentry_operations aufs_dop = { + .d_revalidate = aufs_d_revalidate, + .d_weak_revalidate = aufs_d_revalidate, + .d_release = aufs_d_release +}; + +/* aufs_dop without d_revalidate */ +const struct dentry_operations aufs_dop_noreval = { + .d_release = aufs_d_release +}; diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h new file mode 100644 index 000000000000..c9f9c704da0a --- /dev/null +++ b/fs/aufs/dentry.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * lookup and dentry operations + */ + +#ifndef __AUFS_DENTRY_H__ +#define __AUFS_DENTRY_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include "dirren.h" +#include "rwsem.h" + +struct au_hdentry { + struct dentry *hd_dentry; + aufs_bindex_t hd_id; +}; + +struct au_dinfo { + atomic_t di_generation; + + struct au_rwsem di_rwsem; + aufs_bindex_t di_btop, di_bbot, di_bwh, di_bdiropq; + unsigned char di_tmpfile; /* to allow the different name */ + struct au_hdentry *di_hdentry; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* flags for au_lkup_dentry() */ +#define AuLkup_ALLOW_NEG 1 +#define AuLkup_IGNORE_PERM (1 << 1) +#define AuLkup_DIRREN (1 << 2) +#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name) +#define au_fset_lkup(flags, name) \ + do { (flags) |= AuLkup_##name; } while (0) +#define au_fclr_lkup(flags, name) \ + do { (flags) &= ~AuLkup_##name; } while (0) + +#ifndef CONFIG_AUFS_DIRREN +#undef AuLkup_DIRREN +#define AuLkup_DIRREN 0 +#endif + +struct au_do_lookup_args { + unsigned int flags; + mode_t type; + struct qstr whname, *name; + struct au_dr_lookup dirren; +}; + +/* ---------------------------------------------------------------------- */ + +/* dentry.c */ +extern const struct dentry_operations aufs_dop, aufs_dop_noreval; +struct au_branch; +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent); +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br); + +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, + unsigned int flags); +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh); +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent); +int au_reval_dpath(struct dentry *dentry, unsigned int sigen); +void au_refresh_dop(struct dentry *dentry, int force_reval); + +/* dinfo.c */ +void au_di_init_once(void *_di); +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc); +void au_di_free(struct au_dinfo *dinfo); +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b); +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src); +int au_di_init(struct dentry *dentry); +void au_di_fin(struct dentry *dentry); +int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink); + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc); +void di_read_unlock(struct dentry *d, int flags); +void di_downgrade_lock(struct dentry *d, int flags); +void di_write_lock(struct dentry *d, unsigned int lsc); +void di_write_unlock(struct dentry *d); +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_unlock2(struct dentry *d1, struct dentry *d2); + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex); +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex); +aufs_bindex_t au_dbtail(struct dentry *dentry); +aufs_bindex_t au_dbtaildir(struct dentry *dentry); + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry); +int au_digen_test(struct dentry *dentry, unsigned int sigen); +int au_dbrange_test(struct dentry *dentry); +void au_update_digen(struct dentry *dentry); +void au_update_dbrange(struct dentry *dentry, int do_put_zero); +void au_update_dbtop(struct dentry *dentry); +void au_update_dbbot(struct dentry *dentry); +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry); + +/* ---------------------------------------------------------------------- */ + +static inline struct au_dinfo *au_di(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for dinfo */ +enum { + AuLsc_DI_CHILD, /* child first */ + AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hnotify */ + AuLsc_DI_CHILD3, /* copyup dirs */ + AuLsc_DI_PARENT, + AuLsc_DI_PARENT2, + AuLsc_DI_PARENT3, + AuLsc_DI_TMP /* temp for replacing dinfo */ +}; + +/* + * di_read_lock_child, di_write_lock_child, + * di_read_lock_child2, di_write_lock_child2, + * di_read_lock_child3, di_write_lock_child3, + * di_read_lock_parent, di_write_lock_parent, + * di_read_lock_parent2, di_write_lock_parent2, + * di_read_lock_parent3, di_write_lock_parent3, + */ +#define AuReadLockFunc(name, lsc) \ +static inline void di_read_lock_##name(struct dentry *d, int flags) \ +{ di_read_lock(d, flags, AuLsc_DI_##lsc); } + +#define AuWriteLockFunc(name, lsc) \ +static inline void di_write_lock_##name(struct dentry *d) \ +{ di_write_lock(d, AuLsc_DI_##lsc); } + +#define AuRWLockFuncs(name, lsc) \ + AuReadLockFunc(name, lsc) \ + AuWriteLockFunc(name, lsc) + +AuRWLockFuncs(child, CHILD); +AuRWLockFuncs(child2, CHILD2); +AuRWLockFuncs(child3, CHILD3); +AuRWLockFuncs(parent, PARENT); +AuRWLockFuncs(parent2, PARENT2); +AuRWLockFuncs(parent3, PARENT3); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem) +#define DiMustAnyLock(d) AuRwMustAnyLock(&au_di(d)->di_rwsem) +#define DiMustWriteLock(d) AuRwMustWriteLock(&au_di(d)->di_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: memory barrier? */ +static inline unsigned int au_digen(struct dentry *d) +{ + return atomic_read(&au_di(d)->di_generation); +} + +static inline void au_h_dentry_init(struct au_hdentry *hdentry) +{ + hdentry->hd_dentry = NULL; +} + +static inline struct au_hdentry *au_hdentry(struct au_dinfo *di, + aufs_bindex_t bindex) +{ + return di->di_hdentry + bindex; +} + +static inline void au_hdput(struct au_hdentry *hd) +{ + if (hd) + dput(hd->hd_dentry); +} + +static inline aufs_bindex_t au_dbtop(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_btop; +} + +static inline aufs_bindex_t au_dbbot(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bbot; +} + +static inline aufs_bindex_t au_dbwh(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bwh; +} + +static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bdiropq; +} + +/* todo: hard/soft set? */ +static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_btop = bindex; +} + +static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bbot = bindex; +} + +static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + /* dbwh can be outside of btop - bbot range */ + au_di(dentry)->di_bwh = bindex; +} + +static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bdiropq = bindex; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_HNOTIFY +static inline void au_digen_dec(struct dentry *d) +{ + atomic_dec(&au_di(d)->di_generation); +} + +static inline void au_hn_di_reinit(struct dentry *dentry) +{ + dentry->d_fsdata = NULL; +} +#else +AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) +#endif /* CONFIG_AUFS_HNOTIFY */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DENTRY_H__ */ diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c new file mode 100644 index 000000000000..be959106d980 --- /dev/null +++ b/fs/aufs/dinfo.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dentry private data + */ + +#include "aufs.h" + +void au_di_init_once(void *_dinfo) +{ + struct au_dinfo *dinfo = _dinfo; + + au_rw_init(&dinfo->di_rwsem); +} + +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) +{ + struct au_dinfo *dinfo; + int nbr, i; + + dinfo = au_cache_alloc_dinfo(); + if (unlikely(!dinfo)) + goto out; + + nbr = au_sbbot(sb) + 1; + if (nbr <= 0) + nbr = 1; + dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); + if (dinfo->di_hdentry) { + au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + dinfo->di_bwh = -1; + dinfo->di_bdiropq = -1; + dinfo->di_tmpfile = 0; + for (i = 0; i < nbr; i++) + dinfo->di_hdentry[i].hd_id = -1; + goto out; + } + + au_cache_free_dinfo(dinfo); + dinfo = NULL; + +out: + return dinfo; +} + +void au_di_free(struct au_dinfo *dinfo) +{ + struct au_hdentry *p; + aufs_bindex_t bbot, bindex; + + /* dentry may not be revalidated */ + bindex = dinfo->di_btop; + if (bindex >= 0) { + bbot = dinfo->di_bbot; + p = au_hdentry(dinfo, bindex); + while (bindex++ <= bbot) + au_hdput(p++); + } + au_kfree_try_rcu(dinfo->di_hdentry); + au_cache_free_dinfo(dinfo); +} + +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) +{ + struct au_hdentry *p; + aufs_bindex_t bi; + + AuRwMustWriteLock(&a->di_rwsem); + AuRwMustWriteLock(&b->di_rwsem); + +#define DiSwap(v, name) \ + do { \ + v = a->di_##name; \ + a->di_##name = b->di_##name; \ + b->di_##name = v; \ + } while (0) + + DiSwap(p, hdentry); + DiSwap(bi, btop); + DiSwap(bi, bbot); + DiSwap(bi, bwh); + DiSwap(bi, bdiropq); + /* smp_mb(); */ + +#undef DiSwap +} + +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) +{ + AuRwMustWriteLock(&dst->di_rwsem); + AuRwMustWriteLock(&src->di_rwsem); + + dst->di_btop = src->di_btop; + dst->di_bbot = src->di_bbot; + dst->di_bwh = src->di_bwh; + dst->di_bdiropq = src->di_bdiropq; + /* smp_mb(); */ +} + +int au_di_init(struct dentry *dentry) +{ + int err; + struct super_block *sb; + struct au_dinfo *dinfo; + + err = 0; + sb = dentry->d_sb; + dinfo = au_di_alloc(sb, AuLsc_DI_CHILD); + if (dinfo) { + atomic_set(&dinfo->di_generation, au_sigen(sb)); + /* smp_mb(); */ /* atomic_set */ + dentry->d_fsdata = dinfo; + } else + err = -ENOMEM; + + return err; +} + +void au_di_fin(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + + dinfo = au_di(dentry); + AuRwDestroy(&dinfo->di_rwsem); + au_di_free(dinfo); +} + +int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink) +{ + int err, sz; + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + err = -ENOMEM; + sz = sizeof(*hdp) * (dinfo->di_bbot + 1); + if (!sz) + sz = sizeof(*hdp); + hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS, + may_shrink); + if (hdp) { + dinfo->di_hdentry = hdp; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void do_ii_write_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_write_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_write_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_write_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_write_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_write_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_write_lock_parent3(inode); + break; + default: + BUG(); + } +} + +static void do_ii_read_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_read_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_read_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_read_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_read_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_read_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_read_lock_parent3(inode); + break; + default: + BUG(); + } +} + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc) +{ + struct inode *inode; + + au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d_really_is_positive(d)) { + inode = d_inode(d); + if (au_ftest_lock(flags, IW)) + do_ii_write_lock(inode, lsc); + else if (au_ftest_lock(flags, IR)) + do_ii_read_lock(inode, lsc); + } +} + +void di_read_unlock(struct dentry *d, int flags) +{ + struct inode *inode; + + if (d_really_is_positive(d)) { + inode = d_inode(d); + if (au_ftest_lock(flags, IW)) { + au_dbg_verify_dinode(d); + ii_write_unlock(inode); + } else if (au_ftest_lock(flags, IR)) { + au_dbg_verify_dinode(d); + ii_read_unlock(inode); + } + } + au_rw_read_unlock(&au_di(d)->di_rwsem); +} + +void di_downgrade_lock(struct dentry *d, int flags) +{ + if (d_really_is_positive(d) && au_ftest_lock(flags, IR)) + ii_downgrade_lock(d_inode(d)); + au_rw_dgrade_lock(&au_di(d)->di_rwsem); +} + +void di_write_lock(struct dentry *d, unsigned int lsc) +{ + au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d_really_is_positive(d)) + do_ii_write_lock(d_inode(d), lsc); +} + +void di_write_unlock(struct dentry *d) +{ + au_dbg_verify_dinode(d); + if (d_really_is_positive(d)) + ii_write_unlock(d_inode(d)); + au_rw_write_unlock(&au_di(d)->di_rwsem); +} + +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d_inode(d1) == d_inode(d2) + || d1->d_sb != d2->d_sb); + + if ((isdir && au_test_subdir(d1, d2)) + || d1 < d2) { + di_write_lock_child(d1); + di_write_lock_child2(d2); + } else { + di_write_lock_child(d2); + di_write_lock_child2(d1); + } +} + +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d_inode(d1) == d_inode(d2) + || d1->d_sb != d2->d_sb); + + if ((isdir && au_test_subdir(d1, d2)) + || d1 < d2) { + di_write_lock_parent(d1); + di_write_lock_parent2(d2); + } else { + di_write_lock_parent(d2); + di_write_lock_parent2(d1); + } +} + +void di_write_unlock2(struct dentry *d1, struct dentry *d2) +{ + di_write_unlock(d1); + if (d_inode(d1) == d_inode(d2)) + au_rw_write_unlock(&au_di(d2)->di_rwsem); + else + di_write_unlock(d2); +} + +/* ---------------------------------------------------------------------- */ + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *d; + + DiMustAnyLock(dentry); + + if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) + return NULL; + AuDebugOn(bindex < 0); + d = au_hdentry(au_di(dentry), bindex)->hd_dentry; + AuDebugOn(d && au_dcount(d) <= 0); + return d; +} + +/* + * extended version of au_h_dptr(). + * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or + * error. + */ +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *h_dentry; + struct inode *inode, *h_inode; + + AuDebugOn(d_really_is_negative(dentry)); + + h_dentry = NULL; + if (au_dbtop(dentry) <= bindex + && bindex <= au_dbbot(dentry)) + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && !au_d_linkable(h_dentry)) { + dget(h_dentry); + goto out; /* success */ + } + + inode = d_inode(dentry); + AuDebugOn(bindex < au_ibtop(inode)); + AuDebugOn(au_ibbot(inode) < bindex); + h_inode = au_h_iptr(inode, bindex); + h_dentry = d_find_alias(h_inode); + if (h_dentry) { + if (!IS_ERR(h_dentry)) { + if (!au_d_linkable(h_dentry)) + goto out; /* success */ + dput(h_dentry); + } else + goto out; + } + + if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) { + h_dentry = au_plink_lkup(inode, bindex); + AuDebugOn(!h_dentry); + if (!IS_ERR(h_dentry)) { + if (!au_d_hashed_positive(h_dentry)) + goto out; /* success */ + dput(h_dentry); + h_dentry = NULL; + } + } + +out: + AuDbgDentry(h_dentry); + return h_dentry; +} + +aufs_bindex_t au_dbtail(struct dentry *dentry) +{ + aufs_bindex_t bbot, bwh; + + bbot = au_dbbot(dentry); + if (0 <= bbot) { + bwh = au_dbwh(dentry); + if (!bwh) + return bwh; + if (0 < bwh && bwh < bbot) + return bwh - 1; + } + return bbot; +} + +aufs_bindex_t au_dbtaildir(struct dentry *dentry) +{ + aufs_bindex_t bbot, bopq; + + bbot = au_dbtail(dentry); + if (0 <= bbot) { + bopq = au_dbdiropq(dentry); + if (0 <= bopq && bopq < bbot) + bbot = bopq; + } + return bbot; +} + +/* ---------------------------------------------------------------------- */ + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry) +{ + struct au_dinfo *dinfo; + struct au_hdentry *hd; + struct au_branch *br; + + DiMustWriteLock(dentry); + + dinfo = au_di(dentry); + hd = au_hdentry(dinfo, bindex); + au_hdput(hd); + hd->hd_dentry = h_dentry; + if (h_dentry) { + br = au_sbr(dentry->d_sb, bindex); + hd->hd_id = br->br_id; + } +} + +int au_dbrange_test(struct dentry *dentry) +{ + int err; + aufs_bindex_t btop, bbot; + + err = 0; + btop = au_dbtop(dentry); + bbot = au_dbbot(dentry); + if (btop >= 0) + AuDebugOn(bbot < 0 && btop > bbot); + else { + err = -EIO; + AuDebugOn(bbot >= 0); + } + + return err; +} + +int au_digen_test(struct dentry *dentry, unsigned int sigen) +{ + int err; + + err = 0; + if (unlikely(au_digen(dentry) != sigen + || au_iigen_test(d_inode(dentry), sigen))) + err = -EIO; + + return err; +} + +void au_update_digen(struct dentry *dentry) +{ + atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); + /* smp_mb(); */ /* atomic_set */ +} + +void au_update_dbrange(struct dentry *dentry, int do_put_zero) +{ + struct au_dinfo *dinfo; + struct dentry *h_d; + struct au_hdentry *hdp; + aufs_bindex_t bindex, bbot; + + DiMustWriteLock(dentry); + + dinfo = au_di(dentry); + if (!dinfo || dinfo->di_btop < 0) + return; + + if (do_put_zero) { + bbot = dinfo->di_bbot; + bindex = dinfo->di_btop; + hdp = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, hdp++) { + h_d = hdp->hd_dentry; + if (h_d && d_is_negative(h_d)) + au_set_h_dptr(dentry, bindex, NULL); + } + } + + dinfo->di_btop = 0; + hdp = au_hdentry(dinfo, dinfo->di_btop); + for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++) + if (hdp->hd_dentry) + break; + if (dinfo->di_btop > dinfo->di_bbot) { + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + return; + } + + hdp = au_hdentry(dinfo, dinfo->di_bbot); + for (; dinfo->di_bbot >= 0; dinfo->di_bbot--, hdp--) + if (hdp->hd_dentry) + break; + AuDebugOn(dinfo->di_btop > dinfo->di_bbot || dinfo->di_bbot < 0); +} + +void au_update_dbtop(struct dentry *dentry) +{ + aufs_bindex_t bindex, bbot; + struct dentry *h_dentry; + + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (d_is_positive(h_dentry)) { + au_set_dbtop(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +void au_update_dbbot(struct dentry *dentry) +{ + aufs_bindex_t bindex, btop; + struct dentry *h_dentry; + + btop = au_dbtop(dentry); + for (bindex = au_dbbot(dentry); bindex >= btop; bindex--) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (d_is_positive(h_dentry)) { + au_set_dbbot(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) +{ + aufs_bindex_t bindex, bbot; + + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) + if (au_h_dptr(dentry, bindex) == h_dentry) + return bindex; + return -1; +} diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c new file mode 100644 index 000000000000..0bcb39ee7255 --- /dev/null +++ b/fs/aufs/dir.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * directory operations + */ + +#include <linux/fs_stack.h> +#include <linux/iversion.h> +#include "aufs.h" + +void au_add_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink += h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink += 2; + smp_mb(); /* for i_nlink */ + /* 0 can happen in revaliding */ + set_nlink(dir, nlink); +} + +void au_sub_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink -= h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink -= 2; + smp_mb(); /* for i_nlink */ + /* nlink == 0 means the branch-fs is broken */ + set_nlink(dir, nlink); +} + +loff_t au_dir_size(struct file *file, struct dentry *dentry) +{ + loff_t sz; + aufs_bindex_t bindex, bbot; + struct file *h_file; + struct dentry *h_dentry; + + sz = 0; + if (file) { + AuDebugOn(!d_is_dir(file->f_path.dentry)); + + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); + bindex <= bbot && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file && file_inode(h_file)) + sz += vfsub_f_size_read(h_file); + } + } else { + AuDebugOn(!dentry); + AuDebugOn(!d_is_dir(dentry)); + + bbot = au_dbtaildir(dentry); + for (bindex = au_dbtop(dentry); + bindex <= bbot && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) + sz += i_size_read(d_inode(h_dentry)); + } + } + if (sz < KMALLOC_MAX_SIZE) + sz = roundup_pow_of_two(sz); + if (sz > KMALLOC_MAX_SIZE) + sz = KMALLOC_MAX_SIZE; + else if (sz < NAME_MAX) { + BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); + sz = AUFS_RDBLK_DEF; + } + return sz; +} + +struct au_dir_ts_arg { + struct dentry *dentry; + aufs_bindex_t brid; +}; + +static void au_do_dir_ts(void *arg) +{ + struct au_dir_ts_arg *a = arg; + struct au_dtime dt; + struct path h_path; + struct inode *dir, *h_dir; + struct super_block *sb; + struct au_branch *br; + struct au_hinode *hdir; + int err; + aufs_bindex_t btop, bindex; + + sb = a->dentry->d_sb; + if (d_really_is_negative(a->dentry)) + goto out; + /* no dir->i_mutex lock */ + aufs_read_lock(a->dentry, AuLock_DW); /* noflush */ + + dir = d_inode(a->dentry); + btop = au_ibtop(dir); + bindex = au_br_index(sb, a->brid); + if (bindex < btop) + goto out_unlock; + + br = au_sbr(sb, bindex); + h_path.dentry = au_h_dptr(a->dentry, bindex); + if (!h_path.dentry) + goto out_unlock; + h_path.mnt = au_br_mnt(br); + au_dtime_store(&dt, a->dentry, &h_path); + + br = au_sbr(sb, btop); + if (!au_br_writable(br->br_perm)) + goto out_unlock; + h_path.dentry = au_h_dptr(a->dentry, btop); + h_path.mnt = au_br_mnt(br); + err = vfsub_mnt_want_write(h_path.mnt); + if (err) + goto out_unlock; + hdir = au_hi(dir, btop); + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + h_dir = au_h_iptr(dir, btop); + if (h_dir->i_nlink + && timespec64_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) { + dt.dt_h_path = h_path; + au_dtime_revert(&dt); + } + au_hn_inode_unlock(hdir); + vfsub_mnt_drop_write(h_path.mnt); + au_cpup_attr_timesizes(dir); + +out_unlock: + aufs_read_unlock(a->dentry, AuLock_DW); +out: + dput(a->dentry); + au_nwt_done(&au_sbi(sb)->si_nowait); + au_kfree_try_rcu(arg); +} + +void au_dir_ts(struct inode *dir, aufs_bindex_t bindex) +{ + int perm, wkq_err; + aufs_bindex_t btop; + struct au_dir_ts_arg *arg; + struct dentry *dentry; + struct super_block *sb; + + IMustLock(dir); + + dentry = d_find_any_alias(dir); + AuDebugOn(!dentry); + sb = dentry->d_sb; + btop = au_ibtop(dir); + if (btop == bindex) { + au_cpup_attr_timesizes(dir); + goto out; + } + + perm = au_sbr_perm(sb, btop); + if (!au_br_writable(perm)) + goto out; + + arg = kmalloc(sizeof(*arg), GFP_NOFS); + if (!arg) + goto out; + + arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */ + arg->brid = au_sbr_id(sb, bindex); + wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0); + if (unlikely(wkq_err)) { + pr_err("wkq %d\n", wkq_err); + dput(dentry); + au_kfree_try_rcu(arg); + } + +out: + dput(dentry); +} + +/* ---------------------------------------------------------------------- */ + +static int reopen_dir(struct file *file) +{ + int err; + unsigned int flags; + aufs_bindex_t bindex, btail, btop; + struct dentry *dentry, *h_dentry; + struct file *h_file; + + /* open all lower dirs */ + dentry = file->f_path.dentry; + btop = au_dbtop(dentry); + for (bindex = au_fbtop(file); bindex < btop; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbtop(file, btop); + + btail = au_dbtaildir(dentry); + for (bindex = au_fbbot_dir(file); btail < bindex; bindex--) + au_set_h_fptr(file, bindex, NULL); + au_set_fbbot_dir(file, btail); + + flags = vfsub_file_flags(file); + for (bindex = btop; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_file = au_hf_dir(file, bindex); + if (h_file) + continue; + + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; /* close all? */ + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + err = 0; + +out: + return err; +} + +static int do_open_dir(struct file *file, int flags, struct file *h_file) +{ + int err; + aufs_bindex_t bindex, btail; + struct dentry *dentry, *h_dentry; + struct vfsmount *mnt; + + FiMustWriteLock(file); + AuDebugOn(h_file); + + err = 0; + mnt = file->f_path.mnt; + dentry = file->f_path.dentry; + file->f_version = inode_query_iversion(d_inode(dentry)); + bindex = au_dbtop(dentry); + au_set_fbtop(file, bindex); + btail = au_dbtaildir(dentry); + au_set_fbbot_dir(file, btail); + for (; !err && bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + err = vfsub_test_mntns(mnt, h_dentry->d_sb); + if (unlikely(err)) + break; + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + break; + } + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + if (!err) + return 0; /* success */ + + /* close all */ + for (bindex = au_fbtop(file); bindex <= btail; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbtop(file, -1); + au_set_fbbot_dir(file, -1); + + return err; +} + +static int aufs_open_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + struct au_fidir *fidir; + + err = -ENOMEM; + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + fidir = au_fidir_alloc(sb); + if (fidir) { + struct au_do_open_args args = { + .open = do_open_dir, + .fidir = fidir + }; + err = au_do_open(file, &args); + if (unlikely(err)) + au_kfree_rcu(fidir); + } + si_read_unlock(sb); + return err; +} + +static int aufs_release_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + struct au_vdir *vdir_cache; + struct au_finfo *finfo; + struct au_fidir *fidir; + struct au_hfile *hf; + aufs_bindex_t bindex, bbot; + + finfo = au_fi(file); + fidir = finfo->fi_hdir; + if (fidir) { + au_hbl_del(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + vdir_cache = fidir->fd_vdir_cache; /* lock-free */ + if (vdir_cache) + au_vdir_free(vdir_cache); + + bindex = finfo->fi_btop; + if (bindex >= 0) { + hf = fidir->fd_hfile + bindex; + /* + * calls fput() instead of filp_close(), + * since no dnotify or lock for the lower file. + */ + bbot = fidir->fd_bbot; + for (; bindex <= bbot; bindex++, hf++) + if (hf->hf_file) + au_hfput(hf, /*execed*/0); + } + au_kfree_rcu(fidir); + finfo->fi_hdir = NULL; + } + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_dir(struct file *file, fl_owner_t id) +{ + int err; + aufs_bindex_t bindex, bbot; + struct file *h_file; + + err = 0; + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file) + err = vfsub_flush(h_file, id); + } + return err; +} + +static int aufs_flush_dir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_dir); +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) +{ + int err; + aufs_bindex_t bbot, bindex; + struct inode *inode; + struct super_block *sb; + + err = 0; + sb = dentry->d_sb; + inode = d_inode(dentry); + IMustLock(inode); + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) { + struct path h_path; + + if (au_test_ro(sb, bindex, inode)) + continue; + h_path.dentry = au_h_dptr(dentry, bindex); + if (!h_path.dentry) + continue; + + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_fsync(NULL, &h_path, datasync); + } + + return err; +} + +static int au_do_fsync_dir(struct file *file, int datasync) +{ + int err; + aufs_bindex_t bbot, bindex; + struct file *h_file; + struct super_block *sb; + struct inode *inode; + + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); + if (unlikely(err)) + goto out; + + inode = file_inode(file); + sb = inode->i_sb; + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { + h_file = au_hf_dir(file, bindex); + if (!h_file || au_test_ro(sb, bindex, inode)) + continue; + + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + } + +out: + return err; +} + +/* + * @file may be NULL + */ +static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct dentry *dentry; + struct inode *inode; + struct super_block *sb; + + err = 0; + dentry = file->f_path.dentry; + inode = d_inode(dentry); + inode_lock(inode); + sb = dentry->d_sb; + si_noflush_read_lock(sb); + if (file) + err = au_do_fsync_dir(file, datasync); + else { + di_write_lock_child(dentry); + err = au_do_fsync_dir_no_file(dentry, datasync); + } + au_cpup_attr_timesizes(inode); + di_write_unlock(dentry); + if (file) + fi_write_unlock(file); + + si_read_unlock(sb); + inode_unlock(inode); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_iterate_shared(struct file *file, struct dir_context *ctx) +{ + int err; + struct dentry *dentry; + struct inode *inode, *h_inode; + struct super_block *sb; + + AuDbg("%pD, ctx{%ps, %llu}\n", file, ctx->actor, ctx->pos); + + dentry = file->f_path.dentry; + inode = d_inode(dentry); + IMustLock(inode); + + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); + if (unlikely(err)) + goto out; + err = au_alive_dir(dentry); + if (!err) + err = au_vdir_init(file); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + if (!au_test_nfsd()) { + err = au_vdir_fill_de(file, ctx); + fsstack_copy_attr_atime(inode, h_inode); + } else { + /* + * nfsd filldir may call lookup_one_len(), vfs_getattr(), + * encode_fh() and others. + */ + atomic_inc(&h_inode->i_count); + di_read_unlock(dentry, AuLock_IR); + si_read_unlock(sb); + err = au_vdir_fill_de(file, ctx); + fsstack_copy_attr_atime(inode, h_inode); + fi_write_unlock(file); + iput(h_inode); + + AuTraceErr(err); + return err; + } + +out_unlock: + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +#define AuTestEmpty_WHONLY 1 +#define AuTestEmpty_CALLED (1 << 1) +#define AuTestEmpty_SHWH (1 << 2) +#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) +#define au_fset_testempty(flags, name) \ + do { (flags) |= AuTestEmpty_##name; } while (0) +#define au_fclr_testempty(flags, name) \ + do { (flags) &= ~AuTestEmpty_##name; } while (0) + +#ifndef CONFIG_AUFS_SHWH +#undef AuTestEmpty_SHWH +#define AuTestEmpty_SHWH 0 +#endif + +struct test_empty_arg { + struct dir_context ctx; + struct au_nhash *whlist; + unsigned int flags; + int err; + aufs_bindex_t bindex; +}; + +static int test_empty_cb(struct dir_context *ctx, const char *__name, + int namelen, loff_t offset __maybe_unused, u64 ino, + unsigned int d_type) +{ + struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg, + ctx); + char *name = (void *)__name; + + arg->err = 0; + au_fset_testempty(arg->flags, CALLED); + /* smp_mb(); */ + if (name[0] == '.' + && (namelen == 1 || (name[1] == '.' && namelen == 2))) + goto out; /* success */ + + if (namelen <= AUFS_WH_PFX_LEN + || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + if (au_ftest_testempty(arg->flags, WHONLY) + && !au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = -ENOTEMPTY; + goto out; + } + + name += AUFS_WH_PFX_LEN; + namelen -= AUFS_WH_PFX_LEN; + if (!au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = au_nhash_append_wh + (arg->whlist, name, namelen, ino, d_type, arg->bindex, + au_ftest_testempty(arg->flags, SHWH)); + +out: + /* smp_mb(); */ + AuTraceErr(arg->err); + return arg->err; +} + +static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err; + struct file *h_file; + struct au_branch *br; + + h_file = au_h_open(dentry, arg->bindex, + O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE, + /*file*/NULL, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = 0; + if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) + && !file_inode(h_file)->i_nlink) + goto out_put; + + do { + arg->err = 0; + au_fclr_testempty(arg->flags, CALLED); + /* smp_mb(); */ + err = vfsub_iterate_dir(h_file, &arg->ctx); + if (err >= 0) + err = arg->err; + } while (!err && au_ftest_testempty(arg->flags, CALLED)); + +out_put: + fput(h_file); + br = au_sbr(dentry->d_sb, arg->bindex); + au_lcnt_dec(&br->br_nfiles); +out: + return err; +} + +struct do_test_empty_args { + int *errp; + struct dentry *dentry; + struct test_empty_arg *arg; +}; + +static void call_do_test_empty(void *args) +{ + struct do_test_empty_args *a = args; + *a->errp = do_test_empty(a->dentry, a->arg); +} + +static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err, wkq_err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = au_h_dptr(dentry, arg->bindex); + h_inode = d_inode(h_dentry); + /* todo: i_mode changes anytime? */ + inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); + err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); + inode_unlock_shared(h_inode); + if (!err) + err = do_test_empty(dentry, arg); + else { + struct do_test_empty_args args = { + .errp = &err, + .dentry = dentry, + .arg = arg + }; + unsigned int flags = arg->flags; + + wkq_err = au_wkq_wait(call_do_test_empty, &args); + if (unlikely(wkq_err)) + err = wkq_err; + arg->flags = flags; + } + + return err; +} + +int au_test_empty_lower(struct dentry *dentry) +{ + int err; + unsigned int rdhash; + aufs_bindex_t bindex, btop, btail; + struct au_nhash whlist; + struct test_empty_arg arg = { + .ctx = { + .actor = test_empty_cb + } + }; + int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg); + + SiMustAnyLock(dentry->d_sb); + + rdhash = au_sbi(dentry->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry)); + err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + + arg.flags = 0; + arg.whlist = &whlist; + btop = au_dbtop(dentry); + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + test_empty = do_test_empty; + if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)) + test_empty = sio_test_empty; + arg.bindex = btop; + err = test_empty(dentry, &arg); + if (unlikely(err)) + goto out_whlist; + + au_fset_testempty(arg.flags, WHONLY); + btail = au_dbtaildir(dentry); + for (bindex = btop + 1; !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) { + arg.bindex = bindex; + err = test_empty(dentry, &arg); + } + } + +out_whlist: + au_nhash_wh_free(&whlist); +out: + return err; +} + +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) +{ + int err; + struct test_empty_arg arg = { + .ctx = { + .actor = test_empty_cb + } + }; + aufs_bindex_t bindex, btail; + + err = 0; + arg.whlist = whlist; + arg.flags = AuTestEmpty_WHONLY; + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + btail = au_dbtaildir(dentry); + for (bindex = au_dbtop(dentry); !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) { + arg.bindex = bindex; + err = sio_test_empty(dentry, &arg); + } + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_dir_fop = { + .owner = THIS_MODULE, + .llseek = default_llseek, + .read = generic_read_dir, + .iterate_shared = aufs_iterate_shared, + .unlocked_ioctl = aufs_ioctl_dir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_compat_ioctl_dir, +#endif + .open = aufs_open_dir, + .release = aufs_release_dir, + .flush = aufs_flush_dir, + .fsync = aufs_fsync_dir +}; diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h new file mode 100644 index 000000000000..e44c2a1a849b --- /dev/null +++ b/fs/aufs/dir.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * directory operations + */ + +#ifndef __AUFS_DIR_H__ +#define __AUFS_DIR_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> + +/* ---------------------------------------------------------------------- */ + +/* need to be faster and smaller */ + +struct au_nhash { + unsigned int nh_num; + struct hlist_head *nh_head; +}; + +struct au_vdir_destr { + unsigned char len; + unsigned char name[]; +} __packed; + +struct au_vdir_dehstr { + struct hlist_node hash; + struct au_vdir_destr *str; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +struct au_vdir_de { + ino_t de_ino; + unsigned char de_type; + /* caution: packed */ + struct au_vdir_destr de_str; +} __packed; + +struct au_vdir_wh { + struct hlist_node wh_hash; +#ifdef CONFIG_AUFS_SHWH + ino_t wh_ino; + aufs_bindex_t wh_bindex; + unsigned char wh_type; +#else + aufs_bindex_t wh_bindex; +#endif + /* caution: packed */ + struct au_vdir_destr wh_str; +} __packed; + +union au_vdir_deblk_p { + unsigned char *deblk; + struct au_vdir_de *de; +}; + +struct au_vdir { + unsigned char **vd_deblk; + unsigned long vd_nblk; + struct { + unsigned long ul; + union au_vdir_deblk_p p; + } vd_last; + + u64 vd_version; + unsigned int vd_deblk_sz; + unsigned long vd_jiffy; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* dir.c */ +extern const struct file_operations aufs_dir_fop; +void au_add_nlink(struct inode *dir, struct inode *h_dir); +void au_sub_nlink(struct inode *dir, struct inode *h_dir); +loff_t au_dir_size(struct file *file, struct dentry *dentry); +void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc); +int au_test_empty_lower(struct dentry *dentry); +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist); + +/* vdir.c */ +unsigned int au_rdhash_est(loff_t sz); +int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp); +void au_nhash_wh_free(struct au_nhash *whlist); +int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, + int limit); +int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen); +int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, + unsigned int d_type, aufs_bindex_t bindex, + unsigned char shwh); +void au_vdir_free(struct au_vdir *vdir); +int au_vdir_init(struct file *file); +int au_vdir_fill_de(struct file *file, struct dir_context *ctx); + +/* ioctl.c */ +long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); + +#ifdef CONFIG_AUFS_RDU +/* rdu.c */ +long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#endif +#else +AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file, + unsigned int cmd, unsigned long arg) +#ifdef CONFIG_COMPAT +AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file, + unsigned int cmd, unsigned long arg) +#endif +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DIR_H__ */ diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c new file mode 100644 index 000000000000..ba4bf56cfb87 --- /dev/null +++ b/fs/aufs/dirren.c @@ -0,0 +1,1316 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2017-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * special handling in renaming a directory + * in order to support looking-up the before-renamed name on the lower readonly + * branches + */ + +#include <linux/byteorder/generic.h> +#include "aufs.h" + +static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent) +{ + int idx; + + idx = au_dr_ihash(ent->dr_h_ino); + au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx); +} + +static int au_dr_hino_test_empty(struct au_dr_br *dr) +{ + int ret, i; + struct hlist_bl_head *hbl; + + ret = 1; + for (i = 0; ret && i < AuDirren_NHASH; i++) { + hbl = dr->dr_h_ino + i; + hlist_bl_lock(hbl); + ret &= hlist_bl_empty(hbl); + hlist_bl_unlock(hbl); + } + + return ret; +} + +static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino) +{ + struct au_dr_hino *found, *ent; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + int idx; + + found = NULL; + idx = au_dr_ihash(ino); + hbl = dr->dr_h_ino + idx; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) + if (ent->dr_h_ino == ino) { + found = ent; + break; + } + hlist_bl_unlock(hbl); + + return found; +} + +int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino, + struct au_dr_hino *add_ent) +{ + int found, idx; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_dr_hino *ent; + + found = 0; + idx = au_dr_ihash(ino); + hbl = dr->dr_h_ino + idx; +#if 0 /* debug print */ + { + struct hlist_bl_node *tmp; + + hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) + AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino); + } +#endif + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) + if (ent->dr_h_ino == ino) { + found = 1; + break; + } + if (!found && add_ent) + hlist_bl_add_head(&add_ent->dr_hnode, hbl); + hlist_bl_unlock(hbl); + + if (!found && add_ent) + AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino); + + return found; +} + +void au_dr_hino_free(struct au_dr_br *dr) +{ + int i; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos, *tmp; + struct au_dr_hino *ent; + + /* SiMustWriteLock(sb); */ + + for (i = 0; i < AuDirren_NHASH; i++) { + hbl = dr->dr_h_ino + i; + /* no spinlock since sbinfo must be write-locked */ + hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) + au_kfree_rcu(ent); + INIT_HLIST_BL_HEAD(hbl); + } +} + +/* returns the number of inodes or an error */ +static int au_dr_hino_store(struct super_block *sb, struct au_branch *br, + struct file *hinofile) +{ + int err, i; + ssize_t ssz; + loff_t pos, oldsize; + __be64 u64; + struct inode *hinoinode; + struct hlist_bl_head *hbl; + struct hlist_bl_node *n1, *n2; + struct au_dr_hino *ent; + + SiMustWriteLock(sb); + AuDebugOn(!au_br_writable(br->br_perm)); + + hinoinode = file_inode(hinofile); + oldsize = i_size_read(hinoinode); + + err = 0; + pos = 0; + hbl = br->br_dirren.dr_h_ino; + for (i = 0; !err && i < AuDirren_NHASH; i++, hbl++) { + /* no bit-lock since sbinfo must be write-locked */ + hlist_bl_for_each_entry_safe(ent, n1, n2, hbl, dr_hnode) { + AuDbg("hi%llu, %pD2\n", + (unsigned long long)ent->dr_h_ino, hinofile); + u64 = cpu_to_be64(ent->dr_h_ino); + ssz = vfsub_write_k(hinofile, &u64, sizeof(u64), &pos); + if (ssz == sizeof(u64)) + continue; + + /* write error */ + pr_err("ssz %zd, %pD2\n", ssz, hinofile); + err = -ENOSPC; + if (ssz < 0) + err = ssz; + break; + } + } + /* regardless the error */ + if (pos < oldsize) { + err = vfsub_trunc(&hinofile->f_path, pos, /*attr*/0, hinofile); + AuTraceErr(err); + } + + AuTraceErr(err); + return err; +} + +static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile) +{ + int err, hidx; + ssize_t ssz; + size_t sz, n; + loff_t pos; + uint64_t u64; + struct au_dr_hino *ent; + struct inode *hinoinode; + struct hlist_bl_head *hbl; + + err = 0; + pos = 0; + hbl = dr->dr_h_ino; + hinoinode = file_inode(hinofile); + sz = i_size_read(hinoinode); + AuDebugOn(sz % sizeof(u64)); + n = sz / sizeof(u64); + while (n--) { + ssz = vfsub_read_k(hinofile, &u64, sizeof(u64), &pos); + if (unlikely(ssz != sizeof(u64))) { + pr_err("ssz %zd, %pD2\n", ssz, hinofile); + err = -EINVAL; + if (ssz < 0) + err = ssz; + goto out_free; + } + + ent = kmalloc(sizeof(*ent), GFP_NOFS); + if (!ent) { + err = -ENOMEM; + AuTraceErr(err); + goto out_free; + } + ent->dr_h_ino = be64_to_cpu((__force __be64)u64); + AuDbg("hi%llu, %pD2\n", + (unsigned long long)ent->dr_h_ino, hinofile); + hidx = au_dr_ihash(ent->dr_h_ino); + au_hbl_add(&ent->dr_hnode, hbl + hidx); + } + goto out; /* success */ + +out_free: + au_dr_hino_free(dr); +out: + AuTraceErr(err); + return err; +} + +/* + * @bindex/@br is a switch to distinguish whether suspending hnotify or not. + * @path is a switch to distinguish load and store. + */ +static int au_dr_hino(struct super_block *sb, aufs_bindex_t bindex, + struct au_branch *br, const struct path *path) +{ + int err, flags; + unsigned char load, suspend; + struct file *hinofile; + struct au_hinode *hdir; + struct inode *dir, *delegated; + struct path hinopath; + struct qstr hinoname = QSTR_INIT(AUFS_WH_DR_BRHINO, + sizeof(AUFS_WH_DR_BRHINO) - 1); + + AuDebugOn(bindex < 0 && !br); + AuDebugOn(bindex >= 0 && br); + + err = -EINVAL; + suspend = !br; + if (suspend) + br = au_sbr(sb, bindex); + load = !!path; + if (!load) { + path = &br->br_path; + AuDebugOn(!au_br_writable(br->br_perm)); + if (unlikely(!au_br_writable(br->br_perm))) + goto out; + } + + hdir = NULL; + if (suspend) { + dir = d_inode(sb->s_root); + hdir = au_hinode(au_ii(dir), bindex); + dir = hdir->hi_inode; + au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); + } else { + dir = d_inode(path->dentry); + inode_lock_nested(dir, AuLsc_I_CHILD); + } + hinopath.dentry = vfsub_lkup_one(&hinoname, path->dentry); + err = PTR_ERR(hinopath.dentry); + if (IS_ERR(hinopath.dentry)) + goto out_unlock; + + err = 0; + flags = O_RDONLY; + if (load) { + if (d_is_negative(hinopath.dentry)) + goto out_dput; /* success */ + } else { + if (au_dr_hino_test_empty(&br->br_dirren)) { + if (d_is_positive(hinopath.dentry)) { + delegated = NULL; + err = vfsub_unlink(dir, &hinopath, &delegated, + /*force*/0); + AuTraceErr(err); + if (unlikely(err)) + pr_err("ignored err %d, %pd2\n", + err, hinopath.dentry); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + err = 0; + } + goto out_dput; + } else if (!d_is_positive(hinopath.dentry)) { + err = vfsub_create(dir, &hinopath, 0600, + /*want_excl*/false); + AuTraceErr(err); + if (unlikely(err)) + goto out_dput; + } + flags = O_WRONLY; + } + hinopath.mnt = path->mnt; + hinofile = vfsub_dentry_open(&hinopath, flags); + if (suspend) + au_hn_inode_unlock(hdir); + else + inode_unlock(dir); + dput(hinopath.dentry); + AuTraceErrPtr(hinofile); + if (IS_ERR(hinofile)) { + err = PTR_ERR(hinofile); + goto out; + } + + if (load) + err = au_dr_hino_load(&br->br_dirren, hinofile); + else + err = au_dr_hino_store(sb, br, hinofile); + fput(hinofile); + goto out; + +out_dput: + dput(hinopath.dentry); +out_unlock: + if (suspend) + au_hn_inode_unlock(hdir); + else + inode_unlock(dir); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path) +{ + int err; + struct kstatfs kstfs; + dev_t dev; + struct dentry *dentry; + struct super_block *sb; + + err = vfs_statfs((void *)path, &kstfs); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + /* todo: support for UUID */ + + if (kstfs.f_fsid.val[0] || kstfs.f_fsid.val[1]) { + brid->type = AuBrid_FSID; + brid->fsid = kstfs.f_fsid; + } else { + dentry = path->dentry; + sb = dentry->d_sb; + dev = sb->s_dev; + if (dev) { + brid->type = AuBrid_DEV; + brid->dev = dev; + } + } + +out: + return err; +} + +int au_dr_br_init(struct super_block *sb, struct au_branch *br, + const struct path *path) +{ + int err, i; + struct au_dr_br *dr; + struct hlist_bl_head *hbl; + + dr = &br->br_dirren; + hbl = dr->dr_h_ino; + for (i = 0; i < AuDirren_NHASH; i++, hbl++) + INIT_HLIST_BL_HEAD(hbl); + + err = au_dr_brid_init(&dr->dr_brid, path); + if (unlikely(err)) + goto out; + + if (au_opt_test(au_mntflags(sb), DIRREN)) + err = au_dr_hino(sb, /*bindex*/-1, br, path); + +out: + AuTraceErr(err); + return err; +} + +int au_dr_br_fin(struct super_block *sb, struct au_branch *br) +{ + int err; + + err = 0; + if (au_br_writable(br->br_perm)) + err = au_dr_hino(sb, /*bindex*/-1, br, /*path*/NULL); + if (!err) + au_dr_hino_free(&br->br_dirren); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode, + char *buf, size_t sz) +{ + int err; + unsigned int major, minor; + char *p; + + p = buf; + err = snprintf(p, sz, "%d_", brid->type); + AuDebugOn(err > sz); + p += err; + sz -= err; + switch (brid->type) { + case AuBrid_Unset: + return -EINVAL; + case AuBrid_UUID: + err = snprintf(p, sz, "%pU", brid->uuid.b); + break; + case AuBrid_FSID: + err = snprintf(p, sz, "%08x-%08x", + brid->fsid.val[0], brid->fsid.val[1]); + break; + case AuBrid_DEV: + major = MAJOR(brid->dev); + minor = MINOR(brid->dev); + if (major <= 0xff && minor <= 0xff) + err = snprintf(p, sz, "%02x%02x", major, minor); + else + err = snprintf(p, sz, "%03x:%05x", major, minor); + break; + } + AuDebugOn(err > sz); + p += err; + sz -= err; + err = snprintf(p, sz, "_%llu", (unsigned long long)h_inode->i_ino); + AuDebugOn(err > sz); + p += err; + sz -= err; + + return p - buf; +} + +static int au_drinfo_name(struct au_branch *br, char *name, int len) +{ + int rlen; + struct dentry *br_dentry; + struct inode *br_inode; + + br_dentry = au_br_dentry(br); + br_inode = d_inode(br_dentry); + rlen = au_brid_str(&br->br_dirren.dr_brid, br_inode, name, len); + AuDebugOn(rlen >= AUFS_DIRREN_ENV_VAL_SZ); + AuDebugOn(rlen > len); + + return rlen; +} + +/* ---------------------------------------------------------------------- */ + +/* + * from the given @h_dentry, construct drinfo at @*fdata. + * when the size of @*fdata is not enough, reallocate and return new @fdata and + * @allocated. + */ +static int au_drinfo_construct(struct au_drinfo_fdata **fdata, + struct dentry *h_dentry, + unsigned char *allocated) +{ + int err, v; + struct au_drinfo_fdata *f, *p; + struct au_drinfo *drinfo; + struct inode *h_inode; + struct qstr *qname; + + err = 0; + f = *fdata; + h_inode = d_inode(h_dentry); + qname = &h_dentry->d_name; + drinfo = &f->drinfo; + drinfo->ino = (__force uint64_t)cpu_to_be64(h_inode->i_ino); + drinfo->oldnamelen = qname->len; + if (*allocated < sizeof(*f) + qname->len) { + v = roundup_pow_of_two(*allocated + qname->len); + p = au_krealloc(f, v, GFP_NOFS, /*may_shrink*/0); + if (unlikely(!p)) { + err = -ENOMEM; + AuTraceErr(err); + goto out; + } + f = p; + *fdata = f; + *allocated = v; + drinfo = &f->drinfo; + } + memcpy(drinfo->oldname, qname->name, qname->len); + AuDbg("i%llu, %.*s\n", + be64_to_cpu((__force __be64)drinfo->ino), drinfo->oldnamelen, + drinfo->oldname); + +out: + AuTraceErr(err); + return err; +} + +/* callers have to free the return value */ +static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino) +{ + struct au_drinfo *ret, *drinfo; + struct au_drinfo_fdata fdata; + int len; + loff_t pos; + ssize_t ssz; + + ret = ERR_PTR(-EIO); + pos = 0; + ssz = vfsub_read_k(file, &fdata, sizeof(fdata), &pos); + if (unlikely(ssz != sizeof(fdata))) { + AuIOErr("ssz %zd, %u, %pD2\n", + ssz, (unsigned int)sizeof(fdata), file); + goto out; + } + + fdata.magic = ntohl((__force __be32)fdata.magic); + switch (fdata.magic) { + case AUFS_DRINFO_MAGIC_V1: + break; + default: + AuIOErr("magic-num 0x%x, 0x%x, %pD2\n", + fdata.magic, AUFS_DRINFO_MAGIC_V1, file); + goto out; + } + + drinfo = &fdata.drinfo; + len = drinfo->oldnamelen; + if (!len) { + AuIOErr("broken drinfo %pD2\n", file); + goto out; + } + + ret = NULL; + drinfo->ino = be64_to_cpu((__force __be64)drinfo->ino); + if (unlikely(h_ino && drinfo->ino != h_ino)) { + AuDbg("ignored i%llu, i%llu, %pD2\n", + (unsigned long long)drinfo->ino, + (unsigned long long)h_ino, file); + goto out; /* success */ + } + + ret = kmalloc(sizeof(*ret) + len, GFP_NOFS); + if (unlikely(!ret)) { + ret = ERR_PTR(-ENOMEM); + AuTraceErrPtr(ret); + goto out; + } + + *ret = *drinfo; + ssz = vfsub_read_k(file, (void *)ret->oldname, len, &pos); + if (unlikely(ssz != len)) { + au_kfree_rcu(ret); + ret = ERR_PTR(-EIO); + AuIOErr("ssz %zd, %u, %pD2\n", ssz, len, file); + goto out; + } + + AuDbg("oldname %.*s\n", ret->oldnamelen, ret->oldname); + +out: + return ret; +} + +/* ---------------------------------------------------------------------- */ + +/* in order to be revertible */ +struct au_drinfo_rev_elm { + int created; + struct dentry *info_dentry; + struct au_drinfo *info_last; +}; + +struct au_drinfo_rev { + unsigned char already; + aufs_bindex_t nelm; + struct au_drinfo_rev_elm elm[]; +}; + +/* todo: isn't it too large? */ +struct au_drinfo_store { + struct path h_ppath; + struct dentry *h_dentry; + struct au_drinfo_fdata *fdata; + char *infoname; /* inside of whname, just after PFX */ + char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ]; + aufs_bindex_t btgt, btail; + unsigned char no_sio, + allocated, /* current size of *fdata */ + infonamelen, /* room size for p */ + whnamelen, /* length of the generated name */ + renameback; /* renamed back */ +}; + +/* on rename(2) error, the caller should revert it using @elm */ +static int au_drinfo_do_store(struct au_drinfo_store *w, + struct au_drinfo_rev_elm *elm) +{ + int err, len; + ssize_t ssz; + loff_t pos; + struct path infopath = { + .mnt = w->h_ppath.mnt + }; + struct inode *h_dir, *h_inode, *delegated; + struct file *infofile; + struct qstr *qname; + + AuDebugOn(elm + && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm))); + + infopath.dentry = vfsub_lookup_one_len(w->whname, w->h_ppath.dentry, + w->whnamelen); + AuTraceErrPtr(infopath.dentry); + if (IS_ERR(infopath.dentry)) { + err = PTR_ERR(infopath.dentry); + goto out; + } + + err = 0; + h_dir = d_inode(w->h_ppath.dentry); + if (elm && d_is_negative(infopath.dentry)) { + err = vfsub_create(h_dir, &infopath, 0600, /*want_excl*/true); + AuTraceErr(err); + if (unlikely(err)) + goto out_dput; + elm->created = 1; + elm->info_dentry = dget(infopath.dentry); + } + + infofile = vfsub_dentry_open(&infopath, O_RDWR); + AuTraceErrPtr(infofile); + if (IS_ERR(infofile)) { + err = PTR_ERR(infofile); + goto out_dput; + } + + h_inode = d_inode(infopath.dentry); + if (elm && i_size_read(h_inode)) { + h_inode = d_inode(w->h_dentry); + elm->info_last = au_drinfo_read_k(infofile, h_inode->i_ino); + AuTraceErrPtr(elm->info_last); + if (IS_ERR(elm->info_last)) { + err = PTR_ERR(elm->info_last); + elm->info_last = NULL; + AuDebugOn(elm->info_dentry); + goto out_fput; + } + } + + if (elm && w->renameback) { + delegated = NULL; + err = vfsub_unlink(h_dir, &infopath, &delegated, /*force*/0); + AuTraceErr(err); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + goto out_fput; + } + + pos = 0; + qname = &w->h_dentry->d_name; + len = sizeof(*w->fdata) + qname->len; + if (!elm) + len = sizeof(*w->fdata) + w->fdata->drinfo.oldnamelen; + ssz = vfsub_write_k(infofile, w->fdata, len, &pos); + if (ssz == len) { + AuDbg("hi%llu, %.*s\n", w->fdata->drinfo.ino, + w->fdata->drinfo.oldnamelen, w->fdata->drinfo.oldname); + goto out_fput; /* success */ + } else { + err = -EIO; + if (ssz < 0) + err = ssz; + /* the caller should revert it using @elm */ + } + +out_fput: + fput(infofile); +out_dput: + dput(infopath.dentry); +out: + AuTraceErr(err); + return err; +} + +struct au_call_drinfo_do_store_args { + int *errp; + struct au_drinfo_store *w; + struct au_drinfo_rev_elm *elm; +}; + +static void au_call_drinfo_do_store(void *args) +{ + struct au_call_drinfo_do_store_args *a = args; + + *a->errp = au_drinfo_do_store(a->w, a->elm); +} + +static int au_drinfo_store_sio(struct au_drinfo_store *w, + struct au_drinfo_rev_elm *elm) +{ + int err, wkq_err; + + if (w->no_sio) + err = au_drinfo_do_store(w, elm); + else { + struct au_call_drinfo_do_store_args a = { + .errp = &err, + .w = w, + .elm = elm + }; + wkq_err = au_wkq_wait(au_call_drinfo_do_store, &a); + if (unlikely(wkq_err)) + err = wkq_err; + } + AuTraceErr(err); + + return err; +} + +static int au_drinfo_store_work_init(struct au_drinfo_store *w, + aufs_bindex_t btgt) +{ + int err; + + memset(w, 0, sizeof(*w)); + w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40); + strcpy(w->whname, AUFS_WH_DR_INFO_PFX); + w->infoname = w->whname + sizeof(AUFS_WH_DR_INFO_PFX) - 1; + w->infonamelen = sizeof(w->whname) - sizeof(AUFS_WH_DR_INFO_PFX); + w->btgt = btgt; + w->no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); + + err = -ENOMEM; + w->fdata = kcalloc(1, w->allocated, GFP_NOFS); + if (unlikely(!w->fdata)) { + AuTraceErr(err); + goto out; + } + w->fdata->magic = (__force uint32_t)htonl(AUFS_DRINFO_MAGIC_V1); + err = 0; + +out: + return err; +} + +static void au_drinfo_store_work_fin(struct au_drinfo_store *w) +{ + au_kfree_rcu(w->fdata); +} + +static void au_drinfo_store_rev(struct au_drinfo_rev *rev, + struct au_drinfo_store *w) +{ + struct au_drinfo_rev_elm *elm; + struct inode *h_dir, *delegated; + int err, nelm; + struct path infopath = { + .mnt = w->h_ppath.mnt + }; + + h_dir = d_inode(w->h_ppath.dentry); + IMustLock(h_dir); + + err = 0; + elm = rev->elm; + for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { + AuDebugOn(elm->created && elm->info_last); + if (elm->created) { + AuDbg("here\n"); + delegated = NULL; + infopath.dentry = elm->info_dentry; + err = vfsub_unlink(h_dir, &infopath, &delegated, + !w->no_sio); + AuTraceErr(err); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + dput(elm->info_dentry); + } else if (elm->info_last) { + AuDbg("here\n"); + w->fdata->drinfo = *elm->info_last; + memcpy(w->fdata->drinfo.oldname, + elm->info_last->oldname, + elm->info_last->oldnamelen); + err = au_drinfo_store_sio(w, /*elm*/NULL); + au_kfree_rcu(elm->info_last); + } + if (unlikely(err)) + AuIOErr("%d, %s\n", err, w->whname); + /* go on even if err */ + } +} + +/* caller has to call au_dr_rename_fin() later */ +static int au_drinfo_store(struct dentry *dentry, aufs_bindex_t btgt, + struct qstr *dst_name, void *_rev) +{ + int err, sz, nelm; + aufs_bindex_t bindex, btail; + struct au_drinfo_store work; + struct au_drinfo_rev *rev, **p; + struct au_drinfo_rev_elm *elm; + struct super_block *sb; + struct au_branch *br; + struct au_hinode *hdir; + + err = au_drinfo_store_work_init(&work, btgt); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + err = -ENOMEM; + btail = au_dbtaildir(dentry); + nelm = btail - btgt; + sz = sizeof(*rev) + sizeof(*elm) * nelm; + rev = kcalloc(1, sz, GFP_NOFS); + if (unlikely(!rev)) { + AuTraceErr(err); + goto out_args; + } + rev->nelm = nelm; + elm = rev->elm; + p = _rev; + *p = rev; + + err = 0; + sb = dentry->d_sb; + work.h_ppath.dentry = au_h_dptr(dentry, btgt); + work.h_ppath.mnt = au_sbr_mnt(sb, btgt); + hdir = au_hi(d_inode(dentry), btgt); + au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); + for (bindex = btgt + 1; bindex <= btail; bindex++, elm++) { + work.h_dentry = au_h_dptr(dentry, bindex); + if (!work.h_dentry) + continue; + + err = au_drinfo_construct(&work.fdata, work.h_dentry, + &work.allocated); + AuTraceErr(err); + if (unlikely(err)) + break; + + work.renameback = au_qstreq(&work.h_dentry->d_name, dst_name); + br = au_sbr(sb, bindex); + work.whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; + work.whnamelen += au_drinfo_name(br, work.infoname, + work.infonamelen); + AuDbg("whname %.*s, i%llu, %.*s\n", + work.whnamelen, work.whname, + be64_to_cpu((__force __be64)work.fdata->drinfo.ino), + work.fdata->drinfo.oldnamelen, + work.fdata->drinfo.oldname); + + err = au_drinfo_store_sio(&work, elm); + AuTraceErr(err); + if (unlikely(err)) + break; + } + if (unlikely(err)) { + /* revert all drinfo */ + au_drinfo_store_rev(rev, &work); + au_kfree_try_rcu(rev); + *p = NULL; + } + au_hn_inode_unlock(hdir); + +out_args: + au_drinfo_store_work_fin(&work); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev) +{ + int err, already; + ino_t ino; + struct super_block *sb; + struct au_branch *br; + struct au_dr_br *dr; + struct dentry *h_dentry; + struct inode *h_inode; + struct au_dr_hino *ent; + struct au_drinfo_rev *rev, **p; + + AuDbg("bindex %d\n", bindex); + + err = -ENOMEM; + ent = kmalloc(sizeof(*ent), GFP_NOFS); + if (unlikely(!ent)) + goto out; + + sb = src->d_sb; + br = au_sbr(sb, bindex); + dr = &br->br_dirren; + h_dentry = au_h_dptr(src, bindex); + h_inode = d_inode(h_dentry); + ino = h_inode->i_ino; + ent->dr_h_ino = ino; + already = au_dr_hino_test_add(dr, ino, ent); + AuDbg("b%d, hi%llu, already %d\n", + bindex, (unsigned long long)ino, already); + + err = au_drinfo_store(src, bindex, dst_name, _rev); + AuTraceErr(err); + if (!err) { + p = _rev; + rev = *p; + rev->already = already; + goto out; /* success */ + } + + /* revert */ + if (!already) + au_dr_hino_del(dr, ent); + au_kfree_rcu(ent); + +out: + AuTraceErr(err); + return err; +} + +void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ + struct au_drinfo_rev *rev; + struct au_drinfo_rev_elm *elm; + int nelm; + + rev = _rev; + elm = rev->elm; + for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { + dput(elm->info_dentry); + au_kfree_rcu(elm->info_last); + } + au_kfree_try_rcu(rev); +} + +void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ + int err; + struct au_drinfo_store work; + struct au_drinfo_rev *rev = _rev; + struct super_block *sb; + struct au_branch *br; + struct inode *h_inode; + struct au_dr_br *dr; + struct au_dr_hino *ent; + + err = au_drinfo_store_work_init(&work, btgt); + if (unlikely(err)) + goto out; + + sb = src->d_sb; + br = au_sbr(sb, btgt); + work.h_ppath.dentry = au_h_dptr(src, btgt); + work.h_ppath.mnt = au_br_mnt(br); + au_drinfo_store_rev(rev, &work); + au_drinfo_store_work_fin(&work); + if (rev->already) + goto out; + + dr = &br->br_dirren; + h_inode = d_inode(work.h_ppath.dentry); + ent = au_dr_hino_find(dr, h_inode->i_ino); + BUG_ON(!ent); + au_dr_hino_del(dr, ent); + au_kfree_rcu(ent); + +out: + au_kfree_try_rcu(rev); + if (unlikely(err)) + pr_err("failed to remove dirren info\n"); +} + +/* ---------------------------------------------------------------------- */ + +static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath, + char *whname, int whnamelen, + struct dentry **info_dentry) +{ + struct au_drinfo *drinfo; + struct file *f; + struct inode *h_dir; + struct path infopath; + int unlocked; + + AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname); + + *info_dentry = NULL; + drinfo = NULL; + unlocked = 0; + h_dir = d_inode(h_ppath->dentry); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + infopath.dentry = vfsub_lookup_one_len(whname, h_ppath->dentry, + whnamelen); + if (IS_ERR(infopath.dentry)) { + drinfo = (void *)infopath.dentry; + goto out; + } + + if (d_is_negative(infopath.dentry)) + goto out_dput; /* success */ + + infopath.mnt = h_ppath->mnt; + f = vfsub_dentry_open(&infopath, O_RDONLY); + inode_unlock_shared(h_dir); + unlocked = 1; + if (IS_ERR(f)) { + drinfo = (void *)f; + goto out_dput; + } + + drinfo = au_drinfo_read_k(f, /*h_ino*/0); + if (IS_ERR_OR_NULL(drinfo)) + goto out_fput; + + AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname); + *info_dentry = dget(infopath.dentry); /* keep it alive */ + +out_fput: + fput(f); +out_dput: + dput(infopath.dentry); +out: + if (!unlocked) + inode_unlock_shared(h_dir); + AuTraceErrPtr(drinfo); + return drinfo; +} + +struct au_drinfo_do_load_args { + struct au_drinfo **drinfop; + struct path *h_ppath; + char *whname; + int whnamelen; + struct dentry **info_dentry; +}; + +static void au_call_drinfo_do_load(void *args) +{ + struct au_drinfo_do_load_args *a = args; + + *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen, + a->info_dentry); +} + +struct au_drinfo_load { + struct path h_ppath; + struct qstr *qname; + unsigned char no_sio; + + aufs_bindex_t ninfo; + struct au_drinfo **drinfo; +}; + +static int au_drinfo_load(struct au_drinfo_load *w, aufs_bindex_t bindex, + struct au_branch *br) +{ + int err, wkq_err, whnamelen, e; + char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ] + = AUFS_WH_DR_INFO_PFX; + struct au_drinfo *drinfo; + struct qstr oldname; + struct inode *h_dir, *delegated; + struct dentry *info_dentry; + struct path infopath; + + whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; + whnamelen += au_drinfo_name(br, whname + whnamelen, + sizeof(whname) - whnamelen); + if (w->no_sio) + drinfo = au_drinfo_do_load(&w->h_ppath, whname, whnamelen, + &info_dentry); + else { + struct au_drinfo_do_load_args args = { + .drinfop = &drinfo, + .h_ppath = &w->h_ppath, + .whname = whname, + .whnamelen = whnamelen, + .info_dentry = &info_dentry + }; + wkq_err = au_wkq_wait(au_call_drinfo_do_load, &args); + if (unlikely(wkq_err)) + drinfo = ERR_PTR(wkq_err); + } + err = PTR_ERR(drinfo); + if (IS_ERR_OR_NULL(drinfo)) + goto out; + + err = 0; + oldname.len = drinfo->oldnamelen; + oldname.name = drinfo->oldname; + if (au_qstreq(w->qname, &oldname)) { + /* the name is renamed back */ + au_kfree_rcu(drinfo); + drinfo = NULL; + + infopath.dentry = info_dentry; + infopath.mnt = w->h_ppath.mnt; + h_dir = d_inode(w->h_ppath.dentry); + delegated = NULL; + inode_lock_nested(h_dir, AuLsc_I_PARENT); + e = vfsub_unlink(h_dir, &infopath, &delegated, !w->no_sio); + inode_unlock(h_dir); + if (unlikely(e)) + AuIOErr("ignored %d, %pd2\n", e, &infopath.dentry); + if (unlikely(e == -EWOULDBLOCK)) + iput(delegated); + } + au_kfree_rcu(w->drinfo[bindex]); + w->drinfo[bindex] = drinfo; + dput(info_dentry); + +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_dr_lkup_free(struct au_drinfo **drinfo, int n) +{ + struct au_drinfo **p = drinfo; + + while (n-- > 0) + au_kfree_rcu(*drinfo++); + au_kfree_try_rcu(p); +} + +int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t btgt) +{ + int err, ninfo; + struct au_drinfo_load w; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + struct inode *h_dir; + struct au_dr_hino *ent; + struct super_block *sb; + + AuDbg("%.*s, name %.*s, whname %.*s, b%d\n", + AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name), + AuLNPair(&lkup->whname), btgt); + + sb = dentry->d_sb; + bbot = au_sbbot(sb); + w.ninfo = bbot + 1; + if (!lkup->dirren.drinfo) { + lkup->dirren.drinfo = kcalloc(w.ninfo, + sizeof(*lkup->dirren.drinfo), + GFP_NOFS); + if (unlikely(!lkup->dirren.drinfo)) { + err = -ENOMEM; + goto out; + } + lkup->dirren.ninfo = w.ninfo; + } + w.drinfo = lkup->dirren.drinfo; + w.no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); + w.h_ppath.dentry = au_h_dptr(dentry, btgt); + AuDebugOn(!w.h_ppath.dentry); + w.h_ppath.mnt = au_sbr_mnt(sb, btgt); + w.qname = &dentry->d_name; + + ninfo = 0; + for (bindex = btgt + 1; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_drinfo_load(&w, bindex, br); + if (unlikely(err)) + goto out_free; + if (w.drinfo[bindex]) + ninfo++; + } + if (!ninfo) { + br = au_sbr(sb, btgt); + h_dir = d_inode(w.h_ppath.dentry); + ent = au_dr_hino_find(&br->br_dirren, h_dir->i_ino); + AuDebugOn(!ent); + au_dr_hino_del(&br->br_dirren, ent); + au_kfree_rcu(ent); + } + goto out; /* success */ + +out_free: + au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); + lkup->dirren.ninfo = 0; + lkup->dirren.drinfo = NULL; +out: + AuTraceErr(err); + return err; +} + +void au_dr_lkup_fin(struct au_do_lookup_args *lkup) +{ + au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); +} + +int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt) +{ + int err; + struct au_drinfo *drinfo; + + err = 0; + if (!lkup->dirren.drinfo) + goto out; + AuDebugOn(lkup->dirren.ninfo <= btgt); + drinfo = lkup->dirren.drinfo[btgt]; + if (!drinfo) + goto out; + + au_kfree_try_rcu(lkup->whname.name); + lkup->whname.name = NULL; + lkup->dirren.dr_name.len = drinfo->oldnamelen; + lkup->dirren.dr_name.name = drinfo->oldname; + lkup->name = &lkup->dirren.dr_name; + err = au_wh_name_alloc(&lkup->whname, lkup->name); + if (!err) + AuDbg("name %.*s, whname %.*s, b%d\n", + AuLNPair(lkup->name), AuLNPair(&lkup->whname), + btgt); + +out: + AuTraceErr(err); + return err; +} + +int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, + ino_t h_ino) +{ + int match; + struct au_drinfo *drinfo; + + match = 1; + if (!lkup->dirren.drinfo) + goto out; + AuDebugOn(lkup->dirren.ninfo <= bindex); + drinfo = lkup->dirren.drinfo[bindex]; + if (!drinfo) + goto out; + + match = (drinfo->ino == h_ino); + AuDbg("match %d\n", match); + +out: + return match; +} + +/* ---------------------------------------------------------------------- */ + +int au_dr_opt_set(struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path); + } + + return err; +} + +int au_dr_opt_flush(struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm)) + err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL); + } + + return err; +} + +int au_dr_opt_clr(struct super_block *sb, int no_flush) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + if (!no_flush) { + err = au_dr_opt_flush(sb); + if (unlikely(err)) + goto out; + } + + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + au_dr_hino_free(&br->br_dirren); + } + +out: + return err; +} diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h new file mode 100644 index 000000000000..1fbc8fb20def --- /dev/null +++ b/fs/aufs/dirren.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * renamed dir info + */ + +#ifndef __AUFS_DIRREN_H__ +#define __AUFS_DIRREN_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include <linux/statfs.h> +#include <linux/uuid.h> +#include "hbl.h" + +#define AuDirren_NHASH 100 + +#ifdef CONFIG_AUFS_DIRREN +enum au_brid_type { + AuBrid_Unset, + AuBrid_UUID, + AuBrid_FSID, + AuBrid_DEV +}; + +struct au_dr_brid { + enum au_brid_type type; + union { + uuid_t uuid; /* unimplemented yet */ + fsid_t fsid; + dev_t dev; + }; +}; + +/* 20 is the max digits length of ulong 64 */ +/* brid-type "_" uuid "_" inum */ +#define AUFS_DIRREN_FNAME_SZ (1 + 1 + UUID_STRING_LEN + 20) +#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20) + +struct au_dr_hino { + struct hlist_bl_node dr_hnode; + ino_t dr_h_ino; +}; + +struct au_dr_br { + struct hlist_bl_head dr_h_ino[AuDirren_NHASH]; + struct au_dr_brid dr_brid; +}; + +struct au_dr_lookup { + /* dr_name is pointed by struct au_do_lookup_args.name */ + struct qstr dr_name; /* subset of dr_info */ + aufs_bindex_t ninfo; + struct au_drinfo **drinfo; +}; +#else +struct au_dr_hino; +/* empty */ +struct au_dr_br { }; +struct au_dr_lookup { }; +#endif + +/* ---------------------------------------------------------------------- */ + +struct au_branch; +struct au_do_lookup_args; +struct au_hinode; +#ifdef CONFIG_AUFS_DIRREN +int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino, + struct au_dr_hino *add_ent); +void au_dr_hino_free(struct au_dr_br *dr); +int au_dr_br_init(struct super_block *sb, struct au_branch *br, + const struct path *path); +int au_dr_br_fin(struct super_block *sb, struct au_branch *br); +int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev); +void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev); +void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev); +int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t bindex); +int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt); +int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, + ino_t h_ino); +void au_dr_lkup_fin(struct au_do_lookup_args *lkup); +int au_dr_opt_set(struct super_block *sb); +int au_dr_opt_flush(struct super_block *sb); +int au_dr_opt_clr(struct super_block *sb, int no_flush); +#else +AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino, + struct au_dr_hino *add_ent); +AuStubVoid(au_dr_hino_free, struct au_dr_br *dr); +AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br, + const struct path *path); +AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br); +AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev); +AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev); +AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex, + void *rev); +AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t bindex); +AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt); +AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup, + aufs_bindex_t bindex, ino_t h_ino); +AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup); +AuStubInt0(au_dr_opt_set, struct super_block *sb); +AuStubInt0(au_dr_opt_flush, struct super_block *sb); +AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush); +#endif + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_DIRREN +static inline int au_dr_ihash(ino_t h_ino) +{ + return h_ino % AuDirren_NHASH; +} +#else +AuStubInt0(au_dr_ihash, ino_t h_ino); +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DIRREN_H__ */ diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c new file mode 100644 index 000000000000..837f94d49f74 --- /dev/null +++ b/fs/aufs/dynop.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dynamically customizable operations for regular files + */ + +#include "aufs.h" + +#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) + +/* + * How large will these lists be? + * Usually just a few elements, 20-30 at most for each, I guess. + */ +static struct hlist_bl_head dynop[AuDyLast]; + +static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl, + const void *h_op) +{ + struct au_dykey *key, *tmp; + struct hlist_bl_node *pos; + + key = NULL; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) + if (tmp->dk_op.dy_hop == h_op) { + if (kref_get_unless_zero(&tmp->dk_kref)) + key = tmp; + break; + } + hlist_bl_unlock(hbl); + + return key; +} + +static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) +{ + struct au_dykey **k, *found; + const void *h_op = key->dk_op.dy_hop; + int i; + + found = NULL; + k = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else + break; + if (!found) { + spin_lock(&br->br_dykey_lock); + for (; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else { + k[i] = key; + break; + } + spin_unlock(&br->br_dykey_lock); + BUG_ON(i == AuBrDynOp); /* expand the array */ + } + + return found; +} + +/* kref_get() if @key is already added */ +static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key) +{ + struct au_dykey *tmp, *found; + struct hlist_bl_node *pos; + const void *h_op = key->dk_op.dy_hop; + + found = NULL; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) + if (tmp->dk_op.dy_hop == h_op) { + if (kref_get_unless_zero(&tmp->dk_kref)) + found = tmp; + break; + } + if (!found) + hlist_bl_add_head(&key->dk_hnode, hbl); + hlist_bl_unlock(hbl); + + if (!found) + DyPrSym(key); + return found; +} + +static void dy_free_rcu(struct rcu_head *rcu) +{ + struct au_dykey *key; + + key = container_of(rcu, struct au_dykey, dk_rcu); + DyPrSym(key); + kfree(key); +} + +static void dy_free(struct kref *kref) +{ + struct au_dykey *key; + struct hlist_bl_head *hbl; + + key = container_of(kref, struct au_dykey, dk_kref); + hbl = dynop + key->dk_op.dy_type; + au_hbl_del(&key->dk_hnode, hbl); + call_rcu(&key->dk_rcu, dy_free_rcu); +} + +void au_dy_put(struct au_dykey *key) +{ + kref_put(&key->dk_kref, dy_free); +} + +/* ---------------------------------------------------------------------- */ + +#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) + +#ifdef CONFIG_AUFS_DEBUG +#define DyDbgDeclare(cnt) unsigned int cnt = 0 +#define DyDbgInc(cnt) do { cnt++; } while (0) +#else +#define DyDbgDeclare(cnt) do {} while (0) +#define DyDbgInc(cnt) do {} while (0) +#endif + +#define DySet(func, dst, src, h_op, h_sb) do { \ + DyDbgInc(cnt); \ + if (h_op->func) { \ + if (src.func) \ + dst.func = src.func; \ + else \ + AuDbg("%s %s\n", au_sbtype(h_sb), #func); \ + } \ +} while (0) + +#define DySetForce(func, dst, src) do { \ + AuDebugOn(!src.func); \ + DyDbgInc(cnt); \ + dst.func = src.func; \ +} while (0) + +#define DySetAop(func) \ + DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) +#define DySetAopForce(func) \ + DySetForce(func, dyaop->da_op, aufs_aop) + +static void dy_aop(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused) +{ + struct au_dyaop *dyaop = (void *)key; + const struct address_space_operations *h_aop = h_op; + DyDbgDeclare(cnt); + + AuDbg("%s\n", au_sbtype(h_sb)); + + DySetAop(writepage); + DySetAopForce(readpage); /* force */ + DySetAop(writepages); + DySetAop(set_page_dirty); + DySetAop(readpages); + DySetAop(write_begin); + DySetAop(write_end); + DySetAop(bmap); + DySetAop(invalidatepage); + DySetAop(releasepage); + DySetAop(freepage); + /* this one will be changed according to an aufs mount option */ + DySetAop(direct_IO); + DySetAop(migratepage); + DySetAop(isolate_page); + DySetAop(putback_page); + DySetAop(launder_page); + DySetAop(is_partially_uptodate); + DySetAop(is_dirty_writeback); + DySetAop(error_remove_page); + DySetAop(swap_activate); + DySetAop(swap_deactivate); + + DyDbgSize(cnt, *h_aop); +} + +/* ---------------------------------------------------------------------- */ + +static void dy_bug(struct kref *kref) +{ + BUG(); +} + +static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br) +{ + struct au_dykey *key, *old; + struct hlist_bl_head *hbl; + struct op { + unsigned int sz; + void (*set)(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused); + }; + static const struct op a[] = { + [AuDy_AOP] = { + .sz = sizeof(struct au_dyaop), + .set = dy_aop + } + }; + const struct op *p; + + hbl = dynop + op->dy_type; + key = dy_gfind_get(hbl, op->dy_hop); + if (key) + goto out_add; /* success */ + + p = a + op->dy_type; + key = kzalloc(p->sz, GFP_NOFS); + if (unlikely(!key)) { + key = ERR_PTR(-ENOMEM); + goto out; + } + + key->dk_op.dy_hop = op->dy_hop; + kref_init(&key->dk_kref); + p->set(key, op->dy_hop, au_br_sb(br)); + old = dy_gadd(hbl, key); + if (old) { + au_kfree_rcu(key); + key = old; + } + +out_add: + old = dy_bradd(br, key); + if (old) + /* its ref-count should never be zero here */ + kref_put(&key->dk_kref, dy_bug); +out: + return key; +} + +/* ---------------------------------------------------------------------- */ +/* + * Aufs prohibits O_DIRECT by default even if the branch supports it. + * This behaviour is necessary to return an error from open(O_DIRECT) instead + * of the succeeding I/O. The dio mount option enables O_DIRECT and makes + * open(O_DIRECT) always succeed, but the succeeding I/O may return an error. + * See the aufs manual in detail. + */ +static void dy_adx(struct au_dyaop *dyaop, int do_dx) +{ + if (!do_dx) + dyaop->da_op.direct_IO = NULL; + else + dyaop->da_op.direct_IO = aufs_aop.direct_IO; +} + +static struct au_dyaop *dy_aget(struct au_branch *br, + const struct address_space_operations *h_aop, + int do_dx) +{ + struct au_dyaop *dyaop; + struct au_dynop op; + + op.dy_type = AuDy_AOP; + op.dy_haop = h_aop; + dyaop = (void *)dy_get(&op, br); + if (IS_ERR(dyaop)) + goto out; + dy_adx(dyaop, do_dx); + +out: + return dyaop; +} + +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode) +{ + int err, do_dx; + struct super_block *sb; + struct au_branch *br; + struct au_dyaop *dyaop; + + AuDebugOn(!S_ISREG(h_inode->i_mode)); + IiMustWriteLock(inode); + + sb = inode->i_sb; + br = au_sbr(sb, bindex); + do_dx = !!au_opt_test(au_mntflags(sb), DIO); + dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx); + err = PTR_ERR(dyaop); + if (IS_ERR(dyaop)) + /* unnecessary to call dy_fput() */ + goto out; + + err = 0; + inode->i_mapping->a_ops = &dyaop->da_op; + +out: + return err; +} + +/* + * Is it safe to replace a_ops during the inode/file is in operation? + * Yes, I hope so. + */ +int au_dy_irefresh(struct inode *inode) +{ + int err; + aufs_bindex_t btop; + struct inode *h_inode; + + err = 0; + if (S_ISREG(inode->i_mode)) { + btop = au_ibtop(inode); + h_inode = au_h_iptr(inode, btop); + err = au_dy_iaop(inode, btop, h_inode); + } + return err; +} + +void au_dy_arefresh(int do_dx) +{ + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_dykey *key; + + hbl = dynop + AuDy_AOP; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(key, pos, hbl, dk_hnode) + dy_adx((void *)key, do_dx); + hlist_bl_unlock(hbl); +} + +/* ---------------------------------------------------------------------- */ + +void __init au_dy_init(void) +{ + int i; + + for (i = 0; i < AuDyLast; i++) + INIT_HLIST_BL_HEAD(dynop + i); +} + +void au_dy_fin(void) +{ + int i; + + for (i = 0; i < AuDyLast; i++) + WARN_ON(!hlist_bl_empty(dynop + i)); +} diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h new file mode 100644 index 000000000000..c0c7a5485ad7 --- /dev/null +++ b/fs/aufs/dynop.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2010-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dynamically customizable operations (for regular files only) + */ + +#ifndef __AUFS_DYNOP_H__ +#define __AUFS_DYNOP_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/kref.h> + +enum {AuDy_AOP, AuDyLast}; + +struct au_dynop { + int dy_type; + union { + const void *dy_hop; + const struct address_space_operations *dy_haop; + }; +}; + +struct au_dykey { + union { + struct hlist_bl_node dk_hnode; + struct rcu_head dk_rcu; + }; + struct au_dynop dk_op; + + /* + * during I am in the branch local array, kref is gotten. when the + * branch is removed, kref is put. + */ + struct kref dk_kref; +}; + +/* stop unioning since their sizes are very different from each other */ +struct au_dyaop { + struct au_dykey da_key; + struct address_space_operations da_op; /* not const */ +}; +/* make sure that 'struct au_dykey *' can be any type */ +static_assert(!offsetof(struct au_dyaop, da_key)); + +/* ---------------------------------------------------------------------- */ + +/* dynop.c */ +struct au_branch; +void au_dy_put(struct au_dykey *key); +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode); +int au_dy_irefresh(struct inode *inode); +void au_dy_arefresh(int do_dio); + +void __init au_dy_init(void); +void au_dy_fin(void); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DYNOP_H__ */ diff --git a/fs/aufs/export.c b/fs/aufs/export.c new file mode 100644 index 000000000000..842df6f05517 --- /dev/null +++ b/fs/aufs/export.c @@ -0,0 +1,838 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * export via nfs + */ + +#include <linux/exportfs.h> +#include <linux/fs_struct.h> +#include <linux/namei.h> +#include <linux/nsproxy.h> +#include <linux/random.h> +#include <linux/writeback.h> +#include "aufs.h" + +union conv { +#ifdef CONFIG_AUFS_INO_T_64 + __u32 a[2]; +#else + __u32 a[1]; +#endif + ino_t ino; +}; + +static ino_t decode_ino(__u32 *a) +{ + union conv u; + + BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); + u.a[0] = a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + u.a[1] = a[1]; +#endif + return u.ino; +} + +static void encode_ino(__u32 *a, ino_t ino) +{ + union conv u; + + u.ino = ino; + a[0] = u.a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + a[1] = u.a[1]; +#endif +} + +/* NFS file handle */ +enum { + Fh_br_id, + Fh_sigen, +#ifdef CONFIG_AUFS_INO_T_64 + /* support 64bit inode number */ + Fh_ino1, + Fh_ino2, + Fh_dir_ino1, + Fh_dir_ino2, +#else + Fh_ino1, + Fh_dir_ino1, +#endif + Fh_igen, + Fh_h_type, + Fh_tail, + + Fh_ino = Fh_ino1, + Fh_dir_ino = Fh_dir_ino1 +}; + +static int au_test_anon(struct dentry *dentry) +{ + /* note: read d_flags without d_lock */ + return !!(dentry->d_flags & DCACHE_DISCONNECTED); +} + +int au_test_nfsd(void) +{ + int ret; + struct task_struct *tsk = current; + char comm[sizeof(tsk->comm)]; + + ret = 0; + if (tsk->flags & PF_KTHREAD) { + get_task_comm(comm, tsk); + ret = !strcmp(comm, "nfsd"); + } + + return ret; +} + +/* ---------------------------------------------------------------------- */ +/* inode generation external table */ + +void au_xigen_inc(struct inode *inode) +{ + loff_t pos; + ssize_t sz; + __u32 igen; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + sb = inode->i_sb; + AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); + + sbinfo = au_sbi(sb); + pos = inode->i_ino; + pos *= sizeof(igen); + igen = inode->i_generation + 1; + sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, + sizeof(igen), &pos); + if (sz == sizeof(igen)) + return; /* success */ + + if (unlikely(sz >= 0)) + AuIOErr("xigen error (%zd)\n", sz); +} + +int au_xigen_new(struct inode *inode) +{ + int err; + loff_t pos; + ssize_t sz; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct file *file; + + err = 0; + /* todo: dirty, at mount time */ + if (inode->i_ino == AUFS_ROOT_INO) + goto out; + sb = inode->i_sb; + SiMustAnyLock(sb); + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + goto out; + + err = -EFBIG; + pos = inode->i_ino; + if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { + AuIOErr1("too large i%lld\n", pos); + goto out; + } + pos *= sizeof(inode->i_generation); + + err = 0; + sbinfo = au_sbi(sb); + file = sbinfo->si_xigen; + BUG_ON(!file); + + if (vfsub_f_size_read(file) + < pos + sizeof(inode->i_generation)) { + inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); + sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + } else + sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + if (sz == sizeof(inode->i_generation)) + goto out; /* success */ + + err = sz; + if (unlikely(sz >= 0)) { + err = -EIO; + AuIOErr("xigen error (%zd)\n", sz); + } + +out: + return err; +} + +int au_xigen_set(struct super_block *sb, struct path *path) +{ + int err; + struct au_sbinfo *sbinfo; + struct file *file; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + file = au_xino_create2(sb, path, sbinfo->si_xigen); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + err = 0; + if (sbinfo->si_xigen) + fput(sbinfo->si_xigen); + sbinfo->si_xigen = file; + +out: + AuTraceErr(err); + return err; +} + +void au_xigen_clr(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + if (sbinfo->si_xigen) { + fput(sbinfo->si_xigen); + sbinfo->si_xigen = NULL; + } +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino) +{ + struct dentry *dentry, *d; + struct inode *inode; + unsigned int sigen; + + dentry = NULL; + inode = ilookup(sb, ino); + if (!inode) + goto out; + + dentry = ERR_PTR(-ESTALE); + sigen = au_sigen(sb); + if (unlikely(au_is_bad_inode(inode) + || IS_DEADDIR(inode) + || sigen != au_iigen(inode, NULL))) + goto out_iput; + + dentry = NULL; + if (!dir_ino || S_ISDIR(inode->i_mode)) + dentry = d_find_alias(inode); + else { + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { + spin_lock(&d->d_lock); + if (!au_test_anon(d) + && d_inode(d->d_parent)->i_ino == dir_ino) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&d->d_lock); + } + spin_unlock(&inode->i_lock); + } + if (unlikely(dentry && au_digen_test(dentry, sigen))) { + /* need to refresh */ + dput(dentry); + dentry = NULL; + } + +out_iput: + iput(inode); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +/* todo: dirty? */ +/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ + +struct au_compare_mnt_args { + /* input */ + struct super_block *sb; + + /* output */ + struct vfsmount *mnt; +}; + +static int au_compare_mnt(struct vfsmount *mnt, void *arg) +{ + struct au_compare_mnt_args *a = arg; + + if (mnt->mnt_sb != a->sb) + return 0; + a->mnt = mntget(mnt); + return 1; +} + +static struct vfsmount *au_mnt_get(struct super_block *sb) +{ + int err; + struct path root; + struct au_compare_mnt_args args = { + .sb = sb + }; + + get_fs_root(current->fs, &root); + rcu_read_lock(); + err = iterate_mounts(au_compare_mnt, &args, root.mnt); + rcu_read_unlock(); + path_put(&root); + AuDebugOn(!err); + AuDebugOn(!args.mnt); + return args.mnt; +} + +struct au_nfsd_si_lock { + unsigned int sigen; + aufs_bindex_t bindex, br_id; + unsigned char force_lock; +}; + +static int si_nfsd_read_lock(struct super_block *sb, + struct au_nfsd_si_lock *nsi_lock) +{ + int err; + aufs_bindex_t bindex; + + si_read_lock(sb, AuLock_FLUSH); + + /* branch id may be wrapped around */ + err = 0; + bindex = au_br_index(sb, nsi_lock->br_id); + if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb)) + goto out; /* success */ + + err = -ESTALE; + bindex = -1; + if (!nsi_lock->force_lock) + si_read_unlock(sb); + +out: + nsi_lock->bindex = bindex; + return err; +} + +struct find_name_by_ino { + struct dir_context ctx; + int called, found; + ino_t ino; + char *name; + int namelen; +}; + +static int +find_name_by_ino(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino, + ctx); + + a->called++; + if (a->ino != ino) + return 0; + + memcpy(a->name, name, namelen); + a->namelen = namelen; + a->found = 1; + return 1; +} + +static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *parent; + struct file *file; + struct inode *dir; + struct find_name_by_ino arg = { + .ctx = { + .actor = find_name_by_ino + } + }; + int err; + + parent = path->dentry; + if (nsi_lock) + si_read_unlock(parent->d_sb); + file = vfsub_dentry_open(path, au_dir_roflags); + dentry = (void *)file; + if (IS_ERR(file)) + goto out; + + dentry = ERR_PTR(-ENOMEM); + arg.name = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!arg.name)) + goto out_file; + arg.ino = ino; + arg.found = 0; + do { + arg.called = 0; + /* smp_mb(); */ + err = vfsub_iterate_dir(file, &arg.ctx); + } while (!err && !arg.found && arg.called); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_name; + /* instead of ENOENT */ + dentry = ERR_PTR(-ESTALE); + if (!arg.found) + goto out_name; + + /* do not call vfsub_lkup_one() */ + dir = d_inode(parent); + dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen); + AuTraceErrPtr(dentry); + if (IS_ERR(dentry)) + goto out_name; + AuDebugOn(au_test_anon(dentry)); + if (unlikely(d_really_is_negative(dentry))) { + dput(dentry); + dentry = ERR_PTR(-ENOENT); + } + +out_name: + free_page((unsigned long)arg.name); +out_file: + fput(file); +out: + if (unlikely(nsi_lock + && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } + AuTraceErrPtr(dentry); + return dentry; +} + +static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry; + struct path path; + + if (dir_ino != AUFS_ROOT_INO) { + path.dentry = decode_by_ino(sb, dir_ino, 0); + dentry = path.dentry; + if (!path.dentry || IS_ERR(path.dentry)) + goto out; + AuDebugOn(au_test_anon(path.dentry)); + } else + path.dentry = dget(sb->s_root); + + path.mnt = au_mnt_get(sb); + dentry = au_lkup_by_ino(&path, ino, nsi_lock); + path_put(&path); + +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static int h_acceptable(void *expv, struct dentry *dentry) +{ + return 1; +} + +static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, + char *buf, int len, struct super_block *sb) +{ + char *p; + int n; + struct path path; + + p = d_path(h_rootpath, buf, len); + if (IS_ERR(p)) + goto out; + n = strlen(p); + + path.mnt = h_rootpath->mnt; + path.dentry = h_parent; + p = d_path(&path, buf, len); + if (IS_ERR(p)) + goto out; + if (n != 1) + p += n; + + path.mnt = au_mnt_get(sb); + path.dentry = sb->s_root; + p = d_path(&path, buf, len - strlen(p)); + mntput(path.mnt); + if (IS_ERR(p)) + goto out; + if (n != 1) + p[strlen(p)] = '/'; + +out: + AuTraceErrPtr(p); + return p; +} + +static +struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh, + int fh_len, struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *h_parent, *root; + struct super_block *h_sb; + char *pathname, *p; + struct vfsmount *h_mnt; + struct au_branch *br; + int err; + struct path path; + + br = au_sbr(sb, nsi_lock->bindex); + h_mnt = au_br_mnt(br); + h_sb = h_mnt->mnt_sb; + /* todo: call lower fh_to_dentry()? fh_to_parent()? */ + lockdep_off(); + h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail), + fh_len - Fh_tail, fh[Fh_h_type], + h_acceptable, /*context*/NULL); + lockdep_on(); + dentry = h_parent; + if (unlikely(!h_parent || IS_ERR(h_parent))) { + AuWarn1("%s decode_fh failed, %ld\n", + au_sbtype(h_sb), PTR_ERR(h_parent)); + goto out; + } + dentry = NULL; + if (unlikely(au_test_anon(h_parent))) { + AuWarn1("%s decode_fh returned a disconnected dentry\n", + au_sbtype(h_sb)); + goto out_h_parent; + } + + dentry = ERR_PTR(-ENOMEM); + pathname = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!pathname)) + goto out_h_parent; + + root = sb->s_root; + path.mnt = h_mnt; + di_read_lock_parent(root, !AuLock_IR); + path.dentry = au_h_dptr(root, nsi_lock->bindex); + di_read_unlock(root, !AuLock_IR); + p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb); + dentry = (void *)p; + if (IS_ERR(p)) + goto out_pathname; + + si_read_unlock(sb); + err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_relock; + + dentry = ERR_PTR(-ENOENT); + AuDebugOn(au_test_anon(path.dentry)); + if (unlikely(d_really_is_negative(path.dentry))) + goto out_path; + + if (ino != d_inode(path.dentry)->i_ino) + dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); + else + dentry = dget(path.dentry); + +out_path: + path_put(&path); +out_relock: + if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } +out_pathname: + free_page((unsigned long)pathname); +out_h_parent: + dput(h_parent); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry * +aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, + int fh_type) +{ + struct dentry *dentry; + __u32 *fh = fid->raw; + struct au_branch *br; + ino_t ino, dir_ino; + struct au_nfsd_si_lock nsi_lock = { + .force_lock = 0 + }; + + dentry = ERR_PTR(-ESTALE); + /* it should never happen, but the file handle is unreliable */ + if (unlikely(fh_len < Fh_tail)) + goto out; + nsi_lock.sigen = fh[Fh_sigen]; + nsi_lock.br_id = fh[Fh_br_id]; + + /* branch id may be wrapped around */ + br = NULL; + if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) + goto out; + nsi_lock.force_lock = 1; + + /* is this inode still cached? */ + ino = decode_ino(fh + Fh_ino); + /* it should never happen */ + if (unlikely(ino == AUFS_ROOT_INO)) + goto out_unlock; + + dir_ino = decode_ino(fh + Fh_dir_ino); + dentry = decode_by_ino(sb, ino, dir_ino); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* is the parent dir cached? */ + br = au_sbr(sb, nsi_lock.bindex); + au_lcnt_inc(&br->br_nfiles); + dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* lookup path */ + dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (unlikely(!dentry)) + /* todo?: make it ESTALE */ + goto out_unlock; + +accept: + if (!au_digen_test(dentry, au_sigen(sb)) + && d_inode(dentry)->i_generation == fh[Fh_igen]) + goto out_unlock; /* success */ + + dput(dentry); + dentry = ERR_PTR(-ESTALE); +out_unlock: + if (br) + au_lcnt_dec(&br->br_nfiles); + si_read_unlock(sb); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +#if 0 /* reserved for future use */ +/* support subtreecheck option */ +static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + struct dentry *parent; + __u32 *fh = fid->raw; + ino_t dir_ino; + + dir_ino = decode_ino(fh + Fh_dir_ino); + parent = decode_by_ino(sb, dir_ino, 0); + if (IS_ERR(parent)) + goto out; + if (!parent) + parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), + dir_ino, fh, fh_len); + +out: + AuTraceErrPtr(parent); + return parent; +} +#endif + +/* ---------------------------------------------------------------------- */ + +static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, + struct inode *dir) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb, *h_sb; + struct dentry *dentry, *parent, *h_parent; + struct inode *h_dir; + struct au_branch *br; + + err = -ENOSPC; + if (unlikely(*max_len <= Fh_tail)) { + AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); + goto out; + } + + err = FILEID_ROOT; + if (inode->i_ino == AUFS_ROOT_INO) { + AuDebugOn(inode->i_ino != AUFS_ROOT_INO); + goto out; + } + + h_parent = NULL; + sb = inode->i_sb; + err = si_read_lock(sb, AuLock_FLUSH); + if (unlikely(err)) + goto out; + +#ifdef CONFIG_AUFS_DEBUG + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + AuWarn1("NFS-exporting requires xino\n"); +#endif + err = -EIO; + parent = NULL; + ii_read_lock_child(inode); + bindex = au_ibtop(inode); + if (!dir) { + dentry = d_find_any_alias(inode); + if (unlikely(!dentry)) + goto out_unlock; + AuDebugOn(au_test_anon(dentry)); + parent = dget_parent(dentry); + dput(dentry); + if (unlikely(!parent)) + goto out_unlock; + if (d_really_is_positive(parent)) + dir = d_inode(parent); + } + + ii_read_lock_parent(dir); + h_dir = au_h_iptr(dir, bindex); + ii_read_unlock(dir); + if (unlikely(!h_dir)) + goto out_parent; + h_parent = d_find_any_alias(h_dir); + if (unlikely(!h_parent)) + goto out_hparent; + + err = -EPERM; + br = au_sbr(sb, bindex); + h_sb = au_br_sb(br); + if (unlikely(!h_sb->s_export_op)) { + AuErr1("%s branch is not exportable\n", au_sbtype(h_sb)); + goto out_hparent; + } + + fh[Fh_br_id] = br->br_id; + fh[Fh_sigen] = au_sigen(sb); + encode_ino(fh + Fh_ino, inode->i_ino); + encode_ino(fh + Fh_dir_ino, dir->i_ino); + fh[Fh_igen] = inode->i_generation; + + *max_len -= Fh_tail; + fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail), + max_len, + /*connectable or subtreecheck*/0); + err = fh[Fh_h_type]; + *max_len += Fh_tail; + /* todo: macros? */ + if (err != FILEID_INVALID) + err = 99; + else + AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb)); + +out_hparent: + dput(h_parent); +out_parent: + dput(parent); +out_unlock: + ii_read_unlock(inode); + si_read_unlock(sb); +out: + if (unlikely(err < 0)) + err = FILEID_INVALID; + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_commit_metadata(struct inode *inode) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct inode *h_inode; + int (*f)(struct inode *inode); + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + ii_write_lock_child(inode); + bindex = au_ibtop(inode); + AuDebugOn(bindex < 0); + h_inode = au_h_iptr(inode, bindex); + + f = h_inode->i_sb->s_export_op->commit_metadata; + if (f) + err = f(h_inode); + else { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0 /* metadata only */ + }; + + err = sync_inode(h_inode, &wbc); + } + + au_cpup_attr_timesizes(inode); + ii_write_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct export_operations aufs_export_op = { + .fh_to_dentry = aufs_fh_to_dentry, + /* .fh_to_parent = aufs_fh_to_parent, */ + .encode_fh = aufs_encode_fh, + .commit_metadata = aufs_commit_metadata +}; + +void au_export_init(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + __u32 u; + + BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS) + && IS_MODULE(CONFIG_EXPORTFS), + AUFS_NAME ": unsupported configuration " + "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y"); + + sb->s_export_op = &aufs_export_op; + sbinfo = au_sbi(sb); + sbinfo->si_xigen = NULL; + get_random_bytes(&u, sizeof(u)); + BUILD_BUG_ON(sizeof(u) != sizeof(int)); + atomic_set(&sbinfo->si_xigen_next, u); +} diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c new file mode 100644 index 000000000000..9894e2124bd5 --- /dev/null +++ b/fs/aufs/f_op.c @@ -0,0 +1,819 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file and vm operations + */ + +#include <linux/aio.h> +#include <linux/fs_stack.h> +#include <linux/mman.h> +#include <linux/security.h> +#include "aufs.h" + +int au_do_open_nondir(struct file *file, int flags, struct file *h_file) +{ + int err; + aufs_bindex_t bindex; + struct dentry *dentry, *h_dentry; + struct au_finfo *finfo; + struct inode *h_inode; + + FiMustWriteLock(file); + + err = 0; + dentry = file->f_path.dentry; + AuDebugOn(IS_ERR_OR_NULL(dentry)); + finfo = au_fi(file); + memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop)); + atomic_set(&finfo->fi_mmapped, 0); + bindex = au_dbtop(dentry); + if (!h_file) { + h_dentry = au_h_dptr(dentry, bindex); + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + goto out; + } + } else { + h_dentry = h_file->f_path.dentry; + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; + /* br ref is already inc-ed */ + } + + if ((flags & __O_TMPFILE) + && !(flags & O_EXCL)) { + h_inode = file_inode(h_file); + spin_lock(&h_inode->i_lock); + h_inode->i_state |= I_LINKABLE; + spin_unlock(&h_inode->i_lock); + } + au_set_fbtop(file, bindex); + au_set_h_fptr(file, bindex, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + +out: + return err; +} + +static int aufs_open_nondir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + struct au_do_open_args args = { + .open = au_do_open_nondir + }; + + AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n", + file, vfsub_file_flags(file), file->f_mode); + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_do_open(file, &args); + si_read_unlock(sb); + return err; +} + +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) +{ + struct au_finfo *finfo; + aufs_bindex_t bindex; + + finfo = au_fi(file); + au_hbl_del(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + bindex = finfo->fi_btop; + if (bindex >= 0) + au_set_h_fptr(file, bindex, NULL); + + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_nondir(struct file *file, fl_owner_t id) +{ + int err; + struct file *h_file; + + err = 0; + h_file = au_hf_top(file); + if (h_file) + err = vfsub_flush(h_file, id); + return err; +} + +static int aufs_flush_nondir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_nondir); +} + +/* ---------------------------------------------------------------------- */ +/* + * read and write functions acquire [fdi]_rwsem once, but release before + * mmap_sem. This is because to stop a race condition between mmap(2). + * Releasing these aufs-rwsem should be safe, no branch-management (by keeping + * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in + * read functions after [fdi]_rwsem are released, but it should be harmless. + */ + +/* Callers should call au_read_post() or fput() in the end */ +struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc) +{ + struct file *h_file; + int err; + + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc); + if (!err) { + di_read_unlock(file->f_path.dentry, AuLock_IR); + h_file = au_hf_top(file); + get_file(h_file); + if (!keep_fi) + fi_read_unlock(file); + } else + h_file = ERR_PTR(err); + + return h_file; +} + +static void au_read_post(struct inode *inode, struct file *h_file) +{ + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(inode, file_inode(h_file)); + fput(h_file); +} + +struct au_write_pre { + /* input */ + unsigned int lsc; + + /* output */ + blkcnt_t blks; + aufs_bindex_t btop; +}; + +/* + * return with iinfo is write-locked + * callers should call au_write_post() or iinfo_write_unlock() + fput() in the + * end + */ +static struct file *au_write_pre(struct file *file, int do_ready, + struct au_write_pre *wpre) +{ + struct file *h_file; + struct dentry *dentry; + int err; + unsigned int lsc; + struct au_pin pin; + + lsc = 0; + if (wpre) + lsc = wpre->lsc; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc); + h_file = ERR_PTR(err); + if (unlikely(err)) + goto out; + + dentry = file->f_path.dentry; + if (do_ready) { + err = au_ready_to_write(file, -1, &pin); + if (unlikely(err)) { + h_file = ERR_PTR(err); + di_write_unlock(dentry); + goto out_fi; + } + } + + di_downgrade_lock(dentry, /*flags*/0); + if (wpre) + wpre->btop = au_fbtop(file); + h_file = au_hf_top(file); + get_file(h_file); + if (wpre) + wpre->blks = file_inode(h_file)->i_blocks; + if (do_ready) + au_unpin(&pin); + di_read_unlock(dentry, /*flags*/0); + +out_fi: + fi_write_unlock(file); +out: + return h_file; +} + +static void au_write_post(struct inode *inode, struct file *h_file, + struct au_write_pre *wpre, ssize_t written) +{ + struct inode *h_inode; + + au_cpup_attr_timesizes(inode); + AuDebugOn(au_ibtop(inode) != wpre->btop); + h_inode = file_inode(h_file); + inode->i_mode = h_inode->i_mode; + ii_write_unlock(inode); + /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */ + if (written > 0) + au_fhsm_wrote(inode->i_sb, wpre->btop, + /*force*/h_inode->i_blocks > wpre->blks); + fput(h_file); +} + +static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + ssize_t err; + struct inode *inode; + struct file *h_file; + struct super_block *sb; + + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + /* filedata may be obsoleted by concurrent copyup, but no problem */ + err = vfsub_read_u(h_file, buf, count, ppos); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +/* + * todo: very ugly + * it locks both of i_mutex and si_rwsem for read in safe. + * if the plink maintenance mode continues forever (that is the problem), + * may loop forever. + */ +static void au_mtx_and_read_lock(struct inode *inode) +{ + int err; + struct super_block *sb = inode->i_sb; + + while (1) { + inode_lock(inode); + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (!err) + break; + inode_unlock(inode); + si_read_lock(sb, AuLock_NOPLMW); + si_read_unlock(sb); + } +} + +static ssize_t aufs_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + char __user *buf = (char __user *)ubuf; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_write_u(h_file, buf, count, ppos); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio, + struct iov_iter *iov_iter) +{ + ssize_t err; + struct file *file; + ssize_t (*iter)(struct kiocb *, struct iov_iter *); + + err = security_file_permission(h_file, rw); + if (unlikely(err)) + goto out; + + err = -ENOSYS; /* the branch doesn't have its ->(read|write)_iter() */ + iter = NULL; + if (rw == MAY_READ) + iter = h_file->f_op->read_iter; + else if (rw == MAY_WRITE) + iter = h_file->f_op->write_iter; + + file = kio->ki_filp; + kio->ki_filp = h_file; + if (iter) { + lockdep_off(); + err = iter(kio, iov_iter); + lockdep_on(); + } else + /* currently there is no such fs */ + WARN_ON_ONCE(1); + kio->ki_filp = file; + +out: + return err; +} + +static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ + ssize_t err; + struct file *file, *h_file; + struct inode *inode; + struct super_block *sb; + + file = kio->ki_filp; + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + if (au_test_loopback_kthread()) { + au_warn_loopback(h_file->f_path.dentry->d_sb); + if (file->f_mapping != h_file->f_mapping) { + file->f_mapping = h_file->f_mapping; + smp_mb(); /* unnecessary? */ + } + } + fi_read_unlock(file); + + err = au_do_iter(h_file, MAY_READ, kio, iov_iter); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *file, *h_file; + + file = kio->ki_filp; + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t err; + struct file *h_file; + struct inode *inode; + struct super_block *sb; + + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_splice_to(h_file, ppos, pipe, len, flags); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t +aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, + size_t len, unsigned int flags) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_splice_from(pipe, h_file, ppos, len, flags); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static long aufs_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + long err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + lockdep_off(); + err = vfs_fallocate(h_file, mode, offset, len); + lockdep_on(); + au_write_post(inode, h_file, &wpre, /*written*/1); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos, + struct file *dst, loff_t dst_pos, + size_t len, unsigned int flags) +{ + ssize_t err; + struct au_write_pre wpre; + enum { SRC, DST }; + struct { + struct inode *inode; + struct file *h_file; + struct super_block *h_sb; + } a[2]; +#define a_src a[SRC] +#define a_dst a[DST] + + err = -EINVAL; + a_src.inode = file_inode(src); + if (unlikely(!S_ISREG(a_src.inode->i_mode))) + goto out; + a_dst.inode = file_inode(dst); + if (unlikely(!S_ISREG(a_dst.inode->i_mode))) + goto out; + + au_mtx_and_read_lock(a_dst.inode); + /* + * in order to match the order in di_write_lock2_{child,parent}(), + * use f_path.dentry for this comparison. + */ + if (src->f_path.dentry < dst->f_path.dentry) { + a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1); + err = PTR_ERR(a_src.h_file); + if (IS_ERR(a_src.h_file)) + goto out_si; + + wpre.lsc = AuLsc_FI_2; + a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); + err = PTR_ERR(a_dst.h_file); + if (IS_ERR(a_dst.h_file)) { + au_read_post(a_src.inode, a_src.h_file); + goto out_si; + } + } else { + wpre.lsc = AuLsc_FI_1; + a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); + err = PTR_ERR(a_dst.h_file); + if (IS_ERR(a_dst.h_file)) + goto out_si; + + a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2); + err = PTR_ERR(a_src.h_file); + if (IS_ERR(a_src.h_file)) { + au_write_post(a_dst.inode, a_dst.h_file, &wpre, + /*written*/0); + goto out_si; + } + } + + err = -EXDEV; + a_src.h_sb = file_inode(a_src.h_file)->i_sb; + a_dst.h_sb = file_inode(a_dst.h_file)->i_sb; + if (unlikely(a_src.h_sb != a_dst.h_sb)) { + AuDbgFile(src); + AuDbgFile(dst); + goto out_file; + } + + err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file, + dst_pos, len, flags); + +out_file: + au_write_post(a_dst.inode, a_dst.h_file, &wpre, err); + fi_read_unlock(src); + au_read_post(a_src.inode, a_src.h_file); +out_si: + si_read_unlock(a_dst.inode->i_sb); + inode_unlock(a_dst.inode); +out: + return err; +#undef a_src +#undef a_dst +} + +/* ---------------------------------------------------------------------- */ + +/* + * The locking order around current->mmap_sem. + * - in most and regular cases + * file I/O syscall -- aufs_read() or something + * -- si_rwsem for read -- mmap_sem + * (Note that [fdi]i_rwsem are released before mmap_sem). + * - in mmap case + * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem + * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for + * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held + * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though. + * It means that when aufs acquires si_rwsem for write, the process should never + * acquire mmap_sem. + * + * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a + * problem either since any directory is not able to be mmap-ed. + * The similar scenario is applied to aufs_readlink() too. + */ + +#if 0 /* stop calling security_file_mmap() */ +/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */ +#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b) + +static unsigned long au_arch_prot_conv(unsigned long flags) +{ + /* currently ppc64 only */ +#ifdef CONFIG_PPC64 + /* cf. linux/arch/powerpc/include/asm/mman.h */ + AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO); + return AuConv_VM_PROT(flags, SAO); +#else + AuDebugOn(arch_calc_vm_prot_bits(-1)); + return 0; +#endif +} + +static unsigned long au_prot_conv(unsigned long flags) +{ + return AuConv_VM_PROT(flags, READ) + | AuConv_VM_PROT(flags, WRITE) + | AuConv_VM_PROT(flags, EXEC) + | au_arch_prot_conv(flags); +} + +/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ +#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) + +static unsigned long au_flag_conv(unsigned long flags) +{ + return AuConv_VM_MAP(flags, GROWSDOWN) + | AuConv_VM_MAP(flags, DENYWRITE) + | AuConv_VM_MAP(flags, LOCKED); +} +#endif + +static int aufs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err; + const unsigned char wlock + = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED); + struct super_block *sb; + struct file *h_file; + struct inode *inode; + + AuDbgVmRegion(file, vma); + + inode = file_inode(file); + sb = inode->i_sb; + lockdep_off(); + si_read_lock(sb, AuLock_NOPLMW); + + h_file = au_write_pre(file, wlock, /*wpre*/NULL); + lockdep_on(); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = 0; + au_set_mmapped(file); + au_vm_file_reset(vma, h_file); + /* + * we cannot call security_mmap_file() here since it may acquire + * mmap_sem or i_mutex. + * + * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags), + * au_flag_conv(vma->vm_flags)); + */ + if (!err) + err = call_mmap(h_file, vma); + if (!err) { + au_vm_prfile_set(vma, file); + fsstack_copy_attr_atime(inode, file_inode(h_file)); + goto out_fput; /* success */ + } + au_unset_mmapped(file); + au_vm_file_reset(vma, file); + +out_fput: + lockdep_off(); + ii_write_unlock(inode); + lockdep_on(); + fput(h_file); +out: + lockdep_off(); + si_read_unlock(sb); + lockdep_on(); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + err = 0; /* -EBADF; */ /* posix? */ + if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out_unlock; + + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + au_write_post(inode, h_file, &wpre, /*written*/0); + +out_unlock: + si_read_unlock(inode->i_sb); + inode_unlock(inode); +out: + return err; +} + +static int aufs_fasync(int fd, struct file *file, int flag) +{ + int err; + struct file *h_file; + struct super_block *sb; + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + if (h_file->f_op->fasync) + err = h_file->f_op->fasync(fd, h_file, flag); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + return err; +} + +static int aufs_setfl(struct file *file, unsigned long arg) +{ + int err; + struct file *h_file; + struct super_block *sb; + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + /* stop calling h_file->fasync */ + arg |= vfsub_file_flags(file) & FASYNC; + err = setfl(/*unused fd*/-1, h_file, arg); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* no one supports this operation, currently */ +#if 0 /* reserved for future use */ +static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, + size_t len, loff_t *pos, int more) +{ +} +#endif + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_file_fop = { + .owner = THIS_MODULE, + + .llseek = default_llseek, + + .read = aufs_read, + .write = aufs_write, + .read_iter = aufs_read_iter, + .write_iter = aufs_write_iter, + +#ifdef CONFIG_AUFS_POLL + .poll = aufs_poll, +#endif + .unlocked_ioctl = aufs_ioctl_nondir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_compat_ioctl_nondir, +#endif + .mmap = aufs_mmap, + .open = aufs_open_nondir, + .flush = aufs_flush_nondir, + .release = aufs_release_nondir, + .fsync = aufs_fsync_nondir, + .fasync = aufs_fasync, + /* .sendpage = aufs_sendpage, */ + .setfl = aufs_setfl, + .splice_write = aufs_splice_write, + .splice_read = aufs_splice_read, +#if 0 /* reserved for future use */ + .aio_splice_write = aufs_aio_splice_write, + .aio_splice_read = aufs_aio_splice_read, +#endif + .fallocate = aufs_fallocate, + .copy_file_range = aufs_copy_file_range +}; diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c new file mode 100644 index 000000000000..9cef93b42993 --- /dev/null +++ b/fs/aufs/fhsm.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2011-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * File-based Hierarchy Storage Management + */ + +#include <linux/anon_inodes.h> +#include <linux/poll.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include "aufs.h" + +static aufs_bindex_t au_fhsm_bottom(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + AuDebugOn(!fhsm); + return fhsm->fhsm_bottom; +} + +void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + AuDebugOn(!fhsm); + fhsm->fhsm_bottom = bindex; +} + +/* ---------------------------------------------------------------------- */ + +static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br) +{ + struct au_br_fhsm *bf; + + bf = br->br_fhsm; + MtxMustLock(&bf->bf_lock); + + return !bf->bf_readable + || time_after(jiffies, + bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire); +} + +/* ---------------------------------------------------------------------- */ + +static void au_fhsm_notify(struct super_block *sb, int val) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + if (au_fhsm_pid(fhsm) + && atomic_read(&fhsm->fhsm_readable) != -1) { + atomic_set(&fhsm->fhsm_readable, val); + if (val) + wake_up(&fhsm->fhsm_wqh); + } +} + +static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex, + struct aufs_stfs *rstfs, int do_lock, int do_notify) +{ + int err; + struct au_branch *br; + struct au_br_fhsm *bf; + + br = au_sbr(sb, bindex); + AuDebugOn(au_br_rdonly(br)); + bf = br->br_fhsm; + AuDebugOn(!bf); + + if (do_lock) + mutex_lock(&bf->bf_lock); + else + MtxMustLock(&bf->bf_lock); + + /* sb->s_root for NFS is unreliable */ + err = au_br_stfs(br, &bf->bf_stfs); + if (unlikely(err)) { + AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err); + goto out; + } + + bf->bf_jiffy = jiffies; + bf->bf_readable = 1; + if (do_notify) + au_fhsm_notify(sb, /*val*/1); + if (rstfs) + *rstfs = bf->bf_stfs; + +out: + if (do_lock) + mutex_unlock(&bf->bf_lock); + au_fhsm_notify(sb, /*val*/1); + + return err; +} + +void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force) +{ + int err; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + struct au_branch *br; + struct au_br_fhsm *bf; + + AuDbg("b%d, force %d\n", bindex, force); + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + if (!au_ftest_si(sbinfo, FHSM) + || fhsm->fhsm_bottom == bindex) + return; + + br = au_sbr(sb, bindex); + bf = br->br_fhsm; + AuDebugOn(!bf); + mutex_lock(&bf->bf_lock); + if (force + || au_fhsm_pid(fhsm) + || au_fhsm_test_jiffy(sbinfo, br)) + err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0, + /*do_notify*/1); + mutex_unlock(&bf->bf_lock); +} + +void au_fhsm_wrote_all(struct super_block *sb, int force) +{ + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + /* exclude the bottom */ + bbot = au_fhsm_bottom(sb); + for (bindex = 0; bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm)) + au_fhsm_wrote(sb, bindex, force); + } +} + +/* ---------------------------------------------------------------------- */ + +static __poll_t au_fhsm_poll(struct file *file, struct poll_table_struct *wait) +{ + __poll_t mask; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + mask = 0; + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; + poll_wait(file, &fhsm->fhsm_wqh, wait); + if (atomic_read(&fhsm->fhsm_readable)) + mask = EPOLLIN /* | EPOLLRDNORM */; + + if (!mask) + AuDbg("mask 0x%x\n", mask); + return mask; +} + +static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr, + struct aufs_stfs *stfs, __s16 brid) +{ + int err; + + err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs)); + if (!err) + err = __put_user(brid, &stbr->brid); + if (unlikely(err)) + err = -EFAULT; + + return err; +} + +static ssize_t au_fhsm_do_read(struct super_block *sb, + struct aufs_stbr __user *stbr, size_t count) +{ + ssize_t err; + int nstbr; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + struct au_br_fhsm *bf; + + /* except the bottom branch */ + err = 0; + nstbr = 0; + bbot = au_fhsm_bottom(sb); + for (bindex = 0; !err && bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (!au_br_fhsm(br->br_perm)) + continue; + + bf = br->br_fhsm; + mutex_lock(&bf->bf_lock); + if (bf->bf_readable) { + err = -EFAULT; + if (count >= sizeof(*stbr)) + err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs, + br->br_id); + if (!err) { + bf->bf_readable = 0; + count -= sizeof(*stbr); + nstbr++; + } + } + mutex_unlock(&bf->bf_lock); + } + if (!err) + err = sizeof(*stbr) * nstbr; + + return err; +} + +static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count, + loff_t *pos) +{ + ssize_t err; + int readable; + aufs_bindex_t nfhsm, bindex, bbot; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + struct au_branch *br; + struct super_block *sb; + + err = 0; + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; +need_data: + spin_lock_irq(&fhsm->fhsm_wqh.lock); + if (!atomic_read(&fhsm->fhsm_readable)) { + if (vfsub_file_flags(file) & O_NONBLOCK) + err = -EAGAIN; + else + err = wait_event_interruptible_locked_irq + (fhsm->fhsm_wqh, + atomic_read(&fhsm->fhsm_readable)); + } + spin_unlock_irq(&fhsm->fhsm_wqh.lock); + if (unlikely(err)) + goto out; + + /* sb may already be dead */ + au_rw_read_lock(&sbinfo->si_rwsem); + readable = atomic_read(&fhsm->fhsm_readable); + if (readable > 0) { + sb = sbinfo->si_sb; + AuDebugOn(!sb); + /* exclude the bottom branch */ + nfhsm = 0; + bbot = au_fhsm_bottom(sb); + for (bindex = 0; bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm)) + nfhsm++; + } + err = -EMSGSIZE; + if (nfhsm * sizeof(struct aufs_stbr) <= count) { + atomic_set(&fhsm->fhsm_readable, 0); + err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf, + count); + } + } + au_rw_read_unlock(&sbinfo->si_rwsem); + if (!readable) + goto need_data; + +out: + return err; +} + +static int au_fhsm_release(struct inode *inode, struct file *file) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + /* sb may already be dead */ + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; + spin_lock(&fhsm->fhsm_spin); + fhsm->fhsm_pid = 0; + spin_unlock(&fhsm->fhsm_spin); + kobject_put(&sbinfo->si_kobj); + + return 0; +} + +static const struct file_operations au_fhsm_fops = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .read = au_fhsm_read, + .poll = au_fhsm_poll, + .release = au_fhsm_release +}; + +int au_fhsm_fd(struct super_block *sb, int oflags) +{ + int err, fd; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = -EINVAL; + if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK))) + goto out; + + err = 0; + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + spin_lock(&fhsm->fhsm_spin); + if (!fhsm->fhsm_pid) + fhsm->fhsm_pid = current->pid; + else + err = -EBUSY; + spin_unlock(&fhsm->fhsm_spin); + if (unlikely(err)) + goto out; + + oflags |= O_RDONLY; + /* oflags |= FMODE_NONOTIFY; */ + fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags); + err = fd; + if (unlikely(fd < 0)) + goto out_pid; + + /* succeed regardless 'fhsm' status */ + kobject_get(&sbinfo->si_kobj); + si_noflush_read_lock(sb); + if (au_ftest_si(sbinfo, FHSM)) + au_fhsm_wrote_all(sb, /*force*/0); + si_read_unlock(sb); + goto out; /* success */ + +out_pid: + spin_lock(&fhsm->fhsm_spin); + fhsm->fhsm_pid = 0; + spin_unlock(&fhsm->fhsm_spin); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_fhsm_br_alloc(struct au_branch *br) +{ + int err; + + err = 0; + br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS); + if (br->br_fhsm) + au_br_fhsm_init(br->br_fhsm); + else + err = -ENOMEM; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_fhsm_fin(struct super_block *sb) +{ + au_fhsm_notify(sb, /*val*/-1); +} + +void au_fhsm_init(struct au_sbinfo *sbinfo) +{ + struct au_fhsm *fhsm; + + fhsm = &sbinfo->si_fhsm; + spin_lock_init(&fhsm->fhsm_spin); + init_waitqueue_head(&fhsm->fhsm_wqh); + atomic_set(&fhsm->fhsm_readable, 0); + fhsm->fhsm_expire + = msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC); + fhsm->fhsm_bottom = -1; +} + +void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec) +{ + sbinfo->si_fhsm.fhsm_expire + = msecs_to_jiffies(sec * MSEC_PER_SEC); +} + +void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo) +{ + unsigned int u; + + if (!au_ftest_si(sbinfo, FHSM)) + return; + + u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC; + if (u != AUFS_FHSM_CACHE_DEF_SEC) + seq_printf(seq, ",fhsm_sec=%u", u); +} diff --git a/fs/aufs/file.c b/fs/aufs/file.c new file mode 100644 index 000000000000..b0075b57d8bc --- /dev/null +++ b/fs/aufs/file.c @@ -0,0 +1,863 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * handling file/dir, and address_space operation + */ + +#ifdef CONFIG_AUFS_DEBUG +#include <linux/migrate.h> +#endif +#include <linux/pagemap.h> +#include "aufs.h" + +/* drop flags for writing */ +unsigned int au_file_roflags(unsigned int flags) +{ + flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC); + flags |= O_RDONLY | O_NOATIME; + return flags; +} + +/* common functions to regular file and dir */ +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file, int force_wr) +{ + struct file *h_file; + struct dentry *h_dentry; + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + struct path h_path; + int err; + + /* a race condition can happen between open and unlink/rmdir */ + h_file = ERR_PTR(-ENOENT); + h_dentry = au_h_dptr(dentry, bindex); + if (au_test_nfsd() && (!h_dentry || d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); + spin_lock(&h_dentry->d_lock); + err = (!d_unhashed(dentry) && d_unlinked(h_dentry)) + /* || !d_inode(dentry)->i_nlink */ + ; + spin_unlock(&h_dentry->d_lock); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + br = au_sbr(sb, bindex); + err = au_br_test_oflag(flags, br); + h_file = ERR_PTR(err); + if (unlikely(err)) + goto out; + + /* drop flags for writing */ + if (au_test_ro(sb, bindex, d_inode(dentry))) { + if (force_wr && !(flags & O_WRONLY)) + force_wr = 0; + flags = au_file_roflags(flags); + if (force_wr) { + h_file = ERR_PTR(-EROFS); + flags = au_file_roflags(flags); + if (unlikely(vfsub_native_ro(h_inode) + || IS_APPEND(h_inode))) + goto out; + flags &= ~O_ACCMODE; + flags |= O_WRONLY; + } + } + flags &= ~O_CREAT; + au_lcnt_inc(&br->br_nfiles); + h_path.dentry = h_dentry; + h_path.mnt = au_br_mnt(br); + h_file = vfsub_dentry_open(&h_path, flags); + if (IS_ERR(h_file)) + goto out_br; + + if (flags & __FMODE_EXEC) { + err = deny_write_access(h_file); + if (unlikely(err)) { + fput(h_file); + h_file = ERR_PTR(err); + goto out_br; + } + } + fsnotify_open(h_file); + goto out; /* success */ + +out_br: + au_lcnt_dec(&br->br_nfiles); +out: + return h_file; +} + +static int au_cmoo(struct dentry *dentry) +{ + int err, cmoo, matched; + unsigned int udba; + struct path h_path; + struct au_pin pin; + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = -1, + .bsrc = -1, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + struct inode *delegated; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + pid_t pid; + struct au_branch *br; + struct dentry *parent; + struct au_hinode *hdir; + + DiMustWriteLock(dentry); + IiMustWriteLock(d_inode(dentry)); + + err = 0; + if (IS_ROOT(dentry)) + goto out; + cpg.bsrc = au_dbtop(dentry); + if (!cpg.bsrc) + goto out; + + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + pid = au_fhsm_pid(fhsm); + rcu_read_lock(); + matched = (pid + && (current->pid == pid + || rcu_dereference(current->real_parent)->pid == pid)); + rcu_read_unlock(); + if (matched) + goto out; + + br = au_sbr(sb, cpg.bsrc); + cmoo = au_br_cmoo(br->br_perm); + if (!cmoo) + goto out; + if (!d_is_reg(dentry)) + cmoo &= AuBrAttr_COO_ALL; + if (!cmoo) + goto out; + + parent = dget_parent(dentry); + di_write_lock_parent(parent); + err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1); + cpg.bdst = err; + if (unlikely(err < 0)) { + err = 0; /* there is no upper writable branch */ + goto out_dgrade; + } + AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst); + + /* do not respect the coo attrib for the target branch */ + err = au_cpup_dirs(dentry, cpg.bdst); + if (unlikely(err)) + goto out_dgrade; + + di_downgrade_lock(parent, AuLock_IR); + udba = au_opt_udba(sb); + err = au_pin(&pin, dentry, cpg.bdst, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_parent; + + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + if (unlikely(err)) + goto out_parent; + if (!(cmoo & AuBrWAttr_MOO)) + goto out_parent; /* success */ + + err = au_pin(&pin, dentry, cpg.bsrc, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_parent; + + h_path.mnt = au_br_mnt(br); + h_path.dentry = au_h_dptr(dentry, cpg.bsrc); + hdir = au_hi(d_inode(parent), cpg.bsrc); + delegated = NULL; + err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1); + au_unpin(&pin); + /* todo: keep h_dentry or not? */ + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + if (unlikely(err)) { + pr_err("unlink %pd after coo failed (%d), ignored\n", + dentry, err); + err = 0; + } + goto out_parent; /* success */ + +out_dgrade: + di_downgrade_lock(parent, AuLock_IR); +out_parent: + di_read_unlock(parent, AuLock_IR); + dput(parent); +out: + AuTraceErr(err); + return err; +} + +int au_do_open(struct file *file, struct au_do_open_args *args) +{ + int err, aopen = args->aopen; + struct dentry *dentry; + struct au_finfo *finfo; + + if (!aopen) + err = au_finfo_init(file, args->fidir); + else { + lockdep_off(); + err = au_finfo_init(file, args->fidir); + lockdep_on(); + } + if (unlikely(err)) + goto out; + + dentry = file->f_path.dentry; + AuDebugOn(IS_ERR_OR_NULL(dentry)); + di_write_lock_child(dentry); + err = au_cmoo(dentry); + di_downgrade_lock(dentry, AuLock_IR); + if (!err) { + if (!aopen) + err = args->open(file, vfsub_file_flags(file), NULL); + else { + lockdep_off(); + err = args->open(file, vfsub_file_flags(file), + args->h_file); + lockdep_on(); + } + } + di_read_unlock(dentry, AuLock_IR); + + finfo = au_fi(file); + if (!err) { + finfo->fi_file = file; + au_hbl_add(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + } + if (!aopen) + fi_write_unlock(file); + else { + lockdep_off(); + fi_write_unlock(file); + lockdep_on(); + } + if (unlikely(err)) { + finfo->fi_hdir = NULL; + au_finfo_fin(file); + } + +out: + AuTraceErr(err); + return err; +} + +int au_reopen_nondir(struct file *file) +{ + int err; + aufs_bindex_t btop; + struct dentry *dentry; + struct au_branch *br; + struct file *h_file, *h_file_tmp; + + dentry = file->f_path.dentry; + btop = au_dbtop(dentry); + br = au_sbr(dentry->d_sb, btop); + h_file_tmp = NULL; + if (au_fbtop(file) == btop) { + h_file = au_hf_top(file); + if (file->f_mode == h_file->f_mode) + return 0; /* success */ + h_file_tmp = h_file; + get_file(h_file_tmp); + au_lcnt_inc(&br->br_nfiles); + au_set_h_fptr(file, btop, NULL); + } + AuDebugOn(au_fi(file)->fi_hdir); + /* + * it can happen + * file exists on both of rw and ro + * open --> dbtop and fbtop are both 0 + * prepend a branch as rw, "rw" become ro + * remove rw/file + * delete the top branch, "rw" becomes rw again + * --> dbtop is 1, fbtop is still 0 + * write --> fbtop is 0 but dbtop is 1 + */ + /* AuDebugOn(au_fbtop(file) < btop); */ + + h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC, + file, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) { + if (h_file_tmp) { + /* revert */ + au_set_h_fptr(file, btop, h_file_tmp); + h_file_tmp = NULL; + } + goto out; /* todo: close all? */ + } + + err = 0; + au_set_fbtop(file, btop); + au_set_h_fptr(file, btop, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + +out: + if (h_file_tmp) { + fput(h_file_tmp); + au_lcnt_dec(&br->br_nfiles); + } + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_reopen_wh(struct file *file, aufs_bindex_t btgt, + struct dentry *hi_wh) +{ + int err; + aufs_bindex_t btop; + struct au_dinfo *dinfo; + struct dentry *h_dentry; + struct au_hdentry *hdp; + + dinfo = au_di(file->f_path.dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + btop = dinfo->di_btop; + dinfo->di_btop = btgt; + hdp = au_hdentry(dinfo, btgt); + h_dentry = hdp->hd_dentry; + hdp->hd_dentry = hi_wh; + err = au_reopen_nondir(file); + hdp->hd_dentry = h_dentry; + dinfo->di_btop = btop; + + return err; +} + +static int au_ready_to_write_wh(struct file *file, loff_t len, + aufs_bindex_t bcpup, struct au_pin *pin) +{ + int err; + struct inode *inode, *h_inode; + struct dentry *h_dentry, *hi_wh; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = bcpup, + .bsrc = -1, + .len = len, + .pin = pin + }; + + au_update_dbtop(cpg.dentry); + inode = d_inode(cpg.dentry); + h_inode = NULL; + if (au_dbtop(cpg.dentry) <= bcpup + && au_dbbot(cpg.dentry) >= bcpup) { + h_dentry = au_h_dptr(cpg.dentry, bcpup); + if (h_dentry && d_is_positive(h_dentry)) + h_inode = d_inode(h_dentry); + } + hi_wh = au_hi_wh(inode, bcpup); + if (!hi_wh && !h_inode) + err = au_sio_cpup_wh(&cpg, file); + else + /* already copied-up after unlink */ + err = au_reopen_wh(file, bcpup, hi_wh); + + if (!err + && (inode->i_nlink > 1 + || (inode->i_state & I_LINKABLE)) + && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK)) + au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup)); + + return err; +} + +/* + * prepare the @file for writing. + */ +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin) +{ + int err; + aufs_bindex_t dbtop; + struct dentry *parent; + struct inode *inode; + struct super_block *sb; + struct file *h_file; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = -1, + .bsrc = -1, + .len = len, + .pin = pin, + .flags = AuCpup_DTIME + }; + + sb = cpg.dentry->d_sb; + inode = d_inode(cpg.dentry); + cpg.bsrc = au_fbtop(file); + err = au_test_ro(sb, cpg.bsrc, inode); + if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) { + err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE, + /*flags*/0); + goto out; + } + + /* need to cpup or reopen */ + parent = dget_parent(cpg.dentry); + di_write_lock_parent(parent); + err = AuWbrCopyup(au_sbi(sb), cpg.dentry); + cpg.bdst = err; + if (unlikely(err < 0)) + goto out_dgrade; + err = 0; + + if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) { + err = au_cpup_dirs(cpg.dentry, cpg.bdst); + if (unlikely(err)) + goto out_dgrade; + } + + err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_dgrade; + + dbtop = au_dbtop(cpg.dentry); + if (dbtop <= cpg.bdst) + cpg.bsrc = cpg.bdst; + + if (dbtop <= cpg.bdst /* just reopen */ + || !d_unhashed(cpg.dentry) /* copyup and reopen */ + ) { + h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0); + if (IS_ERR(h_file)) + err = PTR_ERR(h_file); + else { + di_downgrade_lock(parent, AuLock_IR); + if (dbtop > cpg.bdst) + err = au_sio_cpup_simple(&cpg); + if (!err) + err = au_reopen_nondir(file); + au_h_open_post(cpg.dentry, cpg.bsrc, h_file); + } + } else { /* copyup as wh and reopen */ + /* + * since writable hfsplus branch is not supported, + * h_open_pre/post() are unnecessary. + */ + err = au_ready_to_write_wh(file, len, cpg.bdst, pin); + di_downgrade_lock(parent, AuLock_IR); + } + + if (!err) { + au_pin_set_parent_lflag(pin, /*lflag*/0); + goto out_dput; /* success */ + } + au_unpin(pin); + goto out_unlock; + +out_dgrade: + di_downgrade_lock(parent, AuLock_IR); +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_dput: + dput(parent); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)) +{ + int err; + struct super_block *sb; + struct inode *inode; + + inode = file_inode(file); + sb = inode->i_sb; + si_noflush_read_lock(sb); + fi_read_lock(file); + ii_read_lock_child(inode); + + err = flush(file, id); + au_cpup_attr_timesizes(inode); + + ii_read_unlock(inode); + fi_read_unlock(file); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_file_refresh_by_inode(struct file *file, int *need_reopen) +{ + int err; + struct au_pin pin; + struct au_finfo *finfo; + struct dentry *parent, *hi_wh; + struct inode *inode; + struct super_block *sb; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = -1, + .bsrc = -1, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME + }; + + FiMustWriteLock(file); + + err = 0; + finfo = au_fi(file); + sb = cpg.dentry->d_sb; + inode = d_inode(cpg.dentry); + cpg.bdst = au_ibtop(inode); + if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry)) + goto out; + + parent = dget_parent(cpg.dentry); + if (au_test_ro(sb, cpg.bdst, inode)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(au_sbi(sb), cpg.dentry); + cpg.bdst = err; + di_read_unlock(parent, !AuLock_IR); + if (unlikely(err < 0)) + goto out_parent; + err = 0; + } + + di_read_lock_parent(parent, AuLock_IR); + hi_wh = au_hi_wh(inode, cpg.bdst); + if (!S_ISDIR(inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode) + && !d_unhashed(cpg.dentry) + && cpg.bdst < au_dbtop(cpg.dentry)) { + err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst); + if (unlikely(err)) + goto out_unlock; + + /* always superio. */ + err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (!err) { + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + } + } else if (hi_wh) { + /* already copied-up after unlink */ + err = au_reopen_wh(file, cpg.bdst, hi_wh); + *need_reopen = 0; + } + +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_parent: + dput(parent); +out: + return err; +} + +static void au_do_refresh_dir(struct file *file) +{ + aufs_bindex_t bindex, bbot, new_bindex, brid; + struct au_hfile *p, tmp, *q; + struct au_finfo *finfo; + struct super_block *sb; + struct au_fidir *fidir; + + FiMustWriteLock(file); + + sb = file->f_path.dentry->d_sb; + finfo = au_fi(file); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + p = fidir->fd_hfile + finfo->fi_btop; + brid = p->hf_br->br_id; + bbot = fidir->fd_bbot; + for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) { + if (!p->hf_file) + continue; + + new_bindex = au_br_index(sb, p->hf_br->br_id); + if (new_bindex == bindex) + continue; + if (new_bindex < 0) { + au_set_h_fptr(file, bindex, NULL); + continue; + } + + /* swap two lower inode, and loop again */ + q = fidir->fd_hfile + new_bindex; + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hf_file) { + bindex--; + p--; + } + } + + p = fidir->fd_hfile; + if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) { + bbot = au_sbbot(sb); + for (finfo->fi_btop = 0; finfo->fi_btop <= bbot; + finfo->fi_btop++, p++) + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; + au_hfput(p, /*execed*/0); + } + } else { + bbot = au_br_index(sb, brid); + for (finfo->fi_btop = 0; finfo->fi_btop < bbot; + finfo->fi_btop++, p++) + if (p->hf_file) + au_hfput(p, /*execed*/0); + bbot = au_sbbot(sb); + } + + p = fidir->fd_hfile + bbot; + for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop; + fidir->fd_bbot--, p--) + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; + au_hfput(p, /*execed*/0); + } + AuDebugOn(fidir->fd_bbot < finfo->fi_btop); +} + +/* + * after branch manipulating, refresh the file. + */ +static int refresh_file(struct file *file, int (*reopen)(struct file *file)) +{ + int err, need_reopen, nbr; + aufs_bindex_t bbot, bindex; + struct dentry *dentry; + struct super_block *sb; + struct au_finfo *finfo; + struct au_hfile *hfile; + + dentry = file->f_path.dentry; + sb = dentry->d_sb; + nbr = au_sbbot(sb) + 1; + finfo = au_fi(file); + if (!finfo->fi_hdir) { + hfile = &finfo->fi_htop; + AuDebugOn(!hfile->hf_file); + bindex = au_br_index(sb, hfile->hf_br->br_id); + AuDebugOn(bindex < 0); + if (bindex != finfo->fi_btop) + au_set_fbtop(file, bindex); + } else { + err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0); + if (unlikely(err)) + goto out; + au_do_refresh_dir(file); + } + + err = 0; + need_reopen = 1; + if (!au_test_mmapped(file)) + err = au_file_refresh_by_inode(file, &need_reopen); + if (finfo->fi_hdir) + /* harmless if err */ + au_fidir_realloc(finfo, nbr, /*may_shrink*/1); + if (!err && need_reopen && !d_unlinked(dentry)) + err = reopen(file); + if (!err) { + au_update_figen(file); + goto out; /* success */ + } + + /* error, close all lower files */ + if (finfo->fi_hdir) { + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); bindex <= bbot; bindex++) + au_set_h_fptr(file, bindex, NULL); + } + +out: + return err; +} + +/* common function to regular file and dir */ +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock, unsigned int fi_lsc) +{ + int err; + unsigned int sigen, figen; + aufs_bindex_t btop; + unsigned char pseudo_link; + struct dentry *dentry; + struct inode *inode; + + err = 0; + dentry = file->f_path.dentry; + inode = d_inode(dentry); + sigen = au_sigen(dentry->d_sb); + fi_write_lock_nested(file, fi_lsc); + figen = au_figen(file); + if (!fi_lsc) + di_write_lock_child(dentry); + else + di_write_lock_child2(dentry); + btop = au_dbtop(dentry); + pseudo_link = (btop != au_ibtop(inode)); + if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + goto out; /* success */ + } + + AuDbg("sigen %d, figen %d\n", sigen, figen); + if (au_digen_test(dentry, sigen)) { + err = au_reval_dpath(dentry, sigen); + AuDebugOn(!err && au_digen_test(dentry, sigen)); + } + + if (!err) + err = refresh_file(file, reopen); + if (!err) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + } else { + di_write_unlock(dentry); + fi_write_unlock(file); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* cf. aufs_nopage() */ +/* for madvise(2) */ +static int aufs_readpage(struct file *file __maybe_unused, struct page *page) +{ + unlock_page(page); + return 0; +} + +/* it will never be called, but necessary to support O_DIRECT */ +static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ BUG(); return 0; } + +/* they will never be called. */ +#ifdef CONFIG_AUFS_DEBUG +static int aufs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ AuUnsupport(); return 0; } +static int aufs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ AuUnsupport(); return 0; } +static int aufs_writepage(struct page *page, struct writeback_control *wbc) +{ AuUnsupport(); return 0; } + +static int aufs_set_page_dirty(struct page *page) +{ AuUnsupport(); return 0; } +static void aufs_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) +{ AuUnsupport(); } +static int aufs_releasepage(struct page *page, gfp_t gfp) +{ AuUnsupport(); return 0; } +#if 0 /* called by memory compaction regardless file */ +static int aufs_migratepage(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ AuUnsupport(); return 0; } +#endif +static bool aufs_isolate_page(struct page *page, isolate_mode_t mode) +{ AuUnsupport(); return true; } +static void aufs_putback_page(struct page *page) +{ AuUnsupport(); } +static int aufs_launder_page(struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_is_partially_uptodate(struct page *page, + unsigned long from, + unsigned long count) +{ AuUnsupport(); return 0; } +static void aufs_is_dirty_writeback(struct page *page, bool *dirty, + bool *writeback) +{ AuUnsupport(); } +static int aufs_error_remove_page(struct address_space *mapping, + struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ AuUnsupport(); return 0; } +static void aufs_swap_deactivate(struct file *file) +{ AuUnsupport(); } +#endif /* CONFIG_AUFS_DEBUG */ + +const struct address_space_operations aufs_aop = { + .readpage = aufs_readpage, + .direct_IO = aufs_direct_IO, +#ifdef CONFIG_AUFS_DEBUG + .writepage = aufs_writepage, + /* no writepages, because of writepage */ + .set_page_dirty = aufs_set_page_dirty, + /* no readpages, because of readpage */ + .write_begin = aufs_write_begin, + .write_end = aufs_write_end, + /* no bmap, no block device */ + .invalidatepage = aufs_invalidatepage, + .releasepage = aufs_releasepage, + /* is fallback_migrate_page ok? */ + /* .migratepage = aufs_migratepage, */ + .isolate_page = aufs_isolate_page, + .putback_page = aufs_putback_page, + .launder_page = aufs_launder_page, + .is_partially_uptodate = aufs_is_partially_uptodate, + .is_dirty_writeback = aufs_is_dirty_writeback, + .error_remove_page = aufs_error_remove_page, + .swap_activate = aufs_swap_activate, + .swap_deactivate = aufs_swap_deactivate +#endif /* CONFIG_AUFS_DEBUG */ +}; diff --git a/fs/aufs/file.h b/fs/aufs/file.h new file mode 100644 index 000000000000..d124d9c8216d --- /dev/null +++ b/fs/aufs/file.h @@ -0,0 +1,342 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file operations + */ + +#ifndef __AUFS_FILE_H__ +#define __AUFS_FILE_H__ + +#ifdef __KERNEL__ + +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/mm_types.h> +#include <linux/poll.h> +#include "rwsem.h" + +struct au_branch; +struct au_hfile { + struct file *hf_file; + struct au_branch *hf_br; +}; + +struct au_vdir; +struct au_fidir { + aufs_bindex_t fd_bbot; + aufs_bindex_t fd_nent; + struct au_vdir *fd_vdir_cache; + struct au_hfile fd_hfile[]; +}; + +static inline int au_fidir_sz(int nent) +{ + AuDebugOn(nent < 0); + return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent; +} + +struct au_finfo { + atomic_t fi_generation; + + struct au_rwsem fi_rwsem; + aufs_bindex_t fi_btop; + + /* do not union them */ + struct { /* for non-dir */ + struct au_hfile fi_htop; + atomic_t fi_mmapped; + }; + struct au_fidir *fi_hdir; /* for dir only */ + + struct hlist_bl_node fi_hlist; + struct file *fi_file; /* very ugly */ + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* file.c */ +extern const struct address_space_operations aufs_aop; +unsigned int au_file_roflags(unsigned int flags); +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file, int force_wr); +struct au_do_open_args { + int aopen; + int (*open)(struct file *file, int flags, + struct file *h_file); + struct au_fidir *fidir; + struct file *h_file; +}; +int au_do_open(struct file *file, struct au_do_open_args *args); +int au_reopen_nondir(struct file *file); +struct au_pin; +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin); +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock, unsigned int fi_lsc); +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)); + +/* poll.c */ +#ifdef CONFIG_AUFS_POLL +__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt); +#endif + +#ifdef CONFIG_AUFS_BR_HFSPLUS +/* hfsplus.c */ +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, + int force_wr); +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#else +AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry, + aufs_bindex_t bindex, int force_wr) +AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#endif + +/* f_op.c */ +extern const struct file_operations aufs_file_fop; +int au_do_open_nondir(struct file *file, int flags, struct file *h_file); +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file); +struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc); + +/* finfo.c */ +void au_hfput(struct au_hfile *hf, int execed); +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, + struct file *h_file); + +void au_update_figen(struct file *file); +struct au_fidir *au_fidir_alloc(struct super_block *sb); +int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink); + +void au_fi_init_once(void *_fi); +void au_finfo_fin(struct file *file); +int au_finfo_init(struct file *file, struct au_fidir *fidir); + +/* ioctl.c */ +long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, + unsigned long arg); +long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, + unsigned long arg); +#endif + +/* ---------------------------------------------------------------------- */ + +static inline struct au_finfo *au_fi(struct file *file) +{ + return file->private_data; +} + +/* ---------------------------------------------------------------------- */ + +#define fi_read_lock(f) au_rw_read_lock(&au_fi(f)->fi_rwsem) +#define fi_write_lock(f) au_rw_write_lock(&au_fi(f)->fi_rwsem) +#define fi_read_trylock(f) au_rw_read_trylock(&au_fi(f)->fi_rwsem) +#define fi_write_trylock(f) au_rw_write_trylock(&au_fi(f)->fi_rwsem) +/* +#define fi_read_trylock_nested(f) \ + au_rw_read_trylock_nested(&au_fi(f)->fi_rwsem) +#define fi_write_trylock_nested(f) \ + au_rw_write_trylock_nested(&au_fi(f)->fi_rwsem) +*/ + +#define fi_read_unlock(f) au_rw_read_unlock(&au_fi(f)->fi_rwsem) +#define fi_write_unlock(f) au_rw_write_unlock(&au_fi(f)->fi_rwsem) +#define fi_downgrade_lock(f) au_rw_dgrade_lock(&au_fi(f)->fi_rwsem) + +/* lock subclass for finfo */ +enum { + AuLsc_FI_1, + AuLsc_FI_2 +}; + +static inline void fi_read_lock_nested(struct file *f, unsigned int lsc) +{ + au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + +static inline void fi_write_lock_nested(struct file *f, unsigned int lsc) +{ + au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + +/* + * fi_read_lock_1, fi_write_lock_1, + * fi_read_lock_2, fi_write_lock_2 + */ +#define AuReadLockFunc(name) \ +static inline void fi_read_lock_##name(struct file *f) \ +{ fi_read_lock_nested(f, AuLsc_FI_##name); } + +#define AuWriteLockFunc(name) \ +static inline void fi_write_lock_##name(struct file *f) \ +{ fi_write_lock_nested(f, AuLsc_FI_##name); } + +#define AuRWLockFuncs(name) \ + AuReadLockFunc(name) \ + AuWriteLockFunc(name) + +AuRWLockFuncs(1); +AuRWLockFuncs(2); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem) +#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem) +#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: hard/soft set? */ +static inline aufs_bindex_t au_fbtop(struct file *file) +{ + FiMustAnyLock(file); + return au_fi(file)->fi_btop; +} + +static inline aufs_bindex_t au_fbbot_dir(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_bbot; +} + +static inline struct au_vdir *au_fvdir_cache(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_vdir_cache; +} + +static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + au_fi(file)->fi_btop = bindex; +} + +static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_bbot = bindex; +} + +static inline void au_set_fvdir_cache(struct file *file, + struct au_vdir *vdir_cache) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache; +} + +static inline struct file *au_hf_top(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(au_fi(file)->fi_hdir); + return au_fi(file)->fi_htop.hf_file; +} + +static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file; +} + +/* todo: memory barrier? */ +static inline unsigned int au_figen(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_generation); +} + +static inline void au_set_mmapped(struct file *f) +{ + if (atomic_inc_return(&au_fi(f)->fi_mmapped)) + return; + pr_warn("fi_mmapped wrapped around\n"); + while (!atomic_inc_return(&au_fi(f)->fi_mmapped)) + ; +} + +static inline void au_unset_mmapped(struct file *f) +{ + atomic_dec(&au_fi(f)->fi_mmapped); +} + +static inline int au_test_mmapped(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_mmapped); +} + +/* customize vma->vm_file */ + +static inline void au_do_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + f = vma->vm_file; + get_file(file); + vma->vm_file = file; + fput(f); +} + +#ifdef CONFIG_MMU +#define AuDbgVmRegion(file, vma) do {} while (0) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + au_do_vm_file_reset(vma, file); +} +#else +#define AuDbgVmRegion(file, vma) \ + AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file)) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + au_do_vm_file_reset(vma, file); + f = vma->vm_region->vm_file; + get_file(file); + vma->vm_region->vm_file = file; + fput(f); +} +#endif /* CONFIG_MMU */ + +/* handle vma->vm_prfile */ +static inline void au_vm_prfile_set(struct vm_area_struct *vma, + struct file *file) +{ + get_file(file); + vma->vm_prfile = file; +#ifndef CONFIG_MMU + get_file(file); + vma->vm_region->vm_prfile = file; +#endif +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FILE_H__ */ diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c new file mode 100644 index 000000000000..25077670a507 --- /dev/null +++ b/fs/aufs/finfo.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file private data + */ + +#include "aufs.h" + +void au_hfput(struct au_hfile *hf, int execed) +{ + if (execed) + allow_write_access(hf->hf_file); + fput(hf->hf_file); + hf->hf_file = NULL; + au_lcnt_dec(&hf->hf_br->br_nfiles); + hf->hf_br = NULL; +} + +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val) +{ + struct au_finfo *finfo = au_fi(file); + struct au_hfile *hf; + struct au_fidir *fidir; + + fidir = finfo->fi_hdir; + if (!fidir) { + AuDebugOn(finfo->fi_btop != bindex); + hf = &finfo->fi_htop; + } else + hf = fidir->fd_hfile + bindex; + + if (hf && hf->hf_file) + au_hfput(hf, vfsub_file_execed(file)); + if (val) { + FiMustWriteLock(file); + AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry)); + hf->hf_file = val; + hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex); + } +} + +void au_update_figen(struct file *file) +{ + atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry)); + /* smp_mb(); */ /* atomic_set */ +} + +/* ---------------------------------------------------------------------- */ + +struct au_fidir *au_fidir_alloc(struct super_block *sb) +{ + struct au_fidir *fidir; + int nbr; + + nbr = au_sbbot(sb) + 1; + if (nbr < 2) + nbr = 2; /* initial allocate for 2 branches */ + fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS); + if (fidir) { + fidir->fd_bbot = -1; + fidir->fd_nent = nbr; + } + + return fidir; +} + +int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink) +{ + int err; + struct au_fidir *fidir, *p; + + AuRwMustWriteLock(&finfo->fi_rwsem); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + + err = -ENOMEM; + p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr), + GFP_NOFS, may_shrink); + if (p) { + p->fd_nent = nbr; + finfo->fi_hdir = p; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_finfo_fin(struct file *file) +{ + struct au_finfo *finfo; + + au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles); + + finfo = au_fi(file); + AuDebugOn(finfo->fi_hdir); + AuRwDestroy(&finfo->fi_rwsem); + au_cache_free_finfo(finfo); +} + +void au_fi_init_once(void *_finfo) +{ + struct au_finfo *finfo = _finfo; + + au_rw_init(&finfo->fi_rwsem); +} + +int au_finfo_init(struct file *file, struct au_fidir *fidir) +{ + int err; + struct au_finfo *finfo; + struct dentry *dentry; + + err = -ENOMEM; + dentry = file->f_path.dentry; + finfo = au_cache_alloc_finfo(); + if (unlikely(!finfo)) + goto out; + + err = 0; + au_lcnt_inc(&au_sbi(dentry->d_sb)->si_nfiles); + au_rw_write_lock(&finfo->fi_rwsem); + finfo->fi_btop = -1; + finfo->fi_hdir = fidir; + atomic_set(&finfo->fi_generation, au_digen(dentry)); + /* smp_mb(); */ /* atomic_set */ + + file->private_data = finfo; + +out: + return err; +} diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h new file mode 100644 index 000000000000..af4bc6c0dd42 --- /dev/null +++ b/fs/aufs/fstype.h @@ -0,0 +1,401 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * judging filesystem type + */ + +#ifndef __AUFS_FSTYPE_H__ +#define __AUFS_FSTYPE_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/magic.h> +#include <linux/nfs_fs.h> +#include <linux/romfs_fs.h> + +static inline int au_test_aufs(struct super_block *sb) +{ + return sb->s_magic == AUFS_SUPER_MAGIC; +} + +static inline const char *au_sbtype(struct super_block *sb) +{ + return sb->s_type->name; +} + +static inline int au_test_iso9660(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ISO9660_FS) + return sb->s_magic == ISOFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_romfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ROMFS_FS) + return sb->s_magic == ROMFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_cramfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_CRAMFS) + return sb->s_magic == CRAMFS_MAGIC; +#endif + return 0; +} + +static inline int au_test_nfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NFS_FS) + return sb->s_magic == NFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_fuse(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_FUSE_FS) + return sb->s_magic == FUSE_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_XFS_FS) + return sb->s_magic == XFS_SB_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_tmpfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_TMPFS + return sb->s_magic == TMPFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ECRYPT_FS) + return !strcmp(au_sbtype(sb), "ecryptfs"); +#else + return 0; +#endif +} + +static inline int au_test_ramfs(struct super_block *sb) +{ + return sb->s_magic == RAMFS_MAGIC; +} + +static inline int au_test_ubifs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_UBIFS_FS) + return sb->s_magic == UBIFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_procfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_PROC_FS + return sb->s_magic == PROC_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_sysfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SYSFS + return sb->s_magic == SYSFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_configfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_CONFIGFS_FS) + return sb->s_magic == CONFIGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_minix(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_MINIX_FS) + return sb->s_magic == MINIX3_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC2 + || sb->s_magic == MINIX_SUPER_MAGIC + || sb->s_magic == MINIX_SUPER_MAGIC2; +#else + return 0; +#endif +} + +static inline int au_test_fat(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_FAT_FS) + return sb->s_magic == MSDOS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_msdos(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_vfat(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_securityfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SECURITYFS + return sb->s_magic == SECURITYFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_squashfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_SQUASHFS) + return sb->s_magic == SQUASHFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_btrfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_BTRFS_FS) + return sb->s_magic == BTRFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xenfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_XENFS) + return sb->s_magic == XENFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_debugfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_DEBUG_FS + return sb->s_magic == DEBUGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_nilfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NILFS) + return sb->s_magic == NILFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_hfsplus(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_HFSPLUS_FS) + return sb->s_magic == HFSPLUS_SUPER_MAGIC; +#else + return 0; +#endif +} + +/* ---------------------------------------------------------------------- */ +/* + * they can't be an aufs branch. + */ +static inline int au_test_fs_unsuppoted(struct super_block *sb) +{ + return +#ifndef CONFIG_AUFS_BR_RAMFS + au_test_ramfs(sb) || +#endif + au_test_procfs(sb) + || au_test_sysfs(sb) + || au_test_configfs(sb) + || au_test_debugfs(sb) + || au_test_securityfs(sb) + || au_test_xenfs(sb) + || au_test_ecryptfs(sb) + /* || !strcmp(au_sbtype(sb), "unionfs") */ + || au_test_aufs(sb); /* will be supported in next version */ +} + +static inline int au_test_fs_remote(struct super_block *sb) +{ + return !au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + && !au_test_ramfs(sb) +#endif + && !(sb->s_type->fs_flags & FS_REQUIRES_DEV); +} + +/* ---------------------------------------------------------------------- */ + +/* + * Note: these functions (below) are created after reading ->getattr() in all + * filesystems under linux/fs. it means we have to do so in every update... + */ + +/* + * some filesystems require getattr to refresh the inode attributes before + * referencing. + * in most cases, we can rely on the inode attribute in NFS (or every remote fs) + * and leave the work for d_revalidate() + */ +static inline int au_test_fs_refresh_iattr(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + /* || au_test_btrfs(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't maintain i_size or i_blocks. + */ +static inline int au_test_fs_bad_iattr_size(struct super_block *sb) +{ + return au_test_xfs(sb) + || au_test_btrfs(sb) + || au_test_ubifs(sb) + || au_test_hfsplus(sb) /* maintained, but incorrect */ + /* || au_test_minix(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't store the correct value in some of their inode + * attributes. + */ +static inline int au_test_fs_bad_iattr(struct super_block *sb) +{ + return au_test_fs_bad_iattr_size(sb) + || au_test_fat(sb) + || au_test_msdos(sb) + || au_test_vfat(sb); +} + +/* they don't check i_nlink in link(2) */ +static inline int au_test_fs_no_limit_nlink(struct super_block *sb) +{ + return au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + || au_test_ramfs(sb) +#endif + || au_test_ubifs(sb) + || au_test_hfsplus(sb); +} + +/* + * filesystems which sets S_NOATIME and S_NOCMTIME. + */ +static inline int au_test_fs_notime(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + || au_test_ubifs(sb) + ; +} + +/* temporary support for i#1 in cramfs */ +static inline int au_test_fs_unique_ino(struct inode *inode) +{ + if (au_test_cramfs(inode->i_sb)) + return inode->i_ino != 1; + return 1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * the filesystem where the xino files placed must support i/o after unlink and + * maintain i_size and i_blocks. + */ +static inline int au_test_fs_bad_xino(struct super_block *sb) +{ + return au_test_fs_remote(sb) + || au_test_fs_bad_iattr_size(sb) + /* don't want unnecessary work for xino */ + || au_test_aufs(sb) + || au_test_ecryptfs(sb) + || au_test_nilfs(sb); +} + +static inline int au_test_fs_trunc_xino(struct super_block *sb) +{ + return au_test_tmpfs(sb) + || au_test_ramfs(sb); +} + +/* + * test if the @sb is real-readonly. + */ +static inline int au_test_fs_rr(struct super_block *sb) +{ + return au_test_squashfs(sb) + || au_test_iso9660(sb) + || au_test_cramfs(sb) + || au_test_romfs(sb); +} + +/* + * test if the @inode is nfs with 'noacl' option + * NFS always sets SB_POSIXACL regardless its mount option 'noacl.' + */ +static inline int au_test_nfs_noacl(struct inode *inode) +{ + return au_test_nfs(inode->i_sb) + /* && IS_POSIXACL(inode) */ + && !nfs_server_capable(inode, NFS_CAP_ACLS); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FSTYPE_H__ */ diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h new file mode 100644 index 000000000000..4d5016bccc51 --- /dev/null +++ b/fs/aufs/hbl.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * helpers for hlist_bl.h + */ + +#ifndef __AUFS_HBL_H__ +#define __AUFS_HBL_H__ + +#ifdef __KERNEL__ + +#include <linux/list_bl.h> + +static inline void au_hbl_add(struct hlist_bl_node *node, + struct hlist_bl_head *hbl) +{ + hlist_bl_lock(hbl); + hlist_bl_add_head(node, hbl); + hlist_bl_unlock(hbl); +} + +static inline void au_hbl_del(struct hlist_bl_node *node, + struct hlist_bl_head *hbl) +{ + hlist_bl_lock(hbl); + hlist_bl_del(node); + hlist_bl_unlock(hbl); +} + +#define au_hbl_for_each(pos, head) \ + for (pos = hlist_bl_first(head); \ + pos; \ + pos = pos->next) + +static inline unsigned long au_hbl_count(struct hlist_bl_head *hbl) +{ + unsigned long cnt; + struct hlist_bl_node *pos; + + cnt = 0; + hlist_bl_lock(hbl); + au_hbl_for_each(pos, hbl) + cnt++; + hlist_bl_unlock(hbl); + return cnt; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_HBL_H__ */ diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c new file mode 100644 index 000000000000..cb4eeb1e6069 --- /dev/null +++ b/fs/aufs/hfsnotify.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * fsnotify for the lower directories + */ + +#include "aufs.h" + +/* FS_IN_IGNORED is unnecessary */ +static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE + | FS_CREATE | FS_EVENT_ON_CHILD); +static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq); +static __cacheline_aligned_in_smp atomic64_t au_hfsn_ifree = ATOMIC64_INIT(0); + +static void au_hfsn_free_mark(struct fsnotify_mark *mark) +{ + struct au_hnotify *hn = container_of(mark, struct au_hnotify, + hn_mark); + /* AuDbg("here\n"); */ + au_cache_free_hnotify(hn); + smp_mb__before_atomic(); /* for atomic64_dec */ + if (atomic64_dec_and_test(&au_hfsn_ifree)) + wake_up(&au_hfsn_wq); +} + +static int au_hfsn_alloc(struct au_hinode *hinode) +{ + int err; + struct au_hnotify *hn; + struct super_block *sb; + struct au_branch *br; + struct fsnotify_mark *mark; + aufs_bindex_t bindex; + + hn = hinode->hi_notify; + sb = hn->hn_aufs_inode->i_sb; + bindex = au_br_index(sb, hinode->hi_id); + br = au_sbr(sb, bindex); + AuDebugOn(!br->br_hfsn); + + mark = &hn->hn_mark; + fsnotify_init_mark(mark, br->br_hfsn->hfsn_group); + mark->mask = AuHfsnMask; + /* + * by udba rename or rmdir, aufs assign a new inode to the known + * h_inode, so specify 1 to allow dups. + */ + lockdep_off(); + err = fsnotify_add_inode_mark(mark, hinode->hi_inode, /*allow_dups*/1); + lockdep_on(); + + return err; +} + +static int au_hfsn_free(struct au_hinode *hinode, struct au_hnotify *hn) +{ + struct fsnotify_mark *mark; + unsigned long long ull; + struct fsnotify_group *group; + + ull = atomic64_inc_return(&au_hfsn_ifree); + BUG_ON(!ull); + + mark = &hn->hn_mark; + spin_lock(&mark->lock); + group = mark->group; + fsnotify_get_group(group); + spin_unlock(&mark->lock); + lockdep_off(); + fsnotify_destroy_mark(mark, group); + fsnotify_put_mark(mark); + fsnotify_put_group(group); + lockdep_on(); + + /* free hn by myself */ + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_ctl(struct au_hinode *hinode, int do_set) +{ + struct fsnotify_mark *mark; + + mark = &hinode->hi_notify->hn_mark; + spin_lock(&mark->lock); + if (do_set) { + AuDebugOn(mark->mask & AuHfsnMask); + mark->mask |= AuHfsnMask; + } else { + AuDebugOn(!(mark->mask & AuHfsnMask)); + mark->mask &= ~AuHfsnMask; + } + spin_unlock(&mark->lock); + /* fsnotify_recalc_inode_mask(hinode->hi_inode); */ +} + +/* ---------------------------------------------------------------------- */ + +/* #define AuDbgHnotify */ +#ifdef AuDbgHnotify +static char *au_hfsn_name(u32 mask) +{ +#ifdef CONFIG_AUFS_DEBUG +#define test_ret(flag) \ + do { \ + if (mask & flag) \ + return #flag; \ + } while (0) + test_ret(FS_ACCESS); + test_ret(FS_MODIFY); + test_ret(FS_ATTRIB); + test_ret(FS_CLOSE_WRITE); + test_ret(FS_CLOSE_NOWRITE); + test_ret(FS_OPEN); + test_ret(FS_MOVED_FROM); + test_ret(FS_MOVED_TO); + test_ret(FS_CREATE); + test_ret(FS_DELETE); + test_ret(FS_DELETE_SELF); + test_ret(FS_MOVE_SELF); + test_ret(FS_UNMOUNT); + test_ret(FS_Q_OVERFLOW); + test_ret(FS_IN_IGNORED); + test_ret(FS_ISDIR); + test_ret(FS_IN_ONESHOT); + test_ret(FS_EVENT_ON_CHILD); + return ""; +#undef test_ret +#else + return "??"; +#endif +} +#endif + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_free_group(struct fsnotify_group *group) +{ + struct au_br_hfsnotify *hfsn = group->private; + + /* AuDbg("here\n"); */ + au_kfree_try_rcu(hfsn); +} + +static int au_hfsn_handle_event(struct fsnotify_group *group, + struct inode *inode, + u32 mask, const void *data, int data_type, + const struct qstr *file_name, u32 cookie, + struct fsnotify_iter_info *iter_info) +{ + int err; + struct au_hnotify *hnotify; + struct inode *h_dir, *h_inode; + struct fsnotify_mark *inode_mark; + + AuDebugOn(data_type != FSNOTIFY_EVENT_INODE); + + err = 0; + /* if FS_UNMOUNT happens, there must be another bug */ + AuDebugOn(mask & FS_UNMOUNT); + if (mask & (FS_IN_IGNORED | FS_UNMOUNT)) + goto out; + + h_dir = inode; + h_inode = NULL; +#ifdef AuDbgHnotify + au_debug_on(); + if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1 + || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) { + AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n", + h_dir->i_ino, mask, au_hfsn_name(mask), + AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0); + /* WARN_ON(1); */ + } + au_debug_off(); +#endif + + inode_mark = fsnotify_iter_inode_mark(iter_info); + AuDebugOn(!inode_mark); + hnotify = container_of(inode_mark, struct au_hnotify, hn_mark); + err = au_hnotify(h_dir, hnotify, mask, file_name, h_inode); + +out: + return err; +} + +static struct fsnotify_ops au_hfsn_ops = { + .handle_event = au_hfsn_handle_event, + .free_group_priv = au_hfsn_free_group, + .free_mark = au_hfsn_free_mark +}; + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_fin_br(struct au_branch *br) +{ + struct au_br_hfsnotify *hfsn; + + hfsn = br->br_hfsn; + if (hfsn) { + lockdep_off(); + fsnotify_put_group(hfsn->hfsn_group); + lockdep_on(); + } +} + +static int au_hfsn_init_br(struct au_branch *br, int perm) +{ + int err; + struct fsnotify_group *group; + struct au_br_hfsnotify *hfsn; + + err = 0; + br->br_hfsn = NULL; + if (!au_br_hnotifyable(perm)) + goto out; + + err = -ENOMEM; + hfsn = kmalloc(sizeof(*hfsn), GFP_NOFS); + if (unlikely(!hfsn)) + goto out; + + err = 0; + group = fsnotify_alloc_group(&au_hfsn_ops); + if (IS_ERR(group)) { + err = PTR_ERR(group); + pr_err("fsnotify_alloc_group() failed, %d\n", err); + goto out_hfsn; + } + + group->private = hfsn; + hfsn->hfsn_group = group; + br->br_hfsn = hfsn; + goto out; /* success */ + +out_hfsn: + au_kfree_try_rcu(hfsn); +out: + return err; +} + +static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (!br->br_hfsn) + err = au_hfsn_init_br(br, perm); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_fin(void) +{ + AuDbg("au_hfsn_ifree %lld\n", (long long)atomic64_read(&au_hfsn_ifree)); + wait_event(au_hfsn_wq, !atomic64_read(&au_hfsn_ifree)); +} + +const struct au_hnotify_op au_hnotify_op = { + .ctl = au_hfsn_ctl, + .alloc = au_hfsn_alloc, + .free = au_hfsn_free, + + .fin = au_hfsn_fin, + + .reset_br = au_hfsn_reset_br, + .fin_br = au_hfsn_fin_br, + .init_br = au_hfsn_init_br +}; diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c new file mode 100644 index 000000000000..d250f019bedf --- /dev/null +++ b/fs/aufs/hfsplus.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * special support for filesystems which acquires an inode mutex + * at final closing a file, eg, hfsplus. + * + * This trick is very simple and stupid, just to open the file before really + * necessary open to tell hfsplus that this is not the final closing. + * The caller should call au_h_open_pre() after acquiring the inode mutex, + * and au_h_open_post() after releasing it. + */ + +#include "aufs.h" + +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, + int force_wr) +{ + struct file *h_file; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + AuDebugOn(!h_dentry); + AuDebugOn(d_is_negative(h_dentry)); + + h_file = NULL; + if (au_test_hfsplus(h_dentry->d_sb) + && d_is_reg(h_dentry)) + h_file = au_h_open(dentry, bindex, + O_RDONLY | O_NOATIME | O_LARGEFILE, + /*file*/NULL, force_wr); + return h_file; +} + +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file) +{ + struct au_branch *br; + + if (h_file) { + fput(h_file); + br = au_sbr(dentry->d_sb, bindex); + au_lcnt_dec(&br->br_nfiles); + } +} diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c new file mode 100644 index 000000000000..231edd1b4753 --- /dev/null +++ b/fs/aufs/hnotify.c @@ -0,0 +1,715 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * abstraction to notify the direct changes on lower directories + */ + +/* #include <linux/iversion.h> */ +#include "aufs.h" + +int au_hn_alloc(struct au_hinode *hinode, struct inode *inode) +{ + int err; + struct au_hnotify *hn; + + err = -ENOMEM; + hn = au_cache_alloc_hnotify(); + if (hn) { + hn->hn_aufs_inode = inode; + hinode->hi_notify = hn; + err = au_hnotify_op.alloc(hinode); + AuTraceErr(err); + if (unlikely(err)) { + hinode->hi_notify = NULL; + au_cache_free_hnotify(hn); + /* + * The upper dir was removed by udba, but the same named + * dir left. In this case, aufs assigns a new inode + * number and set the monitor again. + * For the lower dir, the old monitor is still left. + */ + if (err == -EEXIST) + err = 0; + } + } + + AuTraceErr(err); + return err; +} + +void au_hn_free(struct au_hinode *hinode) +{ + struct au_hnotify *hn; + + hn = hinode->hi_notify; + if (hn) { + hinode->hi_notify = NULL; + if (au_hnotify_op.free(hinode, hn)) + au_cache_free_hnotify(hn); + } +} + +/* ---------------------------------------------------------------------- */ + +void au_hn_ctl(struct au_hinode *hinode, int do_set) +{ + if (hinode->hi_notify) + au_hnotify_op.ctl(hinode, do_set); +} + +void au_hn_reset(struct inode *inode, unsigned int flags) +{ + aufs_bindex_t bindex, bbot; + struct inode *hi; + struct dentry *iwhdentry; + + bbot = au_ibbot(inode); + for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) { + hi = au_h_iptr(inode, bindex); + if (!hi) + continue; + + /* inode_lock_nested(hi, AuLsc_I_CHILD); */ + iwhdentry = au_hi_wh(inode, bindex); + if (iwhdentry) + dget(iwhdentry); + au_igrab(hi); + au_set_h_iptr(inode, bindex, NULL, 0); + au_set_h_iptr(inode, bindex, au_igrab(hi), + flags & ~AuHi_XINO); + iput(hi); + dput(iwhdentry); + /* inode_unlock(hi); */ + } +} + +/* ---------------------------------------------------------------------- */ + +static int hn_xino(struct inode *inode, struct inode *h_inode) +{ + int err; + aufs_bindex_t bindex, bbot, bfound, btop; + struct inode *h_i; + + err = 0; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("branch root dir was changed\n"); + goto out; + } + + bfound = -1; + bbot = au_ibbot(inode); + btop = au_ibtop(inode); +#if 0 /* reserved for future use */ + if (bindex == bbot) { + /* keep this ino in rename case */ + goto out; + } +#endif + for (bindex = btop; bindex <= bbot; bindex++) + if (au_h_iptr(inode, bindex) == h_inode) { + bfound = bindex; + break; + } + if (bfound < 0) + goto out; + + for (bindex = btop; bindex <= bbot; bindex++) { + h_i = au_h_iptr(inode, bindex); + if (!h_i) + continue; + + err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0); + /* ignore this error */ + /* bad action? */ + } + + /* children inode number will be broken */ + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_tree(struct dentry *dentry) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, dentry, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + struct dentry *d; + + d = dentries[j]; + if (IS_ROOT(d)) + continue; + + au_digen_dec(d); + if (d_really_is_positive(d)) + /* todo: reset children xino? + cached children only? */ + au_iigen_dec(d_inode(d)); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +/* + * return 0 if processed. + */ +static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode, + const unsigned int isdir) +{ + int err; + struct dentry *d; + struct qstr *dname; + + err = 1; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("branch root dir was changed\n"); + err = 0; + goto out; + } + + if (!isdir) { + AuDebugOn(!name); + au_iigen_dec(inode); + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len != nlen + && memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + continue; + } + err = 0; + au_digen_dec(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&inode->i_lock); + } else { + au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR); + d = d_find_any_alias(inode); + if (!d) { + au_iigen_dec(inode); + goto out; + } + + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len == nlen && !memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + err = hn_gen_tree(d); + spin_lock(&d->d_lock); + } + spin_unlock(&d->d_lock); + dput(d); + } + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir) +{ + int err; + + if (IS_ROOT(dentry)) { + pr_warn("branch root dir was changed\n"); + return 0; + } + + err = 0; + if (!isdir) { + au_digen_dec(dentry); + if (d_really_is_positive(dentry)) + au_iigen_dec(d_inode(dentry)); + } else { + au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR); + if (d_really_is_positive(dentry)) + err = hn_gen_tree(dentry); + } + + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* hnotify job flags */ +#define AuHnJob_XINO0 1 +#define AuHnJob_GEN (1 << 1) +#define AuHnJob_DIRENT (1 << 2) +#define AuHnJob_ISDIR (1 << 3) +#define AuHnJob_TRYXINO0 (1 << 4) +#define AuHnJob_MNTPNT (1 << 5) +#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name) +#define au_fset_hnjob(flags, name) \ + do { (flags) |= AuHnJob_##name; } while (0) +#define au_fclr_hnjob(flags, name) \ + do { (flags) &= ~AuHnJob_##name; } while (0) + +enum { + AuHn_CHILD, + AuHn_PARENT, + AuHnLast +}; + +struct au_hnotify_args { + struct inode *h_dir, *dir, *h_child_inode; + u32 mask; + unsigned int flags[AuHnLast]; + unsigned int h_child_nlen; + char h_child_name[]; +}; + +struct hn_job_args { + unsigned int flags; + struct inode *inode, *h_inode, *dir, *h_dir; + struct dentry *dentry; + char *h_name; + int h_nlen; +}; + +static int hn_job(struct hn_job_args *a) +{ + const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR); + int e; + + /* reset xino */ + if (au_ftest_hnjob(a->flags, XINO0) && a->inode) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + + if (au_ftest_hnjob(a->flags, TRYXINO0) + && a->inode + && a->h_inode) { + inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); + if (!a->h_inode->i_nlink + && !(a->h_inode->i_state & I_LINKABLE)) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + inode_unlock_shared(a->h_inode); + } + + /* make the generation obsolete */ + if (au_ftest_hnjob(a->flags, GEN)) { + e = -1; + if (a->inode) + e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode, + isdir); + if (e && a->dentry) + hn_gen_by_name(a->dentry, isdir); + /* ignore this error */ + } + + /* make dir entries obsolete */ + if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) { + struct au_vdir *vdir; + + vdir = au_ivdir(a->inode); + if (vdir) + vdir->vd_jiffy = 0; + /* IMustLock(a->inode); */ + /* inode_inc_iversion(a->inode); */ + } + + /* can do nothing but warn */ + if (au_ftest_hnjob(a->flags, MNTPNT) + && a->dentry + && d_mountpoint(a->dentry)) + pr_warn("mount-point %pd is removed or renamed\n", a->dentry); + + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen, + struct inode *dir) +{ + struct dentry *dentry, *d, *parent; + struct qstr *dname; + + parent = d_find_any_alias(dir); + if (!parent) + return NULL; + + dentry = NULL; + spin_lock(&parent->d_lock); + list_for_each_entry(d, &parent->d_subdirs, d_child) { + /* AuDbg("%pd\n", d); */ + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + dname = &d->d_name; + if (dname->len != nlen || memcmp(dname->name, name, nlen)) + goto cont_unlock; + if (au_di(d)) + au_digen_dec(d); + else + goto cont_unlock; + if (au_dcount(d) > 0) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + +cont_unlock: + spin_unlock(&d->d_lock); + } + spin_unlock(&parent->d_lock); + dput(parent); + + if (dentry) + di_write_lock_child(dentry); + + return dentry; +} + +static struct inode *lookup_wlock_by_ino(struct super_block *sb, + aufs_bindex_t bindex, ino_t h_ino) +{ + struct inode *inode; + ino_t ino; + int err; + + inode = NULL; + err = au_xino_read(sb, bindex, h_ino, &ino); + if (!err && ino) + inode = ilookup(sb, ino); + if (!inode) + goto out; + + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("wrong root branch\n"); + iput(inode); + inode = NULL; + goto out; + } + + ii_write_lock_child(inode); + +out: + return inode; +} + +static void au_hn_bh(void *_args) +{ + struct au_hnotify_args *a = _args; + struct super_block *sb; + aufs_bindex_t bindex, bbot, bfound; + unsigned char xino, try_iput; + int err; + struct inode *inode; + ino_t h_ino; + struct hn_job_args args; + struct dentry *dentry; + struct au_sbinfo *sbinfo; + + AuDebugOn(!_args); + AuDebugOn(!a->h_dir); + AuDebugOn(!a->dir); + AuDebugOn(!a->mask); + AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n", + a->mask, a->dir->i_ino, a->h_dir->i_ino, + a->h_child_inode ? a->h_child_inode->i_ino : 0); + + inode = NULL; + dentry = NULL; + /* + * do not lock a->dir->i_mutex here + * because of d_revalidate() may cause a deadlock. + */ + sb = a->dir->i_sb; + AuDebugOn(!sb); + sbinfo = au_sbi(sb); + AuDebugOn(!sbinfo); + si_write_lock(sb, AuLock_NOPLMW); + + if (au_opt_test(sbinfo->si_mntflags, DIRREN)) + switch (a->mask & FS_EVENTS_POSS_ON_CHILD) { + case FS_MOVED_FROM: + case FS_MOVED_TO: + AuWarn1("DIRREN with UDBA may not work correctly " + "for the direct rename(2)\n"); + } + + ii_read_lock_parent(a->dir); + bfound = -1; + bbot = au_ibbot(a->dir); + for (bindex = au_ibtop(a->dir); bindex <= bbot; bindex++) + if (au_h_iptr(a->dir, bindex) == a->h_dir) { + bfound = bindex; + break; + } + ii_read_unlock(a->dir); + if (unlikely(bfound < 0)) + goto out; + + xino = !!au_opt_test(au_mntflags(sb), XINO); + h_ino = 0; + if (a->h_child_inode) + h_ino = a->h_child_inode->i_ino; + + if (a->h_child_nlen + && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN) + || au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT))) + dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen, + a->dir); + try_iput = 0; + if (dentry && d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (xino && !inode && h_ino + && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) { + inode = lookup_wlock_by_ino(sb, bfound, h_ino); + try_iput = 1; + } + + args.flags = a->flags[AuHn_CHILD]; + args.dentry = dentry; + args.inode = inode; + args.h_inode = a->h_child_inode; + args.dir = a->dir; + args.h_dir = a->h_dir; + args.h_name = a->h_child_name; + args.h_nlen = a->h_child_nlen; + err = hn_job(&args); + if (dentry) { + if (au_di(dentry)) + di_write_unlock(dentry); + dput(dentry); + } + if (inode && try_iput) { + ii_write_unlock(inode); + iput(inode); + } + + ii_write_lock_parent(a->dir); + args.flags = a->flags[AuHn_PARENT]; + args.dentry = NULL; + args.inode = a->dir; + args.h_inode = a->h_dir; + args.dir = NULL; + args.h_dir = NULL; + args.h_name = NULL; + args.h_nlen = 0; + err = hn_job(&args); + ii_write_unlock(a->dir); + +out: + iput(a->h_child_inode); + iput(a->h_dir); + iput(a->dir); + si_write_unlock(sb); + au_nwt_done(&sbinfo->si_nowait); + au_kfree_rcu(a); +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, + const struct qstr *h_child_qstr, struct inode *h_child_inode) +{ + int err, len; + unsigned int flags[AuHnLast], f; + unsigned char isdir, isroot, wh; + struct inode *dir; + struct au_hnotify_args *args; + char *p, *h_child_name; + + err = 0; + AuDebugOn(!hnotify || !hnotify->hn_aufs_inode); + dir = igrab(hnotify->hn_aufs_inode); + if (!dir) + goto out; + + isroot = (dir->i_ino == AUFS_ROOT_INO); + wh = 0; + h_child_name = (void *)h_child_qstr->name; + len = h_child_qstr->len; + if (h_child_name) { + if (len > AUFS_WH_PFX_LEN + && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + h_child_name += AUFS_WH_PFX_LEN; + len -= AUFS_WH_PFX_LEN; + wh = 1; + } + } + + isdir = 0; + if (h_child_inode) + isdir = !!S_ISDIR(h_child_inode->i_mode); + flags[AuHn_PARENT] = AuHnJob_ISDIR; + flags[AuHn_CHILD] = 0; + if (isdir) + flags[AuHn_CHILD] = AuHnJob_ISDIR; + au_fset_hnjob(flags[AuHn_PARENT], DIRENT); + au_fset_hnjob(flags[AuHn_CHILD], GEN); + switch (mask & ALL_FSNOTIFY_DIRENT_EVENTS) { + case FS_MOVED_FROM: + case FS_MOVED_TO: + au_fset_hnjob(flags[AuHn_CHILD], XINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + /*FALLTHROUGH*/ + case FS_CREATE: + AuDebugOn(!h_child_name); + break; + + case FS_DELETE: + /* + * aufs never be able to get this child inode. + * revalidation should be in d_revalidate() + * by checking i_nlink, i_generation or d_unhashed(). + */ + AuDebugOn(!h_child_name); + au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + break; + + default: + AuDebugOn(1); + } + + if (wh) + h_child_inode = NULL; + + err = -ENOMEM; + /* iput() and kfree() will be called in au_hnotify() */ + args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS); + if (unlikely(!args)) { + AuErr1("no memory\n"); + iput(dir); + goto out; + } + args->flags[AuHn_PARENT] = flags[AuHn_PARENT]; + args->flags[AuHn_CHILD] = flags[AuHn_CHILD]; + args->mask = mask; + args->dir = dir; + args->h_dir = igrab(h_dir); + if (h_child_inode) + h_child_inode = igrab(h_child_inode); /* can be NULL */ + args->h_child_inode = h_child_inode; + args->h_child_nlen = len; + if (len) { + p = (void *)args; + p += sizeof(*args); + memcpy(p, h_child_name, len); + p[len] = 0; + } + + /* NFS fires the event for silly-renamed one from kworker */ + f = 0; + if (!dir->i_nlink + || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE))) + f = AuWkq_NEST; + err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); + if (unlikely(err)) { + pr_err("wkq %d\n", err); + iput(args->h_child_inode); + iput(args->h_dir); + iput(args->dir); + au_kfree_rcu(args); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + AuDebugOn(!(udba & AuOptMask_UDBA)); + + err = 0; + if (au_hnotify_op.reset_br) + err = au_hnotify_op.reset_br(udba, br, perm); + + return err; +} + +int au_hnotify_init_br(struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (au_hnotify_op.init_br) + err = au_hnotify_op.init_br(br, perm); + + return err; +} + +void au_hnotify_fin_br(struct au_branch *br) +{ + if (au_hnotify_op.fin_br) + au_hnotify_op.fin_br(br); +} + +static void au_hn_destroy_cache(void) +{ + kmem_cache_destroy(au_cache[AuCache_HNOTIFY]); + au_cache[AuCache_HNOTIFY] = NULL; +} + +int __init au_hnotify_init(void) +{ + int err; + + err = -ENOMEM; + au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify); + if (au_cache[AuCache_HNOTIFY]) { + err = 0; + if (au_hnotify_op.init) + err = au_hnotify_op.init(); + if (unlikely(err)) + au_hn_destroy_cache(); + } + AuTraceErr(err); + return err; +} + +void au_hnotify_fin(void) +{ + if (au_hnotify_op.fin) + au_hnotify_op.fin(); + + /* cf. au_cache_fin() */ + if (au_cache[AuCache_HNOTIFY]) + au_hn_destroy_cache(); +} diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c new file mode 100644 index 000000000000..2d09f80153b2 --- /dev/null +++ b/fs/aufs/i_op.c @@ -0,0 +1,1502 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (except add/del/rename) + */ + +#include <linux/device_cgroup.h> +#include <linux/fs_stack.h> +#include <linux/iversion.h> +#include <linux/namei.h> +#include <linux/security.h> +#include "aufs.h" + +static int h_permission(struct inode *h_inode, int mask, + struct path *h_path, int brperm) +{ + int err; + const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + + err = -EPERM; + if (write_mask && IS_IMMUTABLE(h_inode)) + goto out; + + err = -EACCES; + if (((mask & MAY_EXEC) + && S_ISREG(h_inode->i_mode) + && (path_noexec(h_path) + || !(h_inode->i_mode & 0111)))) + goto out; + + /* + * - skip the lower fs test in the case of write to ro branch. + * - nfs dir permission write check is optimized, but a policy for + * link/rename requires a real check. + * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.' + * in this case, generic_permission() returns -EOPNOTSUPP. + */ + if ((write_mask && !au_br_writable(brperm)) + || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) + && write_mask && !(mask & MAY_READ)) + || !h_inode->i_op->permission) { + /* AuLabel(generic_permission); */ + /* AuDbg("get_acl %ps\n", h_inode->i_op->get_acl); */ + err = generic_permission(h_inode, mask); + if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode)) + err = h_inode->i_op->permission(h_inode, mask); + AuTraceErr(err); + } else { + /* AuLabel(h_inode->permission); */ + err = h_inode->i_op->permission(h_inode, mask); + AuTraceErr(err); + } + + if (!err) + err = devcgroup_inode_permission(h_inode, mask); + if (!err) + err = security_inode_permission(h_inode, mask); + +out: + return err; +} + +static int aufs_permission(struct inode *inode, int mask) +{ + int err; + aufs_bindex_t bindex, bbot; + const unsigned char isdir = !!S_ISDIR(inode->i_mode), + write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + + /* todo: support rcu-walk? */ + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH); + ii_read_lock_child(inode); +#if 0 /* reserved for future use */ + /* + * This test may be rather 'too much' since the test is essentially done + * in the aufs_lookup(). Theoretically it is possible that the inode + * generation doesn't match to the superblock's here. But it isn't a + * big deal I suppose. + */ + err = au_iigen_test(inode, au_sigen(sb)); + if (unlikely(err)) + goto out; +#endif + + if (!isdir + || write_mask + || au_opt_test(au_mntflags(sb), DIRPERM1)) { + err = au_busy_or_stale(); + h_inode = au_h_iptr(inode, au_ibtop(inode)); + if (unlikely(!h_inode + || (h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT))) + goto out; + + err = 0; + bindex = au_ibtop(inode); + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, &br->br_path, br->br_perm); + if (write_mask + && !err + && !special_file(h_inode->i_mode)) { + /* test whether the upper writable branch exists */ + err = -EROFS; + for (; bindex >= 0; bindex--) + if (!au_br_rdonly(au_sbr(sb, bindex))) { + err = 0; + break; + } + } + goto out; + } + + /* non-write to dir */ + err = 0; + bbot = au_ibbot(inode); + for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) { + err = au_busy_or_stale(); + if (unlikely(!S_ISDIR(h_inode->i_mode))) + break; + + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, &br->br_path, + br->br_perm); + } + } + +out: + ii_read_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret, *parent; + struct inode *inode; + struct super_block *sb; + int err, npositive; + + IMustLock(dir); + + /* todo: support rcu-walk? */ + ret = ERR_PTR(-ECHILD); + if (flags & LOOKUP_RCU) + goto out; + + ret = ERR_PTR(-ENAMETOOLONG); + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out; + + sb = dir->i_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out; + + err = au_di_init(dentry); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out_si; + + inode = NULL; + npositive = 0; /* suppress a warning */ + parent = dentry->d_parent; /* dir inode is locked */ + di_read_lock_parent(parent, AuLock_IR); + err = au_alive_dir(parent); + if (!err) + err = au_digen_test(parent, au_sigen(sb)); + if (!err) { + /* regardless LOOKUP_CREATE, always ALLOW_NEG */ + npositive = au_lkup_dentry(dentry, au_dbtop(parent), + AuLkup_ALLOW_NEG); + err = npositive; + } + di_read_unlock(parent, AuLock_IR); + ret = ERR_PTR(err); + if (unlikely(err < 0)) + goto out_unlock; + + if (npositive) { + inode = au_new_inode(dentry, /*must_new*/0); + if (IS_ERR(inode)) { + ret = (void *)inode; + inode = NULL; + goto out_unlock; + } + } + + if (inode) + atomic_inc(&inode->i_count); + ret = d_splice_alias(inode, dentry); +#if 0 /* reserved for future use */ + if (unlikely(d_need_lookup(dentry))) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_NEED_LOOKUP; + spin_unlock(&dentry->d_lock); + } else +#endif + if (inode) { + if (!IS_ERR(ret)) { + iput(inode); + if (ret && ret != dentry) + ii_write_unlock(inode); + } else { + ii_write_unlock(inode); + iput(inode); + inode = NULL; + } + } + +out_unlock: + di_write_unlock(dentry); +out_si: + si_read_unlock(sb); +out: + return ret; +} + +/* ---------------------------------------------------------------------- */ + +/* + * very dirty and complicated aufs ->atomic_open(). + * aufs_atomic_open() + * + au_aopen_or_create() + * + add_simple() + * + vfsub_atomic_open() + * + branch fs ->atomic_open() + * may call the actual 'open' for h_file + * + inc br_nfiles only if opened + * + au_aopen_no_open() or au_aopen_do_open() + * + * au_aopen_do_open() + * + finish_open() + * + au_do_aopen() + * + au_do_open() the body of all 'open' + * + au_do_open_nondir() + * set the passed h_file + * + * au_aopen_no_open() + * + finish_no_open() + */ + +struct aopen_node { + struct hlist_bl_node hblist; + struct file *file, *h_file; +}; + +static int au_do_aopen(struct inode *inode, struct file *file) +{ + struct hlist_bl_head *aopen; + struct hlist_bl_node *pos; + struct aopen_node *node; + struct au_do_open_args args = { + .aopen = 1, + .open = au_do_open_nondir + }; + + aopen = &au_sbi(inode->i_sb)->si_aopen; + hlist_bl_lock(aopen); + hlist_bl_for_each_entry(node, pos, aopen, hblist) + if (node->file == file) { + args.h_file = node->h_file; + break; + } + hlist_bl_unlock(aopen); + /* AuDebugOn(!args.h_file); */ + + return au_do_open(file, &args); +} + +static int au_aopen_do_open(struct file *file, struct dentry *dentry, + struct aopen_node *aopen_node) +{ + int err; + struct hlist_bl_head *aopen; + + AuLabel(here); + aopen = &au_sbi(dentry->d_sb)->si_aopen; + au_hbl_add(&aopen_node->hblist, aopen); + err = finish_open(file, dentry, au_do_aopen); + au_hbl_del(&aopen_node->hblist, aopen); + /* AuDbgFile(file); */ + AuDbg("%pd%s%s\n", dentry, + (file->f_mode & FMODE_CREATED) ? " created" : "", + (file->f_mode & FMODE_OPENED) ? " opened" : ""); + + AuTraceErr(err); + return err; +} + +static int au_aopen_no_open(struct file *file, struct dentry *dentry) +{ + int err; + + AuLabel(here); + dget(dentry); + err = finish_no_open(file, dentry); + + AuTraceErr(err); + return err; +} + +static int aufs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flag, + umode_t create_mode) +{ + int err, did_open; + unsigned int lkup_flags; + aufs_bindex_t bindex; + struct super_block *sb; + struct dentry *parent, *d; + struct vfsub_aopen_args args = { + .open_flag = open_flag, + .create_mode = create_mode + }; + struct aopen_node aopen_node = { + .file = file + }; + + IMustLock(dir); + AuDbg("open_flag 0%o\n", open_flag); + AuDbgDentry(dentry); + + err = 0; + if (!au_di(dentry)) { + lkup_flags = LOOKUP_OPEN; + if (open_flag & O_CREAT) + lkup_flags |= LOOKUP_CREATE; + d = aufs_lookup(dir, dentry, lkup_flags); + if (IS_ERR(d)) { + err = PTR_ERR(d); + AuTraceErr(err); + goto out; + } else if (d) { + /* + * obsoleted dentry found. + * another error will be returned later. + */ + d_drop(d); + AuDbgDentry(d); + dput(d); + } + AuDbgDentry(dentry); + } + + if (d_is_positive(dentry) + || d_unhashed(dentry) + || d_unlinked(dentry) + || !(open_flag & O_CREAT)) { + err = au_aopen_no_open(file, dentry); + goto out; /* success */ + } + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + parent = dentry->d_parent; /* dir is locked */ + di_write_lock_parent(parent); + err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); + if (unlikely(err < 0)) + goto out_parent; + + AuDbgDentry(dentry); + if (d_is_positive(dentry)) { + err = au_aopen_no_open(file, dentry); + goto out_parent; /* success */ + } + + args.file = alloc_empty_file(file->f_flags, current_cred()); + err = PTR_ERR(args.file); + if (IS_ERR(args.file)) + goto out_parent; + + bindex = au_dbtop(dentry); + err = au_aopen_or_create(dir, dentry, &args); + AuTraceErr(err); + AuDbgFile(args.file); + file->f_mode = args.file->f_mode & ~FMODE_OPENED; + did_open = !!(args.file->f_mode & FMODE_OPENED); + if (!did_open) { + fput(args.file); + args.file = NULL; + } + di_write_unlock(parent); + di_write_unlock(dentry); + if (unlikely(err < 0)) { + if (args.file) + fput(args.file); + goto out_sb; + } + + if (!did_open) + err = au_aopen_no_open(file, dentry); + else { + aopen_node.h_file = args.file; + err = au_aopen_do_open(file, dentry, &aopen_node); + } + if (unlikely(err < 0)) { + if (args.file) + fput(args.file); + if (did_open) + au_lcnt_dec(&args.br->br_nfiles); + } + goto out_sb; /* success */ + +out_parent: + di_write_unlock(parent); + di_write_unlock(dentry); +out_sb: + si_read_unlock(sb); +out: + AuTraceErr(err); + AuDbgFile(file); + return err; +} + + +/* ---------------------------------------------------------------------- */ + +static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, + const unsigned char add_entry, aufs_bindex_t bcpup, + aufs_bindex_t btop) +{ + int err; + struct dentry *h_parent; + struct inode *h_dir; + + if (add_entry) + IMustLock(d_inode(parent)); + else + di_write_lock_parent(parent); + + err = 0; + if (!au_h_dptr(parent, bcpup)) { + if (btop > bcpup) + err = au_cpup_dirs(dentry, bcpup); + else if (btop < bcpup) + err = au_cpdown_dirs(dentry, bcpup); + else + BUG(); + } + if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) { + h_parent = au_h_dptr(parent, bcpup); + h_dir = d_inode(h_parent); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + err = au_lkup_neg(dentry, bcpup, /*wh*/0); + /* todo: no unlock here */ + inode_unlock_shared(h_dir); + + AuDbg("bcpup %d\n", bcpup); + if (!err) { + if (d_really_is_negative(dentry)) + au_set_h_dptr(dentry, btop, NULL); + au_update_dbrange(dentry, /*do_put_zero*/0); + } + } + + if (!add_entry) + di_write_unlock(parent); + if (!err) + err = bcpup; /* success */ + + AuTraceErr(err); + return err; +} + +/* + * decide the branch and the parent dir where we will create a new entry. + * returns new bindex or an error. + * copyup the parent dir if needed. + */ +int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, + struct au_wr_dir_args *args) +{ + int err; + unsigned int flags; + aufs_bindex_t bcpup, btop, src_btop; + const unsigned char add_entry + = au_ftest_wrdir(args->flags, ADD_ENTRY) + | au_ftest_wrdir(args->flags, TMPFILE); + struct super_block *sb; + struct dentry *parent; + struct au_sbinfo *sbinfo; + + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + parent = dget_parent(dentry); + btop = au_dbtop(dentry); + bcpup = btop; + if (args->force_btgt < 0) { + if (src_dentry) { + src_btop = au_dbtop(src_dentry); + if (src_btop < btop) + bcpup = src_btop; + } else if (add_entry) { + flags = 0; + if (au_ftest_wrdir(args->flags, ISDIR)) + au_fset_wbr(flags, DIR); + err = AuWbrCreate(sbinfo, dentry, flags); + bcpup = err; + } + + if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) { + if (add_entry) + err = AuWbrCopyup(sbinfo, dentry); + else { + if (!IS_ROOT(dentry)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(sbinfo, dentry); + di_read_unlock(parent, !AuLock_IR); + } else + err = AuWbrCopyup(sbinfo, dentry); + } + bcpup = err; + if (unlikely(err < 0)) + goto out; + } + } else { + bcpup = args->force_btgt; + AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry))); + } + + AuDbg("btop %d, bcpup %d\n", btop, bcpup); + err = bcpup; + if (bcpup == btop) + goto out; /* success */ + + /* copyup the new parent into the branch we process */ + err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop); + if (err >= 0) { + if (d_really_is_negative(dentry)) { + au_set_h_dptr(dentry, btop, NULL); + au_set_dbtop(dentry, bcpup); + au_set_dbbot(dentry, bcpup); + } + AuDebugOn(add_entry + && !au_ftest_wrdir(args->flags, TMPFILE) + && !au_h_dptr(dentry, bcpup)); + } + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_pin_hdir_unlock(struct au_pin *p) +{ + if (p->hdir) + au_hn_inode_unlock(p->hdir); +} + +int au_pin_hdir_lock(struct au_pin *p) +{ + int err; + + err = 0; + if (!p->hdir) + goto out; + + /* even if an error happens later, keep this lock */ + au_hn_inode_lock_nested(p->hdir, p->lsc_hi); + + err = -EBUSY; + if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent))) + goto out; + + err = 0; + if (p->h_dentry) + err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode, + p->h_parent, p->br); + +out: + return err; +} + +int au_pin_hdir_relock(struct au_pin *p) +{ + int err, i; + struct inode *h_i; + struct dentry *h_d[] = { + p->h_dentry, + p->h_parent + }; + + err = au_pin_hdir_lock(p); + if (unlikely(err)) + goto out; + + for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) { + if (!h_d[i]) + continue; + if (d_is_positive(h_d[i])) { + h_i = d_inode(h_d[i]); + err = !h_i->i_nlink; + } + } + +out: + return err; +} + +static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task) +{ + atomic_long_set(&p->hdir->hi_inode->i_rwsem.owner, (long)task); +} + +void au_pin_hdir_acquire_nest(struct au_pin *p) +{ + if (p->hdir) { + rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map, + p->lsc_hi, 0, NULL, _RET_IP_); + au_pin_hdir_set_owner(p, current); + } +} + +void au_pin_hdir_release(struct au_pin *p) +{ + if (p->hdir) { + au_pin_hdir_set_owner(p, p->task); + rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, _RET_IP_); + } +} + +struct dentry *au_pinned_h_parent(struct au_pin *pin) +{ + if (pin && pin->parent) + return au_h_dptr(pin->parent, pin->bindex); + return NULL; +} + +void au_unpin(struct au_pin *p) +{ + if (p->hdir) + au_pin_hdir_unlock(p); + if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE)) + vfsub_mnt_drop_write(p->h_mnt); + if (!p->hdir) + return; + + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + iput(p->hdir->hi_inode); + dput(p->parent); + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; + /* do not clear p->task */ +} + +int au_do_pin(struct au_pin *p) +{ + int err; + struct super_block *sb; + struct inode *h_dir; + + err = 0; + sb = p->dentry->d_sb; + p->br = au_sbr(sb, p->bindex); + if (IS_ROOT(p->dentry)) { + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = au_br_mnt(p->br); + err = vfsub_mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + goto out_err; + } + } + goto out; + } + + p->h_dentry = NULL; + if (p->bindex <= au_dbbot(p->dentry)) + p->h_dentry = au_h_dptr(p->dentry, p->bindex); + + p->parent = dget_parent(p->dentry); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_lock(p->parent, AuLock_IR, p->lsc_di); + + h_dir = NULL; + p->h_parent = au_h_dptr(p->parent, p->bindex); + p->hdir = au_hi(d_inode(p->parent), p->bindex); + if (p->hdir) + h_dir = p->hdir->hi_inode; + + /* + * udba case, or + * if DI_LOCKED is not set, then p->parent may be different + * and h_parent can be NULL. + */ + if (unlikely(!p->hdir || !h_dir || !p->h_parent)) { + err = -EBUSY; + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + dput(p->parent); + p->parent = NULL; + goto out_err; + } + + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = au_br_mnt(p->br); + err = vfsub_mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + dput(p->parent); + p->parent = NULL; + goto out_err; + } + } + + au_igrab(h_dir); + err = au_pin_hdir_lock(p); + if (!err) + goto out; /* success */ + + au_unpin(p); + +out_err: + pr_err("err %d\n", err); + err = au_busy_or_stale(); +out: + return err; +} + +void au_pin_init(struct au_pin *p, struct dentry *dentry, + aufs_bindex_t bindex, int lsc_di, int lsc_hi, + unsigned int udba, unsigned char flags) +{ + p->dentry = dentry; + p->udba = udba; + p->lsc_di = lsc_di; + p->lsc_hi = lsc_hi; + p->flags = flags; + p->bindex = bindex; + + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; + + p->h_dentry = NULL; + p->h_parent = NULL; + p->br = NULL; + p->task = current; +} + +int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, + unsigned int udba, unsigned char flags) +{ + au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2, + udba, flags); + return au_do_pin(pin); +} + +/* ---------------------------------------------------------------------- */ + +/* + * ->setattr() and ->getattr() are called in various cases. + * chmod, stat: dentry is revalidated. + * fchmod, fstat: file and dentry are not revalidated, additionally they may be + * unhashed. + * for ->setattr(), ia->ia_file is passed from ftruncate only. + */ +/* todo: consolidate with do_refresh() and simple_reval_dpath() */ +int au_reval_for_attr(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *parent; + + err = 0; + if (au_digen_test(dentry, sigen)) { + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + } + + AuTraceErr(err); + return err; +} + +int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, + struct au_icpup_args *a) +{ + int err; + loff_t sz; + aufs_bindex_t btop, ibtop; + struct dentry *hi_wh, *parent; + struct inode *inode; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = 0 + }; + + if (d_is_dir(dentry)) + au_fset_wrdir(wr_dir_args.flags, ISDIR); + /* plink or hi_wh() case */ + btop = au_dbtop(dentry); + inode = d_inode(dentry); + ibtop = au_ibtop(inode); + if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode)) + wr_dir_args.force_btgt = ibtop; + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + if (unlikely(err < 0)) + goto out; + a->btgt = err; + if (err != btop) + au_fset_icpup(a->flags, DID_CPUP); + + err = 0; + a->pin_flags = AuPin_MNT_WRITE; + parent = NULL; + if (!IS_ROOT(dentry)) { + au_fset_pin(a->pin_flags, DI_LOCKED); + parent = dget_parent(dentry); + di_write_lock_parent(parent); + } + + err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); + if (unlikely(err)) + goto out_parent; + + sz = -1; + a->h_path.dentry = au_h_dptr(dentry, btop); + a->h_inode = d_inode(a->h_path.dentry); + if (ia && (ia->ia_valid & ATTR_SIZE)) { + inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); + if (ia->ia_size < i_size_read(a->h_inode)) + sz = ia->ia_size; + inode_unlock_shared(a->h_inode); + } + + hi_wh = NULL; + if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) { + hi_wh = au_hi_wh(inode, a->btgt); + if (!hi_wh) { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->btgt, + .bsrc = -1, + .len = sz, + .pin = &a->pin + }; + err = au_sio_cpup_wh(&cpg, /*file*/NULL); + if (unlikely(err)) + goto out_unlock; + hi_wh = au_hi_wh(inode, a->btgt); + /* todo: revalidate hi_wh? */ + } + } + + if (parent) { + au_pin_set_parent_lflag(&a->pin, /*lflag*/0); + di_downgrade_lock(parent, AuLock_IR); + dput(parent); + parent = NULL; + } + if (!au_ftest_icpup(a->flags, DID_CPUP)) + goto out; /* success */ + + if (!d_unhashed(dentry)) { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->btgt, + .bsrc = btop, + .len = sz, + .pin = &a->pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + err = au_sio_cpup_simple(&cpg); + if (!err) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + } else if (!hi_wh) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + else + a->h_path.dentry = hi_wh; /* do not dget here */ + +out_unlock: + a->h_inode = d_inode(a->h_path.dentry); + if (!err) + goto out; /* success */ + au_unpin(&a->pin); +out_parent: + if (parent) { + di_write_unlock(parent); + dput(parent); + } +out: + if (!err) + inode_lock_nested(a->h_inode, AuLsc_I_CHILD); + return err; +} + +static int aufs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; + struct inode *inode, *delegated; + struct super_block *sb; + struct file *file; + struct au_icpup_args *a; + + inode = d_inode(dentry); + IMustLock(inode); + + err = setattr_prepare(dentry, ia); + if (unlikely(err)) + goto out; + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + ia->ia_valid &= ~ATTR_MODE; + + file = NULL; + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_kfree; + + if (ia->ia_valid & ATTR_FILE) { + /* currently ftruncate(2) only */ + AuDebugOn(!d_is_reg(dentry)); + file = ia->ia_file; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, + /*fi_lsc*/0); + if (unlikely(err)) + goto out_si; + ia->ia_file = au_hf_top(file); + a->udba = AuOpt_UDBA_NONE; + } else { + /* fchmod() doesn't pass ia_file */ + a->udba = au_opt_udba(sb); + di_write_lock_child(dentry); + /* no d_unlinked(), to set UDBA_NONE for root */ + if (d_unhashed(dentry)) + a->udba = AuOpt_UDBA_NONE; + if (a->udba != AuOpt_UDBA_NONE) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out_dentry; + } + } + + err = au_pin_and_icpup(dentry, ia, a); + if (unlikely(err < 0)) + goto out_dentry; + if (au_ftest_icpup(a->flags, DID_CPUP)) { + ia->ia_file = NULL; + ia->ia_valid &= ~ATTR_FILE; + } + + a->h_path.mnt = au_sbr_mnt(sb, a->btgt); + if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME)) + == (ATTR_MODE | ATTR_CTIME)) { + err = security_path_chmod(&a->h_path, ia->ia_mode); + if (unlikely(err)) + goto out_unlock; + } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID)) + && (ia->ia_valid & ATTR_CTIME)) { + err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid); + if (unlikely(err)) + goto out_unlock; + } + + if (ia->ia_valid & ATTR_SIZE) { + struct file *f; + + if (ia->ia_size < i_size_read(inode)) + /* unmap only */ + truncate_setsize(inode, ia->ia_size); + + f = NULL; + if (ia->ia_valid & ATTR_FILE) + f = ia->ia_file; + inode_unlock(a->h_inode); + err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); + inode_lock_nested(a->h_inode, AuLsc_I_CHILD); + } else { + delegated = NULL; + while (1) { + err = vfsub_notify_change(&a->h_path, ia, &delegated); + if (delegated) { + err = break_deleg_wait(&delegated); + if (!err) + continue; + } + break; + } + } + /* + * regardless aufs 'acl' option setting. + * why don't all acl-aware fs call this func from their ->setattr()? + */ + if (!err && (ia->ia_valid & ATTR_MODE)) + err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); + if (!err) + au_cpup_attr_changeable(inode); + +out_unlock: + inode_unlock(a->h_inode); + au_unpin(&a->pin); + if (unlikely(err)) + au_update_dbtop(dentry); +out_dentry: + di_write_unlock(dentry); + if (file) { + fi_write_unlock(file); + ia->ia_file = file; + ia->ia_valid |= ATTR_FILE; + } +out_si: + si_read_unlock(sb); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} + +#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) +static int au_h_path_to_set_attr(struct dentry *dentry, + struct au_icpup_args *a, struct path *h_path) +{ + int err; + struct super_block *sb; + + sb = dentry->d_sb; + a->udba = au_opt_udba(sb); + /* no d_unlinked(), to set UDBA_NONE for root */ + if (d_unhashed(dentry)) + a->udba = AuOpt_UDBA_NONE; + if (a->udba != AuOpt_UDBA_NONE) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out; + } + err = au_pin_and_icpup(dentry, /*ia*/NULL, a); + if (unlikely(err < 0)) + goto out; + + h_path->dentry = a->h_path.dentry; + h_path->mnt = au_sbr_mnt(sb, a->btgt); + +out: + return err; +} + +ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, + struct au_sxattr *arg) +{ + int err; + struct path h_path; + struct super_block *sb; + struct au_icpup_args *a; + struct inode *h_inode; + + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_kfree; + + h_path.dentry = NULL; /* silence gcc */ + di_write_lock_child(dentry); + err = au_h_path_to_set_attr(dentry, a, &h_path); + if (unlikely(err)) + goto out_di; + + inode_unlock(a->h_inode); + switch (arg->type) { + case AU_XATTR_SET: + AuDebugOn(d_is_negative(h_path.dentry)); + err = vfsub_setxattr(h_path.dentry, + arg->u.set.name, arg->u.set.value, + arg->u.set.size, arg->u.set.flags); + break; + case AU_ACL_SET: + err = -EOPNOTSUPP; + h_inode = d_inode(h_path.dentry); + if (h_inode->i_op->set_acl) + /* this will call posix_acl_update_mode */ + err = h_inode->i_op->set_acl(h_inode, + arg->u.acl_set.acl, + arg->u.acl_set.type); + break; + } + if (!err) + au_cpup_attr_timesizes(inode); + + au_unpin(&a->pin); + if (unlikely(err)) + au_update_dbtop(dentry); + +out_di: + di_write_unlock(dentry); + si_read_unlock(sb); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} +#endif + +static void au_refresh_iattr(struct inode *inode, struct kstat *st, + unsigned int nlink) +{ + unsigned int n; + + inode->i_mode = st->mode; + /* don't i_[ug]id_write() here */ + inode->i_uid = st->uid; + inode->i_gid = st->gid; + inode->i_atime = st->atime; + inode->i_mtime = st->mtime; + inode->i_ctime = st->ctime; + + au_cpup_attr_nlink(inode, /*force*/0); + if (S_ISDIR(inode->i_mode)) { + n = inode->i_nlink; + n -= nlink; + n += st->nlink; + smp_mb(); /* for i_nlink */ + /* 0 can happen */ + set_nlink(inode, n); + } + + spin_lock(&inode->i_lock); + inode->i_blocks = st->blocks; + i_size_write(inode, st->size); + spin_unlock(&inode->i_lock); +} + +/* + * common routine for aufs_getattr() and au_getxattr(). + * returns zero or negative (an error). + * @dentry will be read-locked in success. + */ +int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force, + struct path *h_path, int locked) +{ + int err; + unsigned int mnt_flags, sigen; + unsigned char udba_none; + aufs_bindex_t bindex; + struct super_block *sb, *h_sb; + + h_path->mnt = NULL; + h_path->dentry = NULL; + + err = 0; + sb = dentry->d_sb; + mnt_flags = au_mntflags(sb); + udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); + + if (unlikely(locked)) + goto body; /* skip locking dinfo */ + + /* support fstat(2) */ + if (!d_unlinked(dentry) && !udba_none) { + sigen = au_sigen(sb); + err = au_digen_test(dentry, sigen); + if (!err) { + di_read_lock_child(dentry, AuLock_IR); + err = au_dbrange_test(dentry); + if (unlikely(err)) { + di_read_unlock(dentry, AuLock_IR); + goto out; + } + } else { + AuDebugOn(IS_ROOT(dentry)); + di_write_lock_child(dentry); + err = au_dbrange_test(dentry); + if (!err) + err = au_reval_for_attr(dentry, sigen); + if (!err) + di_downgrade_lock(dentry, AuLock_IR); + else { + di_write_unlock(dentry); + goto out; + } + } + } else + di_read_lock_child(dentry, AuLock_IR); + +body: + if (!inode) { + inode = d_inode(dentry); + if (unlikely(!inode)) + goto out; + } + bindex = au_ibtop(inode); + h_path->mnt = au_sbr_mnt(sb, bindex); + h_sb = h_path->mnt->mnt_sb; + if (!force + && !au_test_fs_bad_iattr(h_sb) + && udba_none) + goto out; /* success */ + + if (au_dbtop(dentry) == bindex) + h_path->dentry = au_h_dptr(dentry, bindex); + else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { + h_path->dentry = au_plink_lkup(inode, bindex); + if (IS_ERR(h_path->dentry)) + /* pretending success */ + h_path->dentry = NULL; + else + dput(h_path->dentry); + } + +out: + return err; +} + +static int aufs_getattr(const struct path *path, struct kstat *st, + u32 request, unsigned int query) +{ + int err; + unsigned char positive; + struct path h_path; + struct dentry *dentry; + struct inode *inode; + struct super_block *sb; + + dentry = path->dentry; + inode = d_inode(dentry); + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + err = au_h_path_getattr(dentry, /*inode*/NULL, /*force*/0, &h_path, + /*locked*/0); + if (unlikely(err)) + goto out_si; + if (unlikely(!h_path.dentry)) + /* illegally overlapped or something */ + goto out_fill; /* pretending success */ + + positive = d_is_positive(h_path.dentry); + if (positive) + /* no vfsub version */ + err = vfs_getattr(&h_path, st, request, query); + if (!err) { + if (positive) + au_refresh_iattr(inode, st, + d_inode(h_path.dentry)->i_nlink); + goto out_fill; /* success */ + } + AuTraceErr(err); + goto out_di; + +out_fill: + generic_fillattr(inode, st); +out_di: + di_read_unlock(dentry, AuLock_IR); +out_si: + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static const char *aufs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + const char *ret; + struct dentry *h_dentry; + struct inode *h_inode; + int err; + aufs_bindex_t bindex; + + ret = NULL; /* suppress a warning */ + err = -ECHILD; + if (!dentry) + goto out; + + err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); + if (unlikely(err)) + goto out; + + err = au_d_hashed_positive(dentry); + if (unlikely(err)) + goto out_unlock; + + err = -EINVAL; + inode = d_inode(dentry); + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (unlikely(!h_inode->i_op->get_link)) + goto out_unlock; + + err = -EBUSY; + h_dentry = NULL; + if (au_dbtop(dentry) <= bindex) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) + dget(h_dentry); + } + if (!h_dentry) { + h_dentry = d_find_any_alias(h_inode); + if (IS_ERR(h_dentry)) { + err = PTR_ERR(h_dentry); + goto out_unlock; + } + } + if (unlikely(!h_dentry)) + goto out_unlock; + + err = 0; + AuDbg("%ps\n", h_inode->i_op->get_link); + AuDbgDentry(h_dentry); + ret = vfs_get_link(h_dentry, done); + dput(h_dentry); + if (IS_ERR(ret)) + err = PTR_ERR(ret); + +out_unlock: + aufs_read_unlock(dentry, AuLock_IR); +out: + if (unlikely(err)) + ret = ERR_PTR(err); + AuTraceErrPtr(ret); + return ret; +} + +/* ---------------------------------------------------------------------- */ + +static int au_is_special(struct inode *inode) +{ + return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK)); +} + +static int aufs_update_time(struct inode *inode, struct timespec64 *ts, + int flags) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct inode *h_inode; + struct vfsmount *h_mnt; + + sb = inode->i_sb; + WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode), + "unexpected s_flags 0x%lx", sb->s_flags); + + /* mmap_sem might be acquired already, cf. aufs_mmap() */ + lockdep_off(); + si_read_lock(sb, AuLock_FLUSH); + ii_write_lock_child(inode); + + err = 0; + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (!au_test_ro(sb, bindex, inode)) { + h_mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mnt_want_write(h_mnt); + if (!err) { + err = vfsub_update_time(h_inode, ts, flags); + vfsub_mnt_drop_write(h_mnt); + } + } else if (au_is_special(h_inode)) { + /* + * Never copy-up here. + * These special files may already be opened and used for + * communicating. If we copied it up, then the communication + * would be corrupted. + */ + AuWarn1("timestamps for i%lu are ignored " + "since it is on readonly branch (hi%lu).\n", + inode->i_ino, h_inode->i_ino); + } else if (flags & ~S_ATIME) { + err = -EIO; + AuIOErr1("unexpected flags 0x%x\n", flags); + AuDebugOn(1); + } + + if (!err) + au_cpup_attr_timesizes(inode); + ii_write_unlock(inode); + si_read_unlock(sb); + lockdep_on(); + + if (!err && (flags & S_VERSION)) + inode_inc_iversion(inode); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* no getattr version will be set by module.c:aufs_init() */ +struct inode_operations aufs_iop_nogetattr[AuIop_Last], + aufs_iop[] = { + [AuIop_SYMLINK] = { + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, /* unsupport for symlink? */ +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .get_link = aufs_get_link, + + /* .update_time = aufs_update_time */ + }, + [AuIop_DIR] = { + .create = aufs_create, + .lookup = aufs_lookup, + .link = aufs_link, + .unlink = aufs_unlink, + .symlink = aufs_symlink, + .mkdir = aufs_mkdir, + .rmdir = aufs_rmdir, + .mknod = aufs_mknod, + .rename = aufs_rename, + + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .update_time = aufs_update_time, + .atomic_open = aufs_atomic_open, + .tmpfile = aufs_tmpfile + }, + [AuIop_OTHER] = { + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .update_time = aufs_update_time + } +}; diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c new file mode 100644 index 000000000000..80f2cfeeaaa0 --- /dev/null +++ b/fs/aufs/i_op_add.c @@ -0,0 +1,936 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (add entry) + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* + * final procedure of adding a new entry, except link(2). + * remove whiteout, instantiate, copyup the parent dir's times and size + * and update version. + * if it failed, re-create the removed whiteout. + */ +static int epilog(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct dentry *dentry) +{ + int err, rerr; + aufs_bindex_t bwh; + struct path h_path; + struct super_block *sb; + struct inode *inode, *h_dir; + struct dentry *wh; + + bwh = -1; + sb = dir->i_sb; + if (wh_dentry) { + h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */ + IMustLock(h_dir); + AuDebugOn(au_h_iptr(dir, bindex) != h_dir); + bwh = au_dbwh(dentry); + h_path.dentry = wh_dentry; + h_path.mnt = au_sbr_mnt(sb, bindex); + err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, + dentry); + if (unlikely(err)) + goto out; + } + + inode = au_new_inode(dentry, /*must_new*/1); + if (!IS_ERR(inode)) { + d_instantiate(dentry, inode); + dir = d_inode(dentry->d_parent); /* dir inode is locked */ + IMustLock(dir); + au_dir_ts(dir, bindex); + inode_inc_iversion(dir); + au_fhsm_wrote(sb, bindex, /*force*/0); + return 0; /* success */ + } + + err = PTR_ERR(inode); + if (!wh_dentry) + goto out; + + /* revert */ + /* dir inode is locked */ + wh = au_wh_create(dentry, bwh, wh_dentry->d_parent); + rerr = PTR_ERR(wh); + if (IS_ERR(wh)) { + AuIOErr("%pd reverting whiteout failed(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } else + dput(wh); + +out: + return err; +} + +static int au_d_may_add(struct dentry *dentry) +{ + int err; + + err = 0; + if (unlikely(d_unhashed(dentry))) + err = -ENOENT; + if (unlikely(d_really_is_positive(dentry))) + err = -EEXIST; + return err; +} + +/* + * simple tests for the adding inode operations. + * following the checks in vfs, plus the parent-child relationship. + */ +int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir) +{ + int err; + umode_t h_mode; + struct dentry *h_dentry; + struct inode *h_inode; + + err = -ENAMETOOLONG; + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out; + + h_dentry = au_h_dptr(dentry, bindex); + if (d_really_is_negative(dentry)) { + err = -EEXIST; + if (unlikely(d_is_positive(h_dentry))) + goto out; + } else { + /* rename(2) case */ + err = -EIO; + if (unlikely(d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); + if (unlikely(!h_inode->i_nlink)) + goto out; + + h_mode = h_inode->i_mode; + if (!isdir) { + err = -EISDIR; + if (unlikely(S_ISDIR(h_mode))) + goto out; + } else if (unlikely(!S_ISDIR(h_mode))) { + err = -ENOTDIR; + goto out; + } + } + + err = 0; + /* expected parent dir is locked */ + if (unlikely(h_parent != h_dentry->d_parent)) + err = -EIO; + +out: + AuTraceErr(err); + return err; +} + +/* + * initial procedure of adding a new entry. + * prepare writable branch and the parent dir, lock it, + * and lookup whiteout for the new entry. + */ +static struct dentry* +lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt, + struct dentry *src_dentry, struct au_pin *pin, + struct au_wr_dir_args *wr_dir_args) +{ + struct dentry *wh_dentry, *h_parent; + struct super_block *sb; + struct au_branch *br; + int err; + unsigned int udba; + aufs_bindex_t bcpup; + + AuDbg("%pd\n", dentry); + + err = au_wr_dir(dentry, src_dentry, wr_dir_args); + bcpup = err; + wh_dentry = ERR_PTR(err); + if (unlikely(err < 0)) + goto out; + + sb = dentry->d_sb; + udba = au_opt_udba(sb); + err = au_pin(pin, dentry, bcpup, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out; + + h_parent = au_pinned_h_parent(pin); + if (udba != AuOpt_UDBA_NONE + && au_dbtop(dentry) == bcpup) + err = au_may_add(dentry, bcpup, h_parent, + au_ftest_wrdir(wr_dir_args->flags, ISDIR)); + else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + err = -ENAMETOOLONG; + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_unpin; + + br = au_sbr(sb, bcpup); + if (dt) { + struct path tmp = { + .dentry = h_parent, + .mnt = au_br_mnt(br) + }; + au_dtime_store(dt, au_pinned_parent(pin), &tmp); + } + + wh_dentry = NULL; + if (bcpup != au_dbwh(dentry)) + goto out; /* success */ + + /* + * ENAMETOOLONG here means that if we allowed create such name, then it + * would not be able to removed in the future. So we don't allow such + * name here and we don't handle ENAMETOOLONG differently here. + */ + wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br); + +out_unpin: + if (IS_ERR(wh_dentry)) + au_unpin(pin); +out: + return wh_dentry; +} + +/* ---------------------------------------------------------------------- */ + +enum { Mknod, Symlink, Creat }; +struct simple_arg { + int type; + union { + struct { + umode_t mode; + bool want_excl; + bool try_aopen; + struct vfsub_aopen_args *aopen; + } c; + struct { + const char *symname; + } s; + struct { + umode_t mode; + dev_t dev; + } m; + } u; +}; + +static int add_simple(struct inode *dir, struct dentry *dentry, + struct simple_arg *arg) +{ + int err, rerr; + aufs_bindex_t btop; + unsigned char created; + const unsigned char try_aopen + = (arg->type == Creat && arg->u.c.try_aopen); + struct vfsub_aopen_args *aopen = arg->u.c.aopen; + struct dentry *wh_dentry, *parent; + struct inode *h_dir; + struct super_block *sb; + struct au_branch *br; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct au_pin pin; + struct path h_path; + struct au_wr_dir_args wr_dir_args; + } *a; + + AuDbg("%pd\n", dentry); + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + a->wr_dir_args.force_btgt = -1; + a->wr_dir_args.flags = AuWrDir_ADD_ENTRY; + + parent = dentry->d_parent; /* dir inode is locked */ + if (!try_aopen) { + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + } + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + if (!try_aopen) + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, + &a->pin, &a->wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + btop = au_dbtop(dentry); + sb = dentry->d_sb; + br = au_sbr(sb, btop); + a->h_path.dentry = au_h_dptr(dentry, btop); + a->h_path.mnt = au_br_mnt(br); + h_dir = au_pinned_h_dir(&a->pin); + switch (arg->type) { + case Creat: + if (!try_aopen || !h_dir->i_op->atomic_open) { + err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode, + arg->u.c.want_excl); + created = !err; + if (!err && try_aopen) + aopen->file->f_mode |= FMODE_CREATED; + } else { + aopen->br = br; + err = vfsub_atomic_open(h_dir, a->h_path.dentry, aopen); + AuDbg("err %d\n", err); + AuDbgFile(aopen->file); + created = err >= 0 + && !!(aopen->file->f_mode & FMODE_CREATED); + } + break; + case Symlink: + err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname); + created = !err; + break; + case Mknod: + err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode, + arg->u.m.dev); + created = !err; + break; + default: + BUG(); + } + if (unlikely(err < 0)) + goto out_unpin; + + err = epilog(dir, btop, wh_dentry, dentry); + if (!err) + goto out_unpin; /* success */ + + /* revert */ + if (created /* && d_is_positive(a->h_path.dentry) */) { + /* no delegation since it is just created */ + rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL, + /*force*/0); + if (rerr) { + AuIOErr("%pd revert failure(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } + au_dtime_revert(&a->dt); + } + if (try_aopen && h_dir->i_op->atomic_open + && (aopen->file->f_mode & FMODE_OPENED)) + /* aopen->file is still opened */ + au_lcnt_dec(&aopen->br->br_nfiles); + +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); +out_parent: + if (!try_aopen) + di_write_unlock(parent); +out_unlock: + if (unlikely(err)) { + au_update_dbtop(dentry); + d_drop(dentry); + } + if (!try_aopen) + aufs_read_unlock(dentry, AuLock_DW); +out_free: + au_kfree_rcu(a); +out: + return err; +} + +int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t dev) +{ + struct simple_arg arg = { + .type = Mknod, + .u.m = { + .mode = mode, + .dev = dev + } + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + struct simple_arg arg = { + .type = Symlink, + .u.s.symname = symname + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool want_excl) +{ + struct simple_arg arg = { + .type = Creat, + .u.c = { + .mode = mode, + .want_excl = want_excl + } + }; + return add_simple(dir, dentry, &arg); +} + +int au_aopen_or_create(struct inode *dir, struct dentry *dentry, + struct vfsub_aopen_args *aopen_args) +{ + struct simple_arg arg = { + .type = Creat, + .u.c = { + .mode = aopen_args->create_mode, + .want_excl = aopen_args->open_flag & O_EXCL, + .try_aopen = true, + .aopen = aopen_args + } + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct dentry *parent, *h_parent, *h_dentry; + struct inode *h_dir, *inode; + struct vfsmount *h_mnt; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_TMPFILE + }; + + /* copy-up may happen */ + inode_lock(dir); + + sb = dir->i_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + + err = au_di_init(dentry); + if (unlikely(err)) + goto out_si; + + err = -EBUSY; + parent = d_find_any_alias(dir); + AuDebugOn(!parent); + di_write_lock_parent(parent); + if (unlikely(d_inode(parent) != dir)) + goto out_parent; + + err = au_digen_test(parent, au_sigen(sb)); + if (unlikely(err)) + goto out_parent; + + bindex = au_dbtop(parent); + au_set_dbtop(dentry, bindex); + au_set_dbbot(dentry, bindex); + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + bindex = err; + if (unlikely(err < 0)) + goto out_parent; + + err = -EOPNOTSUPP; + h_dir = au_h_iptr(dir, bindex); + if (unlikely(!h_dir->i_op->tmpfile)) + goto out_parent; + + h_mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mnt_want_write(h_mnt); + if (unlikely(err)) + goto out_parent; + + h_parent = au_h_dptr(parent, bindex); + h_dentry = vfs_tmpfile(h_parent, mode, /*open_flag*/0); + if (IS_ERR(h_dentry)) { + err = PTR_ERR(h_dentry); + goto out_mnt; + } + + au_set_dbtop(dentry, bindex); + au_set_dbbot(dentry, bindex); + au_set_h_dptr(dentry, bindex, dget(h_dentry)); + inode = au_new_inode(dentry, /*must_new*/1); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + au_set_h_dptr(dentry, bindex, NULL); + au_set_dbtop(dentry, -1); + au_set_dbbot(dentry, -1); + } else { + if (!inode->i_nlink) + set_nlink(inode, 1); + d_tmpfile(dentry, inode); + au_di(dentry)->di_tmpfile = 1; + + /* update without i_mutex */ + if (au_ibtop(dir) == au_dbtop(dentry)) + au_cpup_attr_timesizes(dir); + } + dput(h_dentry); + +out_mnt: + vfsub_mnt_drop_write(h_mnt); +out_parent: + di_write_unlock(parent); + dput(parent); + di_write_unlock(dentry); + if (unlikely(err)) { + au_di_fin(dentry); + dentry->d_fsdata = NULL; + } +out_si: + si_read_unlock(sb); +out: + inode_unlock(dir); + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct au_link_args { + aufs_bindex_t bdst, bsrc; + struct au_pin pin; + struct path h_path; + struct dentry *src_parent, *parent; +}; + +static int au_cpup_before_link(struct dentry *src_dentry, + struct au_link_args *a) +{ + int err; + struct dentry *h_src_dentry; + struct au_cp_generic cpg = { + .dentry = src_dentry, + .bdst = a->bdst, + .bsrc = a->bsrc, + .len = -1, + .pin = &a->pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */ + }; + + di_read_lock_parent(a->src_parent, AuLock_IR); + err = au_test_and_cpup_dirs(src_dentry, a->bdst); + if (unlikely(err)) + goto out; + + h_src_dentry = au_h_dptr(src_dentry, a->bsrc); + err = au_pin(&a->pin, src_dentry, a->bdst, + au_opt_udba(src_dentry->d_sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out; + + err = au_sio_cpup_simple(&cpg); + au_unpin(&a->pin); + +out: + di_read_unlock(a->src_parent, AuLock_IR); + return err; +} + +static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry, + struct au_link_args *a) +{ + int err; + unsigned char plink; + aufs_bindex_t bbot; + struct dentry *h_src_dentry; + struct inode *h_inode, *inode, *delegated; + struct super_block *sb; + struct file *h_file; + + plink = 0; + h_inode = NULL; + sb = src_dentry->d_sb; + inode = d_inode(src_dentry); + if (au_ibtop(inode) <= a->bdst) + h_inode = au_h_iptr(inode, a->bdst); + if (!h_inode || !h_inode->i_nlink) { + /* copyup src_dentry as the name of dentry. */ + bbot = au_dbbot(dentry); + if (bbot < a->bsrc) + au_set_dbbot(dentry, a->bsrc); + au_set_h_dptr(dentry, a->bsrc, + dget(au_h_dptr(src_dentry, a->bsrc))); + dget(a->h_path.dentry); + au_set_h_dptr(dentry, a->bdst, NULL); + AuDbg("temporary d_inode...\n"); + spin_lock(&dentry->d_lock); + dentry->d_inode = d_inode(src_dentry); /* tmp */ + spin_unlock(&dentry->d_lock); + h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0); + if (IS_ERR(h_file)) + err = PTR_ERR(h_file); + else { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->bdst, + .bsrc = -1, + .len = -1, + .pin = &a->pin, + .flags = AuCpup_KEEPLINO + }; + err = au_sio_cpup_simple(&cpg); + au_h_open_post(dentry, a->bsrc, h_file); + if (!err) { + dput(a->h_path.dentry); + a->h_path.dentry = au_h_dptr(dentry, a->bdst); + } else + au_set_h_dptr(dentry, a->bdst, + a->h_path.dentry); + } + spin_lock(&dentry->d_lock); + dentry->d_inode = NULL; /* restore */ + spin_unlock(&dentry->d_lock); + AuDbg("temporary d_inode...done\n"); + au_set_h_dptr(dentry, a->bsrc, NULL); + au_set_dbbot(dentry, bbot); + } else { + /* the inode of src_dentry already exists on a.bdst branch */ + h_src_dentry = d_find_alias(h_inode); + if (!h_src_dentry && au_plink_test(inode)) { + plink = 1; + h_src_dentry = au_plink_lkup(inode, a->bdst); + err = PTR_ERR(h_src_dentry); + if (IS_ERR(h_src_dentry)) + goto out; + + if (unlikely(d_is_negative(h_src_dentry))) { + dput(h_src_dentry); + h_src_dentry = NULL; + } + + } + if (h_src_dentry) { + delegated = NULL; + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + dput(h_src_dentry); + } else { + AuIOErr("no dentry found for hi%lu on b%d\n", + h_inode->i_ino, a->bdst); + err = -EIO; + } + } + + if (!err && !plink) + au_plink_append(inode, a->bdst, a->h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +int aufs_link(struct dentry *src_dentry, struct inode *dir, + struct dentry *dentry) +{ + int err, rerr; + struct au_dtime dt; + struct au_link_args *a; + struct dentry *wh_dentry, *h_src_dentry; + struct inode *inode, *delegated; + struct super_block *sb; + struct au_wr_dir_args wr_dir_args = { + /* .force_btgt = -1, */ + .flags = AuWrDir_ADD_ENTRY + }; + + IMustLock(dir); + inode = d_inode(src_dentry); + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + a->parent = dentry->d_parent; /* dir inode is locked */ + err = aufs_read_and_write_lock2(dentry, src_dentry, + AuLock_NOPLM | AuLock_GEN); + if (unlikely(err)) + goto out_kfree; + err = au_d_linkable(src_dentry); + if (unlikely(err)) + goto out_unlock; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + a->src_parent = dget_parent(src_dentry); + wr_dir_args.force_btgt = au_ibtop(inode); + + di_write_lock_parent(a->parent); + wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt); + wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin, + &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + err = 0; + sb = dentry->d_sb; + a->bdst = au_dbtop(dentry); + a->h_path.dentry = au_h_dptr(dentry, a->bdst); + a->h_path.mnt = au_sbr_mnt(sb, a->bdst); + a->bsrc = au_ibtop(inode); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + if (!h_src_dentry && au_di(src_dentry)->di_tmpfile) + h_src_dentry = dget(au_hi_wh(inode, a->bsrc)); + if (!h_src_dentry) { + a->bsrc = au_dbtop(src_dentry); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + AuDebugOn(!h_src_dentry); + } else if (IS_ERR(h_src_dentry)) { + err = PTR_ERR(h_src_dentry); + goto out_parent; + } + + /* + * aufs doesn't touch the credential so + * security_dentry_create_files_as() is unnecessary. + */ + if (au_opt_test(au_mntflags(sb), PLINK)) { + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) + err = au_cpup_or_link(src_dentry, dentry, a); + else { + delegated = NULL; + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + } + dput(h_src_dentry); + } else { + /* + * copyup src_dentry to the branch we process, + * and then link(2) to it. + */ + dput(h_src_dentry); + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) { + au_unpin(&a->pin); + di_write_unlock(a->parent); + err = au_cpup_before_link(src_dentry, a); + di_write_lock_parent(a->parent); + if (!err) + err = au_pin(&a->pin, dentry, a->bdst, + au_opt_udba(sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_wh; + } + if (!err) { + h_src_dentry = au_h_dptr(src_dentry, a->bdst); + err = -ENOENT; + if (h_src_dentry && d_is_positive(h_src_dentry)) { + delegated = NULL; + err = vfsub_link(h_src_dentry, + au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry" + " for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + } + } + } + if (unlikely(err)) + goto out_unpin; + + if (wh_dentry) { + a->h_path.dentry = wh_dentry; + err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path, + dentry); + if (unlikely(err)) + goto out_revert; + } + + au_dir_ts(dir, a->bdst); + inode_inc_iversion(dir); + inc_nlink(inode); + inode->i_ctime = dir->i_ctime; + d_instantiate(dentry, au_igrab(inode)); + if (d_unhashed(a->h_path.dentry)) + /* some filesystem calls d_drop() */ + d_drop(dentry); + /* some filesystems consume an inode even hardlink */ + au_fhsm_wrote(sb, a->bdst, /*force*/0); + goto out_unpin; /* success */ + +out_revert: + /* no delegation since it is just created */ + rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, + /*delegated*/NULL, /*force*/0); + if (unlikely(rerr)) { + AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr); + err = -EIO; + } + au_dtime_revert(&dt); +out_unpin: + au_unpin(&a->pin); +out_wh: + dput(wh_dentry); +out_parent: + di_write_unlock(a->parent); + dput(a->src_parent); +out_unlock: + if (unlikely(err)) { + au_update_dbtop(dentry); + d_drop(dentry); + } + aufs_read_and_write_unlock2(dentry, src_dentry); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} + +int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err, rerr; + aufs_bindex_t bindex; + unsigned char diropq; + struct path h_path; + struct dentry *wh_dentry, *parent, *opq_dentry; + struct inode *h_inode; + struct super_block *sb; + struct { + struct au_pin pin; + struct au_dtime dt; + } *a; /* reduce the stack usage */ + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR + }; + + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, + &a->pin, &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + sb = dentry->d_sb; + bindex = au_dbtop(dentry); + h_path.dentry = au_h_dptr(dentry, bindex); + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode); + if (unlikely(err)) + goto out_unpin; + + /* make the dir opaque */ + diropq = 0; + h_inode = d_inode(h_path.dentry); + if (wh_dentry + || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) { + inode_lock_nested(h_inode, AuLsc_I_CHILD); + opq_dentry = au_diropq_create(dentry, bindex); + inode_unlock(h_inode); + err = PTR_ERR(opq_dentry); + if (IS_ERR(opq_dentry)) + goto out_dir; + dput(opq_dentry); + diropq = 1; + } + + err = epilog(dir, bindex, wh_dentry, dentry); + if (!err) { + inc_nlink(dir); + goto out_unpin; /* success */ + } + + /* revert */ + if (diropq) { + AuLabel(revert opq); + inode_lock_nested(h_inode, AuLsc_I_CHILD); + rerr = au_diropq_remove(dentry, bindex); + inode_unlock(h_inode); + if (rerr) { + AuIOErr("%pd reverting diropq failed(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } + } + +out_dir: + AuLabel(revert dir); + rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path); + if (rerr) { + AuIOErr("%pd reverting dir failed(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } + au_dtime_revert(&a->dt); +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); +out_parent: + di_write_unlock(parent); +out_unlock: + if (unlikely(err)) { + au_update_dbtop(dentry); + d_drop(dentry); + } + aufs_read_unlock(dentry, AuLock_DW); +out_free: + au_kfree_rcu(a); +out: + return err; +} diff --git a/fs/aufs/i_op_del.c b/fs/aufs/i_op_del.c new file mode 100644 index 000000000000..9beba2ba8db0 --- /dev/null +++ b/fs/aufs/i_op_del.c @@ -0,0 +1,513 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (del entry) + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* + * decide if a new whiteout for @dentry is necessary or not. + * when it is necessary, prepare the parent dir for the upper branch whose + * branch index is @bcpup for creation. the actual creation of the whiteout will + * be done by caller. + * return value: + * 0: wh is unnecessary + * plus: wh is necessary + * minus: error + */ +int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup) +{ + int need_wh, err; + aufs_bindex_t btop; + struct super_block *sb; + + sb = dentry->d_sb; + btop = au_dbtop(dentry); + if (*bcpup < 0) { + *bcpup = btop; + if (au_test_ro(sb, btop, d_inode(dentry))) { + err = AuWbrCopyup(au_sbi(sb), dentry); + *bcpup = err; + if (unlikely(err < 0)) + goto out; + } + } else + AuDebugOn(btop < *bcpup + || au_test_ro(sb, *bcpup, d_inode(dentry))); + AuDbg("bcpup %d, btop %d\n", *bcpup, btop); + + if (*bcpup != btop) { + err = au_cpup_dirs(dentry, *bcpup); + if (unlikely(err)) + goto out; + need_wh = 1; + } else { + struct au_dinfo *dinfo, *tmp; + + need_wh = -ENOMEM; + dinfo = au_di(dentry); + tmp = au_di_alloc(sb, AuLsc_DI_TMP); + if (tmp) { + au_di_cp(tmp, dinfo); + au_di_swap(tmp, dinfo); + /* returns the number of positive dentries */ + need_wh = au_lkup_dentry(dentry, btop + 1, + /* AuLkup_IGNORE_PERM */ 0); + au_di_swap(tmp, dinfo); + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + } + } + 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); + if (d_really_is_positive(dentry)) { + err = -ENOENT; + if (unlikely(d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); + if (unlikely(!h_inode->i_nlink)) + goto out; + + h_mode = h_inode->i_mode; + if (!isdir) { + err = -EISDIR; + if (unlikely(S_ISDIR(h_mode))) + goto out; + } else if (unlikely(!S_ISDIR(h_mode))) { + err = -ENOTDIR; + goto out; + } + } else { + /* rename(2) case */ + err = -EIO; + if (unlikely(d_is_positive(h_dentry))) + goto out; + } + + err = -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_opt_test(au_mntflags(dentry->d_sb), DIRPERM1) + && au_test_h_perm(d_inode(h_parent), + MAY_EXEC | MAY_WRITE))) + goto out; + + h_latest = au_sio_lkup_one(&dentry->d_name, h_parent); + err = -EIO; + if (IS_ERR(h_latest)) + goto out; + if (h_latest == h_dentry) + err = 0; + dput(h_latest); + +out: + return err; +} + +/* + * decide the branch where we operate for @dentry. the branch index will be set + * @rbcpup. after deciding it, 'pin' it and store the timestamps of the parent + * dir for reverting. + * when a new whiteout is necessary, create it. + */ +static struct dentry* +lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup, + struct au_dtime *dt, struct au_pin *pin) +{ + struct dentry *wh_dentry; + struct super_block *sb; + struct 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_dbtop(dentry) == bcpup) { + err = au_may_del(dentry, bcpup, h_path.dentry, isdir); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_unpin; + } + + h_path.mnt = au_sbr_mnt(sb, bcpup); + au_dtime_store(dt, au_pinned_parent(pin), &h_path); + wh_dentry = NULL; + if (!need_wh) + goto out; /* success, no need to create whiteout */ + + wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry); + if (IS_ERR(wh_dentry)) + goto out_unpin; + + /* returns with the parent is locked and wh_dentry is dget-ed */ + goto out; /* success */ + +out_unpin: + au_unpin(pin); +out: + 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; + struct inode *inode; + + sb = dentry->d_sb; + SiMustAnyLock(sb); + h_dentry = au_h_dptr(dentry, bindex); + err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex)); + if (unlikely(err)) + goto out; + + /* stop monitoring */ + inode = d_inode(dentry); + au_hn_free(au_hi(inode, bindex)); + + if (!au_test_fs_remote(h_dentry->d_sb)) { + dirwh = au_sbi(sb)->si_dirwh; + rmdir_later = (dirwh <= 1); + if (!rmdir_later) + rmdir_later = au_nhash_test_longer_wh(whlist, bindex, + dirwh); + if (rmdir_later) + return rmdir_later; + } + + err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist); + if (unlikely(err)) { + AuIOErr("rmdir %pd, b%d failed, %d. ignored\n", + h_dentry, bindex, err); + err = 0; + } + +out: + AuTraceErr(err); + return err; +} + +/* + * final procedure for deleting a entry. + * maintain dentry and iattr. + */ +static void epilog(struct inode *dir, struct dentry *dentry, + aufs_bindex_t bindex) +{ + struct inode *inode; + + inode = d_inode(dentry); + d_drop(dentry); + inode->i_ctime = dir->i_ctime; + + au_dir_ts(dir, bindex); + inode_inc_iversion(dir); +} + +/* + * when an error happened, remove the created whiteout and revert everything. + */ +static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex, + aufs_bindex_t bwh, struct dentry *wh_dentry, + struct dentry *dentry, struct au_dtime *dt) +{ + int rerr; + struct path h_path = { + .dentry = wh_dentry, + .mnt = au_sbr_mnt(dir->i_sb, bindex) + }; + + rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry); + if (!rerr) { + au_set_dbwh(dentry, bwh); + au_dtime_revert(dt); + return 0; + } + + AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr); + return -EIO; +} + +/* ---------------------------------------------------------------------- */ + +int aufs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + aufs_bindex_t bwh, bindex, btop; + struct inode *inode, *h_dir, *delegated; + struct dentry *parent, *wh_dentry; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct au_pin pin; + struct path h_path; + } *a; + + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + err = au_d_hashed_positive(dentry); + if (unlikely(err)) + goto out_unlock; + inode = d_inode(dentry); + IMustLock(inode); + err = -EISDIR; + if (unlikely(d_is_dir(dentry))) + goto out_unlock; /* possible? */ + + btop = au_dbtop(dentry); + bwh = au_dbwh(dentry); + bindex = -1; + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt, + &a->pin); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop); + a->h_path.dentry = au_h_dptr(dentry, btop); + dget(a->h_path.dentry); + if (bindex == btop) { + h_dir = au_pinned_h_dir(&a->pin); + delegated = NULL; + err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + } else { + /* dir inode is locked */ + h_dir = d_inode(wh_dentry->d_parent); + IMustLock(h_dir); + err = 0; + } + + if (!err) { + vfsub_drop_nlink(inode); + epilog(dir, dentry, bindex); + + /* update target timestamps */ + if (bindex == btop) { + vfsub_update_h_iattr(&a->h_path, /*did*/NULL); + /*ignore*/ + inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; + } else + /* todo: this timestamp may be reverted later */ + inode->i_ctime = h_dir->i_ctime; + goto out_unpin; /* success */ + } + + /* revert */ + if (wh_dentry) { + int rerr; + + rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, + &a->dt); + if (rerr) + err = rerr; + } + +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); + dput(a->h_path.dentry); +out_parent: + di_write_unlock(parent); +out_unlock: + aufs_read_unlock(dentry, AuLock_DW); +out_free: + au_kfree_rcu(a); +out: + return err; +} + +int aufs_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err, rmdir_later; + aufs_bindex_t bwh, bindex, btop; + struct inode *inode; + struct dentry *parent, *wh_dentry, *h_dentry; + struct au_whtmp_rmdir *args; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct au_pin pin; + } *a; + + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); + if (unlikely(err)) + goto out_free; + err = au_alive_dir(dentry); + if (unlikely(err)) + goto out_unlock; + inode = d_inode(dentry); + IMustLock(inode); + err = -ENOTDIR; + if (unlikely(!d_is_dir(dentry))) + goto out_unlock; /* possible? */ + + err = -ENOMEM; + args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS); + if (unlikely(!args)) + goto out_unlock; + + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + err = au_test_empty(dentry, &args->whlist); + if (unlikely(err)) + goto out_parent; + + btop = au_dbtop(dentry); + bwh = au_dbwh(dentry); + bindex = -1; + wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt, + &a->pin); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + h_dentry = au_h_dptr(dentry, btop); + dget(h_dentry); + rmdir_later = 0; + if (bindex == btop) { + err = renwh_and_rmdir(dentry, btop, &args->whlist, dir); + if (err > 0) { + rmdir_later = err; + err = 0; + } + } else { + /* stop monitoring */ + au_hn_free(au_hi(inode, btop)); + + /* dir inode is locked */ + IMustLock(d_inode(wh_dentry->d_parent)); + err = 0; + } + + if (!err) { + vfsub_dead_dir(inode); + au_set_dbdiropq(dentry, -1); + epilog(dir, dentry, bindex); + + if (rmdir_later) { + au_whtmp_kick_rmdir(dir, btop, h_dentry, args); + args = NULL; + } + + goto out_unpin; /* success */ + } + + /* revert */ + AuLabel(revert); + if (wh_dentry) { + int rerr; + + rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, + &a->dt); + if (rerr) + err = rerr; + } + +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); + dput(h_dentry); +out_parent: + di_write_unlock(parent); + if (args) + au_whtmp_rmdir_free(args); +out_unlock: + aufs_read_unlock(dentry, AuLock_DW); +out_free: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c new file mode 100644 index 000000000000..435fa50811ff --- /dev/null +++ b/fs/aufs/i_op_ren.c @@ -0,0 +1,1250 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operation (rename entry) + * todo: this is crazy monster + */ + +#include <linux/iversion.h> +#include "aufs.h" + +enum { AuSRC, AuDST, AuSrcDst }; +enum { AuPARENT, AuCHILD, AuParentChild }; + +#define AuRen_ISDIR_SRC 1 +#define AuRen_ISDIR_DST (1 << 1) +#define AuRen_ISSAMEDIR (1 << 2) +#define AuRen_WHSRC (1 << 3) +#define AuRen_WHDST (1 << 4) +#define AuRen_MNT_WRITE (1 << 5) +#define AuRen_DT_DSTDIR (1 << 6) +#define AuRen_DIROPQ_SRC (1 << 7) +#define AuRen_DIROPQ_DST (1 << 8) +#define AuRen_DIRREN (1 << 9) +#define AuRen_DROPPED_SRC (1 << 10) +#define AuRen_DROPPED_DST (1 << 11) +#define au_ftest_ren(flags, name) ((flags) & AuRen_##name) +#define au_fset_ren(flags, name) \ + do { (flags) |= AuRen_##name; } while (0) +#define au_fclr_ren(flags, name) \ + do { (flags) &= ~AuRen_##name; } while (0) + +#ifndef CONFIG_AUFS_DIRREN +#undef AuRen_DIRREN +#define AuRen_DIRREN 0 +#endif + +struct au_ren_args { + struct { + struct dentry *dentry, *h_dentry, *parent, *h_parent, + *wh_dentry; + struct inode *dir, *inode; + struct au_hinode *hdir, *hinode; + struct au_dtime dt[AuParentChild]; + aufs_bindex_t btop, bdiropq; + } sd[AuSrcDst]; + +#define src_dentry sd[AuSRC].dentry +#define src_dir sd[AuSRC].dir +#define src_inode sd[AuSRC].inode +#define src_h_dentry sd[AuSRC].h_dentry +#define src_parent sd[AuSRC].parent +#define src_h_parent sd[AuSRC].h_parent +#define src_wh_dentry sd[AuSRC].wh_dentry +#define src_hdir sd[AuSRC].hdir +#define src_hinode sd[AuSRC].hinode +#define src_h_dir sd[AuSRC].hdir->hi_inode +#define src_dt sd[AuSRC].dt +#define src_btop sd[AuSRC].btop +#define src_bdiropq sd[AuSRC].bdiropq + +#define dst_dentry sd[AuDST].dentry +#define dst_dir sd[AuDST].dir +#define dst_inode sd[AuDST].inode +#define dst_h_dentry sd[AuDST].h_dentry +#define dst_parent sd[AuDST].parent +#define dst_h_parent sd[AuDST].h_parent +#define dst_wh_dentry sd[AuDST].wh_dentry +#define dst_hdir sd[AuDST].hdir +#define dst_hinode sd[AuDST].hinode +#define dst_h_dir sd[AuDST].hdir->hi_inode +#define dst_dt sd[AuDST].dt +#define dst_btop sd[AuDST].btop +#define dst_bdiropq sd[AuDST].bdiropq + + struct dentry *h_trap; + struct au_branch *br; + struct path h_path; + struct au_nhash whlist; + aufs_bindex_t btgt, src_bwh; + + struct { + unsigned short auren_flags; + unsigned char flags; /* syscall parameter */ + unsigned char exchange; + } __packed; + + struct au_whtmp_rmdir *thargs; + struct dentry *h_dst; + struct au_hinode *h_root; +}; + +/* ---------------------------------------------------------------------- */ + +/* + * functions for reverting. + * when an error happened in a single rename systemcall, we should revert + * everything as if nothing happened. + * we don't need to revert the copied-up/down the parent dir since they are + * harmless. + */ + +#define RevertFailure(fmt, ...) do { \ + AuIOErr("revert failure: " fmt " (%d, %d)\n", \ + ##__VA_ARGS__, err, rerr); \ + err = -EIO; \ +} while (0) + +static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx) +{ + int rerr; + struct dentry *d; +#define src_or_dst(member) a->sd[idx].member + + d = src_or_dst(dentry); /* {src,dst}_dentry */ + au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD); + rerr = au_diropq_remove(d, a->btgt); + au_hn_inode_unlock(src_or_dst(hinode)); + au_set_dbdiropq(d, src_or_dst(bdiropq)); + if (rerr) + RevertFailure("remove diropq %pd", d); + +#undef src_or_dst_ +} + +static void au_ren_rev_diropq(int err, struct au_ren_args *a) +{ + if (au_ftest_ren(a->auren_flags, DIROPQ_SRC)) + au_ren_do_rev_diropq(err, a, AuSRC); + if (au_ftest_ren(a->auren_flags, DIROPQ_DST)) + au_ren_do_rev_diropq(err, a, AuDST); +} + +static void au_ren_rev_rename(int err, struct au_ren_args *a) +{ + int rerr; + struct inode *delegated; + + a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, + a->src_h_parent); + rerr = PTR_ERR(a->h_path.dentry); + if (IS_ERR(a->h_path.dentry)) { + RevertFailure("lkup one %pd", a->src_dentry); + return; + } + + delegated = NULL; + rerr = vfsub_rename(a->dst_h_dir, + au_h_dptr(a->src_dentry, a->btgt), + a->src_h_dir, &a->h_path, &delegated, a->flags); + if (unlikely(rerr == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal rename\n"); + iput(delegated); + } + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */ + if (rerr) + RevertFailure("rename %pd", a->src_dentry); +} + +static void au_ren_rev_whtmp(int err, struct au_ren_args *a) +{ + int rerr; + struct inode *delegated; + + a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, + a->dst_h_parent); + rerr = PTR_ERR(a->h_path.dentry); + if (IS_ERR(a->h_path.dentry)) { + RevertFailure("lkup one %pd", a->dst_dentry); + return; + } + if (d_is_positive(a->h_path.dentry)) { + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + return; + } + + delegated = NULL; + rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path, + &delegated, a->flags); + if (unlikely(rerr == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal rename\n"); + iput(delegated); + } + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + if (!rerr) + au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst)); + else + RevertFailure("rename %pd", a->h_dst); +} + +static void au_ren_rev_whsrc(int err, struct au_ren_args *a) +{ + int rerr; + + a->h_path.dentry = a->src_wh_dentry; + rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry); + au_set_dbwh(a->src_dentry, a->src_bwh); + if (rerr) + RevertFailure("unlink %pd", a->src_wh_dentry); +} +#undef RevertFailure + +/* ---------------------------------------------------------------------- */ + +/* + * when we have to copyup the renaming entry, do it with the rename-target name + * in order to minimize the cost (the later actual rename is unnecessary). + * otherwise rename it on the target branch. + */ +static int au_ren_or_cpup(struct au_ren_args *a) +{ + int err; + struct dentry *d; + struct inode *delegated; + + d = a->src_dentry; + if (au_dbtop(d) == a->btgt) { + a->h_path.dentry = a->dst_h_dentry; + AuDebugOn(au_dbtop(d) != a->btgt); + delegated = NULL; + err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt), + a->dst_h_dir, &a->h_path, &delegated, + a->flags); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal rename\n"); + iput(delegated); + } + } else + BUG(); + + if (!err && a->h_dst) + /* it will be set to dinfo later */ + dget(a->h_dst); + + return err; +} + +/* cf. aufs_rmdir() */ +static int au_ren_del_whtmp(struct au_ren_args *a) +{ + int err; + struct inode *dir; + + dir = a->dst_dir; + SiMustAnyLock(dir->i_sb); + if (!au_nhash_test_longer_wh(&a->whlist, a->btgt, + au_sbi(dir->i_sb)->si_dirwh) + || au_test_fs_remote(a->h_dst->d_sb)) { + err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist); + if (unlikely(err)) + pr_warn("failed removing whtmp dir %pd (%d), " + "ignored.\n", a->h_dst, err); + } else { + au_nhash_wh_free(&a->thargs->whlist); + a->thargs->whlist = a->whlist; + a->whlist.nh_num = 0; + au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs); + dput(a->h_dst); + a->thargs = NULL; + } + + return 0; +} + +/* make it 'opaque' dir. */ +static int au_ren_do_diropq(struct au_ren_args *a, int idx) +{ + int err; + struct dentry *d, *diropq; +#define src_or_dst(member) a->sd[idx].member + + err = 0; + d = src_or_dst(dentry); /* {src,dst}_dentry */ + src_or_dst(bdiropq) = au_dbdiropq(d); + src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt); + au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD); + diropq = au_diropq_create(d, a->btgt); + au_hn_inode_unlock(src_or_dst(hinode)); + if (IS_ERR(diropq)) + err = PTR_ERR(diropq); + else + dput(diropq); + +#undef src_or_dst_ + return err; +} + +static int au_ren_diropq(struct au_ren_args *a) +{ + int err; + unsigned char always; + struct dentry *d; + + err = 0; + d = a->dst_dentry; /* already renamed on the branch */ + always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ); + if (au_ftest_ren(a->auren_flags, ISDIR_SRC) + && !au_ftest_ren(a->auren_flags, DIRREN) + && a->btgt != au_dbdiropq(a->src_dentry) + && (a->dst_wh_dentry + || a->btgt <= au_dbdiropq(d) + /* hide the lower to keep xino */ + /* the lowers may not be a dir, but we hide them anyway */ + || a->btgt < au_dbbot(d) + || always)) { + AuDbg("here\n"); + err = au_ren_do_diropq(a, AuSRC); + if (unlikely(err)) + goto out; + au_fset_ren(a->auren_flags, DIROPQ_SRC); + } + if (!a->exchange) + goto out; /* success */ + + d = a->src_dentry; /* already renamed on the branch */ + if (au_ftest_ren(a->auren_flags, ISDIR_DST) + && a->btgt != au_dbdiropq(a->dst_dentry) + && (a->btgt < au_dbdiropq(d) + || a->btgt < au_dbbot(d) + || always)) { + AuDbgDentry(a->src_dentry); + AuDbgDentry(a->dst_dentry); + err = au_ren_do_diropq(a, AuDST); + if (unlikely(err)) + goto out_rev_src; + au_fset_ren(a->auren_flags, DIROPQ_DST); + } + goto out; /* success */ + +out_rev_src: + AuDbg("err %d, reverting src\n", err); + au_ren_rev_diropq(err, a); +out: + return err; +} + +static int do_rename(struct au_ren_args *a) +{ + int err; + struct dentry *d, *h_d; + + if (!a->exchange) { + /* prepare workqueue args for asynchronous rmdir */ + h_d = a->dst_h_dentry; + if (au_ftest_ren(a->auren_flags, ISDIR_DST) + /* && !au_ftest_ren(a->auren_flags, DIRREN) */ + && d_is_positive(h_d)) { + err = -ENOMEM; + a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb, + GFP_NOFS); + if (unlikely(!a->thargs)) + goto out; + a->h_dst = dget(h_d); + } + + /* create whiteout for src_dentry */ + if (au_ftest_ren(a->auren_flags, WHSRC)) { + a->src_bwh = au_dbwh(a->src_dentry); + AuDebugOn(a->src_bwh >= 0); + a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt, + a->src_h_parent); + err = PTR_ERR(a->src_wh_dentry); + if (IS_ERR(a->src_wh_dentry)) + goto out_thargs; + } + + /* lookup whiteout for dentry */ + if (au_ftest_ren(a->auren_flags, WHDST)) { + h_d = au_wh_lkup(a->dst_h_parent, + &a->dst_dentry->d_name, a->br); + err = PTR_ERR(h_d); + if (IS_ERR(h_d)) + goto out_whsrc; + if (d_is_negative(h_d)) + dput(h_d); + else + a->dst_wh_dentry = h_d; + } + + /* 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, /*wh*/0); + if (unlikely(err)) + goto out_whtmp; + a->dst_h_dentry = au_h_dptr(d, a->btgt); + } + } + + BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt); +#if 0 /* debugging */ + BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN) + && d_is_positive(a->dst_h_dentry) + && a->src_btop != a->btgt); +#endif + + /* rename by vfs_rename or cpup */ + err = au_ren_or_cpup(a); + if (unlikely(err)) + /* leave the copied-up one */ + goto out_whtmp; + + /* make dir opaque */ + err = au_ren_diropq(a); + if (unlikely(err)) + goto out_rename; + + /* update target timestamps */ + if (a->exchange) { + AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt); + a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt); + vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/ + a->dst_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; + } + AuDebugOn(au_dbtop(a->src_dentry) != a->btgt); + a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt); + vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/ + a->src_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; + + if (!a->exchange) { + /* remove whiteout for dentry */ + if (a->dst_wh_dentry) { + a->h_path.dentry = a->dst_wh_dentry; + err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path, + a->dst_dentry); + if (unlikely(err)) + goto out_diropq; + } + + /* remove whtmp */ + if (a->thargs) + au_ren_del_whtmp(a); /* ignore this error */ + + au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0); + } + err = 0; + goto out_success; + +out_diropq: + au_ren_rev_diropq(err, a); +out_rename: + au_ren_rev_rename(err, a); + dput(a->h_dst); +out_whtmp: + if (a->thargs) + au_ren_rev_whtmp(err, a); +out_whdst: + dput(a->dst_wh_dentry); + a->dst_wh_dentry = NULL; +out_whsrc: + if (a->src_wh_dentry) + au_ren_rev_whsrc(err, a); +out_success: + dput(a->src_wh_dentry); + dput(a->dst_wh_dentry); +out_thargs: + if (a->thargs) { + dput(a->h_dst); + au_whtmp_rmdir_free(a->thargs); + a->thargs = NULL; + } +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * 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 @a->src_dentry dir can be rename source or not. + * if it can, return 0. + * success means, + * - it is a logically empty dir. + * - or, it exists on writable branch and has no children including whiteouts + * on the lower branch unless DIRREN is on. + */ +static int may_rename_srcdir(struct au_ren_args *a) +{ + int err; + unsigned int rdhash; + aufs_bindex_t btop, btgt; + struct dentry *dentry; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + dentry = a->src_dentry; + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + if (au_opt_test(sbinfo->si_mntflags, DIRREN)) + au_fset_ren(a->auren_flags, DIRREN); + + btgt = a->btgt; + btop = au_dbtop(dentry); + if (btop != btgt) { + struct au_nhash whlist; + + SiMustAnyLock(sb); + rdhash = sbinfo->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, + dentry)); + err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_test_empty(dentry, &whlist); + au_nhash_wh_free(&whlist); + goto out; + } + + if (btop == au_dbtaildir(dentry)) + return 0; /* success */ + + err = au_test_empty_lower(dentry); + +out: + if (err == -ENOTEMPTY) { + if (au_ftest_ren(a->auren_flags, DIRREN)) { + err = 0; + } else { + AuWarn1("renaming dir who has child(ren) on multiple " + "branches, is not supported\n"); + err = -EXDEV; + } + } + return err; +} + +/* side effect: sets whlist and h_dentry */ +static int au_ren_may_dir(struct au_ren_args *a) +{ + int err; + unsigned int rdhash; + struct dentry *d; + + d = a->dst_dentry; + SiMustAnyLock(d->d_sb); + + err = 0; + if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) { + rdhash = au_sbi(d->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d)); + err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + + if (!a->exchange) { + au_set_dbtop(d, a->dst_btop); + err = may_rename_dstdir(d, &a->whlist); + au_set_dbtop(d, a->btgt); + } else + err = may_rename_srcdir(a); + } + a->dst_h_dentry = au_h_dptr(d, au_dbtop(d)); + if (unlikely(err)) + goto out; + + d = a->src_dentry; + a->src_h_dentry = au_h_dptr(d, au_dbtop(d)); + if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) { + err = may_rename_srcdir(a); + if (unlikely(err)) { + au_nhash_wh_free(&a->whlist); + a->whlist.nh_num = 0; + } + } +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * 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_btop == a->btgt) { + err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent, + au_ftest_ren(a->auren_flags, ISDIR_SRC)); + if (unlikely(err)) + goto out; + err = -EINVAL; + if (unlikely(a->src_h_dentry == a->h_trap)) + goto out; + } + + err = 0; + if (a->dst_btop != a->btgt) + goto out; + + err = -ENOTEMPTY; + if (unlikely(a->dst_h_dentry == a->h_trap)) + goto out; + + err = -EIO; + isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST); + if (d_really_is_negative(a->dst_dentry)) { + if (d_is_negative(a->dst_h_dentry)) + err = au_may_add(a->dst_dentry, a->btgt, + a->dst_h_parent, isdir); + } else { + if (unlikely(d_is_negative(a->dst_h_dentry))) + goto out; + h_inode = d_inode(a->dst_h_dentry); + if (h_inode->i_nlink) + err = au_may_del(a->dst_dentry, a->btgt, + a->dst_h_parent, isdir); + } + +out: + if (unlikely(err == -ENOENT || err == -EEXIST)) + err = -EIO; + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * locking order + * (VFS) + * - src_dir and dir by lock_rename() + * - inode if exists + * (aufs) + * - lock all + * + src_dentry and dentry by aufs_read_and_write_lock2() which calls, + * + si_read_lock + * + di_write_lock2_child() + * + di_write_lock_child() + * + ii_write_lock_child() + * + di_write_lock_child2() + * + ii_write_lock_child2() + * + src_parent and parent + * + di_write_lock_parent() + * + ii_write_lock_parent() + * + di_write_lock_parent2() + * + ii_write_lock_parent2() + * + lower src_dir and dir by vfsub_lock_rename() + * + verify the every relationships between child and parent. if any + * of them failed, unlock all and return -EBUSY. + */ +static void au_ren_unlock(struct au_ren_args *a) +{ + vfsub_unlock_rename(a->src_h_parent, a->src_hdir, + a->dst_h_parent, a->dst_hdir); + if (au_ftest_ren(a->auren_flags, DIRREN) + && a->h_root) + au_hn_inode_unlock(a->h_root); + if (au_ftest_ren(a->auren_flags, MNT_WRITE)) + vfsub_mnt_drop_write(au_br_mnt(a->br)); +} + +static 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); + + err = vfsub_mnt_want_write(au_br_mnt(a->br)); + if (unlikely(err)) + goto out; + au_fset_ren(a->auren_flags, MNT_WRITE); + if (au_ftest_ren(a->auren_flags, DIRREN)) { + struct dentry *root; + struct inode *dir; + + /* + * sbinfo is already locked, so this ii_read_lock is + * unnecessary. but our debugging feature checks it. + */ + root = a->src_inode->i_sb->s_root; + if (root != a->src_parent && root != a->dst_parent) { + dir = d_inode(root); + ii_read_lock_parent3(dir); + a->h_root = au_hi(dir, a->btgt); + ii_read_unlock(dir); + au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3); + } + } + a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir, + a->dst_h_parent, a->dst_hdir); + udba = au_opt_udba(a->src_dentry->d_sb); + if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent) + || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent))) + err = au_busy_or_stale(); + if (!err && au_dbtop(a->src_dentry) == a->btgt) + err = au_h_verify(a->src_h_dentry, udba, + d_inode(a->src_h_parent), a->src_h_parent, + a->br); + if (!err && au_dbtop(a->dst_dentry) == a->btgt) + err = au_h_verify(a->dst_h_dentry, udba, + d_inode(a->dst_h_parent), a->dst_h_parent, + a->br); + if (!err) + goto out; /* success */ + + err = au_busy_or_stale(); + au_ren_unlock(a); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_ren_refresh_dir(struct au_ren_args *a) +{ + struct inode *dir; + + dir = a->dst_dir; + inode_inc_iversion(dir); + if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) { + /* is this updating defined in POSIX? */ + au_cpup_attr_timesizes(a->src_inode); + au_cpup_attr_nlink(dir, /*force*/1); + } + au_dir_ts(dir, a->btgt); + + if (a->exchange) { + dir = a->src_dir; + inode_inc_iversion(dir); + if (au_ftest_ren(a->auren_flags, ISDIR_DST)) { + /* is this updating defined in POSIX? */ + au_cpup_attr_timesizes(a->dst_inode); + au_cpup_attr_nlink(dir, /*force*/1); + } + au_dir_ts(dir, a->btgt); + } + + if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) + return; + + dir = a->src_dir; + inode_inc_iversion(dir); + if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) + au_cpup_attr_nlink(dir, /*force*/1); + au_dir_ts(dir, a->btgt); +} + +static void au_ren_refresh(struct au_ren_args *a) +{ + aufs_bindex_t bbot, bindex; + struct dentry *d, *h_d; + struct inode *i, *h_i; + struct super_block *sb; + + d = a->dst_dentry; + d_drop(d); + if (a->h_dst) + /* already dget-ed by au_ren_or_cpup() */ + au_set_h_dptr(d, a->btgt, a->h_dst); + + i = a->dst_inode; + if (i) { + if (!a->exchange) { + if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) + vfsub_drop_nlink(i); + else { + vfsub_dead_dir(i); + au_cpup_attr_timesizes(i); + } + au_update_dbrange(d, /*do_put_zero*/1); + } else + au_cpup_attr_nlink(i, /*force*/1); + } else { + bbot = a->btgt; + for (bindex = au_dbtop(d); bindex < bbot; bindex++) + au_set_h_dptr(d, bindex, NULL); + bbot = au_dbbot(d); + for (bindex = a->btgt + 1; bindex <= bbot; bindex++) + au_set_h_dptr(d, bindex, NULL); + au_update_dbrange(d, /*do_put_zero*/0); + } + + if (a->exchange + || au_ftest_ren(a->auren_flags, DIRREN)) { + d_drop(a->src_dentry); + if (au_ftest_ren(a->auren_flags, DIRREN)) + au_set_dbwh(a->src_dentry, -1); + return; + } + + d = a->src_dentry; + au_set_dbwh(d, -1); + bbot = au_dbbot(d); + for (bindex = a->btgt + 1; bindex <= bbot; bindex++) { + h_d = au_h_dptr(d, bindex); + if (h_d) + au_set_h_dptr(d, bindex, NULL); + } + au_set_dbbot(d, a->btgt); + + sb = d->d_sb; + i = a->src_inode; + if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i)) + return; /* success */ + + bbot = au_ibbot(i); + for (bindex = a->btgt + 1; bindex <= bbot; bindex++) { + h_i = au_h_iptr(i, bindex); + if (h_i) { + au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0); + /* ignore this error */ + au_set_h_iptr(i, bindex, NULL, 0); + } + } + au_set_ibbot(i, a->btgt); +} + +/* ---------------------------------------------------------------------- */ + +/* mainly for link(2) and rename(2) */ +int au_wbr(struct dentry *dentry, aufs_bindex_t btgt) +{ + aufs_bindex_t bdiropq, bwh; + struct dentry *parent; + struct au_branch *br; + + parent = dentry->d_parent; + IMustLock(d_inode(parent)); /* dir is locked */ + + bdiropq = au_dbdiropq(parent); + bwh = au_dbwh(dentry); + br = au_sbr(dentry->d_sb, btgt); + if (au_br_rdonly(br) + || (0 <= bdiropq && bdiropq < btgt) + || (0 <= bwh && bwh < btgt)) + btgt = -1; + + AuDbg("btgt %d\n", btgt); + return btgt; +} + +/* sets src_btop, dst_btop and btgt */ +static int au_ren_wbr(struct au_ren_args *a) +{ + int err; + struct au_wr_dir_args wr_dir_args = { + /* .force_btgt = -1, */ + .flags = AuWrDir_ADD_ENTRY + }; + + a->src_btop = au_dbtop(a->src_dentry); + a->dst_btop = au_dbtop(a->dst_dentry); + if (au_ftest_ren(a->auren_flags, ISDIR_SRC) + || au_ftest_ren(a->auren_flags, ISDIR_DST)) + au_fset_wrdir(wr_dir_args.flags, ISDIR); + wr_dir_args.force_btgt = a->src_btop; + if (a->dst_inode && a->dst_btop < a->src_btop) + wr_dir_args.force_btgt = a->dst_btop; + wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt); + err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args); + a->btgt = err; + if (a->exchange) + au_update_dbtop(a->dst_dentry); + + 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->auren_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->auren_flags, DT_DSTDIR); + if (!au_ftest_ren(a->auren_flags, ISDIR_SRC) + && !a->exchange) + return; + + a->h_path.dentry = a->src_h_dentry; + au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path); + if (d_is_positive(a->dst_h_dentry)) { + au_fset_ren(a->auren_flags, DT_DSTDIR); + a->h_path.dentry = a->dst_h_dentry; + au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path); + } +} + +static void au_ren_rev_dt(int err, struct au_ren_args *a) +{ + struct dentry *h_d; + struct inode *h_inode; + + au_dtime_revert(a->src_dt + AuPARENT); + if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) + au_dtime_revert(a->dst_dt + AuPARENT); + + if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) { + h_d = a->src_dt[AuCHILD].dt_h_path.dentry; + h_inode = d_inode(h_d); + inode_lock_nested(h_inode, AuLsc_I_CHILD); + au_dtime_revert(a->src_dt + AuCHILD); + inode_unlock(h_inode); + + if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) { + h_d = a->dst_dt[AuCHILD].dt_h_path.dentry; + h_inode = d_inode(h_d); + inode_lock_nested(h_inode, AuLsc_I_CHILD); + au_dtime_revert(a->dst_dt + AuCHILD); + inode_unlock(h_inode); + } + } +} + +/* ---------------------------------------------------------------------- */ + +int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, + struct inode *_dst_dir, struct dentry *_dst_dentry, + unsigned int _flags) +{ + int err, lock_flags; + void *rev; + /* reduce stack space */ + struct au_ren_args *a; + struct au_pin pin; + + AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags); + IMustLock(_src_dir); + IMustLock(_dst_dir); + + err = -EINVAL; + if (unlikely(_flags & RENAME_WHITEOUT)) + goto out; + + err = -ENOMEM; + BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE); + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + a->flags = _flags; + BUILD_BUG_ON(sizeof(a->exchange) == sizeof(u8) + && RENAME_EXCHANGE > U8_MAX); + a->exchange = _flags & RENAME_EXCHANGE; + a->src_dir = _src_dir; + a->src_dentry = _src_dentry; + a->src_inode = NULL; + if (d_really_is_positive(a->src_dentry)) + a->src_inode = d_inode(a->src_dentry); + a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */ + a->dst_dir = _dst_dir; + a->dst_dentry = _dst_dentry; + a->dst_inode = NULL; + if (d_really_is_positive(a->dst_dentry)) + a->dst_inode = d_inode(a->dst_dentry); + a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */ + if (a->dst_inode) { + /* + * if EXCHANGE && src is non-dir && dst is dir, + * dst is not locked. + */ + /* IMustLock(a->dst_inode); */ + au_igrab(a->dst_inode); + } + + err = -ENOTDIR; + lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN; + if (d_is_dir(a->src_dentry)) { + au_fset_ren(a->auren_flags, ISDIR_SRC); + if (unlikely(!a->exchange + && d_really_is_positive(a->dst_dentry) + && !d_is_dir(a->dst_dentry))) + goto out_free; + lock_flags |= AuLock_DIRS; + } + if (a->dst_inode && d_is_dir(a->dst_dentry)) { + au_fset_ren(a->auren_flags, ISDIR_DST); + if (unlikely(!a->exchange + && d_really_is_positive(a->src_dentry) + && !d_is_dir(a->src_dentry))) + goto out_free; + lock_flags |= AuLock_DIRS; + } + err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, + lock_flags); + if (unlikely(err)) + goto out_free; + + err = au_d_hashed_positive(a->src_dentry); + if (unlikely(err)) + goto out_unlock; + err = -ENOENT; + if (a->dst_inode) { + /* + * If it is a dir, VFS unhash it before this + * function. It means we cannot rely upon d_unhashed(). + */ + if (unlikely(!a->dst_inode->i_nlink)) + goto out_unlock; + if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) { + err = au_d_hashed_positive(a->dst_dentry); + if (unlikely(err && !a->exchange)) + goto out_unlock; + } else if (unlikely(IS_DEADDIR(a->dst_inode))) + goto out_unlock; + } else if (unlikely(d_unhashed(a->dst_dentry))) + goto out_unlock; + + /* + * is it possible? + * yes, it happened (in linux-3.3-rcN) but I don't know why. + * there may exist a problem somewhere else. + */ + err = -EINVAL; + if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry))) + goto out_unlock; + + au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */ + di_write_lock_parent(a->dst_parent); + + /* which branch we process */ + err = au_ren_wbr(a); + if (unlikely(err < 0)) + goto out_parent; + a->br = au_sbr(a->dst_dentry->d_sb, a->btgt); + a->h_path.mnt = au_br_mnt(a->br); + + /* are they available to be renamed */ + err = au_ren_may_dir(a); + if (unlikely(err)) + goto out_children; + + /* prepare the writable parent dir on the same branch */ + if (a->dst_btop == a->btgt) { + au_fset_ren(a->auren_flags, WHDST); + } else { + err = au_cpup_dirs(a->dst_dentry, a->btgt); + if (unlikely(err)) + goto out_children; + } + + err = 0; + if (!a->exchange) { + if (a->src_dir != a->dst_dir) { + /* + * this temporary unlock is safe, + * because both dir->i_mutex are locked. + */ + di_write_unlock(a->dst_parent); + di_write_lock_parent(a->src_parent); + err = au_wr_dir_need_wh(a->src_dentry, + au_ftest_ren(a->auren_flags, + ISDIR_SRC), + &a->btgt); + di_write_unlock(a->src_parent); + di_write_lock2_parent(a->src_parent, a->dst_parent, + /*isdir*/1); + au_fclr_ren(a->auren_flags, ISSAMEDIR); + } else + err = au_wr_dir_need_wh(a->src_dentry, + au_ftest_ren(a->auren_flags, + ISDIR_SRC), + &a->btgt); + } + if (unlikely(err < 0)) + goto out_children; + if (err) + au_fset_ren(a->auren_flags, WHSRC); + + /* cpup src */ + if (a->src_btop != a->btgt) { + err = au_pin(&pin, a->src_dentry, a->btgt, + au_opt_udba(a->src_dentry->d_sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (!err) { + struct au_cp_generic cpg = { + .dentry = a->src_dentry, + .bdst = a->btgt, + .bsrc = a->src_btop, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop); + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + } + if (unlikely(err)) + goto out_children; + a->src_btop = a->btgt; + a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt); + if (!a->exchange) + au_fset_ren(a->auren_flags, WHSRC); + } + + /* cpup dst */ + if (a->exchange && a->dst_inode + && a->dst_btop != a->btgt) { + err = au_pin(&pin, a->dst_dentry, a->btgt, + au_opt_udba(a->dst_dentry->d_sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (!err) { + struct au_cp_generic cpg = { + .dentry = a->dst_dentry, + .bdst = a->btgt, + .bsrc = a->dst_btop, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + } + if (unlikely(err)) + goto out_children; + a->dst_btop = a->btgt; + a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt); + } + + /* lock them all */ + err = au_ren_lock(a); + if (unlikely(err)) + /* leave the copied-up one */ + goto out_children; + + if (!a->exchange) { + if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE)) + err = au_may_ren(a); + else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN)) + err = -ENAMETOOLONG; + if (unlikely(err)) + goto out_hdir; + } + + /* store timestamps to be revertible */ + au_ren_dt(a); + + /* store dirren info */ + if (au_ftest_ren(a->auren_flags, DIRREN)) { + err = au_dr_rename(a->src_dentry, a->btgt, + &a->dst_dentry->d_name, &rev); + AuTraceErr(err); + if (unlikely(err)) + goto out_dt; + } + + /* here we go */ + err = do_rename(a); + if (unlikely(err)) + goto out_dirren; + + if (au_ftest_ren(a->auren_flags, DIRREN)) + au_dr_rename_fin(a->src_dentry, a->btgt, rev); + + /* update dir attributes */ + au_ren_refresh_dir(a); + + /* dput/iput all lower dentries */ + au_ren_refresh(a); + + goto out_hdir; /* success */ + +out_dirren: + if (au_ftest_ren(a->auren_flags, DIRREN)) + au_dr_rename_rev(a->src_dentry, a->btgt, rev); +out_dt: + au_ren_rev_dt(err, a); +out_hdir: + au_ren_unlock(a); +out_children: + au_nhash_wh_free(&a->whlist); + if (err && a->dst_inode && a->dst_btop != a->btgt) { + AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt); + au_set_h_dptr(a->dst_dentry, a->btgt, NULL); + au_set_dbtop(a->dst_dentry, a->dst_btop); + } +out_parent: + if (!err) { + if (d_unhashed(a->src_dentry)) + au_fset_ren(a->auren_flags, DROPPED_SRC); + if (d_unhashed(a->dst_dentry)) + au_fset_ren(a->auren_flags, DROPPED_DST); + if (!a->exchange) + d_move(a->src_dentry, a->dst_dentry); + else { + d_exchange(a->src_dentry, a->dst_dentry); + if (au_ftest_ren(a->auren_flags, DROPPED_DST)) + d_drop(a->dst_dentry); + } + if (au_ftest_ren(a->auren_flags, DROPPED_SRC)) + d_drop(a->src_dentry); + } else { + au_update_dbtop(a->dst_dentry); + if (!a->dst_inode) + d_drop(a->dst_dentry); + } + if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) + di_write_unlock(a->dst_parent); + else + di_write_unlock2(a->src_parent, a->dst_parent); +out_unlock: + aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry); +out_free: + iput(a->dst_inode); + if (a->thargs) + au_whtmp_rmdir_free(a->thargs); + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} diff --git a/fs/aufs/iinfo.c b/fs/aufs/iinfo.c new file mode 100644 index 000000000000..016db39451cd --- /dev/null +++ b/fs/aufs/iinfo.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode private data + */ + +#include "aufs.h" + +struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) +{ + struct inode *h_inode; + struct au_hinode *hinode; + + IiMustAnyLock(inode); + + hinode = au_hinode(au_ii(inode), bindex); + h_inode = hinode->hi_inode; + AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); + return h_inode; +} + +/* todo: hard/soft set? */ +void au_hiput(struct au_hinode *hinode) +{ + au_hn_free(hinode); + dput(hinode->hi_whdentry); + iput(hinode->hi_inode); +} + +unsigned int au_hi_flags(struct inode *inode, int isdir) +{ + unsigned int flags; + const unsigned int mnt_flags = au_mntflags(inode->i_sb); + + flags = 0; + if (au_opt_test(mnt_flags, XINO)) + au_fset_hi(flags, XINO); + if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY)) + au_fset_hi(flags, HNOTIFY); + return flags; +} + +void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode, unsigned int flags) +{ + struct au_hinode *hinode; + struct inode *hi; + struct au_iinfo *iinfo = au_ii(inode); + + IiMustWriteLock(inode); + + hinode = au_hinode(iinfo, bindex); + hi = hinode->hi_inode; + AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); + + if (hi) + au_hiput(hinode); + hinode->hi_inode = h_inode; + if (h_inode) { + int err; + struct super_block *sb = inode->i_sb; + struct au_branch *br; + + AuDebugOn(inode->i_mode + && (h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT)); + if (bindex == iinfo->ii_btop) + au_cpup_igen(inode, h_inode); + br = au_sbr(sb, bindex); + hinode->hi_id = br->br_id; + if (au_ftest_hi(flags, XINO)) { + err = au_xino_write(sb, bindex, h_inode->i_ino, + inode->i_ino); + if (unlikely(err)) + AuIOErr1("failed au_xino_write() %d\n", err); + } + + if (au_ftest_hi(flags, HNOTIFY) + && au_br_hnotifyable(br->br_perm)) { + err = au_hn_alloc(hinode, inode); + if (unlikely(err)) + AuIOErr1("au_hn_alloc() %d\n", err); + } + } +} + +void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_wh) +{ + struct au_hinode *hinode; + + IiMustWriteLock(inode); + + hinode = au_hinode(au_ii(inode), bindex); + AuDebugOn(hinode->hi_whdentry); + hinode->hi_whdentry = h_wh; +} + +void au_update_iigen(struct inode *inode, int half) +{ + struct au_iinfo *iinfo; + struct au_iigen *iigen; + unsigned int sigen; + + sigen = au_sigen(inode->i_sb); + iinfo = au_ii(inode); + iigen = &iinfo->ii_generation; + spin_lock(&iigen->ig_spin); + iigen->ig_generation = sigen; + if (half) + au_ig_fset(iigen->ig_flags, HALF_REFRESHED); + else + au_ig_fclr(iigen->ig_flags, HALF_REFRESHED); + spin_unlock(&iigen->ig_spin); +} + +/* it may be called at remount time, too */ +void au_update_ibrange(struct inode *inode, int do_put_zero) +{ + struct au_iinfo *iinfo; + aufs_bindex_t bindex, bbot; + + AuDebugOn(au_is_bad_inode(inode)); + IiMustWriteLock(inode); + + iinfo = au_ii(inode); + if (do_put_zero && iinfo->ii_btop >= 0) { + for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; + bindex++) { + struct inode *h_i; + + h_i = au_hinode(iinfo, bindex)->hi_inode; + if (h_i + && !h_i->i_nlink + && !(h_i->i_state & I_LINKABLE)) + au_set_h_iptr(inode, bindex, NULL, 0); + } + } + + iinfo->ii_btop = -1; + iinfo->ii_bbot = -1; + bbot = au_sbbot(inode->i_sb); + for (bindex = 0; bindex <= bbot; bindex++) + if (au_hinode(iinfo, bindex)->hi_inode) { + iinfo->ii_btop = bindex; + break; + } + if (iinfo->ii_btop >= 0) + for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--) + if (au_hinode(iinfo, bindex)->hi_inode) { + iinfo->ii_bbot = bindex; + break; + } + AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot); +} + +/* ---------------------------------------------------------------------- */ + +void au_icntnr_init_once(void *_c) +{ + struct au_icntnr *c = _c; + struct au_iinfo *iinfo = &c->iinfo; + + spin_lock_init(&iinfo->ii_generation.ig_spin); + au_rw_init(&iinfo->ii_rwsem); + inode_init_once(&c->vfs_inode); +} + +void au_hinode_init(struct au_hinode *hinode) +{ + hinode->hi_inode = NULL; + hinode->hi_id = -1; + au_hn_init(hinode); + hinode->hi_whdentry = NULL; +} + +int au_iinfo_init(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct super_block *sb; + struct au_hinode *hi; + int nbr, i; + + sb = inode->i_sb; + iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); + nbr = au_sbbot(sb) + 1; + if (unlikely(nbr <= 0)) + nbr = 1; + hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS); + if (hi) { + au_lcnt_inc(&au_sbi(sb)->si_ninodes); + + iinfo->ii_hinode = hi; + for (i = 0; i < nbr; i++, hi++) + au_hinode_init(hi); + + iinfo->ii_generation.ig_generation = au_sigen(sb); + iinfo->ii_btop = -1; + iinfo->ii_bbot = -1; + iinfo->ii_vdir = NULL; + return 0; + } + return -ENOMEM; +} + +int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink) +{ + int err, i; + struct au_hinode *hip; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + err = -ENOMEM; + hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS, + may_shrink); + if (hip) { + iinfo->ii_hinode = hip; + i = iinfo->ii_bbot + 1; + hip += i; + for (; i < nbr; i++, hip++) + au_hinode_init(hip); + err = 0; + } + + return err; +} + +void au_iinfo_fin(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct au_hinode *hi; + struct super_block *sb; + aufs_bindex_t bindex, bbot; + const unsigned char unlinked = !inode->i_nlink; + + AuDebugOn(au_is_bad_inode(inode)); + + sb = inode->i_sb; + au_lcnt_dec(&au_sbi(sb)->si_ninodes); + if (si_pid_test(sb)) + au_xino_delete_inode(inode, unlinked); + else { + /* + * it is safe to hide the dependency between sbinfo and + * sb->s_umount. + */ + lockdep_off(); + si_noflush_read_lock(sb); + au_xino_delete_inode(inode, unlinked); + si_read_unlock(sb); + lockdep_on(); + } + + iinfo = au_ii(inode); + if (iinfo->ii_vdir) + au_vdir_free(iinfo->ii_vdir); + + bindex = iinfo->ii_btop; + if (bindex >= 0) { + hi = au_hinode(iinfo, bindex); + bbot = iinfo->ii_bbot; + while (bindex++ <= bbot) { + if (hi->hi_inode) + au_hiput(hi); + hi++; + } + } + au_kfree_rcu(iinfo->ii_hinode); + AuRwDestroy(&iinfo->ii_rwsem); +} diff --git a/fs/aufs/inode.c b/fs/aufs/inode.c new file mode 100644 index 000000000000..4de1b7507c5b --- /dev/null +++ b/fs/aufs/inode.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode functions + */ + +#include <linux/iversion.h> +#include "aufs.h" + +struct inode *au_igrab(struct inode *inode) +{ + if (inode) { + AuDebugOn(!atomic_read(&inode->i_count)); + ihold(inode); + } + return inode; +} + +static void au_refresh_hinode_attr(struct inode *inode, int do_version) +{ + au_cpup_attr_all(inode, /*force*/0); + au_update_iigen(inode, /*half*/1); + if (do_version) + inode_inc_iversion(inode); +} + +static int au_ii_refresh(struct inode *inode, int *update) +{ + int err, e, nbr; + umode_t type; + aufs_bindex_t bindex, new_bindex; + struct super_block *sb; + struct au_iinfo *iinfo; + struct au_hinode *p, *q, tmp; + + AuDebugOn(au_is_bad_inode(inode)); + IiMustWriteLock(inode); + + *update = 0; + sb = inode->i_sb; + nbr = au_sbbot(sb) + 1; + type = inode->i_mode & S_IFMT; + iinfo = au_ii(inode); + err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0); + if (unlikely(err)) + goto out; + + AuDebugOn(iinfo->ii_btop < 0); + p = au_hinode(iinfo, iinfo->ii_btop); + for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; + bindex++, p++) { + if (!p->hi_inode) + continue; + + AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT)); + new_bindex = au_br_index(sb, p->hi_id); + if (new_bindex == bindex) + continue; + + if (new_bindex < 0) { + *update = 1; + au_hiput(p); + p->hi_inode = NULL; + continue; + } + + if (new_bindex < iinfo->ii_btop) + iinfo->ii_btop = new_bindex; + if (iinfo->ii_bbot < new_bindex) + iinfo->ii_bbot = new_bindex; + /* swap two lower inode, and loop again */ + q = au_hinode(iinfo, new_bindex); + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hi_inode) { + bindex--; + p--; + } + } + au_update_ibrange(inode, /*do_put_zero*/0); + au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */ + e = au_dy_irefresh(inode); + if (unlikely(e && !err)) + err = e; + +out: + AuTraceErr(err); + return err; +} + +void au_refresh_iop(struct inode *inode, int force_getattr) +{ + int type; + struct au_sbinfo *sbi = au_sbi(inode->i_sb); + const struct inode_operations *iop + = force_getattr ? aufs_iop : sbi->si_iop_array; + + if (inode->i_op == iop) + return; + + switch (inode->i_mode & S_IFMT) { + case S_IFDIR: + type = AuIop_DIR; + break; + case S_IFLNK: + type = AuIop_SYMLINK; + break; + default: + type = AuIop_OTHER; + break; + } + + inode->i_op = iop + type; + /* unnecessary smp_wmb() */ +} + +int au_refresh_hinode_self(struct inode *inode) +{ + int err, update; + + err = au_ii_refresh(inode, &update); + if (!err) + au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); + + AuTraceErr(err); + return err; +} + +int au_refresh_hinode(struct inode *inode, struct dentry *dentry) +{ + int err, e, update; + unsigned int flags; + umode_t mode; + aufs_bindex_t bindex, bbot; + unsigned char isdir; + struct au_hinode *p; + struct au_iinfo *iinfo; + + err = au_ii_refresh(inode, &update); + if (unlikely(err)) + goto out; + + update = 0; + iinfo = au_ii(inode); + p = au_hinode(iinfo, iinfo->ii_btop); + mode = (inode->i_mode & S_IFMT); + isdir = S_ISDIR(mode); + flags = au_hi_flags(inode, isdir); + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { + struct inode *h_i, *h_inode; + struct dentry *h_d; + + h_d = au_h_dptr(dentry, bindex); + if (!h_d || d_is_negative(h_d)) + continue; + + h_inode = d_inode(h_d); + AuDebugOn(mode != (h_inode->i_mode & S_IFMT)); + if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) { + h_i = au_h_iptr(inode, bindex); + if (h_i) { + if (h_i == h_inode) + continue; + err = -EIO; + break; + } + } + if (bindex < iinfo->ii_btop) + iinfo->ii_btop = bindex; + if (iinfo->ii_bbot < bindex) + iinfo->ii_bbot = bindex; + au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags); + update = 1; + } + au_update_ibrange(inode, /*do_put_zero*/0); + e = au_dy_irefresh(inode); + if (unlikely(e && !err)) + err = e; + if (!err) + au_refresh_hinode_attr(inode, update && isdir); + +out: + AuTraceErr(err); + return err; +} + +static int set_inode(struct inode *inode, struct dentry *dentry) +{ + int err; + unsigned int flags; + umode_t mode; + aufs_bindex_t bindex, btop, btail; + unsigned char isdir; + struct dentry *h_dentry; + struct inode *h_inode; + struct au_iinfo *iinfo; + const struct inode_operations *iop; + + IiMustWriteLock(inode); + + err = 0; + isdir = 0; + iop = au_sbi(inode->i_sb)->si_iop_array; + btop = au_dbtop(dentry); + h_dentry = au_h_dptr(dentry, btop); + h_inode = d_inode(h_dentry); + mode = h_inode->i_mode; + switch (mode & S_IFMT) { + case S_IFREG: + btail = au_dbtail(dentry); + inode->i_op = iop + AuIop_OTHER; + inode->i_fop = &aufs_file_fop; + err = au_dy_iaop(inode, btop, h_inode); + if (unlikely(err)) + goto out; + break; + case S_IFDIR: + isdir = 1; + btail = au_dbtaildir(dentry); + inode->i_op = iop + AuIop_DIR; + inode->i_fop = &aufs_dir_fop; + break; + case S_IFLNK: + btail = au_dbtail(dentry); + inode->i_op = iop + AuIop_SYMLINK; + break; + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + case S_IFSOCK: + btail = au_dbtail(dentry); + inode->i_op = iop + AuIop_OTHER; + init_special_inode(inode, mode, h_inode->i_rdev); + break; + default: + AuIOErr("Unknown file type 0%o\n", mode); + err = -EIO; + goto out; + } + + /* do not set hnotify for whiteouted dirs (SHWH mode) */ + flags = au_hi_flags(inode, isdir); + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH) + && au_ftest_hi(flags, HNOTIFY) + && dentry->d_name.len > AUFS_WH_PFX_LEN + && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) + au_fclr_hi(flags, HNOTIFY); + iinfo = au_ii(inode); + iinfo->ii_btop = btop; + iinfo->ii_bbot = btail; + for (bindex = btop; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) + au_set_h_iptr(inode, bindex, + au_igrab(d_inode(h_dentry)), flags); + } + au_cpup_attr_all(inode, /*force*/1); + /* + * to force calling aufs_get_acl() every time, + * do not call cache_no_acl() for aufs inode. + */ + +out: + return err; +} + +/* + * successful returns with iinfo write_locked + * minus: errno + * zero: success, matched + * plus: no error, but unmatched + */ +static int reval_inode(struct inode *inode, struct dentry *dentry) +{ + int err; + unsigned int gen, igflags; + aufs_bindex_t bindex, bbot; + struct inode *h_inode, *h_dinode; + struct dentry *h_dentry; + + /* + * before this function, if aufs got any iinfo lock, it must be only + * one, the parent dir. + * it can happen by UDBA and the obsoleted inode number. + */ + err = -EIO; + if (unlikely(inode->i_ino == parent_ino(dentry))) + goto out; + + err = 1; + ii_write_lock_new_child(inode); + h_dentry = au_h_dptr(dentry, au_dbtop(dentry)); + h_dinode = d_inode(h_dentry); + bbot = au_ibbot(inode); + for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (!h_inode || h_inode != h_dinode) + continue; + + err = 0; + gen = au_iigen(inode, &igflags); + if (gen == au_digen(dentry) + && !au_ig_ftest(igflags, HALF_REFRESHED)) + break; + + /* fully refresh inode using dentry */ + err = au_refresh_hinode(inode, dentry); + if (!err) + au_update_iigen(inode, /*half*/0); + break; + } + + if (unlikely(err)) + ii_write_unlock(inode); +out: + return err; +} + +int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + unsigned int d_type, ino_t *ino) +{ + int err, idx; + const int isnondir = d_type != DT_DIR; + + /* prevent hardlinked inode number from race condition */ + if (isnondir) { + err = au_xinondir_enter(sb, bindex, h_ino, &idx); + if (unlikely(err)) + goto out; + } + + err = au_xino_read(sb, bindex, h_ino, ino); + if (unlikely(err)) + goto out_xinondir; + + if (!*ino) { + err = -EIO; + *ino = au_xino_new_ino(sb); + if (unlikely(!*ino)) + goto out_xinondir; + err = au_xino_write(sb, bindex, h_ino, *ino); + if (unlikely(err)) + goto out_xinondir; + } + +out_xinondir: + if (isnondir && idx >= 0) + au_xinondir_leave(sb, bindex, h_ino, idx); +out: + return err; +} + +/* successful returns with iinfo write_locked */ +/* todo: return with unlocked? */ +struct inode *au_new_inode(struct dentry *dentry, int must_new) +{ + struct inode *inode, *h_inode; + struct dentry *h_dentry; + struct super_block *sb; + ino_t h_ino, ino; + int err, idx, hlinked; + aufs_bindex_t btop; + + sb = dentry->d_sb; + btop = au_dbtop(dentry); + h_dentry = au_h_dptr(dentry, btop); + h_inode = d_inode(h_dentry); + h_ino = h_inode->i_ino; + hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1; + +new_ino: + /* + * stop 'race'-ing between hardlinks under different + * parents. + */ + if (hlinked) { + err = au_xinondir_enter(sb, btop, h_ino, &idx); + inode = ERR_PTR(err); + if (unlikely(err)) + goto out; + } + + err = au_xino_read(sb, btop, h_ino, &ino); + inode = ERR_PTR(err); + if (unlikely(err)) + goto out_xinondir; + + if (!ino) { + ino = au_xino_new_ino(sb); + if (unlikely(!ino)) { + inode = ERR_PTR(-EIO); + goto out_xinondir; + } + } + + AuDbg("i%lu\n", (unsigned long)ino); + inode = au_iget_locked(sb, ino); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out_xinondir; + + AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW)); + if (inode->i_state & I_NEW) { + ii_write_lock_new_child(inode); + err = set_inode(inode, dentry); + if (!err) { + unlock_new_inode(inode); + goto out_xinondir; /* success */ + } + + /* + * iget_failed() calls iput(), but we need to call + * ii_write_unlock() after iget_failed(). so dirty hack for + * i_count. + */ + atomic_inc(&inode->i_count); + iget_failed(inode); + ii_write_unlock(inode); + au_xino_write(sb, btop, h_ino, /*ino*/0); + /* ignore this error */ + goto out_iput; + } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) { + /* + * horrible race condition between lookup, readdir and copyup + * (or something). + */ + if (hlinked && idx >= 0) + au_xinondir_leave(sb, btop, h_ino, idx); + err = reval_inode(inode, dentry); + if (unlikely(err < 0)) { + hlinked = 0; + goto out_iput; + } + if (!err) + goto out; /* success */ + else if (hlinked && idx >= 0) { + err = au_xinondir_enter(sb, btop, h_ino, &idx); + if (unlikely(err)) { + iput(inode); + inode = ERR_PTR(err); + goto out; + } + } + } + + if (unlikely(au_test_fs_unique_ino(h_inode))) + AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir," + " b%d, %s, %pd, hi%lu, i%lu.\n", + btop, au_sbtype(h_dentry->d_sb), dentry, + (unsigned long)h_ino, (unsigned long)ino); + ino = 0; + err = au_xino_write(sb, btop, h_ino, /*ino*/0); + if (!err) { + iput(inode); + if (hlinked && idx >= 0) + au_xinondir_leave(sb, btop, h_ino, idx); + goto new_ino; + } + +out_iput: + iput(inode); + inode = ERR_PTR(err); +out_xinondir: + if (hlinked && idx >= 0) + au_xinondir_leave(sb, btop, h_ino, idx); +out: + return inode; +} + +/* ---------------------------------------------------------------------- */ + +int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, + struct inode *inode) +{ + int err; + struct inode *hi; + + err = au_br_rdonly(au_sbr(sb, bindex)); + + /* pseudo-link after flushed may happen out of bounds */ + if (!err + && inode + && au_ibtop(inode) <= bindex + && bindex <= au_ibbot(inode)) { + /* + * permission check is unnecessary since vfsub routine + * will be called later + */ + hi = au_h_iptr(inode, bindex); + if (hi) + err = IS_IMMUTABLE(hi) ? -EROFS : 0; + } + + return err; +} + +int au_test_h_perm(struct inode *h_inode, int mask) +{ + if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) + return 0; + return inode_permission(h_inode, mask); +} + +int au_test_h_perm_sio(struct inode *h_inode, int mask) +{ + if (au_test_nfs(h_inode->i_sb) + && (mask & MAY_WRITE) + && S_ISDIR(h_inode->i_mode)) + mask |= MAY_READ; /* force permission check */ + return au_test_h_perm(h_inode, mask); +} diff --git a/fs/aufs/inode.h b/fs/aufs/inode.h new file mode 100644 index 000000000000..af32a233200e --- /dev/null +++ b/fs/aufs/inode.h @@ -0,0 +1,698 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations + */ + +#ifndef __AUFS_INODE_H__ +#define __AUFS_INODE_H__ + +#ifdef __KERNEL__ + +#include <linux/fsnotify.h> +#include "rwsem.h" + +struct vfsmount; + +struct au_hnotify { +#ifdef CONFIG_AUFS_HNOTIFY +#ifdef CONFIG_AUFS_HFSNOTIFY + /* never use fsnotify_add_vfsmount_mark() */ + struct fsnotify_mark hn_mark; +#endif + struct inode *hn_aufs_inode; /* no get/put */ + struct rcu_head rcu; +#endif +} ____cacheline_aligned_in_smp; + +struct au_hinode { + struct inode *hi_inode; + aufs_bindex_t hi_id; +#ifdef CONFIG_AUFS_HNOTIFY + struct au_hnotify *hi_notify; +#endif + + /* reference to the copied-up whiteout with get/put */ + struct dentry *hi_whdentry; +}; + +/* ig_flags */ +#define AuIG_HALF_REFRESHED 1 +#define au_ig_ftest(flags, name) ((flags) & AuIG_##name) +#define au_ig_fset(flags, name) \ + do { (flags) |= AuIG_##name; } while (0) +#define au_ig_fclr(flags, name) \ + do { (flags) &= ~AuIG_##name; } while (0) + +struct au_iigen { + spinlock_t ig_spin; + __u32 ig_generation, ig_flags; +}; + +struct au_vdir; +struct au_iinfo { + struct au_iigen ii_generation; + struct super_block *ii_hsb1; /* no get/put */ + + struct au_rwsem ii_rwsem; + aufs_bindex_t ii_btop, ii_bbot; + __u32 ii_higen; + struct au_hinode *ii_hinode; + struct au_vdir *ii_vdir; +}; + +struct au_icntnr { + struct au_iinfo iinfo; + struct inode vfs_inode; + struct hlist_bl_node plink; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* au_pin flags */ +#define AuPin_DI_LOCKED 1 +#define AuPin_MNT_WRITE (1 << 1) +#define au_ftest_pin(flags, name) ((flags) & AuPin_##name) +#define au_fset_pin(flags, name) \ + do { (flags) |= AuPin_##name; } while (0) +#define au_fclr_pin(flags, name) \ + do { (flags) &= ~AuPin_##name; } while (0) + +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; + + /* temporary unlock/relock for copyup */ + struct dentry *h_dentry, *h_parent; + struct au_branch *br; + struct task_struct *task; +}; + +void au_pin_hdir_unlock(struct au_pin *p); +int au_pin_hdir_lock(struct au_pin *p); +int au_pin_hdir_relock(struct au_pin *p); +void au_pin_hdir_acquire_nest(struct au_pin *p); +void au_pin_hdir_release(struct au_pin *p); + +/* ---------------------------------------------------------------------- */ + +static inline struct au_iinfo *au_ii(struct inode *inode) +{ + BUG_ON(is_bad_inode(inode)); + return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); +} + +/* ---------------------------------------------------------------------- */ + +/* inode.c */ +struct inode *au_igrab(struct inode *inode); +void au_refresh_iop(struct inode *inode, int force_getattr); +int au_refresh_hinode_self(struct inode *inode); +int au_refresh_hinode(struct inode *inode, struct dentry *dentry); +int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + unsigned int d_type, ino_t *ino); +struct inode *au_new_inode(struct dentry *dentry, int must_new); +int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, + struct inode *inode); +int au_test_h_perm(struct inode *h_inode, int mask); +int au_test_h_perm_sio(struct inode *h_inode, int mask); + +static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex, + ino_t h_ino, unsigned int d_type, ino_t *ino) +{ +#ifdef CONFIG_AUFS_SHWH + return au_ino(sb, bindex, h_ino, d_type, ino); +#else + return 0; +#endif +} + +/* i_op.c */ +enum { + AuIop_SYMLINK, + AuIop_DIR, + AuIop_OTHER, + AuIop_Last +}; +extern struct inode_operations aufs_iop[AuIop_Last], /* not const */ + aufs_iop_nogetattr[AuIop_Last]; + +/* au_wr_dir flags */ +#define AuWrDir_ADD_ENTRY 1 +#define AuWrDir_ISDIR (1 << 1) +#define AuWrDir_TMPFILE (1 << 2) +#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name) +#define au_fset_wrdir(flags, name) \ + do { (flags) |= AuWrDir_##name; } while (0) +#define au_fclr_wrdir(flags, name) \ + do { (flags) &= ~AuWrDir_##name; } while (0) + +struct au_wr_dir_args { + aufs_bindex_t force_btgt; + unsigned char flags; +}; +int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, + struct au_wr_dir_args *args); + +struct dentry *au_pinned_h_parent(struct au_pin *pin); +void au_pin_init(struct au_pin *pin, struct dentry *dentry, + aufs_bindex_t bindex, int lsc_di, int lsc_hi, + unsigned int udba, unsigned char flags); +int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, + unsigned int udba, unsigned char flags) __must_check; +int au_do_pin(struct au_pin *pin) __must_check; +void au_unpin(struct au_pin *pin); +int au_reval_for_attr(struct dentry *dentry, unsigned int sigen); + +#define AuIcpup_DID_CPUP 1 +#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name) +#define au_fset_icpup(flags, name) \ + do { (flags) |= AuIcpup_##name; } while (0) +#define au_fclr_icpup(flags, name) \ + do { (flags) &= ~AuIcpup_##name; } while (0) + +struct au_icpup_args { + unsigned char flags; + unsigned char pin_flags; + aufs_bindex_t btgt; + unsigned int udba; + struct au_pin pin; + struct path h_path; + struct inode *h_inode; +}; + +int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, + struct au_icpup_args *a); + +int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force, + struct path *h_path, int locked); + +/* i_op_add.c */ +int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir); +int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t dev); +int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); +int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool want_excl); +struct vfsub_aopen_args; +int au_aopen_or_create(struct inode *dir, struct dentry *dentry, + struct vfsub_aopen_args *args); +int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode); +int aufs_link(struct dentry *src_dentry, struct inode *dir, + struct dentry *dentry); +int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); + +/* 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, + unsigned int flags); + +/* iinfo.c */ +struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex); +void au_hiput(struct au_hinode *hinode); +void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_wh); +unsigned int au_hi_flags(struct inode *inode, int isdir); + +/* hinode flags */ +#define AuHi_XINO 1 +#define AuHi_HNOTIFY (1 << 1) +#define au_ftest_hi(flags, name) ((flags) & AuHi_##name) +#define au_fset_hi(flags, name) \ + do { (flags) |= AuHi_##name; } while (0) +#define au_fclr_hi(flags, name) \ + do { (flags) &= ~AuHi_##name; } while (0) + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuHi_HNOTIFY +#define AuHi_HNOTIFY 0 +#endif + +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, int half); +void au_update_ibrange(struct inode *inode, int do_put_zero); + +void au_icntnr_init_once(void *_c); +void au_hinode_init(struct au_hinode *hinode); +int au_iinfo_init(struct inode *inode); +void au_iinfo_fin(struct inode *inode); +int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink); + +#ifdef CONFIG_PROC_FS +/* plink.c */ +int au_plink_maint(struct super_block *sb, int flags); +struct au_sbinfo; +void au_plink_maint_leave(struct au_sbinfo *sbinfo); +int au_plink_maint_enter(struct super_block *sb); +#ifdef CONFIG_AUFS_DEBUG +void au_plink_list(struct super_block *sb); +#else +AuStubVoid(au_plink_list, struct super_block *sb) +#endif +int au_plink_test(struct inode *inode); +struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex); +void au_plink_append(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_dentry); +void au_plink_put(struct super_block *sb, int verbose); +void au_plink_clean(struct super_block *sb, int verbose); +void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id); +#else +AuStubInt0(au_plink_maint, struct super_block *sb, int flags); +AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo); +AuStubInt0(au_plink_maint_enter, struct super_block *sb); +AuStubVoid(au_plink_list, struct super_block *sb); +AuStubInt0(au_plink_test, struct inode *inode); +AuStub(struct dentry *, au_plink_lkup, return NULL, + struct inode *inode, aufs_bindex_t bindex); +AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_dentry); +AuStubVoid(au_plink_put, struct super_block *sb, int verbose); +AuStubVoid(au_plink_clean, struct super_block *sb, int verbose); +AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id); +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_AUFS_XATTR +/* xattr.c */ +int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags, + unsigned int verbose); +ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size); +void au_xattr_init(struct super_block *sb); +#else +AuStubInt0(au_cpup_xattr, struct dentry *h_dst, struct dentry *h_src, + int ignore_flags, unsigned int verbose); +AuStubVoid(au_xattr_init, struct super_block *sb); +#endif + +#ifdef CONFIG_FS_POSIX_ACL +struct posix_acl *aufs_get_acl(struct inode *inode, int type); +int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +#endif + +#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) +enum { + AU_XATTR_SET, + AU_ACL_SET +}; + +struct au_sxattr { + int type; + union { + struct { + const char *name; + const void *value; + size_t size; + int flags; + } set; + struct { + struct posix_acl *acl; + int type; + } acl_set; + } u; +}; +ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, + struct au_sxattr *arg); +#endif + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for iinfo */ +enum { + AuLsc_II_CHILD, /* child first */ + AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */ + AuLsc_II_CHILD3, /* copyup dirs */ + AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */ + AuLsc_II_PARENT2, + AuLsc_II_PARENT3, /* copyup dirs */ + AuLsc_II_NEW_CHILD +}; + +/* + * ii_read_lock_child, ii_write_lock_child, + * ii_read_lock_child2, ii_write_lock_child2, + * ii_read_lock_child3, ii_write_lock_child3, + * ii_read_lock_parent, ii_write_lock_parent, + * ii_read_lock_parent2, ii_write_lock_parent2, + * ii_read_lock_parent3, ii_write_lock_parent3, + * ii_read_lock_new_child, ii_write_lock_new_child, + */ +#define AuReadLockFunc(name, lsc) \ +static inline void ii_read_lock_##name(struct inode *i) \ +{ \ + au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ +} + +#define AuWriteLockFunc(name, lsc) \ +static inline void ii_write_lock_##name(struct inode *i) \ +{ \ + au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ +} + +#define AuRWLockFuncs(name, lsc) \ + AuReadLockFunc(name, lsc) \ + AuWriteLockFunc(name, lsc) + +AuRWLockFuncs(child, CHILD); +AuRWLockFuncs(child2, CHILD2); +AuRWLockFuncs(child3, CHILD3); +AuRWLockFuncs(parent, PARENT); +AuRWLockFuncs(parent2, PARENT2); +AuRWLockFuncs(parent3, PARENT3); +AuRWLockFuncs(new_child, NEW_CHILD); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define ii_read_unlock(i) au_rw_read_unlock(&au_ii(i)->ii_rwsem) +#define ii_write_unlock(i) au_rw_write_unlock(&au_ii(i)->ii_rwsem) +#define ii_downgrade_lock(i) au_rw_dgrade_lock(&au_ii(i)->ii_rwsem) + +#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem) +#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem) +#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem) + +/* ---------------------------------------------------------------------- */ + +static inline void au_icntnr_init(struct au_icntnr *c) +{ +#ifdef CONFIG_AUFS_DEBUG + c->vfs_inode.i_mode = 0; +#endif +} + +static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags) +{ + unsigned int gen; + struct au_iinfo *iinfo; + struct au_iigen *iigen; + + iinfo = au_ii(inode); + iigen = &iinfo->ii_generation; + spin_lock(&iigen->ig_spin); + if (igflags) + *igflags = iigen->ig_flags; + gen = iigen->ig_generation; + spin_unlock(&iigen->ig_spin); + + return gen; +} + +/* tiny test for inode number */ +/* tmpfs generation is too rough */ +static inline int au_test_higen(struct inode *inode, struct inode *h_inode) +{ + struct au_iinfo *iinfo; + + iinfo = au_ii(inode); + AuRwMustAnyLock(&iinfo->ii_rwsem); + return !(iinfo->ii_hsb1 == h_inode->i_sb + && iinfo->ii_higen == h_inode->i_generation); +} + +static inline void au_iigen_dec(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct au_iigen *iigen; + + iinfo = au_ii(inode); + iigen = &iinfo->ii_generation; + spin_lock(&iigen->ig_spin); + iigen->ig_generation--; + spin_unlock(&iigen->ig_spin); +} + +static inline int au_iigen_test(struct inode *inode, unsigned int sigen) +{ + int err; + + err = 0; + if (unlikely(inode && au_iigen(inode, NULL) != sigen)) + err = -EIO; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo, + aufs_bindex_t bindex) +{ + return iinfo->ii_hinode + bindex; +} + +static inline int au_is_bad_inode(struct inode *inode) +{ + return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0)); +} + +static inline aufs_bindex_t au_ii_br_id(struct inode *inode, + aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_hinode(au_ii(inode), bindex)->hi_id; +} + +static inline aufs_bindex_t au_ibtop(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_btop; +} + +static inline aufs_bindex_t au_ibbot(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_bbot; +} + +static inline struct au_vdir *au_ivdir(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_vdir; +} + +static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_hinode(au_ii(inode), bindex)->hi_whdentry; +} + +static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_btop = bindex; +} + +static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_bbot = bindex; +} + +static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_vdir = vdir; +} + +static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_hinode(au_ii(inode), bindex); +} + +/* ---------------------------------------------------------------------- */ + +static 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) { + if (lflag) + au_fset_pin(pin->flags, DI_LOCKED); + else + au_fclr_pin(pin->flags, DI_LOCKED); + } +} + +#if 0 /* reserved */ +static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent) +{ + if (pin) { + dput(pin->parent); + pin->parent = dget(parent); + } +} +#endif + +/* ---------------------------------------------------------------------- */ + +struct au_branch; +#ifdef CONFIG_AUFS_HNOTIFY +struct au_hnotify_op { + void (*ctl)(struct au_hinode *hinode, int do_set); + int (*alloc)(struct au_hinode *hinode); + + /* + * if it returns true, the the caller should free hinode->hi_notify, + * otherwise ->free() frees it. + */ + int (*free)(struct au_hinode *hinode, + struct au_hnotify *hn) __must_check; + + void (*fin)(void); + int (*init)(void); + + int (*reset_br)(unsigned int udba, struct au_branch *br, int perm); + void (*fin_br)(struct au_branch *br); + int (*init_br)(struct au_branch *br, int perm); +}; + +/* hnotify.c */ +int au_hn_alloc(struct au_hinode *hinode, struct inode *inode); +void au_hn_free(struct au_hinode *hinode); +void au_hn_ctl(struct au_hinode *hinode, int do_set); +void au_hn_reset(struct inode *inode, unsigned int flags); +int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, + const struct qstr *h_child_qstr, struct inode *h_child_inode); +int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm); +int au_hnotify_init_br(struct au_branch *br, int perm); +void au_hnotify_fin_br(struct au_branch *br); +int __init au_hnotify_init(void); +void au_hnotify_fin(void); + +/* hfsnotify.c */ +extern const struct au_hnotify_op au_hnotify_op; + +static inline +void au_hn_init(struct au_hinode *hinode) +{ + hinode->hi_notify = NULL; +} + +static inline struct au_hnotify *au_hn(struct au_hinode *hinode) +{ + return hinode->hi_notify; +} + +#else +AuStub(int, au_hn_alloc, return -EOPNOTSUPP, + struct au_hinode *hinode __maybe_unused, + struct inode *inode __maybe_unused) +AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode) +AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused) +AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused, + int do_set __maybe_unused) +AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused, + unsigned int flags __maybe_unused) +AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused, + struct au_branch *br __maybe_unused, + int perm __maybe_unused) +AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused, + int perm __maybe_unused) +AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused) +AuStubInt0(__init au_hnotify_init, void) +AuStubVoid(au_hnotify_fin, void) +AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused) +#endif /* CONFIG_AUFS_HNOTIFY */ + +static inline void au_hn_suspend(struct au_hinode *hdir) +{ + au_hn_ctl(hdir, /*do_set*/0); +} + +static inline void au_hn_resume(struct au_hinode *hdir) +{ + au_hn_ctl(hdir, /*do_set*/1); +} + +static inline void au_hn_inode_lock(struct au_hinode *hdir) +{ + inode_lock(hdir->hi_inode); + au_hn_suspend(hdir); +} + +static inline void au_hn_inode_lock_nested(struct au_hinode *hdir, + unsigned int sc __maybe_unused) +{ + inode_lock_nested(hdir->hi_inode, sc); + au_hn_suspend(hdir); +} + +#if 0 /* unused */ +#include "vfsub.h" +static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir, + unsigned int sc) +{ + inode_lock_shared_nested(hdir->hi_inode, sc); + au_hn_suspend(hdir); +} +#endif + +static inline void au_hn_inode_unlock(struct au_hinode *hdir) +{ + au_hn_resume(hdir); + inode_unlock(hdir->hi_inode); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_INODE_H__ */ diff --git a/fs/aufs/ioctl.c b/fs/aufs/ioctl.c new file mode 100644 index 000000000000..ae4f73386b90 --- /dev/null +++ b/fs/aufs/ioctl.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * ioctl + * plink-management and readdir in userspace. + * assist the pathconf(3) wrapper library. + * move-down + * File-based Hierarchical Storage Management. + */ + +#include <linux/compat.h> +#include <linux/file.h> +#include "aufs.h" + +static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg) +{ + int err, fd; + aufs_bindex_t wbi, bindex, bbot; + struct file *h_file; + struct super_block *sb; + struct dentry *root; + struct au_branch *br; + struct aufs_wbr_fd wbrfd = { + .oflags = au_dir_roflags, + .brid = -1 + }; + const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY + | O_NOATIME | O_CLOEXEC; + + AuDebugOn(wbrfd.oflags & ~valid); + + if (arg) { + err = copy_from_user(&wbrfd, arg, sizeof(wbrfd)); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + + err = -EINVAL; + AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid); + wbrfd.oflags |= au_dir_roflags; + AuDbg("0%o\n", wbrfd.oflags); + if (unlikely(wbrfd.oflags & ~valid)) + goto out; + } + + fd = get_unused_fd_flags(0); + err = fd; + if (unlikely(fd < 0)) + goto out; + + h_file = ERR_PTR(-EINVAL); + wbi = 0; + br = NULL; + sb = path->dentry->d_sb; + root = sb->s_root; + aufs_read_lock(root, AuLock_IR); + bbot = au_sbbot(sb); + if (wbrfd.brid >= 0) { + wbi = au_br_index(sb, wbrfd.brid); + if (unlikely(wbi < 0 || wbi > bbot)) + goto out_unlock; + } + + h_file = ERR_PTR(-ENOENT); + br = au_sbr(sb, wbi); + if (!au_br_writable(br->br_perm)) { + if (arg) + goto out_unlock; + + bindex = wbi + 1; + wbi = -1; + for (; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm)) { + wbi = bindex; + br = au_sbr(sb, wbi); + break; + } + } + } + AuDbg("wbi %d\n", wbi); + if (wbi >= 0) + h_file = au_h_open(root, wbi, wbrfd.oflags, NULL, + /*force_wr*/0); + +out_unlock: + aufs_read_unlock(root, AuLock_IR); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out_fd; + + au_lcnt_dec(&br->br_nfiles); /* cf. au_h_open() */ + fd_install(fd, h_file); + err = fd; + goto out; /* success */ + +out_fd: + put_unused_fd(fd); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err; + struct dentry *dentry; + + switch (cmd) { + case AUFS_CTL_RDU: + case AUFS_CTL_RDU_INO: + err = au_rdu_ioctl(file, cmd, arg); + break; + + case AUFS_CTL_WBR_FD: + err = au_wbr_fd(&file->f_path, (void __user *)arg); + break; + + case AUFS_CTL_IBUSY: + err = au_ibusy_ioctl(file, arg); + break; + + case AUFS_CTL_BRINFO: + err = au_brinfo_ioctl(file, arg); + break; + + case AUFS_CTL_FHSM_FD: + dentry = file->f_path.dentry; + if (IS_ROOT(dentry)) + err = au_fhsm_fd(dentry->d_sb, arg); + else + err = -ENOTTY; + break; + + default: + /* do not call the lower */ + AuDbg("0x%x\n", cmd); + err = -ENOTTY; + } + + AuTraceErr(err); + return err; +} + +long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err; + + switch (cmd) { + case AUFS_CTL_MVDOWN: + err = au_mvdown(file->f_path.dentry, (void __user *)arg); + break; + + case AUFS_CTL_WBR_FD: + err = au_wbr_fd(&file->f_path, (void __user *)arg); + break; + + default: + /* do not call the lower */ + AuDbg("0x%x\n", cmd); + err = -ENOTTY; + } + + AuTraceErr(err); + return err; +} + +#ifdef CONFIG_COMPAT +long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err; + + switch (cmd) { + case AUFS_CTL_RDU: + case AUFS_CTL_RDU_INO: + err = au_rdu_compat_ioctl(file, cmd, arg); + break; + + case AUFS_CTL_IBUSY: + err = au_ibusy_compat_ioctl(file, arg); + break; + + case AUFS_CTL_BRINFO: + err = au_brinfo_compat_ioctl(file, arg); + break; + + default: + err = aufs_ioctl_dir(file, cmd, arg); + } + + AuTraceErr(err); + return err; +} + +long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg)); +} +#endif diff --git a/fs/aufs/lcnt.h b/fs/aufs/lcnt.h new file mode 100644 index 000000000000..8afcabe55826 --- /dev/null +++ b/fs/aufs/lcnt.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * simple long counter wrapper + */ + +#ifndef __AUFS_LCNT_H__ +#define __AUFS_LCNT_H__ + +#ifdef __KERNEL__ + +#include "debug.h" + +#define AuLCntATOMIC 1 +#define AuLCntPCPUCNT 2 +/* + * why does percpu_refcount require extra synchronize_rcu()s in + * au_br_do_free() + */ +#define AuLCntPCPUREF 3 + +/* #define AuLCntChosen AuLCntATOMIC */ +#define AuLCntChosen AuLCntPCPUCNT +/* #define AuLCntChosen AuLCntPCPUREF */ + +#if AuLCntChosen == AuLCntATOMIC +#include <linux/atomic.h> + +typedef atomic_long_t au_lcnt_t; + +static inline int au_lcnt_init(au_lcnt_t *cnt, void *release __maybe_unused) +{ + atomic_long_set(cnt, 0); + return 0; +} + +static inline void au_lcnt_wait_for_fin(au_lcnt_t *cnt __maybe_unused) +{ + /* empty */ +} + +static inline void au_lcnt_fin(au_lcnt_t *cnt __maybe_unused, + int do_sync __maybe_unused) +{ + /* empty */ +} + +static inline void au_lcnt_inc(au_lcnt_t *cnt) +{ + atomic_long_inc(cnt); +} + +static inline void au_lcnt_dec(au_lcnt_t *cnt) +{ + atomic_long_dec(cnt); +} + +static inline long au_lcnt_read(au_lcnt_t *cnt, int do_rev __maybe_unused) +{ + return atomic_long_read(cnt); +} +#endif + +#if AuLCntChosen == AuLCntPCPUCNT +#include <linux/percpu_counter.h> + +typedef struct percpu_counter au_lcnt_t; + +static inline int au_lcnt_init(au_lcnt_t *cnt, void *release __maybe_unused) +{ + return percpu_counter_init(cnt, 0, GFP_NOFS); +} + +static inline void au_lcnt_wait_for_fin(au_lcnt_t *cnt __maybe_unused) +{ + /* empty */ +} + +static inline void au_lcnt_fin(au_lcnt_t *cnt, int do_sync __maybe_unused) +{ + percpu_counter_destroy(cnt); +} + +static inline void au_lcnt_inc(au_lcnt_t *cnt) +{ + percpu_counter_inc(cnt); +} + +static inline void au_lcnt_dec(au_lcnt_t *cnt) +{ + percpu_counter_dec(cnt); +} + +static inline long au_lcnt_read(au_lcnt_t *cnt, int do_rev __maybe_unused) +{ + s64 n; + + n = percpu_counter_sum(cnt); + BUG_ON(n < 0); + if (LONG_MAX != LLONG_MAX + && n > LONG_MAX) + AuWarn1("%s\n", "wrap-around"); + + return n; +} +#endif + +#if AuLCntChosen == AuLCntPCPUREF +#include <linux/percpu-refcount.h> + +typedef struct percpu_ref au_lcnt_t; + +static inline int au_lcnt_init(au_lcnt_t *cnt, percpu_ref_func_t *release) +{ + if (!release) + release = percpu_ref_exit; + return percpu_ref_init(cnt, release, /*percpu mode*/0, GFP_NOFS); +} + +static inline void au_lcnt_wait_for_fin(au_lcnt_t *cnt __maybe_unused) +{ + synchronize_rcu(); +} + +static inline void au_lcnt_fin(au_lcnt_t *cnt, int do_sync) +{ + percpu_ref_kill(cnt); + if (do_sync) + au_lcnt_wait_for_fin(cnt); +} + +static inline void au_lcnt_inc(au_lcnt_t *cnt) +{ + percpu_ref_get(cnt); +} + +static inline void au_lcnt_dec(au_lcnt_t *cnt) +{ + percpu_ref_put(cnt); +} + +/* + * avoid calling this func as possible. + */ +static inline long au_lcnt_read(au_lcnt_t *cnt, int do_rev) +{ + long l; + + percpu_ref_switch_to_atomic_sync(cnt); + l = atomic_long_read(&cnt->count); + if (do_rev) + percpu_ref_switch_to_percpu(cnt); + + /* percpu_ref is initialized by 1 instead of 0 */ + return l - 1; +} +#endif + +#ifdef CONFIG_AUFS_DEBUG +#define AuLCntZero(val) do { \ + long l = val; \ + if (l) \ + AuDbg("%s = %ld\n", #val, l); \ +} while (0) +#else +#define AuLCntZero(val) do {} while (0) +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_LCNT_H__ */ diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c new file mode 100644 index 000000000000..63732e938684 --- /dev/null +++ b/fs/aufs/loop.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * support for loopback block device as a branch + */ + +#include "aufs.h" + +/* added into drivers/block/loop.c */ +static struct file *(*backing_file_func)(struct super_block *sb); + +/* + * test if two lower dentries have overlapping branches. + */ +int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding) +{ + struct super_block *h_sb; + struct file *backing_file; + + if (unlikely(!backing_file_func)) { + /* don't load "loop" module here */ + backing_file_func = symbol_get(loop_backing_file); + if (unlikely(!backing_file_func)) + /* "loop" module is not loaded */ + return 0; + } + + h_sb = h_adding->d_sb; + backing_file = backing_file_func(h_sb); + if (!backing_file) + return 0; + + h_adding = backing_file->f_path.dentry; + /* + * h_adding can be local NFS. + * in this case aufs cannot detect the loop. + */ + if (unlikely(h_adding->d_sb == sb)) + return 1; + return !!au_test_subdir(h_adding, sb->s_root); +} + +/* true if a kernel thread named 'loop[0-9].*' accesses a file */ +int au_test_loopback_kthread(void) +{ + int ret; + struct task_struct *tsk = current; + char c, comm[sizeof(tsk->comm)]; + + ret = 0; + if (tsk->flags & PF_KTHREAD) { + get_task_comm(comm, tsk); + c = comm[4]; + ret = ('0' <= c && c <= '9' + && !strncmp(comm, "loop", 4)); + } + + return ret; +} + +/* ---------------------------------------------------------------------- */ + +#define au_warn_loopback_step 16 +static int au_warn_loopback_nelem = au_warn_loopback_step; +static unsigned long *au_warn_loopback_array; + +void au_warn_loopback(struct super_block *h_sb) +{ + int i, new_nelem; + unsigned long *a, magic; + static DEFINE_SPINLOCK(spin); + + magic = h_sb->s_magic; + spin_lock(&spin); + a = au_warn_loopback_array; + for (i = 0; i < au_warn_loopback_nelem && *a; i++) + if (a[i] == magic) { + spin_unlock(&spin); + return; + } + + /* h_sb is new to us, print it */ + if (i < au_warn_loopback_nelem) { + a[i] = magic; + goto pr; + } + + /* expand the array */ + new_nelem = au_warn_loopback_nelem + au_warn_loopback_step; + a = au_kzrealloc(au_warn_loopback_array, + au_warn_loopback_nelem * sizeof(unsigned long), + new_nelem * sizeof(unsigned long), GFP_ATOMIC, + /*may_shrink*/0); + if (a) { + au_warn_loopback_nelem = new_nelem; + au_warn_loopback_array = a; + a[i] = magic; + goto pr; + } + + spin_unlock(&spin); + AuWarn1("realloc failed, ignored\n"); + return; + +pr: + spin_unlock(&spin); + pr_warn("you may want to try another patch for loopback file " + "on %s(0x%lx) branch\n", au_sbtype(h_sb), magic); +} + +int au_loopback_init(void) +{ + int err; + struct super_block *sb __maybe_unused; + + BUILD_BUG_ON(sizeof(sb->s_magic) != sizeof(*au_warn_loopback_array)); + + err = 0; + au_warn_loopback_array = kcalloc(au_warn_loopback_step, + sizeof(unsigned long), GFP_NOFS); + if (unlikely(!au_warn_loopback_array)) + err = -ENOMEM; + + return err; +} + +void au_loopback_fin(void) +{ + if (backing_file_func) + symbol_put(loop_backing_file); + au_kfree_try_rcu(au_warn_loopback_array); +} diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h new file mode 100644 index 000000000000..65c38bbb5d56 --- /dev/null +++ b/fs/aufs/loop.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * support for loopback mount as a branch + */ + +#ifndef __AUFS_LOOP_H__ +#define __AUFS_LOOP_H__ + +#ifdef __KERNEL__ + +struct dentry; +struct super_block; + +#ifdef CONFIG_AUFS_BDEV_LOOP +/* drivers/block/loop.c */ +struct file *loop_backing_file(struct super_block *sb); + +/* loop.c */ +int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding); +int au_test_loopback_kthread(void); +void au_warn_loopback(struct super_block *h_sb); + +int au_loopback_init(void); +void au_loopback_fin(void); +#else +AuStub(struct file *, loop_backing_file, return NULL, struct super_block *sb) + +AuStubInt0(au_test_loopback_overlap, struct super_block *sb, + struct dentry *h_adding) +AuStubInt0(au_test_loopback_kthread, void) +AuStubVoid(au_warn_loopback, struct super_block *h_sb) + +AuStubInt0(au_loopback_init, void) +AuStubVoid(au_loopback_fin, void) +#endif /* BLK_DEV_LOOP */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_LOOP_H__ */ diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk new file mode 100644 index 000000000000..7bc9eef3ffec --- /dev/null +++ b/fs/aufs/magic.mk @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: GPL-2.0 + +# defined in ${srctree}/fs/fuse/inode.c +# tristate +ifdef CONFIG_FUSE_FS +ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546 +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/ubifs/ubifs.h +# tristate +ifdef CONFIG_UBIFS_FS +ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905 +endif + +# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h +# tristate +ifdef CONFIG_HFSPLUS_FS +ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b +endif diff --git a/fs/aufs/module.c b/fs/aufs/module.c new file mode 100644 index 000000000000..7245197a6cbf --- /dev/null +++ b/fs/aufs/module.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * module global variables and operations + */ + +#include <linux/module.h> +#include <linux/seq_file.h> +#include "aufs.h" + +/* shrinkable realloc */ +void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink) +{ + size_t sz; + int diff; + + sz = 0; + diff = -1; + if (p) { +#if 0 /* unused */ + if (!new_sz) { + au_kfree_rcu(p); + p = NULL; + goto out; + } +#else + AuDebugOn(!new_sz); +#endif + sz = ksize(p); + diff = au_kmidx_sub(sz, new_sz); + } + if (sz && !diff) + goto out; + + if (sz < new_sz) + /* expand or SLOB */ + p = krealloc(p, new_sz, gfp); + else if (new_sz < sz && may_shrink) { + /* shrink */ + void *q; + + q = kmalloc(new_sz, gfp); + if (q) { + if (p) { + memcpy(q, p, new_sz); + au_kfree_try_rcu(p); + } + p = q; + } else + p = NULL; + } + +out: + return p; +} + +void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp, + int may_shrink) +{ + p = au_krealloc(p, new_sz, gfp, may_shrink); + if (p && new_sz > nused) + memset(p + nused, 0, new_sz - nused); + return p; +} + +/* ---------------------------------------------------------------------- */ +/* + * aufs caches + */ +struct kmem_cache *au_cache[AuCache_Last]; + +static void au_cache_fin(void) +{ + int i; + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + + /* excluding AuCache_HNOTIFY */ + BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last); + for (i = 0; i < AuCache_HNOTIFY; i++) { + kmem_cache_destroy(au_cache[i]); + au_cache[i] = NULL; + } +} + +static int __init au_cache_init(void) +{ + au_cache[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once); + if (au_cache[AuCache_DINFO]) + /* SLAB_DESTROY_BY_RCU */ + au_cache[AuCache_ICNTNR] = AuCacheCtor(au_icntnr, + au_icntnr_init_once); + if (au_cache[AuCache_ICNTNR]) + au_cache[AuCache_FINFO] = AuCacheCtor(au_finfo, + au_fi_init_once); + if (au_cache[AuCache_FINFO]) + au_cache[AuCache_VDIR] = AuCache(au_vdir); + if (au_cache[AuCache_VDIR]) + au_cache[AuCache_DEHSTR] = AuCache(au_vdir_dehstr); + if (au_cache[AuCache_DEHSTR]) + return 0; + + au_cache_fin(); + return -ENOMEM; +} + +/* ---------------------------------------------------------------------- */ + +int au_dir_roflags; + +#ifdef CONFIG_AUFS_SBILIST +/* + * iterate_supers_type() doesn't protect us from + * remounting (branch management) + */ +struct hlist_bl_head au_sbilist; +#endif + +/* + * functions for module interface. + */ +MODULE_LICENSE("GPL"); +/* MODULE_LICENSE("GPL v2"); */ +MODULE_AUTHOR("Junjiro R. Okajima <aufs-users@lists.sourceforge.net>"); +MODULE_DESCRIPTION(AUFS_NAME + " -- Advanced multi layered unification filesystem"); +MODULE_VERSION(AUFS_VERSION); +MODULE_ALIAS_FS(AUFS_NAME); + +/* 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, 0444); + +/* this module parameter has no meaning when USER_NS is disabled */ +bool au_userns; +MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns"); +module_param_named(allow_userns, au_userns, bool, 0444); + +/* ---------------------------------------------------------------------- */ + +static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */ + +int au_seq_path(struct seq_file *seq, struct path *path) +{ + int err; + + err = seq_path(seq, path, au_esc_chars); + if (err >= 0) + err = 0; + else + err = -ENOMEM; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +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); + + memcpy(aufs_iop_nogetattr, aufs_iop, sizeof(aufs_iop)); + for (i = 0; i < AuIop_Last; i++) + aufs_iop_nogetattr[i].getattr = NULL; + + memset(au_cache, 0, sizeof(au_cache)); /* including hnotify */ + + au_sbilist_init(); + sysaufs_brs_init(); + au_debug_init(); + au_dy_init(); + err = sysaufs_init(); + if (unlikely(err)) + goto out; + err = dbgaufs_init(); + if (unlikely(err)) + goto out_sysaufs; + err = au_procfs_init(); + if (unlikely(err)) + goto out_dbgaufs; + err = au_wkq_init(); + if (unlikely(err)) + goto out_procfs; + err = au_loopback_init(); + if (unlikely(err)) + goto out_wkq; + err = au_hnotify_init(); + if (unlikely(err)) + goto out_loopback; + err = au_sysrq_init(); + if (unlikely(err)) + goto out_hin; + err = au_cache_init(); + if (unlikely(err)) + goto out_sysrq; + + aufs_fs_type.fs_flags |= au_userns ? FS_USERNS_MOUNT : 0; + err = register_filesystem(&aufs_fs_type); + if (unlikely(err)) + goto out_cache; + + /* since we define pr_fmt, call printk directly */ + printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n"); + goto out; /* success */ + +out_cache: + au_cache_fin(); +out_sysrq: + au_sysrq_fin(); +out_hin: + au_hnotify_fin(); +out_loopback: + au_loopback_fin(); +out_wkq: + au_wkq_fin(); +out_procfs: + au_procfs_fin(); +out_dbgaufs: + dbgaufs_fin(); +out_sysaufs: + sysaufs_fin(); + au_dy_fin(); +out: + return err; +} + +static void __exit aufs_exit(void) +{ + unregister_filesystem(&aufs_fs_type); + au_cache_fin(); + au_sysrq_fin(); + au_hnotify_fin(); + au_loopback_fin(); + au_wkq_fin(); + au_procfs_fin(); + dbgaufs_fin(); + sysaufs_fin(); + au_dy_fin(); +} + +module_init(aufs_init); +module_exit(aufs_exit); diff --git a/fs/aufs/module.h b/fs/aufs/module.h new file mode 100644 index 000000000000..d6a76788d2ff --- /dev/null +++ b/fs/aufs/module.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * module initialization and module-global + */ + +#ifndef __AUFS_MODULE_H__ +#define __AUFS_MODULE_H__ + +#ifdef __KERNEL__ + +#include <linux/slab.h> +#include "debug.h" +#include "dentry.h" +#include "dir.h" +#include "file.h" +#include "inode.h" + +struct path; +struct seq_file; + +/* module parameters */ +extern int sysaufs_brs; +extern bool au_userns; + +/* ---------------------------------------------------------------------- */ + +extern int au_dir_roflags; + +void *au_krealloc(void *p, unsigned int new_sz, gfp_t gfp, int may_shrink); +void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp, + int may_shrink); + +/* + * Comparing the size of the object with sizeof(struct rcu_head) + * case 1: object is always larger + * --> au_kfree_rcu() or au_kfree_do_rcu() + * case 2: object is always smaller + * --> au_kfree_small() + * case 3: object can be any size + * --> au_kfree_try_rcu() + */ + +static inline void au_kfree_do_rcu(const void *p) +{ + struct { + struct rcu_head rcu; + } *a = (void *)p; + + kfree_rcu(a, rcu); +} + +#define au_kfree_rcu(_p) do { \ + typeof(_p) p = (_p); \ + BUILD_BUG_ON(sizeof(*p) < sizeof(struct rcu_head)); \ + if (p) \ + au_kfree_do_rcu(p); \ + } while (0) + +#define au_kfree_do_sz_test(sz) (sz >= sizeof(struct rcu_head)) +#define au_kfree_sz_test(p) (p && au_kfree_do_sz_test(ksize(p))) + +static inline void au_kfree_try_rcu(const void *p) +{ + if (!p) + return; + if (au_kfree_sz_test(p)) + au_kfree_do_rcu(p); + else + kfree(p); +} + +static inline void au_kfree_small(const void *p) +{ + if (!p) + return; + AuDebugOn(au_kfree_sz_test(p)); + kfree(p); +} + +static inline int au_kmidx_sub(size_t sz, size_t new_sz) +{ +#ifndef CONFIG_SLOB + return kmalloc_index(sz) - kmalloc_index(new_sz); +#else + return -1; /* SLOB is untested */ +#endif +} + +int au_seq_path(struct seq_file *seq, struct path *path); + +#ifdef CONFIG_PROC_FS +/* procfs.c */ +int __init au_procfs_init(void); +void au_procfs_fin(void); +#else +AuStubInt0(au_procfs_init, void); +AuStubVoid(au_procfs_fin, void); +#endif + +/* ---------------------------------------------------------------------- */ + +/* kmem cache */ +enum { + AuCache_DINFO, + AuCache_ICNTNR, + AuCache_FINFO, + AuCache_VDIR, + AuCache_DEHSTR, + AuCache_HNOTIFY, /* must be last */ + AuCache_Last +}; + +extern struct kmem_cache *au_cache[AuCache_Last]; + +#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD) +#define AuCache(type) KMEM_CACHE(type, AuCacheFlags) +#define AuCacheCtor(type, ctor) \ + kmem_cache_create(#type, sizeof(struct type), \ + __alignof__(struct type), AuCacheFlags, ctor) + +#define AuCacheFuncs(name, index) \ + static inline struct au_##name *au_cache_alloc_##name(void) \ + { return kmem_cache_alloc(au_cache[AuCache_##index], GFP_NOFS); } \ + static inline void au_cache_free_##name##_norcu(struct au_##name *p) \ + { kmem_cache_free(au_cache[AuCache_##index], p); } \ + \ + static inline void au_cache_free_##name##_rcu_cb(struct rcu_head *rcu) \ + { void *p = rcu; \ + p -= offsetof(struct au_##name, rcu); \ + kmem_cache_free(au_cache[AuCache_##index], p); } \ + static inline void au_cache_free_##name##_rcu(struct au_##name *p) \ + { BUILD_BUG_ON(sizeof(struct au_##name) < sizeof(struct rcu_head)); \ + call_rcu(&p->rcu, au_cache_free_##name##_rcu_cb); } \ + \ + static inline void au_cache_free_##name(struct au_##name *p) \ + { /* au_cache_free_##name##_norcu(p); */ \ + au_cache_free_##name##_rcu(p); } + +AuCacheFuncs(dinfo, DINFO); +AuCacheFuncs(icntnr, ICNTNR); +AuCacheFuncs(finfo, FINFO); +AuCacheFuncs(vdir, VDIR); +AuCacheFuncs(vdir_dehstr, DEHSTR); +#ifdef CONFIG_AUFS_HNOTIFY +AuCacheFuncs(hnotify, HNOTIFY); +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_MODULE_H__ */ diff --git a/fs/aufs/mvdown.c b/fs/aufs/mvdown.c new file mode 100644 index 000000000000..c39a39e52ebc --- /dev/null +++ b/fs/aufs/mvdown.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2011-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * move-down, opposite of copy-up + */ + +#include "aufs.h" + +struct au_mvd_args { + struct { + struct super_block *h_sb; + struct dentry *h_parent; + struct au_hinode *hdir; + struct inode *h_dir, *h_inode; + struct au_pin pin; + } info[AUFS_MVDOWN_NARRAY]; + + struct aufs_mvdown mvdown; + struct dentry *dentry, *parent; + struct inode *inode, *dir; + struct super_block *sb; + aufs_bindex_t bopq, bwh, bfound; + unsigned char rename_lock; +}; + +#define mvd_errno mvdown.au_errno +#define mvd_bsrc mvdown.stbr[AUFS_MVDOWN_UPPER].bindex +#define mvd_src_brid mvdown.stbr[AUFS_MVDOWN_UPPER].brid +#define mvd_bdst mvdown.stbr[AUFS_MVDOWN_LOWER].bindex +#define mvd_dst_brid mvdown.stbr[AUFS_MVDOWN_LOWER].brid + +#define mvd_h_src_sb info[AUFS_MVDOWN_UPPER].h_sb +#define mvd_h_src_parent info[AUFS_MVDOWN_UPPER].h_parent +#define mvd_hdir_src info[AUFS_MVDOWN_UPPER].hdir +#define mvd_h_src_dir info[AUFS_MVDOWN_UPPER].h_dir +#define mvd_h_src_inode info[AUFS_MVDOWN_UPPER].h_inode +#define mvd_pin_src info[AUFS_MVDOWN_UPPER].pin + +#define mvd_h_dst_sb info[AUFS_MVDOWN_LOWER].h_sb +#define mvd_h_dst_parent info[AUFS_MVDOWN_LOWER].h_parent +#define mvd_hdir_dst info[AUFS_MVDOWN_LOWER].hdir +#define mvd_h_dst_dir info[AUFS_MVDOWN_LOWER].h_dir +#define mvd_h_dst_inode info[AUFS_MVDOWN_LOWER].h_inode +#define mvd_pin_dst info[AUFS_MVDOWN_LOWER].pin + +#define AU_MVD_PR(flag, ...) do { \ + if (flag) \ + pr_err(__VA_ARGS__); \ + } while (0) + +static int find_lower_writable(struct au_mvd_args *a) +{ + struct super_block *sb; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + sb = a->sb; + bindex = a->mvd_bsrc; + bbot = au_sbbot(sb); + if (a->mvdown.flags & AUFS_MVDOWN_FHSM_LOWER) + for (bindex++; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm) + && !sb_rdonly(au_br_sb(br))) + return bindex; + } + else if (!(a->mvdown.flags & AUFS_MVDOWN_ROLOWER)) + for (bindex++; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (!au_br_rdonly(br)) + return bindex; + } + else + for (bindex++; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (!sb_rdonly(au_br_sb(br))) { + if (au_br_rdonly(br)) + a->mvdown.flags + |= AUFS_MVDOWN_ROLOWER_R; + return bindex; + } + } + + return -1; +} + +/* make the parent dir on bdst */ +static int au_do_mkdir(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + + err = 0; + a->mvd_hdir_src = au_hi(a->dir, a->mvd_bsrc); + a->mvd_hdir_dst = au_hi(a->dir, a->mvd_bdst); + a->mvd_h_src_parent = au_h_dptr(a->parent, a->mvd_bsrc); + a->mvd_h_dst_parent = NULL; + if (au_dbbot(a->parent) >= a->mvd_bdst) + a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst); + if (!a->mvd_h_dst_parent) { + err = au_cpdown_dirs(a->dentry, a->mvd_bdst); + if (unlikely(err)) { + AU_MVD_PR(dmsg, "cpdown_dirs failed\n"); + goto out; + } + a->mvd_h_dst_parent = au_h_dptr(a->parent, a->mvd_bdst); + } + +out: + AuTraceErr(err); + return err; +} + +/* lock them all */ +static int au_do_lock(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct dentry *h_trap; + + a->mvd_h_src_sb = au_sbr_sb(a->sb, a->mvd_bsrc); + a->mvd_h_dst_sb = au_sbr_sb(a->sb, a->mvd_bdst); + err = au_pin(&a->mvd_pin_dst, a->dentry, a->mvd_bdst, + au_opt_udba(a->sb), + AuPin_MNT_WRITE | AuPin_DI_LOCKED); + AuTraceErr(err); + if (unlikely(err)) { + AU_MVD_PR(dmsg, "pin_dst failed\n"); + goto out; + } + + if (a->mvd_h_src_sb != a->mvd_h_dst_sb) { + a->rename_lock = 0; + au_pin_init(&a->mvd_pin_src, a->dentry, a->mvd_bsrc, + AuLsc_DI_PARENT, AuLsc_I_PARENT3, + au_opt_udba(a->sb), + AuPin_MNT_WRITE | AuPin_DI_LOCKED); + err = au_do_pin(&a->mvd_pin_src); + AuTraceErr(err); + a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent); + if (unlikely(err)) { + AU_MVD_PR(dmsg, "pin_src failed\n"); + goto out_dst; + } + goto out; /* success */ + } + + a->rename_lock = 1; + au_pin_hdir_unlock(&a->mvd_pin_dst); + err = au_pin(&a->mvd_pin_src, a->dentry, a->mvd_bsrc, + au_opt_udba(a->sb), + AuPin_MNT_WRITE | AuPin_DI_LOCKED); + AuTraceErr(err); + a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent); + if (unlikely(err)) { + AU_MVD_PR(dmsg, "pin_src failed\n"); + au_pin_hdir_lock(&a->mvd_pin_dst); + goto out_dst; + } + au_pin_hdir_unlock(&a->mvd_pin_src); + h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, + a->mvd_h_dst_parent, a->mvd_hdir_dst); + if (h_trap) { + err = (h_trap != a->mvd_h_src_parent); + if (err) + err = (h_trap != a->mvd_h_dst_parent); + } + BUG_ON(err); /* it should never happen */ + if (unlikely(a->mvd_h_src_dir != au_pinned_h_dir(&a->mvd_pin_src))) { + err = -EBUSY; + AuTraceErr(err); + vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, + a->mvd_h_dst_parent, a->mvd_hdir_dst); + au_pin_hdir_lock(&a->mvd_pin_src); + au_unpin(&a->mvd_pin_src); + au_pin_hdir_lock(&a->mvd_pin_dst); + goto out_dst; + } + goto out; /* success */ + +out_dst: + au_unpin(&a->mvd_pin_dst); +out: + AuTraceErr(err); + return err; +} + +static void au_do_unlock(const unsigned char dmsg, struct au_mvd_args *a) +{ + if (!a->rename_lock) + au_unpin(&a->mvd_pin_src); + else { + vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src, + a->mvd_h_dst_parent, a->mvd_hdir_dst); + au_pin_hdir_lock(&a->mvd_pin_src); + au_unpin(&a->mvd_pin_src); + au_pin_hdir_lock(&a->mvd_pin_dst); + } + au_unpin(&a->mvd_pin_dst); +} + +/* copy-down the file */ +static int au_do_cpdown(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct au_cp_generic cpg = { + .dentry = a->dentry, + .bdst = a->mvd_bdst, + .bsrc = a->mvd_bsrc, + .len = -1, + .pin = &a->mvd_pin_dst, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + + AuDbg("b%d, b%d\n", cpg.bsrc, cpg.bdst); + if (a->mvdown.flags & AUFS_MVDOWN_OWLOWER) + au_fset_cpup(cpg.flags, OVERWRITE); + if (a->mvdown.flags & AUFS_MVDOWN_ROLOWER) + au_fset_cpup(cpg.flags, RWDST); + err = au_sio_cpdown_simple(&cpg); + if (unlikely(err)) + AU_MVD_PR(dmsg, "cpdown failed\n"); + + AuTraceErr(err); + return err; +} + +/* + * unlink the whiteout on bdst if exist which may be created by UDBA while we + * were sleeping + */ +static int au_do_unlink_wh(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct path h_path; + struct au_branch *br; + struct inode *delegated; + + br = au_sbr(a->sb, a->mvd_bdst); + h_path.dentry = au_wh_lkup(a->mvd_h_dst_parent, &a->dentry->d_name, br); + err = PTR_ERR(h_path.dentry); + if (IS_ERR(h_path.dentry)) { + AU_MVD_PR(dmsg, "wh_lkup failed\n"); + goto out; + } + + err = 0; + if (d_is_positive(h_path.dentry)) { + h_path.mnt = au_br_mnt(br); + delegated = NULL; + err = vfsub_unlink(d_inode(a->mvd_h_dst_parent), &h_path, + &delegated, /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + if (unlikely(err)) + AU_MVD_PR(dmsg, "wh_unlink failed\n"); + } + dput(h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +/* + * unlink the topmost h_dentry + */ +static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct path h_path; + struct inode *delegated; + + h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc); + h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc); + delegated = NULL; + err = vfsub_unlink(a->mvd_h_src_dir, &h_path, &delegated, /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + if (unlikely(err)) + AU_MVD_PR(dmsg, "unlink failed\n"); + + AuTraceErr(err); + return err; +} + +/* Since mvdown succeeded, we ignore an error of this function */ +static void au_do_stfs(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct au_branch *br; + + a->mvdown.flags |= AUFS_MVDOWN_STFS_FAILED; + br = au_sbr(a->sb, a->mvd_bsrc); + err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_UPPER].stfs); + if (!err) { + br = au_sbr(a->sb, a->mvd_bdst); + a->mvdown.stbr[AUFS_MVDOWN_LOWER].brid = br->br_id; + err = au_br_stfs(br, &a->mvdown.stbr[AUFS_MVDOWN_LOWER].stfs); + } + if (!err) + a->mvdown.flags &= ~AUFS_MVDOWN_STFS_FAILED; + else + AU_MVD_PR(dmsg, "statfs failed (%d), ignored\n", err); +} + +/* + * copy-down the file and unlink the bsrc file. + * - unlink the bdst whout if exist + * - copy-down the file (with whtmp name and rename) + * - unlink the bsrc file + */ +static int au_do_mvdown(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + + err = au_do_mkdir(dmsg, a); + if (!err) + err = au_do_lock(dmsg, a); + if (unlikely(err)) + goto out; + + /* + * do not revert the activities we made on bdst since they should be + * harmless in aufs. + */ + + err = au_do_cpdown(dmsg, a); + if (!err) + err = au_do_unlink_wh(dmsg, a); + if (!err && !(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) + err = au_do_unlink(dmsg, a); + if (unlikely(err)) + goto out_unlock; + + AuDbg("%pd2, 0x%x, %d --> %d\n", + a->dentry, a->mvdown.flags, a->mvd_bsrc, a->mvd_bdst); + if (find_lower_writable(a) < 0) + a->mvdown.flags |= AUFS_MVDOWN_BOTTOM; + + if (a->mvdown.flags & AUFS_MVDOWN_STFS) + au_do_stfs(dmsg, a); + + /* maintain internal array */ + if (!(a->mvdown.flags & AUFS_MVDOWN_KUPPER)) { + au_set_h_dptr(a->dentry, a->mvd_bsrc, NULL); + au_set_dbtop(a->dentry, a->mvd_bdst); + au_set_h_iptr(a->inode, a->mvd_bsrc, NULL, /*flags*/0); + au_set_ibtop(a->inode, a->mvd_bdst); + } else { + /* hide the lower */ + au_set_h_dptr(a->dentry, a->mvd_bdst, NULL); + au_set_dbbot(a->dentry, a->mvd_bsrc); + au_set_h_iptr(a->inode, a->mvd_bdst, NULL, /*flags*/0); + au_set_ibbot(a->inode, a->mvd_bsrc); + } + if (au_dbbot(a->dentry) < a->mvd_bdst) + au_set_dbbot(a->dentry, a->mvd_bdst); + if (au_ibbot(a->inode) < a->mvd_bdst) + au_set_ibbot(a->inode, a->mvd_bdst); + +out_unlock: + au_do_unlock(dmsg, a); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* make sure the file is idle */ +static int au_mvd_args_busy(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err, plinked; + + err = 0; + plinked = !!au_opt_test(au_mntflags(a->sb), PLINK); + if (au_dbtop(a->dentry) == a->mvd_bsrc + && au_dcount(a->dentry) == 1 + && atomic_read(&a->inode->i_count) == 1 + /* && a->mvd_h_src_inode->i_nlink == 1 */ + && (!plinked || !au_plink_test(a->inode)) + && a->inode->i_nlink == 1) + goto out; + + err = -EBUSY; + AU_MVD_PR(dmsg, + "b%d, d{b%d, c%d?}, i{c%d?, l%u}, hi{l%u}, p{%d, %d}\n", + a->mvd_bsrc, au_dbtop(a->dentry), au_dcount(a->dentry), + atomic_read(&a->inode->i_count), a->inode->i_nlink, + a->mvd_h_src_inode->i_nlink, + plinked, plinked ? au_plink_test(a->inode) : 0); + +out: + AuTraceErr(err); + return err; +} + +/* make sure the parent dir is fine */ +static int au_mvd_args_parent(const unsigned char dmsg, + struct au_mvd_args *a) +{ + int err; + aufs_bindex_t bindex; + + err = 0; + if (unlikely(au_alive_dir(a->parent))) { + err = -ENOENT; + AU_MVD_PR(dmsg, "parent dir is dead\n"); + goto out; + } + + a->bopq = au_dbdiropq(a->parent); + bindex = au_wbr_nonopq(a->dentry, a->mvd_bdst); + AuDbg("b%d\n", bindex); + if (unlikely((bindex >= 0 && bindex < a->mvd_bdst) + || (a->bopq != -1 && a->bopq < a->mvd_bdst))) { + err = -EINVAL; + a->mvd_errno = EAU_MVDOWN_OPAQUE; + AU_MVD_PR(dmsg, "ancestor is opaque b%d, b%d\n", + a->bopq, a->mvd_bdst); + } + +out: + AuTraceErr(err); + return err; +} + +static int au_mvd_args_intermediate(const unsigned char dmsg, + struct au_mvd_args *a) +{ + int err; + struct au_dinfo *dinfo, *tmp; + + /* lookup the next lower positive entry */ + err = -ENOMEM; + tmp = au_di_alloc(a->sb, AuLsc_DI_TMP); + if (unlikely(!tmp)) + goto out; + + a->bfound = -1; + a->bwh = -1; + dinfo = au_di(a->dentry); + au_di_cp(tmp, dinfo); + au_di_swap(tmp, dinfo); + + /* returns the number of positive dentries */ + err = au_lkup_dentry(a->dentry, a->mvd_bsrc + 1, + /* AuLkup_IGNORE_PERM */ 0); + if (!err) + a->bwh = au_dbwh(a->dentry); + else if (err > 0) + a->bfound = au_dbtop(a->dentry); + + au_di_swap(tmp, dinfo); + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + if (unlikely(err < 0)) + AU_MVD_PR(dmsg, "failed look-up lower\n"); + + /* + * here, we have these cases. + * bfound == -1 + * no positive dentry under bsrc. there are more sub-cases. + * bwh < 0 + * there no whiteout, we can safely move-down. + * bwh <= bsrc + * impossible + * bsrc < bwh && bwh < bdst + * there is a whiteout on RO branch. cannot proceed. + * bwh == bdst + * there is a whiteout on the RW target branch. it should + * be removed. + * bdst < bwh + * there is a whiteout somewhere unrelated branch. + * -1 < bfound && bfound <= bsrc + * impossible. + * bfound < bdst + * found, but it is on RO branch between bsrc and bdst. cannot + * proceed. + * bfound == bdst + * found, replace it if AUFS_MVDOWN_FORCE is set. otherwise return + * error. + * bdst < bfound + * found, after we create the file on bdst, it will be hidden. + */ + + AuDebugOn(a->bfound == -1 + && a->bwh != -1 + && a->bwh <= a->mvd_bsrc); + AuDebugOn(-1 < a->bfound + && a->bfound <= a->mvd_bsrc); + + err = -EINVAL; + if (a->bfound == -1 + && a->mvd_bsrc < a->bwh + && a->bwh != -1 + && a->bwh < a->mvd_bdst) { + a->mvd_errno = EAU_MVDOWN_WHITEOUT; + AU_MVD_PR(dmsg, "bsrc %d, bdst %d, bfound %d, bwh %d\n", + a->mvd_bsrc, a->mvd_bdst, a->bfound, a->bwh); + goto out; + } else if (a->bfound != -1 && a->bfound < a->mvd_bdst) { + a->mvd_errno = EAU_MVDOWN_UPPER; + AU_MVD_PR(dmsg, "bdst %d, bfound %d\n", + a->mvd_bdst, a->bfound); + goto out; + } + + err = 0; /* success */ + +out: + AuTraceErr(err); + return err; +} + +static int au_mvd_args_exist(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + + err = 0; + if (!(a->mvdown.flags & AUFS_MVDOWN_OWLOWER) + && a->bfound == a->mvd_bdst) + err = -EEXIST; + AuTraceErr(err); + return err; +} + +static int au_mvd_args(const unsigned char dmsg, struct au_mvd_args *a) +{ + int err; + struct au_branch *br; + + err = -EISDIR; + if (unlikely(S_ISDIR(a->inode->i_mode))) + goto out; + + err = -EINVAL; + if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_UPPER)) + a->mvd_bsrc = au_ibtop(a->inode); + else { + a->mvd_bsrc = au_br_index(a->sb, a->mvd_src_brid); + if (unlikely(a->mvd_bsrc < 0 + || (a->mvd_bsrc < au_dbtop(a->dentry) + || au_dbbot(a->dentry) < a->mvd_bsrc + || !au_h_dptr(a->dentry, a->mvd_bsrc)) + || (a->mvd_bsrc < au_ibtop(a->inode) + || au_ibbot(a->inode) < a->mvd_bsrc + || !au_h_iptr(a->inode, a->mvd_bsrc)))) { + a->mvd_errno = EAU_MVDOWN_NOUPPER; + AU_MVD_PR(dmsg, "no upper\n"); + goto out; + } + } + if (unlikely(a->mvd_bsrc == au_sbbot(a->sb))) { + a->mvd_errno = EAU_MVDOWN_BOTTOM; + AU_MVD_PR(dmsg, "on the bottom\n"); + goto out; + } + a->mvd_h_src_inode = au_h_iptr(a->inode, a->mvd_bsrc); + br = au_sbr(a->sb, a->mvd_bsrc); + err = au_br_rdonly(br); + if (!(a->mvdown.flags & AUFS_MVDOWN_ROUPPER)) { + if (unlikely(err)) + goto out; + } else if (!(vfsub_native_ro(a->mvd_h_src_inode) + || IS_APPEND(a->mvd_h_src_inode))) { + if (err) + a->mvdown.flags |= AUFS_MVDOWN_ROUPPER_R; + /* go on */ + } else + goto out; + + err = -EINVAL; + if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_LOWER)) { + a->mvd_bdst = find_lower_writable(a); + if (unlikely(a->mvd_bdst < 0)) { + a->mvd_errno = EAU_MVDOWN_BOTTOM; + AU_MVD_PR(dmsg, "no writable lower branch\n"); + goto out; + } + } else { + a->mvd_bdst = au_br_index(a->sb, a->mvd_dst_brid); + if (unlikely(a->mvd_bdst < 0 + || au_sbbot(a->sb) < a->mvd_bdst)) { + a->mvd_errno = EAU_MVDOWN_NOLOWERBR; + AU_MVD_PR(dmsg, "no lower brid\n"); + goto out; + } + } + + err = au_mvd_args_busy(dmsg, a); + if (!err) + err = au_mvd_args_parent(dmsg, a); + if (!err) + err = au_mvd_args_intermediate(dmsg, a); + if (!err) + err = au_mvd_args_exist(dmsg, a); + if (!err) + AuDbg("b%d, b%d\n", a->mvd_bsrc, a->mvd_bdst); + +out: + AuTraceErr(err); + return err; +} + +int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg) +{ + int err, e; + unsigned char dmsg; + struct au_mvd_args *args; + struct inode *inode; + + inode = d_inode(dentry); + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = -ENOMEM; + args = kmalloc(sizeof(*args), GFP_NOFS); + if (unlikely(!args)) + goto out; + + err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown)); + if (!err) + /* VERIFY_WRITE */ + err = !access_ok(uarg, sizeof(*uarg)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out_free; + } + AuDbg("flags 0x%x\n", args->mvdown.flags); + args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R); + args->mvdown.au_errno = 0; + args->dentry = dentry; + args->inode = inode; + args->sb = dentry->d_sb; + + err = -ENOENT; + dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG); + args->parent = dget_parent(dentry); + args->dir = d_inode(args->parent); + inode_lock_nested(args->dir, I_MUTEX_PARENT); + dput(args->parent); + if (unlikely(args->parent != dentry->d_parent)) { + AU_MVD_PR(dmsg, "parent dir is moved\n"); + goto out_dir; + } + + inode_lock_nested(inode, I_MUTEX_CHILD); + err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW); + if (unlikely(err)) + goto out_inode; + + di_write_lock_parent(args->parent); + err = au_mvd_args(dmsg, args); + if (unlikely(err)) + goto out_parent; + + err = au_do_mvdown(dmsg, args); + if (unlikely(err)) + goto out_parent; + + au_cpup_attr_timesizes(args->dir); + au_cpup_attr_timesizes(inode); + if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER)) + au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst)); + /* au_digen_dec(dentry); */ + +out_parent: + di_write_unlock(args->parent); + aufs_read_unlock(dentry, AuLock_DW); +out_inode: + inode_unlock(inode); +out_dir: + inode_unlock(args->dir); +out_free: + e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown)); + if (unlikely(e)) + err = -EFAULT; + au_kfree_rcu(args); +out: + AuTraceErr(err); + return err; +} diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c new file mode 100644 index 000000000000..16e785facf9b --- /dev/null +++ b/fs/aufs/opts.c @@ -0,0 +1,1880 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * mount options/flags + */ + +#include <linux/namei.h> +#include <linux/types.h> /* a distribution requires */ +#include <linux/parser.h> +#include "aufs.h" + +/* ---------------------------------------------------------------------- */ + +enum { + Opt_br, + Opt_add, Opt_del, Opt_mod, Opt_append, Opt_prepend, + Opt_idel, Opt_imod, + Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash, + Opt_rdblk_def, Opt_rdhash_def, + Opt_xino, 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_shwh, Opt_noshwh, + Opt_plink, Opt_noplink, Opt_list_plink, + Opt_udba, + Opt_dio, Opt_nodio, + Opt_diropq_a, Opt_diropq_w, + Opt_warn_perm, Opt_nowarn_perm, + Opt_wbr_copyup, Opt_wbr_create, + Opt_fhsm_sec, + Opt_verbose, Opt_noverbose, + Opt_sum, Opt_nosum, Opt_wsum, + Opt_dirperm1, Opt_nodirperm1, + Opt_dirren, Opt_nodirren, + Opt_acl, Opt_noacl, + Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err +}; + +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"}, + +#ifdef CONFIG_PROC_FS + {Opt_plink, "plink"}, +#else + {Opt_ignore_silent, "plink"}, +#endif + + {Opt_noplink, "noplink"}, + +#ifdef CONFIG_AUFS_DEBUG + {Opt_list_plink, "list_plink"}, +#endif + + {Opt_udba, "udba=%s"}, + + {Opt_dio, "dio"}, + {Opt_nodio, "nodio"}, + +#ifdef CONFIG_AUFS_DIRREN + {Opt_dirren, "dirren"}, + {Opt_nodirren, "nodirren"}, +#else + {Opt_ignore, "dirren"}, + {Opt_ignore_silent, "nodirren"}, +#endif + +#ifdef CONFIG_AUFS_FHSM + {Opt_fhsm_sec, "fhsm_sec=%d"}, +#else + {Opt_ignore, "fhsm_sec=%d"}, +#endif + + {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, "nodlgt"}, + {Opt_ignore, "clean_plink"}, + +#ifdef CONFIG_AUFS_SHWH + {Opt_shwh, "shwh"}, +#endif + {Opt_noshwh, "noshwh"}, + + {Opt_dirperm1, "dirperm1"}, + {Opt_nodirperm1, "nodirperm1"}, + + {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_rdblk, "rdblk=%d"}, + {Opt_rdblk_def, "rdblk=def"}, + {Opt_rdhash, "rdhash=%d"}, + {Opt_rdhash_def, "rdhash=def"}, + + {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"}, + + /* generic VFS flag */ +#ifdef CONFIG_FS_POSIX_ACL + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, +#else + {Opt_ignore, "acl"}, + {Opt_ignore_silent, "noacl"}, +#endif + + /* 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"}, + + /* temporary workaround, due to old mount(8)? */ + {Opt_ignore_silent, "relatime"}, + + {Opt_err, NULL} +}; + +/* ---------------------------------------------------------------------- */ + +static const char *au_parser_pattern(int val, match_table_t tbl) +{ + struct match_token *p; + + p = tbl; + while (p->pattern) { + if (p->token == val) + return p->pattern; + p++; + } + BUG(); + return "??"; +} + +static const char *au_optstr(int *val, match_table_t tbl) +{ + struct match_token *p; + int v; + + v = *val; + if (!v) + goto out; + p = tbl; + while (p->pattern) { + if (p->token + && (v & p->token) == p->token) { + *val &= ~p->token; + return p->pattern; + } + p++; + } + +out: + return NULL; +} + +/* ---------------------------------------------------------------------- */ + +static match_table_t brperm = { + {AuBrPerm_RO, AUFS_BRPERM_RO}, + {AuBrPerm_RR, AUFS_BRPERM_RR}, + {AuBrPerm_RW, AUFS_BRPERM_RW}, + {0, NULL} +}; + +static match_table_t brattr = { + /* general */ + {AuBrAttr_COO_REG, AUFS_BRATTR_COO_REG}, + {AuBrAttr_COO_ALL, AUFS_BRATTR_COO_ALL}, + /* 'unpin' attrib is meaningless since linux-3.18-rc1 */ + {AuBrAttr_UNPIN, AUFS_BRATTR_UNPIN}, +#ifdef CONFIG_AUFS_FHSM + {AuBrAttr_FHSM, AUFS_BRATTR_FHSM}, +#endif +#ifdef CONFIG_AUFS_XATTR + {AuBrAttr_ICEX, AUFS_BRATTR_ICEX}, + {AuBrAttr_ICEX_SEC, AUFS_BRATTR_ICEX_SEC}, + {AuBrAttr_ICEX_SYS, AUFS_BRATTR_ICEX_SYS}, + {AuBrAttr_ICEX_TR, AUFS_BRATTR_ICEX_TR}, + {AuBrAttr_ICEX_USR, AUFS_BRATTR_ICEX_USR}, + {AuBrAttr_ICEX_OTH, AUFS_BRATTR_ICEX_OTH}, +#endif + + /* ro/rr branch */ + {AuBrRAttr_WH, AUFS_BRRATTR_WH}, + + /* rw branch */ + {AuBrWAttr_MOO, AUFS_BRWATTR_MOO}, + {AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH}, + + {0, NULL} +}; + +static int br_attr_val(char *str, match_table_t table, substring_t args[]) +{ + int attr, v; + char *p; + + attr = 0; + do { + p = strchr(str, '+'); + if (p) + *p = 0; + v = match_token(str, table, args); + if (v) { + if (v & AuBrAttr_CMOO_Mask) + attr &= ~AuBrAttr_CMOO_Mask; + attr |= v; + } else { + if (p) + *p = '+'; + pr_warn("ignored branch attribute %s\n", str); + break; + } + if (p) + str = p + 1; + } while (p); + + return attr; +} + +static int au_do_optstr_br_attr(au_br_perm_str_t *str, int perm) +{ + int sz; + const char *p; + char *q; + + q = str->a; + *q = 0; + p = au_optstr(&perm, brattr); + if (p) { + sz = strlen(p); + memcpy(q, p, sz + 1); + q += sz; + } else + goto out; + + do { + p = au_optstr(&perm, brattr); + if (p) { + *q++ = '+'; + sz = strlen(p); + memcpy(q, p, sz + 1); + q += sz; + } + } while (p); + +out: + return q - str->a; +} + +static int noinline_for_stack br_perm_val(char *perm) +{ + int val, bad, sz; + char *p; + substring_t args[MAX_OPT_ARGS]; + au_br_perm_str_t attr; + + p = strchr(perm, '+'); + if (p) + *p = 0; + val = match_token(perm, brperm, args); + if (!val) { + if (p) + *p = '+'; + pr_warn("ignored branch permission %s\n", perm); + val = AuBrPerm_RO; + goto out; + } + if (!p) + goto out; + + val |= br_attr_val(p + 1, brattr, args); + + bad = 0; + switch (val & AuBrPerm_Mask) { + case AuBrPerm_RO: + case AuBrPerm_RR: + bad = val & AuBrWAttr_Mask; + val &= ~AuBrWAttr_Mask; + break; + case AuBrPerm_RW: + bad = val & AuBrRAttr_Mask; + val &= ~AuBrRAttr_Mask; + break; + } + + /* + * 'unpin' attrib becomes meaningless since linux-3.18-rc1, but aufs + * does not treat it as an error, just warning. + * this is a tiny guard for the user operation. + */ + if (val & AuBrAttr_UNPIN) { + bad |= AuBrAttr_UNPIN; + val &= ~AuBrAttr_UNPIN; + } + + if (unlikely(bad)) { + sz = au_do_optstr_br_attr(&attr, bad); + AuDebugOn(!sz); + pr_warn("ignored branch attribute %s\n", attr.a); + } + +out: + return val; +} + +void au_optstr_br_perm(au_br_perm_str_t *str, int perm) +{ + au_br_perm_str_t attr; + const char *p; + char *q; + int sz; + + q = str->a; + p = au_optstr(&perm, brperm); + AuDebugOn(!p || !*p); + sz = strlen(p); + memcpy(q, p, sz + 1); + q += sz; + + sz = au_do_optstr_br_attr(&attr, perm); + if (sz) { + *q++ = '+'; + memcpy(q, attr.a, sz + 1); + } + + AuDebugOn(strlen(str->a) >= sizeof(str->a)); +} + +/* ---------------------------------------------------------------------- */ + +static match_table_t udbalevel = { + {AuOpt_UDBA_REVAL, "reval"}, + {AuOpt_UDBA_NONE, "none"}, +#ifdef CONFIG_AUFS_HNOTIFY + {AuOpt_UDBA_HNOTIFY, "notify"}, /* abstraction */ +#ifdef CONFIG_AUFS_HFSNOTIFY + {AuOpt_UDBA_HNOTIFY, "fsnotify"}, +#endif +#endif + {-1, NULL} +}; + +static int noinline_for_stack 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, 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"}, + + /* top-down regardless the parent, and then mfs */ + {AuWbrCreate_TDMFS, "tdmfs:%d"}, + {AuWbrCreate_TDMFSV, "tdmfs:%d:%d"}, + + {AuWbrCreate_MFSRR, "mfsrr:%d"}, + {AuWbrCreate_MFSRRV, "mfsrr:%d:%d"}, + {AuWbrCreate_PMFS, "pmfs"}, + {AuWbrCreate_PMFSV, "pmfs:%d"}, + {AuWbrCreate_PMFSRR, "pmfsrr:%d"}, + {AuWbrCreate_PMFSRRV, "pmfsrr:%d:%d"}, + + {-1, NULL} +}; + +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 (!match_u64(arg, &ull)) + create->mfsrr_watermark = ull; + else { + pr_err("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 && n <= AUFS_MFS_MAX_SEC) + create->mfs_second = n; + else { + pr_err("bad integer in %s\n", str); + err = -EINVAL; + } + + return err; +} + +static int noinline_for_stack +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: + case AuWbrCreate_TDMFSV: + case AuWbrCreate_PMFSRRV: + 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: + case AuWbrCreate_TDMFS: + case AuWbrCreate_PMFSRR: + 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_DEF_SEC; + 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, 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 noinline_for_stack 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, 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_rdblk: + AuDbg("rdblk %u\n", opt->rdblk); + break; + case Opt_rdblk_def: + AuDbg("rdblk_def\n"); + break; + case Opt_rdhash: + AuDbg("rdhash %u\n", opt->rdhash); + break; + case Opt_rdhash_def: + AuDbg("rdhash_def\n"); + break; + case Opt_xino: + u.xino = &opt->xino; + AuDbg("xino {%s %pD}\n", u.xino->path, u.xino->file); + 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_shwh: + AuLabel(shwh); + break; + case Opt_noshwh: + AuLabel(noshwh); + break; + case Opt_dirperm1: + AuLabel(dirperm1); + break; + case Opt_nodirperm1: + AuLabel(nodirperm1); + 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_dio: + AuLabel(dio); + break; + case Opt_nodio: + AuLabel(nodio); + 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_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: + case AuWbrCreate_TDMFS: + AuDbg("%llu watermark\n", + u.create->mfsrr_watermark); + break; + case AuWbrCreate_MFSRRV: + case AuWbrCreate_TDMFSV: + case AuWbrCreate_PMFSRRV: + 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; + case Opt_fhsm_sec: + AuDbg("fhsm_sec %u\n", opt->fhsm_second); + break; + case Opt_dirren: + AuLabel(dirren); + break; + case Opt_nodirren: + AuLabel(nodirren); + break; + case Opt_acl: + AuLabel(acl); + break; + case Opt_noacl: + AuLabel(noacl); + 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_RO; + 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 & SB_RDONLY)) + add->perm = AuBrPerm_RW; + } + opt->type = Opt_add; + goto out; + } + pr_err("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)) + pr_err("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_sbbot(sb) < bindex) { + pr_err("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 noinline_for_stack +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)) { + pr_err("no permission %s\n", args[0].from); + goto out; + } + + *p++ = 0; + err = vfsub_kern_path(mod->path, lkup_dirflags, &path); + if (unlikely(err)) { + pr_err("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_sbbot(sb) < bindex) { + pr_err("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, /*wbrtop*/0); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + + err = -EINVAL; + if (unlikely(file->f_path.dentry->d_sb == sb)) { + fput(file); + pr_err("%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 noinline_for_stack +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 bbot, bindex; + struct path path; + struct dentry *root; + + err = vfsub_kern_path(args[0].from, lkup_dirflags, &path); + if (unlikely(err)) { + pr_err("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); + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; 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)) { + pr_err("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))) { + pr_err("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))) { + pr_err("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))) { + pr_err("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))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + u.xino_itrunc->bindex = n; + aufs_read_lock(root, AuLock_FLUSH); + if (n < 0 || au_sbbot(sb) < n) { + pr_err("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], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + if (unlikely(n > AUFS_RDCACHE_MAX)) { + pr_err("rdcache must be smaller than %d\n", + AUFS_RDCACHE_MAX); + break; + } + opt->rdcache = n; + err = 0; + opt->type = token; + break; + case Opt_rdblk: + if (unlikely(match_int(&a->args[0], &n) + || n < 0 + || n > KMALLOC_MAX_SIZE)) { + pr_err("bad integer in %s\n", opt_str); + break; + } + if (unlikely(n && n < NAME_MAX)) { + pr_err("rdblk must be larger than %d\n", + NAME_MAX); + break; + } + opt->rdblk = n; + err = 0; + opt->type = token; + break; + case Opt_rdhash: + if (unlikely(match_int(&a->args[0], &n) + || n < 0 + || n * sizeof(struct hlist_head) + > KMALLOC_MAX_SIZE)) { + pr_err("bad integer in %s\n", opt_str); + break; + } + opt->rdhash = n; + 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_shwh: + case Opt_noshwh: + case Opt_dirperm1: + case Opt_nodirperm1: + case Opt_plink: + case Opt_noplink: + case Opt_list_plink: + case Opt_dio: + case Opt_nodio: + case Opt_diropq_a: + case Opt_diropq_w: + case Opt_warn_perm: + case Opt_nowarn_perm: + case Opt_verbose: + case Opt_noverbose: + case Opt_sum: + case Opt_nosum: + case Opt_wsum: + case Opt_rdblk_def: + case Opt_rdhash_def: + case Opt_dirren: + case Opt_nodirren: + case Opt_acl: + case Opt_noacl: + err = 0; + 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 + pr_err("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 + pr_err("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 + pr_err("wrong value, %s\n", opt_str); + break; + + case Opt_fhsm_sec: + if (unlikely(match_int(&a->args[0], &n) + || n < 0)) { + pr_err("bad integer in %s\n", opt_str); + break; + } + if (sysaufs_brs) { + opt->fhsm_second = n; + opt->type = token; + } else + pr_warn("ignored %s\n", opt_str); + err = 0; + break; + + case Opt_ignore: + pr_warn("ignored %s\n", opt_str); + /*FALLTHROUGH*/ + case Opt_ignore_silent: + skipped = 1; + err = 0; + break; + case Opt_err: + pr_err("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; + } + } + + au_kfree_rcu(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; + + SiMustWriteLock(sb); + + 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: + case AuWbrCreate_TDMFS: + case AuWbrCreate_TDMFSV: + case AuWbrCreate_PMFSRR: + case AuWbrCreate_PMFSRRV: + 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 + = msecs_to_jiffies(create->mfs_second * MSEC_PER_SEC); + 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; + + SiMustWriteLock(sb); + + 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, /*verbose*/1); + 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_dio: + au_opt_set(sbinfo->si_mntflags, DIO); + au_fset_opts(opts->flags, REFRESH_DYAOP); + break; + case Opt_nodio: + au_opt_clr(sbinfo->si_mntflags, DIO); + au_fset_opts(opts->flags, REFRESH_DYAOP); + break; + + case Opt_fhsm_sec: + au_fhsm_set(sbinfo, opt->fhsm_second); + 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_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); + break; + 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 + = msecs_to_jiffies(opt->rdcache * MSEC_PER_SEC); + break; + case Opt_rdblk: + sbinfo->si_rdblk = opt->rdblk; + break; + case Opt_rdblk_def: + sbinfo->si_rdblk = AUFS_RDBLK_DEF; + break; + case Opt_rdhash: + sbinfo->si_rdhash = opt->rdhash; + break; + case Opt_rdhash_def: + sbinfo->si_rdhash = AUFS_RDHASH_DEF; + break; + + case Opt_shwh: + au_opt_set(sbinfo->si_mntflags, SHWH); + break; + case Opt_noshwh: + au_opt_clr(sbinfo->si_mntflags, SHWH); + break; + + case Opt_dirperm1: + au_opt_set(sbinfo->si_mntflags, DIRPERM1); + break; + case Opt_nodirperm1: + au_opt_clr(sbinfo->si_mntflags, DIRPERM1); + 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, + /*idx_begin*/0); + 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; + + case Opt_dirren: + err = 1; + if (!au_opt_test(sbinfo->si_mntflags, DIRREN)) { + err = au_dr_opt_set(sb); + if (!err) + err = 1; + } + if (err == 1) + au_opt_set(sbinfo->si_mntflags, DIRREN); + break; + case Opt_nodirren: + err = 1; + if (au_opt_test(sbinfo->si_mntflags, DIRREN)) { + err = au_dr_opt_clr(sb, au_ftest_opts(opts->flags, + DR_FLUSHED)); + if (!err) + err = 1; + } + if (err == 1) + au_opt_clr(sbinfo->si_mntflags, DIRREN); + break; + + case Opt_acl: + sb->s_flags |= SB_POSIXACL; + break; + case Opt_noacl: + sb->s_flags &= ~SB_POSIXACL; + 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_sbbot(sb) + 1; + if (opt->add.bindex < 0) + opt->add.bindex = 0; + goto add; + /* Always goto add, not fallthrough */ + case Opt_prepend: + opt->add.bindex = 0; + /* fallthrough */ + add: /* indented label */ + case Opt_add: + err = au_br_add(sb, &opt->add, + au_ftest_opts(opts->flags, REMOUNT)); + if (!err) { + err = 1; + au_fset_opts(opts->flags, REFRESH); + } + 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); + } + 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); + } + 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; + + 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; + break; + + case Opt_noxino: + au_xino_clr(sb); + *opt_xino = (void *)-1; + break; + } + + return err; +} + +int au_opts_verify(struct super_block *sb, unsigned long sb_flags, + unsigned int pending) +{ + int err, fhsm; + aufs_bindex_t bindex, bbot; + unsigned char do_plink, skip, do_free, can_no_dreval; + struct au_branch *br; + struct au_wbr *wbr; + struct dentry *root, *dentry; + struct inode *dir, *h_dir; + struct au_sbinfo *sbinfo; + struct au_hinode *hdir; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA)); + + if (!(sb_flags & SB_RDONLY)) { + if (unlikely(!au_br_writable(au_sbr_perm(sb, 0)))) + pr_warn("first branch should be rw\n"); + if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH))) + pr_warn_once("shwh should be used with ro\n"); + } + + if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY) + && !au_opt_test(sbinfo->si_mntflags, XINO)) + pr_warn_once("udba=*notify requires xino\n"); + + if (au_opt_test(sbinfo->si_mntflags, DIRPERM1)) + pr_warn_once("dirperm1 breaks the protection" + " by the permission bits on the lower branch\n"); + + err = 0; + fhsm = 0; + root = sb->s_root; + dir = d_inode(root); + do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK); + can_no_dreval = !!au_opt_test((sbinfo->si_mntflags | pending), + UDBA_NONE); + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) { + skip = 0; + h_dir = au_h_iptr(dir, bindex); + br = au_sbr(sb, bindex); + + if ((br->br_perm & AuBrAttr_ICEX) + && !h_dir->i_op->listxattr) + br->br_perm &= ~AuBrAttr_ICEX; +#if 0 /* untested */ + if ((br->br_perm & AuBrAttr_ICEX_SEC) + && (au_br_sb(br)->s_flags & SB_NOSEC)) + br->br_perm &= ~AuBrAttr_ICEX_SEC; +#endif + + do_free = 0; + wbr = br->br_wbr; + if (wbr) + wbr_wh_read_lock(wbr); + + if (!au_br_writable(br->br_perm)) { + do_free = !!wbr; + skip = (!wbr + || (!wbr->wbr_whbase + && !wbr->wbr_plink + && !wbr->wbr_orph)); + } else if (!au_br_wh_linkable(br->br_perm)) { + /* 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; + } + } else { + /* 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; + } + } + if (wbr) + wbr_wh_read_unlock(wbr); + + if (can_no_dreval) { + dentry = br->br_path.dentry; + spin_lock(&dentry->d_lock); + if (dentry->d_flags & + (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE)) + can_no_dreval = 0; + spin_unlock(&dentry->d_lock); + } + + if (au_br_fhsm(br->br_perm)) { + fhsm++; + AuDebugOn(!br->br_fhsm); + } + + if (skip) + continue; + + hdir = au_hi(dir, bindex); + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + if (wbr) + wbr_wh_write_lock(wbr); + err = au_wh_init(br, sb); + if (wbr) + wbr_wh_write_unlock(wbr); + au_hn_inode_unlock(hdir); + + if (!err && do_free) { + au_kfree_rcu(wbr); + br->br_wbr = NULL; + } + } + + if (can_no_dreval) + au_fset_si(sbinfo, NO_DREVAL); + else + au_fclr_si(sbinfo, NO_DREVAL); + + if (fhsm >= 2) { + au_fset_si(sbinfo, FHSM); + for (bindex = bbot; bindex >= 0; bindex--) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm)) { + au_fhsm_set_bottom(sb, bindex); + break; + } + } + } else { + au_fclr_si(sbinfo, FHSM); + au_fhsm_set_bottom(sb, -1); + } + + return err; +} + +int au_opts_mount(struct super_block *sb, struct au_opts *opts) +{ + int err; + unsigned int tmp; + aufs_bindex_t bindex, bbot; + struct au_opt *opt; + struct au_opt_xino *opt_xino, xino; + struct au_sbinfo *sbinfo; + struct au_branch *br; + struct inode *dir; + + SiMustWriteLock(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 > 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; + + bbot = au_sbbot(sb); + if (unlikely(bbot < 0)) { + err = -EINVAL; + pr_err("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 */ + tmp &= AuOptMask_UDBA; + sbinfo->si_mntflags &= ~AuOptMask_UDBA; + sbinfo->si_mntflags |= tmp; + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_hnotify_reset_br(tmp, br, br->br_perm); + if (unlikely(err)) + AuIOErr("hnotify failed on br %d, %d, ignored\n", + bindex, err); + /* go on even if err */ + } + if (au_opt_test(tmp, UDBA_HNOTIFY)) { + dir = d_inode(sb->s_root); + au_hn_reset(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; + unsigned char no_dreval; + struct inode *dir; + struct au_opt_xino *opt_xino; + struct au_opt *opt; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + err = au_dr_opt_flush(sb); + if (unlikely(err)) + goto out; + au_fset_opts(opts->flags, DR_FLUSHED); + + dir = d_inode(sb->s_root); + sbinfo = au_sbi(sb); + opt_xino = NULL; + 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 */ + + no_dreval = !!au_ftest_si(sbinfo, NO_DREVAL); + rerr = au_opts_verify(sb, opts->sb_flags, /*pending*/0); + if (unlikely(rerr && !err)) + err = rerr; + + if (no_dreval != !!au_ftest_si(sbinfo, NO_DREVAL)) + au_fset_opts(opts->flags, REFRESH_IDOP); + + 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) + && (opts->given_udba + || au_opt_test(sbinfo->si_mntflags, XINO) + || au_ftest_opts(opts->flags, REFRESH_IDOP) + )) + au_fset_opts(opts->flags, REFRESH); + + AuDbg("status 0x%x\n", opts->flags); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +unsigned int au_opt_udba(struct super_block *sb) +{ + return au_mntflags(sb) & AuOptMask_UDBA; +} diff --git a/fs/aufs/opts.h b/fs/aufs/opts.h new file mode 100644 index 000000000000..79f3ea56f8bb --- /dev/null +++ b/fs/aufs/opts.h @@ -0,0 +1,225 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * mount options/flags + */ + +#ifndef __AUFS_OPTS_H__ +#define __AUFS_OPTS_H__ + +#ifdef __KERNEL__ + +#include <linux/path.h> + +struct file; + +/* ---------------------------------------------------------------------- */ + +/* 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_HNOTIFY (1 << 4) +#define AuOpt_SHWH (1 << 5) /* show whiteout */ +#define AuOpt_PLINK (1 << 6) /* pseudo-link */ +#define AuOpt_DIRPERM1 (1 << 7) /* ignore the lower dir's perm + bits */ +#define AuOpt_ALWAYS_DIROPQ (1 << 9) /* policy to creating diropq */ +#define AuOpt_SUM (1 << 10) /* summation for statfs(2) */ +#define AuOpt_SUM_W (1 << 11) /* unimplemented */ +#define AuOpt_WARN_PERM (1 << 12) /* warn when add-branch */ +#define AuOpt_VERBOSE (1 << 13) /* print the cause of error */ +#define AuOpt_DIO (1 << 14) /* direct io */ +#define AuOpt_DIRREN (1 << 15) /* directory rename */ + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuOpt_UDBA_HNOTIFY +#define AuOpt_UDBA_HNOTIFY 0 +#endif +#ifndef CONFIG_AUFS_DIRREN +#undef AuOpt_DIRREN +#define AuOpt_DIRREN 0 +#endif +#ifndef CONFIG_AUFS_SHWH +#undef AuOpt_SHWH +#define AuOpt_SHWH 0 +#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_HNOTIFY) + +#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) do { \ + ((flags) &= ~AuOpt_##name); \ +} while (0) + +static inline unsigned int au_opts_plink(unsigned int mntflags) +{ +#ifdef CONFIG_PROC_FS + return mntflags; +#else + return mntflags & ~AuOpt_PLINK; +#endif +} + +/* ---------------------------------------------------------------------- */ + +/* 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_TDMFS, /* top down regardless parent and mfs */ + AuWbrCreate_TDMFSV, /* top down regardless parent and mfs */ + AuWbrCreate_PMFS, /* parent and mfs */ + AuWbrCreate_PMFSV, /* parent and mfs with seconds */ + AuWbrCreate_PMFSRR, /* parent, mfs and round-robin */ + AuWbrCreate_PMFSRRV, /* plus 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; + unsigned int rdblk; + unsigned int rdhash; + int udba; + struct au_opt_wbr_create wbr_create; + int wbr_copyup; + unsigned int fhsm_second; + }; +}; + +/* opts flags */ +#define AuOpts_REMOUNT 1 +#define AuOpts_REFRESH (1 << 1) +#define AuOpts_TRUNC_XIB (1 << 2) +#define AuOpts_REFRESH_DYAOP (1 << 3) +#define AuOpts_REFRESH_IDOP (1 << 4) +#define AuOpts_DR_FLUSHED (1 << 5) +#define au_ftest_opts(flags, name) ((flags) & AuOpts_##name) +#define au_fset_opts(flags, name) \ + do { (flags) |= AuOpts_##name; } while (0) +#define au_fclr_opts(flags, name) \ + do { (flags) &= ~AuOpts_##name; } while (0) + +#ifndef CONFIG_AUFS_DIRREN +#undef AuOpts_DR_FLUSHED +#define AuOpts_DR_FLUSHED 0 +#endif + +struct au_opts { + struct au_opt *opt; + int max_opt; + + unsigned int given_udba; + unsigned int flags; + unsigned long sb_flags; +}; + +/* ---------------------------------------------------------------------- */ + +/* opts.c */ +void au_optstr_br_perm(au_br_perm_str_t *str, int perm); +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); +struct super_block; +int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts); +int au_opts_verify(struct super_block *sb, unsigned long sb_flags, + unsigned int pending); +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 --git a/fs/aufs/plink.c b/fs/aufs/plink.c new file mode 100644 index 000000000000..850829b21888 --- /dev/null +++ b/fs/aufs/plink.c @@ -0,0 +1,516 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * pseudo-link + */ + +#include "aufs.h" + +/* + * the pseudo-link maintenance mode. + * during a user process maintains the pseudo-links, + * prohibit adding a new plink and branch manipulation. + * + * Flags + * NOPLM: + * For entry functions which will handle plink, and i_mutex is already held + * in VFS. + * They cannot wait and should return an error at once. + * Callers has to check the error. + * NOPLMW: + * For entry functions which will handle plink, but i_mutex is not held + * in VFS. + * They can wait the plink maintenance mode to finish. + * + * They behave like F_SETLK and F_SETLKW. + * If the caller never handle plink, then both flags are unnecessary. + */ + +int au_plink_maint(struct super_block *sb, int flags) +{ + int err; + pid_t pid, ppid; + struct task_struct *parent, *prev; + struct au_sbinfo *sbi; + + SiMustAnyLock(sb); + + err = 0; + if (!au_opt_test(au_mntflags(sb), PLINK)) + goto out; + + sbi = au_sbi(sb); + pid = sbi->si_plink_maint_pid; + if (!pid || pid == current->pid) + goto out; + + /* todo: it highly depends upon /sbin/mount.aufs */ + prev = NULL; + parent = current; + ppid = 0; + rcu_read_lock(); + while (1) { + parent = rcu_dereference(parent->real_parent); + if (parent == prev) + break; + ppid = task_pid_vnr(parent); + if (pid == ppid) { + rcu_read_unlock(); + goto out; + } + prev = parent; + } + rcu_read_unlock(); + + if (au_ftest_lock(flags, NOPLMW)) { + /* if there is no i_mutex lock in VFS, we don't need to wait */ + /* AuDebugOn(!lockdep_depth(current)); */ + while (sbi->si_plink_maint_pid) { + si_read_unlock(sb); + /* gave up wake_up_bit() */ + wait_event(sbi->si_plink_wq, !sbi->si_plink_maint_pid); + + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&sbi->si_nowait); + si_noflush_read_lock(sb); + } + } else if (au_ftest_lock(flags, NOPLM)) { + AuDbg("ppid %d, pid %d\n", ppid, pid); + err = -EAGAIN; + } + +out: + return err; +} + +void au_plink_maint_leave(struct au_sbinfo *sbinfo) +{ + spin_lock(&sbinfo->si_plink_maint_lock); + sbinfo->si_plink_maint_pid = 0; + spin_unlock(&sbinfo->si_plink_maint_lock); + wake_up_all(&sbinfo->si_plink_wq); +} + +int au_plink_maint_enter(struct super_block *sb) +{ + int err; + struct au_sbinfo *sbinfo; + + err = 0; + sbinfo = au_sbi(sb); + /* make sure i am the only one in this fs */ + si_write_lock(sb, AuLock_FLUSH); + if (au_opt_test(au_mntflags(sb), PLINK)) { + spin_lock(&sbinfo->si_plink_maint_lock); + if (!sbinfo->si_plink_maint_pid) + sbinfo->si_plink_maint_pid = current->pid; + else + err = -EBUSY; + spin_unlock(&sbinfo->si_plink_maint_lock); + } + si_write_unlock(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_DEBUG +void au_plink_list(struct super_block *sb) +{ + int i; + struct au_sbinfo *sbinfo; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_icntnr *icntnr; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + for (i = 0; i < AuPlink_NHASH; i++) { + hbl = sbinfo->si_plink + i; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(icntnr, pos, hbl, plink) + AuDbg("%lu\n", icntnr->vfs_inode.i_ino); + hlist_bl_unlock(hbl); + } +} +#endif + +/* is the inode pseudo-linked? */ +int au_plink_test(struct inode *inode) +{ + int found, i; + struct au_sbinfo *sbinfo; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_icntnr *icntnr; + + sbinfo = au_sbi(inode->i_sb); + AuRwMustAnyLock(&sbinfo->si_rwsem); + AuDebugOn(!au_opt_test(au_mntflags(inode->i_sb), PLINK)); + AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); + + found = 0; + i = au_plink_hash(inode->i_ino); + hbl = sbinfo->si_plink + i; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(icntnr, pos, hbl, plink) + if (&icntnr->vfs_inode == inode) { + found = 1; + break; + } + hlist_bl_unlock(hbl); + 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; +} + +struct au_do_plink_lkup_args { + struct dentry **errp; + struct qstr *tgtname; + struct dentry *h_parent; + struct au_branch *br; +}; + +static struct dentry *au_do_plink_lkup(struct qstr *tgtname, + struct dentry *h_parent, + struct au_branch *br) +{ + struct dentry *h_dentry; + struct inode *h_inode; + + h_inode = d_inode(h_parent); + inode_lock_shared_nested(h_inode, AuLsc_I_CHILD2); + h_dentry = vfsub_lkup_one(tgtname, h_parent); + inode_unlock_shared(h_inode); + return h_dentry; +} + +static void au_call_do_plink_lkup(void *args) +{ + struct au_do_plink_lkup_args *a = args; + *a->errp = au_do_plink_lkup(a->tgtname, a->h_parent, a->br); +} + +/* 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; + int wkq_err; + char a[PLINK_NAME_LEN]; + struct qstr tgtname = QSTR_INIT(a, 0); + + AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); + + br = au_sbr(inode->i_sb, bindex); + h_parent = br->br_wbr->wbr_plink; + tgtname.len = plink_name(a, sizeof(a), inode, bindex); + + if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) { + struct au_do_plink_lkup_args args = { + .errp = &h_dentry, + .tgtname = &tgtname, + .h_parent = h_parent, + .br = br + }; + + wkq_err = au_wkq_wait(au_call_do_plink_lkup, &args); + if (unlikely(wkq_err)) + h_dentry = ERR_PTR(wkq_err); + } else + h_dentry = au_do_plink_lkup(&tgtname, h_parent, br); + + 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 = au_br_mnt(br) + }; + struct inode *h_dir, *delegated; + + h_dir = d_inode(h_parent); + inode_lock_nested(h_dir, AuLsc_I_CHILD2); +again: + h_path.dentry = vfsub_lkup_one(tgt, h_parent); + err = PTR_ERR(h_path.dentry); + if (IS_ERR(h_path.dentry)) + goto out; + + err = 0; + /* wh.plink dir is not monitored */ + /* todo: is it really safe? */ + if (d_is_positive(h_path.dentry) + && d_inode(h_path.dentry) != d_inode(h_dentry)) { + delegated = NULL; + err = vfsub_unlink(h_dir, &h_path, &delegated, /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + dput(h_path.dentry); + h_path.dentry = NULL; + if (!err) + goto again; + } + if (!err && d_is_negative(h_path.dentry)) { + delegated = NULL; + err = vfsub_link(h_dentry, h_dir, &h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + } + dput(h_path.dentry); + +out: + inode_unlock(h_dir); + 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; + char a[PLINK_NAME_LEN]; + struct qstr tgtname = QSTR_INIT(a, 0); + + wbr = au_sbr(inode->i_sb, bindex)->br_wbr; + h_parent = wbr->wbr_plink; + tgtname.len = plink_name(a, sizeof(a), inode, bindex); + + /* always superio. */ + if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) { + 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); + + return err; +} + +/* + * 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 hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_icntnr *icntnr; + int found, err, cnt, i; + + sb = inode->i_sb; + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + found = au_plink_test(inode); + if (found) + return; + + i = au_plink_hash(inode->i_ino); + hbl = sbinfo->si_plink + i; + au_igrab(inode); + + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(icntnr, pos, hbl, plink) { + if (&icntnr->vfs_inode == inode) { + found = 1; + break; + } + } + if (!found) { + icntnr = container_of(inode, struct au_icntnr, vfs_inode); + hlist_bl_add_head(&icntnr->plink, hbl); + } + hlist_bl_unlock(hbl); + if (!found) { + cnt = au_hbl_count(hbl); +#define msg "unexpectedly unbalanced or too many pseudo-links" + if (cnt > AUFS_PLINK_WARN) + AuWarn1(msg ", %d\n", cnt); +#undef msg + err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex)); + if (unlikely(err)) { + pr_warn("err %d, damaged pseudo link.\n", err); + au_hbl_del(&icntnr->plink, hbl); + iput(&icntnr->vfs_inode); + } + } else + iput(&icntnr->vfs_inode); +} + +/* free all plinks */ +void au_plink_put(struct super_block *sb, int verbose) +{ + int i, warned; + struct au_sbinfo *sbinfo; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos, *tmp; + struct au_icntnr *icntnr; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + /* no spin_lock since sbinfo is write-locked */ + warned = 0; + for (i = 0; i < AuPlink_NHASH; i++) { + hbl = sbinfo->si_plink + i; + if (!warned && verbose && !hlist_bl_empty(hbl)) { + pr_warn("pseudo-link is not flushed"); + warned = 1; + } + hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) + iput(&icntnr->vfs_inode); + INIT_HLIST_BL_HEAD(hbl); + } +} + +void au_plink_clean(struct super_block *sb, int verbose) +{ + struct dentry *root; + + root = sb->s_root; + aufs_write_lock(root); + if (au_opt_test(au_mntflags(sb), PLINK)) + au_plink_put(sb, verbose); + aufs_write_unlock(root); +} + +static int au_plink_do_half_refresh(struct inode *inode, aufs_bindex_t br_id) +{ + int do_put; + aufs_bindex_t btop, bbot, bindex; + + do_put = 0; + btop = au_ibtop(inode); + bbot = au_ibbot(inode); + if (btop >= 0) { + for (bindex = btop; bindex <= bbot; 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; + } + if (do_put) + for (bindex = btop; bindex <= bbot; bindex++) + if (au_h_iptr(inode, bindex)) { + do_put = 0; + break; + } + } else + do_put = 1; + + return do_put; +} + +/* 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 hlist_bl_head *hbl; + struct hlist_bl_node *pos, *tmp; + struct au_icntnr *icntnr; + struct inode *inode; + int i, do_put; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + /* no bit_lock since sbinfo is write-locked */ + for (i = 0; i < AuPlink_NHASH; i++) { + hbl = sbinfo->si_plink + i; + hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) { + inode = au_igrab(&icntnr->vfs_inode); + ii_write_lock_child(inode); + do_put = au_plink_do_half_refresh(inode, br_id); + if (do_put) { + hlist_bl_del(&icntnr->plink); + iput(inode); + } + ii_write_unlock(inode); + iput(inode); + } + } +} diff --git a/fs/aufs/poll.c b/fs/aufs/poll.c new file mode 100644 index 000000000000..6975d3ab2d29 --- /dev/null +++ b/fs/aufs/poll.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * poll operation + * There is only one filesystem which implements ->poll operation, currently. + */ + +#include "aufs.h" + +__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt) +{ + __poll_t mask; + struct file *h_file; + struct super_block *sb; + + /* We should pretend an error happened. */ + mask = EPOLLERR /* | EPOLLIN | EPOLLOUT */; + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + if (IS_ERR(h_file)) { + AuDbg("h_file %ld\n", PTR_ERR(h_file)); + goto out; + } + + mask = vfs_poll(h_file, pt); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + if (mask & EPOLLERR) + AuDbg("mask 0x%x\n", mask); + return mask; +} diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c new file mode 100644 index 000000000000..0789335650de --- /dev/null +++ b/fs/aufs/posix_acl.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * posix acl operations + */ + +#include <linux/fs.h> +#include "aufs.h" + +struct posix_acl *aufs_get_acl(struct inode *inode, int type) +{ + struct posix_acl *acl; + int err; + aufs_bindex_t bindex; + struct inode *h_inode; + struct super_block *sb; + + acl = NULL; + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH); + ii_read_lock_child(inode); + if (!(sb->s_flags & SB_POSIXACL)) + goto out; + + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (unlikely(!h_inode + || ((h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT)))) { + err = au_busy_or_stale(); + acl = ERR_PTR(err); + goto out; + } + + /* always topmost only */ + acl = get_acl(h_inode, type); + if (IS_ERR(acl)) + forget_cached_acl(inode, type); + else + set_cached_acl(inode, type, acl); + +out: + ii_read_unlock(inode); + si_read_unlock(sb); + + AuTraceErrPtr(acl); + return acl; +} + +int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int err; + ssize_t ssz; + struct dentry *dentry; + struct au_sxattr arg = { + .type = AU_ACL_SET, + .u.acl_set = { + .acl = acl, + .type = type + }, + }; + + IMustLock(inode); + + if (inode->i_ino == AUFS_ROOT_INO) + dentry = dget(inode->i_sb->s_root); + else { + dentry = d_find_alias(inode); + if (!dentry) + dentry = d_find_any_alias(inode); + if (!dentry) { + pr_warn("cannot handle this inode, " + "please report to aufs-users ML\n"); + err = -ENOENT; + goto out; + } + } + + ssz = au_sxattr(dentry, inode, &arg); + /* forget even it if succeeds since the branch might set differently */ + forget_cached_acl(inode, type); + dput(dentry); + err = ssz; + if (ssz >= 0) + err = 0; + +out: + return err; +} diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c new file mode 100644 index 000000000000..50ee0a9c1bcb --- /dev/null +++ b/fs/aufs/procfs.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * procfs interfaces + */ + +#include <linux/proc_fs.h> +#include "aufs.h" + +static int au_procfs_plm_release(struct inode *inode, struct file *file) +{ + struct au_sbinfo *sbinfo; + + sbinfo = file->private_data; + if (sbinfo) { + au_plink_maint_leave(sbinfo); + kobject_put(&sbinfo->si_kobj); + } + + return 0; +} + +static void au_procfs_plm_write_clean(struct file *file) +{ + struct au_sbinfo *sbinfo; + + sbinfo = file->private_data; + if (sbinfo) + au_plink_clean(sbinfo->si_sb, /*verbose*/0); +} + +static int au_procfs_plm_write_si(struct file *file, unsigned long id) +{ + int err; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct hlist_bl_node *pos; + + err = -EBUSY; + if (unlikely(file->private_data)) + goto out; + + sb = NULL; + /* don't use au_sbilist_lock() here */ + hlist_bl_lock(&au_sbilist); + hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) + if (id == sysaufs_si_id(sbinfo)) { + if (kobject_get_unless_zero(&sbinfo->si_kobj)) + sb = sbinfo->si_sb; + break; + } + hlist_bl_unlock(&au_sbilist); + + err = -EINVAL; + if (unlikely(!sb)) + goto out; + + err = au_plink_maint_enter(sb); + if (!err) + /* keep kobject_get() */ + file->private_data = sbinfo; + else + kobject_put(&sbinfo->si_kobj); +out: + return err; +} + +/* + * Accept a valid "si=xxxx" only. + * Once it is accepted successfully, accept "clean" too. + */ +static ssize_t au_procfs_plm_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + ssize_t err; + unsigned long id; + /* last newline is allowed */ + char buf[3 + sizeof(unsigned long) * 2 + 1]; + + err = -EACCES; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = -EINVAL; + if (unlikely(count > sizeof(buf))) + goto out; + + err = copy_from_user(buf, ubuf, count); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + buf[count] = 0; + + err = -EINVAL; + if (!strcmp("clean", buf)) { + au_procfs_plm_write_clean(file); + goto out_success; + } else if (unlikely(strncmp("si=", buf, 3))) + goto out; + + err = kstrtoul(buf + 3, 16, &id); + if (unlikely(err)) + goto out; + + err = au_procfs_plm_write_si(file, id); + if (unlikely(err)) + goto out; + +out_success: + err = count; /* success */ +out: + return err; +} + +static const struct proc_ops au_procfs_plm_op = { + .proc_write = au_procfs_plm_write, + .proc_release = au_procfs_plm_release +}; + +/* ---------------------------------------------------------------------- */ + +static struct proc_dir_entry *au_procfs_dir; + +void au_procfs_fin(void) +{ + remove_proc_entry(AUFS_PLINK_MAINT_NAME, au_procfs_dir); + remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); +} + +int __init au_procfs_init(void) +{ + int err; + struct proc_dir_entry *entry; + + err = -ENOMEM; + au_procfs_dir = proc_mkdir(AUFS_PLINK_MAINT_DIR, NULL); + if (unlikely(!au_procfs_dir)) + goto out; + + entry = proc_create(AUFS_PLINK_MAINT_NAME, S_IFREG | 0200, + au_procfs_dir, &au_procfs_plm_op); + if (unlikely(!entry)) + goto out_dir; + + err = 0; + goto out; /* success */ + + +out_dir: + remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); +out: + return err; +} diff --git a/fs/aufs/rdu.c b/fs/aufs/rdu.c new file mode 100644 index 000000000000..afd77564f3dc --- /dev/null +++ b/fs/aufs/rdu.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * readdir in userspace. + */ + +#include <linux/compat.h> +#include <linux/fs_stack.h> +#include <linux/security.h> +#include "aufs.h" + +/* bits for struct aufs_rdu.flags */ +#define AuRdu_CALLED 1 +#define AuRdu_CONT (1 << 1) +#define AuRdu_FULL (1 << 2) +#define au_ftest_rdu(flags, name) ((flags) & AuRdu_##name) +#define au_fset_rdu(flags, name) \ + do { (flags) |= AuRdu_##name; } while (0) +#define au_fclr_rdu(flags, name) \ + do { (flags) &= ~AuRdu_##name; } while (0) + +struct au_rdu_arg { + struct dir_context ctx; + struct aufs_rdu *rdu; + union au_rdu_ent_ul ent; + unsigned long end; + + struct super_block *sb; + int err; +}; + +static int au_rdu_fill(struct dir_context *ctx, const char *name, int nlen, + loff_t offset, u64 h_ino, unsigned int d_type) +{ + int err, len; + struct au_rdu_arg *arg = container_of(ctx, struct au_rdu_arg, ctx); + struct aufs_rdu *rdu = arg->rdu; + struct au_rdu_ent ent; + + err = 0; + arg->err = 0; + au_fset_rdu(rdu->cookie.flags, CALLED); + len = au_rdu_len(nlen); + if (arg->ent.ul + len < arg->end) { + ent.ino = h_ino; + ent.bindex = rdu->cookie.bindex; + ent.type = d_type; + ent.nlen = nlen; + if (unlikely(nlen > AUFS_MAX_NAMELEN)) + ent.type = DT_UNKNOWN; + + /* unnecessary to support mmap_sem since this is a dir */ + err = -EFAULT; + if (copy_to_user(arg->ent.e, &ent, sizeof(ent))) + goto out; + if (copy_to_user(arg->ent.e->name, name, nlen)) + goto out; + /* the terminating NULL */ + if (__put_user(0, arg->ent.e->name + nlen)) + goto out; + err = 0; + /* AuDbg("%p, %.*s\n", arg->ent.p, nlen, name); */ + arg->ent.ul += len; + rdu->rent++; + } else { + err = -EFAULT; + au_fset_rdu(rdu->cookie.flags, FULL); + rdu->full = 1; + rdu->tail = arg->ent; + } + +out: + /* AuTraceErr(err); */ + return err; +} + +static int au_rdu_do(struct file *h_file, struct au_rdu_arg *arg) +{ + int err; + loff_t offset; + struct au_rdu_cookie *cookie = &arg->rdu->cookie; + + /* we don't have to care (FMODE_32BITHASH | FMODE_64BITHASH) for ext4 */ + offset = vfsub_llseek(h_file, cookie->h_pos, SEEK_SET); + err = offset; + if (unlikely(offset != cookie->h_pos)) + goto out; + + err = 0; + do { + arg->err = 0; + au_fclr_rdu(cookie->flags, CALLED); + /* smp_mb(); */ + err = vfsub_iterate_dir(h_file, &arg->ctx); + if (err >= 0) + err = arg->err; + } while (!err + && au_ftest_rdu(cookie->flags, CALLED) + && !au_ftest_rdu(cookie->flags, FULL)); + cookie->h_pos = h_file->f_pos; + +out: + AuTraceErr(err); + return err; +} + +static int au_rdu(struct file *file, struct aufs_rdu *rdu) +{ + int err; + aufs_bindex_t bbot; + struct au_rdu_arg arg = { + .ctx = { + .actor = au_rdu_fill + } + }; + struct dentry *dentry; + struct inode *inode; + struct file *h_file; + struct au_rdu_cookie *cookie = &rdu->cookie; + + /* VERIFY_WRITE */ + err = !access_ok(rdu->ent.e, rdu->sz); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + rdu->rent = 0; + rdu->tail = rdu->ent; + rdu->full = 0; + arg.rdu = rdu; + arg.ent = rdu->ent; + arg.end = arg.ent.ul; + arg.end += rdu->sz; + + err = -ENOTDIR; + if (unlikely(!file->f_op->iterate && !file->f_op->iterate_shared)) + goto out; + + err = security_file_permission(file, MAY_READ); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + dentry = file->f_path.dentry; + inode = d_inode(dentry); + inode_lock_shared(inode); + + arg.sb = inode->i_sb; + err = si_read_lock(arg.sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_mtx; + err = au_alive_dir(dentry); + if (unlikely(err)) + goto out_si; + /* todo: reval? */ + fi_read_lock(file); + + err = -EAGAIN; + if (unlikely(au_ftest_rdu(cookie->flags, CONT) + && cookie->generation != au_figen(file))) + goto out_unlock; + + err = 0; + if (!rdu->blk) { + rdu->blk = au_sbi(arg.sb)->si_rdblk; + if (!rdu->blk) + rdu->blk = au_dir_size(file, /*dentry*/NULL); + } + bbot = au_fbtop(file); + if (cookie->bindex < bbot) + cookie->bindex = bbot; + bbot = au_fbbot_dir(file); + /* AuDbg("b%d, b%d\n", cookie->bindex, bbot); */ + for (; !err && cookie->bindex <= bbot; + cookie->bindex++, cookie->h_pos = 0) { + h_file = au_hf_dir(file, cookie->bindex); + if (!h_file) + continue; + + au_fclr_rdu(cookie->flags, FULL); + err = au_rdu_do(h_file, &arg); + AuTraceErr(err); + if (unlikely(au_ftest_rdu(cookie->flags, FULL) || err)) + break; + } + AuDbg("rent %llu\n", rdu->rent); + + if (!err && !au_ftest_rdu(cookie->flags, CONT)) { + rdu->shwh = !!au_opt_test(au_sbi(arg.sb)->si_mntflags, SHWH); + au_fset_rdu(cookie->flags, CONT); + cookie->generation = au_figen(file); + } + + ii_read_lock_child(inode); + fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibtop(inode))); + ii_read_unlock(inode); + +out_unlock: + fi_read_unlock(file); +out_si: + si_read_unlock(arg.sb); +out_mtx: + inode_unlock_shared(inode); +out: + AuTraceErr(err); + return err; +} + +static int au_rdu_ino(struct file *file, struct aufs_rdu *rdu) +{ + int err; + ino_t ino; + unsigned long long nent; + union au_rdu_ent_ul *u; + struct au_rdu_ent ent; + struct super_block *sb; + + err = 0; + nent = rdu->nent; + u = &rdu->ent; + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + while (nent-- > 0) { + /* unnecessary to support mmap_sem since this is a dir */ + err = copy_from_user(&ent, u->e, sizeof(ent)); + if (!err) + /* VERIFY_WRITE */ + err = !access_ok(&u->e->ino, sizeof(ino)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + break; + } + + /* AuDbg("b%d, i%llu\n", ent.bindex, ent.ino); */ + if (!ent.wh) + err = au_ino(sb, ent.bindex, ent.ino, ent.type, &ino); + else + err = au_wh_ino(sb, ent.bindex, ent.ino, ent.type, + &ino); + if (unlikely(err)) { + AuTraceErr(err); + break; + } + + err = __put_user(ino, &u->e->ino); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + break; + } + u->ul += au_rdu_len(ent.nlen); + } + si_read_unlock(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_rdu_verify(struct aufs_rdu *rdu) +{ + AuDbg("rdu{%llu, %p, %u | %u | %llu, %u, %u | " + "%llu, b%d, 0x%x, g%u}\n", + rdu->sz, rdu->ent.e, rdu->verify[AufsCtlRduV_SZ], + rdu->blk, + rdu->rent, rdu->shwh, rdu->full, + rdu->cookie.h_pos, rdu->cookie.bindex, rdu->cookie.flags, + rdu->cookie.generation); + + if (rdu->verify[AufsCtlRduV_SZ] == sizeof(*rdu)) + return 0; + + AuDbg("%u:%u\n", + rdu->verify[AufsCtlRduV_SZ], (unsigned int)sizeof(*rdu)); + return -EINVAL; +} + +long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err, e; + struct aufs_rdu rdu; + void __user *p = (void __user *)arg; + + err = copy_from_user(&rdu, p, sizeof(rdu)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + err = au_rdu_verify(&rdu); + if (unlikely(err)) + goto out; + + switch (cmd) { + case AUFS_CTL_RDU: + err = au_rdu(file, &rdu); + if (unlikely(err)) + break; + + e = copy_to_user(p, &rdu, sizeof(rdu)); + if (unlikely(e)) { + err = -EFAULT; + AuTraceErr(err); + } + break; + case AUFS_CTL_RDU_INO: + err = au_rdu_ino(file, &rdu); + break; + + default: + /* err = -ENOTTY; */ + err = -EINVAL; + } + +out: + AuTraceErr(err); + return err; +} + +#ifdef CONFIG_COMPAT +long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err, e; + struct aufs_rdu rdu; + void __user *p = compat_ptr(arg); + + /* todo: get_user()? */ + err = copy_from_user(&rdu, p, sizeof(rdu)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + rdu.ent.e = compat_ptr(rdu.ent.ul); + err = au_rdu_verify(&rdu); + if (unlikely(err)) + goto out; + + switch (cmd) { + case AUFS_CTL_RDU: + err = au_rdu(file, &rdu); + if (unlikely(err)) + break; + + rdu.ent.ul = ptr_to_compat(rdu.ent.e); + rdu.tail.ul = ptr_to_compat(rdu.tail.e); + e = copy_to_user(p, &rdu, sizeof(rdu)); + if (unlikely(e)) { + err = -EFAULT; + AuTraceErr(err); + } + break; + case AUFS_CTL_RDU_INO: + err = au_rdu_ino(file, &rdu); + break; + + default: + /* err = -ENOTTY; */ + err = -EINVAL; + } + +out: + AuTraceErr(err); + return err; +} +#endif diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h new file mode 100644 index 000000000000..370eae159348 --- /dev/null +++ b/fs/aufs/rwsem.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * simple read-write semaphore wrappers + */ + +#ifndef __AUFS_RWSEM_H__ +#define __AUFS_RWSEM_H__ + +#ifdef __KERNEL__ + +#include "debug.h" + +/* in the future, the name 'au_rwsem' will be totally gone */ +#define au_rwsem rw_semaphore + +/* to debug easier, do not make them inlined functions */ +#define AuRwMustNoWaiters(rw) AuDebugOn(rwsem_is_contended(rw)) +/* rwsem_is_locked() is unusable */ +#define AuRwMustReadLock(rw) AuDebugOn(!lockdep_recursing(current) \ + && debug_locks \ + && !lockdep_is_held_type(rw, 1)) +#define AuRwMustWriteLock(rw) AuDebugOn(!lockdep_recursing(current) \ + && debug_locks \ + && !lockdep_is_held_type(rw, 0)) +#define AuRwMustAnyLock(rw) AuDebugOn(!lockdep_recursing(current) \ + && debug_locks \ + && !lockdep_is_held(rw)) +#define AuRwDestroy(rw) AuDebugOn(!lockdep_recursing(current) \ + && debug_locks \ + && lockdep_is_held(rw)) + +#define au_rw_init(rw) init_rwsem(rw) + +#define au_rw_init_wlock(rw) do { \ + au_rw_init(rw); \ + down_write(rw); \ + } while (0) + +#define au_rw_init_wlock_nested(rw, lsc) do { \ + au_rw_init(rw); \ + down_write_nested(rw, lsc); \ + } while (0) + +#define au_rw_read_lock(rw) down_read(rw) +#define au_rw_read_lock_nested(rw, lsc) down_read_nested(rw, lsc) +#define au_rw_read_unlock(rw) up_read(rw) +#define au_rw_dgrade_lock(rw) downgrade_write(rw) +#define au_rw_write_lock(rw) down_write(rw) +#define au_rw_write_lock_nested(rw, lsc) down_write_nested(rw, lsc) +#define au_rw_write_unlock(rw) up_write(rw) +/* why is not _nested version defined? */ +#define au_rw_read_trylock(rw) down_read_trylock(rw) +#define au_rw_write_trylock(rw) down_write_trylock(rw) + +#endif /* __KERNEL__ */ +#endif /* __AUFS_RWSEM_H__ */ diff --git a/fs/aufs/sbinfo.c b/fs/aufs/sbinfo.c new file mode 100644 index 000000000000..3835be61d978 --- /dev/null +++ b/fs/aufs/sbinfo.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * superblock private data + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* + * they are necessary regardless sysfs is disabled. + */ +void au_si_free(struct kobject *kobj) +{ + int i; + struct au_sbinfo *sbinfo; + char *locked __maybe_unused; /* debug only */ + + sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); + for (i = 0; i < AuPlink_NHASH; i++) + AuDebugOn(!hlist_bl_empty(sbinfo->si_plink + i)); + AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len)); + + AuLCntZero(au_lcnt_read(&sbinfo->si_ninodes, /*do_rev*/0)); + au_lcnt_fin(&sbinfo->si_ninodes, /*do_sync*/0); + AuLCntZero(au_lcnt_read(&sbinfo->si_nfiles, /*do_rev*/0)); + au_lcnt_fin(&sbinfo->si_nfiles, /*do_sync*/0); + + dbgaufs_si_fin(sbinfo); + au_rw_write_lock(&sbinfo->si_rwsem); + au_br_free(sbinfo); + au_rw_write_unlock(&sbinfo->si_rwsem); + + au_kfree_try_rcu(sbinfo->si_branch); + mutex_destroy(&sbinfo->si_xib_mtx); + AuRwDestroy(&sbinfo->si_rwsem); + + au_lcnt_wait_for_fin(&sbinfo->si_ninodes); + /* si_nfiles is waited too */ + au_kfree_rcu(sbinfo); +} + +int au_si_alloc(struct super_block *sb) +{ + int err, i; + struct au_sbinfo *sbinfo; + + err = -ENOMEM; + sbinfo = kzalloc(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; + + err = sysaufs_si_init(sbinfo); + if (!err) { + dbgaufs_si_null(sbinfo); + err = dbgaufs_si_init(sbinfo); + if (unlikely(err)) + kobject_put(&sbinfo->si_kobj); + } + if (unlikely(err)) + goto out_br; + + au_nwt_init(&sbinfo->si_nowait); + au_rw_init_wlock(&sbinfo->si_rwsem); + + au_lcnt_init(&sbinfo->si_ninodes, /*release*/NULL); + au_lcnt_init(&sbinfo->si_nfiles, /*release*/NULL); + + sbinfo->si_bbot = -1; + sbinfo->si_last_br_id = AUFS_BRANCH_MAX / 2; + + sbinfo->si_wbr_copyup = AuWbrCopyup_Def; + sbinfo->si_wbr_create = AuWbrCreate_Def; + sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup; + sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create; + + au_fhsm_init(sbinfo); + + sbinfo->si_mntflags = au_opts_plink(AuOpt_Def); + + sbinfo->si_xino_jiffy = jiffies; + sbinfo->si_xino_expire + = msecs_to_jiffies(AUFS_XINO_DEF_SEC * MSEC_PER_SEC); + mutex_init(&sbinfo->si_xib_mtx); + /* leave si_xib_last_pindex and si_xib_next_bit */ + + INIT_HLIST_BL_HEAD(&sbinfo->si_aopen); + + sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC); + sbinfo->si_rdblk = AUFS_RDBLK_DEF; + sbinfo->si_rdhash = AUFS_RDHASH_DEF; + sbinfo->si_dirwh = AUFS_DIRWH_DEF; + + for (i = 0; i < AuPlink_NHASH; i++) + INIT_HLIST_BL_HEAD(sbinfo->si_plink + i); + init_waitqueue_head(&sbinfo->si_plink_wq); + spin_lock_init(&sbinfo->si_plink_maint_lock); + + INIT_HLIST_BL_HEAD(&sbinfo->si_files); + + /* with getattr by default */ + sbinfo->si_iop_array = aufs_iop; + + /* leave other members for sysaufs and si_mnt. */ + sbinfo->si_sb = sb; + sb->s_fs_info = sbinfo; + si_pid_set(sb); + return 0; /* success */ + +out_br: + au_kfree_try_rcu(sbinfo->si_branch); +out_sbinfo: + au_kfree_rcu(sbinfo); +out: + return err; +} + +int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr, int may_shrink) +{ + int err, sz; + struct au_branch **brp; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + err = -ENOMEM; + sz = sizeof(*brp) * (sbinfo->si_bbot + 1); + if (unlikely(!sz)) + sz = sizeof(*brp); + brp = au_kzrealloc(sbinfo->si_branch, sz, sizeof(*brp) * nbr, GFP_NOFS, + may_shrink); + if (brp) { + sbinfo->si_branch = brp; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +unsigned int au_sigen_inc(struct super_block *sb) +{ + unsigned int gen; + struct inode *inode; + + SiMustWriteLock(sb); + + gen = ++au_sbi(sb)->si_generation; + au_update_digen(sb->s_root); + inode = d_inode(sb->s_root); + au_update_iigen(inode, /*half*/0); + inode_inc_iversion(inode); + return gen; +} + +aufs_bindex_t au_new_br_id(struct super_block *sb) +{ + aufs_bindex_t br_id; + int i; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + for (i = 0; i <= AUFS_BRANCH_MAX; i++) { + br_id = ++sbinfo->si_last_br_id; + AuDebugOn(br_id < 0); + if (br_id && au_br_index(sb, br_id) < 0) + return br_id; + } + + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* it is ok that new 'nwt' tasks are appended while we are sleeping */ +int si_read_lock(struct super_block *sb, int flags) +{ + int err; + + err = 0; + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + + si_noflush_read_lock(sb); + err = au_plink_maint(sb, flags); + if (unlikely(err)) + si_read_unlock(sb); + + return err; +} + +int si_write_lock(struct super_block *sb, int flags) +{ + int err; + + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + + si_noflush_write_lock(sb); + err = au_plink_maint(sb, flags); + if (unlikely(err)) + si_write_unlock(sb); + + return err; +} + +/* dentry and super_block lock. call at entry point */ +int aufs_read_lock(struct dentry *dentry, int flags) +{ + int err; + struct super_block *sb; + + sb = dentry->d_sb; + err = si_read_lock(sb, flags); + if (unlikely(err)) + goto out; + + if (au_ftest_lock(flags, DW)) + di_write_lock_child(dentry); + else + di_read_lock_child(dentry, flags); + + if (au_ftest_lock(flags, GEN)) { + err = au_digen_test(dentry, au_sigen(sb)); + if (!au_opt_test(au_mntflags(sb), UDBA_NONE)) + AuDebugOn(!err && au_dbrange_test(dentry)); + else if (!err) + err = au_dbrange_test(dentry); + if (unlikely(err)) + aufs_read_unlock(dentry, flags); + } + +out: + return err; +} + +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, AuLock_FLUSH | AuLock_NOPLMW); + di_write_lock_child(dentry); +} + +void aufs_write_unlock(struct dentry *dentry) +{ + di_write_unlock(dentry); + si_write_unlock(dentry->d_sb); +} + +int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags) +{ + int err; + unsigned int sigen; + struct super_block *sb; + + sb = d1->d_sb; + err = si_read_lock(sb, flags); + if (unlikely(err)) + goto out; + + di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIRS)); + + if (au_ftest_lock(flags, GEN)) { + sigen = au_sigen(sb); + err = au_digen_test(d1, sigen); + AuDebugOn(!err && au_dbrange_test(d1)); + if (!err) { + err = au_digen_test(d2, sigen); + AuDebugOn(!err && au_dbrange_test(d2)); + } + if (unlikely(err)) + aufs_read_and_write_unlock2(d1, d2); + } + +out: + return err; +} + +void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2) +{ + di_write_unlock2(d1, d2); + si_read_unlock(d1->d_sb); +} diff --git a/fs/aufs/super.c b/fs/aufs/super.c new file mode 100644 index 000000000000..aa7f210e5493 --- /dev/null +++ b/fs/aufs/super.c @@ -0,0 +1,1047 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * mount and super_block operations + */ + +#include <linux/iversion.h> +#include <linux/mm.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include <linux/vmalloc.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) { + au_icntnr_init(c); + inode_set_iversion(&c->vfs_inode, 1); /* sigen(sb); */ + c->iinfo.ii_hinode = NULL; + return &c->vfs_inode; + } + return NULL; +} + +static void aufs_destroy_inode(struct inode *inode) +{ + if (!au_is_bad_inode(inode)) + au_iinfo_fin(inode); +} + +static void aufs_free_inode(struct inode *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_inc_iversion(inode); + 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, bbot; + struct path path; + struct au_hdentry *hdp; + struct au_branch *br; + au_br_perm_str_t perm; + + err = 0; + bbot = au_sbbot(sb); + bindex = 0; + hdp = au_hdentry(au_di(sb->s_root), bindex); + for (; !err && bindex <= bbot; bindex++, hdp++) { + br = au_sbr(sb, bindex); + path.mnt = au_br_mnt(br); + path.dentry = hdp->hd_dentry; + err = au_seq_path(seq, &path); + if (!err) { + au_optstr_br_perm(&perm, br->br_perm); + seq_printf(seq, "=%s", perm.a); + if (bindex != bbot) + seq_putc(seq, ':'); + } + } + if (unlikely(err || seq_has_overflowed(seq))) + err = -E2BIG; + + return err; +} + +static void au_gen_fmt(char *fmt, int len __maybe_unused, const char *pat, + const char *append) +{ + char *p; + + p = fmt; + while (*pat != ':') + *p++ = *pat++; + *p++ = *pat++; + strcpy(p, append); + AuDebugOn(strlen(fmt) >= len); +} + +static void au_show_wbr_create(struct seq_file *m, int v, + struct au_sbinfo *sbinfo) +{ + const char *pat; + char fmt[32]; + struct au_wbr_mfs *mfs; + + AuRwMustAnyLock(&sbinfo->si_rwsem); + + seq_puts(m, ",create="); + pat = au_optstr_wbr_create(v); + mfs = &sbinfo->si_wbr_mfs; + switch (v) { + case AuWbrCreate_TDP: + case AuWbrCreate_RR: + case AuWbrCreate_MFS: + case AuWbrCreate_PMFS: + seq_puts(m, pat); + break; + case AuWbrCreate_MFSRR: + case AuWbrCreate_TDMFS: + case AuWbrCreate_PMFSRR: + au_gen_fmt(fmt, sizeof(fmt), pat, "%llu"); + seq_printf(m, fmt, mfs->mfsrr_watermark); + break; + case AuWbrCreate_MFSV: + case AuWbrCreate_PMFSV: + au_gen_fmt(fmt, sizeof(fmt), pat, "%lu"); + seq_printf(m, fmt, + jiffies_to_msecs(mfs->mfs_expire) + / MSEC_PER_SEC); + break; + case AuWbrCreate_MFSRRV: + case AuWbrCreate_TDMFSV: + case AuWbrCreate_PMFSRRV: + au_gen_fmt(fmt, sizeof(fmt), pat, "%llu:%lu"); + seq_printf(m, fmt, mfs->mfsrr_watermark, + jiffies_to_msecs(mfs->mfs_expire) / MSEC_PER_SEC); + break; + default: + BUG(); + } +} + +static int au_show_xino(struct seq_file *seq, struct super_block *sb) +{ +#ifdef CONFIG_SYSFS + return 0; +#else + int err; + const int len = sizeof(AUFS_XINO_FNAME) - 1; + aufs_bindex_t bindex, brid; + struct qstr *name; + struct file *f; + struct dentry *d, *h_root; + struct au_branch *br; + + AuRwMustAnyLock(&sbinfo->si_rwsem); + + err = 0; + f = au_sbi(sb)->si_xib; + if (!f) + goto out; + + /* stop printing the default xino path on the first writable branch */ + h_root = NULL; + bindex = au_xi_root(sb, f->f_path.dentry); + if (bindex >= 0) { + br = au_sbr_sb(sb, bindex); + h_root = au_br_dentry(br); + } + + d = f->f_path.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 dentry *dentry) +{ + int err; + 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) + +#define AuUInt(name, str, val) do { \ + if (val != AUFS_##name##_DEF) \ + seq_printf(m, "," #str "=%u", val); \ +} while (0) + + sb = dentry->d_sb; + if (sb->s_flags & SB_POSIXACL) + seq_puts(m, ",acl"); +#if 0 /* reserved for future use */ + if (sb->s_flags & SB_I_VERSION) + seq_puts(m, ",i_version"); +#endif + + /* lock free root dinfo */ + 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, sb); + if (unlikely(err)) + goto out; + } else + seq_puts(m, ",noxino"); + + AuBool(TRUNC_XINO, trunc_xino); + AuStr(UDBA, udba); + AuBool(SHWH, shwh); + AuBool(PLINK, plink); + AuBool(DIO, dio); + AuBool(DIRPERM1, dirperm1); + + 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'); + + AuUInt(DIRWH, dirwh, sbinfo->si_dirwh); + + v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC; + AuUInt(RDCACHE, rdcache, v); + + AuUInt(RDBLK, rdblk, sbinfo->si_rdblk); + AuUInt(RDHASH, rdhash, sbinfo->si_rdhash); + + au_fhsm_show(m, sbinfo); + + AuBool(DIRREN, dirren); + 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 AuBool +#undef AuStr +#undef AuUInt +} + +/* ---------------------------------------------------------------------- */ + +/* 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 u64 au_mul_till_max(u64 a, long mul) +{ + u64 old; + + old = a; + a *= mul; + if (old <= a) + return a; + return ULLONG_MAX; +} + +static int au_statfs_sum(struct super_block *sb, struct kstatfs *buf) +{ + int err; + long bsize, factor; + u64 blocks, bfree, bavail, files, ffree; + aufs_bindex_t bbot, bindex, i; + unsigned char shared; + struct path h_path; + struct super_block *h_sb; + + err = 0; + bsize = LONG_MAX; + files = 0; + ffree = 0; + blocks = 0; + bfree = 0; + bavail = 0; + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + h_path.mnt = au_sbr_mnt(sb, bindex); + h_sb = h_path.mnt->mnt_sb; + shared = 0; + for (i = 0; !shared && i < bindex; i++) + shared = (au_sbr_sb(sb, i) == h_sb); + if (shared) + continue; + + /* sb->s_root for NFS is unreliable */ + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, buf); + if (unlikely(err)) + goto out; + + if (bsize > buf->f_bsize) { + /* + * we will reduce bsize, so we have to expand blocks + * etc. to match them again + */ + factor = (bsize / buf->f_bsize); + blocks = au_mul_till_max(blocks, factor); + bfree = au_mul_till_max(bfree, factor); + bavail = au_mul_till_max(bavail, factor); + bsize = buf->f_bsize; + } + + factor = (buf->f_bsize / bsize); + blocks = au_add_till_max(blocks, + au_mul_till_max(buf->f_blocks, factor)); + bfree = au_add_till_max(bfree, + au_mul_till_max(buf->f_bfree, factor)); + bavail = au_add_till_max(bavail, + au_mul_till_max(buf->f_bavail, factor)); + files = au_add_till_max(files, buf->f_files); + ffree = au_add_till_max(ffree, buf->f_ffree); + } + + buf->f_bsize = bsize; + buf->f_blocks = blocks; + buf->f_bfree = bfree; + buf->f_bavail = bavail; + buf->f_files = files; + buf->f_ffree = ffree; + buf->f_frsize = 0; + +out: + return err; +} + +static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err; + struct path h_path; + 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 */ + h_path.mnt = au_sbr_mnt(sb, 0); + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, buf); + } else + err = au_statfs_sum(sb, buf); + si_read_unlock(sb); + + if (!err) { + buf->f_type = AUFS_SUPER_MAGIC; + buf->f_namelen = AUFS_MAX_NAMELEN; + memset(&buf->f_fsid, 0, sizeof(buf->f_fsid)); + } + /* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */ + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_sync_fs(struct super_block *sb, int wait) +{ + int err, e; + aufs_bindex_t bbot, bindex; + struct au_branch *br; + struct super_block *h_sb; + + err = 0; + si_noflush_read_lock(sb); + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (!au_br_writable(br->br_perm)) + continue; + + h_sb = au_sbr_sb(sb, bindex); + e = vfsub_sync_filesystem(h_sb, wait); + if (unlikely(e && !err)) + err = e; + /* go on even if an error happens */ + } + si_read_unlock(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* 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) + kobject_put(&sbinfo->si_kobj); +} + +/* ---------------------------------------------------------------------- */ + +void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, + struct super_block *sb, void *arg) +{ + void *array; + unsigned long long n, sz; + + array = NULL; + n = 0; + if (!*hint) + goto out; + + if (*hint > ULLONG_MAX / sizeof(array)) { + array = ERR_PTR(-EMFILE); + pr_err("hint %llu\n", *hint); + goto out; + } + + sz = sizeof(array) * *hint; + array = kzalloc(sz, GFP_NOFS); + if (unlikely(!array)) + array = vzalloc(sz); + if (unlikely(!array)) { + array = ERR_PTR(-ENOMEM); + goto out; + } + + n = cb(sb, array, *hint, arg); + AuDebugOn(n > *hint); + +out: + *hint = n; + return array; +} + +static unsigned long long au_iarray_cb(struct super_block *sb, void *a, + unsigned long long max __maybe_unused, + void *arg) +{ + unsigned long long n; + struct inode **p, *inode; + struct list_head *head; + + n = 0; + p = a; + head = arg; + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(inode, head, i_sb_list) { + if (!au_is_bad_inode(inode) + && au_ii(inode)->ii_btop >= 0) { + spin_lock(&inode->i_lock); + if (atomic_read(&inode->i_count)) { + au_igrab(inode); + *p++ = inode; + n++; + AuDebugOn(n > max); + } + spin_unlock(&inode->i_lock); + } + } + spin_unlock(&sb->s_inode_list_lock); + + return n; +} + +struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max) +{ + struct au_sbinfo *sbi; + + sbi = au_sbi(sb); + *max = au_lcnt_read(&sbi->si_ninodes, /*do_rev*/1); + return au_array_alloc(max, au_iarray_cb, sb, &sb->s_inodes); +} + +void au_iarray_free(struct inode **a, unsigned long long max) +{ + unsigned long long ull; + + for (ull = 0; ull < max; ull++) + iput(a[ull]); + kvfree(a); +} + +/* ---------------------------------------------------------------------- */ + +/* + * refresh dentry and inode at remount time. + */ +/* todo: consolidate with simple_reval_dpath() and au_reval_for_attr() */ +static int au_do_refresh(struct dentry *dentry, unsigned int dir_flags, + struct dentry *parent) +{ + int err; + + di_write_lock_child(dentry); + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(dentry, parent); + if (!err && dir_flags) + au_hn_reset(d_inode(dentry), dir_flags); + di_read_unlock(parent, AuLock_IR); + di_write_unlock(dentry); + + return err; +} + +static int au_do_refresh_d(struct dentry *dentry, unsigned int sigen, + struct au_sbinfo *sbinfo, + const unsigned int dir_flags, unsigned int do_idop) +{ + int err; + struct dentry *parent; + + err = 0; + parent = dget_parent(dentry); + if (!au_digen_test(parent, sigen) && au_digen_test(dentry, sigen)) { + if (d_really_is_positive(dentry)) { + if (!d_is_dir(dentry)) + err = au_do_refresh(dentry, /*dir_flags*/0, + parent); + else { + err = au_do_refresh(dentry, dir_flags, parent); + if (unlikely(err)) + au_fset_si(sbinfo, FAILED_REFRESH_DIR); + } + } else + err = au_do_refresh(dentry, /*dir_flags*/0, parent); + AuDbgDentry(dentry); + } + dput(parent); + + if (!err) { + if (do_idop) + au_refresh_dop(dentry, /*force_reval*/0); + } else + au_refresh_dop(dentry, /*force_reval*/1); + + AuTraceErr(err); + return err; +} + +static int au_refresh_d(struct super_block *sb, unsigned int do_idop) +{ + int err, i, j, ndentry, e; + unsigned int sigen; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries, *d; + struct au_sbinfo *sbinfo; + struct dentry *root = sb->s_root; + const unsigned int dir_flags = au_hi_flags(d_inode(root), /*isdir*/1); + + if (do_idop) + au_refresh_dop(root, /*force_reval*/0); + + 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; + + sigen = au_sigen(sb); + sbinfo = au_sbi(sb); + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + d = dentries[j]; + e = au_do_refresh_d(d, sigen, sbinfo, dir_flags, + do_idop); + if (unlikely(e && !err)) + err = e; + /* go on even err */ + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static int au_refresh_i(struct super_block *sb, unsigned int do_idop) +{ + int err, e; + unsigned int sigen; + unsigned long long max, ull; + struct inode *inode, **array; + + array = au_iarray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + sigen = au_sigen(sb); + for (ull = 0; ull < max; ull++) { + inode = array[ull]; + if (unlikely(!inode)) + break; + + e = 0; + ii_write_lock_child(inode); + if (au_iigen(inode, NULL) != sigen) { + e = au_refresh_hinode_self(inode); + if (unlikely(e)) { + au_refresh_iop(inode, /*force_getattr*/1); + pr_err("error %d, i%lu\n", e, inode->i_ino); + if (!err) + err = e; + /* go on even if err */ + } + } + if (!e && do_idop) + au_refresh_iop(inode, /*force_getattr*/0); + ii_write_unlock(inode); + } + + au_iarray_free(array, max); + +out: + return err; +} + +static void au_remount_refresh(struct super_block *sb, unsigned int do_idop) +{ + int err, e; + unsigned int udba; + aufs_bindex_t bindex, bbot; + struct dentry *root; + struct inode *inode; + struct au_branch *br; + struct au_sbinfo *sbi; + + au_sigen_inc(sb); + sbi = au_sbi(sb); + au_fclr_si(sbi, FAILED_REFRESH_DIR); + + root = sb->s_root; + DiMustNoWaiters(root); + inode = d_inode(root); + IiMustNoWaiters(inode); + + udba = au_opt_udba(sb); + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_hnotify_reset_br(udba, br, br->br_perm); + if (unlikely(err)) + AuIOErr("hnotify failed on br %d, %d, ignored\n", + bindex, err); + /* go on even if err */ + } + au_hn_reset(inode, au_hi_flags(inode, /*isdir*/1)); + + if (do_idop) { + if (au_ftest_si(sbi, NO_DREVAL)) { + AuDebugOn(sb->s_d_op == &aufs_dop_noreval); + sb->s_d_op = &aufs_dop_noreval; + AuDebugOn(sbi->si_iop_array == aufs_iop_nogetattr); + sbi->si_iop_array = aufs_iop_nogetattr; + } else { + AuDebugOn(sb->s_d_op == &aufs_dop); + sb->s_d_op = &aufs_dop; + AuDebugOn(sbi->si_iop_array == aufs_iop); + sbi->si_iop_array = aufs_iop; + } + pr_info("reset to %ps and %ps\n", + sb->s_d_op, sbi->si_iop_array); + } + + di_write_unlock(root); + err = au_refresh_d(sb, do_idop); + e = au_refresh_i(sb, do_idop); + if (unlikely(e && !err)) + err = e; + /* aufs_write_lock() calls ..._child() */ + di_write_lock_child(root); + + au_cpup_attr_all(inode, /*force*/1); + + if (unlikely(err)) + AuIOErr("refresh failed, ignored, %d\n", err); +} + +/* 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, do_dx; + unsigned int mntflags; + struct au_opts opts = { + .opt = NULL + }; + struct dentry *root; + struct inode *inode; + struct au_sbinfo *sbinfo; + + err = 0; + root = sb->s_root; + if (!data || !*data) { + err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (!err) { + di_write_lock_child(root); + err = au_opts_verify(sb, *flags, /*pending*/0); + aufs_write_unlock(root); + } + goto out; + } + + err = -ENOMEM; + 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 = d_inode(root); + inode_lock(inode); + err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_mtx; + di_write_lock_child(root); + + /* au_opts_remount() may return an error */ + err = au_opts_remount(sb, &opts); + au_opts_free(&opts); + + if (au_ftest_opts(opts.flags, REFRESH)) + au_remount_refresh(sb, au_ftest_opts(opts.flags, REFRESH_IDOP)); + + if (au_ftest_opts(opts.flags, REFRESH_DYAOP)) { + mntflags = au_mntflags(sb); + do_dx = !!au_opt_test(mntflags, DIO); + au_dy_arefresh(do_dx); + } + + au_fhsm_wrote_all(sb, /*force*/1); /* ?? */ + aufs_write_unlock(root); + +out_mtx: + inode_unlock(inode); +out_opts: + free_page((unsigned long)opts.opt); +out: + err = cvt_err(err); + AuTraceErr(err); + return err; +} + +static const struct super_operations aufs_sop = { + .alloc_inode = aufs_alloc_inode, + .destroy_inode = aufs_destroy_inode, + .free_inode = aufs_free_inode, + /* always deleting, no clearing */ + .drop_inode = generic_delete_inode, + .show_options = aufs_show_options, + .statfs = aufs_statfs, + .put_super = aufs_put_super, + .sync_fs = aufs_sync_fs, + .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_iop + AuIop_DIR; /* with getattr by default */ + inode->i_fop = &aufs_dir_fop; + inode->i_mode = S_IFDIR; + set_nlink(inode, 2); + unlock_new_inode(inode); + + root = d_make_root(inode); + if (unlikely(!root)) + goto out; + err = PTR_ERR(root); + if (IS_ERR(root)) + goto out; + + err = au_di_init(root); + if (!err) { + sb->s_root = root; + return 0; /* success */ + } + dput(root); + +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 = { + .opt = NULL + }; + struct au_sbinfo *sbinfo; + struct dentry *root; + struct inode *inode; + char *arg = raw_data; + + if (unlikely(!arg || !*arg)) { + err = -EINVAL; + pr_err("no arg\n"); + goto out; + } + + err = -ENOMEM; + 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; + sbinfo = au_sbi(sb); + + /* all timestamps always follow the ones on the branch */ + sb->s_flags |= SB_NOATIME | SB_NODIRATIME; + sb->s_flags |= SB_I_VERSION; /* do we really need this? */ + sb->s_op = &aufs_sop; + sb->s_d_op = &aufs_dop; + sb->s_magic = AUFS_SUPER_MAGIC; + sb->s_maxbytes = 0; + sb->s_stack_depth = 1; + au_export_init(sb); + au_xattr_init(sb); + + err = alloc_root(sb); + if (unlikely(err)) { + si_write_unlock(sb); + goto out_info; + } + root = sb->s_root; + inode = d_inode(root); + + /* + * 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. */ + inode_lock(inode); + aufs_write_lock(root); + err = au_opts_mount(sb, &opts); + au_opts_free(&opts); + if (!err && au_ftest_si(sbinfo, NO_DREVAL)) { + sb->s_d_op = &aufs_dop_noreval; + pr_info("%ps\n", sb->s_d_op); + au_refresh_dop(root, /*force_reval*/0); + sbinfo->si_iop_array = aufs_iop_nogetattr; + au_refresh_iop(inode, /*force_getattr*/0); + } + aufs_write_unlock(root); + inode_unlock(inode); + if (!err) + goto out_opts; /* success */ + +out_root: + dput(root); + sb->s_root = NULL; +out_info: + kobject_put(&sbinfo->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 struct dentry *aufs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name __maybe_unused, + void *raw_data) +{ + struct dentry *root; + + /* all timestamps always follow the ones on the branch */ + /* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */ + root = mount_nodev(fs_type, flags, raw_data, aufs_fill_super); + if (IS_ERR(root)) + goto out; + + au_sbilist_add(root->d_sb); + +out: + return root; +} + +static void aufs_kill_sb(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + sbinfo = au_sbi(sb); + if (sbinfo) { + au_sbilist_del(sb); + aufs_write_lock(sb->s_root); + au_fhsm_fin(sb); + if (sbinfo->si_wbr_create_ops->fin) + sbinfo->si_wbr_create_ops->fin(sb); + if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) { + au_opt_set_udba(sbinfo->si_mntflags, UDBA_NONE); + au_remount_refresh(sb, /*do_idop*/0); + } + if (au_opt_test(sbinfo->si_mntflags, PLINK)) + au_plink_put(sb, /*verbose*/1); + au_xino_clr(sb); + au_dr_opt_flush(sb); + sbinfo->si_sb = NULL; + aufs_write_unlock(sb->s_root); + au_nwt_flush(&sbinfo->si_nowait); + } + kill_anon_super(sb); +} + +struct file_system_type aufs_fs_type = { + .name = AUFS_FSTYPE, + /* a race between rename and others */ + .fs_flags = FS_RENAME_DOES_D_MOVE, + .mount = aufs_mount, + .kill_sb = aufs_kill_sb, + /* no need to __module_get() and module_put(). */ + .owner = THIS_MODULE, +}; diff --git a/fs/aufs/super.h b/fs/aufs/super.h new file mode 100644 index 000000000000..c0cb0051242c --- /dev/null +++ b/fs/aufs/super.h @@ -0,0 +1,589 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * super_block operations + */ + +#ifndef __AUFS_SUPER_H__ +#define __AUFS_SUPER_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/kobject.h> +#include "hbl.h" +#include "lcnt.h" +#include "rwsem.h" +#include "wkq.h" + +/* policies to select one among multiple writable branches */ +struct au_wbr_copyup_operations { + int (*copyup)(struct dentry *dentry); +}; + +#define AuWbr_DIR 1 /* target is a dir */ +#define AuWbr_PARENT (1 << 1) /* always require a parent */ + +#define au_ftest_wbr(flags, name) ((flags) & AuWbr_##name) +#define au_fset_wbr(flags, name) { (flags) |= AuWbr_##name; } +#define au_fclr_wbr(flags, name) { (flags) &= ~AuWbr_##name; } + +struct au_wbr_create_operations { + int (*create)(struct dentry *dentry, unsigned int flags); + 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; +}; + +#define AuPlink_NHASH 100 +static inline int au_plink_hash(ino_t ino) +{ + return ino % AuPlink_NHASH; +} + +/* File-based Hierarchical Storage Management */ +struct au_fhsm { +#ifdef CONFIG_AUFS_FHSM + /* allow only one process who can receive the notification */ + spinlock_t fhsm_spin; + pid_t fhsm_pid; + wait_queue_head_t fhsm_wqh; + atomic_t fhsm_readable; + + /* these are protected by si_rwsem */ + unsigned long fhsm_expire; + aufs_bindex_t fhsm_bottom; +#endif +}; + +struct au_branch; +struct au_sbinfo { + /* nowait tasks in the system-wide workqueue */ + struct au_nowait_tasks si_nowait; + + /* + * tried sb->s_umount, but failed due to the dependency between i_mutex. + * rwsem for au_sbinfo is necessary. + */ + struct au_rwsem si_rwsem; + + /* + * dirty approach to protect sb->sb_inodes and ->s_files (gone) from + * remount. + */ + au_lcnt_t si_ninodes, si_nfiles; + + /* branch management */ + unsigned int si_generation; + + /* see AuSi_ flags */ + unsigned char au_si_status; + + aufs_bindex_t si_bbot; + + /* dirty trick to keep br_id plus */ + unsigned int si_last_br_id : + sizeof(aufs_bindex_t) * BITS_PER_BYTE - 1; + 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; + + /* File-based Hierarchical Storage Management */ + struct au_fhsm si_fhsm; + + /* mount flags */ + /* include/asm-ia64/siginfo.h defines a macro named si_flags */ + unsigned int si_mntflags; + + /* external inode number (bitmap and translation table) */ + vfs_readf_t si_xread; + vfs_writef_t si_xwrite; + loff_t si_ximaxent; /* max entries in a xino */ + + 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; + + unsigned long si_xino_jiffy; + unsigned long si_xino_expire; + /* reserved for future use */ + /* unsigned long long si_xib_limit; */ /* Max xib file size */ + +#ifdef CONFIG_AUFS_EXPORT + /* i_generation */ + /* todo: make xigen file an array to support many inode numbers */ + struct file *si_xigen; + atomic_t si_xigen_next; +#endif + + /* dirty trick to support atomic_open */ + struct hlist_bl_head si_aopen; + + /* vdir parameters */ + unsigned long si_rdcache; /* max cache time in jiffies */ + unsigned int si_rdblk; /* deblk size */ + unsigned int si_rdhash; /* hash size */ + + /* + * 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; + + /* pseudo_link list */ + struct hlist_bl_head si_plink[AuPlink_NHASH]; + wait_queue_head_t si_plink_wq; + spinlock_t si_plink_maint_lock; + pid_t si_plink_maint_pid; + + /* file list */ + struct hlist_bl_head si_files; + + /* with/without getattr, brother of sb->s_d_op */ + const struct inode_operations *si_iop_array; + + /* + * sysfs and lifetime management. + * this is not a small structure and it may be a waste of memory in case + * of sysfs is disabled, particularly when many aufs-es are mounted. + * but using sysfs is majority. + */ + struct kobject si_kobj; +#ifdef CONFIG_DEBUG_FS + struct dentry *si_dbgaufs; + struct dentry *si_dbgaufs_plink; + struct dentry *si_dbgaufs_xib; +#ifdef CONFIG_AUFS_EXPORT + struct dentry *si_dbgaufs_xigen; +#endif +#endif + +#ifdef CONFIG_AUFS_SBILIST + struct hlist_bl_node si_list; +#endif + + /* dirty, necessary for unmounting, sysfs and sysrq */ + struct super_block *si_sb; +}; + +/* 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 unnecessary + */ +#define AuSi_FAILED_REFRESH_DIR 1 +#define AuSi_FHSM (1 << 1) /* fhsm is active now */ +#define AuSi_NO_DREVAL (1 << 2) /* disable all d_revalidate */ + +#ifndef CONFIG_AUFS_FHSM +#undef AuSi_FHSM +#define AuSi_FHSM 0 +#endif + +static inline unsigned char au_do_ftest_si(struct au_sbinfo *sbi, + unsigned int flag) +{ + AuRwMustAnyLock(&sbi->si_rwsem); + return sbi->au_si_status & flag; +} +#define au_ftest_si(sbinfo, name) au_do_ftest_si(sbinfo, AuSi_##name) +#define au_fset_si(sbinfo, name) do { \ + AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ + (sbinfo)->au_si_status |= AuSi_##name; \ +} while (0) +#define au_fclr_si(sbinfo, name) do { \ + AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ + (sbinfo)->au_si_status &= ~AuSi_##name; \ +} while (0) + +/* ---------------------------------------------------------------------- */ + +/* policy to select one among writable branches */ +#define AuWbrCopyup(sbinfo, ...) \ + ((sbinfo)->si_wbr_copyup_ops->copyup(__VA_ARGS__)) +#define AuWbrCreate(sbinfo, ...) \ + ((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__)) + +/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */ +#define AuLock_DW 1 /* write-lock dentry */ +#define AuLock_IR (1 << 1) /* read-lock inode */ +#define AuLock_IW (1 << 2) /* write-lock inode */ +#define AuLock_FLUSH (1 << 3) /* wait for 'nowait' tasks */ +#define AuLock_DIRS (1 << 4) /* target is a pair of dirs */ + /* except RENAME_EXCHANGE */ +#define AuLock_NOPLM (1 << 5) /* return err in plm mode */ +#define AuLock_NOPLMW (1 << 6) /* wait for plm mode ends */ +#define AuLock_GEN (1 << 7) /* test digen/iigen */ +#define au_ftest_lock(flags, name) ((flags) & AuLock_##name) +#define au_fset_lock(flags, name) \ + do { (flags) |= AuLock_##name; } while (0) +#define au_fclr_lock(flags, name) \ + do { (flags) &= ~AuLock_##name; } while (0) + +/* ---------------------------------------------------------------------- */ + +/* super.c */ +extern struct file_system_type aufs_fs_type; +struct inode *au_iget_locked(struct super_block *sb, ino_t ino); +typedef unsigned long long (*au_arraycb_t)(struct super_block *sb, void *array, + unsigned long long max, void *arg); +void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, + struct super_block *sb, void *arg); +struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max); +void au_iarray_free(struct inode **a, unsigned long long max); + +/* 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, int may_shrink); + +unsigned int au_sigen_inc(struct super_block *sb); +aufs_bindex_t au_new_br_id(struct super_block *sb); + +int si_read_lock(struct super_block *sb, int flags); +int si_write_lock(struct super_block *sb, int flags); +int 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); +int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags); +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); +int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex); +int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop); + +/* mvdown.c */ +int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *arg); + +#ifdef CONFIG_AUFS_FHSM +/* fhsm.c */ + +static inline pid_t au_fhsm_pid(struct au_fhsm *fhsm) +{ + pid_t pid; + + spin_lock(&fhsm->fhsm_spin); + pid = fhsm->fhsm_pid; + spin_unlock(&fhsm->fhsm_spin); + + return pid; +} + +void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force); +void au_fhsm_wrote_all(struct super_block *sb, int force); +int au_fhsm_fd(struct super_block *sb, int oflags); +int au_fhsm_br_alloc(struct au_branch *br); +void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex); +void au_fhsm_fin(struct super_block *sb); +void au_fhsm_init(struct au_sbinfo *sbinfo); +void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec); +void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo); +#else +AuStubVoid(au_fhsm_wrote, struct super_block *sb, aufs_bindex_t bindex, + int force) +AuStubVoid(au_fhsm_wrote_all, struct super_block *sb, int force) +AuStub(int, au_fhsm_fd, return -EOPNOTSUPP, struct super_block *sb, int oflags) +AuStub(pid_t, au_fhsm_pid, return 0, struct au_fhsm *fhsm) +AuStubInt0(au_fhsm_br_alloc, struct au_branch *br) +AuStubVoid(au_fhsm_set_bottom, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(au_fhsm_fin, struct super_block *sb) +AuStubVoid(au_fhsm_init, struct au_sbinfo *sbinfo) +AuStubVoid(au_fhsm_set, struct au_sbinfo *sbinfo, unsigned int sec) +AuStubVoid(au_fhsm_show, struct seq_file *seq, struct au_sbinfo *sbinfo) +#endif + +/* ---------------------------------------------------------------------- */ + +static inline struct au_sbinfo *au_sbi(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_EXPORT +int au_test_nfsd(void); +void au_export_init(struct super_block *sb); +void au_xigen_inc(struct inode *inode); +int au_xigen_new(struct inode *inode); +int au_xigen_set(struct super_block *sb, struct path *path); +void au_xigen_clr(struct super_block *sb); + +static inline int au_busy_or_stale(void) +{ + if (!au_test_nfsd()) + return -EBUSY; + return -ESTALE; +} +#else +AuStubInt0(au_test_nfsd, void) +AuStubVoid(au_export_init, struct super_block *sb) +AuStubVoid(au_xigen_inc, struct inode *inode) +AuStubInt0(au_xigen_new, struct inode *inode) +AuStubInt0(au_xigen_set, struct super_block *sb, struct path *path) +AuStubVoid(au_xigen_clr, struct super_block *sb) +AuStub(int, au_busy_or_stale, return -EBUSY, void) +#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_SBILIST +/* module.c */ +extern struct hlist_bl_head au_sbilist; + +static inline void au_sbilist_init(void) +{ + INIT_HLIST_BL_HEAD(&au_sbilist); +} + +static inline void au_sbilist_add(struct super_block *sb) +{ + au_hbl_add(&au_sbi(sb)->si_list, &au_sbilist); +} + +static inline void au_sbilist_del(struct super_block *sb) +{ + au_hbl_del(&au_sbi(sb)->si_list, &au_sbilist); +} + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +static inline void au_sbilist_lock(void) +{ + hlist_bl_lock(&au_sbilist); +} + +static inline void au_sbilist_unlock(void) +{ + hlist_bl_unlock(&au_sbilist); +} +#define AuGFP_SBILIST GFP_ATOMIC +#else +AuStubVoid(au_sbilist_lock, void) +AuStubVoid(au_sbilist_unlock, void) +#define AuGFP_SBILIST GFP_NOFS +#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ +#else +AuStubVoid(au_sbilist_init, void) +AuStubVoid(au_sbilist_add, struct super_block *sb) +AuStubVoid(au_sbilist_del, struct super_block *sb) +AuStubVoid(au_sbilist_lock, void) +AuStubVoid(au_sbilist_unlock, void) +#define AuGFP_SBILIST GFP_NOFS +#endif + +/* ---------------------------------------------------------------------- */ + +static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo) +{ + /* + * This function is a dynamic '__init' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ +#ifdef CONFIG_DEBUG_FS + sbinfo->si_dbgaufs = NULL; + sbinfo->si_dbgaufs_plink = NULL; + sbinfo->si_dbgaufs_xib = NULL; +#ifdef CONFIG_AUFS_EXPORT + sbinfo->si_dbgaufs_xigen = NULL; +#endif +#endif +} + +/* ---------------------------------------------------------------------- */ + +/* current->atomic_flags */ +/* this value should never corrupt the ones defined in linux/sched.h */ +#define PFA_AUFS 0x10 + +TASK_PFA_TEST(AUFS, test_aufs) /* task_test_aufs */ +TASK_PFA_SET(AUFS, aufs) /* task_set_aufs */ +TASK_PFA_CLEAR(AUFS, aufs) /* task_clear_aufs */ + +static inline int si_pid_test(struct super_block *sb) +{ + return !!task_test_aufs(current); +} + +static inline void si_pid_clr(struct super_block *sb) +{ + AuDebugOn(!task_test_aufs(current)); + task_clear_aufs(current); +} + +static inline void si_pid_set(struct super_block *sb) +{ + AuDebugOn(task_test_aufs(current)); + task_set_aufs(current); +} + +/* ---------------------------------------------------------------------- */ + +/* lock superblock. mainly for entry point functions */ +#define __si_read_lock(sb) au_rw_read_lock(&au_sbi(sb)->si_rwsem) +#define __si_write_lock(sb) au_rw_write_lock(&au_sbi(sb)->si_rwsem) +#define __si_read_trylock(sb) au_rw_read_trylock(&au_sbi(sb)->si_rwsem) +#define __si_write_trylock(sb) au_rw_write_trylock(&au_sbi(sb)->si_rwsem) +/* +#define __si_read_trylock_nested(sb) \ + au_rw_read_trylock_nested(&au_sbi(sb)->si_rwsem) +#define __si_write_trylock_nested(sb) \ + au_rw_write_trylock_nested(&au_sbi(sb)->si_rwsem) +*/ + +#define __si_read_unlock(sb) au_rw_read_unlock(&au_sbi(sb)->si_rwsem) +#define __si_write_unlock(sb) au_rw_write_unlock(&au_sbi(sb)->si_rwsem) +#define __si_downgrade_lock(sb) au_rw_dgrade_lock(&au_sbi(sb)->si_rwsem) + +#define SiMustNoWaiters(sb) AuRwMustNoWaiters(&au_sbi(sb)->si_rwsem) +#define SiMustAnyLock(sb) AuRwMustAnyLock(&au_sbi(sb)->si_rwsem) +#define SiMustWriteLock(sb) AuRwMustWriteLock(&au_sbi(sb)->si_rwsem) + +static inline void si_noflush_read_lock(struct super_block *sb) +{ + __si_read_lock(sb); + si_pid_set(sb); +} + +static inline int si_noflush_read_trylock(struct super_block *sb) +{ + int locked; + + locked = __si_read_trylock(sb); + if (locked) + si_pid_set(sb); + return locked; +} + +static inline void si_noflush_write_lock(struct super_block *sb) +{ + __si_write_lock(sb); + si_pid_set(sb); +} + +static inline int si_noflush_write_trylock(struct super_block *sb) +{ + int locked; + + locked = __si_write_trylock(sb); + if (locked) + si_pid_set(sb); + return locked; +} + +#if 0 /* reserved */ +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); +} +#endif + +static inline void si_read_unlock(struct super_block *sb) +{ + si_pid_clr(sb); + __si_read_unlock(sb); +} + +#if 0 /* reserved */ +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); +} +#endif + +static inline void si_write_unlock(struct super_block *sb) +{ + si_pid_clr(sb); + __si_write_unlock(sb); +} + +#if 0 /* reserved */ +static inline void si_downgrade_lock(struct super_block *sb) +{ + __si_downgrade_lock(sb); +} +#endif + +/* ---------------------------------------------------------------------- */ + +static inline aufs_bindex_t au_sbbot(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_bbot; +} + +static inline unsigned int au_mntflags(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_mntflags; +} + +static inline unsigned int au_sigen(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_generation; +} + +static inline struct au_branch *au_sbr(struct super_block *sb, + aufs_bindex_t bindex) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_branch[0 + bindex]; +} + +static inline loff_t au_xi_maxent(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_ximaxent; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_SUPER_H__ */ diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c new file mode 100644 index 000000000000..f615471231b5 --- /dev/null +++ b/fs/aufs/sysaufs.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sysfs interface and lifetime management + * they are necessary regardless sysfs is disabled. + */ + +#include <linux/random.h> +#include "aufs.h" + +unsigned long sysaufs_si_mask; +struct kset *sysaufs_kset; + +#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 const 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_kset; + /* cf. sysaufs_name() */ + err = kobject_init_and_add + (&sbinfo->si_kobj, &au_sbi_ktype, /*&sysaufs_kset->kobj*/NULL, + SysaufsSiNamePrefix "%lx", sysaufs_si_id(sbinfo)); + + return err; +} + +void sysaufs_fin(void) +{ + sysfs_remove_group(&sysaufs_kset->kobj, sysaufs_attr_group); + kset_unregister(sysaufs_kset); +} + +int __init sysaufs_init(void) +{ + int err; + + do { + get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask)); + } while (!sysaufs_si_mask); + + err = -EINVAL; + sysaufs_kset = kset_create_and_add(AUFS_NAME, NULL, fs_kobj); + if (unlikely(!sysaufs_kset)) + goto out; + err = PTR_ERR(sysaufs_kset); + if (IS_ERR(sysaufs_kset)) + goto out; + err = sysfs_create_group(&sysaufs_kset->kobj, sysaufs_attr_group); + if (unlikely(err)) + kset_unregister(sysaufs_kset); + +out: + return err; +} diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h new file mode 100644 index 000000000000..55c5c9868f3b --- /dev/null +++ b/fs/aufs/sysaufs.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sysfs interface and mount lifetime management + */ + +#ifndef __SYSAUFS_H__ +#define __SYSAUFS_H__ + +#ifdef __KERNEL__ + +#include <linux/sysfs.h> +#include "module.h" + +struct super_block; +struct au_sbinfo; + +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_kset; +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); +long au_brinfo_ioctl(struct file *file, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_brinfo_compat_ioctl(struct file *file, unsigned long arg); +#endif + +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 + +AuStubInt0(sysaufs_si_xi_path, struct seq_file *seq, struct super_block *sb) +AuStub(ssize_t, sysaufs_si_show, return 0, struct kobject *kobj, + struct attribute *attr, char *buf) +AuStubVoid(sysaufs_br_init, struct au_branch *br) +AuStubVoid(sysaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(sysaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) + +static inline void sysaufs_brs_init(void) +{ + sysaufs_brs = 0; +} + +#endif /* CONFIG_SYSFS */ + +#endif /* __KERNEL__ */ +#endif /* __SYSAUFS_H__ */ diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c new file mode 100644 index 000000000000..46638d88ef21 --- /dev/null +++ b/fs/aufs/sysfs.c @@ -0,0 +1,374 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sysfs interface + */ + +#include <linux/compat.h> +#include <linux/seq_file.h> +#include "aufs.h" + +#ifdef CONFIG_AUFS_FS_MODULE +/* this entry violates the "one line per file" policy of sysfs */ +static ssize_t config_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + ssize_t err; + static char *conf = +/* this file is generated at compiling */ +#include "conf.str" + ; + + err = snprintf(buf, PAGE_SIZE, conf); + if (unlikely(err >= PAGE_SIZE)) + err = -EFBIG; + return err; +} + +static struct kobj_attribute au_config_attr = __ATTR_RO(config); +#endif + +static struct attribute *au_attr[] = { +#ifdef CONFIG_AUFS_FS_MODULE + &au_config_attr.attr, +#endif + 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; + + SiMustAnyLock(sb); + + 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, int idx) +{ + int err; + struct path path; + struct dentry *root; + struct au_branch *br; + au_br_perm_str_t perm; + + AuDbg("b%d\n", bindex); + + err = 0; + root = sb->s_root; + di_read_lock_parent(root, !AuLock_IR); + br = au_sbr(sb, bindex); + + switch (idx) { + case AuBrSysfs_BR: + path.mnt = au_br_mnt(br); + path.dentry = au_h_dptr(root, bindex); + err = au_seq_path(seq, &path); + if (!err) { + au_optstr_br_perm(&perm, br->br_perm); + seq_printf(seq, "=%s\n", perm.a); + } + break; + case AuBrSysfs_BRID: + seq_printf(seq, "%d\n", br->br_id); + break; + } + di_read_unlock(root, !AuLock_IR); + if (unlikely(err || seq_has_overflowed(seq))) + err = -E2BIG; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +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" +#define SysaufsBrid_PREFIX "brid" + +/* todo: file size may exceed PAGE_SIZE */ +ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + ssize_t err; + int idx; + long l; + aufs_bindex_t bbot; + 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; + + /* + * prevent a race condition between sysfs and aufs. + * for instance, sysfs_file_read() calls sysfs_get_active_two() which + * prohibits maintaining the sysfs entries. + * hew we acquire read lock after sysfs_get_active_two(). + * on the other hand, the remount process may maintain the sysfs/aufs + * entries after acquiring write lock. + * it can cause a deadlock. + * simply we gave up processing read here. + */ + err = -EBUSY; + if (unlikely(!si_noflush_read_trylock(sb))) + goto out; + + seq = au_seq(buf, PAGE_SIZE); + err = PTR_ERR(seq); + if (IS_ERR(seq)) + goto out_unlock; + + 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++; + } + + if (!strncmp(name, SysaufsBrid_PREFIX, + sizeof(SysaufsBrid_PREFIX) - 1)) { + idx = AuBrSysfs_BRID; + name += sizeof(SysaufsBrid_PREFIX) - 1; + } else if (!strncmp(name, SysaufsBr_PREFIX, + sizeof(SysaufsBr_PREFIX) - 1)) { + idx = AuBrSysfs_BR; + name += sizeof(SysaufsBr_PREFIX) - 1; + } else + BUG(); + + err = kstrtol(name, 10, &l); + if (!err) { + bbot = au_sbbot(sb); + if (l <= bbot) + err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l, idx); + else + err = -ENOENT; + } + +out_seq: + if (!err) { + err = seq->count; + /* sysfs limit */ + if (unlikely(err == PAGE_SIZE)) + err = -EFBIG; + } + au_kfree_rcu(seq); +out_unlock: + si_read_unlock(sb); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_brinfo(struct super_block *sb, union aufs_brinfo __user *arg) +{ + int err; + int16_t brid; + aufs_bindex_t bindex, bbot; + size_t sz; + char *buf; + struct seq_file *seq; + struct au_branch *br; + + si_read_lock(sb, AuLock_FLUSH); + bbot = au_sbbot(sb); + err = bbot + 1; + if (!arg) + goto out; + + err = -ENOMEM; + buf = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!buf)) + goto out; + + seq = au_seq(buf, PAGE_SIZE); + err = PTR_ERR(seq); + if (IS_ERR(seq)) + goto out_buf; + + sz = sizeof(*arg) - offsetof(union aufs_brinfo, path); + for (bindex = 0; bindex <= bbot; bindex++, arg++) { + /* VERIFY_WRITE */ + err = !access_ok(arg, sizeof(*arg)); + if (unlikely(err)) + break; + + br = au_sbr(sb, bindex); + brid = br->br_id; + BUILD_BUG_ON(sizeof(brid) != sizeof(arg->id)); + err = __put_user(brid, &arg->id); + if (unlikely(err)) + break; + + BUILD_BUG_ON(sizeof(br->br_perm) != sizeof(arg->perm)); + err = __put_user(br->br_perm, &arg->perm); + if (unlikely(err)) + break; + + err = au_seq_path(seq, &br->br_path); + if (unlikely(err)) + break; + seq_putc(seq, '\0'); + if (!seq_has_overflowed(seq)) { + err = copy_to_user(arg->path, seq->buf, seq->count); + seq->count = 0; + if (unlikely(err)) + break; + } else { + err = -E2BIG; + goto out_seq; + } + } + if (unlikely(err)) + err = -EFAULT; + +out_seq: + au_kfree_rcu(seq); +out_buf: + free_page((unsigned long)buf); +out: + si_read_unlock(sb); + return err; +} + +long au_brinfo_ioctl(struct file *file, unsigned long arg) +{ + return au_brinfo(file->f_path.dentry->d_sb, (void __user *)arg); +} + +#ifdef CONFIG_COMPAT +long au_brinfo_compat_ioctl(struct file *file, unsigned long arg) +{ + return au_brinfo(file->f_path.dentry->d_sb, compat_ptr(arg)); +} +#endif + +/* ---------------------------------------------------------------------- */ + +void sysaufs_br_init(struct au_branch *br) +{ + int i; + struct au_brsysfs *br_sysfs; + struct attribute *attr; + + br_sysfs = br->br_sysfs; + for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { + attr = &br_sysfs->attr; + sysfs_attr_init(attr); + attr->name = br_sysfs->name; + attr->mode = 0444; + br_sysfs++; + } +} + +void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ + struct au_branch *br; + struct kobject *kobj; + struct au_brsysfs *br_sysfs; + int i; + aufs_bindex_t bbot; + + if (!sysaufs_brs) + return; + + kobj = &au_sbi(sb)->si_kobj; + bbot = au_sbbot(sb); + for (; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + br_sysfs = br->br_sysfs; + for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { + sysfs_remove_file(kobj, &br_sysfs->attr); + br_sysfs++; + } + } +} + +void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) +{ + int err, i; + aufs_bindex_t bbot; + struct kobject *kobj; + struct au_branch *br; + struct au_brsysfs *br_sysfs; + + if (!sysaufs_brs) + return; + + kobj = &au_sbi(sb)->si_kobj; + bbot = au_sbbot(sb); + for (; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + br_sysfs = br->br_sysfs; + snprintf(br_sysfs[AuBrSysfs_BR].name, sizeof(br_sysfs->name), + SysaufsBr_PREFIX "%d", bindex); + snprintf(br_sysfs[AuBrSysfs_BRID].name, sizeof(br_sysfs->name), + SysaufsBrid_PREFIX "%d", bindex); + for (i = 0; i < ARRAY_SIZE(br->br_sysfs); i++) { + err = sysfs_create_file(kobj, &br_sysfs->attr); + if (unlikely(err)) + pr_warn("failed %s under sysfs(%d)\n", + br_sysfs->name, err); + br_sysfs++; + } + } +} diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c new file mode 100644 index 000000000000..fc8aa4a2839f --- /dev/null +++ b/fs/aufs/sysrq.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * magic sysrq handler + */ + +/* #include <linux/sysrq.h> */ +#include <linux/writeback.h> +#include "aufs.h" + +/* ---------------------------------------------------------------------- */ + +static void sysrq_sb(struct super_block *sb) +{ + char *plevel; + struct au_sbinfo *sbinfo; + struct file *file; + struct hlist_bl_head *files; + struct hlist_bl_node *pos; + struct au_finfo *finfo; + struct inode *i; + + plevel = au_plevel; + au_plevel = KERN_WARNING; + + /* since we define pr_fmt, call printk directly */ +#define pr(str) printk(KERN_WARNING AUFS_NAME ": " str) + + sbinfo = au_sbi(sb); + printk(KERN_WARNING "si=%lx\n", sysaufs_si_id(sbinfo)); + pr("superblock\n"); + au_dpri_sb(sb); + +#if 0 /* reserved */ + do { + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + + err = au_dpages_init(&dpages, GFP_ATOMIC); + if (unlikely(err)) + break; + err = au_dcsub_pages(&dpages, sb->s_root, NULL, NULL); + if (!err) + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) + au_dpri_dentry(dpage->dentries[j]); + } + au_dpages_free(&dpages); + } while (0); +#endif + + pr("isolated inode\n"); + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(i, &sb->s_inodes, i_sb_list) { + spin_lock(&i->i_lock); + if (hlist_empty(&i->i_dentry)) + au_dpri_inode(i); + spin_unlock(&i->i_lock); + } + spin_unlock(&sb->s_inode_list_lock); + + pr("files\n"); + files = &au_sbi(sb)->si_files; + hlist_bl_lock(files); + hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { + umode_t mode; + + file = finfo->fi_file; + mode = file_inode(file)->i_mode; + if (!special_file(mode)) + au_dpri_file(file); + } + hlist_bl_unlock(files); + pr("done\n"); + +#undef pr + au_plevel = plevel; +} + +/* ---------------------------------------------------------------------- */ + +/* module parameter */ +static char *aufs_sysrq_key = "a"; +module_param_named(sysrq, aufs_sysrq_key, charp, 0444); +MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME); + +static void au_sysrq(int key __maybe_unused) +{ + struct au_sbinfo *sbinfo; + struct hlist_bl_node *pos; + + lockdep_off(); + au_sbilist_lock(); + hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) + sysrq_sb(sbinfo->si_sb); + au_sbilist_unlock(); + lockdep_on(); +} + +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)) + pr_err("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)) + pr_err("err %d (ignored)\n", err); +} diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c new file mode 100644 index 000000000000..5ba006b80724 --- /dev/null +++ b/fs/aufs/vdir.c @@ -0,0 +1,896 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * virtual or vertical directory + */ + +#include <linux/iversion.h> +#include "aufs.h" + +static unsigned int calc_size(int nlen) +{ + return ALIGN(sizeof(struct au_vdir_de) + nlen, sizeof(ino_t)); +} + +static int set_deblk_end(union au_vdir_deblk_p *p, + union au_vdir_deblk_p *deblk_end) +{ + if (calc_size(0) <= deblk_end->deblk - p->deblk) { + 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->deblk - p->deblk) + return !p->de->de_str.len; + return 1; +} + +static unsigned char *last_deblk(struct au_vdir *vdir) +{ + return vdir->vd_deblk[vdir->vd_nblk - 1]; +} + +/* ---------------------------------------------------------------------- */ + +/* estimate the appropriate size for name hash table */ +unsigned int au_rdhash_est(loff_t sz) +{ + unsigned int n; + + n = UINT_MAX; + sz >>= 10; + if (sz < n) + n = sz; + if (sz < AUFS_RDHASH_DEF) + n = AUFS_RDHASH_DEF; + /* pr_info("n %u\n", n); */ + return n; +} + +/* + * the allocated memory has to be freed by + * au_nhash_wh_free() or au_nhash_de_free(). + */ +int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp) +{ + struct hlist_head *head; + unsigned int u; + size_t sz; + + sz = sizeof(*nhash->nh_head) * num_hash; + head = kmalloc(sz, gfp); + if (head) { + nhash->nh_num = num_hash; + nhash->nh_head = head; + for (u = 0; u < num_hash; u++) + INIT_HLIST_HEAD(head++); + return 0; /* success */ + } + + return -ENOMEM; +} + +static void nhash_count(struct hlist_head *head) +{ +#if 0 /* debugging */ + unsigned long n; + struct hlist_node *pos; + + n = 0; + hlist_for_each(pos, head) + n++; + pr_info("%lu\n", n); +#endif +} + +static void au_nhash_wh_do_free(struct hlist_head *head) +{ + struct au_vdir_wh *pos; + struct hlist_node *node; + + hlist_for_each_entry_safe(pos, node, head, wh_hash) + au_kfree_rcu(pos); +} + +static void au_nhash_de_do_free(struct hlist_head *head) +{ + struct au_vdir_dehstr *pos; + struct hlist_node *node; + + hlist_for_each_entry_safe(pos, node, head, hash) + au_cache_free_vdir_dehstr(pos); +} + +static void au_nhash_do_free(struct au_nhash *nhash, + void (*free)(struct hlist_head *head)) +{ + unsigned int n; + struct hlist_head *head; + + n = nhash->nh_num; + if (!n) + return; + + head = nhash->nh_head; + while (n-- > 0) { + nhash_count(head); + free(head++); + } + au_kfree_try_rcu(nhash->nh_head); +} + +void au_nhash_wh_free(struct au_nhash *whlist) +{ + au_nhash_do_free(whlist, au_nhash_wh_do_free); +} + +static void au_nhash_de_free(struct au_nhash *delist) +{ + au_nhash_do_free(delist, au_nhash_de_do_free); +} + +/* ---------------------------------------------------------------------- */ + +int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, + int limit) +{ + int num; + unsigned int u, n; + struct hlist_head *head; + struct au_vdir_wh *pos; + + num = 0; + n = whlist->nh_num; + head = whlist->nh_head; + for (u = 0; u < n; u++, head++) + hlist_for_each_entry(pos, head, wh_hash) + if (pos->wh_bindex == btgt && ++num > limit) + return 1; + return 0; +} + +static struct hlist_head *au_name_hash(struct au_nhash *nhash, + unsigned char *name, + unsigned int len) +{ + unsigned int v; + /* const unsigned int magic_bit = 12; */ + + AuDebugOn(!nhash->nh_num || !nhash->nh_head); + + v = 0; + if (len > 8) + len = 8; + while (len--) + v += *name++; + /* v = hash_long(v, magic_bit); */ + v %= nhash->nh_num; + return nhash->nh_head + v; +} + +static int au_nhash_test_name(struct au_vdir_destr *str, const char *name, + int nlen) +{ + return str->len == nlen && !memcmp(str->name, name, nlen); +} + +/* returns found or not */ +int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen) +{ + struct hlist_head *head; + struct au_vdir_wh *pos; + struct au_vdir_destr *str; + + head = au_name_hash(whlist, name, nlen); + hlist_for_each_entry(pos, head, wh_hash) { + str = &pos->wh_str; + AuDbg("%.*s\n", str->len, str->name); + if (au_nhash_test_name(str, name, nlen)) + return 1; + } + return 0; +} + +/* returns found(true) or not */ +static int test_known(struct au_nhash *delist, char *name, int nlen) +{ + struct hlist_head *head; + struct au_vdir_dehstr *pos; + struct au_vdir_destr *str; + + head = au_name_hash(delist, name, nlen); + hlist_for_each_entry(pos, head, hash) { + str = pos->str; + AuDbg("%.*s\n", str->len, str->name); + if (au_nhash_test_name(str, name, nlen)) + return 1; + } + return 0; +} + +static void au_shwh_init_wh(struct au_vdir_wh *wh, ino_t ino, + unsigned char d_type) +{ +#ifdef CONFIG_AUFS_SHWH + wh->wh_ino = ino; + wh->wh_type = d_type; +#endif +} + +/* ---------------------------------------------------------------------- */ + +int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, + unsigned int d_type, aufs_bindex_t bindex, + unsigned char shwh) +{ + int err; + struct au_vdir_destr *str; + struct au_vdir_wh *wh; + + AuDbg("%.*s\n", nlen, name); + AuDebugOn(!whlist->nh_num || !whlist->nh_head); + + err = -ENOMEM; + wh = kmalloc(sizeof(*wh) + nlen, GFP_NOFS); + if (unlikely(!wh)) + goto out; + + err = 0; + wh->wh_bindex = bindex; + if (shwh) + au_shwh_init_wh(wh, ino, d_type); + str = &wh->wh_str; + str->len = nlen; + memcpy(str->name, name, nlen); + hlist_add_head(&wh->wh_hash, au_name_hash(whlist, name, nlen)); + /* smp_mb(); */ + +out: + return err; +} + +static int append_deblk(struct au_vdir *vdir) +{ + int err; + unsigned long ul; + const unsigned int deblk_sz = vdir->vd_deblk_sz; + union au_vdir_deblk_p p, deblk_end; + unsigned char **o; + + err = -ENOMEM; + o = au_krealloc(vdir->vd_deblk, sizeof(*o) * (vdir->vd_nblk + 1), + GFP_NOFS, /*may_shrink*/0); + if (unlikely(!o)) + goto out; + + vdir->vd_deblk = o; + p.deblk = kmalloc(deblk_sz, GFP_NOFS); + if (p.deblk) { + ul = vdir->vd_nblk++; + vdir->vd_deblk[ul] = p.deblk; + vdir->vd_last.ul = ul; + vdir->vd_last.p.deblk = p.deblk; + deblk_end.deblk = p.deblk + deblk_sz; + err = set_deblk_end(&p, &deblk_end); + } + +out: + return err; +} + +static int append_de(struct au_vdir *vdir, char *name, int nlen, ino_t ino, + unsigned int d_type, struct au_nhash *delist) +{ + int err; + unsigned int sz; + const unsigned int deblk_sz = vdir->vd_deblk_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 + deblk_sz; + room = &vdir->vd_last.p; + AuDebugOn(room->deblk < p.deblk || deblk_end.deblk <= room->deblk + || !is_deblk_end(room, &deblk_end)); + + sz = calc_size(nlen); + if (unlikely(sz > deblk_end.deblk - room->deblk)) { + err = append_deblk(vdir); + if (unlikely(err)) + goto out; + + p.deblk = last_deblk(vdir); + deblk_end.deblk = p.deblk + deblk_sz; + /* smp_mb(); */ + AuDebugOn(room->deblk != p.deblk); + } + + err = -ENOMEM; + dehstr = au_cache_alloc_vdir_dehstr(); + if (unlikely(!dehstr)) + goto out; + + dehstr->str = &room->de->de_str; + hlist_add_head(&dehstr->hash, au_name_hash(delist, name, nlen)); + room->de->de_ino = ino; + room->de->de_type = d_type; + room->de->de_str.len = nlen; + memcpy(room->de->de_str.name, name, nlen); + + err = 0; + room->deblk += sz; + if (unlikely(set_deblk_end(room, &deblk_end))) + err = append_deblk(vdir); + /* smp_mb(); */ + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_vdir_free(struct au_vdir *vdir) +{ + unsigned char **deblk; + + deblk = vdir->vd_deblk; + while (vdir->vd_nblk--) + au_kfree_try_rcu(*deblk++); + au_kfree_try_rcu(vdir->vd_deblk); + au_cache_free_vdir(vdir); +} + +static struct au_vdir *alloc_vdir(struct file *file) +{ + struct au_vdir *vdir; + struct super_block *sb; + int err; + + sb = file->f_path.dentry->d_sb; + SiMustAnyLock(sb); + + 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_deblk_sz = au_sbi(sb)->si_rdblk; + if (!vdir->vd_deblk_sz) { + /* estimate the appropriate size for deblk */ + vdir->vd_deblk_sz = au_dir_size(file, /*dentry*/NULL); + /* pr_info("vd_deblk_sz %u\n", vdir->vd_deblk_sz); */ + } + vdir->vd_nblk = 0; + vdir->vd_version = 0; + vdir->vd_jiffy = 0; + err = append_deblk(vdir); + if (!err) + return vdir; /* success */ + + au_kfree_try_rcu(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) { + au_kfree_try_rcu(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 + vdir->vd_deblk_sz; + err = set_deblk_end(&p, &deblk_end); + /* keep vd_dblk_sz */ + vdir->vd_last.ul = 0; + vdir->vd_last.p.deblk = vdir->vd_deblk[0]; + vdir->vd_version = 0; + vdir->vd_jiffy = 0; + /* smp_mb(); */ + return err; +} + +/* ---------------------------------------------------------------------- */ + +#define AuFillVdir_CALLED 1 +#define AuFillVdir_WHABLE (1 << 1) +#define AuFillVdir_SHWH (1 << 2) +#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name) +#define au_fset_fillvdir(flags, name) \ + do { (flags) |= AuFillVdir_##name; } while (0) +#define au_fclr_fillvdir(flags, name) \ + do { (flags) &= ~AuFillVdir_##name; } while (0) + +#ifndef CONFIG_AUFS_SHWH +#undef AuFillVdir_SHWH +#define AuFillVdir_SHWH 0 +#endif + +struct fillvdir_arg { + struct dir_context ctx; + 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(struct dir_context *ctx, const char *__name, int nlen, + loff_t offset __maybe_unused, u64 h_ino, + unsigned int d_type) +{ + struct fillvdir_arg *arg = container_of(ctx, struct fillvdir_arg, ctx); + char *name = (void *)__name; + struct super_block *sb; + ino_t ino; + const unsigned char shwh = !!au_ftest_fillvdir(arg->flags, SHWH); + + arg->err = 0; + sb = arg->file->f_path.dentry->d_sb; + au_fset_fillvdir(arg->flags, CALLED); + /* smp_mb(); */ + if (nlen <= AUFS_WH_PFX_LEN + || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + if (test_known(&arg->delist, name, nlen) + || au_nhash_test_known_wh(&arg->whlist, name, nlen)) + goto out; /* already exists or whiteouted */ + + arg->err = au_ino(sb, arg->bindex, h_ino, d_type, &ino); + if (!arg->err) { + if (unlikely(nlen > AUFS_MAX_NAMELEN)) + d_type = DT_UNKNOWN; + arg->err = append_de(arg->vdir, name, nlen, ino, + d_type, &arg->delist); + } + } else if (au_ftest_fillvdir(arg->flags, WHABLE)) { + name += AUFS_WH_PFX_LEN; + nlen -= AUFS_WH_PFX_LEN; + if (au_nhash_test_known_wh(&arg->whlist, name, nlen)) + goto out; /* already whiteouted */ + + ino = 0; /* just to suppress a warning */ + if (shwh) + arg->err = au_wh_ino(sb, arg->bindex, h_ino, d_type, + &ino); + if (!arg->err) { + if (nlen <= AUFS_MAX_NAMELEN + AUFS_WH_PFX_LEN) + d_type = DT_UNKNOWN; + arg->err = au_nhash_append_wh + (&arg->whlist, name, nlen, ino, d_type, + arg->bindex, shwh); + } + } + +out: + if (!arg->err) + arg->vdir->vd_jiffy = jiffies; + /* smp_mb(); */ + AuTraceErr(arg->err); + return arg->err; +} + +static int au_handle_shwh(struct super_block *sb, struct au_vdir *vdir, + struct au_nhash *whlist, struct au_nhash *delist) +{ +#ifdef CONFIG_AUFS_SHWH + int err; + unsigned int nh, u; + struct hlist_head *head; + struct au_vdir_wh *pos; + struct hlist_node *n; + char *p, *o; + struct au_vdir_destr *destr; + + AuDebugOn(!au_opt_test(au_mntflags(sb), SHWH)); + + err = -ENOMEM; + o = p = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = 0; + nh = whlist->nh_num; + memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); + p += AUFS_WH_PFX_LEN; + for (u = 0; u < nh; u++) { + head = whlist->nh_head + u; + hlist_for_each_entry_safe(pos, n, head, wh_hash) { + destr = &pos->wh_str; + memcpy(p, destr->name, destr->len); + err = append_de(vdir, o, destr->len + AUFS_WH_PFX_LEN, + pos->wh_ino, pos->wh_type, delist); + if (unlikely(err)) + break; + } + } + + free_page((unsigned long)o); + +out: + AuTraceErr(err); + return err; +#else + return 0; +#endif +} + +static int au_do_read_vdir(struct fillvdir_arg *arg) +{ + int err; + unsigned int rdhash; + loff_t offset; + aufs_bindex_t bbot, bindex, btop; + unsigned char shwh; + struct file *hf, *file; + struct super_block *sb; + + file = arg->file; + sb = file->f_path.dentry->d_sb; + SiMustAnyLock(sb); + + rdhash = au_sbi(sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(file, /*dentry*/NULL)); + err = au_nhash_alloc(&arg->delist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_nhash_alloc(&arg->whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out_delist; + + err = 0; + arg->flags = 0; + shwh = 0; + if (au_opt_test(au_mntflags(sb), SHWH)) { + shwh = 1; + au_fset_fillvdir(arg->flags, SHWH); + } + btop = au_fbtop(file); + bbot = au_fbbot_dir(file); + for (bindex = btop; !err && bindex <= bbot; bindex++) { + hf = au_hf_dir(file, bindex); + if (!hf) + continue; + + offset = vfsub_llseek(hf, 0, SEEK_SET); + err = offset; + if (unlikely(offset)) + break; + + arg->bindex = bindex; + au_fclr_fillvdir(arg->flags, WHABLE); + if (shwh + || (bindex != bbot + && au_br_whable(au_sbr_perm(sb, bindex)))) + au_fset_fillvdir(arg->flags, WHABLE); + do { + arg->err = 0; + au_fclr_fillvdir(arg->flags, CALLED); + /* smp_mb(); */ + err = vfsub_iterate_dir(hf, &arg->ctx); + if (err >= 0) + err = arg->err; + } while (!err && au_ftest_fillvdir(arg->flags, CALLED)); + + /* + * dir_relax() may be good for concurrency, but aufs should not + * use it since it will cause a lockdep problem. + */ + } + + if (!err && shwh) + err = au_handle_shwh(sb, arg->vdir, &arg->whlist, &arg->delist); + + au_nhash_wh_free(&arg->whlist); + +out_delist: + au_nhash_de_free(&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 = { + .ctx = { + .actor = fillvdir + } + }; + struct inode *inode; + struct au_vdir *vdir, *allocated; + + err = 0; + inode = file_inode(file); + IMustLock(inode); + IiMustWriteLock(inode); + SiMustAnyLock(inode->i_sb); + + 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(file); + err = PTR_ERR(vdir); + if (IS_ERR(vdir)) + goto out; + err = 0; + allocated = vdir; + } else if (may_read + && (!inode_eq_iversion(inode, 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; */ /* todo: ctx->pos? */ + vdir->vd_version = inode_query_iversion(inode); + vdir->vd_last.ul = 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, rerr; + unsigned long ul, n; + const unsigned int deblk_sz = src->vd_deblk_sz; + + AuDebugOn(tgt->vd_nblk != 1); + + err = -ENOMEM; + if (tgt->vd_nblk < src->vd_nblk) { + unsigned char **p; + + p = au_krealloc(tgt->vd_deblk, sizeof(*p) * src->vd_nblk, + GFP_NOFS, /*may_shrink*/0); + if (unlikely(!p)) + goto out; + tgt->vd_deblk = p; + } + + if (tgt->vd_deblk_sz != deblk_sz) { + unsigned char *p; + + tgt->vd_deblk_sz = deblk_sz; + p = au_krealloc(tgt->vd_deblk[0], deblk_sz, GFP_NOFS, + /*may_shrink*/1); + if (unlikely(!p)) + goto out; + tgt->vd_deblk[0] = p; + } + memcpy(tgt->vd_deblk[0], src->vd_deblk[0], deblk_sz); + tgt->vd_version = src->vd_version; + tgt->vd_jiffy = src->vd_jiffy; + + n = src->vd_nblk; + for (ul = 1; ul < n; ul++) { + tgt->vd_deblk[ul] = kmemdup(src->vd_deblk[ul], deblk_sz, + GFP_NOFS); + if (unlikely(!tgt->vd_deblk[ul])) + goto out; + tgt->vd_nblk++; + } + tgt->vd_nblk = n; + tgt->vd_last.ul = tgt->vd_last.ul; + tgt->vd_last.p.deblk = tgt->vd_deblk[tgt->vd_last.ul]; + tgt->vd_last.p.deblk += src->vd_last.p.deblk + - src->vd_deblk[src->vd_last.ul]; + /* 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; + + /* test file->f_pos here instead of ctx->pos */ + 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(file); + 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) { + /* test file->f_pos here instead of ctx->pos */ + err = reinit_vdir(vdir_cache); + if (unlikely(err)) + goto out; + } else + return 0; /* success */ + + inode = file_inode(file); + err = copy_vdir(vdir_cache, au_ivdir(inode)); + if (!err) { + file->f_version = inode_query_iversion(inode); + 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.ul]; + offset = vdir->vd_last.p.deblk - p.deblk; + offset += vdir->vd_deblk_sz * vdir->vd_last.ul; + return offset; +} + +/* returns true or false */ +static int seek_vdir(struct file *file, struct dir_context *ctx) +{ + int valid; + unsigned int deblk_sz; + unsigned long ul, 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 (ctx->pos == offset) + goto out; + + vdir_cache->vd_last.ul = 0; + vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0]; + if (!ctx->pos) + goto out; + + valid = 0; + deblk_sz = vdir_cache->vd_deblk_sz; + ul = div64_u64(ctx->pos, deblk_sz); + AuDbg("ul %lu\n", ul); + if (ul >= vdir_cache->vd_nblk) + goto out; + + n = vdir_cache->vd_nblk; + for (; ul < n; ul++) { + p.deblk = vdir_cache->vd_deblk[ul]; + deblk_end.deblk = p.deblk + deblk_sz; + offset = ul; + offset *= deblk_sz; + while (!is_deblk_end(&p, &deblk_end) && offset < ctx->pos) { + unsigned int l; + + l = calc_size(p.de->de_str.len); + offset += l; + p.deblk += l; + } + if (!is_deblk_end(&p, &deblk_end)) { + valid = 1; + vdir_cache->vd_last.ul = ul; + vdir_cache->vd_last.p = p; + break; + } + } + +out: + /* smp_mb(); */ + if (!valid) + AuDbg("valid %d\n", !valid); + return valid; +} + +int au_vdir_fill_de(struct file *file, struct dir_context *ctx) +{ + unsigned int l, deblk_sz; + union au_vdir_deblk_p deblk_end; + struct au_vdir *vdir_cache; + struct au_vdir_de *de; + + if (!seek_vdir(file, ctx)) + return 0; + + vdir_cache = au_fvdir_cache(file); + deblk_sz = vdir_cache->vd_deblk_sz; + while (1) { + deblk_end.deblk = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; + deblk_end.deblk += deblk_sz; + 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, ctx->pos, + (unsigned long)de->de_ino, de->de_type); + if (unlikely(!dir_emit(ctx, de->de_str.name, + de->de_str.len, de->de_ino, + de->de_type))) { + /* todo: ignore the error caused by udba? */ + /* return err; */ + return 0; + } + + l = calc_size(de->de_str.len); + vdir_cache->vd_last.p.deblk += l; + ctx->pos += l; + } + if (vdir_cache->vd_last.ul < vdir_cache->vd_nblk - 1) { + vdir_cache->vd_last.ul++; + vdir_cache->vd_last.p.deblk + = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; + ctx->pos = deblk_sz * vdir_cache->vd_last.ul; + continue; + } + break; + } + + /* smp_mb(); */ + return 0; +} diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c new file mode 100644 index 000000000000..a5e10c5c004f --- /dev/null +++ b/fs/aufs/vfsub.c @@ -0,0 +1,895 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for VFS + */ + +#include <linux/mnt_namespace.h> +#include <linux/namei.h> +#include <linux/nsproxy.h> +#include <linux/security.h> +#include <linux/splice.h> +#include "aufs.h" + +#ifdef CONFIG_AUFS_BR_FUSE +int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb) +{ + if (!au_test_fuse(h_sb) || !au_userns) + return 0; + + return is_current_mnt_ns(mnt) ? 0 : -EACCES; +} +#endif + +int vfsub_sync_filesystem(struct super_block *h_sb, int wait) +{ + int err; + + lockdep_off(); + down_read(&h_sb->s_umount); + err = __sync_filesystem(h_sb, wait); + up_read(&h_sb->s_umount); + lockdep_on(); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +int vfsub_update_h_iattr(struct path *h_path, int *did) +{ + 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 = vfsub_getattr(h_path, &st); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct file *vfsub_dentry_open(struct path *path, int flags) +{ + return dentry_open(path, flags /* | __FMODE_NONOTIFY */, + current_cred()); +} + +struct file *vfsub_filp_open(const char *path, int oflags, int mode) +{ + struct file *file; + + lockdep_off(); + file = filp_open(path, + oflags /* | __FMODE_NONOTIFY */, + mode); + lockdep_on(); + if (IS_ERR(file)) + goto out; + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ + +out: + return file; +} + +/* + * Ideally this function should call VFS:do_last() in order to keep all its + * checkings. But it is very hard for aufs to regenerate several VFS internal + * structure such as nameidata. This is a second (or third) best approach. + * cf. linux/fs/namei.c:do_last(), lookup_open() and atomic_open(). + */ +int vfsub_atomic_open(struct inode *dir, struct dentry *dentry, + struct vfsub_aopen_args *args) +{ + int err; + struct au_branch *br = args->br; + struct file *file = args->file; + /* copied from linux/fs/namei.c:atomic_open() */ + struct dentry *const DENTRY_NOT_SET = (void *)-1UL; + + IMustLock(dir); + AuDebugOn(!dir->i_op->atomic_open); + + err = au_br_test_oflag(args->open_flag, br); + if (unlikely(err)) + goto out; + + au_lcnt_inc(&br->br_nfiles); + file->f_path.dentry = DENTRY_NOT_SET; + file->f_path.mnt = au_br_mnt(br); + AuDbg("%ps\n", dir->i_op->atomic_open); + err = dir->i_op->atomic_open(dir, dentry, file, args->open_flag, + args->create_mode); + if (unlikely(err < 0)) { + au_lcnt_dec(&br->br_nfiles); + goto out; + } + + /* temporary workaround for nfsv4 branch */ + if (au_test_nfs(dir->i_sb)) + nfs_mark_for_revalidate(dir); + + if (file->f_mode & FMODE_CREATED) + fsnotify_create(dir, dentry); + if (!(file->f_mode & FMODE_OPENED)) { + au_lcnt_dec(&br->br_nfiles); + goto out; + } + + /* todo: call VFS:may_open() here */ + /* todo: ima_file_check() too? */ + if (!err && (args->open_flag & __FMODE_EXEC)) + err = deny_write_access(file); + if (!err) + fsnotify_open(file); + else + au_lcnt_dec(&br->br_nfiles); + /* note that the file is created and still opened */ + +out: + return err; +} + +int vfsub_kern_path(const char *name, unsigned int flags, struct path *path) +{ + int err; + + err = kern_path(name, flags, path); + if (!err && d_is_positive(path->dentry)) + vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ + return err; +} + +struct dentry *vfsub_lookup_one_len_unlocked(const char *name, + struct dentry *parent, int len) +{ + struct path path = { + .mnt = NULL + }; + + path.dentry = lookup_one_len_unlocked(name, parent, len); + if (IS_ERR(path.dentry)) + goto out; + if (d_is_positive(path.dentry)) + vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ + +out: + AuTraceErrPtr(path.dentry); + return path.dentry; +} + +struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, + int len) +{ + struct path path = { + .mnt = NULL + }; + + /* VFS checks it too, but by WARN_ON_ONCE() */ + IMustLock(d_inode(parent)); + + path.dentry = lookup_one_len(name, parent, len); + if (IS_ERR(path.dentry)) + goto out; + if (d_is_positive(path.dentry)) + vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ + +out: + AuTraceErrPtr(path.dentry); + return path.dentry; +} + +void vfsub_call_lkup_one(void *args) +{ + struct vfsub_lkup_one_args *a = args; + *a->errp = vfsub_lkup_one(a->name, a->parent); +} + +/* ---------------------------------------------------------------------- */ + +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_hn_suspend(hdir1); + if (hdir1 != hdir2) + au_hn_suspend(hdir2); + + return d; +} + +void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, + struct dentry *d2, struct au_hinode *hdir2) +{ + au_hn_resume(hdir1); + if (hdir1 != hdir2) + au_hn_resume(hdir2); + lockdep_off(); + unlock_rename(d1, d2); + lockdep_on(); +} + +/* ---------------------------------------------------------------------- */ + +int vfsub_create(struct inode *dir, struct path *path, int mode, bool want_excl) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_mknod(path, d, mode, 0); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_create(dir, path->dentry, mode, want_excl); + lockdep_on(); + 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, d, symname); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_symlink(dir, path->dentry, symname); + lockdep_on(); + 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, d, mode, new_encode_dev(dev)); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_mknod(dir, path->dentry, mode, dev); + lockdep_on(); + 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; +} + +static int au_test_nlink(struct inode *inode) +{ + const unsigned int link_max = UINT_MAX >> 1; /* rough margin */ + + if (!au_test_fs_no_limit_nlink(inode->i_sb) + || inode->i_nlink < link_max) + return 0; + return -EMLINK; +} + +int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path, + struct inode **delegated_inode) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + err = au_test_nlink(d_inode(src_dentry)); + if (unlikely(err)) + return err; + + /* we don't call may_linkat() */ + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_link(src_dentry, path, d); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_link(src_dentry, dir, path->dentry, delegated_inode); + 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, + struct inode **delegated_inode, unsigned int flags) +{ + 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, d, /*flags*/0); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_rename(src_dir, src_dentry, dir, path->dentry, + delegated_inode, flags); + 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, d, mode); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_mkdir(dir, path->dentry, mode); + lockdep_on(); + 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, d); + 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; +} + +/* ---------------------------------------------------------------------- */ + +/* todo: support mmap_sem? */ +ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, + loff_t *ppos) +{ + ssize_t err; + + lockdep_off(); + err = vfs_read(file, ubuf, count, ppos); + lockdep_on(); + 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; + union { + void *k; + char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = vfsub_read_u(file, buf.u, 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; + union { + void *k; + const char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = vfsub_write_u(file, buf.u, count, ppos); + set_fs(oldfs); + return err; +} + +int vfsub_flush(struct file *file, fl_owner_t id) +{ + int err; + + err = 0; + if (file->f_op->flush) { + if (!au_test_nfs(file->f_path.dentry->d_sb)) + err = file->f_op->flush(file, id); + else { + lockdep_off(); + err = file->f_op->flush(file, id); + lockdep_on(); + } + if (!err) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); + /*ignore*/ + } + return err; +} + +int vfsub_iterate_dir(struct file *file, struct dir_context *ctx) +{ + int err; + + AuDbg("%pD, ctx{%ps, %llu}\n", file, ctx->actor, ctx->pos); + + lockdep_off(); + err = iterate_dir(file, ctx); + 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 = do_splice_to(in, ppos, pipe, len, flags); + lockdep_on(); + file_accessed(in); + 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 = do_splice_from(pipe, out, ppos, len, flags); + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&out->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +int vfsub_fsync(struct file *file, struct path *path, int datasync) +{ + int err; + + /* file can be NULL */ + lockdep_off(); + err = vfs_fsync(file, datasync); + lockdep_on(); + if (!err) { + if (!path) { + AuDebugOn(!file); + path = &file->f_path; + } + vfsub_update_h_iattr(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; + struct super_block *h_sb; + + if (!h_file) { + err = vfsub_truncate(h_path, length); + goto out; + } + + h_inode = d_inode(h_path->dentry); + h_sb = h_inode->i_sb; + lockdep_off(); + sb_start_write(h_sb); + lockdep_on(); + err = locks_verify_truncate(h_inode, h_file, length); + if (!err) + err = security_path_truncate(h_path); + if (!err) { + lockdep_off(); + err = do_truncate(h_path->dentry, length, attr, h_file); + lockdep_on(); + } + lockdep_off(); + sb_end_write(h_sb); + lockdep_on(); + +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) { + lockdep_off(); + err = vfsub_mkdir(dir, path, mode); + lockdep_on(); + } 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) { + lockdep_off(); + err = vfsub_rmdir(dir, path); + lockdep_on(); + } 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; + struct inode **delegated_inode; +}; + +static void call_notify_change(void *args) +{ + struct notify_change_args *a = args; + struct inode *h_inode; + + h_inode = d_inode(a->path->dentry); + 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, + a->delegated_inode); + 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, + struct inode **delegated_inode) +{ + int err; + struct notify_change_args args = { + .errp = &err, + .path = path, + .ia = ia, + .delegated_inode = delegated_inode + }; + + call_notify_change(&args); + + return err; +} + +int vfsub_sio_notify_change(struct path *path, struct iattr *ia, + struct inode **delegated_inode) +{ + int err, wkq_err; + struct notify_change_args args = { + .errp = &err, + .path = path, + .ia = ia, + .delegated_inode = delegated_inode + }; + + 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; + struct inode **delegated_inode; +}; + +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) + && au_dcount(d) == 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 = NULL; + if (d_is_positive(d)) { + h_inode = d_inode(d); + ihold(h_inode); + } + + lockdep_off(); + *a->errp = vfs_unlink(a->dir, d, a->delegated_inode); + 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, + struct inode **delegated_inode, int force) +{ + int err; + struct unlink_args args = { + .errp = &err, + .dir = dir, + .path = path, + .delegated_inode = delegated_inode + }; + + 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 --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h new file mode 100644 index 000000000000..705f033ba2c3 --- /dev/null +++ b/fs/aufs/vfsub.h @@ -0,0 +1,354 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for VFS + */ + +#ifndef __AUFS_VFSUB_H__ +#define __AUFS_VFSUB_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/posix_acl.h> +#include <linux/xattr.h> +#include "debug.h" + +/* copied from linux/fs/internal.h */ +/* todo: BAD approach!! */ +extern void __mnt_drop_write(struct vfsmount *); +extern struct file *alloc_empty_file(int, const struct cred *); + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for lower inode */ +/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */ +/* reduce? gave up. */ +enum { + AuLsc_I_Begin = I_MUTEX_PARENT2, /* 5 */ + AuLsc_I_PARENT, /* lower inode, parent first */ + AuLsc_I_PARENT2, /* copyup dirs */ + AuLsc_I_PARENT3, /* copyup wh */ + 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) AuDebugOn(!inode_is_locked(i)) + +/* ---------------------------------------------------------------------- */ + +static inline void vfsub_drop_nlink(struct inode *inode) +{ + AuDebugOn(!inode->i_nlink); + drop_nlink(inode); +} + +static inline void vfsub_dead_dir(struct inode *inode) +{ + AuDebugOn(!S_ISDIR(inode->i_mode)); + inode->i_flags |= S_DEAD; + clear_nlink(inode); +} + +static inline int vfsub_native_ro(struct inode *inode) +{ + return sb_rdonly(inode->i_sb) + || IS_RDONLY(inode) + /* || IS_APPEND(inode) */ + || IS_IMMUTABLE(inode); +} + +#ifdef CONFIG_AUFS_BR_FUSE +int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb); +#else +AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb); +#endif + +int vfsub_sync_filesystem(struct super_block *h_sb, int wait); + +/* ---------------------------------------------------------------------- */ + +int vfsub_update_h_iattr(struct path *h_path, int *did); +struct file *vfsub_dentry_open(struct path *path, int flags); +struct file *vfsub_filp_open(const char *path, int oflags, int mode); +struct au_branch; +struct vfsub_aopen_args { + struct file *file; + unsigned int open_flag; + umode_t create_mode; + struct au_branch *br; +}; +int vfsub_atomic_open(struct inode *dir, struct dentry *dentry, + struct vfsub_aopen_args *args); +int vfsub_kern_path(const char *name, unsigned int flags, struct path *path); + +struct dentry *vfsub_lookup_one_len_unlocked(const char *name, + struct dentry *parent, int len); +struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, + int len); + +struct vfsub_lkup_one_args { + struct dentry **errp; + struct qstr *name; + struct dentry *parent; +}; + +static inline struct dentry *vfsub_lkup_one(struct qstr *name, + struct dentry *parent) +{ + return vfsub_lookup_one_len(name->name, parent, name->len); +} + +void vfsub_call_lkup_one(void *args); + +/* ---------------------------------------------------------------------- */ + +static inline int vfsub_mnt_want_write(struct vfsmount *mnt) +{ + int err; + + lockdep_off(); + err = mnt_want_write(mnt); + lockdep_on(); + return err; +} + +static inline void vfsub_mnt_drop_write(struct vfsmount *mnt) +{ + lockdep_off(); + mnt_drop_write(mnt); + lockdep_on(); +} + +#if 0 /* reserved */ +static inline void vfsub_mnt_drop_write_file(struct file *file) +{ + lockdep_off(); + mnt_drop_write_file(file); + lockdep_on(); +} +#endif + +/* ---------------------------------------------------------------------- */ + +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, + bool want_excl); +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, struct inode **delegated_inode); +int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry, + struct inode *hdir, struct path *path, + struct inode **delegated_inode, unsigned int flags); +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_flush(struct file *file, fl_owner_t id); +int vfsub_iterate_dir(struct file *file, struct dir_context *ctx); + +static inline loff_t vfsub_f_size_read(struct file *file) +{ + return i_size_read(file_inode(file)); +} + +static inline unsigned int vfsub_file_flags(struct file *file) +{ + unsigned int flags; + + spin_lock(&file->f_lock); + flags = file->f_flags; + spin_unlock(&file->f_lock); + + return flags; +} + +static inline int vfsub_file_execed(struct file *file) +{ + /* todo: direct access f_flags */ + return !!(vfsub_file_flags(file) & __FMODE_EXEC); +} + +#if 0 /* reserved */ +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*/ +} +#endif + +#if 0 /* reserved */ +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_path); + vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ +} +#endif + +static inline int vfsub_update_time(struct inode *h_inode, + struct timespec64 *ts, int flags) +{ + return update_time(h_inode, ts, flags); + /* no vfsub_update_h_iattr() since we don't have struct path */ +} + +#ifdef CONFIG_FS_POSIX_ACL +static inline int vfsub_acl_chmod(struct inode *h_inode, umode_t h_mode) +{ + int err; + + err = posix_acl_chmod(h_inode, h_mode); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} +#else +AuStubInt0(vfsub_acl_chmod, struct inode *h_inode, umode_t h_mode); +#endif + +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); + +static inline long vfsub_truncate(struct path *path, loff_t length) +{ + long err; + + lockdep_off(); + err = vfs_truncate(path, length); + lockdep_on(); + return err; +} + +int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, + struct file *h_file); +int vfsub_fsync(struct file *file, struct path *path, int datasync); + +/* + * re-use branch fs's ioctl(FICLONE) while aufs itself doesn't support such + * ioctl. + */ +static inline loff_t vfsub_clone_file_range(struct file *src, struct file *dst, + loff_t len) +{ + loff_t err; + + lockdep_off(); + err = vfs_clone_file_range(src, 0, dst, 0, len, /*remap_flags*/0); + lockdep_on(); + + return err; +} + +/* copy_file_range(2) is a systemcall */ +static inline ssize_t vfsub_copy_file_range(struct file *src, loff_t src_pos, + struct file *dst, loff_t dst_pos, + size_t len, unsigned int flags) +{ + ssize_t ssz; + + lockdep_off(); + ssz = vfs_copy_file_range(src, src_pos, dst, dst_pos, len, flags); + lockdep_on(); + + return ssz; +} + +/* ---------------------------------------------------------------------- */ + +static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t err; + + lockdep_off(); + err = vfs_llseek(file, offset, origin); + lockdep_on(); + return err; +} + +/* ---------------------------------------------------------------------- */ + +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, + struct inode **delegated_inode); +int vfsub_notify_change(struct path *path, struct iattr *ia, + struct inode **delegated_inode); +int vfsub_unlink(struct inode *dir, struct path *path, + struct inode **delegated_inode, int force); + +static inline int vfsub_getattr(const struct path *path, struct kstat *st) +{ + return vfs_getattr(path, st, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); +} + +/* ---------------------------------------------------------------------- */ + +static inline int vfsub_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err; + + lockdep_off(); + err = vfs_setxattr(dentry, name, value, size, flags); + lockdep_on(); + + return err; +} + +static inline int vfsub_removexattr(struct dentry *dentry, const char *name) +{ + int err; + + lockdep_off(); + err = vfs_removexattr(dentry, name); + lockdep_on(); + + return err; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_VFSUB_H__ */ diff --git a/fs/aufs/wbr_policy.c b/fs/aufs/wbr_policy.c new file mode 100644 index 000000000000..a7cc1109f69d --- /dev/null +++ b/fs/aufs/wbr_policy.c @@ -0,0 +1,830 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 = d_inode(h_src); + 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(d_inode(h_path->dentry), h_isrc->i_flags); + /* no delegation since it is just created */ + err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL); + + /* is this nfs only? */ + if (!err && sbits && au_test_nfs(h_path->dentry->d_sb)) { + ia.ia_valid = ATTR_FORCE | ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + err = vfsub_sio_notify_change(h_path, &ia, /*delegated*/NULL); + } + + 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) \ + do { (flags) |= AuCpdown_##name; } while (0) +#define au_fclr_cpdown(flags, name) \ + do { (flags) &= ~AuCpdown_##name; } while (0) + +static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst, + unsigned int *flags) +{ + 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(*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 (d_is_positive(h_path.dentry)) { + h_path.mnt = au_br_mnt(br); + 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 au_pin *pin, + struct dentry *h_parent, void *arg) +{ + int err, rerr; + aufs_bindex_t bopq, btop; + struct path h_path; + struct dentry *parent; + struct inode *h_dir, *h_inode, *inode, *dir; + unsigned int *flags = arg; + + btop = au_dbtop(dentry); + /* dentry is di-locked */ + parent = dget_parent(dentry); + dir = d_inode(parent); + h_dir = d_inode(h_parent); + AuDebugOn(h_dir != au_h_iptr(dir, bdst)); + IMustLock(h_dir); + + err = au_lkup_neg(dentry, bdst, /*wh*/0); + 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, 0755); + if (unlikely(err)) + goto out_put; + au_fset_cpdown(*flags, MADE_DIR); + + bopq = au_dbdiropq(dentry); + au_fclr_cpdown(*flags, WHED); + au_fclr_cpdown(*flags, DIROPQ); + if (au_dbwh(dentry) == bdst) + au_fset_cpdown(*flags, WHED); + if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst) + au_fset_cpdown(*flags, PARENT_OPQ); + h_inode = d_inode(h_path.dentry); + inode_lock_nested(h_inode, AuLsc_I_CHILD); + if (au_ftest_cpdown(*flags, WHED)) { + err = au_cpdown_dir_opq(dentry, bdst, flags); + if (unlikely(err)) { + inode_unlock(h_inode); + goto out_dir; + } + } + + err = au_cpdown_attr(&h_path, au_h_dptr(dentry, btop)); + inode_unlock(h_inode); + if (unlikely(err)) + goto out_opq; + + if (au_ftest_cpdown(*flags, WHED)) { + err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst); + if (unlikely(err)) + goto out_opq; + } + + inode = d_inode(dentry); + if (au_ibbot(inode) < bdst) + au_set_ibbot(inode, bdst); + au_set_h_iptr(inode, bdst, au_igrab(h_inode), + au_hi_flags(inode, /*isdir*/1)); + au_fhsm_wrote(dentry->d_sb, bdst, /*force*/0); + goto out; /* success */ + + /* revert */ +out_opq: + if (au_ftest_cpdown(*flags, DIROPQ)) { + inode_lock_nested(h_inode, AuLsc_I_CHILD); + rerr = au_diropq_remove(dentry, bdst); + inode_unlock(h_inode); + if (unlikely(rerr)) { + AuIOErr("failed removing diropq for %pd b%d (%d)\n", + dentry, bdst, rerr); + err = -EIO; + goto out; + } + } +out_dir: + if (au_ftest_cpdown(*flags, MADE_DIR)) { + rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path); + if (unlikely(rerr)) { + AuIOErr("failed removing %pd b%d (%d)\n", + dentry, bdst, rerr); + err = -EIO; + } + } +out_put: + au_set_h_dptr(dentry, bdst, NULL); + if (au_dbbot(dentry) == bdst) + au_update_dbbot(dentry); +out: + dput(parent); + return err; +} + +int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + int err; + unsigned int flags; + + flags = 0; + err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &flags); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* policies for create */ + +int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex) +{ + int err, i, j, ndentry; + aufs_bindex_t bopq; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries, *parent, *d; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + parent = dget_parent(dentry); + err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/0); + if (unlikely(err)) + goto out_free; + + err = bindex; + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + d = dentries[j]; + di_read_lock_parent2(d, !AuLock_IR); + bopq = au_dbdiropq(d); + di_read_unlock(d, !AuLock_IR); + if (bopq >= 0 && bopq < err) + err = bopq; + } + } + +out_free: + dput(parent); + au_dpages_free(&dpages); +out: + return err; +} + +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, + unsigned int flags __maybe_unused) +{ + int err; + aufs_bindex_t btop, bindex; + struct super_block *sb; + struct dentry *parent, *h_parent; + + sb = dentry->d_sb; + btop = au_dbtop(dentry); + err = btop; + if (!au_br_rdonly(au_sbr(sb, btop))) + goto out; + + err = -EROFS; + parent = dget_parent(dentry); + for (bindex = au_dbtop(parent); bindex < btop; bindex++) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || d_is_negative(h_parent)) + 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, btop - 1); + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + } + +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) + err = au_wbr_nonopq(dentry, err); + + 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_sbbot(sb)); + atomic_set(&au_sbi(sb)->si_wbr_rr_next, -err); /* less important */ + /* smp_mb(); */ + + AuDbg("b%d\n", err); + return err; +} + +static int au_wbr_create_rr(struct dentry *dentry, unsigned int flags) +{ + int err, nbr; + unsigned int u; + aufs_bindex_t bindex, bbot; + 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; + bbot = au_sbbot(sb); + nbr = bbot + 1; + for (bindex = 0; bindex <= bbot; bindex++) { + if (!au_ftest_wbr(flags, DIR)) { + 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; + } + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +out: + AuDbg("%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* most free space */ +static void au_mfs(struct dentry *dentry, struct dentry *parent) +{ + struct super_block *sb; + struct au_branch *br; + struct au_wbr_mfs *mfs; + struct dentry *h_parent; + aufs_bindex_t bindex, bbot; + int err; + unsigned long long b, bavail; + struct path h_path; + /* 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; + MtxMustLock(&mfs->mfs_lock); + mfs->mfs_bindex = -EROFS; + mfs->mfsrr_bytes = 0; + if (!parent) { + bindex = 0; + bbot = au_sbbot(sb); + } else { + bindex = au_dbtop(parent); + bbot = au_dbtaildir(parent); + } + + for (; bindex <= bbot; bindex++) { + if (parent) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || d_is_negative(h_parent)) + continue; + } + br = au_sbr(sb, bindex); + if (au_br_rdonly(br)) + continue; + + /* sb->s_root for NFS is unreliable */ + h_path.mnt = au_br_mnt(br); + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, 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); + au_kfree_rcu(st); +} + +static int au_wbr_create_mfs(struct dentry *dentry, unsigned int flags) +{ + int err; + struct dentry *parent; + struct super_block *sb; + struct au_wbr_mfs *mfs; + + err = au_wbr_create_exp(dentry); + if (err >= 0) + goto out; + + sb = dentry->d_sb; + parent = NULL; + if (au_ftest_wbr(flags, PARENT)) + parent = dget_parent(dentry); + 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, parent); + mutex_unlock(&mfs->mfs_lock); + err = mfs->mfs_bindex; + dput(parent); + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +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; +} + +/* ---------------------------------------------------------------------- */ + +/* top down regardless parent, and then mfs */ +static int au_wbr_create_tdmfs(struct dentry *dentry, + unsigned int flags __maybe_unused) +{ + int err; + aufs_bindex_t bwh, btail, bindex, bfound, bmfs; + unsigned long long watermark; + struct super_block *sb; + struct au_wbr_mfs *mfs; + struct au_branch *br; + struct dentry *parent; + + 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_mfs(dentry, /*parent*/NULL); + watermark = mfs->mfsrr_watermark; + bmfs = mfs->mfs_bindex; + mutex_unlock(&mfs->mfs_lock); + + /* another style of au_wbr_create_exp() */ + bwh = au_dbwh(dentry); + parent = dget_parent(dentry); + btail = au_dbtaildir(parent); + if (bwh >= 0 && bwh < btail) + btail = bwh; + + err = au_wbr_nonopq(dentry, btail); + if (unlikely(err < 0)) + goto out; + btail = err; + bfound = -1; + for (bindex = 0; bindex <= btail; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_rdonly(br)) + continue; + if (br->br_wbr->wbr_bytes > watermark) { + bfound = bindex; + break; + } + } + err = bfound; + if (err < 0) + err = bmfs; + +out: + dput(parent); + AuDbg("b%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* most free space and then round robin */ +static int au_wbr_create_mfsrr(struct dentry *dentry, unsigned int flags) +{ + int err; + struct au_wbr_mfs *mfs; + + err = au_wbr_create_mfs(dentry, flags); + if (err >= 0) { + mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs; + mutex_lock(&mfs->mfs_lock); + if (mfs->mfsrr_bytes < mfs->mfsrr_watermark) + err = au_wbr_create_rr(dentry, flags); + mutex_unlock(&mfs->mfs_lock); + } + + 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, unsigned int flags) +{ + int err, e2; + unsigned long long b; + aufs_bindex_t bindex, btop, bbot; + struct super_block *sb; + struct dentry *parent, *h_parent; + struct au_branch *br; + + err = au_wbr_create_tdp(dentry, flags); + if (unlikely(err < 0)) + goto out; + parent = dget_parent(dentry); + btop = au_dbtop(parent); + bbot = au_dbtaildir(parent); + if (btop == bbot) + goto out_parent; /* success */ + + e2 = au_wbr_create_mfs(dentry, flags); + 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 = btop; bindex <= bbot; bindex++) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || d_is_negative(h_parent)) + 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); + } + } + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +out_parent: + dput(parent); +out: + AuDbg("b%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * - top down parent + * - most free space with parent + * - most free space round-robin regardless parent + */ +static int au_wbr_create_pmfsrr(struct dentry *dentry, unsigned int flags) +{ + int err; + unsigned long long watermark; + struct super_block *sb; + struct au_branch *br; + struct au_wbr_mfs *mfs; + + err = au_wbr_create_pmfs(dentry, flags | AuWbr_PARENT); + if (unlikely(err < 0)) + goto out; + + sb = dentry->d_sb; + br = au_sbr(sb, err); + mfs = &au_sbi(sb)->si_wbr_mfs; + mutex_lock(&mfs->mfs_lock); + watermark = mfs->mfsrr_watermark; + mutex_unlock(&mfs->mfs_lock); + if (br->br_wbr->wbr_bytes < watermark) + /* regardless the parent dir */ + err = au_wbr_create_mfsrr(dentry, flags); + +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, /*flags, anything is ok*/0); +} + +/* bottom up parent */ +static int au_wbr_copyup_bup(struct dentry *dentry) +{ + int err; + aufs_bindex_t bindex, btop; + struct dentry *parent, *h_parent; + struct super_block *sb; + + err = -EROFS; + sb = dentry->d_sb; + parent = dget_parent(dentry); + btop = au_dbtop(parent); + for (bindex = au_dbtop(dentry); bindex >= btop; bindex--) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || d_is_negative(h_parent)) + 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, btop - 1); + + AuDbg("b%d\n", err); + return err; +} + +/* bottom up */ +int au_wbr_do_copyup_bu(struct dentry *dentry, aufs_bindex_t btop) +{ + int err; + + err = au_wbr_bu(dentry->d_sb, btop); + AuDbg("b%d\n", err); + if (err > btop) + err = au_wbr_nonopq(dentry, err); + + AuDbg("b%d\n", err); + return err; +} + +static int au_wbr_copyup_bu(struct dentry *dentry) +{ + int err; + aufs_bindex_t btop; + + btop = au_dbtop(dentry); + err = au_wbr_do_copyup_bu(dentry, btop); + 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_TDMFS] = { + .create = au_wbr_create_tdmfs, + .init = au_wbr_create_init_mfs, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_TDMFSV] = { + .create = au_wbr_create_tdmfs, + .init = au_wbr_create_init_mfs, + .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 + }, + [AuWbrCreate_PMFSRR] = { + .create = au_wbr_create_pmfsrr, + .init = au_wbr_create_init_mfsrr, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_PMFSRRV] = { + .create = au_wbr_create_pmfsrr, + .init = au_wbr_create_init_mfsrr, + .fin = au_wbr_create_fin_mfs + } +}; diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c new file mode 100644 index 000000000000..efe0c16508db --- /dev/null +++ b/fs/aufs/whout.c @@ -0,0 +1,1062 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * whiteout for logical deletion and opaque directory + */ + +#include "aufs.h" + +#define WH_MASK 0444 + +/* + * 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 = QSTR_INIT(AUFS_WH_DIROPQ, + 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, int try_sio) +{ + int err; + struct dentry *wh_dentry; + + if (!try_sio) + wh_dentry = vfsub_lkup_one(wh_name, h_parent); + else + wh_dentry = au_sio_lkup_one(wh_name, h_parent); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) { + if (err == -ENAMETOOLONG) + err = 0; + goto out; + } + + err = 0; + if (d_is_negative(wh_dentry)) + goto out_wh; /* success */ + + err = 1; + if (d_is_reg(wh_dentry)) + goto out_wh; /* success */ + + err = -EIO; + AuIOErr("%pd Invalid whiteout entry type 0%o.\n", + wh_dentry, d_inode(wh_dentry)->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) +{ + int err; + struct inode *h_dir; + + h_dir = d_inode(h_dentry); + err = au_wh_test(h_dentry, &diropq_name, + 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) +{ + struct dentry *dentry; + int i; + char defname[NAME_MAX - AUFS_MAX_NAMELEN + DNAME_INLINE_LEN + 1], + *name, *p; + /* strict atomic_t is unnecessary here */ + static unsigned short cnt; + struct qstr qs; + + BUILD_BUG_ON(sizeof(cnt) * 2 > AUFS_WH_TMP_LEN); + + name = defname; + qs.len = sizeof(defname) - DNAME_INLINE_LEN + prefix->len - 1; + if (unlikely(prefix->len > DNAME_INLINE_LEN)) { + dentry = ERR_PTR(-ENAMETOOLONG); + if (unlikely(qs.len > NAME_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 <= AUFS_WH_TMP_LEN); + + qs.name = name; + for (i = 0; i < 3; i++) { + sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++); + dentry = au_sio_lkup_one(&qs, h_parent); + if (IS_ERR(dentry) || d_is_negative(dentry)) + goto out_name; + dput(dentry); + } + /* pr_warn("could not get random name\n"); */ + dentry = ERR_PTR(-EEXIST); + AuDbg("%.*s\n", AuLNPair(&qs)); + BUG(); + +out_name: + if (name != defname) + au_kfree_try_rcu(name); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* + * 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 = au_br_mnt(br) + }; + struct inode *h_dir, *delegated; + struct dentry *h_parent; + + h_parent = h_dentry->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + 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() */ + delegated = NULL; + err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path, &delegated, + /*flags*/0); + AuTraceErr(err); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal rename\n"); + iput(delegated); + } + dput(h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ +/* + * functions for removing a whiteout + */ + +static int do_unlink_wh(struct inode *h_dir, struct path *h_path) +{ + int err, force; + struct inode *delegated; + + /* + * 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) + && !uid_eq(current_fsuid(), d_inode(h_path->dentry)->i_uid); + delegated = NULL; + err = vfsub_unlink(h_dir, h_path, &delegated, force); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + return err; +} + +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 = au_br_mnt(br) + }; + + err = 0; + h_path.dentry = vfsub_lkup_one(wh, h_parent); + if (IS_ERR(h_path.dentry)) + err = PTR_ERR(h_path.dentry); + else { + if (d_is_reg(h_path.dentry)) + err = do_unlink_wh(d_inode(h_parent), &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; + struct inode *delegated; + + if (d_is_negative(whpath->dentry)) + return; + + if (isdir) + err = vfsub_rmdir(h_dir, whpath); + else { + delegated = NULL; + err = vfsub_unlink(h_dir, whpath, &delegated, /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + } + if (unlikely(err)) + pr_warn("failed removing %pd (%d), ignored.\n", + whpath->dentry, err); +} + +static int test_linkable(struct dentry *h_root) +{ + struct inode *h_dir = d_inode(h_root); + + if (h_dir->i_op->link) + return 0; + + pr_err("%pd (%s) doesn't support link(2), use noplink and rw+nolwh\n", + h_root, au_sbtype(h_root->d_sb)); + return -ENOSYS; /* the branch doesn't have its ->link() */ +} + +/* 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 (d_is_negative(path->dentry)) { + int mode = 0700; + + if (au_test_nfs(path->dentry->d_sb)) + mode |= 0111; + err = vfsub_mkdir(h_dir, path, mode); + } else if (d_is_dir(path->dentry)) + err = 0; + else + pr_err("unknown %pd exists\n", 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 message + * zero: success + * plus: error, caller should NOT print the message + */ +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 = d_inode(h_root); + 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; + + WbrWhMustWriteLock(wbr); + + 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 = d_inode(h_root); + if (d_is_negative(base[AuBrWh_BASE].dentry)) { + h_path->dentry = base[AuBrWh_BASE].dentry; + err = vfsub_create(h_dir, h_path, WH_MASK, /*want_excl*/true); + } else if (d_is_reg(base[AuBrWh_BASE].dentry)) + err = 0; + else + pr_err("unknown %pd2 exists\n", 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 au_branch *br, struct super_block *sb) +{ + int err, i; + const unsigned char do_plink + = !!au_opt_test(au_mntflags(sb), PLINK); + struct inode *h_dir; + struct path path = br->br_path; + struct dentry *h_root = path.dentry; + struct au_wbr *wbr = br->br_wbr; + static const struct qstr base_name[] = { + [AuBrWh_BASE] = QSTR_INIT(AUFS_BASE_NAME, + sizeof(AUFS_BASE_NAME) - 1), + [AuBrWh_PLINK] = QSTR_INIT(AUFS_PLINKDIR_NAME, + sizeof(AUFS_PLINKDIR_NAME) - 1), + [AuBrWh_ORPH] = QSTR_INIT(AUFS_ORPHDIR_NAME, + 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 + } + }; + + if (wbr) + WbrWhMustWriteLock(wbr); + + 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; + if (!au_br_writable(br->br_perm)) { + h_dir = d_inode(h_root); + au_wh_init_ro(h_dir, base, &path); + } else if (!au_br_wh_linkable(br->br_perm)) { + err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path); + if (err > 0) + goto out; + else if (err) + goto out_err; + } else { + err = au_wh_init_rw(h_root, wbr, do_plink, base, &path); + if (err > 0) + goto out; + else if (err) + goto out_err; + } + goto out; /* success */ + +out_err: + pr_err("an error(%d) on the writable branch %pd(%s)\n", + err, 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, *delegated; + 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; + + di_read_lock_parent(a->sb->s_root, AuLock_IR); + dir = d_inode(a->sb->s_root); + hdir = au_hi(dir, bindex); + h_root = au_h_dptr(a->sb->s_root, bindex); + AuDebugOn(h_root != au_br_dentry(a->br)); + + au_hn_inode_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) { + h_path.dentry = wbr->wbr_whbase; + h_path.mnt = au_br_mnt(a->br); + delegated = NULL; + err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, + /*force*/0); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + } else { + pr_warn("%pd is moved, ignored\n", wbr->wbr_whbase); + err = 0; + } + dput(wbr->wbr_whbase); + wbr->wbr_whbase = NULL; + if (!err) + err = au_wh_init(a->br, a->sb); + wbr_wh_write_unlock(wbr); + au_hn_inode_unlock(hdir); + di_read_unlock(a->sb->s_root, AuLock_IR); + if (!err) + au_fhsm_wrote(a->sb, bindex, /*force*/0); + +out: + if (wbr) + atomic_dec(&wbr->wbr_wh_running); + au_lcnt_dec(&a->br->br_count); + si_write_unlock(a->sb); + au_nwt_done(&au_sbi(a->sb)->si_nowait); + au_kfree_rcu(a); + 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; + au_lcnt_inc(&br->br_count); + wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb, /*flags*/0); + if (unlikely(wkq_err)) { + atomic_dec(&br->br_wbr->wbr_wh_running); + au_lcnt_dec(&br->br_count); + au_kfree_rcu(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, *delegated; + + h_parent = wh->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + + br = au_sbr(sb, bindex); + h_path.mnt = au_br_mnt(br); + wbr = br->br_wbr; + wbr_wh_read_lock(wbr); + if (wbr->wbr_whbase) { + delegated = NULL; + err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + 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, /*want_excl*/true); + if (!err) + au_fhsm_wrote(sb, bindex, /*force*/0); + +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 = vfsub_lkup_one(&diropq_name, h_dentry); + 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 = au_br_mnt(br) + }; + err = do_unlink_wh(au_h_iptr(d_inode(dentry), 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(d_inode(h_dentry), 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 = vfsub_lkup_one(&wh_name, h_parent); + au_kfree_try_rcu(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) && d_is_negative(wh_dentry)) { + err = link_or_create_wh(sb, bindex, wh_dentry); + if (!err) { + au_set_dbwh(dentry, bindex); + au_fhsm_wrote(sb, bindex, /*force*/0); + } 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; + unsigned long ul, n; + struct qstr wh_name; + char *p; + struct hlist_head *head; + struct au_vdir_wh *pos; + struct au_vdir_destr *str; + + err = -ENOMEM; + p = (void *)__get_free_page(GFP_NOFS); + 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; + n = whlist->nh_num; + head = whlist->nh_head; + for (ul = 0; !err && ul < n; ul++, head++) { + hlist_for_each_entry(pos, head, wh_hash) { + if (pos->wh_bindex != bindex) + continue; + + str = &pos->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; + } + } + free_page((unsigned long)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); +} + +/* ---------------------------------------------------------------------- */ + +struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp) +{ + struct au_whtmp_rmdir *whtmp; + int err; + unsigned int rdhash; + + SiMustAnyLock(sb); + + whtmp = kzalloc(sizeof(*whtmp), gfp); + if (unlikely(!whtmp)) { + whtmp = ERR_PTR(-ENOMEM); + goto out; + } + + /* no estimation for dir size */ + rdhash = au_sbi(sb)->si_rdhash; + if (!rdhash) + rdhash = AUFS_RDHASH_DEF; + err = au_nhash_alloc(&whtmp->whlist, rdhash, gfp); + if (unlikely(err)) { + au_kfree_rcu(whtmp); + whtmp = ERR_PTR(err); + } + +out: + return whtmp; +} + +void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp) +{ + if (whtmp->br) + au_lcnt_dec(&whtmp->br->br_count); + dput(whtmp->wh_dentry); + iput(whtmp->dir); + au_nhash_wh_free(&whtmp->whlist); + au_kfree_rcu(whtmp); +} + +/* + * 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; + unsigned int h_nlink; + struct path h_tmp; + struct inode *wh_inode, *h_dir; + struct au_branch *br; + + h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */ + IMustLock(h_dir); + + br = au_sbr(dir->i_sb, bindex); + wh_inode = d_inode(wh_dentry); + inode_lock_nested(wh_inode, 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; + } + inode_unlock(wh_inode); + + if (!err) { + h_tmp.dentry = wh_dentry; + h_tmp.mnt = au_br_mnt(br); + h_nlink = h_dir->i_nlink; + err = vfsub_rmdir(h_dir, &h_tmp); + /* some fs doesn't change the parent nlink in some cases */ + h_nlink -= h_dir->i_nlink; + } + + if (!err) { + if (au_ibtop(dir) == bindex) { + /* todo: dir->i_mutex is necessary */ + au_cpup_attr_timesizes(dir); + if (h_nlink) + vfsub_drop_nlink(dir); + } + return 0; /* success */ + } + + pr_warn("failed removing %pd(%d), ignored\n", wh_dentry, err); + return err; +} + +static void call_rmdir_whtmp(void *args) +{ + int err; + aufs_bindex_t bindex; + struct au_whtmp_rmdir *a = args; + struct super_block *sb; + struct dentry *h_parent; + struct inode *h_dir; + struct au_hinode *hdir; + + /* rmdir by nfsd may cause deadlock with this i_mutex */ + /* inode_lock(a->dir); */ + err = -EROFS; + sb = a->dir->i_sb; + si_read_lock(sb, !AuLock_FLUSH); + if (!au_br_writable(a->br->br_perm)) + goto out; + bindex = au_br_index(sb, a->br->br_id); + if (unlikely(bindex < 0)) + goto out; + + err = -EIO; + ii_write_lock_parent(a->dir); + h_parent = dget_parent(a->wh_dentry); + h_dir = d_inode(h_parent); + hdir = au_hi(a->dir, bindex); + err = vfsub_mnt_want_write(au_br_mnt(a->br)); + if (unlikely(err)) + goto out_mnt; + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent, + a->br); + if (!err) + err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry, &a->whlist); + au_hn_inode_unlock(hdir); + vfsub_mnt_drop_write(au_br_mnt(a->br)); + +out_mnt: + dput(h_parent); + ii_write_unlock(a->dir); +out: + /* inode_unlock(a->dir); */ + au_whtmp_rmdir_free(a); + si_read_unlock(sb); + au_nwt_done(&au_sbi(sb)->si_nowait); + 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_whtmp_rmdir *args) +{ + int wkq_err; + struct super_block *sb; + + IMustLock(dir); + + /* all post-process will be done in do_rmdir_whtmp(). */ + sb = dir->i_sb; + args->dir = au_igrab(dir); + args->br = au_sbr(sb, bindex); + au_lcnt_inc(&args->br->br_count); + args->wh_dentry = dget(wh_dentry); + wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, sb, /*flags*/0); + if (unlikely(wkq_err)) { + pr_warn("rmdir error %pd (%d), ignored\n", wh_dentry, wkq_err); + au_whtmp_rmdir_free(args); + } +} diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h new file mode 100644 index 000000000000..65459ba0e790 --- /dev/null +++ b/fs/aufs/whout.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * whiteout for logical deletion and opaque directory + */ + +#ifndef __AUFS_WHOUT_H__ +#define __AUFS_WHOUT_H__ + +#ifdef __KERNEL__ + +#include "dir.h" + +/* whout.c */ +int au_wh_name_alloc(struct qstr *wh, const struct qstr *name); +int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, int try_sio); +int au_diropq_test(struct dentry *h_dentry); +struct au_branch; +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 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) \ + do { (flags) |= AuDiropq_##name; } while (0) +#define au_fclr_diropq(flags, name) \ + do { (flags) &= ~AuDiropq_##name; } while (0) + +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 { + struct inode *dir; + struct au_branch *br; + struct dentry *wh_dentry; + struct au_nhash whlist; +}; + +struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp); +void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp); +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_whtmp_rmdir *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 --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c new file mode 100644 index 000000000000..4d66bb2dc657 --- /dev/null +++ b/fs/aufs/wkq.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * workqueue for asynchronous/super-io operations + * todo: try new credential scheme + */ + +#include <linux/module.h> +#include "aufs.h" + +/* internal workqueue named AUFS_WKQ_NAME */ + +static struct workqueue_struct *au_wkq; + +struct au_wkinfo { + struct work_struct wk; + struct kobject *kobj; + + unsigned int flags; /* see wkq.h */ + + au_wkq_func_t func; + void *args; + +#ifdef CONFIG_LOCKDEP + int dont_check; + struct held_lock **hlock; +#endif + + struct completion *comp; +}; + +/* ---------------------------------------------------------------------- */ +/* + * Aufs passes some operations to the workqueue such as the internal copyup. + * This scheme looks rather unnatural for LOCKDEP debugging feature, since the + * job run by workqueue depends upon the locks acquired in the other task. + * Delegating a small operation to the workqueue, aufs passes its lockdep + * information too. And the job in the workqueue restores the info in order to + * pretend as if it acquired those locks. This is just to make LOCKDEP work + * correctly and expectedly. + */ + +#ifndef CONFIG_LOCKDEP +AuStubInt0(au_wkq_lockdep_alloc, struct au_wkinfo *wkinfo); +AuStubVoid(au_wkq_lockdep_free, struct au_wkinfo *wkinfo); +AuStubVoid(au_wkq_lockdep_pre, struct au_wkinfo *wkinfo); +AuStubVoid(au_wkq_lockdep_post, struct au_wkinfo *wkinfo); +AuStubVoid(au_wkq_lockdep_init, struct au_wkinfo *wkinfo); +#else +static void au_wkq_lockdep_init(struct au_wkinfo *wkinfo) +{ + wkinfo->hlock = NULL; + wkinfo->dont_check = 0; +} + +/* + * 1: matched + * 0: unmatched + */ +static int au_wkq_lockdep_test(struct lock_class_key *key, const char *name) +{ + static DEFINE_SPINLOCK(spin); + static struct { + char *name; + struct lock_class_key *key; + } a[] = { + { .name = "&sbinfo->si_rwsem" }, + { .name = "&finfo->fi_rwsem" }, + { .name = "&dinfo->di_rwsem" }, + { .name = "&iinfo->ii_rwsem" } + }; + static int set; + int i; + + /* lockless read from 'set.' see below */ + if (set == ARRAY_SIZE(a)) { + for (i = 0; i < ARRAY_SIZE(a); i++) + if (a[i].key == key) + goto match; + goto unmatch; + } + + spin_lock(&spin); + if (set) + for (i = 0; i < ARRAY_SIZE(a); i++) + if (a[i].key == key) { + spin_unlock(&spin); + goto match; + } + for (i = 0; i < ARRAY_SIZE(a); i++) { + if (a[i].key) { + if (unlikely(a[i].key == key)) { /* rare but possible */ + spin_unlock(&spin); + goto match; + } else + continue; + } + if (strstr(a[i].name, name)) { + /* + * the order of these three lines is important for the + * lockless read above. + */ + a[i].key = key; + spin_unlock(&spin); + set++; + /* AuDbg("%d, %s\n", set, name); */ + goto match; + } + } + spin_unlock(&spin); + goto unmatch; + +match: + return 1; +unmatch: + return 0; +} + +static int au_wkq_lockdep_alloc(struct au_wkinfo *wkinfo) +{ + int err, n; + struct task_struct *curr; + struct held_lock **hl, *held_locks, *p; + + err = 0; + curr = current; + wkinfo->dont_check = lockdep_recursing(curr); + if (wkinfo->dont_check) + goto out; + n = curr->lockdep_depth; + if (!n) + goto out; + + err = -ENOMEM; + wkinfo->hlock = kmalloc_array(n + 1, sizeof(*wkinfo->hlock), GFP_NOFS); + if (unlikely(!wkinfo->hlock)) + goto out; + + err = 0; +#if 0 /* left for debugging */ + if (0 && au_debug_test()) + lockdep_print_held_locks(curr); +#endif + held_locks = curr->held_locks; + hl = wkinfo->hlock; + while (n--) { + p = held_locks++; + if (au_wkq_lockdep_test(p->instance->key, p->instance->name)) + *hl++ = p; + } + *hl = NULL; + +out: + return err; +} + +static void au_wkq_lockdep_free(struct au_wkinfo *wkinfo) +{ + au_kfree_try_rcu(wkinfo->hlock); +} + +static void au_wkq_lockdep_pre(struct au_wkinfo *wkinfo) +{ + struct held_lock *p, **hl = wkinfo->hlock; + int subclass; + + if (wkinfo->dont_check) + lockdep_off(); + if (!hl) + return; + while ((p = *hl++)) { /* assignment */ + subclass = lockdep_hlock_class(p)->subclass; + /* AuDbg("%s, %d\n", p->instance->name, subclass); */ + if (p->read) + rwsem_acquire_read(p->instance, subclass, 0, + /*p->acquire_ip*/_RET_IP_); + else + rwsem_acquire(p->instance, subclass, 0, + /*p->acquire_ip*/_RET_IP_); + } +} + +static void au_wkq_lockdep_post(struct au_wkinfo *wkinfo) +{ + struct held_lock *p, **hl = wkinfo->hlock; + + if (wkinfo->dont_check) + lockdep_on(); + if (!hl) + return; + while ((p = *hl++)) /* assignment */ + rwsem_release(p->instance, /*p->acquire_ip*/_RET_IP_); +} +#endif + +static void wkq_func(struct work_struct *wk) +{ + struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk); + + AuDebugOn(!uid_eq(current_fsuid(), GLOBAL_ROOT_UID)); + AuDebugOn(rlimit(RLIMIT_FSIZE) != RLIM_INFINITY); + + au_wkq_lockdep_pre(wkinfo); + wkinfo->func(wkinfo->args); + au_wkq_lockdep_post(wkinfo); + if (au_ftest_wkq(wkinfo->flags, WAIT)) + complete(wkinfo->comp); + else { + kobject_put(wkinfo->kobj); + module_put(THIS_MODULE); /* todo: ?? */ + au_kfree_rcu(wkinfo); + } +} + +/* + * Since struct completion is large, try allocating it dynamically. + */ +#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) +{ + au_kfree_rcu(comp); +} + +static void au_wkq_run(struct au_wkinfo *wkinfo) +{ + if (au_ftest_wkq(wkinfo->flags, NEST)) { + if (au_wkq_test()) { + AuWarn1("wkq from wkq, unless silly-rename on NFS," + " due to a dead dir by UDBA," + " or async xino write?\n"); + AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT)); + } + } else + au_dbg_verify_kthread(); + + if (au_ftest_wkq(wkinfo->flags, WAIT)) { + INIT_WORK_ONSTACK(&wkinfo->wk, wkq_func); + queue_work(au_wkq, &wkinfo->wk); + } else { + INIT_WORK(&wkinfo->wk, wkq_func); + schedule_work(&wkinfo->wk); + } +} + +/* + * Be careful. It is easy to make deadlock happen. + * processA: lock, wkq and wait + * processB: wkq and wait, lock in wkq + * --> deadlock + */ +int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args) +{ + int err; + AuWkqCompDeclare(comp); + struct au_wkinfo wkinfo = { + .flags = flags, + .func = func, + .args = args + }; + + err = au_wkq_comp_alloc(&wkinfo, &comp); + if (unlikely(err)) + goto out; + err = au_wkq_lockdep_alloc(&wkinfo); + if (unlikely(err)) + goto out_comp; + if (!err) { + au_wkq_run(&wkinfo); + /* no timeout, no interrupt */ + wait_for_completion(wkinfo.comp); + } + au_wkq_lockdep_free(&wkinfo); + +out_comp: + au_wkq_comp_free(comp); +out: + destroy_work_on_stack(&wkinfo.wk); + return err; +} + +/* + * Note: dget/dput() in func for aufs dentries are not supported. It will be a + * problem in a concurrent umounting. + */ +int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, + unsigned int flags) +{ + 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->kobj = &au_sbi(sb)->si_kobj; + wkinfo->flags = flags & ~AuWkq_WAIT; + wkinfo->func = func; + wkinfo->args = args; + wkinfo->comp = NULL; + au_wkq_lockdep_init(wkinfo); + kobject_get(wkinfo->kobj); + __module_get(THIS_MODULE); /* todo: ?? */ + + au_wkq_run(wkinfo); + } else { + err = -ENOMEM; + au_nwt_done(&au_sbi(sb)->si_nowait); + } + + 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) +{ + destroy_workqueue(au_wkq); +} + +int __init au_wkq_init(void) +{ + int err; + + err = 0; + au_wkq = alloc_workqueue(AUFS_WKQ_NAME, 0, WQ_DFL_ACTIVE); + if (IS_ERR(au_wkq)) + err = PTR_ERR(au_wkq); + else if (!au_wkq) + err = -ENOMEM; + + return err; +} diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h new file mode 100644 index 000000000000..5be76b69d8ff --- /dev/null +++ b/fs/aufs/wkq.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * workqueue for asynchronous/super-io operations + * todo: try new credentials management scheme + */ + +#ifndef __AUFS_WKQ_H__ +#define __AUFS_WKQ_H__ + +#ifdef __KERNEL__ + +#include <linux/wait.h> + +struct super_block; + +/* ---------------------------------------------------------------------- */ + +/* + * 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 AuWkq_NEST (1 << 1) +#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name) +#define au_fset_wkq(flags, name) \ + do { (flags) |= AuWkq_##name; } while (0) +#define au_fclr_wkq(flags, name) \ + do { (flags) &= ~AuWkq_##name; } while (0) + +/* wkq.c */ +int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args); +int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, + unsigned int flags); +void au_nwt_init(struct au_nowait_tasks *nwt); +int __init au_wkq_init(void); +void au_wkq_fin(void); + +/* ---------------------------------------------------------------------- */ + +static inline int au_wkq_test(void) +{ + return current->flags & PF_WQ_WORKER; +} + +static inline int au_wkq_wait(au_wkq_func_t func, void *args) +{ + return au_wkq_do_wait(AuWkq_WAIT, func, args); +} + +static inline void au_nwt_done(struct au_nowait_tasks *nwt) +{ + if (atomic_dec_and_test(&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 --git a/fs/aufs/xattr.c b/fs/aufs/xattr.c new file mode 100644 index 000000000000..103c4275e5fc --- /dev/null +++ b/fs/aufs/xattr.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * handling xattr functions + */ + +#include <linux/fs.h> +#include <linux/posix_acl_xattr.h> +#include <linux/xattr.h> +#include "aufs.h" + +static int au_xattr_ignore(int err, char *name, unsigned int ignore_flags) +{ + if (!ignore_flags) + goto out; + switch (err) { + case -ENOMEM: + case -EDQUOT: + goto out; + } + + if ((ignore_flags & AuBrAttr_ICEX) == AuBrAttr_ICEX) { + err = 0; + goto out; + } + +#define cmp(brattr, prefix) do { \ + if (!strncmp(name, XATTR_##prefix##_PREFIX, \ + XATTR_##prefix##_PREFIX_LEN)) { \ + if (ignore_flags & AuBrAttr_ICEX_##brattr) \ + err = 0; \ + goto out; \ + } \ + } while (0) + + cmp(SEC, SECURITY); + cmp(SYS, SYSTEM); + cmp(TR, TRUSTED); + cmp(USR, USER); +#undef cmp + + if (ignore_flags & AuBrAttr_ICEX_OTH) + err = 0; + +out: + return err; +} + +static const int au_xattr_out_of_list = AuBrAttr_ICEX_OTH << 1; + +static int au_do_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, + char *name, char **buf, unsigned int ignore_flags, + unsigned int verbose) +{ + int err; + ssize_t ssz; + struct inode *h_idst; + + ssz = vfs_getxattr_alloc(h_src, name, buf, 0, GFP_NOFS); + err = ssz; + if (unlikely(err <= 0)) { + if (err == -ENODATA + || (err == -EOPNOTSUPP + && ((ignore_flags & au_xattr_out_of_list) + || (au_test_nfs_noacl(d_inode(h_src)) + && (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) + || !strcmp(name, + XATTR_NAME_POSIX_ACL_DEFAULT)))) + )) + err = 0; + if (err && (verbose || au_debug_test())) + pr_err("%s, err %d\n", name, err); + goto out; + } + + /* unlock it temporary */ + h_idst = d_inode(h_dst); + inode_unlock(h_idst); + err = vfsub_setxattr(h_dst, name, *buf, ssz, /*flags*/0); + inode_lock_nested(h_idst, AuLsc_I_CHILD2); + if (unlikely(err)) { + if (verbose || au_debug_test()) + pr_err("%s, err %d\n", name, err); + err = au_xattr_ignore(err, name, ignore_flags); + } + +out: + return err; +} + +int au_cpup_xattr(struct dentry *h_dst, struct dentry *h_src, int ignore_flags, + unsigned int verbose) +{ + int err, unlocked, acl_access, acl_default; + ssize_t ssz; + struct inode *h_isrc, *h_idst; + char *value, *p, *o, *e; + + /* try stopping to update the source inode while we are referencing */ + /* there should not be the parent-child relationship between them */ + h_isrc = d_inode(h_src); + h_idst = d_inode(h_dst); + inode_unlock(h_idst); + inode_lock_shared_nested(h_isrc, AuLsc_I_CHILD); + inode_lock_nested(h_idst, AuLsc_I_CHILD2); + unlocked = 0; + + /* some filesystems don't list POSIX ACL, for example tmpfs */ + ssz = vfs_listxattr(h_src, NULL, 0); + err = ssz; + if (unlikely(err < 0)) { + AuTraceErr(err); + if (err == -ENODATA + || err == -EOPNOTSUPP) + err = 0; /* ignore */ + goto out; + } + + err = 0; + p = NULL; + o = NULL; + if (ssz) { + err = -ENOMEM; + p = kmalloc(ssz, GFP_NOFS); + o = p; + if (unlikely(!p)) + goto out; + err = vfs_listxattr(h_src, p, ssz); + } + inode_unlock_shared(h_isrc); + unlocked = 1; + AuDbg("err %d, ssz %zd\n", err, ssz); + if (unlikely(err < 0)) + goto out_free; + + err = 0; + e = p + ssz; + value = NULL; + acl_access = 0; + acl_default = 0; + while (!err && p < e) { + acl_access |= !strncmp(p, XATTR_NAME_POSIX_ACL_ACCESS, + sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1); + acl_default |= !strncmp(p, XATTR_NAME_POSIX_ACL_DEFAULT, + sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) + - 1); + err = au_do_cpup_xattr(h_dst, h_src, p, &value, ignore_flags, + verbose); + p += strlen(p) + 1; + } + AuTraceErr(err); + ignore_flags |= au_xattr_out_of_list; + if (!err && !acl_access) { + err = au_do_cpup_xattr(h_dst, h_src, + XATTR_NAME_POSIX_ACL_ACCESS, &value, + ignore_flags, verbose); + AuTraceErr(err); + } + if (!err && !acl_default) { + err = au_do_cpup_xattr(h_dst, h_src, + XATTR_NAME_POSIX_ACL_DEFAULT, &value, + ignore_flags, verbose); + AuTraceErr(err); + } + + au_kfree_try_rcu(value); + +out_free: + au_kfree_try_rcu(o); +out: + if (!unlocked) + inode_unlock_shared(h_isrc); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_smack_reentering(struct super_block *sb) +{ +#if IS_ENABLED(CONFIG_SECURITY_SMACK) || IS_ENABLED(CONFIG_SECURITY_SELINUX) + /* + * as a part of lookup, smack_d_instantiate() is called, and it calls + * i_op->getxattr(). ouch. + */ + return si_pid_test(sb); +#else + return 0; +#endif +} + +enum { + AU_XATTR_LIST, + AU_XATTR_GET +}; + +struct au_lgxattr { + int type; + union { + struct { + char *list; + size_t size; + } list; + struct { + const char *name; + void *value; + size_t size; + } get; + } u; +}; + +static ssize_t au_lgxattr(struct dentry *dentry, struct inode *inode, + struct au_lgxattr *arg) +{ + ssize_t err; + int reenter; + struct path h_path; + struct super_block *sb; + + sb = dentry->d_sb; + reenter = au_smack_reentering(sb); + if (!reenter) { + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + } + err = au_h_path_getattr(dentry, inode, /*force*/1, &h_path, reenter); + if (unlikely(err)) + goto out_si; + if (unlikely(!h_path.dentry)) + /* illegally overlapped or something */ + goto out_di; /* pretending success */ + + /* always topmost entry only */ + switch (arg->type) { + case AU_XATTR_LIST: + err = vfs_listxattr(h_path.dentry, + arg->u.list.list, arg->u.list.size); + break; + case AU_XATTR_GET: + AuDebugOn(d_is_negative(h_path.dentry)); + err = vfs_getxattr(h_path.dentry, + arg->u.get.name, arg->u.get.value, + arg->u.get.size); + break; + } + +out_di: + if (!reenter) + di_read_unlock(dentry, AuLock_IR); +out_si: + if (!reenter) + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size) +{ + struct au_lgxattr arg = { + .type = AU_XATTR_LIST, + .u.list = { + .list = list, + .size = size + }, + }; + + return au_lgxattr(dentry, /*inode*/NULL, &arg); +} + +static ssize_t au_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) +{ + struct au_lgxattr arg = { + .type = AU_XATTR_GET, + .u.get = { + .name = name, + .value = value, + .size = size + }, + }; + + return au_lgxattr(dentry, inode, &arg); +} + +static int au_setxattr(struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) +{ + struct au_sxattr arg = { + .type = AU_XATTR_SET, + .u.set = { + .name = name, + .value = value, + .size = size, + .flags = flags + }, + }; + + return au_sxattr(dentry, inode, &arg); +} + +/* ---------------------------------------------------------------------- */ + +static int au_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return au_getxattr(dentry, inode, name, buffer, size); +} + +static int au_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) +{ + return au_setxattr(dentry, inode, name, value, size, flags); +} + +static const struct xattr_handler au_xattr_handler = { + .name = "", + .prefix = "", + .get = au_xattr_get, + .set = au_xattr_set +}; + +static const struct xattr_handler *au_xattr_handlers[] = { +#ifdef CONFIG_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &au_xattr_handler, /* must be last */ + NULL +}; + +void au_xattr_init(struct super_block *sb) +{ + sb->s_xattr = au_xattr_handlers; +} diff --git a/fs/aufs/xino.c b/fs/aufs/xino.c new file mode 100644 index 000000000000..b3152c0ce0b5 --- /dev/null +++ b/fs/aufs/xino.c @@ -0,0 +1,1966 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * external inode number translation table and bitmap + * + * things to consider + * - the lifetime + * + au_xino object + * + XINO files (xino, xib, xigen) + * + dynamic debugfs entries (xiN) + * + static debugfs entries (xib, xigen) + * + static sysfs entry (xi_path) + * - several entry points to handle them. + * + mount(2) without xino option (default) + * + mount(2) with xino option + * + mount(2) with noxino option + * + umount(2) + * + remount with add/del branches + * + remount with xino/noxino options + */ + +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include "aufs.h" + +static aufs_bindex_t sbr_find_shared(struct super_block *sb, aufs_bindex_t btop, + aufs_bindex_t bbot, + struct super_block *h_sb) +{ + /* todo: try binary-search if the branches are many */ + for (; btop <= bbot; btop++) + if (h_sb == au_sbr_sb(sb, btop)) + return btop; + return -1; +} + +/* + * find another branch who is on the same filesystem of the specified + * branch{@btgt}. search until @bbot. + */ +static aufs_bindex_t is_sb_shared(struct super_block *sb, aufs_bindex_t btgt, + aufs_bindex_t bbot) +{ + aufs_bindex_t bindex; + struct super_block *tgt_sb; + + tgt_sb = au_sbr_sb(sb, btgt); + bindex = sbr_find_shared(sb, /*btop*/0, btgt - 1, tgt_sb); + if (bindex < 0) + bindex = sbr_find_shared(sb, btgt + 1, bbot, tgt_sb); + + return bindex; +} + +/* ---------------------------------------------------------------------- */ + +/* + * stop unnecessary notify events at creating xino files + */ + +aufs_bindex_t au_xi_root(struct super_block *sb, struct dentry *dentry) +{ + aufs_bindex_t bfound, bindex, bbot; + struct dentry *parent; + struct au_branch *br; + + bfound = -1; + parent = dentry->d_parent; /* safe d_parent access */ + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_dentry(br) == parent) { + bfound = bindex; + break; + } + } + + AuDbg("bfound b%d\n", bfound); + return bfound; +} + +struct au_xino_lock_dir { + struct au_hinode *hdir; + struct dentry *parent; + struct inode *dir; +}; + +static struct dentry *au_dget_parent_lock(struct dentry *dentry, + unsigned int lsc) +{ + struct dentry *parent; + struct inode *dir; + + parent = dget_parent(dentry); + dir = d_inode(parent); + inode_lock_nested(dir, lsc); +#if 0 /* it should not happen */ + spin_lock(&dentry->d_lock); + if (unlikely(dentry->d_parent != parent)) { + spin_unlock(&dentry->d_lock); + inode_unlock(dir); + dput(parent); + parent = NULL; + goto out; + } + spin_unlock(&dentry->d_lock); + +out: +#endif + return parent; +} + +static void au_xino_lock_dir(struct super_block *sb, struct path *xipath, + struct au_xino_lock_dir *ldir) +{ + aufs_bindex_t bindex; + + ldir->hdir = NULL; + bindex = au_xi_root(sb, xipath->dentry); + if (bindex >= 0) { + /* rw branch root */ + ldir->hdir = au_hi(d_inode(sb->s_root), bindex); + au_hn_inode_lock_nested(ldir->hdir, AuLsc_I_PARENT); + } else { + /* other */ + ldir->parent = au_dget_parent_lock(xipath->dentry, + AuLsc_I_PARENT); + ldir->dir = d_inode(ldir->parent); + } +} + +static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir) +{ + if (ldir->hdir) + au_hn_inode_unlock(ldir->hdir); + else { + inode_unlock(ldir->dir); + dput(ldir->parent); + } +} + +/* ---------------------------------------------------------------------- */ + +/* + * create and set a new xino file + */ +struct file *au_xino_create(struct super_block *sb, char *fpath, int silent, + int wbrtop) +{ + struct file *file; + struct dentry *h_parent, *d; + struct inode *h_dir, *inode; + int err; + static DEFINE_MUTEX(mtx); + + /* + * at mount-time, and the xino file is the default path, + * hnotify is disabled so we have no notify events to ignore. + * when a user specified the xino, we cannot get au_hdir to be ignored. + */ + if (!wbrtop) + mutex_lock(&mtx); + file = vfsub_filp_open(fpath, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE + /* | __FMODE_NONOTIFY */, + 0666); + if (IS_ERR(file)) { + if (!wbrtop) + mutex_unlock(&mtx); + if (!silent) + pr_err("open %s(%ld)\n", fpath, PTR_ERR(file)); + return file; + } + + /* keep file count */ + err = 0; + d = file->f_path.dentry; + h_parent = au_dget_parent_lock(d, AuLsc_I_PARENT); + if (!wbrtop) + mutex_unlock(&mtx); + /* mnt_want_write() is unnecessary here */ + h_dir = d_inode(h_parent); + inode = file_inode(file); + /* no delegation since it is just created */ + if (inode->i_nlink) + err = vfsub_unlink(h_dir, &file->f_path, /*delegated*/NULL, + /*force*/0); + inode_unlock(h_dir); + dput(h_parent); + if (unlikely(err)) { + if (!silent) + pr_err("unlink %s(%d)\n", fpath, err); + goto out; + } + + err = -EINVAL; + if (unlikely(sb == d->d_sb)) { + if (!silent) + pr_err("%s must be outside\n", fpath); + goto out; + } + if (unlikely(au_test_fs_bad_xino(d->d_sb))) { + if (!silent) + pr_err("xino doesn't support %s(%s)\n", + fpath, au_sbtype(d->d_sb)); + goto out; + } + return file; /* success */ + +out: + fput(file); + file = ERR_PTR(err); + return file; +} + +/* + * create a new xinofile at the same place/path as @base. + */ +struct file *au_xino_create2(struct super_block *sb, struct path *base, + struct file *copy_src) +{ + struct file *file; + struct dentry *dentry, *parent; + struct inode *dir, *delegated; + struct qstr *name; + struct path path; + int err, do_unlock; + struct au_xino_lock_dir ldir; + + do_unlock = 1; + au_xino_lock_dir(sb, base, &ldir); + dentry = base->dentry; + parent = dentry->d_parent; /* dir inode is locked */ + dir = d_inode(parent); + IMustLock(dir); + + name = &dentry->d_name; + path.dentry = vfsub_lookup_one_len(name->name, parent, name->len); + if (IS_ERR(path.dentry)) { + file = (void *)path.dentry; + pr_err("%pd lookup err %ld\n", dentry, PTR_ERR(path.dentry)); + goto out; + } + + /* no need to mnt_want_write() since we call dentry_open() later */ + err = vfs_create(dir, path.dentry, 0666, NULL); + if (unlikely(err)) { + file = ERR_PTR(err); + pr_err("%pd create err %d\n", dentry, err); + goto out_dput; + } + + path.mnt = base->mnt; + file = vfsub_dentry_open(&path, + O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE + /* | __FMODE_NONOTIFY */); + if (IS_ERR(file)) { + pr_err("%pd open err %ld\n", dentry, PTR_ERR(file)); + goto out_dput; + } + + delegated = NULL; + err = vfsub_unlink(dir, &file->f_path, &delegated, /*force*/0); + au_xino_unlock_dir(&ldir); + do_unlock = 0; + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + if (unlikely(err)) { + pr_err("%pd unlink err %d\n", dentry, err); + goto out_fput; + } + + if (copy_src) { + /* no one can touch copy_src xino */ + err = au_copy_file(file, copy_src, vfsub_f_size_read(copy_src)); + if (unlikely(err)) { + pr_err("%pd copy err %d\n", dentry, err); + goto out_fput; + } + } + goto out_dput; /* success */ + +out_fput: + fput(file); + file = ERR_PTR(err); +out_dput: + dput(path.dentry); +out: + if (do_unlock) + au_xino_unlock_dir(&ldir); + return file; +} + +struct file *au_xino_file1(struct au_xino *xi) +{ + struct file *file; + unsigned int u, nfile; + + file = NULL; + nfile = xi->xi_nfile; + for (u = 0; u < nfile; u++) { + file = xi->xi_file[u]; + if (file) + break; + } + + return file; +} + +static int au_xino_file_set(struct au_xino *xi, int idx, struct file *file) +{ + int err; + struct file *f; + void *p; + + if (file) + get_file(file); + + err = 0; + f = NULL; + if (idx < xi->xi_nfile) { + f = xi->xi_file[idx]; + if (f) + fput(f); + } else { + p = au_kzrealloc(xi->xi_file, + sizeof(*xi->xi_file) * xi->xi_nfile, + sizeof(*xi->xi_file) * (idx + 1), + GFP_NOFS, /*may_shrink*/0); + if (p) { + MtxMustLock(&xi->xi_mtx); + xi->xi_file = p; + xi->xi_nfile = idx + 1; + } else { + err = -ENOMEM; + if (file) + fput(file); + goto out; + } + } + xi->xi_file[idx] = file; + +out: + return err; +} + +/* + * if @xinew->xi is not set, then create new xigen file. + */ +struct file *au_xi_new(struct super_block *sb, struct au_xi_new *xinew) +{ + struct file *file; + int err; + + SiMustAnyLock(sb); + + file = au_xino_create2(sb, xinew->base, xinew->copy_src); + if (IS_ERR(file)) { + err = PTR_ERR(file); + pr_err("%s[%d], err %d\n", + xinew->xi ? "xino" : "xigen", + xinew->idx, err); + goto out; + } + + if (xinew->xi) + err = au_xino_file_set(xinew->xi, xinew->idx, file); + else { + BUG(); + /* todo: make xigen file an array */ + /* err = au_xigen_file_set(sb, xinew->idx, file); */ + } + fput(file); + if (unlikely(err)) + file = ERR_PTR(err); + +out: + return file; +} + +/* ---------------------------------------------------------------------- */ + +/* + * truncate xino files + */ +static int au_xino_do_trunc(struct super_block *sb, aufs_bindex_t bindex, + int idx, struct kstatfs *st) +{ + int err; + blkcnt_t blocks; + struct file *file, *new_xino; + struct au_xi_new xinew = { + .idx = idx + }; + + err = 0; + xinew.xi = au_sbr(sb, bindex)->br_xino; + file = au_xino_file(xinew.xi, idx); + if (!file) + goto out; + + xinew.base = &file->f_path; + err = vfs_statfs(xinew.base, st); + if (unlikely(err)) { + AuErr1("statfs err %d, ignored\n", err); + err = 0; + goto out; + } + + blocks = file_inode(file)->i_blocks; + pr_info("begin truncating xino(b%d-%d), ib%llu, %llu/%llu free blks\n", + bindex, idx, (u64)blocks, st->f_bfree, st->f_blocks); + + xinew.copy_src = file; + new_xino = au_xi_new(sb, &xinew); + if (IS_ERR(new_xino)) { + err = PTR_ERR(new_xino); + pr_err("xino(b%d-%d), err %d, ignored\n", bindex, idx, err); + goto out; + } + + err = vfs_statfs(&new_xino->f_path, st); + if (!err) + pr_info("end truncating xino(b%d-%d), ib%llu, %llu/%llu free blks\n", + bindex, idx, (u64)file_inode(new_xino)->i_blocks, + st->f_bfree, st->f_blocks); + else { + AuErr1("statfs err %d, ignored\n", err); + err = 0; + } + +out: + return err; +} + +int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin) +{ + int err, i; + unsigned long jiffy; + aufs_bindex_t bbot; + struct kstatfs *st; + struct au_branch *br; + struct au_xino *xi; + + err = -ENOMEM; + st = kmalloc(sizeof(*st), GFP_NOFS); + if (unlikely(!st)) + goto out; + + err = -EINVAL; + bbot = au_sbbot(sb); + if (unlikely(bindex < 0 || bbot < bindex)) + goto out_st; + + err = 0; + jiffy = jiffies; + br = au_sbr(sb, bindex); + xi = br->br_xino; + for (i = idx_begin; !err && i < xi->xi_nfile; i++) + err = au_xino_do_trunc(sb, bindex, i, st); + if (!err) + au_sbi(sb)->si_xino_jiffy = jiffy; + +out_st: + au_kfree_rcu(st); +out: + return err; +} + +struct xino_do_trunc_args { + struct super_block *sb; + struct au_branch *br; + int idx; +}; + +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, idx; + aufs_bindex_t bindex; + + err = 0; + sb = args->sb; + dir = d_inode(sb->s_root); + br = args->br; + idx = args->idx; + + si_noflush_write_lock(sb); + ii_read_lock_parent(dir); + bindex = au_br_index(sb, br->br_id); + err = au_xino_trunc(sb, bindex, idx); + ii_read_unlock(dir); + if (unlikely(err)) + pr_warn("err b%d, (%d)\n", bindex, err); + atomic_dec(&br->br_xino->xi_truncating); + au_lcnt_dec(&br->br_count); + si_write_unlock(sb); + au_nwt_done(&au_sbi(sb)->si_nowait); + au_kfree_rcu(args); +} + +/* + * returns the index in the xi_file array whose corresponding file is necessary + * to truncate, or -1 which means no need to truncate. + */ +static int xino_trunc_test(struct super_block *sb, struct au_branch *br) +{ + int err; + unsigned int u; + struct kstatfs st; + struct au_sbinfo *sbinfo; + struct au_xino *xi; + struct file *file; + + /* todo: si_xino_expire and the ratio should be customizable */ + sbinfo = au_sbi(sb); + if (time_before(jiffies, + sbinfo->si_xino_jiffy + sbinfo->si_xino_expire)) + return -1; + + /* truncation border */ + xi = br->br_xino; + for (u = 0; u < xi->xi_nfile; u++) { + file = au_xino_file(xi, u); + if (!file) + continue; + + err = vfs_statfs(&file->f_path, &st); + if (unlikely(err)) { + AuErr1("statfs err %d, ignored\n", err); + return -1; + } + if (div64_u64(st.f_bfree * 100, st.f_blocks) + >= AUFS_XINO_DEF_TRUNC) + return u; + } + + return -1; +} + +static void xino_try_trunc(struct super_block *sb, struct au_branch *br) +{ + int idx; + struct xino_do_trunc_args *args; + int wkq_err; + + idx = xino_trunc_test(sb, br); + if (idx < 0) + return; + + if (atomic_inc_return(&br->br_xino->xi_truncating) > 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; + } + + au_lcnt_inc(&br->br_count); + args->sb = sb; + args->br = br; + args->idx = idx; + wkq_err = au_wkq_nowait(xino_do_trunc, args, sb, /*flags*/0); + if (!wkq_err) + return; /* success */ + + pr_err("wkq %d\n", wkq_err); + au_lcnt_dec(&br->br_count); + au_kfree_rcu(args); + +out: + atomic_dec(&br->br_xino->xi_truncating); +} + +/* ---------------------------------------------------------------------- */ + +struct au_xi_calc { + int idx; + loff_t pos; +}; + +static void au_xi_calc(struct super_block *sb, ino_t h_ino, + struct au_xi_calc *calc) +{ + loff_t maxent; + + maxent = au_xi_maxent(sb); + calc->idx = div64_u64_rem(h_ino, maxent, &calc->pos); + calc->pos *= sizeof(ino_t); +} + +static int au_xino_do_new_async(struct super_block *sb, struct au_branch *br, + struct au_xi_calc *calc) +{ + int err; + struct file *file; + struct au_xino *xi = br->br_xino; + struct au_xi_new xinew = { + .xi = xi + }; + + SiMustAnyLock(sb); + + err = 0; + if (!xi) + goto out; + + mutex_lock(&xi->xi_mtx); + file = au_xino_file(xi, calc->idx); + if (file) + goto out_mtx; + + file = au_xino_file(xi, /*idx*/-1); + AuDebugOn(!file); + xinew.idx = calc->idx; + xinew.base = &file->f_path; + /* xinew.copy_src = NULL; */ + file = au_xi_new(sb, &xinew); + if (IS_ERR(file)) + err = PTR_ERR(file); + +out_mtx: + mutex_unlock(&xi->xi_mtx); +out: + return err; +} + +struct au_xino_do_new_async_args { + struct super_block *sb; + struct au_branch *br; + struct au_xi_calc calc; + ino_t ino; +}; + +struct au_xi_writing { + struct hlist_bl_node node; + ino_t h_ino, ino; +}; + +static int au_xino_do_write(vfs_writef_t write, struct file *file, + struct au_xi_calc *calc, ino_t ino); + +static void au_xino_call_do_new_async(void *args) +{ + struct au_xino_do_new_async_args *a = args; + struct au_branch *br; + struct super_block *sb; + struct au_sbinfo *sbi; + struct inode *root; + struct file *file; + struct au_xi_writing *del, *p; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + int err; + + br = a->br; + sb = a->sb; + sbi = au_sbi(sb); + si_noflush_read_lock(sb); + root = d_inode(sb->s_root); + ii_read_lock_child(root); + err = au_xino_do_new_async(sb, br, &a->calc); + if (unlikely(err)) { + AuIOErr("err %d\n", err); + goto out; + } + + file = au_xino_file(br->br_xino, a->calc.idx); + AuDebugOn(!file); + err = au_xino_do_write(sbi->si_xwrite, file, &a->calc, a->ino); + if (unlikely(err)) { + AuIOErr("err %d\n", err); + goto out; + } + + del = NULL; + hbl = &br->br_xino->xi_writing; + hlist_bl_lock(hbl); + au_hbl_for_each(pos, hbl) { + p = container_of(pos, struct au_xi_writing, node); + if (p->ino == a->ino) { + del = p; + hlist_bl_del(&p->node); + break; + } + } + hlist_bl_unlock(hbl); + au_kfree_rcu(del); + +out: + au_lcnt_dec(&br->br_count); + ii_read_unlock(root); + si_read_unlock(sb); + au_nwt_done(&sbi->si_nowait); + au_kfree_rcu(a); +} + +/* + * create a new xino file asynchronously + */ +static int au_xino_new_async(struct super_block *sb, struct au_branch *br, + struct au_xi_calc *calc, ino_t ino) +{ + int err; + struct au_xino_do_new_async_args *arg; + + err = -ENOMEM; + arg = kmalloc(sizeof(*arg), GFP_NOFS); + if (unlikely(!arg)) + goto out; + + arg->sb = sb; + arg->br = br; + arg->calc = *calc; + arg->ino = ino; + au_lcnt_inc(&br->br_count); + err = au_wkq_nowait(au_xino_call_do_new_async, arg, sb, AuWkq_NEST); + if (unlikely(err)) { + pr_err("wkq %d\n", err); + au_lcnt_dec(&br->br_count); + au_kfree_rcu(arg); + } + +out: + return err; +} + +/* + * read @ino from xinofile for the specified branch{@sb, @bindex} + * at the position of @h_ino. + */ +int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t *ino) +{ + int err; + ssize_t sz; + struct au_xi_calc calc; + struct au_sbinfo *sbinfo; + struct file *file; + struct au_xino *xi; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_xi_writing *p; + + *ino = 0; + if (!au_opt_test(au_mntflags(sb), XINO)) + return 0; /* no xino */ + + err = 0; + au_xi_calc(sb, h_ino, &calc); + xi = au_sbr(sb, bindex)->br_xino; + file = au_xino_file(xi, calc.idx); + if (!file) { + hbl = &xi->xi_writing; + hlist_bl_lock(hbl); + au_hbl_for_each(pos, hbl) { + p = container_of(pos, struct au_xi_writing, node); + if (p->h_ino == h_ino) { + AuDbg("hi%llu, i%llu, found\n", + (u64)p->h_ino, (u64)p->ino); + *ino = p->ino; + break; + } + } + hlist_bl_unlock(hbl); + return 0; + } else if (vfsub_f_size_read(file) < calc.pos + sizeof(*ino)) + return 0; /* no xino */ + + sbinfo = au_sbi(sb); + sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &calc.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; +} + +static int au_xino_do_write(vfs_writef_t write, struct file *file, + struct au_xi_calc *calc, ino_t ino) +{ + ssize_t sz; + + sz = xino_fwrite(write, file, &ino, sizeof(ino), &calc->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_xi_calc calc; + struct file *file; + struct au_branch *br; + struct au_xino *xi; + struct au_xi_writing *p; + + SiMustAnyLock(sb); + + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, XINO)) + return 0; + + au_xi_calc(sb, h_ino, &calc); + br = au_sbr(sb, bindex); + xi = br->br_xino; + file = au_xino_file(xi, calc.idx); + if (!file) { + /* store the inum pair into the list */ + p = kmalloc(sizeof(*p), GFP_NOFS | __GFP_NOFAIL); + p->h_ino = h_ino; + p->ino = ino; + au_hbl_add(&p->node, &xi->xi_writing); + + /* create and write a new xino file asynchronously */ + err = au_xino_new_async(sb, br, &calc, ino); + if (!err) + return 0; /* success */ + goto out; + } + + err = au_xino_do_write(au_sbi(sb)->si_xwrite, file, &calc, ino); + if (!err) { + br = au_sbr(sb, bindex); + if (au_opt_test(mnt_flags, TRUNC_XINO) + && au_test_fs_trunc_xino(au_br_sb(br))) + xino_try_trunc(sb, br); + return 0; /* success */ + } + +out: + AuIOErr("write failed (%d)\n", err); + return -EIO; +} + +static ssize_t xino_fread_wkq(vfs_readf_t func, struct file *file, void *buf, + size_t size, loff_t *pos); + +/* todo: unnecessary to support mmap_sem since kernel-space? */ +ssize_t xino_fread(vfs_readf_t func, struct file *file, void *kbuf, size_t size, + loff_t *pos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + char __user *u; + } buf; + int i; + const int prevent_endless = 10; + + i = 0; + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + do { + err = func(file, buf.u, size, pos); + if (err == -EINTR + && !au_wkq_test() + && fatal_signal_pending(current)) { + set_fs(oldfs); + err = xino_fread_wkq(func, file, kbuf, size, pos); + BUG_ON(err == -EINTR); + oldfs = get_fs(); + set_fs(KERNEL_DS); + } + } while (i++ < prevent_endless + && (err == -EAGAIN || err == -EINTR)); + set_fs(oldfs); + +#if 0 /* reserved for future use */ + if (err > 0) + fsnotify_access(file->f_path.dentry); +#endif + + return err; +} + +struct xino_fread_args { + ssize_t *errp; + vfs_readf_t func; + struct file *file; + void *buf; + size_t size; + loff_t *pos; +}; + +static void call_xino_fread(void *args) +{ + struct xino_fread_args *a = args; + *a->errp = xino_fread(a->func, a->file, a->buf, a->size, a->pos); +} + +static ssize_t xino_fread_wkq(vfs_readf_t func, struct file *file, void *buf, + size_t size, loff_t *pos) +{ + ssize_t err; + int wkq_err; + struct xino_fread_args args = { + .errp = &err, + .func = func, + .file = file, + .buf = buf, + .size = size, + .pos = pos + }; + + wkq_err = au_wkq_wait(call_xino_fread, &args); + if (unlikely(wkq_err)) + err = wkq_err; + + return err; +} + +static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf, + size_t size, loff_t *pos); + +static ssize_t do_xino_fwrite(vfs_writef_t func, struct file *file, void *kbuf, + size_t size, loff_t *pos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + const char __user *u; + } buf; + int i; + const int prevent_endless = 10; + + i = 0; + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + do { + err = func(file, buf.u, size, pos); + if (err == -EINTR + && !au_wkq_test() + && fatal_signal_pending(current)) { + set_fs(oldfs); + err = xino_fwrite_wkq(func, file, kbuf, size, pos); + BUG_ON(err == -EINTR); + oldfs = get_fs(); + set_fs(KERNEL_DS); + } + } while (i++ < prevent_endless + && (err == -EAGAIN || err == -EINTR)); + set_fs(oldfs); + +#if 0 /* reserved for future use */ + if (err > 0) + fsnotify_modify(file->f_path.dentry); +#endif + + return err; +} + +struct do_xino_fwrite_args { + ssize_t *errp; + vfs_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); +} + +static ssize_t xino_fwrite_wkq(vfs_writef_t func, struct file *file, void *buf, + size_t size, loff_t *pos) +{ + ssize_t err; + int wkq_err; + struct do_xino_fwrite_args args = { + .errp = &err, + .func = func, + .file = file, + .buf = buf, + .size = size, + .pos = pos + }; + + /* + * it breaks RLIMIT_FSIZE and normal user's limit, + * users should care about quota and real 'filesystem full.' + */ + wkq_err = au_wkq_wait(call_do_xino_fwrite, &args); + if (unlikely(wkq_err)) + err = wkq_err; + + return err; +} + +ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, + size_t size, loff_t *pos) +{ + ssize_t err; + + if (rlimit(RLIMIT_FSIZE) == RLIM_INFINITY) { + lockdep_off(); + err = do_xino_fwrite(func, file, buf, size, pos); + lockdep_on(); + } else { + lockdep_off(); + err = xino_fwrite_wkq(func, file, buf, size, pos); + lockdep_on(); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * 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 (vfsub_f_size_read(xib) >= 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; +} + +static void au_xib_clear_bit(struct inode *inode) +{ + int err, bit; + unsigned long pindex; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + AuDebugOn(inode->i_nlink); + + sb = inode->i_sb; + xib_calc_bit(inode->i_ino, &pindex, &bit); + AuDebugOn(page_bits <= bit); + sbinfo = au_sbi(sb); + 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); +} + +/* ---------------------------------------------------------------------- */ + +/* + * truncate 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; + vfs_readf_t func; + ino_t *ino; + unsigned long *p; + + err = 0; + sbinfo = au_sbi(sb); + MtxMustLock(&sbinfo->si_xib_mtx); + p = sbinfo->si_xib_buf; + func = sbinfo->si_xread; + pend = vfsub_f_size_read(file); + 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, i; + unsigned int nfile; + aufs_bindex_t bindex, bbot; + void *page; + struct au_branch *br; + struct au_xino *xi; + struct file *file; + + err = -ENOMEM; + page = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!page)) + goto out; + + err = 0; + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) + if (!bindex || is_sb_shared(sb, bindex, bindex - 1) < 0) { + br = au_sbr(sb, bindex); + xi = br->br_xino; + nfile = xi->xi_nfile; + for (i = 0; i < nfile; i++) { + file = au_xino_file(xi, i); + if (file) + err = do_xib_restore(sb, file, page); + } + } else + AuDbg("skip shared 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_sbinfo *sbinfo; + unsigned long *p; + struct file *file; + + SiMustWriteLock(sb); + + err = 0; + sbinfo = au_sbi(sb); + if (!au_opt_test(sbinfo->si_mntflags, XINO)) + goto out; + + file = sbinfo->si_xib; + if (vfsub_f_size_read(file) <= PAGE_SIZE) + goto out; + + file = au_xino_create2(sb, &sbinfo->si_xib->f_path, NULL); + 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; +} + +/* ---------------------------------------------------------------------- */ + +struct au_xino *au_xino_alloc(unsigned int nfile) +{ + struct au_xino *xi; + + xi = kzalloc(sizeof(*xi), GFP_NOFS); + if (unlikely(!xi)) + goto out; + xi->xi_nfile = nfile; + xi->xi_file = kcalloc(nfile, sizeof(*xi->xi_file), GFP_NOFS); + if (unlikely(!xi->xi_file)) + goto out_free; + + xi->xi_nondir.total = 8; /* initial size */ + xi->xi_nondir.array = kcalloc(xi->xi_nondir.total, sizeof(ino_t), + GFP_NOFS); + if (unlikely(!xi->xi_nondir.array)) + goto out_file; + + spin_lock_init(&xi->xi_nondir.spin); + init_waitqueue_head(&xi->xi_nondir.wqh); + mutex_init(&xi->xi_mtx); + INIT_HLIST_BL_HEAD(&xi->xi_writing); + atomic_set(&xi->xi_truncating, 0); + kref_init(&xi->xi_kref); + goto out; /* success */ + +out_file: + au_kfree_try_rcu(xi->xi_file); +out_free: + au_kfree_rcu(xi); + xi = NULL; +out: + return xi; +} + +static int au_xino_init(struct au_branch *br, int idx, struct file *file) +{ + int err; + struct au_xino *xi; + + err = 0; + xi = au_xino_alloc(idx + 1); + if (unlikely(!xi)) { + err = -ENOMEM; + goto out; + } + + if (file) + get_file(file); + xi->xi_file[idx] = file; + AuDebugOn(br->br_xino); + br->br_xino = xi; + +out: + return err; +} + +static void au_xino_release(struct kref *kref) +{ + struct au_xino *xi; + int i; + unsigned long ul; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos, *n; + struct au_xi_writing *p; + + xi = container_of(kref, struct au_xino, xi_kref); + for (i = 0; i < xi->xi_nfile; i++) + if (xi->xi_file[i]) + fput(xi->xi_file[i]); + for (i = xi->xi_nondir.total - 1; i >= 0; i--) + AuDebugOn(xi->xi_nondir.array[i]); + mutex_destroy(&xi->xi_mtx); + hbl = &xi->xi_writing; + ul = au_hbl_count(hbl); + if (unlikely(ul)) { + pr_warn("xi_writing %lu\n", ul); + hlist_bl_lock(hbl); + hlist_bl_for_each_entry_safe(p, pos, n, hbl, node) { + hlist_bl_del(&p->node); + /* kmemleak reported au_kfree_rcu() doesn't free it */ + kfree(p); + } + hlist_bl_unlock(hbl); + } + au_kfree_try_rcu(xi->xi_file); + au_kfree_try_rcu(xi->xi_nondir.array); + au_kfree_rcu(xi); +} + +int au_xino_put(struct au_branch *br) +{ + int ret; + struct au_xino *xi; + + ret = 0; + xi = br->br_xino; + if (xi) { + br->br_xino = NULL; + ret = kref_put(&xi->xi_kref, au_xino_release); + } + + return ret; +} + +/* ---------------------------------------------------------------------- */ + +/* + * xino mount option handlers + */ + +/* xino bitmap */ +static void xino_clear_xib(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + /* unnecessary to clear sbinfo->si_xread and ->si_xwrite */ + if (sbinfo->si_xib) + fput(sbinfo->si_xib); + sbinfo->si_xib = NULL; + if (sbinfo->si_xib_buf) + free_page((unsigned long)sbinfo->si_xib_buf); + sbinfo->si_xib_buf = NULL; +} + +static int au_xino_set_xib(struct super_block *sb, struct path *path) +{ + int err; + loff_t pos; + struct au_sbinfo *sbinfo; + struct file *file; + struct super_block *xi_sb; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + file = au_xino_create2(sb, path, 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 = vfs_readf(file); + sbinfo->si_xwrite = vfs_writef(file); + xi_sb = file_inode(file)->i_sb; + sbinfo->si_ximaxent = xi_sb->s_maxbytes; + if (unlikely(sbinfo->si_ximaxent < PAGE_SIZE)) { + err = -EIO; + pr_err("s_maxbytes(%llu) on %s is too small\n", + (u64)sbinfo->si_ximaxent, au_sbtype(xi_sb)); + goto out_unset; + } + sbinfo->si_ximaxent /= sizeof(ino_t); + + 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 (vfsub_f_size_read(file) < 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: + if (sbinfo->si_xib_buf) + 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; +out: + AuTraceErr(err); + return err; +} + +/* xino for each branch */ +static void xino_clear_br(struct super_block *sb) +{ + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + AuDebugOn(!br); + au_xino_put(br); + } +} + +static void au_xino_set_br_shared(struct super_block *sb, struct au_branch *br, + aufs_bindex_t bshared) +{ + struct au_branch *brshared; + + brshared = au_sbr(sb, bshared); + AuDebugOn(!brshared->br_xino); + AuDebugOn(!brshared->br_xino->xi_file); + if (br->br_xino != brshared->br_xino) { + au_xino_get(brshared); + au_xino_put(br); + br->br_xino = brshared->br_xino; + } +} + +struct au_xino_do_set_br { + vfs_writef_t writef; + struct au_branch *br; + ino_t h_ino; + aufs_bindex_t bshared; +}; + +static int au_xino_do_set_br(struct super_block *sb, struct path *path, + struct au_xino_do_set_br *args) +{ + int err; + struct au_xi_calc calc; + struct file *file; + struct au_branch *br; + struct au_xi_new xinew = { + .base = path + }; + + br = args->br; + xinew.xi = br->br_xino; + au_xi_calc(sb, args->h_ino, &calc); + xinew.copy_src = au_xino_file(xinew.xi, calc.idx); + if (args->bshared >= 0) + /* shared xino */ + au_xino_set_br_shared(sb, br, args->bshared); + else if (!xinew.xi) { + /* new xino */ + err = au_xino_init(br, calc.idx, xinew.copy_src); + if (unlikely(err)) + goto out; + } + + /* force re-creating */ + xinew.xi = br->br_xino; + xinew.idx = calc.idx; + mutex_lock(&xinew.xi->xi_mtx); + file = au_xi_new(sb, &xinew); + mutex_unlock(&xinew.xi->xi_mtx); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + AuDebugOn(!file); + + err = au_xino_do_write(args->writef, file, &calc, AUFS_ROOT_INO); + if (unlikely(err)) + au_xino_put(br); + +out: + AuTraceErr(err); + return err; +} + +static int au_xino_set_br(struct super_block *sb, struct path *path) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_xino_do_set_br args; + struct inode *inode; + + SiMustWriteLock(sb); + + bbot = au_sbbot(sb); + inode = d_inode(sb->s_root); + args.writef = au_sbi(sb)->si_xwrite; + for (bindex = 0; bindex <= bbot; bindex++) { + args.h_ino = au_h_iptr(inode, bindex)->i_ino; + args.br = au_sbr(sb, bindex); + args.bshared = is_sb_shared(sb, bindex, bindex - 1); + err = au_xino_do_set_br(sb, path, &args); + if (unlikely(err)) + break; + } + + AuTraceErr(err); + 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); + dbgaufs_brs_del(sb, 0); + 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 *xiopt, int remount) +{ + int err, skip; + struct dentry *dentry, *parent, *cur_dentry, *cur_parent; + struct qstr *dname, *cur_name; + struct file *cur_xino; + struct au_sbinfo *sbinfo; + struct path *path, *cur_path; + + SiMustWriteLock(sb); + + err = 0; + sbinfo = au_sbi(sb); + path = &xiopt->file->f_path; + dentry = path->dentry; + parent = dget_parent(dentry); + if (remount) { + skip = 0; + cur_xino = sbinfo->si_xib; + if (cur_xino) { + cur_path = &cur_xino->f_path; + cur_dentry = cur_path->dentry; + cur_parent = dget_parent(cur_dentry); + cur_name = &cur_dentry->d_name; + dname = &dentry->d_name; + skip = (cur_parent == parent + && au_qstreq(dname, cur_name)); + dput(cur_parent); + } + if (skip) + goto out; + } + + au_opt_set(sbinfo->si_mntflags, XINO); + err = au_xino_set_xib(sb, path); + /* si_x{read,write} are set */ + if (!err) + err = au_xigen_set(sb, path); + if (!err) + err = au_xino_set_br(sb, path); + if (!err) { + dbgaufs_brs_add(sb, 0, /*topdown*/1); + goto out; /* success */ + } + + /* reset all */ + AuIOErr("failed setting xino(%d).\n", err); + au_xino_clr(sb); + +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 bbot, bindex, bwr; + + br = NULL; + bbot = au_sbbot(sb); + bwr = -1; + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm) + && !au_test_fs_bad_xino(au_br_sb(br))) { + bwr = bindex; + break; + } + } + + if (bwr >= 0) { + file = ERR_PTR(-ENOMEM); + page = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!page)) + goto out; + path.mnt = au_br_mnt(br); + 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, /*wbrtop*/1); + } + free_page((unsigned long)page); + } else { + file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0, + /*wbrtop*/0); + if (IS_ERR(file)) + goto out; + h_sb = file->f_path.dentry->d_sb; + if (unlikely(au_test_fs_bad_xino(h_sb))) { + pr_err("xino doesn't support %s(%s)\n", + AUFS_XINO_DEFPATH, au_sbtype(h_sb)); + fput(file); + file = ERR_PTR(-EINVAL); + } + } + +out: + return file; +} + +/* ---------------------------------------------------------------------- */ + +/* + * 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 found then share the xinofile with another branch. + */ +int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t h_ino, + struct path *base) +{ + int err; + struct au_xino_do_set_br args = { + .h_ino = h_ino, + .br = br + }; + + args.writef = au_sbi(sb)->si_xwrite; + args.bshared = sbr_find_shared(sb, /*btop*/0, au_sbbot(sb), + au_br_sb(br)); + err = au_xino_do_set_br(sb, base, &args); + if (unlikely(err)) + au_xino_put(br); + + 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 = vfsub_f_size_read(file) / 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 = free_bit + 1; + 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; +} + +/* for s_op->delete_inode() */ +void au_xino_delete_inode(struct inode *inode, const int unlinked) +{ + int err; + unsigned int mnt_flags; + aufs_bindex_t bindex, bbot, bi; + unsigned char try_trunc; + struct au_iinfo *iinfo; + struct super_block *sb; + struct au_hinode *hi; + struct inode *h_inode; + struct au_branch *br; + vfs_writef_t xwrite; + struct au_xi_calc calc; + struct file *file; + + AuDebugOn(au_is_bad_inode(inode)); + + sb = inode->i_sb; + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, XINO) + || inode->i_ino == AUFS_ROOT_INO) + return; + + if (unlinked) { + au_xigen_inc(inode); + au_xib_clear_bit(inode); + } + + iinfo = au_ii(inode); + bindex = iinfo->ii_btop; + if (bindex < 0) + return; + + xwrite = au_sbi(sb)->si_xwrite; + try_trunc = !!au_opt_test(mnt_flags, TRUNC_XINO); + hi = au_hinode(iinfo, bindex); + bbot = iinfo->ii_bbot; + for (; bindex <= bbot; bindex++, hi++) { + h_inode = hi->hi_inode; + if (!h_inode + || (!unlinked && h_inode->i_nlink)) + continue; + + /* inode may not be revalidated */ + bi = au_br_index(sb, hi->hi_id); + if (bi < 0) + continue; + + br = au_sbr(sb, bi); + au_xi_calc(sb, h_inode->i_ino, &calc); + file = au_xino_file(br->br_xino, calc.idx); + if (IS_ERR_OR_NULL(file)) + continue; + + err = au_xino_do_write(xwrite, file, &calc, /*ino*/0); + if (!err && try_trunc + && au_test_fs_trunc_xino(au_br_sb(br))) + xino_try_trunc(sb, br); + } +} + +/* ---------------------------------------------------------------------- */ + +static int au_xinondir_find(struct au_xino *xi, ino_t h_ino) +{ + int found, total, i; + + found = -1; + total = xi->xi_nondir.total; + for (i = 0; i < total; i++) { + if (xi->xi_nondir.array[i] != h_ino) + continue; + found = i; + break; + } + + return found; +} + +static int au_xinondir_expand(struct au_xino *xi) +{ + int err, sz; + ino_t *p; + + BUILD_BUG_ON(KMALLOC_MAX_SIZE > INT_MAX); + + err = -ENOMEM; + sz = xi->xi_nondir.total * sizeof(ino_t); + if (unlikely(sz > KMALLOC_MAX_SIZE / 2)) + goto out; + p = au_kzrealloc(xi->xi_nondir.array, sz, sz << 1, GFP_ATOMIC, + /*may_shrink*/0); + if (p) { + xi->xi_nondir.array = p; + xi->xi_nondir.total <<= 1; + AuDbg("xi_nondir.total %d\n", xi->xi_nondir.total); + err = 0; + } + +out: + return err; +} + +void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, + ino_t h_ino, int idx) +{ + struct au_xino *xi; + + AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); + xi = au_sbr(sb, bindex)->br_xino; + AuDebugOn(idx < 0 || xi->xi_nondir.total <= idx); + + spin_lock(&xi->xi_nondir.spin); + AuDebugOn(xi->xi_nondir.array[idx] != h_ino); + xi->xi_nondir.array[idx] = 0; + spin_unlock(&xi->xi_nondir.spin); + wake_up_all(&xi->xi_nondir.wqh); +} + +int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + int *idx) +{ + int err, found, empty; + struct au_xino *xi; + + err = 0; + *idx = -1; + if (!au_opt_test(au_mntflags(sb), XINO)) + goto out; /* no xino */ + + xi = au_sbr(sb, bindex)->br_xino; + +again: + spin_lock(&xi->xi_nondir.spin); + found = au_xinondir_find(xi, h_ino); + if (found == -1) { + empty = au_xinondir_find(xi, /*h_ino*/0); + if (empty == -1) { + empty = xi->xi_nondir.total; + err = au_xinondir_expand(xi); + if (unlikely(err)) + goto out_unlock; + } + xi->xi_nondir.array[empty] = h_ino; + *idx = empty; + } else { + spin_unlock(&xi->xi_nondir.spin); + wait_event(xi->xi_nondir.wqh, + xi->xi_nondir.array[found] != h_ino); + goto again; + } + +out_unlock: + spin_unlock(&xi->xi_nondir.spin); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_xino_path(struct seq_file *seq, struct file *file) +{ + int err; + + err = au_seq_path(seq, &file->f_path); + if (unlikely(err)) + goto out; + +#define Deleted "\\040(deleted)" + seq->count -= sizeof(Deleted) - 1; + AuDebugOn(memcmp(seq->buf + seq->count, Deleted, + sizeof(Deleted) - 1)); +#undef Deleted + +out: + return err; +} diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index 8bbb734f3f51..49384d55a908 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -48,6 +48,7 @@ enum { IO_TREE_INODE_FILE_EXTENT, IO_TREE_LOG_CSUM_RANGE, IO_TREE_SELFTEST, + IO_TREE_DEVICE_ALLOC_STATE, }; struct extent_io_tree { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 79e9a80bd37a..f9d8bd309948 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -406,7 +406,7 @@ void __exit btrfs_cleanup_fs_uuids(void) * Returned struct is not linked onto any lists and must be destroyed using * btrfs_free_device. */ -static struct btrfs_device *__alloc_device(void) +static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) { struct btrfs_device *dev; @@ -433,7 +433,8 @@ static struct btrfs_device *__alloc_device(void) btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); - extent_io_tree_init(NULL, &dev->alloc_state, 0, NULL); + extent_io_tree_init(fs_info, &dev->alloc_state, + IO_TREE_DEVICE_ALLOC_STATE, NULL); return dev; } @@ -6545,7 +6546,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, if (WARN_ON(!devid && !fs_info)) return ERR_PTR(-EINVAL); - dev = __alloc_device(); + dev = __alloc_device(fs_info); if (IS_ERR(dev)) return dev; diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 689162e2e175..3150c19cdc2f 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -530,8 +530,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -541,8 +541,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 1\n", + cls, con, tag, end); return 0; } @@ -552,8 +552,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_CTX) || (con != ASN1_CON) || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 0\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", + cls, con, tag, end); return 0; } @@ -564,8 +564,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p (%d) exit 1\n", - cls, con, tag, end, *end); + cifs_dbg(FYI, "cls = %d con = %d tag = %d sequence_end = %p exit 1\n", + cls, con, tag, sequence_end); return 0; } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 6025d7fc7bbf..d0658891b0a6 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -338,7 +338,7 @@ invalidate_key: goto out_key_put; } -static int +int sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid, struct cifs_fattr *fattr, uint sidtype) { @@ -359,7 +359,8 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid, return -EIO; } - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) { + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) || + (cifs_sb_master_tcon(cifs_sb)->posix_extensions)) { uint32_t unix_id; bool is_group; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 7a836ec0438e..f4751cb39123 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -208,6 +208,8 @@ extern int cifs_set_file_info(struct inode *inode, struct iattr *attrs, extern int cifs_rename_pending_delete(const char *full_path, struct dentry *dentry, const unsigned int xid); +extern int sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid, + struct cifs_fattr *fattr, uint sidtype); extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct inode *inode, bool get_mode_from_special_sid, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a61abde09ffe..f4ecc13b02c0 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3594,7 +3594,10 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) */ tcon->retry = volume_info->retry; tcon->nocase = volume_info->nocase; - tcon->nohandlecache = volume_info->nohandlecache; + if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) + tcon->nohandlecache = volume_info->nohandlecache; + else + tcon->nohandlecache = 1; tcon->nodelete = volume_info->nodelete; tcon->local_lease = volume_info->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 6df0922e7e30..709fb53e9fee 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -267,9 +267,8 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, if (reparse_file_needs_reval(fattr)) fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; - /* TODO map SIDs */ - fattr->cf_uid = cifs_sb->mnt_uid; - fattr->cf_gid = cifs_sb->mnt_gid; + sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); + sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); } static void __dir_info_to_fattr(struct cifs_fattr *fattr, const void *info) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index d44df8f95bcd..09e1cd320ee5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3072,7 +3072,12 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, oparms.tcon = tcon; oparms.desired_access = READ_CONTROL; oparms.disposition = FILE_OPEN; - oparms.create_options = cifs_create_options(cifs_sb, 0); + /* + * When querying an ACL, even if the file is a symlink we want to open + * the source not the target, and so the protocol requires that the + * client specify this flag when opening a reparse point + */ + oparms.create_options = cifs_create_options(cifs_sb, 0) | OPEN_REPARSE_POINT; oparms.fid = &fid; oparms.reconnect = false; @@ -3924,7 +3929,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, if (rc) { cifs_server_dbg(VFS, "%s: Could not get %scryption key\n", __func__, enc ? "en" : "de"); - return 0; + return rc; } rc = smb3_crypto_aead_allocate(server); @@ -4103,7 +4108,8 @@ smb3_is_transform_hdr(void *buf) static int decrypt_raw_data(struct TCP_Server_Info *server, char *buf, unsigned int buf_data_size, struct page **pages, - unsigned int npages, unsigned int page_data_size) + unsigned int npages, unsigned int page_data_size, + bool is_offloaded) { struct kvec iov[2]; struct smb_rqst rqst = {NULL}; @@ -4129,7 +4135,8 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, memmove(buf, iov[1].iov_base, buf_data_size); - server->total_read = buf_data_size + page_data_size; + if (!is_offloaded) + server->total_read = buf_data_size + page_data_size; return rc; } @@ -4342,7 +4349,7 @@ static void smb2_decrypt_offload(struct work_struct *work) struct mid_q_entry *mid; rc = decrypt_raw_data(dw->server, dw->buf, dw->server->vals->read_rsp_size, - dw->ppages, dw->npages, dw->len); + dw->ppages, dw->npages, dw->len, true); if (rc) { cifs_dbg(VFS, "error decrypting rc=%d\n", rc); goto free_pages; @@ -4448,7 +4455,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid, non_offloaded_decrypt: rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size, - pages, npages, len); + pages, npages, len, false); if (rc) goto free_pages; @@ -4504,7 +4511,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, server->total_read += length; buf_size = pdu_length - sizeof(struct smb2_transform_hdr); - length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0); + length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0, false); if (length) return length; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index d23ff162c78b..0b32c64eb405 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -178,10 +178,15 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, 32, 32)) return false; + /* + * IV_INO_LBLK_32 hashes the inode number, so in principle it can + * support any ino_bits. However, currently the inode number is gotten + * from inode::i_ino which is 'unsigned long'. So for now the + * implementation limit is 32 bits. + */ if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) && - /* This uses hashed inode numbers, so ino_bits doesn't matter. */ !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_32", - INT_MAX, 32)) + 32, 32)) return false; if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { diff --git a/fs/d_path.c b/fs/d_path.c index 0f1fc1743302..a69e2cd36e6e 100644 --- a/fs/d_path.c +++ b/fs/d_path.c @@ -102,6 +102,8 @@ restart: if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { struct mount *parent = READ_ONCE(mnt->mnt_parent); + struct mnt_namespace *mnt_ns; + /* Escaped? */ if (dentry != vfsmnt->mnt_root) { bptr = *buffer; @@ -116,7 +118,9 @@ restart: vfsmnt = &mnt->mnt; continue; } - if (is_mounted(vfsmnt) && !is_anon_ns(mnt->mnt_ns)) + mnt_ns = READ_ONCE(mnt->mnt_ns); + /* open-coded is_mounted() to use local mnt_ns */ + if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) error = 1; // absolute root else error = 2; // detached or not attached yet diff --git a/fs/dcache.c b/fs/dcache.c index 361ea7ab30ea..e6e467c9e86c 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1285,7 +1285,7 @@ enum d_walk_ret { * * The @enter() callbacks are called with d_lock held. */ -static void d_walk(struct dentry *parent, void *data, +void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; @@ -1390,6 +1390,7 @@ rename_retry: seq = 1; goto again; } +EXPORT_SYMBOL_GPL(d_walk); struct check_mount { struct vfsmount *mnt; @@ -2935,6 +2936,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) write_sequnlock(&rename_lock); } +EXPORT_SYMBOL_GPL(d_exchange); /** * d_ancestor - search for an ancestor diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 3b21082e1b55..3b1012a3c439 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -216,6 +216,7 @@ struct dlm_space { struct list_head members; struct mutex members_lock; int members_count; + struct dlm_nodes *nds; }; struct dlm_comms { @@ -424,6 +425,7 @@ static struct config_group *make_space(struct config_group *g, const char *name) INIT_LIST_HEAD(&sp->members); mutex_init(&sp->members_lock); sp->members_count = 0; + sp->nds = nds; return &sp->group; fail: @@ -445,6 +447,7 @@ static void drop_space(struct config_group *g, struct config_item *i) static void release_space(struct config_item *i) { struct dlm_space *sp = config_item_to_space(i); + kfree(sp->nds); kfree(sp); } diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 28bb5689333a..15880a68faad 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -141,6 +141,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; + /* replace invalid slashes like kobject_set_name_vargs does for /sys/firmware/efi/vars. */ + strreplace(name, '/', '!'); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, is_removable); if (!inode) diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 87e437e7b34f..f86e3247febc 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -473,8 +473,6 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler, return -EOPNOTSUPP; break; case EROFS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; break; case EROFS_XATTR_INDEX_SECURITY: break; diff --git a/fs/exec.c b/fs/exec.c index e6e8a9a70327..049c0013679e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -62,6 +62,7 @@ #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> +#include <linux/io_uring.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -111,6 +112,7 @@ bool path_noexec(const struct path *path) return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } +EXPORT_SYMBOL_GPL(path_noexec); #ifdef CONFIG_USELIB /* @@ -1847,6 +1849,11 @@ static int __do_execve_file(int fd, struct filename *filename, * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; + /* + * Cancel any io_uring activity across execve + */ + io_uring_task_cancel(); + retval = unshare_files(&displaced); if (retval) goto out_ret; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ff46defc6568..dc943e714d14 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -466,7 +466,7 @@ struct flex_groups { /* Flags which are mutually exclusive to DAX */ #define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\ - EXT4_JOURNAL_DATA_FL) + EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_FL) /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index dbccf46f1770..37347ba868b7 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -108,6 +108,9 @@ static int ext4_getfsmap_helper(struct super_block *sb, /* Are we just counting mappings? */ if (info->gfi_head->fmh_count == 0) { + if (info->gfi_head->fmh_entries == UINT_MAX) + return EXT4_QUERY_RANGE_ABORT; + if (rec_fsblk > info->gfi_next_fsblk) info->gfi_head->fmh_entries++; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e88eff999bd1..79d32ea606aa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4037,7 +4037,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, struct ext4_buddy e4b; int err; int busy = 0; - int free = 0; + int free, free_total = 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) @@ -4065,8 +4065,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, INIT_LIST_HEAD(&list); repeat: + free = 0; ext4_lock_group(sb, group); - this_cpu_inc(discard_pa_seq); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); @@ -4083,6 +4083,9 @@ repeat: /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); + if (!free) + this_cpu_inc(discard_pa_seq); + /* we can trust pa_free ... */ free += pa->pa_free; @@ -4092,22 +4095,6 @@ repeat: list_add(&pa->u.pa_tmp_list, &list); } - /* if we still need more blocks and some PAs were used, try again */ - if (free < needed && busy) { - busy = 0; - ext4_unlock_group(sb, group); - cond_resched(); - goto repeat; - } - - /* found anything to free? */ - if (list_empty(&list)) { - BUG_ON(free != 0); - mb_debug(sb, "Someone else may have freed PA for this group %u\n", - group); - goto out; - } - /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { @@ -4125,14 +4112,22 @@ repeat: call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } -out: + free_total += free; + + /* if we still need more blocks and some PAs were used, try again */ + if (free_total < needed && busy) { + ext4_unlock_group(sb, group); + cond_resched(); + busy = 0; + goto repeat; + } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", - free, group, grp->bb_free); - return free; + free_total, group, grp->bb_free); + return free_total; } /* diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0b38bf29c07e..9cf88162ab66 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -347,7 +347,7 @@ static void __save_error_info(struct super_block *sb, int error, return; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); ext4_update_tstamp(es, s_last_error_time); - strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); + strscpy_pad(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); es->s_last_error_ino = cpu_to_le32(ino); es->s_last_error_block = cpu_to_le64(block); @@ -408,7 +408,7 @@ static void __save_error_info(struct super_block *sb, int error, if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; es->s_first_error_time_hi = es->s_last_error_time_hi; - strncpy(es->s_first_error_func, func, + strscpy_pad(es->s_first_error_func, func, sizeof(es->s_first_error_func)); es->s_first_error_line = cpu_to_le32(line); es->s_first_error_ino = es->s_last_error_ino; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 44582a4db513..1e014535c253 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -287,6 +287,13 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if ((fi->i_flags & F2FS_CASEFOLD_FL) && !f2fs_sb_has_casefold(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: inode (ino=%lx) has casefold flag, but casefold feature is off", + __func__, inode->i_ino); + return false; + } + if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) && fi->i_flags & F2FS_COMPR_FL && F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index c5e32ceb9482..e186d3af6136 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -964,4 +964,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) } kobject_del(&sbi->s_kobj); kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); } diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig index ca31993dcb47..0b2c8fa88119 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -75,6 +75,27 @@ config VFAT_FS To compile this as a module, choose M here: the module will be called vfat. +config VFAT_FS_NO_DUALNAMES + bool "disable VFAT dual names support (patent workaround)" + depends on VFAT_FS + help + This option disables support for dual filenames on VFAT filesystems. + If this option is enabled then file creation will either put + a short (8.3) name or a long name on the file, but never both. + The field where a shortname would normally go is filled with + invalid characters such that it cannot be considered a valid + short filename. + + That means that long filenames created with this option + disabled will not be accessible at all to operating systems + that do not understand the FAT long filename extensions. + + Users considering disabling this option should consider the + implications of any patents that may exist on dual filenames + in VFAT. + + If unsure, say N + config FAT_DEFAULT_CODEPAGE int "Default codepage for FAT" depends on MSDOS_FS || VFAT_FS @@ -101,6 +122,17 @@ config FAT_DEFAULT_IOCHARSET Enable any character sets you need in File Systems/Native Language Support. +config VFAT_NO_CREATE_WITH_LONGNAMES + bool "Disable creating files with long names" + depends on VFAT_FS + default n + help + Set this to disable support for creating files or directories with + names longer than 8.3 (the original DOS maximum file name length) + e.g. naming a file FILE1234.TXT would be allowed but creating or + renaming a file to FILE12345.TXT or FILE1234.TEXT would not + be permitted. Reading files with long file names is still permitted. + config FAT_DEFAULT_UTF8 bool "Enable FAT UTF-8 option by default" depends on VFAT_FS diff --git a/fs/fat/dir.c b/fs/fat/dir.c index b4ddf48fa444..1c453681d43c 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -367,7 +367,8 @@ static int fat_parse_short(struct super_block *sb, dotoffset = 1; } - memcpy(work, de->name, sizeof(work)); + memcpy(work, de->name, sizeof(de->name)); + /* For an explanation of the special treatment of 0x05 in * filenames, see msdos_format_name in namei_msdos.c */ @@ -499,6 +500,13 @@ parse_record: goto end_of_dir; } + /* + * The FAT_NO_83NAME flag is used to mark files + * created with no 8.3 short name + */ + if (de->lcase & FAT_NO_83NAME) + goto compare_longname; + /* Never prepend '.' to hidden files here. * That is done only for msdos mounts (and only when * 'dotsOK=yes'); if we are executing here, it is in the @@ -512,6 +520,7 @@ parse_record: if (fat_name_match(sbi, name, name_len, bufname, len)) goto found; +compare_longname: if (nr_slots) { void *longname = unicode + FAT_MAX_UNI_CHARS; int size = PATH_MAX - FAT_MAX_UNI_SIZE; @@ -603,6 +612,8 @@ parse_record: if (de->attr != ATTR_EXT && IS_FREE(de->name)) goto record_end; } else { + if (de->lcase & FAT_NO_83NAME) + goto record_end; if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name)) goto record_end; } @@ -957,6 +968,10 @@ int fat_scan(struct inode *dir, const unsigned char *name, sinfo->bh = NULL; while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh, &sinfo->de) >= 0) { + /* skip files marked as having no 8.3 short name */ + if (sinfo->de->lcase & FAT_NO_83NAME) + continue; + if (!strncmp(sinfo->de->name, name, MSDOS_NAME)) { sinfo->slot_off -= sizeof(*sinfo->de); sinfo->nr_slots = 1; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 0cdd0fb9f742..1b3647143181 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -22,6 +22,7 @@ #include <linux/namei.h> #include <linux/kernel.h> #include <linux/iversion.h> +#include <linux/random.h> #include "fat.h" static inline unsigned long vfat_d_version(struct dentry *dentry) @@ -336,6 +337,17 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls, int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen; int is_shortname; struct shortname_info base_info, ext_info; + unsigned opts_shortname = opts->shortname; + +#ifdef CONFIG_VFAT_FS_NO_DUALNAMES + /* + * When we do not have dualnames, we want to maximise the + * chance that a file will be able to be represented with just + * a 8.3 entry. We can do that by using the WINNT case + * handling extensions to FAT. + */ + opts_shortname = VFAT_SFN_CREATE_WINNT; +#endif is_shortname = 1; INIT_SHORTNAME_INFO(&base_info); @@ -444,13 +456,22 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls, memcpy(name_res, base, baselen); memcpy(name_res + 8, ext, extlen); *lcase = 0; + +#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES + if (is_shortname == 0) + return -ENAMETOOLONG; + if (!base_info.valid || !ext_info.valid) + return -EINVAL; + opts_shortname = VFAT_SFN_CREATE_WINNT; +#endif + if (is_shortname && base_info.valid && ext_info.valid) { if (vfat_find_form(dir, name_res) == 0) return -EEXIST; - if (opts->shortname & VFAT_SFN_CREATE_WIN95) { + if (opts_shortname & VFAT_SFN_CREATE_WIN95) { return (base_info.upper && ext_info.upper); - } else if (opts->shortname & VFAT_SFN_CREATE_WINNT) { + } else if (opts_shortname & VFAT_SFN_CREATE_WINNT) { if ((base_info.upper || base_info.lower) && (ext_info.upper || ext_info.lower)) { if (!base_info.upper && base_info.lower) @@ -576,6 +597,66 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, return 0; } +#ifdef CONFIG_VFAT_FS_NO_DUALNAMES +/* + * This function creates a dummy 8.3 entry which is as compatible as + * possible with existing FAT devices, while not being a valid + * filename under windows or Linux + */ +static void vfat_build_dummy_83_buffer(struct inode *dir, char *msdos_name, + int is_dir) +{ + /* + * These characters are all invalid in 8.3 names, plus have + * been shown to be harmless on all tested devices + */ + const char invalidchar[] = { 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x0B, + 0x0C, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13, + 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1A, + 0x1B, 0x1C, 0x1D, 0x1E, 0x1F, 0x22, 0x2a, + 0x3a, 0x3c, 0x3e, 0x3f, 0x5b, 0x5d, 0x7c }; + int i, tilde_pos, slash_pos; + u32 rand_num = prandom_u32(); + + /* We need a '~' in the prefix to make Win98 happy. */ + tilde_pos = rand_num % 8; + rand_num >>= 3; + + /* + * the '/' makes sure that even unpatched Linux systems can't + * get at files by the 8.3 entry. Don't put in a / in + * directories as it can cause problems with some + * photo frames + */ + if (is_dir) + slash_pos = -1; + else { + slash_pos = (tilde_pos + 1 + rand_num % 7) % 8; + rand_num >>= 3; + } + + /* + * fill in the first 8 bytes with invalid characters. Note + * that we need to be careful not to run out of randomness. We + * leave the 3 byte extension in place as some cheap MP3 + * players need them. + */ + for (i = 0; i < 8; i++) { + if (i == tilde_pos) + msdos_name[i] = '~'; + else if (i == slash_pos) + msdos_name[i] = '/'; + else { + msdos_name[i] = + invalidchar[rand_num % sizeof(invalidchar)]; + rand_num /= sizeof(invalidchar); + if (rand_num < sizeof(invalidchar)) + rand_num = prandom_u32(); + } + } +} +#endif + static int vfat_build_slots(struct inode *dir, const unsigned char *name, int len, int is_dir, int cluster, struct timespec64 *ts, @@ -583,15 +664,19 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name, { struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); struct fat_mount_options *opts = &sbi->options; - struct msdos_dir_slot *ps; struct msdos_dir_entry *de; - unsigned char cksum, lcase; + unsigned char lcase; unsigned char msdos_name[MSDOS_NAME]; wchar_t *uname; __le16 time, date; u8 time_cs; - int err, ulen, usize, i; + int err, ulen, usize; +#ifndef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES + int i; + struct msdos_dir_slot *ps; + unsigned char cksum; loff_t offset; +#endif *nr_slots = 0; @@ -618,6 +703,16 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name, goto shortname; } +#ifdef CONFIG_VFAT_FS_NO_DUALNAMES + printk_once(KERN_INFO + "VFAT: not creating 8.3 short filenames for long names\n"); + vfat_build_dummy_83_buffer(dir, msdos_name, is_dir); + lcase = FAT_NO_83NAME; +#endif + +#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES + de = (struct msdos_dir_entry *)slots; +#else /* build the entry of long file name */ cksum = fat_checksum(msdos_name); @@ -635,6 +730,7 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name, } slots[0].id |= 0x40; de = (struct msdos_dir_entry *)ps; +#endif shortname: /* build the entry of 8.3 alias name */ @@ -1059,7 +1155,11 @@ static struct dentry *vfat_mount(struct file_system_type *fs_type, static struct file_system_type vfat_fs_type = { .owner = THIS_MODULE, +#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES + .name = "lfat", +#else .name = "vfat", +#endif .mount = vfat_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, @@ -1079,6 +1179,9 @@ static void __exit exit_vfat_fs(void) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VFAT filesystem support"); MODULE_AUTHOR("Gordon Chaffee"); +#ifdef CONFIG_VFAT_NO_CREATE_WITH_LONGNAMES +MODULE_ALIAS("lfat"); +#endif module_init(init_vfat_fs) module_exit(exit_vfat_fs) diff --git a/fs/fcntl.c b/fs/fcntl.c index 2e4c0fa2074b..f2c90a416b75 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -32,7 +32,7 @@ #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) -static int setfl(int fd, struct file * filp, unsigned long arg) +int setfl(int fd, struct file *filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; @@ -63,6 +63,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); + if (!error && filp->f_op->setfl) + error = filp->f_op->setfl(filp, arg); if (error) return error; @@ -83,6 +85,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) out: return error; } +EXPORT_SYMBOL_GPL(setfl); static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) diff --git a/fs/file.c b/fs/file.c index abb8b7081d7a..8e2c532bb02e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -18,6 +18,7 @@ #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/io_uring.h> unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; @@ -439,6 +440,7 @@ void exit_files(struct task_struct *tsk) struct files_struct * files = tsk->files; if (files) { + io_uring_files_cancel(files); task_lock(tsk); tsk->files = NULL; task_unlock(tsk); diff --git a/fs/file_table.c b/fs/file_table.c index 656647f9575a..6e11f3dc333f 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -162,6 +162,7 @@ over: } return ERR_PTR(-ENFILE); } +EXPORT_SYMBOL_GPL(alloc_empty_file); /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. @@ -376,6 +377,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL_GPL(__fput_sync); void __init files_init(void) { diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 02b3c36b3676..5078a6ca7dfc 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -785,15 +785,16 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) struct page *newpage; struct pipe_buffer *buf = cs->pipebufs; + get_page(oldpage); err = unlock_request(cs->req); if (err) - return err; + goto out_put_old; fuse_copy_finish(cs); err = pipe_buf_confirm(cs->pipe, buf); if (err) - return err; + goto out_put_old; BUG_ON(!cs->nr_segs); cs->currbuf = buf; @@ -833,7 +834,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL); if (err) { unlock_page(newpage); - return err; + goto out_put_old; } get_page(newpage); @@ -852,14 +853,19 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (err) { unlock_page(newpage); put_page(newpage); - return err; + goto out_put_old; } unlock_page(oldpage); + /* Drop ref for ap->pages[] array */ put_page(oldpage); cs->len = 0; - return 0; + err = 0; +out_put_old: + /* Drop ref obtained in this function */ + put_page(oldpage); + return err; out_fallback_unlock: unlock_page(newpage); @@ -868,10 +874,10 @@ out_fallback: cs->offset = buf->offset; err = lock_request(cs->req); - if (err) - return err; + if (!err) + err = 1; - return 1; + goto out_put_old; } static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, @@ -883,14 +889,16 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, if (cs->nr_segs >= cs->pipe->max_usage) return -EIO; + get_page(page); err = unlock_request(cs->req); - if (err) + if (err) { + put_page(page); return err; + } fuse_copy_finish(cs); buf = cs->pipebufs; - get_page(page); buf->page = page; buf->offset = offset; buf->len = count; diff --git a/fs/inode.c b/fs/inode.c index 72c4c347afb7..07d0cb8d5c98 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1768,12 +1768,13 @@ EXPORT_SYMBOL(generic_update_time); * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ -static int update_time(struct inode *inode, struct timespec64 *time, int flags) +int update_time(struct inode *inode, struct timespec64 *time, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, time, flags); return generic_update_time(inode, time, flags); } +EXPORT_SYMBOL_GPL(update_time); /** * touch_atime - update the access time diff --git a/fs/io-wq.c b/fs/io-wq.c index cb9e5a444fba..56a229621a83 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -60,6 +60,7 @@ struct io_worker { const struct cred *cur_creds; const struct cred *saved_creds; struct files_struct *restore_files; + struct nsproxy *restore_nsproxy; struct fs_struct *restore_fs; }; @@ -87,7 +88,7 @@ enum { */ struct io_wqe { struct { - spinlock_t lock; + raw_spinlock_t lock; struct io_wq_work_list work_list; unsigned long hash_map; unsigned flags; @@ -148,11 +149,12 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) if (current->files != worker->restore_files) { __acquire(&wqe->lock); - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); dropped_lock = true; task_lock(current); current->files = worker->restore_files; + current->nsproxy = worker->restore_nsproxy; task_unlock(current); } @@ -166,7 +168,7 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) if (worker->mm) { if (!dropped_lock) { __acquire(&wqe->lock); - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); dropped_lock = true; } __set_current_state(TASK_RUNNING); @@ -200,7 +202,6 @@ static void io_worker_exit(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; struct io_wqe_acct *acct = io_wqe_get_acct(wqe, worker); - unsigned nr_workers; /* * If we're not at zero, someone else is holding a brief reference @@ -220,23 +221,19 @@ static void io_worker_exit(struct io_worker *worker) worker->flags = 0; preempt_enable(); - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); if (__io_worker_unuse(wqe, worker)) { __release(&wqe->lock); - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); } acct->nr_workers--; - nr_workers = wqe->acct[IO_WQ_ACCT_BOUND].nr_workers + - wqe->acct[IO_WQ_ACCT_UNBOUND].nr_workers; - spin_unlock_irq(&wqe->lock); - - /* all workers gone, wq exit can proceed */ - if (!nr_workers && refcount_dec_and_test(&wqe->wq->refs)) - complete(&wqe->wq->done); + raw_spin_unlock_irq(&wqe->lock); kfree_rcu(worker, rcu); + if (refcount_dec_and_test(&wqe->wq->refs)) + complete(&wqe->wq->done); } static inline bool io_wqe_run_queue(struct io_wqe *wqe) @@ -318,6 +315,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); worker->restore_files = current->files; + worker->restore_nsproxy = current->nsproxy; worker->restore_fs = current->fs; io_wqe_inc_running(wqe, worker); } @@ -454,6 +452,7 @@ static void io_impersonate_work(struct io_worker *worker, if (work->files && current->files != work->files) { task_lock(current); current->files = work->files; + current->nsproxy = work->nsproxy; task_unlock(current); } if (work->fs && current->fs != work->fs) @@ -504,7 +503,7 @@ get_next: else if (!wq_list_empty(&wqe->work_list)) wqe->flags |= IO_WQE_FLAG_STALLED; - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); if (!work) break; io_assign_current_work(worker, work); @@ -539,7 +538,7 @@ get_next: io_wqe_enqueue(wqe, linked); if (hash != -1U && !next_hashed) { - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); wqe->hash_map &= ~BIT_ULL(hash); wqe->flags &= ~IO_WQE_FLAG_STALLED; /* dependent work is not hashed */ @@ -547,11 +546,11 @@ get_next: /* skip unnecessary unlock-lock wqe->lock */ if (!work) goto get_next; - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); } } while (work); - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); } while (1); } @@ -566,7 +565,7 @@ static int io_wqe_worker(void *data) while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { set_current_state(TASK_INTERRUPTIBLE); loop: - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); if (io_wqe_run_queue(wqe)) { __set_current_state(TASK_RUNNING); io_worker_handle_work(worker); @@ -577,7 +576,7 @@ loop: __release(&wqe->lock); goto loop; } - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); if (signal_pending(current)) flush_signals(current); if (schedule_timeout(WORKER_IDLE_TIMEOUT)) @@ -589,11 +588,11 @@ loop: } if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); if (!wq_list_empty(&wqe->work_list)) io_worker_handle_work(worker); else - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); } io_worker_exit(worker); @@ -633,14 +632,14 @@ void io_wq_worker_sleeping(struct task_struct *tsk) worker->flags &= ~IO_WORKER_F_RUNNING; - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); io_wqe_dec_running(wqe, worker); - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); } static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) { - struct io_wqe_acct *acct =&wqe->acct[index]; + struct io_wqe_acct *acct = &wqe->acct[index]; struct io_worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node); @@ -659,7 +658,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) return false; } - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); list_add_tail_rcu(&worker->all_list, &wqe->all_list); worker->flags |= IO_WORKER_F_FREE; @@ -668,11 +667,12 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND)) worker->flags |= IO_WORKER_F_FIXED; acct->nr_workers++; - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); if (index == IO_WQ_ACCT_UNBOUND) atomic_inc(&wq->user->processes); + refcount_inc(&wq->refs); wake_up_process(worker->task); return true; } @@ -688,28 +688,63 @@ static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index) return acct->nr_workers < acct->max_workers; } +static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) +{ + send_sig(SIGINT, worker->task, 1); + return false; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct io_worker *worker; + bool ret = false; + + list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { + if (io_worker_get(worker)) { + /* no task if node is/was offline */ + if (worker->task) + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + + return ret; +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + wake_up_process(worker->task); + return false; +} + /* * Manager thread. Tasked with creating new workers, if we need them. */ static int io_wq_manager(void *data) { struct io_wq *wq = data; - int workers_to_create = num_possible_nodes(); int node; /* create fixed workers */ - refcount_set(&wq->refs, workers_to_create); + refcount_set(&wq->refs, 1); for_each_node(node) { if (!node_online(node)) continue; - if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) - goto err; - workers_to_create--; + if (create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) + continue; + set_bit(IO_WQ_BIT_ERROR, &wq->state); + set_bit(IO_WQ_BIT_EXIT, &wq->state); + goto out; } - while (workers_to_create--) - refcount_dec(&wq->refs); - complete(&wq->done); while (!kthread_should_stop()) { @@ -723,12 +758,12 @@ static int io_wq_manager(void *data) if (!node_online(node)) continue; - spin_lock_irq(&wqe->lock); + raw_spin_lock_irq(&wqe->lock); if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) fork_worker[IO_WQ_ACCT_BOUND] = true; if (io_wqe_need_worker(wqe, IO_WQ_ACCT_UNBOUND)) fork_worker[IO_WQ_ACCT_UNBOUND] = true; - spin_unlock_irq(&wqe->lock); + raw_spin_unlock_irq(&wqe->lock); if (fork_worker[IO_WQ_ACCT_BOUND]) create_io_worker(wq, wqe, IO_WQ_ACCT_BOUND); if (fork_worker[IO_WQ_ACCT_UNBOUND]) @@ -741,12 +776,18 @@ static int io_wq_manager(void *data) if (current->task_works) task_work_run(); - return 0; -err: - set_bit(IO_WQ_BIT_ERROR, &wq->state); - set_bit(IO_WQ_BIT_EXIT, &wq->state); - if (refcount_sub_and_test(workers_to_create, &wq->refs)) +out: + if (refcount_dec_and_test(&wq->refs)) { complete(&wq->done); + return 0; + } + /* if ERROR is set and we get here, we have workers to wake */ + if (test_bit(IO_WQ_BIT_ERROR, &wq->state)) { + rcu_read_lock(); + for_each_node(node) + io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL); + rcu_read_unlock(); + } return 0; } @@ -825,10 +866,10 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) } work_flags = work->flags; - spin_lock_irqsave(&wqe->lock, flags); + raw_spin_lock_irqsave(&wqe->lock, flags); io_wqe_insert_work(wqe, work); wqe->flags &= ~IO_WQE_FLAG_STALLED; - spin_unlock_irqrestore(&wqe->lock, flags); + raw_spin_unlock_irqrestore(&wqe->lock, flags); if ((work_flags & IO_WQ_WORK_CONCURRENT) || !atomic_read(&acct->nr_running)) @@ -854,37 +895,6 @@ void io_wq_hash_work(struct io_wq_work *work, void *val) work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); } -static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) -{ - send_sig(SIGINT, worker->task, 1); - return false; -} - -/* - * Iterate the passed in list and call the specific function for each - * worker that isn't exiting - */ -static bool io_wq_for_each_worker(struct io_wqe *wqe, - bool (*func)(struct io_worker *, void *), - void *data) -{ - struct io_worker *worker; - bool ret = false; - - list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { - if (io_worker_get(worker)) { - /* no task if node is/was offline */ - if (worker->task) - ret = func(worker, data); - io_worker_release(worker); - if (ret) - break; - } - } - - return ret; -} - void io_wq_cancel_all(struct io_wq *wq) { int node; @@ -955,13 +965,13 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe, unsigned long flags; retry: - spin_lock_irqsave(&wqe->lock, flags); + raw_spin_lock_irqsave(&wqe->lock, flags); wq_list_for_each(node, prev, &wqe->work_list) { work = container_of(node, struct io_wq_work, list); if (!match->fn(work, match->data)) continue; io_wqe_remove_pending(wqe, work, prev); - spin_unlock_irqrestore(&wqe->lock, flags); + raw_spin_unlock_irqrestore(&wqe->lock, flags); io_run_cancel(work, wqe); match->nr_pending++; if (!match->cancel_all) @@ -970,7 +980,7 @@ retry: /* not safe to continue after unlock */ goto retry; } - spin_unlock_irqrestore(&wqe->lock, flags); + raw_spin_unlock_irqrestore(&wqe->lock, flags); } static void io_wqe_cancel_running_work(struct io_wqe *wqe, @@ -1078,7 +1088,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) } atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); wqe->wq = wq; - spin_lock_init(&wqe->lock); + raw_spin_lock_init(&wqe->lock); INIT_WQ_LIST(&wqe->work_list); INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0); INIT_LIST_HEAD(&wqe->all_list); @@ -1117,12 +1127,6 @@ bool io_wq_get(struct io_wq *wq, struct io_wq_data *data) return refcount_inc_not_zero(&wq->use_refs); } -static bool io_wq_worker_wake(struct io_worker *worker, void *data) -{ - wake_up_process(worker->task); - return false; -} - static void __io_wq_destroy(struct io_wq *wq) { int node; diff --git a/fs/io-wq.h b/fs/io-wq.h index 071f1a997800..9be6def2b5a6 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -88,6 +88,7 @@ struct io_wq_work { struct files_struct *files; struct mm_struct *mm; const struct cred *creds; + struct nsproxy *nsproxy; struct fs_struct *fs; unsigned flags; }; diff --git a/fs/io_uring.c b/fs/io_uring.c index d2bb2ae9551f..8e9c58fa7636 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,6 +78,7 @@ #include <linux/fs_struct.h> #include <linux/splice.h> #include <linux/task_work.h> +#include <linux/io_uring.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -264,7 +265,16 @@ struct io_ring_ctx { /* IO offload */ struct io_wq *io_wq; struct task_struct *sqo_thread; /* if using sq thread polling */ - struct mm_struct *sqo_mm; + + /* + * For SQPOLL usage - we hold a reference to the parent task, so we + * have access to the ->files + */ + struct task_struct *sqo_task; + + /* Only used for accounting purposes */ + struct mm_struct *mm_account; + wait_queue_head_t sqo_wait; /* @@ -274,8 +284,6 @@ struct io_ring_ctx { */ struct fixed_file_data *file_data; unsigned nr_user_files; - int ring_fd; - struct file *ring_file; /* if used, fixed mapped user buffers */ unsigned nr_user_bufs; @@ -541,7 +549,6 @@ enum { REQ_F_NO_FILE_TABLE_BIT, REQ_F_QUEUE_TIMEOUT_BIT, REQ_F_WORK_INITIALIZED_BIT, - REQ_F_TASK_PINNED_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -599,8 +606,6 @@ enum { REQ_F_QUEUE_TIMEOUT = BIT(REQ_F_QUEUE_TIMEOUT_BIT), /* io_wq_work is initialized */ REQ_F_WORK_INITIALIZED = BIT(REQ_F_WORK_INITIALIZED_BIT), - /* req->task is refcounted */ - REQ_F_TASK_PINNED = BIT(REQ_F_TASK_PINNED_BIT), }; struct async_poll { @@ -915,21 +920,6 @@ struct sock *io_uring_get_socket(struct file *file) } EXPORT_SYMBOL(io_uring_get_socket); -static void io_get_req_task(struct io_kiocb *req) -{ - if (req->flags & REQ_F_TASK_PINNED) - return; - get_task_struct(req->task); - req->flags |= REQ_F_TASK_PINNED; -} - -/* not idempotent -- it doesn't clear REQ_F_TASK_PINNED */ -static void __io_put_req_task(struct io_kiocb *req) -{ - if (req->flags & REQ_F_TASK_PINNED) - put_task_struct(req->task); -} - static void io_file_put_work(struct work_struct *work); /* @@ -1141,14 +1131,34 @@ static void io_kill_timeout(struct io_kiocb *req) } } -static void io_kill_timeouts(struct io_ring_ctx *ctx) +static bool io_task_match(struct io_kiocb *req, struct task_struct *tsk) +{ + struct io_ring_ctx *ctx = req->ctx; + + if (!tsk || req->task == tsk) + return true; + if ((ctx->flags & IORING_SETUP_SQPOLL) && req->task == ctx->sqo_thread) + return true; + return false; +} + +/* + * Returns true if we found and killed one or more timeouts + */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk) { struct io_kiocb *req, *tmp; + int canceled = 0; spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, list) - io_kill_timeout(req); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, list) { + if (io_task_match(req, tsk)) { + io_kill_timeout(req); + canceled++; + } + } spin_unlock_irq(&ctx->completion_lock); + return canceled != 0; } static void __io_queue_deferred(struct io_ring_ctx *ctx) @@ -1229,12 +1239,24 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) eventfd_signal(ctx->cq_ev_fd, 1); } +static inline bool io_match_files(struct io_kiocb *req, + struct files_struct *files) +{ + if (!files) + return true; + if (req->flags & REQ_F_WORK_INITIALIZED) + return req->work.files == files; + return false; +} + /* Returns true if there are no backlogged entries after the flush */ -static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) +static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, + struct task_struct *tsk, + struct files_struct *files) { struct io_rings *rings = ctx->rings; + struct io_kiocb *req, *tmp; struct io_uring_cqe *cqe; - struct io_kiocb *req; unsigned long flags; LIST_HEAD(list); @@ -1253,7 +1275,12 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) ctx->cq_overflow_flushed = 1; cqe = NULL; - while (!list_empty(&ctx->cq_overflow_list)) { + list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, list) { + if (tsk && req->task != tsk) + continue; + if (!io_match_files(req, files)) + continue; + cqe = io_get_cqring(ctx); if (!cqe && !force) break; @@ -1307,7 +1334,12 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, cflags); - } else if (ctx->cq_overflow_flushed) { + } else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) { + /* + * If we're in ring overflow flush mode, or in task cancel mode, + * then we cannot store the request for later flushing, we need + * to drop it on the floor. + */ WRITE_ONCE(ctx->rings->cq_overflow, atomic_inc_return(&ctx->cached_cq_overflow)); } else { @@ -1412,15 +1444,35 @@ static inline void io_put_file(struct io_kiocb *req, struct file *file, fput(file); } +static void io_req_drop_files(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + req->flags &= ~REQ_F_INFLIGHT; + put_files_struct(req->work.files); + put_nsproxy(req->work.nsproxy); + req->work.files = NULL; +} + static void __io_req_aux_free(struct io_kiocb *req) { + struct io_uring_task *tctx = req->task->io_uring; if (req->flags & REQ_F_NEED_CLEANUP) io_cleanup_req(req); kfree(req->io); if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - __io_put_req_task(req); + atomic_long_inc(&tctx->req_complete); + if (tctx->in_idle) + wake_up(&tctx->wait); + put_task_struct(req->task); io_req_work_drop_env(req); } @@ -1428,16 +1480,8 @@ static void __io_free_req(struct io_kiocb *req) { __io_req_aux_free(req); - if (req->flags & REQ_F_INFLIGHT) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - if (waitqueue_active(&ctx->inflight_wait)) - wake_up(&ctx->inflight_wait); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - } + if (req->flags & REQ_F_INFLIGHT) + io_req_drop_files(req); percpu_ref_put(&req->ctx->refs); if (likely(!io_is_fallback_req(req))) @@ -1717,7 +1761,7 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) if (noflush && !list_empty(&ctx->cq_overflow_list)) return -1U; - io_cqring_overflow_flush(ctx, false); + io_cqring_overflow_flush(ctx, false, NULL, NULL); } /* See comment at the top of this file */ @@ -1738,7 +1782,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req) if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req)) return false; - if (req->file || req->io) + if (req->file || req->io || req->task) rb->need_iter++; rb->reqs[rb->to_free++] = req; @@ -1762,6 +1806,12 @@ static int io_put_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { + /* + * Not safe to run on exiting task, and the task_work handling will + * not add work to such a task. + */ + if (unlikely(current->flags & PF_EXITING)) + return false; if (current->task_works) { __set_current_state(TASK_RUNNING); task_work_run(); @@ -3492,8 +3542,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); - if ((req->file && req->file->f_op == &io_uring_fops) || - req->close.fd == req->ctx->ring_fd) + if ((req->file && req->file->f_op == &io_uring_fops)) return -EBADF; req->close.put_file = NULL; @@ -4397,9 +4446,10 @@ static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx, { if (io_op_defs[req->opcode].needs_mm && !current->mm) { if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) || - !mmget_not_zero(ctx->sqo_mm))) + !ctx->sqo_task->mm || + !mmget_not_zero(ctx->sqo_task->mm))) return -EFAULT; - kthread_use_mm(ctx->sqo_mm); + kthread_use_mm(ctx->sqo_task->mm); } return 0; @@ -4550,7 +4600,6 @@ static bool io_arm_poll_handler(struct io_kiocb *req) if (req->flags & REQ_F_WORK_INITIALIZED) memcpy(&apoll->work, &req->work, sizeof(req->work)); - io_get_req_task(req); req->apoll = apoll; INIT_HLIST_NODE(&req->hash_node); @@ -4635,7 +4684,10 @@ static bool io_poll_remove_one(struct io_kiocb *req) return do_complete; } -static void io_poll_remove_all(struct io_ring_ctx *ctx) +/* + * Returns true if we found and killed one or more poll requests + */ +static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk) { struct hlist_node *tmp; struct io_kiocb *req; @@ -4646,13 +4698,17 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx) struct hlist_head *list; list = &ctx->cancel_hash[i]; - hlist_for_each_entry_safe(req, tmp, list, hash_node) - posted += io_poll_remove_one(req); + hlist_for_each_entry_safe(req, tmp, list, hash_node) { + if (io_task_match(req, tsk)) + posted += io_poll_remove_one(req); + } } spin_unlock_irq(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); + + return posted != 0; } static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) @@ -4738,8 +4794,6 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; - - io_get_req_task(req); return 0; } @@ -5626,32 +5680,20 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, static int io_grab_files(struct io_kiocb *req) { - int ret = -EBADF; struct io_ring_ctx *ctx = req->ctx; if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE)) return 0; - if (!ctx->ring_file) - return -EBADF; - rcu_read_lock(); + req->work.files = get_files_struct(current); + get_nsproxy(current->nsproxy); + req->work.nsproxy = current->nsproxy; + req->flags |= REQ_F_INFLIGHT; + spin_lock_irq(&ctx->inflight_lock); - /* - * We use the f_ops->flush() handler to ensure that we can flush - * out work accessing these files if the fd is closed. Check if - * the fd has changed since we started down this path, and disallow - * this operation if it has. - */ - if (fcheck(ctx->ring_fd) == ctx->ring_file) { - list_add(&req->inflight_entry, &ctx->inflight_list); - req->flags |= REQ_F_INFLIGHT; - req->work.files = current->files; - ret = 0; - } + list_add(&req->inflight_entry, &ctx->inflight_list); spin_unlock_irq(&ctx->inflight_lock); - rcu_read_unlock(); - - return ret; + return 0; } static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) @@ -6021,6 +6063,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, /* one is dropped after submission, the other at completion */ refcount_set(&req->refs, 2); req->task = current; + get_task_struct(req->task); + atomic_long_inc(&req->task->io_uring->req_issue); req->result = 0; if (unlikely(req->opcode >= IORING_OP_LAST)) @@ -6056,8 +6100,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, return io_req_set_file(state, req, READ_ONCE(sqe->fd)); } -static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, - struct file *ring_file, int ring_fd) +static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) { struct io_submit_state state, *statep = NULL; struct io_kiocb *link = NULL; @@ -6066,7 +6109,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, /* if we have a backlog and couldn't flush it all, return BUSY */ if (test_bit(0, &ctx->sq_check_overflow)) { if (!list_empty(&ctx->cq_overflow_list) && - !io_cqring_overflow_flush(ctx, false)) + !io_cqring_overflow_flush(ctx, false, NULL, NULL)) return -EBUSY; } @@ -6081,9 +6124,6 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, statep = &state; } - ctx->ring_fd = ring_fd; - ctx->ring_file = ring_file; - for (i = 0; i < nr; i++) { const struct io_uring_sqe *sqe; struct io_kiocb *req; @@ -6244,7 +6284,7 @@ static int io_sq_thread(void *data) mutex_lock(&ctx->uring_lock); if (likely(!percpu_ref_is_dying(&ctx->refs))) - ret = io_submit_sqes(ctx, to_submit, NULL, -1); + ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); timeout = jiffies + ctx->sq_thread_idle; } @@ -7073,14 +7113,38 @@ out_fput: return ret; } +static int io_uring_alloc_task_context(struct task_struct *task) +{ + struct io_uring_task *tctx; + + tctx = kmalloc(sizeof(*tctx), GFP_KERNEL); + if (unlikely(!tctx)) + return -ENOMEM; + + xa_init(&tctx->xa); + init_waitqueue_head(&tctx->wait); + tctx->last = NULL; + tctx->in_idle = 0; + atomic_long_set(&tctx->req_issue, 0); + atomic_long_set(&tctx->req_complete, 0); + task->io_uring = tctx; + return 0; +} + +void __io_uring_free(struct task_struct *tsk) +{ + struct io_uring_task *tctx = tsk->io_uring; + + WARN_ON_ONCE(!xa_empty(&tctx->xa)); + kfree(tctx); + tsk->io_uring = NULL; +} + static int io_sq_offload_start(struct io_ring_ctx *ctx, struct io_uring_params *p) { int ret; - mmgrab(current->mm); - ctx->sqo_mm = current->mm; - if (ctx->flags & IORING_SETUP_SQPOLL) { ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) @@ -7111,6 +7175,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, ctx->sqo_thread = NULL; goto err; } + ret = io_uring_alloc_task_context(ctx->sqo_thread); + if (ret) + goto err; wake_up_process(ctx->sqo_thread); } else if (p->flags & IORING_SETUP_SQ_AFF) { /* Can't have SQ_AFF without SQPOLL */ @@ -7125,8 +7192,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, return 0; err: io_finish_async(ctx); - mmdrop(ctx->sqo_mm); - ctx->sqo_mm = NULL; return ret; } @@ -7456,8 +7521,12 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) static void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_finish_async(ctx); - if (ctx->sqo_mm) - mmdrop(ctx->sqo_mm); + if (ctx->sqo_task) { + put_task_struct(ctx->sqo_task); + ctx->sqo_task = NULL; + mmdrop(ctx->mm_account); + ctx->mm_account = NULL; + } io_iopoll_reap_events(ctx); io_sqe_buffer_unregister(ctx); @@ -7528,7 +7597,7 @@ static void io_ring_exit_work(struct work_struct *work) ctx = container_of(work, struct io_ring_ctx, exit_work); if (ctx->rings) - io_cqring_overflow_flush(ctx, true); + io_cqring_overflow_flush(ctx, true, NULL, NULL); /* * If we're doing polled IO and end up having requests being @@ -7539,7 +7608,7 @@ static void io_ring_exit_work(struct work_struct *work) while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20)) { io_iopoll_reap_events(ctx); if (ctx->rings) - io_cqring_overflow_flush(ctx, true); + io_cqring_overflow_flush(ctx, true, NULL, NULL); } io_ring_ctx_free(ctx); } @@ -7550,8 +7619,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) percpu_ref_kill(&ctx->refs); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx); - io_poll_remove_all(ctx); + io_kill_timeouts(ctx, NULL); + io_poll_remove_all(ctx, NULL); if (ctx->io_wq) io_wq_cancel_all(ctx->io_wq); @@ -7559,7 +7628,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_iopoll_reap_events(ctx); /* if we failed setting up the ctx, we might not have any rings */ if (ctx->rings) - io_cqring_overflow_flush(ctx, true); + io_cqring_overflow_flush(ctx, true, NULL, NULL); idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); /* @@ -7588,7 +7657,7 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data) { struct files_struct *files = data; - return work->files == files; + return !files || work->files == files; } /* @@ -7609,12 +7678,6 @@ static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req) return false; } -static inline bool io_match_files(struct io_kiocb *req, - struct files_struct *files) -{ - return (req->flags & REQ_F_WORK_INITIALIZED) && req->work.files == files; -} - static bool io_match_link_files(struct io_kiocb *req, struct files_struct *files) { @@ -7729,11 +7792,14 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } -static void io_uring_cancel_files(struct io_ring_ctx *ctx, +/* + * Returns true if we found and killed one or more files pinning requests + */ +static bool io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { if (list_empty_careful(&ctx->inflight_list)) - return; + return false; io_cancel_defer_files(ctx, files); /* cancel all at once, should be faster than doing it one by one*/ @@ -7745,7 +7811,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (req->work.files != files) + if (files && req->work.files != files) continue; /* req is being completed, ignore */ if (!refcount_inc_not_zero(&req->refs)) @@ -7791,9 +7857,13 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_put_req(cancel_req); } + /* cancellations _may_ trigger task work */ + io_run_task_work(); schedule(); finish_wait(&ctx->inflight_wait, &wait); } + + return true; } static bool io_cancel_task_cb(struct io_wq_work *work, void *data) @@ -7801,21 +7871,198 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct task_struct *task = data; - return req->task == task; + return io_task_match(req, task); +} + +static bool __io_uring_cancel_task_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + bool ret; + + ret = io_uring_cancel_files(ctx, files); + if (!files) { + enum io_wq_cancel cret; + + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, task, true); + if (cret != IO_WQ_CANCEL_NOTFOUND) + ret = true; + + /* SQPOLL thread does its own polling */ + if (!(ctx->flags & IORING_SETUP_SQPOLL)) { + if (!list_empty_careful(&ctx->poll_list)) { + io_iopoll_reap_events(ctx); + ret = true; + } + } + + ret |= io_poll_remove_all(ctx, task); + ret |= io_kill_timeouts(ctx, task); + } + + return ret; +} + +/* + * We need to iteratively cancel requests, in case a request has dependent + * hard links. These persist even for failure of cancelations, hence keep + * looping until none are found. + */ +static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, + struct files_struct *files) +{ + struct task_struct *task = current; + + if (ctx->flags & IORING_SETUP_SQPOLL) + task = ctx->sqo_thread; + + io_cqring_overflow_flush(ctx, true, task, files); + + while (__io_uring_cancel_task_requests(ctx, task, files)) { + io_run_task_work(); + cond_resched(); + } +} + +/* + * Note that this task has used io_uring. We use it for cancelation purposes. + */ +static int io_uring_add_task_file(struct file *file) +{ + struct io_uring_task *tctx = current->io_uring; + + if (unlikely(!tctx)) { + int ret; + + ret = io_uring_alloc_task_context(current); + if (unlikely(ret)) + return ret; + tctx = current->io_uring; + } + if (tctx->last != file) { + void *old = xa_load(&tctx->xa, (unsigned long)file); + + if (!old) { + get_file(file); + xa_store(&tctx->xa, (unsigned long)file, file, GFP_KERNEL); + } + tctx->last = file; + } + + return 0; +} + +/* + * Remove this io_uring_file -> task mapping. + */ +static void io_uring_del_task_file(struct file *file) +{ + struct io_uring_task *tctx = current->io_uring; + + if (tctx->last == file) + tctx->last = NULL; + file = xa_erase(&tctx->xa, (unsigned long)file); + if (file) + fput(file); +} + +static void __io_uring_attempt_task_drop(struct file *file) +{ + struct file *old = xa_load(¤t->io_uring->xa, (unsigned long)file); + + if (old == file) + io_uring_del_task_file(file); +} + +/* + * Drop task note for this file if we're the only ones that hold it after + * pending fput() + */ +static void io_uring_attempt_task_drop(struct file *file, bool exiting) +{ + if (!current->io_uring) + return; + /* + * fput() is pending, will be 2 if the only other ref is our potential + * task file note. If the task is exiting, drop regardless of count. + */ + if (!exiting && atomic_long_read(&file->f_count) != 2) + return; + + __io_uring_attempt_task_drop(file); +} + +void __io_uring_files_cancel(struct files_struct *files) +{ + struct io_uring_task *tctx = current->io_uring; + struct file *file; + unsigned long index; + + /* make sure overflow events are dropped */ + tctx->in_idle = true; + + xa_for_each(&tctx->xa, index, file) { + struct io_ring_ctx *ctx = file->private_data; + + io_uring_cancel_task_requests(ctx, files); + if (files) + io_uring_del_task_file(file); + } +} + +static inline bool io_uring_task_idle(struct io_uring_task *tctx) +{ + return atomic_long_read(&tctx->req_issue) == + atomic_long_read(&tctx->req_complete); +} + +/* + * Find any io_uring fd that this task has registered or done IO on, and cancel + * requests. + */ +void __io_uring_task_cancel(void) +{ + struct io_uring_task *tctx = current->io_uring; + DEFINE_WAIT(wait); + long completions; + + /* make sure overflow events are dropped */ + tctx->in_idle = true; + + while (!io_uring_task_idle(tctx)) { + /* read completions before cancelations */ + completions = atomic_long_read(&tctx->req_complete); + __io_uring_files_cancel(NULL); + + prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); + + /* + * If we've seen completions, retry. This avoids a race where + * a completion comes in before we did prepare_to_wait(). + */ + if (completions != atomic_long_read(&tctx->req_complete)) + continue; + if (io_uring_task_idle(tctx)) + break; + schedule(); + } + + finish_wait(&tctx->wait, &wait); + tctx->in_idle = false; } static int io_uring_flush(struct file *file, void *data) { struct io_ring_ctx *ctx = file->private_data; - io_uring_cancel_files(ctx, data); - /* * If the task is going away, cancel work it may have pending */ if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) - io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, current, true); + data = NULL; + io_uring_cancel_task_requests(ctx, data); + io_uring_attempt_task_drop(file, !data); return 0; } @@ -7924,13 +8171,16 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { if (!list_empty_careful(&ctx->cq_overflow_list)) - io_cqring_overflow_flush(ctx, false); + io_cqring_overflow_flush(ctx, false, NULL, NULL); if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sqo_wait); submitted = to_submit; } else if (to_submit) { + ret = io_uring_add_task_file(f.file); + if (unlikely(ret)) + goto out; mutex_lock(&ctx->uring_lock); - submitted = io_submit_sqes(ctx, to_submit, f.file, fd); + submitted = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); if (submitted != to_submit) @@ -8142,6 +8392,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); if (IS_ERR(file)) { +err_fd: put_unused_fd(ret); ret = PTR_ERR(file); goto err; @@ -8150,6 +8401,10 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; #endif + if (unlikely(io_uring_add_task_file(file))) { + file = ERR_PTR(-ENOMEM); + goto err_fd; + } fd_install(ret, file); return ret; err: @@ -8228,6 +8483,16 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->user = user; ctx->creds = get_current_cred(); + ctx->sqo_task = get_task_struct(current); + /* + * This is just grabbed for accounting purposes. When a process exits, + * the mm is exited and dropped before the files, hence we need to hang + * on to this mm purely for the purposes of being able to unaccount + * memory (locked/pinned vm). It's not used for anything else. + */ + mmgrab(current->mm); + ctx->mm_account = current->mm; + ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index bcfc288dba3f..b115e7d47fce 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -49,16 +49,8 @@ iomap_page_create(struct inode *inode, struct page *page) if (iop || i_blocksize(inode) == PAGE_SIZE) return iop; - iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); - atomic_set(&iop->read_count, 0); - atomic_set(&iop->write_count, 0); + iop = kzalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); spin_lock_init(&iop->uptodate_lock); - bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); - - /* - * migrate_page_move_mapping() assumes that pages with private data have - * their count elevated by 1. - */ attach_page_private(page, iop); return iop; } @@ -574,10 +566,10 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, loff_t block_start = pos & ~(block_size - 1); loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1); unsigned from = offset_in_page(pos), to = from + len, poff, plen; - int status; if (PageUptodate(page)) return 0; + ClearPageError(page); do { iomap_adjust_read_range(inode, iop, &block_start, @@ -594,14 +586,13 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) return -EIO; zero_user_segments(page, poff, from, to, poff + plen); - iomap_set_range_uptodate(page, poff, plen); - continue; + } else { + int status = iomap_read_page_sync(block_start, page, + poff, plen, srcmap); + if (status) + return status; } - - status = iomap_read_page_sync(block_start, page, poff, plen, - srcmap); - if (status) - return status; + iomap_set_range_uptodate(page, poff, plen); } while ((block_start += plen) < block_end); return 0; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index ec7b78e6feca..28d656b15300 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -387,6 +387,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, return iomap_dio_bio_actor(inode, pos, length, dio, iomap); case IOMAP_INLINE: return iomap_dio_inline_actor(inode, pos, length, dio, iomap); + case IOMAP_DELALLOC: + /* + * DIO is not serialised against mmap() access at all, and so + * if the page_mkwrite occurs between the writeback and the + * iomap_apply() call in the DIO path, then it will see the + * DELALLOC block that the page-mkwrite allocated. + */ + pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", + dio->iocb->ki_filp, current->comm); + return -EIO; default: WARN_ON_ONCE(1); return -EIO; diff --git a/fs/namespace.c b/fs/namespace.c index 4a0f600a3328..2b7e1ac8c4c5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -431,6 +431,7 @@ void __mnt_drop_write(struct vfsmount *mnt) mnt_dec_writers(real_mount(mnt)); preempt_enable(); } +EXPORT_SYMBOL_GPL(__mnt_drop_write); /** * mnt_drop_write - give up write access to a mount @@ -792,6 +793,13 @@ static inline int check_mnt(struct mount *mnt) return mnt->mnt_ns == current->nsproxy->mnt_ns; } +/* for aufs, CONFIG_AUFS_BR_FUSE */ +int is_current_mnt_ns(struct vfsmount *mnt) +{ + return check_mnt(real_mount(mnt)); +} +EXPORT_SYMBOL_GPL(is_current_mnt_ns); + /* * vfsmount lock must be held for write */ @@ -1955,6 +1963,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, } return 0; } +EXPORT_SYMBOL_GPL(iterate_mounts); static void lock_mnt_tree(struct mount *mnt) { diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 88e1763e02f3..80f39072acf4 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -40,6 +40,19 @@ config NFS_V2 If unsure, say Y. +config NFS_DEF_FILE_IO_SIZE + int "Default size for NFS I/O read and write at runtime" + depends on NFS_FS + default "4096" + help + To change the default rsize and wsize supported by the NFS client, + adjust NFS_DEF_FILE_IO_SIZE. 64KB is a typical maximum, but some + servers can support a megabyte or more. The default is left at 4096 + bytes, which is reasonable for NFS over UDP, however, for some + systems, setting a smaller value like 1024 can work around + limitations in the driver or hardware and result in overall + improved performance. + config NFS_V3 tristate "NFS client support for NFS version 3" depends on NFS_FS diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index ccc88be88d6a..a30b4bcb95a2 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -94,6 +94,7 @@ enum { static const struct constant_table nfs_param_enums_local_lock[] = { { "all", Opt_local_lock_all }, { "flock", Opt_local_lock_flock }, + { "posix", Opt_local_lock_posix }, { "none", Opt_local_lock_none }, {} }; diff --git a/fs/notify/group.c b/fs/notify/group.c index a4a4b1c64d32..86dc2efb1850 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -100,6 +100,7 @@ void fsnotify_get_group(struct fsnotify_group *group) { refcount_inc(&group->refcnt); } +EXPORT_SYMBOL_GPL(fsnotify_get_group); /* * Drop a reference to a group. Free it if it's through. diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d4359a1df3d5..84933a0af49b 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1809,6 +1809,12 @@ int ntfs_read_inode_mount(struct inode *vi) brelse(bh); } + if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) { + ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.", + le32_to_cpu(m->bytes_allocated), vol->mft_record_size); + goto err_out; + } + /* Apply the mst fixups. */ if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) { /* FIXME: Try to use the $MFTMirr now. */ diff --git a/fs/open.c b/fs/open.c index 6cd48a61cda3..bb623ca6397e 100644 --- a/fs/open.c +++ b/fs/open.c @@ -65,6 +65,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, inode_unlock(dentry->d_inode); return ret; } +EXPORT_SYMBOL_GPL(do_truncate); long vfs_truncate(const struct path *path, loff_t length) { diff --git a/fs/proc/base.c b/fs/proc/base.c index d86c0afc8a85..9de08d2427e3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1046,7 +1046,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { - static DEFINE_MUTEX(oom_adj_mutex); struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; @@ -1086,7 +1085,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) struct task_struct *p = find_lock_task_mm(task); if (p) { - if (atomic_read(&p->mm->mm_users) > 1) { + if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } @@ -2170,7 +2169,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { - *path = vma->vm_file->f_path; + *path = vma_pr_or_file(vma)->f_path; path_get(path); rc = 0; } diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 13452b32e2bd..38acccfef9d4 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -40,7 +40,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) file = region->vm_file; if (file) { - struct inode *inode = file_inode(region->vm_file); + struct inode *inode; + + file = vmr_pr_or_file(region); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index dbda4499a859..5f6fdf574d83 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -280,7 +280,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) const char *name = NULL; if (file) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode; + + file = vma_pr_or_file(vma); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; @@ -1793,7 +1796,7 @@ static int show_numa_map(struct seq_file *m, void *v) struct proc_maps_private *proc_priv = &numa_priv->proc_maps; struct vm_area_struct *vma = v; struct numa_maps *md = &numa_priv->md; - struct file *file = vma->vm_file; + struct file *file = vma_pr_or_file(vma); struct mm_struct *mm = vma->vm_mm; struct mempolicy *pol; char buffer[64]; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a6d21fc0033c..02c2de31196e 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -155,7 +155,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) file = vma->vm_file; if (file) { - struct inode *inode = file_inode(vma->vm_file); + struct inode *inode; + + file = vma_pr_or_file(vma); + inode = file_inode(file); dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT; diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 58fc2a7c7fd1..e69a2bfdd81c 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -282,6 +282,7 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); + d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 414695454956..355523f4a4bf 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -224,7 +224,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, if (!pages) goto out_free; - nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages); + nr = find_get_pages_contig(inode->i_mapping, pgoff, lpages, pages); if (nr != lpages) goto out_free_pages; /* leave if some pages were missing */ diff --git a/fs/read_write.c b/fs/read_write.c index 9a5cb9c2f0d4..0786717c4c3a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -488,6 +488,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) inc_syscr(current); return ret; } +EXPORT_SYMBOL_GPL(vfs_read); static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { @@ -507,6 +508,30 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t return ret; } +vfs_readf_t vfs_readf(struct file *file) +{ + const struct file_operations *fop = file->f_op; + + if (fop->read) + return fop->read; + if (fop->read_iter) + return new_sync_read; + return ERR_PTR(-ENOSYS); /* doesn't have ->read(|_iter)() op */ +} +EXPORT_SYMBOL_GPL(vfs_readf); + +vfs_writef_t vfs_writef(struct file *file) +{ + const struct file_operations *fop = file->f_op; + + if (fop->write) + return fop->write; + if (fop->write_iter) + return new_sync_write; + return ERR_PTR(-ENOSYS); /* doesn't have ->write(|_iter)() op */ +} +EXPORT_SYMBOL_GPL(vfs_writef); + /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { @@ -594,6 +619,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ file_end_write(file); return ret; } +EXPORT_SYMBOL_GPL(vfs_write); /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index e43fed96704d..c76d563dec0e 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2159,7 +2159,8 @@ out_end_trans: out_inserted_sd: clear_nlink(inode); th->t_trans_id = 0; /* so the caller can't use this handle later */ - unlock_new_inode(inode); /* OK to do even if we hadn't locked it */ + if (inode->i_state & I_NEW) + unlock_new_inode(inode); iput(inode); return err; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index a6bce5b1fb1d..1b9c7a387dc7 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1258,6 +1258,10 @@ static int reiserfs_parse_options(struct super_block *s, "turned on."); return 0; } + if (qf_names[qtype] != + REISERFS_SB(s)->s_qf_names[qtype]) + kfree(qf_names[qtype]); + qf_names[qtype] = NULL; if (*arg) { /* Some filename specified? */ if (REISERFS_SB(s)->s_qf_names[qtype] && strcmp(REISERFS_SB(s)->s_qf_names[qtype], @@ -1287,10 +1291,6 @@ static int reiserfs_parse_options(struct super_block *s, else *mount_options |= 1 << REISERFS_GRPQUOTA; } else { - if (qf_names[qtype] != - REISERFS_SB(s)->s_qf_names[qtype]) - kfree(qf_names[qtype]); - qf_names[qtype] = NULL; if (qtype == USRQUOTA) *mount_options &= ~(1 << REISERFS_USRQUOTA); else diff --git a/fs/splice.c b/fs/splice.c index ce75aec52274..ea94bac4072d 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -859,20 +859,21 @@ EXPORT_SYMBOL(generic_splice_sendpage); /* * Attempt to initiate a splice from pipe to file. */ -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { if (out->f_op->splice_write) return out->f_op->splice_write(pipe, out, ppos, len, flags); return default_file_splice_write(pipe, out, ppos, len, flags); } +EXPORT_SYMBOL_GPL(do_splice_from); /* * Attempt to initiate a splice from a file to a pipe. */ -static long do_splice_to(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { int ret; @@ -890,6 +891,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, return in->f_op->splice_read(in, ppos, pipe, len, flags); return default_file_splice_read(in, ppos, pipe, len, flags); } +EXPORT_SYMBOL_GPL(do_splice_to); /** * splice_direct_to_actor - splices data directly between two non-pipes diff --git a/fs/sync.c b/fs/sync.c index 1373a610dc78..fa5c7fba7f1b 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -28,7 +28,7 @@ * wait == 1 case since in that case write_inode() functions do * sync_dirty_buffer() and thus effectively write one block at a time. */ -static int __sync_filesystem(struct super_block *sb, int wait) +int __sync_filesystem(struct super_block *sb, int wait) { if (wait) sync_inodes_sb(sb); @@ -39,6 +39,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) sb->s_op->sync_fs(sb, wait); return __sync_blockdev(sb->s_bdev, wait); } +EXPORT_SYMBOL_GPL(__sync_filesystem); /* * Write out and wait upon all dirty data associated with this diff --git a/fs/udf/inode.c b/fs/udf/inode.c index adaba8e8b326..566118417e56 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -139,21 +139,24 @@ void udf_evict_inode(struct inode *inode) struct udf_inode_info *iinfo = UDF_I(inode); int want_delete = 0; - if (!inode->i_nlink && !is_bad_inode(inode)) { - want_delete = 1; - udf_setsize(inode, 0); - udf_update_inode(inode, IS_SYNC(inode)); + if (!is_bad_inode(inode)) { + if (!inode->i_nlink) { + want_delete = 1; + udf_setsize(inode, 0); + udf_update_inode(inode, IS_SYNC(inode)); + } + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && + inode->i_size != iinfo->i_lenExtents) { + udf_warn(inode->i_sb, + "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", + inode->i_ino, inode->i_mode, + (unsigned long long)inode->i_size, + (unsigned long long)iinfo->i_lenExtents); + } } truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); - if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && - inode->i_size != iinfo->i_lenExtents) { - udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", - inode->i_ino, inode->i_mode, - (unsigned long long)inode->i_size, - (unsigned long long)iinfo->i_lenExtents); - } kfree(iinfo->i_ext.i_data); iinfo->i_ext.i_data = NULL; udf_clear_extent_cache(inode); diff --git a/fs/udf/super.c b/fs/udf/super.c index f747bf72edbe..a6ce0ddb392c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1353,6 +1353,12 @@ static int udf_load_sparable_map(struct super_block *sb, (int)spm->numSparingTables); return -EIO; } + if (le32_to_cpu(spm->sizeSparingTable) > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Too big sparing table size (%u)\n", + le32_to_cpu(spm->sizeSparingTable)); + return -EIO; + } for (i = 0; i < spm->numSparingTables; i++) { loc = le32_to_cpu(spm->locSparingTable[i]); diff --git a/fs/xattr.c b/fs/xattr.c index 95f38f57347f..f01b5bd9c102 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -333,6 +333,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, *xattr_value = value; return error; } +EXPORT_SYMBOL_GPL(vfs_getxattr_alloc); ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 9498ced947be..2a3857618930 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1018,7 +1018,6 @@ xfs_rtalloc_query_range( struct xfs_mount *mp = tp->t_mountp; xfs_rtblock_t rtstart; xfs_rtblock_t rtend; - xfs_rtblock_t rem; int is_free; int error = 0; @@ -1027,13 +1026,12 @@ xfs_rtalloc_query_range( if (low_rec->ar_startext >= mp->m_sb.sb_rextents || low_rec->ar_startext == high_rec->ar_startext) return 0; - if (high_rec->ar_startext > mp->m_sb.sb_rextents) - high_rec->ar_startext = mp->m_sb.sb_rextents; + high_rec->ar_startext = min(high_rec->ar_startext, + mp->m_sb.sb_rextents - 1); /* Iterate the bitmap, looking for discrepancies. */ rtstart = low_rec->ar_startext; - rem = high_rec->ar_startext - rtstart; - while (rem) { + while (rtstart <= high_rec->ar_startext) { /* Is the first block free? */ error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend, &is_free); @@ -1042,7 +1040,7 @@ xfs_rtalloc_query_range( /* How long does the extent go for? */ error = xfs_rtfind_forw(mp, tp, rtstart, - high_rec->ar_startext - 1, &rtend); + high_rec->ar_startext, &rtend); if (error) break; @@ -1055,7 +1053,6 @@ xfs_rtalloc_query_range( break; } - rem -= rtend - rtstart + 1; rtstart = rtend + 1; } diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 04faa7310c4f..8140bd870226 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -721,6 +721,8 @@ xlog_recover_get_buf_lsn( case XFS_ABTC_MAGIC: case XFS_RMAP_CRC_MAGIC: case XFS_REFC_CRC_MAGIC: + case XFS_FIBT_CRC_MAGIC: + case XFS_FIBT_MAGIC: case XFS_IBT_CRC_MAGIC: case XFS_IBT_MAGIC: { struct xfs_btree_block *btb = blk; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4d7385426149..3ebc73ccc133 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1005,6 +1005,21 @@ xfs_file_fadvise( return ret; } +/* Does this file, inode, or mount want synchronous writes? */ +static inline bool xfs_file_sync_writes(struct file *filp) +{ + struct xfs_inode *ip = XFS_I(file_inode(filp)); + + if (ip->i_mount->m_flags & XFS_MOUNT_WSYNC) + return true; + if (filp->f_flags & (__O_SYNC | O_DSYNC)) + return true; + if (IS_SYNC(file_inode(filp))) + return true; + + return false; +} + STATIC loff_t xfs_file_remap_range( struct file *file_in, @@ -1062,7 +1077,7 @@ xfs_file_remap_range( if (ret) goto out_unlock; - if (mp->m_flags & XFS_MOUNT_WSYNC) + if (xfs_file_sync_writes(file_in) || xfs_file_sync_writes(file_out)) xfs_log_force_inode(dest); out_unlock: xfs_reflink_remap_unlock(file_in, file_out); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 4eebcec4aae6..9ce5e7d5bf8f 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -26,7 +26,7 @@ #include "xfs_rtalloc.h" /* Convert an xfs_fsmap to an fsmap. */ -void +static void xfs_fsmap_from_internal( struct fsmap *dest, struct xfs_fsmap *src) @@ -155,8 +155,7 @@ xfs_fsmap_owner_from_rmap( /* getfsmap query state */ struct xfs_getfsmap_info { struct xfs_fsmap_head *head; - xfs_fsmap_format_t formatter; /* formatting fn */ - void *format_arg; /* format buffer */ + struct fsmap *fsmap_recs; /* mapping records */ struct xfs_buf *agf_bp; /* AGF, for refcount queries */ xfs_daddr_t next_daddr; /* next daddr we expect */ u64 missing_owner; /* owner of holes */ @@ -224,6 +223,20 @@ xfs_getfsmap_is_shared( return 0; } +static inline void +xfs_getfsmap_format( + struct xfs_mount *mp, + struct xfs_fsmap *xfm, + struct xfs_getfsmap_info *info) +{ + struct fsmap *rec; + + trace_xfs_getfsmap_mapping(mp, xfm); + + rec = &info->fsmap_recs[info->head->fmh_entries++]; + xfs_fsmap_from_internal(rec, xfm); +} + /* * Format a reverse mapping for getfsmap, having translated rm_startblock * into the appropriate daddr units. @@ -256,6 +269,9 @@ xfs_getfsmap_helper( /* Are we just counting mappings? */ if (info->head->fmh_count == 0) { + if (info->head->fmh_entries == UINT_MAX) + return -ECANCELED; + if (rec_daddr > info->next_daddr) info->head->fmh_entries++; @@ -285,10 +301,7 @@ xfs_getfsmap_helper( fmr.fmr_offset = 0; fmr.fmr_length = rec_daddr - info->next_daddr; fmr.fmr_flags = FMR_OF_SPECIAL_OWNER; - error = info->formatter(&fmr, info->format_arg); - if (error) - return error; - info->head->fmh_entries++; + xfs_getfsmap_format(mp, &fmr, info); } if (info->last) @@ -320,11 +333,8 @@ xfs_getfsmap_helper( if (shared) fmr.fmr_flags |= FMR_OF_SHARED; } - error = info->formatter(&fmr, info->format_arg); - if (error) - return error; - info->head->fmh_entries++; + xfs_getfsmap_format(mp, &fmr, info); out: rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); if (info->next_daddr < rec_daddr) @@ -792,11 +802,11 @@ xfs_getfsmap_check_keys( #endif /* CONFIG_XFS_RT */ /* - * Get filesystem's extents as described in head, and format for - * output. Calls formatter to fill the user's buffer until all - * extents are mapped, until the passed-in head->fmh_count slots have - * been filled, or until the formatter short-circuits the loop, if it - * is tracking filled-in extents on its own. + * Get filesystem's extents as described in head, and format for output. Fills + * in the supplied records array until there are no more reverse mappings to + * return or head.fmh_entries == head.fmh_count. In the second case, this + * function returns -ECANCELED to indicate that more records would have been + * returned. * * Key to Confusion * ---------------- @@ -816,8 +826,7 @@ int xfs_getfsmap( struct xfs_mount *mp, struct xfs_fsmap_head *head, - xfs_fsmap_format_t formatter, - void *arg) + struct fsmap *fsmap_recs) { struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ @@ -892,8 +901,7 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.formatter = formatter; - info.format_arg = arg; + info.fsmap_recs = fsmap_recs; info.head = head; /* diff --git a/fs/xfs/xfs_fsmap.h b/fs/xfs/xfs_fsmap.h index c6c57739b862..a0775788e7b1 100644 --- a/fs/xfs/xfs_fsmap.h +++ b/fs/xfs/xfs_fsmap.h @@ -27,13 +27,9 @@ struct xfs_fsmap_head { struct xfs_fsmap fmh_keys[2]; /* low and high keys */ }; -void xfs_fsmap_from_internal(struct fsmap *dest, struct xfs_fsmap *src); void xfs_fsmap_to_internal(struct xfs_fsmap *dest, struct fsmap *src); -/* fsmap to userspace formatter - copy to user & advance pointer */ -typedef int (*xfs_fsmap_format_t)(struct xfs_fsmap *, void *); - int xfs_getfsmap(struct xfs_mount *mp, struct xfs_fsmap_head *head, - xfs_fsmap_format_t formatter, void *arg); + struct fsmap *out_recs); #endif /* __XFS_FSMAP_H__ */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a190212ca85d..e2a8edcb367b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1707,39 +1707,17 @@ out_free_buf: return error; } -struct getfsmap_info { - struct xfs_mount *mp; - struct fsmap_head __user *data; - unsigned int idx; - __u32 last_flags; -}; - -STATIC int -xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv) -{ - struct getfsmap_info *info = priv; - struct fsmap fm; - - trace_xfs_getfsmap_mapping(info->mp, xfm); - - info->last_flags = xfm->fmr_flags; - xfs_fsmap_from_internal(&fm, xfm); - if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm, - sizeof(struct fsmap))) - return -EFAULT; - - return 0; -} - STATIC int xfs_ioc_getfsmap( struct xfs_inode *ip, struct fsmap_head __user *arg) { - struct getfsmap_info info = { NULL }; struct xfs_fsmap_head xhead = {0}; struct fsmap_head head; - bool aborted = false; + struct fsmap *recs; + unsigned int count; + __u32 last_flags = 0; + bool done = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) @@ -1751,38 +1729,112 @@ xfs_ioc_getfsmap( sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; + /* + * Use an internal memory buffer so that we don't have to copy fsmap + * data to userspace while holding locks. Start by trying to allocate + * up to 128k for the buffer, but fall back to a single page if needed. + */ + count = min_t(unsigned int, head.fmh_count, + 131072 / sizeof(struct fsmap)); + recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL); + if (!recs) { + count = min_t(unsigned int, head.fmh_count, + PAGE_SIZE / sizeof(struct fsmap)); + recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL); + if (!recs) + return -ENOMEM; + } + xhead.fmh_iflags = head.fmh_iflags; - xhead.fmh_count = head.fmh_count; xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]); xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]); trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]); - info.mp = ip->i_mount; - info.data = arg; - error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info); - if (error == -ECANCELED) { - error = 0; - aborted = true; - } else if (error) - return error; + head.fmh_entries = 0; + do { + struct fsmap __user *user_recs; + struct fsmap *last_rec; + + user_recs = &arg->fmh_recs[head.fmh_entries]; + xhead.fmh_entries = 0; + xhead.fmh_count = min_t(unsigned int, count, + head.fmh_count - head.fmh_entries); + + /* Run query, record how many entries we got. */ + error = xfs_getfsmap(ip->i_mount, &xhead, recs); + switch (error) { + case 0: + /* + * There are no more records in the result set. Copy + * whatever we got to userspace and break out. + */ + done = true; + break; + case -ECANCELED: + /* + * The internal memory buffer is full. Copy whatever + * records we got to userspace and go again if we have + * not yet filled the userspace buffer. + */ + error = 0; + break; + default: + goto out_free; + } + head.fmh_entries += xhead.fmh_entries; + head.fmh_oflags = xhead.fmh_oflags; - /* If we didn't abort, set the "last" flag in the last fmx */ - if (!aborted && info.idx) { - info.last_flags |= FMR_OF_LAST; - if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags, - &info.last_flags, sizeof(info.last_flags))) - return -EFAULT; + /* + * If the caller wanted a record count or there aren't any + * new records to return, we're done. + */ + if (head.fmh_count == 0 || xhead.fmh_entries == 0) + break; + + /* Copy all the records we got out to userspace. */ + if (copy_to_user(user_recs, recs, + xhead.fmh_entries * sizeof(struct fsmap))) { + error = -EFAULT; + goto out_free; + } + + /* Remember the last record flags we copied to userspace. */ + last_rec = &recs[xhead.fmh_entries - 1]; + last_flags = last_rec->fmr_flags; + + /* Set up the low key for the next iteration. */ + xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec); + trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); + } while (!done && head.fmh_entries < head.fmh_count); + + /* + * If there are no more records in the query result set and we're not + * in counting mode, mark the last record returned with the LAST flag. + */ + if (done && head.fmh_count > 0 && head.fmh_entries > 0) { + struct fsmap __user *user_rec; + + last_flags |= FMR_OF_LAST; + user_rec = &arg->fmh_recs[head.fmh_entries - 1]; + + if (copy_to_user(&user_rec->fmr_flags, &last_flags, + sizeof(last_flags))) { + error = -EFAULT; + goto out_free; + } } /* copy back header */ - head.fmh_entries = xhead.fmh_entries; - head.fmh_oflags = xhead.fmh_oflags; - if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) - return -EFAULT; + if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) { + error = -EFAULT; + goto out_free; + } - return 0; +out_free: + kmem_free(recs); + return error; } STATIC int diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 6209e7b6b895..86994d7f7cba 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -247,6 +247,9 @@ xfs_rtallocate_extent_block( end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1; i <= end; i++) { + /* Make sure we don't scan off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, i + maxlen) - i; + /* * See if there's a free extent of maxlen starting at i. * If it's not so then next will contain the first non-free. @@ -442,6 +445,14 @@ xfs_rtallocate_extent_near( */ if (bno >= mp->m_sb.sb_rextents) bno = mp->m_sb.sb_rextents - 1; + + /* Make sure we don't run off the end of the rt volume. */ + maxlen = min(mp->m_sb.sb_rextents, bno + maxlen) - bno; + if (maxlen < minlen) { + *rtblock = NULLRTBLOCK; + return 0; + } + /* * Try the exact allocation first. */ diff --git a/fs/yaffs2/Kconfig b/fs/yaffs2/Kconfig new file mode 100644 index 000000000000..408570fc7a5e --- /dev/null +++ b/fs/yaffs2/Kconfig @@ -0,0 +1,171 @@ +# +# yaffs file system configurations +# + +config YAFFS_FS + tristate "yaffs2 file system support" + default n + depends on MTD_BLOCK + select YAFFS_YAFFS1 + select YAFFS_YAFFS2 + help + yaffs2, or Yet Another Flash File System, is a file system + optimised for NAND Flash chips. + + To compile the yaffs2 file system support as a module, choose M + here: the module will be called yaffs2. + + If unsure, say N. + + Further information on yaffs2 is available at + <http://www.aleph1.co.uk/yaffs/>. + +config YAFFS_YAFFS1 + bool "512 byte / page devices" + depends on YAFFS_FS + default y + help + Enable yaffs1 support -- yaffs for 512 byte / page devices + + Not needed for 2K-page devices. + + If unsure, say Y. + +config YAFFS_9BYTE_TAGS + bool "Use older-style on-NAND data format with pageStatus byte" + depends on YAFFS_YAFFS1 + default n + help + + Older-style on-NAND data format has a "pageStatus" byte to record + chunk/page state. This byte is zero when the page is discarded. + Choose this option if you have existing on-NAND data using this + format that you need to continue to support. New data written + also uses the older-style format. Note: Use of this option + generally requires that MTD's oob layout be adjusted to use the + older-style format. See notes on tags formats and MTD versions + in yaffs_mtdif1.c. + + If unsure, say N. + +config YAFFS_DOES_ECC + bool "Lets yaffs do its own ECC" + depends on YAFFS_FS && YAFFS_YAFFS1 && !YAFFS_9BYTE_TAGS + default n + help + This enables yaffs to use its own ECC functions instead of using + the ones from the generic MTD-NAND driver. + + If unsure, say N. + +config YAFFS_ECC_WRONG_ORDER + bool "Use the same ecc byte order as Steven Hill's nand_ecc.c" + depends on YAFFS_FS && YAFFS_DOES_ECC && !YAFFS_9BYTE_TAGS + default n + help + This makes yaffs_ecc.c use the same ecc byte order as Steven + Hill's nand_ecc.c. If not set, then you get the same ecc byte + order as SmartMedia. + + If unsure, say N. + +config YAFFS_YAFFS2 + bool "2048 byte (or larger) / page devices" + depends on YAFFS_FS + default y + help + Enable yaffs2 support -- yaffs for >= 2K bytes per page devices + + If unsure, say Y. + +config YAFFS_AUTO_YAFFS2 + bool "Autoselect yaffs2 format" + depends on YAFFS_YAFFS2 + default y + help + Without this, you need to explicitely use yaffs2 as the file + system type. With this, you can say "yaffs" and yaffs or yaffs2 + will be used depending on the device page size (yaffs on + 512-byte page devices, yaffs2 on 2K page devices). + + If unsure, say Y. + +config YAFFS_DISABLE_TAGS_ECC + bool "Disable yaffs from doing ECC on tags by default" + depends on YAFFS_FS && YAFFS_YAFFS2 + default n + help + This defaults yaffs to using its own ECC calculations on tags instead of + just relying on the MTD. + This behavior can also be overridden with tags_ecc_on and + tags_ecc_off mount options. + + If unsure, say N. + +config YAFFS_ALWAYS_CHECK_CHUNK_ERASED + bool "Force chunk erase check" + depends on YAFFS_FS + default n + help + Normally yaffs only checks chunks before writing until an erased + chunk is found. This helps to detect any partially written + chunks that might have happened due to power loss. + + Enabling this forces on the test that chunks are erased in flash + before writing to them. This takes more time but is potentially + a bit more secure. + + Suggest setting Y during development and ironing out driver + issues etc. Suggest setting to N if you want faster writing. + + If unsure, say Y. + +config YAFFS_EMPTY_LOST_AND_FOUND + bool "Empty lost and found on boot" + depends on YAFFS_FS + default n + help + If this is enabled then the contents of lost and found is + automatically dumped at mount. + + If unsure, say N. + +config YAFFS_DISABLE_BLOCK_REFRESHING + bool "Disable yaffs2 block refreshing" + depends on YAFFS_FS + default n + help + If this is set, then block refreshing is disabled. + Block refreshing infrequently refreshes the oldest block in + a yaffs2 file system. This mechanism helps to refresh flash to + mitigate against data loss. This is particularly useful for MLC. + + If unsure, say N. + +config YAFFS_DISABLE_BACKGROUND + bool "Disable yaffs2 background processing" + depends on YAFFS_FS + default n + help + If this is set, then background processing is disabled. + Background processing makes many foreground activities faster. + + If unsure, say N. + +config YAFFS_DISABLE_BAD_BLOCK_MARKING + bool "Disable yaffs2 bad block marking" + depends on YAFFS_FS + default n + help + Useful during early flash bring up to prevent problems causing + lots of bad block marking. + + If unsure, say N. + +config YAFFS_XATTR + bool "Enable yaffs2 xattr support" + depends on YAFFS_FS + default y + help + If this is set then yaffs2 will provide xattr support. + If unsure, say Y. diff --git a/fs/yaffs2/Makefile b/fs/yaffs2/Makefile new file mode 100644 index 000000000000..c05239594827 --- /dev/null +++ b/fs/yaffs2/Makefile @@ -0,0 +1,19 @@ +# +# Makefile for the linux YAFFS filesystem routines. +# + +obj-$(CONFIG_YAFFS_FS) += yaffs.o + +yaffs-y := yaffs_ecc.o yaffs_vfs.o yaffs_guts.o yaffs_checkptrw.o +yaffs-y += yaffs_packedtags1.o yaffs_packedtags2.o yaffs_nand.o +yaffs-y += yaffs_tagscompat.o yaffs_tagsmarshall.o +yaffs-y += yaffs_endian.o +yaffs-y += yaffs_mtdif.o +yaffs-y += yaffs_nameval.o yaffs_attribs.o +yaffs-y += yaffs_allocator.o +yaffs-y += yaffs_yaffs1.o +yaffs-y += yaffs_yaffs2.o +yaffs-y += yaffs_bitmap.o +yaffs-y += yaffs_summary.o +yaffs-y += yaffs_verify.o + diff --git a/fs/yaffs2/yaffs_allocator.c b/fs/yaffs2/yaffs_allocator.c new file mode 100644 index 000000000000..be27833ad497 --- /dev/null +++ b/fs/yaffs2/yaffs_allocator.c @@ -0,0 +1,356 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_allocator.h" +#include "yaffs_guts.h" +#include "yaffs_trace.h" +#include "yportenv.h" + +/* + * Each entry in yaffs_tnode_list and yaffs_obj_list hold blocks + * of approx 100 objects that are themn allocated singly. + * This is basically a simplified slab allocator. + * + * We don't use the Linux slab allocator because slab does not allow + * us to dump all the objects in one hit when we do a umount and tear + * down all the tnodes and objects. slab requires that we first free + * the individual objects. + * + * Once yaffs has been mainlined I shall try to motivate for a change + * to slab to provide the extra features we need here. + */ + +struct yaffs_tnode_list { + struct yaffs_tnode_list *next; + struct yaffs_tnode *tnodes; +}; + +struct yaffs_obj_list { + struct yaffs_obj_list *next; + struct yaffs_obj *objects; +}; + +struct yaffs_allocator { + int n_tnodes_created; + struct yaffs_tnode *free_tnodes; + int n_free_tnodes; + struct yaffs_tnode_list *alloc_tnode_list; + + int n_obj_created; + struct list_head free_objs; + int n_free_objects; + + struct yaffs_obj_list *allocated_obj_list; +}; + +static void yaffs_deinit_raw_tnodes(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator = + (struct yaffs_allocator *)dev->allocator; + struct yaffs_tnode_list *tmp; + + if (!allocator) { + BUG(); + return; + } + + while (allocator->alloc_tnode_list) { + tmp = allocator->alloc_tnode_list->next; + + kfree(allocator->alloc_tnode_list->tnodes); + kfree(allocator->alloc_tnode_list); + allocator->alloc_tnode_list = tmp; + } + + allocator->free_tnodes = NULL; + allocator->n_free_tnodes = 0; + allocator->n_tnodes_created = 0; +} + +static void yaffs_init_raw_tnodes(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator = dev->allocator; + + if (!allocator) { + BUG(); + return; + } + + allocator->alloc_tnode_list = NULL; + allocator->free_tnodes = NULL; + allocator->n_free_tnodes = 0; + allocator->n_tnodes_created = 0; +} + +static int yaffs_create_tnodes(struct yaffs_dev *dev, int n_tnodes) +{ + struct yaffs_allocator *allocator = + (struct yaffs_allocator *)dev->allocator; + int i; + struct yaffs_tnode *new_tnodes; + u8 *mem; + struct yaffs_tnode *curr; + struct yaffs_tnode *next; + struct yaffs_tnode_list *tnl; + + if (!allocator) { + BUG(); + return YAFFS_FAIL; + } + + if (n_tnodes < 1) + return YAFFS_OK; + + /* make these things */ + new_tnodes = kmalloc(n_tnodes * dev->tnode_size, GFP_NOFS); + mem = (u8 *) new_tnodes; + + if (!new_tnodes) { + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs: Could not allocate Tnodes"); + return YAFFS_FAIL; + } + + /* New hookup for wide tnodes */ + for (i = 0; i < n_tnodes - 1; i++) { + curr = (struct yaffs_tnode *)&mem[i * dev->tnode_size]; + next = (struct yaffs_tnode *)&mem[(i + 1) * dev->tnode_size]; + curr->internal[0] = next; + } + + curr = (struct yaffs_tnode *)&mem[(n_tnodes - 1) * dev->tnode_size]; + curr->internal[0] = allocator->free_tnodes; + allocator->free_tnodes = (struct yaffs_tnode *)mem; + + allocator->n_free_tnodes += n_tnodes; + allocator->n_tnodes_created += n_tnodes; + + /* Now add this bunch of tnodes to a list for freeing up. + * NB If we can't add this to the management list it isn't fatal + * but it just means we can't free this bunch of tnodes later. + */ + tnl = kmalloc(sizeof(struct yaffs_tnode_list), GFP_NOFS); + if (!tnl) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Could not add tnodes to management list"); + return YAFFS_FAIL; + } else { + tnl->tnodes = new_tnodes; + tnl->next = allocator->alloc_tnode_list; + allocator->alloc_tnode_list = tnl; + } + + yaffs_trace(YAFFS_TRACE_ALLOCATE, "Tnodes added"); + + return YAFFS_OK; +} + +struct yaffs_tnode *yaffs_alloc_raw_tnode(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator = + (struct yaffs_allocator *)dev->allocator; + struct yaffs_tnode *tn = NULL; + + if (!allocator) { + BUG(); + return NULL; + } + + /* If there are none left make more */ + if (!allocator->free_tnodes) + yaffs_create_tnodes(dev, YAFFS_ALLOCATION_NTNODES); + + if (allocator->free_tnodes) { + tn = allocator->free_tnodes; + allocator->free_tnodes = allocator->free_tnodes->internal[0]; + allocator->n_free_tnodes--; + } + + return tn; +} + +/* FreeTnode frees up a tnode and puts it back on the free list */ +void yaffs_free_raw_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn) +{ + struct yaffs_allocator *allocator = dev->allocator; + + if (!allocator) { + BUG(); + return; + } + + if (tn) { + tn->internal[0] = allocator->free_tnodes; + allocator->free_tnodes = tn; + allocator->n_free_tnodes++; + } + dev->checkpoint_blocks_required = 0; /* force recalculation */ +} + +/*--------------- yaffs_obj alloaction ------------------------ + * + * Free yaffs_objs are stored in a list using obj->siblings. + * The blocks of allocated objects are stored in a linked list. + */ + +static void yaffs_init_raw_objs(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator = dev->allocator; + + if (!allocator) { + BUG(); + return; + } + + allocator->allocated_obj_list = NULL; + INIT_LIST_HEAD(&allocator->free_objs); + allocator->n_free_objects = 0; +} + +static void yaffs_deinit_raw_objs(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator = dev->allocator; + struct yaffs_obj_list *tmp; + + if (!allocator) { + BUG(); + return; + } + + while (allocator->allocated_obj_list) { + tmp = allocator->allocated_obj_list->next; + kfree(allocator->allocated_obj_list->objects); + kfree(allocator->allocated_obj_list); + allocator->allocated_obj_list = tmp; + } + + INIT_LIST_HEAD(&allocator->free_objs); + allocator->n_free_objects = 0; + allocator->n_obj_created = 0; +} + +static int yaffs_create_free_objs(struct yaffs_dev *dev, int n_obj) +{ + struct yaffs_allocator *allocator = dev->allocator; + int i; + struct yaffs_obj *new_objs; + struct yaffs_obj_list *list; + + if (!allocator) { + BUG(); + return YAFFS_FAIL; + } + + if (n_obj < 1) + return YAFFS_OK; + + /* make these things */ + new_objs = kmalloc(n_obj * sizeof(struct yaffs_obj), GFP_NOFS); + list = kmalloc(sizeof(struct yaffs_obj_list), GFP_NOFS); + + if (!new_objs || !list) { + kfree(new_objs); + new_objs = NULL; + kfree(list); + list = NULL; + yaffs_trace(YAFFS_TRACE_ALLOCATE, + "Could not allocate more objects"); + return YAFFS_FAIL; + } + + /* Hook them into the free list */ + for (i = 0; i < n_obj; i++) + list_add(&new_objs[i].siblings, &allocator->free_objs); + + allocator->n_free_objects += n_obj; + allocator->n_obj_created += n_obj; + + /* Now add this bunch of Objects to a list for freeing up. */ + + list->objects = new_objs; + list->next = allocator->allocated_obj_list; + allocator->allocated_obj_list = list; + + return YAFFS_OK; +} + +struct yaffs_obj *yaffs_alloc_raw_obj(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj = NULL; + struct list_head *lh; + struct yaffs_allocator *allocator = dev->allocator; + + if (!allocator) { + BUG(); + return obj; + } + + /* If there are none left make more */ + if (list_empty(&allocator->free_objs)) + yaffs_create_free_objs(dev, YAFFS_ALLOCATION_NOBJECTS); + + if (!list_empty(&allocator->free_objs)) { + lh = allocator->free_objs.next; + obj = list_entry(lh, struct yaffs_obj, siblings); + list_del_init(lh); + allocator->n_free_objects--; + } + + return obj; +} + +void yaffs_free_raw_obj(struct yaffs_dev *dev, struct yaffs_obj *obj) +{ + + struct yaffs_allocator *allocator = dev->allocator; + + if (!allocator) { + BUG(); + return; + } + + /* Link into the free list. */ + list_add(&obj->siblings, &allocator->free_objs); + allocator->n_free_objects++; +} + +void yaffs_deinit_raw_tnodes_and_objs(struct yaffs_dev *dev) +{ + + if (!dev->allocator) { + BUG(); + return; + } + + yaffs_deinit_raw_tnodes(dev); + yaffs_deinit_raw_objs(dev); + kfree(dev->allocator); + dev->allocator = NULL; +} + +void yaffs_init_raw_tnodes_and_objs(struct yaffs_dev *dev) +{ + struct yaffs_allocator *allocator; + + if (dev->allocator) { + BUG(); + return; + } + + allocator = kmalloc(sizeof(struct yaffs_allocator), GFP_NOFS); + if (allocator) { + dev->allocator = allocator; + yaffs_init_raw_tnodes(dev); + yaffs_init_raw_objs(dev); + } +} + diff --git a/fs/yaffs2/yaffs_allocator.h b/fs/yaffs2/yaffs_allocator.h new file mode 100644 index 000000000000..0dacd9f75b5e --- /dev/null +++ b/fs/yaffs2/yaffs_allocator.h @@ -0,0 +1,29 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_ALLOCATOR_H__ +#define __YAFFS_ALLOCATOR_H__ + +#include "yaffs_guts.h" + +void yaffs_init_raw_tnodes_and_objs(struct yaffs_dev *dev); +void yaffs_deinit_raw_tnodes_and_objs(struct yaffs_dev *dev); + +struct yaffs_tnode *yaffs_alloc_raw_tnode(struct yaffs_dev *dev); +void yaffs_free_raw_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn); + +struct yaffs_obj *yaffs_alloc_raw_obj(struct yaffs_dev *dev); +void yaffs_free_raw_obj(struct yaffs_dev *dev, struct yaffs_obj *obj); + +#endif diff --git a/fs/yaffs2/yaffs_attribs.c b/fs/yaffs2/yaffs_attribs.c new file mode 100644 index 000000000000..a9ced27250aa --- /dev/null +++ b/fs/yaffs2/yaffs_attribs.c @@ -0,0 +1,135 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_guts.h" +#include "yaffs_attribs.h" + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 14, 0)) +#define IATTR_UID ia_uid +#define IATTR_GID ia_gid +#else +#define IATTR_UID ia_uid.val +#define IATTR_GID ia_gid.val +#endif + +/* + * Loading attibs from/to object header assumes the object header + * is in cpu endian. + */ +void yaffs_load_attribs(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh) +{ + obj->yst_uid = oh->yst_uid; + obj->yst_gid = oh->yst_gid; + obj->yst_atime = oh->yst_atime; + obj->yst_mtime = oh->yst_mtime; + obj->yst_ctime = oh->yst_ctime; + obj->yst_rdev = oh->yst_rdev; +} + +void yaffs_load_attribs_oh(struct yaffs_obj_hdr *oh, struct yaffs_obj *obj) +{ + oh->yst_uid = obj->yst_uid; + oh->yst_gid = obj->yst_gid; + oh->yst_atime = obj->yst_atime; + oh->yst_mtime = obj->yst_mtime; + oh->yst_ctime = obj->yst_ctime; + oh->yst_rdev = obj->yst_rdev; + +} + +void yaffs_load_current_time(struct yaffs_obj *obj, int do_a, int do_c) +{ + obj->yst_mtime = Y_CURRENT_TIME; + if (do_a) + obj->yst_atime = obj->yst_mtime; + if (do_c) + obj->yst_ctime = obj->yst_mtime; +} + +void yaffs_attribs_init(struct yaffs_obj *obj, u32 gid, u32 uid, u32 rdev) +{ + yaffs_load_current_time(obj, 1, 1); + obj->yst_rdev = rdev; + obj->yst_uid = uid; + obj->yst_gid = gid; +} + +static loff_t yaffs_get_file_size(struct yaffs_obj *obj) +{ + YCHAR *alias = NULL; + obj = yaffs_get_equivalent_obj(obj); + + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + return obj->variant.file_variant.file_size; + case YAFFS_OBJECT_TYPE_SYMLINK: + alias = obj->variant.symlink_variant.alias; + if (!alias) + return 0; + return strnlen(alias, YAFFS_MAX_ALIAS_LENGTH); + default: + return 0; + } +} + +int yaffs_set_attribs(struct yaffs_obj *obj, struct iattr *attr) +{ + unsigned int valid = attr->ia_valid; + + if (valid & ATTR_MODE) + obj->yst_mode = attr->ia_mode; + if (valid & ATTR_UID) + obj->yst_uid = attr->IATTR_UID; + if (valid & ATTR_GID) + obj->yst_gid = attr->IATTR_GID; + + if (valid & ATTR_ATIME) + obj->yst_atime = Y_TIME_CONVERT(attr->ia_atime); + if (valid & ATTR_CTIME) + obj->yst_ctime = Y_TIME_CONVERT(attr->ia_ctime); + if (valid & ATTR_MTIME) + obj->yst_mtime = Y_TIME_CONVERT(attr->ia_mtime); + + if (valid & ATTR_SIZE) + yaffs_resize_file(obj, attr->ia_size); + + yaffs_update_oh(obj, NULL, 1, 0, 0, NULL); + + return YAFFS_OK; + +} + +int yaffs_get_attribs(struct yaffs_obj *obj, struct iattr *attr) +{ + unsigned int valid = 0; + + attr->ia_mode = obj->yst_mode; + valid |= ATTR_MODE; + attr->IATTR_UID = obj->yst_uid; + valid |= ATTR_UID; + attr->IATTR_GID = obj->yst_gid; + valid |= ATTR_GID; + + Y_TIME_CONVERT(attr->ia_atime) = obj->yst_atime; + valid |= ATTR_ATIME; + Y_TIME_CONVERT(attr->ia_ctime) = obj->yst_ctime; + valid |= ATTR_CTIME; + Y_TIME_CONVERT(attr->ia_mtime) = obj->yst_mtime; + valid |= ATTR_MTIME; + + attr->ia_size = yaffs_get_file_size(obj); + valid |= ATTR_SIZE; + + attr->ia_valid = valid; + + return YAFFS_OK; +} diff --git a/fs/yaffs2/yaffs_attribs.h b/fs/yaffs2/yaffs_attribs.h new file mode 100644 index 000000000000..4ce6550c3d9c --- /dev/null +++ b/fs/yaffs2/yaffs_attribs.h @@ -0,0 +1,27 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_ATTRIBS_H__ +#define __YAFFS_ATTRIBS_H__ + +#include "yaffs_guts.h" + +void yaffs_load_attribs(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh); +void yaffs_load_attribs_oh(struct yaffs_obj_hdr *oh, struct yaffs_obj *obj); +void yaffs_attribs_init(struct yaffs_obj *obj, u32 gid, u32 uid, u32 rdev); +void yaffs_load_current_time(struct yaffs_obj *obj, int do_a, int do_c); +int yaffs_set_attribs(struct yaffs_obj *obj, struct iattr *attr); +int yaffs_get_attribs(struct yaffs_obj *obj, struct iattr *attr); + +#endif diff --git a/fs/yaffs2/yaffs_bitmap.c b/fs/yaffs2/yaffs_bitmap.c new file mode 100644 index 000000000000..481558041ddf --- /dev/null +++ b/fs/yaffs2/yaffs_bitmap.c @@ -0,0 +1,98 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_bitmap.h" +#include "yaffs_trace.h" +/* + * Chunk bitmap manipulations + */ + +static inline u8 *yaffs_block_bits(struct yaffs_dev *dev, int blk) +{ + if (blk < (int)dev->internal_start_block || + blk > (int)dev->internal_end_block) { + yaffs_trace(YAFFS_TRACE_ERROR, + "BlockBits block %d is not valid", + blk); + BUG(); + } + return dev->chunk_bits + + (dev->chunk_bit_stride * (blk - dev->internal_start_block)); +} + +void yaffs_verify_chunk_bit_id(struct yaffs_dev *dev, int blk, int chunk) +{ + if (blk < (int)dev->internal_start_block || + blk > (int)dev->internal_end_block || + chunk < 0 || chunk >= (int)dev->param.chunks_per_block) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Chunk Id (%d:%d) invalid", + blk, chunk); + BUG(); + } +} + +void yaffs_clear_chunk_bits(struct yaffs_dev *dev, int blk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + + memset(blk_bits, 0, dev->chunk_bit_stride); +} + +void yaffs_clear_chunk_bit(struct yaffs_dev *dev, int blk, int chunk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + + yaffs_verify_chunk_bit_id(dev, blk, chunk); + blk_bits[chunk / 8] &= ~(1 << (chunk & 7)); +} + +void yaffs_set_chunk_bit(struct yaffs_dev *dev, int blk, int chunk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + + yaffs_verify_chunk_bit_id(dev, blk, chunk); + blk_bits[chunk / 8] |= (1 << (chunk & 7)); +} + +int yaffs_check_chunk_bit(struct yaffs_dev *dev, int blk, int chunk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + + yaffs_verify_chunk_bit_id(dev, blk, chunk); + return (blk_bits[chunk / 8] & (1 << (chunk & 7))) ? 1 : 0; +} + +int yaffs_still_some_chunks(struct yaffs_dev *dev, int blk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + int i; + + for (i = 0; i < dev->chunk_bit_stride; i++) { + if (*blk_bits) + return 1; + blk_bits++; + } + return 0; +} + +int yaffs_count_chunk_bits(struct yaffs_dev *dev, int blk) +{ + u8 *blk_bits = yaffs_block_bits(dev, blk); + int i; + int n = 0; + + for (i = 0; i < dev->chunk_bit_stride; i++, blk_bits++) + n += hweight8(*blk_bits); + + return n; +} diff --git a/fs/yaffs2/yaffs_bitmap.h b/fs/yaffs2/yaffs_bitmap.h new file mode 100644 index 000000000000..30bbd3bbb1e0 --- /dev/null +++ b/fs/yaffs2/yaffs_bitmap.h @@ -0,0 +1,32 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +/* + * Chunk bitmap manipulations + */ + +#ifndef __YAFFS_BITMAP_H__ +#define __YAFFS_BITMAP_H__ + +#include "yaffs_guts.h" + +void yaffs_verify_chunk_bit_id(struct yaffs_dev *dev, int blk, int chunk); +void yaffs_clear_chunk_bits(struct yaffs_dev *dev, int blk); +void yaffs_clear_chunk_bit(struct yaffs_dev *dev, int blk, int chunk); +void yaffs_set_chunk_bit(struct yaffs_dev *dev, int blk, int chunk); +int yaffs_check_chunk_bit(struct yaffs_dev *dev, int blk, int chunk); +int yaffs_still_some_chunks(struct yaffs_dev *dev, int blk); +int yaffs_count_chunk_bits(struct yaffs_dev *dev, int blk); + +#endif diff --git a/fs/yaffs2/yaffs_checkptrw.c b/fs/yaffs2/yaffs_checkptrw.c new file mode 100644 index 000000000000..53688b5c34d9 --- /dev/null +++ b/fs/yaffs2/yaffs_checkptrw.c @@ -0,0 +1,480 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_checkptrw.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_endian.h" + +struct yaffs_checkpt_chunk_hdr { + int version; + int seq; + u32 sum; + u32 xor; +} ; + + +static int apply_chunk_offset(struct yaffs_dev *dev, int chunk) +{ + return chunk - dev->chunk_offset; +} + +static int apply_block_offset(struct yaffs_dev *dev, int block) +{ + return block - dev->block_offset; +} + + +static void yaffs2_do_endian_hdr(struct yaffs_dev *dev, + struct yaffs_checkpt_chunk_hdr *hdr) +{ + if (!dev->swap_endian) + return; + hdr->version = swap_s32(hdr->version); + hdr->seq = swap_s32(hdr->seq); + hdr->sum = swap_u32(hdr->sum); + hdr->xor = swap_u32(hdr->xor); +} + +static void yaffs2_checkpt_init_chunk_hdr(struct yaffs_dev *dev) +{ + struct yaffs_checkpt_chunk_hdr hdr; + + hdr.version = YAFFS_CHECKPOINT_VERSION; + hdr.seq = dev->checkpt_page_seq; + hdr.sum = dev->checkpt_sum; + hdr.xor = dev->checkpt_xor; + + dev->checkpt_byte_offs = sizeof(hdr); + + yaffs2_do_endian_hdr(dev, &hdr); + memcpy(dev->checkpt_buffer, &hdr, sizeof(hdr)); +} + +static int yaffs2_checkpt_check_chunk_hdr(struct yaffs_dev *dev) +{ + struct yaffs_checkpt_chunk_hdr hdr; + + memcpy(&hdr, dev->checkpt_buffer, sizeof(hdr)); + yaffs2_do_endian_hdr(dev, &hdr); + + dev->checkpt_byte_offs = sizeof(hdr); + + return hdr.version == YAFFS_CHECKPOINT_VERSION && + hdr.seq == dev->checkpt_page_seq && + hdr.sum == dev->checkpt_sum && + hdr.xor == dev->checkpt_xor; +} + +static int yaffs2_checkpt_space_ok(struct yaffs_dev *dev) +{ + int blocks_avail = dev->n_erased_blocks - dev->param.n_reserved_blocks; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "checkpt blocks_avail = %d", blocks_avail); + + return (blocks_avail <= 0) ? 0 : 1; +} + +static int yaffs_checkpt_erase(struct yaffs_dev *dev) +{ + u32 i; + + if (!dev->drv.drv_erase_fn) + return 0; + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "checking blocks %d to %d", + dev->internal_start_block, dev->internal_end_block); + + for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + struct yaffs_block_info *bi = yaffs_get_block_info(dev, i); + int offset_i = apply_block_offset(dev, i); + int result; + + if (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "erasing checkpt block %d", i); + + dev->n_erasures++; + + result = dev->drv.drv_erase_fn(dev, offset_i); + if(result) { + bi->block_state = YAFFS_BLOCK_STATE_EMPTY; + dev->n_erased_blocks++; + dev->n_free_chunks += + dev->param.chunks_per_block; + } else { + dev->drv.drv_mark_bad_fn(dev, offset_i); + bi->block_state = YAFFS_BLOCK_STATE_DEAD; + } + } + } + + dev->blocks_in_checkpt = 0; + + return 1; +} + +static void yaffs2_checkpt_find_erased_block(struct yaffs_dev *dev) +{ + u32 i; + int blocks_avail = dev->n_erased_blocks - dev->param.n_reserved_blocks; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "allocating checkpt block: erased %d reserved %d avail %d next %d ", + dev->n_erased_blocks, dev->param.n_reserved_blocks, + blocks_avail, dev->checkpt_next_block); + + if (dev->checkpt_next_block >= 0 && + dev->checkpt_next_block <= (int)dev->internal_end_block && + blocks_avail > 0) { + + for (i = dev->checkpt_next_block; i <= dev->internal_end_block; + i++) { + struct yaffs_block_info *bi; + + bi = yaffs_get_block_info(dev, i); + if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) { + dev->checkpt_next_block = i + 1; + dev->checkpt_cur_block = i; + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "allocating checkpt block %d", i); + return; + } + } + } + yaffs_trace(YAFFS_TRACE_CHECKPOINT, "out of checkpt blocks"); + + dev->checkpt_next_block = -1; + dev->checkpt_cur_block = -1; +} + +static void yaffs2_checkpt_find_block(struct yaffs_dev *dev) +{ + u32 i; + struct yaffs_ext_tags tags; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "find next checkpt block: start: blocks %d next %d", + dev->blocks_in_checkpt, dev->checkpt_next_block); + + if (dev->blocks_in_checkpt < dev->checkpt_max_blocks) + for (i = dev->checkpt_next_block; i <= dev->internal_end_block; + i++) { + int chunk = i * dev->param.chunks_per_block; + enum yaffs_block_state state; + u32 seq; + + dev->tagger.read_chunk_tags_fn(dev, + apply_chunk_offset(dev, chunk), + NULL, &tags); + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "find next checkpt block: search: block %d state %d oid %d seq %d eccr %d", + i, (int) state, + tags.obj_id, tags.seq_number, + tags.ecc_result); + + if (tags.seq_number != YAFFS_SEQUENCE_CHECKPOINT_DATA) + continue; + + dev->tagger.query_block_fn(dev, + apply_block_offset(dev, i), + &state, &seq); + if (state == YAFFS_BLOCK_STATE_DEAD) + continue; + + /* Right kind of block */ + dev->checkpt_next_block = tags.obj_id; + dev->checkpt_cur_block = i; + dev->checkpt_block_list[dev->blocks_in_checkpt] = i; + dev->blocks_in_checkpt++; + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "found checkpt block %d", i); + return; + } + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, "found no more checkpt blocks"); + + dev->checkpt_next_block = -1; + dev->checkpt_cur_block = -1; +} + +int yaffs2_checkpt_open(struct yaffs_dev *dev, int writing) +{ + u32 i; + + dev->checkpt_open_write = writing; + + /* Got the functions we need? */ + if (!dev->tagger.write_chunk_tags_fn || + !dev->tagger.read_chunk_tags_fn || + !dev->drv.drv_erase_fn || + !dev->drv.drv_mark_bad_fn) + return 0; + + if (writing && !yaffs2_checkpt_space_ok(dev)) + return 0; + + if (!dev->checkpt_buffer) + dev->checkpt_buffer = + kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS); + if (!dev->checkpt_buffer) + return 0; + + dev->checkpt_page_seq = 0; + dev->checkpt_byte_count = 0; + dev->checkpt_sum = 0; + dev->checkpt_xor = 0; + dev->checkpt_cur_block = -1; + dev->checkpt_cur_chunk = -1; + dev->checkpt_next_block = dev->internal_start_block; + + if (writing) { + memset(dev->checkpt_buffer, 0, dev->data_bytes_per_chunk); + yaffs2_checkpt_init_chunk_hdr(dev); + return yaffs_checkpt_erase(dev); + } + + /* Opening for a read */ + /* Set to a value that will kick off a read */ + dev->checkpt_byte_offs = dev->data_bytes_per_chunk; + /* A checkpoint block list of 1 checkpoint block per 16 block is + * (hopefully) going to be way more than we need */ + dev->blocks_in_checkpt = 0; + dev->checkpt_max_blocks = + (dev->internal_end_block - dev->internal_start_block) / 16 + 2; + if (!dev->checkpt_block_list) + dev->checkpt_block_list = + kmalloc(sizeof(int) * dev->checkpt_max_blocks, GFP_NOFS); + + if (!dev->checkpt_block_list) + return 0; + + for (i = 0; i < dev->checkpt_max_blocks; i++) + dev->checkpt_block_list[i] = -1; + + return 1; +} + +int yaffs2_get_checkpt_sum(struct yaffs_dev *dev, u32 * sum) +{ + u32 composite_sum; + + composite_sum = (dev->checkpt_sum << 8) | (dev->checkpt_xor & 0xff); + *sum = composite_sum; + return 1; +} + +static int yaffs2_checkpt_flush_buffer(struct yaffs_dev *dev) +{ + int chunk; + int offset_chunk; + struct yaffs_ext_tags tags; + + if (dev->checkpt_cur_block < 0) { + yaffs2_checkpt_find_erased_block(dev); + dev->checkpt_cur_chunk = 0; + } + + if (dev->checkpt_cur_block < 0) + return 0; + + tags.is_deleted = 0; + tags.obj_id = dev->checkpt_next_block; /* Hint to next place to look */ + tags.chunk_id = dev->checkpt_page_seq + 1; + tags.seq_number = YAFFS_SEQUENCE_CHECKPOINT_DATA; + tags.n_bytes = dev->data_bytes_per_chunk; + if (dev->checkpt_cur_chunk == 0) { + /* First chunk we write for the block? Set block state to + checkpoint */ + struct yaffs_block_info *bi = + yaffs_get_block_info(dev, dev->checkpt_cur_block); + bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT; + dev->blocks_in_checkpt++; + } + + chunk = + dev->checkpt_cur_block * dev->param.chunks_per_block + + dev->checkpt_cur_chunk; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "checkpoint wite buffer nand %d(%d:%d) objid %d chId %d", + chunk, dev->checkpt_cur_block, dev->checkpt_cur_chunk, + tags.obj_id, tags.chunk_id); + + offset_chunk = apply_chunk_offset(dev, chunk); + + dev->n_page_writes++; + + dev->tagger.write_chunk_tags_fn(dev, offset_chunk, + dev->checkpt_buffer, &tags); + dev->checkpt_page_seq++; + dev->checkpt_cur_chunk++; + if (dev->checkpt_cur_chunk >= (int)dev->param.chunks_per_block) { + dev->checkpt_cur_chunk = 0; + dev->checkpt_cur_block = -1; + } + memset(dev->checkpt_buffer, 0, dev->data_bytes_per_chunk); + + yaffs2_checkpt_init_chunk_hdr(dev); + + + return 1; +} + +int yaffs2_checkpt_wr(struct yaffs_dev *dev, const void *data, int n_bytes) +{ + int i = 0; + int ok = 1; + u8 *data_bytes = (u8 *) data; + + if (!dev->checkpt_buffer) + return 0; + + if (!dev->checkpt_open_write) + return -1; + + while (i < n_bytes && ok) { + dev->checkpt_buffer[dev->checkpt_byte_offs] = *data_bytes; + dev->checkpt_sum += *data_bytes; + dev->checkpt_xor ^= *data_bytes; + + dev->checkpt_byte_offs++; + i++; + data_bytes++; + dev->checkpt_byte_count++; + + if (dev->checkpt_byte_offs < 0 || + dev->checkpt_byte_offs >= (int)dev->data_bytes_per_chunk) + ok = yaffs2_checkpt_flush_buffer(dev); + } + + return i; +} + +int yaffs2_checkpt_rd(struct yaffs_dev *dev, void *data, int n_bytes) +{ + int i = 0; + struct yaffs_ext_tags tags; + int chunk; + int offset_chunk; + u8 *data_bytes = (u8 *) data; + + if (!dev->checkpt_buffer) + return 0; + + if (dev->checkpt_open_write) + return -1; + + while (i < n_bytes) { + + if (dev->checkpt_byte_offs < 0 || + dev->checkpt_byte_offs >= (int)dev->data_bytes_per_chunk) { + + if (dev->checkpt_cur_block < 0) { + yaffs2_checkpt_find_block(dev); + dev->checkpt_cur_chunk = 0; + } + + /* Bail out if we can't find a checpoint block */ + if (dev->checkpt_cur_block < 0) + break; + + chunk = dev->checkpt_cur_block * + dev->param.chunks_per_block + + dev->checkpt_cur_chunk; + + offset_chunk = apply_chunk_offset(dev, chunk); + dev->n_page_reads++; + + /* Read in the next chunk */ + dev->tagger.read_chunk_tags_fn(dev, + offset_chunk, + dev->checkpt_buffer, + &tags); + + /* Bail out if the chunk is corrupted. */ + if (tags.chunk_id != (u32)(dev->checkpt_page_seq + 1) || + tags.ecc_result > YAFFS_ECC_RESULT_FIXED || + tags.seq_number != YAFFS_SEQUENCE_CHECKPOINT_DATA) + break; + + /* Bail out if it is not a checkpoint chunk. */ + if(!yaffs2_checkpt_check_chunk_hdr(dev)) + break; + + dev->checkpt_page_seq++; + dev->checkpt_cur_chunk++; + + if (dev->checkpt_cur_chunk >= + (int)dev->param.chunks_per_block) + dev->checkpt_cur_block = -1; + + } + + *data_bytes = dev->checkpt_buffer[dev->checkpt_byte_offs]; + dev->checkpt_sum += *data_bytes; + dev->checkpt_xor ^= *data_bytes; + dev->checkpt_byte_offs++; + i++; + data_bytes++; + dev->checkpt_byte_count++; + } + + return i; /* Number of bytes read */ +} + +int yaffs_checkpt_close(struct yaffs_dev *dev) +{ + u32 i; + + if (dev->checkpt_open_write) { + if (dev->checkpt_byte_offs != + sizeof(sizeof(struct yaffs_checkpt_chunk_hdr))) + yaffs2_checkpt_flush_buffer(dev); + } else if (dev->checkpt_block_list) { + for (i = 0; + i < dev->blocks_in_checkpt && + dev->checkpt_block_list[i] >= 0; i++) { + int blk = dev->checkpt_block_list[i]; + struct yaffs_block_info *bi = NULL; + + if ((int)dev->internal_start_block <= blk && + blk <= (int)dev->internal_end_block) + bi = yaffs_get_block_info(dev, blk); + if (bi && bi->block_state == YAFFS_BLOCK_STATE_EMPTY) + bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT; + } + } + + dev->n_free_chunks -= + dev->blocks_in_checkpt * dev->param.chunks_per_block; + dev->n_erased_blocks -= dev->blocks_in_checkpt; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, "checkpoint byte count %d", + dev->checkpt_byte_count); + + if (dev->checkpt_buffer) + return 1; + else + return 0; +} + +int yaffs2_checkpt_invalidate_stream(struct yaffs_dev *dev) +{ + /* Erase the checkpoint data */ + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "checkpoint invalidate of %d blocks", + dev->blocks_in_checkpt); + + return yaffs_checkpt_erase(dev); +} diff --git a/fs/yaffs2/yaffs_checkptrw.h b/fs/yaffs2/yaffs_checkptrw.h new file mode 100644 index 000000000000..4820fb09519c --- /dev/null +++ b/fs/yaffs2/yaffs_checkptrw.h @@ -0,0 +1,32 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_CHECKPTRW_H__ +#define __YAFFS_CHECKPTRW_H__ + +#include "yaffs_guts.h" + +int yaffs2_checkpt_open(struct yaffs_dev *dev, int writing); + +int yaffs2_checkpt_wr(struct yaffs_dev *dev, const void *data, int n_bytes); + +int yaffs2_checkpt_rd(struct yaffs_dev *dev, void *data, int n_bytes); + +int yaffs2_get_checkpt_sum(struct yaffs_dev *dev, u32 * sum); + +int yaffs_checkpt_close(struct yaffs_dev *dev); + +int yaffs2_checkpt_invalidate_stream(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_ecc.c b/fs/yaffs2/yaffs_ecc.c new file mode 100644 index 000000000000..911f8f79a064 --- /dev/null +++ b/fs/yaffs2/yaffs_ecc.c @@ -0,0 +1,280 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * This code implements the ECC algorithm used in SmartMedia. + * + * The ECC comprises 22 bits of parity information and is stuffed into 3 bytes. + * The two unused bit are set to 1. + * The ECC can correct single bit errors in a 256-byte page of data. Thus, two + * such ECC blocks are used on a 512-byte NAND page. + * + */ + +#include "yportenv.h" + +#include "yaffs_ecc.h" + +/* Table generated by gen-ecc.c + * Using a table means we do not have to calculate p1..p4 and p1'..p4' + * for each byte of data. These are instead provided in a table in bits7..2. + * Bit 0 of each entry indicates whether the entry has an odd or even parity, + * and therefore this bytes influence on the line parity. + */ + +static const unsigned char column_parity_table[] = { + 0x00, 0x55, 0x59, 0x0c, 0x65, 0x30, 0x3c, 0x69, + 0x69, 0x3c, 0x30, 0x65, 0x0c, 0x59, 0x55, 0x00, + 0x95, 0xc0, 0xcc, 0x99, 0xf0, 0xa5, 0xa9, 0xfc, + 0xfc, 0xa9, 0xa5, 0xf0, 0x99, 0xcc, 0xc0, 0x95, + 0x99, 0xcc, 0xc0, 0x95, 0xfc, 0xa9, 0xa5, 0xf0, + 0xf0, 0xa5, 0xa9, 0xfc, 0x95, 0xc0, 0xcc, 0x99, + 0x0c, 0x59, 0x55, 0x00, 0x69, 0x3c, 0x30, 0x65, + 0x65, 0x30, 0x3c, 0x69, 0x00, 0x55, 0x59, 0x0c, + 0xa5, 0xf0, 0xfc, 0xa9, 0xc0, 0x95, 0x99, 0xcc, + 0xcc, 0x99, 0x95, 0xc0, 0xa9, 0xfc, 0xf0, 0xa5, + 0x30, 0x65, 0x69, 0x3c, 0x55, 0x00, 0x0c, 0x59, + 0x59, 0x0c, 0x00, 0x55, 0x3c, 0x69, 0x65, 0x30, + 0x3c, 0x69, 0x65, 0x30, 0x59, 0x0c, 0x00, 0x55, + 0x55, 0x00, 0x0c, 0x59, 0x30, 0x65, 0x69, 0x3c, + 0xa9, 0xfc, 0xf0, 0xa5, 0xcc, 0x99, 0x95, 0xc0, + 0xc0, 0x95, 0x99, 0xcc, 0xa5, 0xf0, 0xfc, 0xa9, + 0xa9, 0xfc, 0xf0, 0xa5, 0xcc, 0x99, 0x95, 0xc0, + 0xc0, 0x95, 0x99, 0xcc, 0xa5, 0xf0, 0xfc, 0xa9, + 0x3c, 0x69, 0x65, 0x30, 0x59, 0x0c, 0x00, 0x55, + 0x55, 0x00, 0x0c, 0x59, 0x30, 0x65, 0x69, 0x3c, + 0x30, 0x65, 0x69, 0x3c, 0x55, 0x00, 0x0c, 0x59, + 0x59, 0x0c, 0x00, 0x55, 0x3c, 0x69, 0x65, 0x30, + 0xa5, 0xf0, 0xfc, 0xa9, 0xc0, 0x95, 0x99, 0xcc, + 0xcc, 0x99, 0x95, 0xc0, 0xa9, 0xfc, 0xf0, 0xa5, + 0x0c, 0x59, 0x55, 0x00, 0x69, 0x3c, 0x30, 0x65, + 0x65, 0x30, 0x3c, 0x69, 0x00, 0x55, 0x59, 0x0c, + 0x99, 0xcc, 0xc0, 0x95, 0xfc, 0xa9, 0xa5, 0xf0, + 0xf0, 0xa5, 0xa9, 0xfc, 0x95, 0xc0, 0xcc, 0x99, + 0x95, 0xc0, 0xcc, 0x99, 0xf0, 0xa5, 0xa9, 0xfc, + 0xfc, 0xa9, 0xa5, 0xf0, 0x99, 0xcc, 0xc0, 0x95, + 0x00, 0x55, 0x59, 0x0c, 0x65, 0x30, 0x3c, 0x69, + 0x69, 0x3c, 0x30, 0x65, 0x0c, 0x59, 0x55, 0x00, +}; + + +/* Calculate the ECC for a 256-byte block of data */ +void yaffs_ecc_calc(const unsigned char *data, unsigned char *ecc) +{ + unsigned int i; + unsigned char col_parity = 0; + unsigned char line_parity = 0; + unsigned char line_parity_prime = 0; + unsigned char t; + unsigned char b; + + for (i = 0; i < 256; i++) { + b = column_parity_table[*data++]; + col_parity ^= b; + + if (b & 0x01) { /* odd number of bits in the byte */ + line_parity ^= i; + line_parity_prime ^= ~i; + } + } + + ecc[2] = (~col_parity) | 0x03; + + t = 0; + if (line_parity & 0x80) + t |= 0x80; + if (line_parity_prime & 0x80) + t |= 0x40; + if (line_parity & 0x40) + t |= 0x20; + if (line_parity_prime & 0x40) + t |= 0x10; + if (line_parity & 0x20) + t |= 0x08; + if (line_parity_prime & 0x20) + t |= 0x04; + if (line_parity & 0x10) + t |= 0x02; + if (line_parity_prime & 0x10) + t |= 0x01; + ecc[1] = ~t; + + t = 0; + if (line_parity & 0x08) + t |= 0x80; + if (line_parity_prime & 0x08) + t |= 0x40; + if (line_parity & 0x04) + t |= 0x20; + if (line_parity_prime & 0x04) + t |= 0x10; + if (line_parity & 0x02) + t |= 0x08; + if (line_parity_prime & 0x02) + t |= 0x04; + if (line_parity & 0x01) + t |= 0x02; + if (line_parity_prime & 0x01) + t |= 0x01; + ecc[0] = ~t; + +} + +/* Correct the ECC on a 256 byte block of data */ + +int yaffs_ecc_correct(unsigned char *data, unsigned char *read_ecc, + const unsigned char *test_ecc) +{ + unsigned char d0, d1, d2; /* deltas */ + + d0 = read_ecc[0] ^ test_ecc[0]; + d1 = read_ecc[1] ^ test_ecc[1]; + d2 = read_ecc[2] ^ test_ecc[2]; + + if ((d0 | d1 | d2) == 0) + return 0; /* no error */ + + if (((d0 ^ (d0 >> 1)) & 0x55) == 0x55 && + ((d1 ^ (d1 >> 1)) & 0x55) == 0x55 && + ((d2 ^ (d2 >> 1)) & 0x54) == 0x54) { + /* Single bit (recoverable) error in data */ + + unsigned byte; + unsigned bit; + + bit = byte = 0; + + if (d1 & 0x80) + byte |= 0x80; + if (d1 & 0x20) + byte |= 0x40; + if (d1 & 0x08) + byte |= 0x20; + if (d1 & 0x02) + byte |= 0x10; + if (d0 & 0x80) + byte |= 0x08; + if (d0 & 0x20) + byte |= 0x04; + if (d0 & 0x08) + byte |= 0x02; + if (d0 & 0x02) + byte |= 0x01; + + if (d2 & 0x80) + bit |= 0x04; + if (d2 & 0x20) + bit |= 0x02; + if (d2 & 0x08) + bit |= 0x01; + + data[byte] ^= (1 << bit); + + return 1; /* Corrected the error */ + } + + if ((hweight8(d0) + hweight8(d1) + hweight8(d2)) == 1) { + /* Reccoverable error in ecc */ + + read_ecc[0] = test_ecc[0]; + read_ecc[1] = test_ecc[1]; + read_ecc[2] = test_ecc[2]; + + return 1; /* Corrected the error */ + } + + /* Unrecoverable error */ + + return -1; + +} + +/* + * ECCxxxOther does ECC calcs on arbitrary n bytes of data + */ +void yaffs_ecc_calc_other(const unsigned char *data, unsigned n_bytes, + struct yaffs_ecc_other *ecc_other) +{ + unsigned int i; + unsigned char col_parity = 0; + unsigned line_parity = 0; + unsigned line_parity_prime = 0; + unsigned char b; + + for (i = 0; i < n_bytes; i++) { + b = column_parity_table[*data++]; + col_parity ^= b; + + if (b & 0x01) { + /* odd number of bits in the byte */ + line_parity ^= i; + line_parity_prime ^= ~i; + } + + } + + ecc_other->col_parity = (col_parity >> 2) & 0x3f; + ecc_other->line_parity = line_parity; + ecc_other->line_parity_prime = line_parity_prime; +} + +int yaffs_ecc_correct_other(unsigned char *data, unsigned n_bytes, + struct yaffs_ecc_other *read_ecc, + const struct yaffs_ecc_other *test_ecc) +{ + unsigned char delta_col; /* column parity delta */ + unsigned delta_line; /* line parity delta */ + unsigned delta_line_prime; /* line parity delta */ + unsigned bit; + + delta_col = read_ecc->col_parity ^ test_ecc->col_parity; + delta_line = read_ecc->line_parity ^ test_ecc->line_parity; + delta_line_prime = + read_ecc->line_parity_prime ^ test_ecc->line_parity_prime; + + if ((delta_col | delta_line | delta_line_prime) == 0) + return 0; /* no error */ + + if (delta_line == ~delta_line_prime && + (((delta_col ^ (delta_col >> 1)) & 0x15) == 0x15)) { + /* Single bit (recoverable) error in data */ + + bit = 0; + + if (delta_col & 0x20) + bit |= 0x04; + if (delta_col & 0x08) + bit |= 0x02; + if (delta_col & 0x02) + bit |= 0x01; + + if (delta_line >= n_bytes) + return -1; + + data[delta_line] ^= (1 << bit); + + return 1; /* corrected */ + } + + if ((hweight32(delta_line) + + hweight32(delta_line_prime) + + hweight8(delta_col)) == 1) { + /* Reccoverable error in ecc */ + + *read_ecc = *test_ecc; + return 1; /* corrected */ + } + + /* Unrecoverable error */ + + return -1; +} diff --git a/fs/yaffs2/yaffs_ecc.h b/fs/yaffs2/yaffs_ecc.h new file mode 100644 index 000000000000..1dc64416895b --- /dev/null +++ b/fs/yaffs2/yaffs_ecc.h @@ -0,0 +1,43 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +/* + * This code implements the ECC algorithm used in SmartMedia. + * + * The ECC comprises 22 bits of parity information and is stuffed into 3 bytes. + * The two unused bit are set to 1. + * The ECC can correct single bit errors in a 256-byte page of data. + * Thus, two such ECC blocks are used on a 512-byte NAND page. + * + */ + +#ifndef __YAFFS_ECC_H__ +#define __YAFFS_ECC_H__ + +struct yaffs_ecc_other { + unsigned char col_parity; + unsigned line_parity; + unsigned line_parity_prime; +}; + +void yaffs_ecc_calc(const unsigned char *data, unsigned char *ecc); +int yaffs_ecc_correct(unsigned char *data, unsigned char *read_ecc, + const unsigned char *test_ecc); + +void yaffs_ecc_calc_other(const unsigned char *data, unsigned n_bytes, + struct yaffs_ecc_other *ecc); +int yaffs_ecc_correct_other(unsigned char *data, unsigned n_bytes, + struct yaffs_ecc_other *read_ecc, + const struct yaffs_ecc_other *test_ecc); +#endif diff --git a/fs/yaffs2/yaffs_endian.c b/fs/yaffs2/yaffs_endian.c new file mode 100644 index 000000000000..6103f4ebb0c2 --- /dev/null +++ b/fs/yaffs2/yaffs_endian.c @@ -0,0 +1,105 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Endian processing functions. + */ + +#include "yaffs_endian.h" +#include "yaffs_guts.h" + + +void yaffs_do_endian_u32(struct yaffs_dev *dev, u32 *val) +{ + if (!dev->swap_endian) + return; + *val = swap_u32(*val); +} + +void yaffs_do_endian_s32(struct yaffs_dev *dev, s32 *val) +{ + if (!dev->swap_endian) + return; + *val = swap_s32(*val); +} + +void yaffs_do_endian_oh(struct yaffs_dev *dev, struct yaffs_obj_hdr *oh) +{ + if (!dev->swap_endian) + return; + /* Change every field */ + oh->type = swap_u32(oh->type); + oh->parent_obj_id = swap_u32(oh->parent_obj_id); + + oh->yst_mode = swap_u32(oh->yst_mode); + + oh->yst_uid = swap_u32(oh->yst_uid); + oh->yst_gid = swap_u32(oh->yst_gid); + oh->yst_atime = swap_u32(oh->yst_atime); + oh->yst_mtime = swap_u32(oh->yst_mtime); + oh->yst_ctime = swap_u32(oh->yst_ctime); + + oh->file_size_low = swap_u32(oh->file_size_low); + + oh->equiv_id = swap_u32(oh->equiv_id); + + oh->yst_rdev = swap_u32(oh->yst_rdev); + + oh->win_ctime[0] = swap_u32(oh->win_ctime[0]); + oh->win_ctime[1] = swap_u32(oh->win_ctime[1]); + oh->win_atime[0] = swap_u32(oh->win_atime[0]); + oh->win_atime[1] = swap_u32(oh->win_atime[1]); + oh->win_mtime[0] = swap_u32(oh->win_mtime[0]); + oh->win_mtime[1] = swap_u32(oh->win_mtime[1]); + + oh->inband_shadowed_obj_id = swap_u32(oh->inband_shadowed_obj_id); + oh->inband_is_shrink = swap_u32(oh->inband_is_shrink); + + oh->file_size_high = swap_u32(oh->file_size_high); + oh->reserved[0] = swap_u32(oh->reserved[0]); + oh->shadows_obj = swap_s32(oh->shadows_obj); + + oh->is_shrink = swap_u32(oh->is_shrink); +} + + +void yaffs_do_endian_packed_tags2(struct yaffs_dev *dev, + struct yaffs_packed_tags2_tags_only *ptt) +{ + if (!dev->swap_endian) + return; + ptt->seq_number = swap_u32(ptt->seq_number); + ptt->obj_id = swap_u32(ptt->obj_id); + ptt->chunk_id = swap_u32(ptt->chunk_id); + ptt->n_bytes = swap_u32(ptt->n_bytes); +} + +void yaffs_endian_config(struct yaffs_dev *dev) +{ + u32 x = 1; + + if (dev->tnode_size < 1) + BUG(); + + dev->swap_endian = 0; + + if (((char *)&x)[0] == 1) { + /* Little Endian. */ + if (dev->param.stored_endian == 2 /* big endian */) + dev->swap_endian = 1; + } else { + /* Big Endian. */ + if (dev->param.stored_endian == 1 /* little endian */) + dev->swap_endian = 1; + } + + if (dev->swap_endian) + dev->tn_swap_buffer = kmalloc(dev->tnode_size, GFP_NOFS); +} diff --git a/fs/yaffs2/yaffs_endian.h b/fs/yaffs2/yaffs_endian.h new file mode 100644 index 000000000000..8c271891a019 --- /dev/null +++ b/fs/yaffs2/yaffs_endian.h @@ -0,0 +1,54 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_ENDIAN_H__ +#define __YAFFS_ENDIAN_H__ +#include "yaffs_guts.h" +#include "yaffs_packedtags2.h" + +static inline u32 swap_u32(u32 val) +{ + return ((val >>24) & 0x000000ff) | + ((val >> 8) & 0x0000ff00) | + ((val << 8) & 0x00ff0000) | + ((val <<24) & 0xff000000); +} + +#define swap_s32(val) \ + (s32)(swap_u32((u32)(val))) + +static inline loff_t swap_loff_t(loff_t lval) +{ + u32 vall = swap_u32(FSIZE_LOW(lval)); + u32 valh; + + if (sizeof(loff_t) == sizeof(u32)) + return (loff_t) vall; + + valh = swap_u32(FSIZE_HIGH(lval)); + + return FSIZE_COMBINE(vall, valh); /*NB: h and l are swapped. */ +} + + + +struct yaffs_dev; +void yaffs_do_endian_s32(struct yaffs_dev *dev, s32 *val); +void yaffs_do_endian_u32(struct yaffs_dev *dev, u32 *val); +void yaffs_do_endian_oh(struct yaffs_dev *dev, struct yaffs_obj_hdr *oh); +void yaffs_do_endian_packed_tags2(struct yaffs_dev *dev, + struct yaffs_packed_tags2_tags_only *ptt); +void yaffs_endian_config(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_getblockinfo.h b/fs/yaffs2/yaffs_getblockinfo.h new file mode 100644 index 000000000000..e84ccf8812db --- /dev/null +++ b/fs/yaffs2/yaffs_getblockinfo.h @@ -0,0 +1,35 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_GETBLOCKINFO_H__ +#define __YAFFS_GETBLOCKINFO_H__ + +#include "yaffs_guts.h" +#include "yaffs_trace.h" + +/* Function to manipulate block info */ +static inline struct yaffs_block_info *yaffs_get_block_info(struct yaffs_dev + *dev, int blk) +{ + if (blk < (int)dev->internal_start_block || + blk > (int)dev->internal_end_block) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>> yaffs: get_block_info block %d is not valid", + blk); + BUG(); + } + return &dev->block_info[blk - dev->internal_start_block]; +} + +#endif diff --git a/fs/yaffs2/yaffs_guts.c b/fs/yaffs2/yaffs_guts.c new file mode 100644 index 000000000000..40a5b46cf6ca --- /dev/null +++ b/fs/yaffs2/yaffs_guts.c @@ -0,0 +1,5212 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yportenv.h" +#include "yaffs_trace.h" + +#include "yaffs_guts.h" +#include "yaffs_endian.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_tagscompat.h" +#include "yaffs_tagsmarshall.h" +#include "yaffs_nand.h" +#include "yaffs_yaffs1.h" +#include "yaffs_yaffs2.h" +#include "yaffs_bitmap.h" +#include "yaffs_verify.h" +#include "yaffs_nand.h" +#include "yaffs_packedtags2.h" +#include "yaffs_nameval.h" +#include "yaffs_allocator.h" +#include "yaffs_attribs.h" +#include "yaffs_summary.h" + +/* Note YAFFS_GC_GOOD_ENOUGH must be <= YAFFS_GC_PASSIVE_THRESHOLD */ +#define YAFFS_GC_GOOD_ENOUGH 2 +#define YAFFS_GC_PASSIVE_THRESHOLD 4 + +#include "yaffs_ecc.h" + +/* Forward declarations */ + +static int yaffs_wr_data_obj(struct yaffs_obj *in, int inode_chunk, + const u8 *buffer, int n_bytes, int use_reserve); + +static void yaffs_fix_null_name(struct yaffs_obj *obj, YCHAR *name, + int buffer_size); + +/* Function to calculate chunk and offset */ + +void yaffs_addr_to_chunk(struct yaffs_dev *dev, loff_t addr, + int *chunk_out, u32 *offset_out) +{ + int chunk; + u32 offset; + + chunk = (u32) (addr >> dev->chunk_shift); + + if (dev->chunk_div == 1) { + /* easy power of 2 case */ + offset = (u32) (addr & dev->chunk_mask); + } else { + /* Non power-of-2 case */ + + loff_t chunk_base; + + chunk /= dev->chunk_div; + + chunk_base = ((loff_t) chunk) * dev->data_bytes_per_chunk; + offset = (u32) (addr - chunk_base); + } + + *chunk_out = chunk; + *offset_out = offset; +} + +/* Function to return the number of shifts for a power of 2 greater than or + * equal to the given number + * Note we don't try to cater for all possible numbers and this does not have to + * be hellishly efficient. + */ + +static inline u32 calc_shifts_ceiling(u32 x) +{ + int extra_bits; + int shifts; + + shifts = extra_bits = 0; + + while (x > 1) { + if (x & 1) + extra_bits++; + x >>= 1; + shifts++; + } + + if (extra_bits) + shifts++; + + return shifts; +} + +/* Function to return the number of shifts to get a 1 in bit 0 + */ + +static inline u32 calc_shifts(u32 x) +{ + u32 shifts; + + shifts = 0; + + if (!x) + return 0; + + while (!(x & 1)) { + x >>= 1; + shifts++; + } + + return shifts; +} + +/* + * Temporary buffer manipulations. + */ + +static int yaffs_init_tmp_buffers(struct yaffs_dev *dev) +{ + int i; + u8 *buf = (u8 *) 1; + + memset(dev->temp_buffer, 0, sizeof(dev->temp_buffer)); + + for (i = 0; buf && i < YAFFS_N_TEMP_BUFFERS; i++) { + dev->temp_buffer[i].in_use = 0; + buf = kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS); + dev->temp_buffer[i].buffer = buf; + } + + return buf ? YAFFS_OK : YAFFS_FAIL; +} + +u8 *yaffs_get_temp_buffer(struct yaffs_dev * dev) +{ + int i; + + dev->temp_in_use++; + if (dev->temp_in_use > dev->max_temp) + dev->max_temp = dev->temp_in_use; + + for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++) { + if (dev->temp_buffer[i].in_use == 0) { + dev->temp_buffer[i].in_use = 1; + return dev->temp_buffer[i].buffer; + } + } + + yaffs_trace(YAFFS_TRACE_BUFFERS, "Out of temp buffers"); + /* + * If we got here then we have to allocate an unmanaged one + * This is not good. + */ + + dev->unmanaged_buffer_allocs++; + return kmalloc(dev->data_bytes_per_chunk, GFP_NOFS); + +} + +void yaffs_release_temp_buffer(struct yaffs_dev *dev, u8 *buffer) +{ + int i; + + dev->temp_in_use--; + + for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++) { + if (dev->temp_buffer[i].buffer == buffer) { + dev->temp_buffer[i].in_use = 0; + return; + } + } + + if (buffer) { + /* assume it is an unmanaged one. */ + yaffs_trace(YAFFS_TRACE_BUFFERS, + "Releasing unmanaged temp buffer"); + kfree(buffer); + dev->unmanaged_buffer_deallocs++; + } + +} + +/* + * Functions for robustisizing TODO + * + */ + +static void yaffs_handle_chunk_wr_ok(struct yaffs_dev *dev, int nand_chunk, + const u8 *data, + const struct yaffs_ext_tags *tags) +{ + (void) dev; + (void) nand_chunk; + (void) data; + (void) tags; +} + +static void yaffs_handle_chunk_update(struct yaffs_dev *dev, int nand_chunk, + const struct yaffs_ext_tags *tags) +{ + (void) dev; + (void) nand_chunk; + (void) tags; +} + +void yaffs_handle_chunk_error(struct yaffs_dev *dev, + struct yaffs_block_info *bi) +{ + if (!bi->gc_prioritise) { + bi->gc_prioritise = 1; + dev->has_pending_prioritised_gc = 1; + bi->chunk_error_strikes++; + + if (bi->chunk_error_strikes > 3) { + bi->needs_retiring = 1; /* Too many stikes, so retire */ + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: Block struck out"); + + } + } +} + +static void yaffs_handle_chunk_wr_error(struct yaffs_dev *dev, int nand_chunk, + int erased_ok) +{ + int flash_block = nand_chunk / dev->param.chunks_per_block; + struct yaffs_block_info *bi = yaffs_get_block_info(dev, flash_block); + + yaffs_handle_chunk_error(dev, bi); + + if (erased_ok) { + /* Was an actual write failure, + * so mark the block for retirement.*/ + bi->needs_retiring = 1; + yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS, + "**>> Block %d needs retiring", flash_block); + } + + /* Delete the chunk */ + yaffs_chunk_del(dev, nand_chunk, 1, __LINE__); + yaffs_skip_rest_of_block(dev); +} + +/* + * Verification code + */ + +/* + * Simple hash function. Needs to have a reasonable spread + */ + +static inline int yaffs_hash_fn(int n) +{ + if (n < 0) + n = -n; + return n % YAFFS_NOBJECT_BUCKETS; +} + +/* + * Access functions to useful fake objects. + * Note that root might have a presence in NAND if permissions are set. + */ + +struct yaffs_obj *yaffs_root(struct yaffs_dev *dev) +{ + return dev->root_dir; +} + +struct yaffs_obj *yaffs_lost_n_found(struct yaffs_dev *dev) +{ + return dev->lost_n_found; +} + +/* + * Erased NAND checking functions + */ + +int yaffs_check_ff(u8 *buffer, int n_bytes) +{ + /* Horrible, slow implementation */ + while (n_bytes--) { + if (*buffer != 0xff) + return 0; + buffer++; + } + return 1; +} + +static int yaffs_check_chunk_erased(struct yaffs_dev *dev, int nand_chunk) +{ + int retval = YAFFS_OK; + u8 *data = yaffs_get_temp_buffer(dev); + struct yaffs_ext_tags tags; + int result; + + result = yaffs_rd_chunk_tags_nand(dev, nand_chunk, data, &tags); + + if (result == YAFFS_FAIL || + tags.ecc_result > YAFFS_ECC_RESULT_NO_ERROR) + retval = YAFFS_FAIL; + + if (!yaffs_check_ff(data, dev->data_bytes_per_chunk) || + tags.chunk_used) { + yaffs_trace(YAFFS_TRACE_NANDACCESS, + "Chunk %d not erased", nand_chunk); + retval = YAFFS_FAIL; + } + + yaffs_release_temp_buffer(dev, data); + + return retval; + +} + +static int yaffs_verify_chunk_written(struct yaffs_dev *dev, + int nand_chunk, + const u8 *data, + struct yaffs_ext_tags *tags) +{ + int retval = YAFFS_OK; + struct yaffs_ext_tags temp_tags; + u8 *buffer = yaffs_get_temp_buffer(dev); + int result; + + result = yaffs_rd_chunk_tags_nand(dev, nand_chunk, buffer, &temp_tags); + if (result == YAFFS_FAIL || + memcmp(buffer, data, dev->data_bytes_per_chunk) || + temp_tags.obj_id != tags->obj_id || + temp_tags.chunk_id != tags->chunk_id || + temp_tags.n_bytes != tags->n_bytes) + retval = YAFFS_FAIL; + + yaffs_release_temp_buffer(dev, buffer); + + return retval; +} + + +int yaffs_check_alloc_available(struct yaffs_dev *dev, int n_chunks) +{ + int reserved_chunks; + int reserved_blocks = dev->param.n_reserved_blocks; + int checkpt_blocks; + + checkpt_blocks = yaffs_calc_checkpt_blocks_required(dev); + + reserved_chunks = + (reserved_blocks + checkpt_blocks) * dev->param.chunks_per_block; + + return (dev->n_free_chunks > (reserved_chunks + n_chunks)); +} + +static int yaffs_find_alloc_block(struct yaffs_dev *dev) +{ + u32 i; + struct yaffs_block_info *bi; + + if (dev->n_erased_blocks < 1) { + /* Hoosterman we've got a problem. + * Can't get space to gc + */ + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: no more erased blocks"); + + return -1; + } + + /* Find an empty block. */ + + for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + dev->alloc_block_finder++; + if (dev->alloc_block_finder < (int)dev->internal_start_block + || dev->alloc_block_finder > (int)dev->internal_end_block) { + dev->alloc_block_finder = dev->internal_start_block; + } + + bi = yaffs_get_block_info(dev, dev->alloc_block_finder); + + if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) { + bi->block_state = YAFFS_BLOCK_STATE_ALLOCATING; + dev->seq_number++; + bi->seq_number = dev->seq_number; + dev->n_erased_blocks--; + yaffs_trace(YAFFS_TRACE_ALLOCATE, + "Allocated block %d, seq %d, %d left" , + dev->alloc_block_finder, dev->seq_number, + dev->n_erased_blocks); + return dev->alloc_block_finder; + } + } + + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs tragedy: no more erased blocks, but there should have been %d", + dev->n_erased_blocks); + + return -1; +} + +static int yaffs_alloc_chunk(struct yaffs_dev *dev, int use_reserver, + struct yaffs_block_info **block_ptr) +{ + int ret_val; + struct yaffs_block_info *bi; + + if (dev->alloc_block < 0) { + /* Get next block to allocate off */ + dev->alloc_block = yaffs_find_alloc_block(dev); + dev->alloc_page = 0; + } + + if (!use_reserver && !yaffs_check_alloc_available(dev, 1)) { + /* No space unless we're allowed to use the reserve. */ + return -1; + } + + if (dev->n_erased_blocks < (int)dev->param.n_reserved_blocks + && dev->alloc_page == 0) + yaffs_trace(YAFFS_TRACE_ALLOCATE, "Allocating reserve"); + + /* Next page please.... */ + if (dev->alloc_block >= 0) { + bi = yaffs_get_block_info(dev, dev->alloc_block); + + ret_val = (dev->alloc_block * dev->param.chunks_per_block) + + dev->alloc_page; + bi->pages_in_use++; + yaffs_set_chunk_bit(dev, dev->alloc_block, dev->alloc_page); + + dev->alloc_page++; + + dev->n_free_chunks--; + + /* If the block is full set the state to full */ + if (dev->alloc_page >= dev->param.chunks_per_block) { + bi->block_state = YAFFS_BLOCK_STATE_FULL; + dev->alloc_block = -1; + } + + if (block_ptr) + *block_ptr = bi; + + return ret_val; + } + + yaffs_trace(YAFFS_TRACE_ERROR, + "!!!!!!!!! Allocator out !!!!!!!!!!!!!!!!!"); + + return -1; +} + +static int yaffs_get_erased_chunks(struct yaffs_dev *dev) +{ + int n; + + n = dev->n_erased_blocks * dev->param.chunks_per_block; + + if (dev->alloc_block > 0) + n += (dev->param.chunks_per_block - dev->alloc_page); + + return n; + +} + +/* + * yaffs_skip_rest_of_block() skips over the rest of the allocation block + * if we don't want to write to it. + */ +void yaffs_skip_rest_of_block(struct yaffs_dev *dev) +{ + struct yaffs_block_info *bi; + + if (dev->alloc_block > 0) { + bi = yaffs_get_block_info(dev, dev->alloc_block); + if (bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING) { + bi->block_state = YAFFS_BLOCK_STATE_FULL; + dev->alloc_block = -1; + } + } +} + +static int yaffs_write_new_chunk(struct yaffs_dev *dev, + const u8 *data, + struct yaffs_ext_tags *tags, int use_reserver) +{ + u32 attempts = 0; + int write_ok = 0; + int chunk; + + yaffs2_checkpt_invalidate(dev); + + do { + struct yaffs_block_info *bi = 0; + int erased_ok = 0; + + chunk = yaffs_alloc_chunk(dev, use_reserver, &bi); + if (chunk < 0) { + /* no space */ + break; + } + + /* First check this chunk is erased, if it needs + * checking. The checking policy (unless forced + * always on) is as follows: + * + * Check the first page we try to write in a block. + * If the check passes then we don't need to check any + * more. If the check fails, we check again... + * If the block has been erased, we don't need to check. + * + * However, if the block has been prioritised for gc, + * then we think there might be something odd about + * this block and stop using it. + * + * Rationale: We should only ever see chunks that have + * not been erased if there was a partially written + * chunk due to power loss. This checking policy should + * catch that case with very few checks and thus save a + * lot of checks that are most likely not needed. + * + * Mods to the above + * If an erase check fails or the write fails we skip the + * rest of the block. + */ + + /* let's give it a try */ + attempts++; + + if (dev->param.always_check_erased) + bi->skip_erased_check = 0; + + if (!bi->skip_erased_check) { + erased_ok = yaffs_check_chunk_erased(dev, chunk); + if (erased_ok != YAFFS_OK) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>> yaffs chunk %d was not erased", + chunk); + + /* If not erased, delete this one, + * skip rest of block and + * try another chunk */ + yaffs_chunk_del(dev, chunk, 1, __LINE__); + yaffs_skip_rest_of_block(dev); + continue; + } + } + + write_ok = yaffs_wr_chunk_tags_nand(dev, chunk, data, tags); + + if (!bi->skip_erased_check) + write_ok = + yaffs_verify_chunk_written(dev, chunk, data, tags); + + if (write_ok != YAFFS_OK) { + /* Clean up aborted write, skip to next block and + * try another chunk */ + yaffs_handle_chunk_wr_error(dev, chunk, erased_ok); + continue; + } + + bi->skip_erased_check = 1; + + /* Copy the data into the robustification buffer */ + yaffs_handle_chunk_wr_ok(dev, chunk, data, tags); + + } while (write_ok != YAFFS_OK && + (yaffs_wr_attempts == 0 || attempts <= yaffs_wr_attempts)); + + if (!write_ok) + chunk = -1; + + if (attempts > 1) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>> yaffs write required %d attempts", + attempts); + dev->n_retried_writes += (attempts - 1); + } + + return chunk; +} + +/* + * Block retiring for handling a broken block. + */ + +static void yaffs_retire_block(struct yaffs_dev *dev, int flash_block) +{ + struct yaffs_block_info *bi = yaffs_get_block_info(dev, flash_block); + + yaffs2_checkpt_invalidate(dev); + + yaffs2_clear_oldest_dirty_seq(dev, bi); + + if (yaffs_mark_bad(dev, flash_block) != YAFFS_OK) { + if (yaffs_erase_block(dev, flash_block) != YAFFS_OK) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: Failed to mark bad and erase block %d", + flash_block); + } else { + struct yaffs_ext_tags tags; + int chunk_id = + flash_block * dev->param.chunks_per_block; + + u8 *buffer = yaffs_get_temp_buffer(dev); + + memset(buffer, 0xff, dev->data_bytes_per_chunk); + memset(&tags, 0, sizeof(tags)); + tags.seq_number = YAFFS_SEQUENCE_BAD_BLOCK; + if (dev->tagger.write_chunk_tags_fn(dev, chunk_id - + dev->chunk_offset, + buffer, + &tags) != YAFFS_OK) + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: Failed to write bad block marker to block %d", + flash_block); + + yaffs_release_temp_buffer(dev, buffer); + } + } + + bi->block_state = YAFFS_BLOCK_STATE_DEAD; + bi->gc_prioritise = 0; + bi->needs_retiring = 0; + + dev->n_retired_blocks++; +} + +/*---------------- Name handling functions ------------*/ + +static void yaffs_load_name_from_oh(struct yaffs_dev *dev, YCHAR *name, + const YCHAR *oh_name, int buff_size) +{ +#ifdef CONFIG_YAFFS_AUTO_UNICODE + if (dev->param.auto_unicode) { + if (*oh_name) { + /* It is an ASCII name, do an ASCII to + * unicode conversion */ + const char *ascii_oh_name = (const char *)oh_name; + int n = buff_size - 1; + while (n > 0 && *ascii_oh_name) { + *name = *ascii_oh_name; + name++; + ascii_oh_name++; + n--; + } + } else { + strncpy(name, oh_name + 1, buff_size - 1); + } + } else { +#else + (void) dev; + { +#endif + strncpy(name, oh_name, buff_size - 1); + } +} + +static void yaffs_load_oh_from_name(struct yaffs_dev *dev, YCHAR *oh_name, + const YCHAR *name) +{ +#ifdef CONFIG_YAFFS_AUTO_UNICODE + + int is_ascii; + const YCHAR *w; + + if (dev->param.auto_unicode) { + + is_ascii = 1; + w = name; + + /* Figure out if the name will fit in ascii character set */ + while (is_ascii && *w) { + if ((*w) & 0xff00) + is_ascii = 0; + w++; + } + + if (is_ascii) { + /* It is an ASCII name, so convert unicode to ascii */ + char *ascii_oh_name = (char *)oh_name; + int n = YAFFS_MAX_NAME_LENGTH - 1; + while (n > 0 && *name) { + *ascii_oh_name = *name; + name++; + ascii_oh_name++; + n--; + } + } else { + /* Unicode name, so save starting at the second YCHAR */ + *oh_name = 0; + strncpy(oh_name + 1, name, YAFFS_MAX_NAME_LENGTH - 2); + } + } else { +#else + dev = dev; + { +#endif + strncpy(oh_name, name, YAFFS_MAX_NAME_LENGTH - 1); + } +} + +static u16 yaffs_calc_name_sum(const YCHAR *name) +{ + u16 sum = 0; + u16 i = 1; + + if (!name) + return 0; + + while ((*name) && i < (YAFFS_MAX_NAME_LENGTH / 2)) { + + /* 0x1f mask is case insensitive */ + sum += ((*name) & 0x1f) * i; + i++; + name++; + } + return sum; +} + + +void yaffs_set_obj_name(struct yaffs_obj *obj, const YCHAR * name) +{ + memset(obj->short_name, 0, sizeof(obj->short_name)); + + if (name && !name[0]) { + yaffs_fix_null_name(obj, obj->short_name, + YAFFS_SHORT_NAME_LENGTH); + name = obj->short_name; + } else if (name && + strnlen(name, YAFFS_SHORT_NAME_LENGTH + 1) <= + YAFFS_SHORT_NAME_LENGTH) { + strcpy(obj->short_name, name); + } + + obj->sum = yaffs_calc_name_sum(name); +} + +void yaffs_set_obj_name_from_oh(struct yaffs_obj *obj, + const struct yaffs_obj_hdr *oh) +{ +#ifdef CONFIG_YAFFS_AUTO_UNICODE + YCHAR tmp_name[YAFFS_MAX_NAME_LENGTH + 1]; + memset(tmp_name, 0, sizeof(tmp_name)); + yaffs_load_name_from_oh(obj->my_dev, tmp_name, oh->name, + YAFFS_MAX_NAME_LENGTH + 1); + yaffs_set_obj_name(obj, tmp_name); +#else + yaffs_set_obj_name(obj, oh->name); +#endif +} + +loff_t yaffs_max_file_size(struct yaffs_dev *dev) +{ + if (sizeof(loff_t) < 8) + return YAFFS_MAX_FILE_SIZE_32; + else + return ((loff_t) YAFFS_MAX_CHUNK_ID) * dev->data_bytes_per_chunk; +} + +/*-------------------- TNODES ------------------- + + * List of spare tnodes + * The list is hooked together using the first pointer + * in the tnode. + */ + +struct yaffs_tnode *yaffs_get_tnode(struct yaffs_dev *dev) +{ + struct yaffs_tnode *tn = yaffs_alloc_raw_tnode(dev); + + if (tn) { + memset(tn, 0, dev->tnode_size); + dev->n_tnodes++; + } + + dev->checkpoint_blocks_required = 0; /* force recalculation */ + + return tn; +} + +/* FreeTnode frees up a tnode and puts it back on the free list */ +static void yaffs_free_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn) +{ + yaffs_free_raw_tnode(dev, tn); + dev->n_tnodes--; + dev->checkpoint_blocks_required = 0; /* force recalculation */ +} + +static void yaffs_deinit_tnodes_and_objs(struct yaffs_dev *dev) +{ + yaffs_deinit_raw_tnodes_and_objs(dev); + dev->n_obj = 0; + dev->n_tnodes = 0; +} + +static void yaffs_load_tnode_0(struct yaffs_dev *dev, struct yaffs_tnode *tn, + unsigned pos, unsigned val) +{ + u32 *map = (u32 *) tn; + u32 bit_in_map; + u32 bit_in_word; + u32 word_in_map; + u32 mask; + + pos &= YAFFS_TNODES_LEVEL0_MASK; + val >>= dev->chunk_grp_bits; + + bit_in_map = pos * dev->tnode_width; + word_in_map = bit_in_map / 32; + bit_in_word = bit_in_map & (32 - 1); + + mask = dev->tnode_mask << bit_in_word; + + map[word_in_map] &= ~mask; + map[word_in_map] |= (mask & (val << bit_in_word)); + + if (dev->tnode_width > (32 - bit_in_word)) { + bit_in_word = (32 - bit_in_word); + word_in_map++; + mask = + dev->tnode_mask >> bit_in_word; + map[word_in_map] &= ~mask; + map[word_in_map] |= (mask & (val >> bit_in_word)); + } +} + +u32 yaffs_get_group_base(struct yaffs_dev *dev, struct yaffs_tnode *tn, + unsigned pos) +{ + u32 *map = (u32 *) tn; + u32 bit_in_map; + u32 bit_in_word; + u32 word_in_map; + u32 val; + + pos &= YAFFS_TNODES_LEVEL0_MASK; + + bit_in_map = pos * dev->tnode_width; + word_in_map = bit_in_map / 32; + bit_in_word = bit_in_map & (32 - 1); + + val = map[word_in_map] >> bit_in_word; + + if (dev->tnode_width > (32 - bit_in_word)) { + bit_in_word = (32 - bit_in_word); + word_in_map++; + val |= (map[word_in_map] << bit_in_word); + } + + val &= dev->tnode_mask; + val <<= dev->chunk_grp_bits; + + return val; +} + +/* ------------------- End of individual tnode manipulation -----------------*/ + +/* ---------Functions to manipulate the look-up tree (made up of tnodes) ------ + * The look up tree is represented by the top tnode and the number of top_level + * in the tree. 0 means only the level 0 tnode is in the tree. + */ + +/* FindLevel0Tnode finds the level 0 tnode, if one exists. */ +struct yaffs_tnode *yaffs_find_tnode_0(struct yaffs_dev *dev, + struct yaffs_file_var *file_struct, + u32 chunk_id) +{ + struct yaffs_tnode *tn = file_struct->top; + u32 i; + int required_depth; + int level = file_struct->top_level; + + (void) dev; + + /* Check sane level and chunk Id */ + if (level < 0 || level > YAFFS_TNODES_MAX_LEVEL) + return NULL; + + if (chunk_id > YAFFS_MAX_CHUNK_ID) + return NULL; + + /* First check we're tall enough (ie enough top_level) */ + + i = chunk_id >> YAFFS_TNODES_LEVEL0_BITS; + required_depth = 0; + while (i) { + i >>= YAFFS_TNODES_INTERNAL_BITS; + required_depth++; + } + + if (required_depth > file_struct->top_level) + return NULL; /* Not tall enough, so we can't find it */ + + /* Traverse down to level 0 */ + while (level > 0 && tn) { + tn = tn->internal[(chunk_id >> + (YAFFS_TNODES_LEVEL0_BITS + + (level - 1) * + YAFFS_TNODES_INTERNAL_BITS)) & + YAFFS_TNODES_INTERNAL_MASK]; + level--; + } + + return tn; +} + +/* add_find_tnode_0 finds the level 0 tnode if it exists, + * otherwise first expands the tree. + * This happens in two steps: + * 1. If the tree isn't tall enough, then make it taller. + * 2. Scan down the tree towards the level 0 tnode adding tnodes if required. + * + * Used when modifying the tree. + * + * If the tn argument is NULL, then a fresh tnode will be added otherwise the + * specified tn will be plugged into the ttree. + */ + +struct yaffs_tnode *yaffs_add_find_tnode_0(struct yaffs_dev *dev, + struct yaffs_file_var *file_struct, + u32 chunk_id, + struct yaffs_tnode *passed_tn) +{ + int required_depth; + int i; + int l; + struct yaffs_tnode *tn; + u32 x; + + /* Check sane level and page Id */ + if (file_struct->top_level < 0 || + file_struct->top_level > YAFFS_TNODES_MAX_LEVEL) + return NULL; + + if (chunk_id > YAFFS_MAX_CHUNK_ID) + return NULL; + + /* First check we're tall enough (ie enough top_level) */ + + x = chunk_id >> YAFFS_TNODES_LEVEL0_BITS; + required_depth = 0; + while (x) { + x >>= YAFFS_TNODES_INTERNAL_BITS; + required_depth++; + } + + if (required_depth > file_struct->top_level) { + /* Not tall enough, gotta make the tree taller */ + for (i = file_struct->top_level; i < required_depth; i++) { + + tn = yaffs_get_tnode(dev); + + if (tn) { + tn->internal[0] = file_struct->top; + file_struct->top = tn; + file_struct->top_level++; + } else { + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs: no more tnodes"); + return NULL; + } + } + } + + /* Traverse down to level 0, adding anything we need */ + + l = file_struct->top_level; + tn = file_struct->top; + + if (l > 0) { + while (l > 0 && tn) { + x = (chunk_id >> + (YAFFS_TNODES_LEVEL0_BITS + + (l - 1) * YAFFS_TNODES_INTERNAL_BITS)) & + YAFFS_TNODES_INTERNAL_MASK; + + if ((l > 1) && !tn->internal[x]) { + /* Add missing non-level-zero tnode */ + tn->internal[x] = yaffs_get_tnode(dev); + if (!tn->internal[x]) + return NULL; + } else if (l == 1) { + /* Looking from level 1 at level 0 */ + if (passed_tn) { + /* If we already have one, release it */ + if (tn->internal[x]) + yaffs_free_tnode(dev, + tn->internal[x]); + tn->internal[x] = passed_tn; + + } else if (!tn->internal[x]) { + /* Don't have one, none passed in */ + tn->internal[x] = yaffs_get_tnode(dev); + if (!tn->internal[x]) + return NULL; + } + } + + tn = tn->internal[x]; + l--; + } + } else { + /* top is level 0 */ + if (passed_tn) { + memcpy(tn, passed_tn, + (dev->tnode_width * YAFFS_NTNODES_LEVEL0) / 8); + yaffs_free_tnode(dev, passed_tn); + } + } + + return tn; +} + +static int yaffs_tags_match(const struct yaffs_ext_tags *tags, int obj_id, + int chunk_obj) +{ + return (tags->chunk_id == (u32)chunk_obj && + tags->obj_id == (u32)obj_id && + !tags->is_deleted) ? 1 : 0; + +} + +static int yaffs_find_chunk_in_group(struct yaffs_dev *dev, int the_chunk, + struct yaffs_ext_tags *tags, int obj_id, + int inode_chunk) +{ + int j; + + for (j = 0; the_chunk && j < dev->chunk_grp_size; j++) { + if (yaffs_check_chunk_bit + (dev, the_chunk / dev->param.chunks_per_block, + the_chunk % dev->param.chunks_per_block)) { + + if (dev->chunk_grp_size == 1) + return the_chunk; + else { + yaffs_rd_chunk_tags_nand(dev, the_chunk, NULL, + tags); + if (yaffs_tags_match(tags, + obj_id, inode_chunk)) { + /* found it; */ + return the_chunk; + } + } + } + the_chunk++; + } + return -1; +} + +int yaffs_find_chunk_in_file(struct yaffs_obj *in, int inode_chunk, + struct yaffs_ext_tags *tags) +{ + /*Get the Tnode, then get the level 0 offset chunk offset */ + struct yaffs_tnode *tn; + int the_chunk = -1; + struct yaffs_ext_tags local_tags; + int ret_val = -1; + struct yaffs_dev *dev = in->my_dev; + + if (!tags) { + /* Passed a NULL, so use our own tags space */ + tags = &local_tags; + } + + tn = yaffs_find_tnode_0(dev, &in->variant.file_variant, inode_chunk); + + if (!tn) + return ret_val; + + the_chunk = yaffs_get_group_base(dev, tn, inode_chunk); + + ret_val = yaffs_find_chunk_in_group(dev, the_chunk, tags, in->obj_id, + inode_chunk); + return ret_val; +} + +static int yaffs_find_del_file_chunk(struct yaffs_obj *in, int inode_chunk, + struct yaffs_ext_tags *tags) +{ + /* Get the Tnode, then get the level 0 offset chunk offset */ + struct yaffs_tnode *tn; + int the_chunk = -1; + struct yaffs_ext_tags local_tags; + struct yaffs_dev *dev = in->my_dev; + int ret_val = -1; + + if (!tags) { + /* Passed a NULL, so use our own tags space */ + tags = &local_tags; + } + + tn = yaffs_find_tnode_0(dev, &in->variant.file_variant, inode_chunk); + + if (!tn) + return ret_val; + + the_chunk = yaffs_get_group_base(dev, tn, inode_chunk); + + ret_val = yaffs_find_chunk_in_group(dev, the_chunk, tags, in->obj_id, + inode_chunk); + + /* Delete the entry in the filestructure (if found) */ + if (ret_val != -1) + yaffs_load_tnode_0(dev, tn, inode_chunk, 0); + + return ret_val; +} + +int yaffs_put_chunk_in_file(struct yaffs_obj *in, int inode_chunk, + int nand_chunk, int in_scan) +{ + /* NB in_scan is zero unless scanning. + * For forward scanning, in_scan is > 0; + * for backward scanning in_scan is < 0 + * + * nand_chunk = 0 is a dummy insert to make sure the tnodes are there. + */ + + struct yaffs_tnode *tn; + struct yaffs_dev *dev = in->my_dev; + int existing_cunk; + struct yaffs_ext_tags existing_tags; + struct yaffs_ext_tags new_tags; + unsigned existing_serial, new_serial; + + if (in->variant_type != YAFFS_OBJECT_TYPE_FILE) { + /* Just ignore an attempt at putting a chunk into a non-file + * during scanning. + * If it is not during Scanning then something went wrong! + */ + if (!in_scan) { + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy:attempt to put data chunk into a non-file" + ); + BUG(); + } + + yaffs_chunk_del(dev, nand_chunk, 1, __LINE__); + return YAFFS_OK; + } + + tn = yaffs_add_find_tnode_0(dev, + &in->variant.file_variant, + inode_chunk, NULL); + if (!tn) + return YAFFS_FAIL; + + if (!nand_chunk) + /* Dummy insert, bail now */ + return YAFFS_OK; + + existing_cunk = yaffs_get_group_base(dev, tn, inode_chunk); + + if (in_scan != 0) { + /* If we're scanning then we need to test for duplicates + * NB This does not need to be efficient since it should only + * happen when the power fails during a write, then only one + * chunk should ever be affected. + * + * Correction for YAFFS2: This could happen quite a lot and we + * need to think about efficiency! TODO + * Update: For backward scanning we don't need to re-read tags + * so this is quite cheap. + */ + + if (existing_cunk > 0) { + /* NB Right now existing chunk will not be real + * chunk_id if the chunk group size > 1 + * thus we have to do a FindChunkInFile to get the + * real chunk id. + * + * We have a duplicate now we need to decide which + * one to use: + * + * Backwards scanning YAFFS2: The old one is what + * we use, dump the new one. + * YAFFS1: Get both sets of tags and compare serial + * numbers. + */ + + if (in_scan > 0) { + /* Only do this for forward scanning */ + yaffs_rd_chunk_tags_nand(dev, + nand_chunk, + NULL, &new_tags); + + /* Do a proper find */ + existing_cunk = + yaffs_find_chunk_in_file(in, inode_chunk, + &existing_tags); + } + + if (existing_cunk <= 0) { + /*Hoosterman - how did this happen? */ + + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: existing chunk < 0 in scan" + ); + + } + + /* NB The deleted flags should be false, otherwise + * the chunks will not be loaded during a scan + */ + + if (in_scan > 0) { + new_serial = new_tags.serial_number; + existing_serial = existing_tags.serial_number; + } + + if ((in_scan > 0) && + (existing_cunk <= 0 || + ((existing_serial + 1) & 3) == new_serial)) { + /* Forward scanning. + * Use new + * Delete the old one and drop through to + * update the tnode + */ + yaffs_chunk_del(dev, existing_cunk, 1, + __LINE__); + } else { + /* Backward scanning or we want to use the + * existing one + * Delete the new one and return early so that + * the tnode isn't changed + */ + yaffs_chunk_del(dev, nand_chunk, 1, __LINE__); + return YAFFS_OK; + } + } + + } + + if (existing_cunk == 0) + in->n_data_chunks++; + + yaffs_load_tnode_0(dev, tn, inode_chunk, nand_chunk); + + return YAFFS_OK; +} + +static void yaffs_soft_del_chunk(struct yaffs_dev *dev, int chunk) +{ + struct yaffs_block_info *the_block; + unsigned block_no; + + yaffs_trace(YAFFS_TRACE_DELETION, "soft delete chunk %d", chunk); + + block_no = chunk / dev->param.chunks_per_block; + the_block = yaffs_get_block_info(dev, block_no); + if (the_block) { + the_block->soft_del_pages++; + dev->n_free_chunks++; + yaffs2_update_oldest_dirty_seq(dev, block_no, the_block); + } +} + +/* SoftDeleteWorker scans backwards through the tnode tree and soft deletes all + * the chunks in the file. + * All soft deleting does is increment the block's softdelete count and pulls + * the chunk out of the tnode. + * Thus, essentially this is the same as DeleteWorker except that the chunks + * are soft deleted. + */ + +static int yaffs_soft_del_worker(struct yaffs_obj *in, struct yaffs_tnode *tn, + u32 level, int chunk_offset) +{ + int i; + int the_chunk; + int all_done = 1; + struct yaffs_dev *dev = in->my_dev; + + if (!tn) + return 1; + + if (level > 0) { + for (i = YAFFS_NTNODES_INTERNAL - 1; + all_done && i >= 0; + i--) { + if (tn->internal[i]) { + all_done = + yaffs_soft_del_worker(in, + tn->internal[i], + level - 1, + (chunk_offset << + YAFFS_TNODES_INTERNAL_BITS) + + i); + if (all_done) { + yaffs_free_tnode(dev, + tn->internal[i]); + tn->internal[i] = NULL; + } else { + /* Can this happen? */ + } + } + } + return (all_done) ? 1 : 0; + } + + /* level 0 */ + for (i = YAFFS_NTNODES_LEVEL0 - 1; i >= 0; i--) { + the_chunk = yaffs_get_group_base(dev, tn, i); + if (the_chunk) { + yaffs_soft_del_chunk(dev, the_chunk); + yaffs_load_tnode_0(dev, tn, i, 0); + } + } + return 1; +} + +static void yaffs_remove_obj_from_dir(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev = obj->my_dev; + struct yaffs_obj *parent; + + yaffs_verify_obj_in_dir(obj); + parent = obj->parent; + + yaffs_verify_dir(parent); + + if (dev && dev->param.remove_obj_fn) + dev->param.remove_obj_fn(obj); + + list_del_init(&obj->siblings); + obj->parent = NULL; + + yaffs_verify_dir(parent); +} + +void yaffs_add_obj_to_dir(struct yaffs_obj *directory, struct yaffs_obj *obj) +{ + if (!directory) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "tragedy: Trying to add an object to a null pointer directory" + ); + BUG(); + return; + } + if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "tragedy: Trying to add an object to a non-directory" + ); + BUG(); + } + + if (obj->siblings.prev == NULL) { + /* Not initialised */ + BUG(); + } + + yaffs_verify_dir(directory); + + yaffs_remove_obj_from_dir(obj); + + /* Now add it */ + list_add(&obj->siblings, &directory->variant.dir_variant.children); + obj->parent = directory; + + if (directory == obj->my_dev->unlinked_dir + || directory == obj->my_dev->del_dir) { + obj->unlinked = 1; + obj->my_dev->n_unlinked_files++; + obj->rename_allowed = 0; + } + + yaffs_verify_dir(directory); + yaffs_verify_obj_in_dir(obj); +} + +static int yaffs_change_obj_name(struct yaffs_obj *obj, + struct yaffs_obj *new_dir, + const YCHAR *new_name, int force, int shadows) +{ + int unlink_op; + int del_op; + struct yaffs_obj *existing_target; + + if (new_dir == NULL) + new_dir = obj->parent; /* use the old directory */ + + if (new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "tragedy: yaffs_change_obj_name: new_dir is not a directory" + ); + BUG(); + } + + unlink_op = (new_dir == obj->my_dev->unlinked_dir); + del_op = (new_dir == obj->my_dev->del_dir); + + existing_target = yaffs_find_by_name(new_dir, new_name); + + /* If the object is a file going into the unlinked directory, + * then it is OK to just stuff it in since duplicate names are OK. + * else only proceed if the new name does not exist and we're putting + * it into a directory. + */ + if (!(unlink_op || del_op || force || + shadows > 0 || !existing_target) || + new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) + return YAFFS_FAIL; + + yaffs_set_obj_name(obj, new_name); + obj->dirty = 1; + yaffs_add_obj_to_dir(new_dir, obj); + + if (unlink_op) + obj->unlinked = 1; + + /* If it is a deletion then we mark it as a shrink for gc */ + if (yaffs_update_oh(obj, new_name, 0, del_op, shadows, NULL) >= 0) + return YAFFS_OK; + + return YAFFS_FAIL; +} + +/*------------------------ Short Operations Cache ------------------------------ + * In many situations where there is no high level buffering a lot of + * reads might be short sequential reads, and a lot of writes may be short + * sequential writes. eg. scanning/writing a jpeg file. + * In these cases, a short read/write cache can provide a huge perfomance + * benefit with dumb-as-a-rock code. + * In Linux, the page cache provides read buffering and the short op cache + * provides write buffering. + * + * There are a small number (~10) of cache chunks per device so that we don't + * need a very intelligent search. + */ + +static int yaffs_obj_cache_dirty(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev = obj->my_dev; + int i; + struct yaffs_cache *cache; + int n_caches = obj->my_dev->param.n_caches; + + for (i = 0; i < n_caches; i++) { + cache = &dev->cache[i]; + if (cache->object == obj && cache->dirty) + return 1; + } + + return 0; +} + +static void yaffs_flush_single_cache(struct yaffs_cache *cache, int discard) +{ + + if (!cache || cache->locked) + return; + + /* Write it out and free it up if need be.*/ + if (cache->dirty) { + yaffs_wr_data_obj(cache->object, + cache->chunk_id, + cache->data, + cache->n_bytes, + 1); + + cache->dirty = 0; + } + + if (discard) + cache->object = NULL; +} + +static void yaffs_flush_file_cache(struct yaffs_obj *obj, int discard) +{ + struct yaffs_dev *dev = obj->my_dev; + int i; + struct yaffs_cache *cache; + int n_caches = obj->my_dev->param.n_caches; + + if (n_caches < 1) + return; + + + /* Find the chunks for this object and flush them. */ + for (i = 0; i < n_caches; i++) { + cache = &dev->cache[i]; + if (cache->object == obj) + yaffs_flush_single_cache(cache, discard); + } + +} + + +void yaffs_flush_whole_cache(struct yaffs_dev *dev, int discard) +{ + struct yaffs_obj *obj; + int n_caches = dev->param.n_caches; + int i; + + /* Find a dirty object in the cache and flush it... + * until there are no further dirty objects. + */ + do { + obj = NULL; + for (i = 0; i < n_caches && !obj; i++) { + if (dev->cache[i].object && dev->cache[i].dirty) + obj = dev->cache[i].object; + } + if (obj) + yaffs_flush_file_cache(obj, discard); + } while (obj); + +} + +/* Grab us an unused cache chunk for use. + * First look for an empty one. + * Then look for the least recently used non-dirty one. + * Then look for the least recently used dirty one...., flush and look again. + */ +static struct yaffs_cache *yaffs_grab_chunk_worker(struct yaffs_dev *dev) +{ + u32 i; + + if (dev->param.n_caches > 0) { + for (i = 0; i < dev->param.n_caches; i++) { + if (!dev->cache[i].object) + return &dev->cache[i]; + } + } + + return NULL; +} + +static struct yaffs_cache *yaffs_grab_chunk_cache(struct yaffs_dev *dev) +{ + struct yaffs_cache *cache; + int usage; + u32 i; + + if (dev->param.n_caches < 1) + return NULL; + + /* First look for an unused cache */ + + cache = yaffs_grab_chunk_worker(dev); + + if (cache) + return cache; + + /* + * Thery were all in use. + * Find the LRU cache and flush it if it is dirty. + */ + + usage = -1; + cache = NULL; + + for (i = 0; i < dev->param.n_caches; i++) { + if (dev->cache[i].object && + !dev->cache[i].locked && + (dev->cache[i].last_use < usage || !cache)) { + usage = dev->cache[i].last_use; + cache = &dev->cache[i]; + } + } + +#if 1 + yaffs_flush_single_cache(cache, 1); +#else + yaffs_flush_file_cache(cache->object, 1); + cache = yaffs_grab_chunk_worker(dev); +#endif + + return cache; +} + +/* Find a cached chunk */ +static struct yaffs_cache *yaffs_find_chunk_cache(const struct yaffs_obj *obj, + int chunk_id) +{ + struct yaffs_dev *dev = obj->my_dev; + u32 i; + + if (dev->param.n_caches < 1) + return NULL; + + for (i = 0; i < dev->param.n_caches; i++) { + if (dev->cache[i].object == obj && + dev->cache[i].chunk_id == chunk_id) { + dev->cache_hits++; + + return &dev->cache[i]; + } + } + return NULL; +} + +/* Mark the chunk for the least recently used algorithym */ +static void yaffs_use_cache(struct yaffs_dev *dev, struct yaffs_cache *cache, + int is_write) +{ + u32 i; + + if (dev->param.n_caches < 1) + return; + + if (dev->cache_last_use < 0 || + dev->cache_last_use > 100000000) { + /* Reset the cache usages */ + for (i = 1; i < dev->param.n_caches; i++) + dev->cache[i].last_use = 0; + + dev->cache_last_use = 0; + } + dev->cache_last_use++; + cache->last_use = dev->cache_last_use; + + if (is_write) + cache->dirty = 1; +} + +/* Invalidate a single cache page. + * Do this when a whole page gets written, + * ie the short cache for this page is no longer valid. + */ +static void yaffs_invalidate_chunk_cache(struct yaffs_obj *object, int chunk_id) +{ + struct yaffs_cache *cache; + + if (object->my_dev->param.n_caches > 0) { + cache = yaffs_find_chunk_cache(object, chunk_id); + + if (cache) + cache->object = NULL; + } +} + +/* Invalidate all the cache pages associated with this object + * Do this whenever ther file is deleted or resized. + */ +static void yaffs_invalidate_whole_cache(struct yaffs_obj *in) +{ + u32 i; + struct yaffs_dev *dev = in->my_dev; + + if (dev->param.n_caches > 0) { + /* Invalidate it. */ + for (i = 0; i < dev->param.n_caches; i++) { + if (dev->cache[i].object == in) + dev->cache[i].object = NULL; + } + } +} + +static void yaffs_unhash_obj(struct yaffs_obj *obj) +{ + int bucket; + struct yaffs_dev *dev = obj->my_dev; + + /* If it is still linked into the bucket list, free from the list */ + if (!list_empty(&obj->hash_link)) { + list_del_init(&obj->hash_link); + bucket = yaffs_hash_fn(obj->obj_id); + dev->obj_bucket[bucket].count--; + } +} + +/* FreeObject frees up a Object and puts it back on the free list */ +static void yaffs_free_obj(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev; + + if (!obj) { + BUG(); + return; + } + dev = obj->my_dev; + yaffs_trace(YAFFS_TRACE_OS, "FreeObject %p inode %p", + obj, obj->my_inode); + if (obj->parent) + BUG(); + if (!list_empty(&obj->siblings)) + BUG(); + + if (obj->my_inode) { + /* We're still hooked up to a cached inode. + * Don't delete now, but mark for later deletion + */ + obj->defered_free = 1; + return; + } + + yaffs_unhash_obj(obj); + + yaffs_free_raw_obj(dev, obj); + dev->n_obj--; + dev->checkpoint_blocks_required = 0; /* force recalculation */ +} + +void yaffs_handle_defered_free(struct yaffs_obj *obj) +{ + if (obj->defered_free) + yaffs_free_obj(obj); +} + +static int yaffs_generic_obj_del(struct yaffs_obj *in) +{ + /* Iinvalidate the file's data in the cache, without flushing. */ + yaffs_invalidate_whole_cache(in); + + if (in->my_dev->param.is_yaffs2 && in->parent != in->my_dev->del_dir) { + /* Move to unlinked directory so we have a deletion record */ + yaffs_change_obj_name(in, in->my_dev->del_dir, _Y("deleted"), 0, + 0); + } + + yaffs_remove_obj_from_dir(in); + yaffs_chunk_del(in->my_dev, in->hdr_chunk, 1, __LINE__); + in->hdr_chunk = 0; + + yaffs_free_obj(in); + return YAFFS_OK; + +} + +static void yaffs_soft_del_file(struct yaffs_obj *obj) +{ + if (!obj->deleted || + obj->variant_type != YAFFS_OBJECT_TYPE_FILE || + obj->soft_del) + return; + + if (obj->n_data_chunks <= 0) { + /* Empty file with no duplicate object headers, + * just delete it immediately */ + yaffs_free_tnode(obj->my_dev, obj->variant.file_variant.top); + obj->variant.file_variant.top = NULL; + yaffs_trace(YAFFS_TRACE_TRACING, + "yaffs: Deleting empty file %d", + obj->obj_id); + yaffs_generic_obj_del(obj); + } else { + yaffs_soft_del_worker(obj, + obj->variant.file_variant.top, + obj->variant. + file_variant.top_level, 0); + obj->soft_del = 1; + } +} + +/* Pruning removes any part of the file structure tree that is beyond the + * bounds of the file (ie that does not point to chunks). + * + * A file should only get pruned when its size is reduced. + * + * Before pruning, the chunks must be pulled from the tree and the + * level 0 tnode entries must be zeroed out. + * Could also use this for file deletion, but that's probably better handled + * by a special case. + * + * This function is recursive. For levels > 0 the function is called again on + * any sub-tree. For level == 0 we just check if the sub-tree has data. + * If there is no data in a subtree then it is pruned. + */ + +static struct yaffs_tnode *yaffs_prune_worker(struct yaffs_dev *dev, + struct yaffs_tnode *tn, u32 level, + int del0) +{ + int i; + int has_data; + + if (!tn) + return tn; + + has_data = 0; + + if (level > 0) { + for (i = 0; i < YAFFS_NTNODES_INTERNAL; i++) { + if (tn->internal[i]) { + tn->internal[i] = + yaffs_prune_worker(dev, + tn->internal[i], + level - 1, + (i == 0) ? del0 : 1); + } + + if (tn->internal[i]) + has_data++; + } + } else { + int tnode_size_u32 = dev->tnode_size / sizeof(u32); + u32 *map = (u32 *) tn; + + for (i = 0; !has_data && i < tnode_size_u32; i++) { + if (map[i]) + has_data++; + } + } + + if (has_data == 0 && del0) { + /* Free and return NULL */ + yaffs_free_tnode(dev, tn); + tn = NULL; + } + return tn; +} + +static int yaffs_prune_tree(struct yaffs_dev *dev, + struct yaffs_file_var *file_struct) +{ + int i; + int has_data; + int done = 0; + struct yaffs_tnode *tn; + + if (file_struct->top_level < 1) + return YAFFS_OK; + + file_struct->top = + yaffs_prune_worker(dev, file_struct->top, file_struct->top_level, 0); + + /* Now we have a tree with all the non-zero branches NULL but + * the height is the same as it was. + * Let's see if we can trim internal tnodes to shorten the tree. + * We can do this if only the 0th element in the tnode is in use + * (ie all the non-zero are NULL) + */ + + while (file_struct->top_level && !done) { + tn = file_struct->top; + + has_data = 0; + for (i = 1; i < YAFFS_NTNODES_INTERNAL; i++) { + if (tn->internal[i]) + has_data++; + } + + if (!has_data) { + file_struct->top = tn->internal[0]; + file_struct->top_level--; + yaffs_free_tnode(dev, tn); + } else { + done = 1; + } + } + + return YAFFS_OK; +} + +/*-------------------- End of File Structure functions.-------------------*/ + +/* alloc_empty_obj gets us a clean Object.*/ +static struct yaffs_obj *yaffs_alloc_empty_obj(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj = yaffs_alloc_raw_obj(dev); + + if (!obj) + return obj; + + dev->n_obj++; + + /* Now sweeten it up... */ + + memset(obj, 0, sizeof(struct yaffs_obj)); + obj->being_created = 1; + + obj->my_dev = dev; + obj->hdr_chunk = 0; + obj->variant_type = YAFFS_OBJECT_TYPE_UNKNOWN; + INIT_LIST_HEAD(&(obj->hard_links)); + INIT_LIST_HEAD(&(obj->hash_link)); + INIT_LIST_HEAD(&obj->siblings); + + /* Now make the directory sane */ + if (dev->root_dir) { + obj->parent = dev->root_dir; + list_add(&(obj->siblings), + &dev->root_dir->variant.dir_variant.children); + } + + /* Add it to the lost and found directory. + * NB Can't put root or lost-n-found in lost-n-found so + * check if lost-n-found exists first + */ + if (dev->lost_n_found) + yaffs_add_obj_to_dir(dev->lost_n_found, obj); + + obj->being_created = 0; + + dev->checkpoint_blocks_required = 0; /* force recalculation */ + + return obj; +} + +static int yaffs_find_nice_bucket(struct yaffs_dev *dev) +{ + int i; + int l = 999; + int lowest = 999999; + + /* Search for the shortest list or one that + * isn't too long. + */ + + for (i = 0; i < 10 && lowest > 4; i++) { + dev->bucket_finder++; + dev->bucket_finder %= YAFFS_NOBJECT_BUCKETS; + if (dev->obj_bucket[dev->bucket_finder].count < lowest) { + lowest = dev->obj_bucket[dev->bucket_finder].count; + l = dev->bucket_finder; + } + } + + return l; +} + +static int yaffs_new_obj_id(struct yaffs_dev *dev) +{ + int bucket = yaffs_find_nice_bucket(dev); + int found = 0; + struct list_head *i; + u32 n = (u32) bucket; + + /* + * Now find an object value that has not already been taken + * by scanning the list, incrementing each time by number of buckets. + */ + while (!found) { + found = 1; + n += YAFFS_NOBJECT_BUCKETS; + list_for_each(i, &dev->obj_bucket[bucket].list) { + /* Check if this value is already taken. */ + if (i && list_entry(i, struct yaffs_obj, + hash_link)->obj_id == n) + found = 0; + } + } + return n; +} + +static void yaffs_hash_obj(struct yaffs_obj *in) +{ + int bucket = yaffs_hash_fn(in->obj_id); + struct yaffs_dev *dev = in->my_dev; + + list_add(&in->hash_link, &dev->obj_bucket[bucket].list); + dev->obj_bucket[bucket].count++; +} + +struct yaffs_obj *yaffs_find_by_number(struct yaffs_dev *dev, u32 number) +{ + int bucket = yaffs_hash_fn(number); + struct list_head *i; + struct yaffs_obj *in; + + list_for_each(i, &dev->obj_bucket[bucket].list) { + /* Look if it is in the list */ + in = list_entry(i, struct yaffs_obj, hash_link); + if (in->obj_id == number) { + /* Don't show if it is defered free */ + if (in->defered_free) + return NULL; + return in; + } + } + + return NULL; +} + +static struct yaffs_obj *yaffs_new_obj(struct yaffs_dev *dev, int number, + enum yaffs_obj_type type) +{ + struct yaffs_obj *the_obj = NULL; + struct yaffs_tnode *tn = NULL; + + if (number < 0) + number = yaffs_new_obj_id(dev); + + if (type == YAFFS_OBJECT_TYPE_FILE) { + tn = yaffs_get_tnode(dev); + if (!tn) + return NULL; + } + + the_obj = yaffs_alloc_empty_obj(dev); + if (!the_obj) { + if (tn) + yaffs_free_tnode(dev, tn); + return NULL; + } + + the_obj->fake = 0; + the_obj->rename_allowed = 1; + the_obj->unlink_allowed = 1; + the_obj->obj_id = number; + yaffs_hash_obj(the_obj); + the_obj->variant_type = type; + yaffs_load_current_time(the_obj, 1, 1); + + switch (type) { + case YAFFS_OBJECT_TYPE_FILE: + the_obj->variant.file_variant.file_size = 0; + the_obj->variant.file_variant.stored_size = 0; + the_obj->variant.file_variant.shrink_size = + yaffs_max_file_size(dev); + the_obj->variant.file_variant.top_level = 0; + the_obj->variant.file_variant.top = tn; + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + INIT_LIST_HEAD(&the_obj->variant.dir_variant.children); + INIT_LIST_HEAD(&the_obj->variant.dir_variant.dirty); + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + case YAFFS_OBJECT_TYPE_HARDLINK: + case YAFFS_OBJECT_TYPE_SPECIAL: + /* No action required */ + break; + case YAFFS_OBJECT_TYPE_UNKNOWN: + /* todo this should not happen */ + break; + } + return the_obj; +} + +static struct yaffs_obj *yaffs_create_fake_dir(struct yaffs_dev *dev, + int number, u32 mode) +{ + + struct yaffs_obj *obj = + yaffs_new_obj(dev, number, YAFFS_OBJECT_TYPE_DIRECTORY); + + if (!obj) + return NULL; + + obj->fake = 1; /* it is fake so it might not use NAND */ + obj->rename_allowed = 0; + obj->unlink_allowed = 0; + obj->deleted = 0; + obj->unlinked = 0; + obj->yst_mode = mode; + obj->my_dev = dev; + obj->hdr_chunk = 0; /* Not a valid chunk. */ + return obj; + +} + + +static void yaffs_init_tnodes_and_objs(struct yaffs_dev *dev) +{ + int i; + + dev->n_obj = 0; + dev->n_tnodes = 0; + yaffs_init_raw_tnodes_and_objs(dev); + + for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) { + INIT_LIST_HEAD(&dev->obj_bucket[i].list); + dev->obj_bucket[i].count = 0; + } +} + +struct yaffs_obj *yaffs_find_or_create_by_number(struct yaffs_dev *dev, + int number, + enum yaffs_obj_type type) +{ + struct yaffs_obj *the_obj = NULL; + + if (number > 0) + the_obj = yaffs_find_by_number(dev, number); + + if (!the_obj) + the_obj = yaffs_new_obj(dev, number, type); + + return the_obj; + +} + +YCHAR *yaffs_clone_str(const YCHAR *str) +{ + YCHAR *new_str = NULL; + int len; + + if (!str) + str = _Y(""); + + len = strnlen(str, YAFFS_MAX_ALIAS_LENGTH); + new_str = kmalloc((len + 1) * sizeof(YCHAR), GFP_NOFS); + if (new_str) { + strncpy(new_str, str, len); + new_str[len] = 0; + } + return new_str; + +} +/* + *yaffs_update_parent() handles fixing a directories mtime and ctime when a new + * link (ie. name) is created or deleted in the directory. + * + * ie. + * create dir/a : update dir's mtime/ctime + * rm dir/a: update dir's mtime/ctime + * modify dir/a: don't update dir's mtimme/ctime + * + * This can be handled immediately or defered. Defering helps reduce the number + * of updates when many files in a directory are changed within a brief period. + * + * If the directory updating is defered then yaffs_update_dirty_dirs must be + * called periodically. + */ + +static void yaffs_update_parent(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev; + + if (!obj) + return; + dev = obj->my_dev; + obj->dirty = 1; + yaffs_load_current_time(obj, 0, 1); + if (dev->param.defered_dir_update) { + struct list_head *link = &obj->variant.dir_variant.dirty; + + if (list_empty(link)) { + list_add(link, &dev->dirty_dirs); + yaffs_trace(YAFFS_TRACE_BACKGROUND, + "Added object %d to dirty directories", + obj->obj_id); + } + + } else { + yaffs_update_oh(obj, NULL, 0, 0, 0, NULL); + } +} + +void yaffs_update_dirty_dirs(struct yaffs_dev *dev) +{ + struct list_head *link; + struct yaffs_obj *obj; + struct yaffs_dir_var *d_s; + union yaffs_obj_var *o_v; + + yaffs_trace(YAFFS_TRACE_BACKGROUND, "Update dirty directories"); + + while (!list_empty(&dev->dirty_dirs)) { + link = dev->dirty_dirs.next; + list_del_init(link); + + d_s = list_entry(link, struct yaffs_dir_var, dirty); + o_v = list_entry(d_s, union yaffs_obj_var, dir_variant); + obj = list_entry(o_v, struct yaffs_obj, variant); + + yaffs_trace(YAFFS_TRACE_BACKGROUND, "Update directory %d", + obj->obj_id); + + if (obj->dirty) + yaffs_update_oh(obj, NULL, 0, 0, 0, NULL); + } +} + +/* + * Mknod (create) a new object. + * equiv_obj only has meaning for a hard link; + * alias_str only has meaning for a symlink. + * rdev only has meaning for devices (a subset of special objects) + */ + +static struct yaffs_obj *yaffs_create_obj(enum yaffs_obj_type type, + struct yaffs_obj *parent, + const YCHAR *name, + u32 mode, + u32 uid, + u32 gid, + struct yaffs_obj *equiv_obj, + const YCHAR *alias_str, u32 rdev) +{ + struct yaffs_obj *in; + YCHAR *str = NULL; + struct yaffs_dev *dev = parent->my_dev; + + /* Check if the entry exists. + * If it does then fail the call since we don't want a dup. */ + if (yaffs_find_by_name(parent, name)) + return NULL; + + if (type == YAFFS_OBJECT_TYPE_SYMLINK) { + str = yaffs_clone_str(alias_str); + if (!str) + return NULL; + } + + in = yaffs_new_obj(dev, -1, type); + + if (!in) { + kfree(str); + return NULL; + } + + in->hdr_chunk = 0; + in->valid = 1; + in->variant_type = type; + + in->yst_mode = mode; + + yaffs_attribs_init(in, gid, uid, rdev); + + in->n_data_chunks = 0; + + yaffs_set_obj_name(in, name); + in->dirty = 1; + + yaffs_add_obj_to_dir(parent, in); + + in->my_dev = parent->my_dev; + + switch (type) { + case YAFFS_OBJECT_TYPE_SYMLINK: + in->variant.symlink_variant.alias = str; + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + in->variant.hardlink_variant.equiv_obj = equiv_obj; + in->variant.hardlink_variant.equiv_id = equiv_obj->obj_id; + list_add(&in->hard_links, &equiv_obj->hard_links); + break; + case YAFFS_OBJECT_TYPE_FILE: + case YAFFS_OBJECT_TYPE_DIRECTORY: + case YAFFS_OBJECT_TYPE_SPECIAL: + case YAFFS_OBJECT_TYPE_UNKNOWN: + /* do nothing */ + break; + } + + if (yaffs_update_oh(in, name, 0, 0, 0, NULL) < 0) { + /* Could not create the object header, fail */ + yaffs_del_obj(in); + in = NULL; + } + + if (in) + yaffs_update_parent(parent); + + return in; +} + +struct yaffs_obj *yaffs_create_file(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid) +{ + return yaffs_create_obj(YAFFS_OBJECT_TYPE_FILE, parent, name, mode, + uid, gid, NULL, NULL, 0); +} + +struct yaffs_obj *yaffs_create_dir(struct yaffs_obj *parent, const YCHAR *name, + u32 mode, u32 uid, u32 gid) +{ + return yaffs_create_obj(YAFFS_OBJECT_TYPE_DIRECTORY, parent, name, + mode, uid, gid, NULL, NULL, 0); +} + +struct yaffs_obj *yaffs_create_special(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid, u32 rdev) +{ + return yaffs_create_obj(YAFFS_OBJECT_TYPE_SPECIAL, parent, name, mode, + uid, gid, NULL, NULL, rdev); +} + +struct yaffs_obj *yaffs_create_symlink(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid, const YCHAR *alias) +{ + return yaffs_create_obj(YAFFS_OBJECT_TYPE_SYMLINK, parent, name, mode, + uid, gid, NULL, alias, 0); +} + +/* yaffs_link_obj returns the object id of the equivalent object.*/ +struct yaffs_obj *yaffs_link_obj(struct yaffs_obj *parent, const YCHAR * name, + struct yaffs_obj *equiv_obj) +{ + /* Get the real object in case we were fed a hard link obj */ + equiv_obj = yaffs_get_equivalent_obj(equiv_obj); + + if (yaffs_create_obj(YAFFS_OBJECT_TYPE_HARDLINK, + parent, name, 0, 0, 0, + equiv_obj, NULL, 0)) + return equiv_obj; + + return NULL; + +} + + + +/*---------------------- Block Management and Page Allocation -------------*/ + +static void yaffs_deinit_blocks(struct yaffs_dev *dev) +{ + if (dev->block_info_alt && dev->block_info) + vfree(dev->block_info); + else + kfree(dev->block_info); + + dev->block_info_alt = 0; + + dev->block_info = NULL; + + if (dev->chunk_bits_alt && dev->chunk_bits) + vfree(dev->chunk_bits); + else + kfree(dev->chunk_bits); + dev->chunk_bits_alt = 0; + dev->chunk_bits = NULL; +} + +static int yaffs_init_blocks(struct yaffs_dev *dev) +{ + int n_blocks = dev->internal_end_block - dev->internal_start_block + 1; + + dev->block_info = NULL; + dev->chunk_bits = NULL; + dev->alloc_block = -1; /* force it to get a new one */ + + /* If the first allocation strategy fails, thry the alternate one */ + dev->block_info = + kmalloc(n_blocks * sizeof(struct yaffs_block_info), GFP_NOFS); + if (!dev->block_info) { + dev->block_info = + vmalloc(n_blocks * sizeof(struct yaffs_block_info)); + dev->block_info_alt = 1; + } else { + dev->block_info_alt = 0; + } + + if (!dev->block_info) + goto alloc_error; + + /* Set up dynamic blockinfo stuff. Round up bytes. */ + dev->chunk_bit_stride = (dev->param.chunks_per_block + 7) / 8; + dev->chunk_bits = + kmalloc(dev->chunk_bit_stride * n_blocks, GFP_NOFS); + if (!dev->chunk_bits) { + dev->chunk_bits = + vmalloc(dev->chunk_bit_stride * n_blocks); + dev->chunk_bits_alt = 1; + } else { + dev->chunk_bits_alt = 0; + } + if (!dev->chunk_bits) + goto alloc_error; + + + memset(dev->block_info, 0, n_blocks * sizeof(struct yaffs_block_info)); + memset(dev->chunk_bits, 0, dev->chunk_bit_stride * n_blocks); + return YAFFS_OK; + +alloc_error: + yaffs_deinit_blocks(dev); + return YAFFS_FAIL; +} + + +void yaffs_block_became_dirty(struct yaffs_dev *dev, int block_no) +{ + struct yaffs_block_info *bi = yaffs_get_block_info(dev, block_no); + int erased_ok = 0; + u32 i; + + /* If the block is still healthy erase it and mark as clean. + * If the block has had a data failure, then retire it. + */ + + yaffs_trace(YAFFS_TRACE_GC | YAFFS_TRACE_ERASE, + "yaffs_block_became_dirty block %d state %d %s", + block_no, bi->block_state, + (bi->needs_retiring) ? "needs retiring" : ""); + + yaffs2_clear_oldest_dirty_seq(dev, bi); + + bi->block_state = YAFFS_BLOCK_STATE_DIRTY; + + /* If this is the block being garbage collected then stop gc'ing */ + if (block_no == (int)dev->gc_block) + dev->gc_block = 0; + + /* If this block is currently the best candidate for gc + * then drop as a candidate */ + if (block_no == (int)dev->gc_dirtiest) { + dev->gc_dirtiest = 0; + dev->gc_pages_in_use = 0; + } + + if (!bi->needs_retiring) { + yaffs2_checkpt_invalidate(dev); + erased_ok = yaffs_erase_block(dev, block_no); + if (!erased_ok) { + dev->n_erase_failures++; + yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS, + "**>> Erasure failed %d", block_no); + } + } + + /* Verify erasure if needed */ + if (erased_ok && + ((yaffs_trace_mask & YAFFS_TRACE_ERASE) || + !yaffs_skip_verification(dev))) { + for (i = 0; i < dev->param.chunks_per_block; i++) { + if (!yaffs_check_chunk_erased(dev, + block_no * dev->param.chunks_per_block + i)) { + yaffs_trace(YAFFS_TRACE_ERROR, + ">>Block %d erasure supposedly OK, but chunk %d not erased", + block_no, i); + } + } + } + + if (!erased_ok) { + /* We lost a block of free space */ + dev->n_free_chunks -= dev->param.chunks_per_block; + yaffs_retire_block(dev, block_no); + yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS, + "**>> Block %d retired", block_no); + return; + } + + /* Clean it up... */ + bi->block_state = YAFFS_BLOCK_STATE_EMPTY; + bi->seq_number = 0; + dev->n_erased_blocks++; + bi->pages_in_use = 0; + bi->soft_del_pages = 0; + bi->has_shrink_hdr = 0; + bi->skip_erased_check = 1; /* Clean, so no need to check */ + bi->gc_prioritise = 0; + bi->has_summary = 0; + + yaffs_clear_chunk_bits(dev, block_no); + + yaffs_trace(YAFFS_TRACE_ERASE, "Erased block %d", block_no); +} + +static inline int yaffs_gc_process_chunk(struct yaffs_dev *dev, + struct yaffs_block_info *bi, + int old_chunk, u8 *buffer) +{ + int new_chunk; + int mark_flash = 1; + struct yaffs_ext_tags tags; + struct yaffs_obj *object; + int matching_chunk; + int ret_val = YAFFS_OK; + + memset(&tags, 0, sizeof(tags)); + yaffs_rd_chunk_tags_nand(dev, old_chunk, + buffer, &tags); + object = yaffs_find_by_number(dev, tags.obj_id); + + yaffs_trace(YAFFS_TRACE_GC_DETAIL, + "Collecting chunk in block %d, %d %d %d ", + dev->gc_chunk, tags.obj_id, + tags.chunk_id, tags.n_bytes); + + if (object && !yaffs_skip_verification(dev)) { + if (tags.chunk_id == 0) + matching_chunk = + object->hdr_chunk; + else if (object->soft_del) + /* Defeat the test */ + matching_chunk = old_chunk; + else + matching_chunk = + yaffs_find_chunk_in_file + (object, tags.chunk_id, + NULL); + + if (old_chunk != matching_chunk) + yaffs_trace(YAFFS_TRACE_ERROR, + "gc: page in gc mismatch: %d %d %d %d", + old_chunk, + matching_chunk, + tags.obj_id, + tags.chunk_id); + } + + if (!object) { + yaffs_trace(YAFFS_TRACE_ERROR, + "page %d in gc has no object: %d %d %d ", + old_chunk, + tags.obj_id, tags.chunk_id, + tags.n_bytes); + } + + if (object && + object->deleted && + object->soft_del && tags.chunk_id != 0) { + /* Data chunk in a soft deleted file, + * throw it away. + * It's a soft deleted data chunk, + * No need to copy this, just forget + * about it and fix up the object. + */ + + /* Free chunks already includes + * softdeleted chunks, how ever this + * chunk is going to soon be really + * deleted which will increment free + * chunks. We have to decrement free + * chunks so this works out properly. + */ + dev->n_free_chunks--; + bi->soft_del_pages--; + + object->n_data_chunks--; + if (object->n_data_chunks <= 0) { + /* remeber to clean up obj */ + dev->gc_cleanup_list[dev->n_clean_ups] = tags.obj_id; + dev->n_clean_ups++; + } + mark_flash = 0; + } else if (object) { + /* It's either a data chunk in a live + * file or an ObjectHeader, so we're + * interested in it. + * NB Need to keep the ObjectHeaders of + * deleted files until the whole file + * has been deleted off + */ + tags.serial_number++; + dev->n_gc_copies++; + + if (tags.chunk_id == 0) { + /* It is an object Id, + * We need to nuke the shrinkheader flags since its + * work is done. + * Also need to clean up shadowing. + * NB We don't want to do all the work of translating + * object header endianism back and forth so we leave + * the oh endian in its stored order. + */ + + struct yaffs_obj_hdr *oh; + oh = (struct yaffs_obj_hdr *) buffer; + + oh->is_shrink = 0; + tags.extra_is_shrink = 0; + oh->shadows_obj = 0; + oh->inband_shadowed_obj_id = 0; + tags.extra_shadows = 0; + + /* Update file size */ + if (object->variant_type == YAFFS_OBJECT_TYPE_FILE) { + yaffs_oh_size_load(dev, oh, + object->variant.file_variant.stored_size, 1); + tags.extra_file_size = + object->variant.file_variant.stored_size; + } + + yaffs_verify_oh(object, oh, &tags, 1); + new_chunk = + yaffs_write_new_chunk(dev, (u8 *) oh, &tags, 1); + } else { + new_chunk = + yaffs_write_new_chunk(dev, buffer, &tags, 1); + } + + if (new_chunk < 0) { + ret_val = YAFFS_FAIL; + } else { + + /* Now fix up the Tnodes etc. */ + + if (tags.chunk_id == 0) { + /* It's a header */ + object->hdr_chunk = new_chunk; + object->serial = tags.serial_number; + } else { + /* It's a data chunk */ + yaffs_put_chunk_in_file(object, tags.chunk_id, + new_chunk, 0); + } + } + } + if (ret_val == YAFFS_OK) + yaffs_chunk_del(dev, old_chunk, mark_flash, __LINE__); + return ret_val; +} + +static int yaffs_gc_block(struct yaffs_dev *dev, int block, int whole_block) +{ + int old_chunk; + int ret_val = YAFFS_OK; + u32 i; + int is_checkpt_block; + int max_copies; + int chunks_before = yaffs_get_erased_chunks(dev); + int chunks_after; + struct yaffs_block_info *bi = yaffs_get_block_info(dev, block); + + is_checkpt_block = (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT); + + yaffs_trace(YAFFS_TRACE_TRACING, + "Collecting block %d, in use %d, shrink %d, whole_block %d", + block, bi->pages_in_use, bi->has_shrink_hdr, + whole_block); + + /*yaffs_verify_free_chunks(dev); */ + + if (bi->block_state == YAFFS_BLOCK_STATE_FULL) + bi->block_state = YAFFS_BLOCK_STATE_COLLECTING; + + bi->has_shrink_hdr = 0; /* clear the flag so that the block can erase */ + + dev->gc_disable = 1; + + yaffs_summary_gc(dev, block); + + if (is_checkpt_block || !yaffs_still_some_chunks(dev, block)) { + yaffs_trace(YAFFS_TRACE_TRACING, + "Collecting block %d that has no chunks in use", + block); + yaffs_block_became_dirty(dev, block); + } else { + + u8 *buffer = yaffs_get_temp_buffer(dev); + + yaffs_verify_blk(dev, bi, block); + + max_copies = (whole_block) ? dev->param.chunks_per_block : 5; + old_chunk = block * dev->param.chunks_per_block + dev->gc_chunk; + + for (/* init already done */ ; + ret_val == YAFFS_OK && + dev->gc_chunk < dev->param.chunks_per_block && + (bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) && + max_copies > 0; + dev->gc_chunk++, old_chunk++) { + if (yaffs_check_chunk_bit(dev, block, dev->gc_chunk)) { + /* Page is in use and might need to be copied */ + max_copies--; + ret_val = yaffs_gc_process_chunk(dev, bi, + old_chunk, buffer); + } + } + yaffs_release_temp_buffer(dev, buffer); + } + + yaffs_verify_collected_blk(dev, bi, block); + + if (bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) { + /* + * The gc did not complete. Set block state back to FULL + * because checkpointing does not restore gc. + */ + bi->block_state = YAFFS_BLOCK_STATE_FULL; + } else { + /* The gc completed. */ + /* Do any required cleanups */ + for (i = 0; i < dev->n_clean_ups; i++) { + /* Time to delete the file too */ + struct yaffs_obj *object = + yaffs_find_by_number(dev, dev->gc_cleanup_list[i]); + if (object) { + yaffs_free_tnode(dev, + object->variant.file_variant.top); + object->variant.file_variant.top = NULL; + yaffs_trace(YAFFS_TRACE_GC, + "yaffs: About to finally delete object %d", + object->obj_id); + yaffs_generic_obj_del(object); + object->my_dev->n_deleted_files--; + } + + } + chunks_after = yaffs_get_erased_chunks(dev); + if (chunks_before >= chunks_after) + yaffs_trace(YAFFS_TRACE_GC, + "gc did not increase free chunks before %d after %d", + chunks_before, chunks_after); + dev->gc_block = 0; + dev->gc_chunk = 0; + dev->n_clean_ups = 0; + } + + dev->gc_disable = 0; + + return ret_val; +} + +/* + * find_gc_block() selects the dirtiest block (or close enough) + * for garbage collection. + */ + +static unsigned yaffs_find_gc_block(struct yaffs_dev *dev, + int aggressive, int background) +{ + u32 i; + u32 iterations; + u32 selected = 0; + int prioritised = 0; + int prioritised_exist = 0; + struct yaffs_block_info *bi; + u32 threshold; + + /* First let's see if we need to grab a prioritised block */ + if (dev->has_pending_prioritised_gc && !aggressive) { + dev->gc_dirtiest = 0; + bi = dev->block_info; + for (i = dev->internal_start_block; + i <= dev->internal_end_block && !selected; i++) { + + if (bi->gc_prioritise) { + prioritised_exist = 1; + if (bi->block_state == YAFFS_BLOCK_STATE_FULL && + yaffs_block_ok_for_gc(dev, bi)) { + selected = i; + prioritised = 1; + } + } + bi++; + } + + /* + * If there is a prioritised block and none was selected then + * this happened because there is at least one old dirty block + * gumming up the works. Let's gc the oldest dirty block. + */ + + if (prioritised_exist && + !selected && dev->oldest_dirty_block > 0) + selected = dev->oldest_dirty_block; + + if (!prioritised_exist) /* None found, so we can clear this */ + dev->has_pending_prioritised_gc = 0; + } + + /* If we're doing aggressive GC then we are happy to take a less-dirty + * block, and search harder. + * else (leasurely gc), then we only bother to do this if the + * block has only a few pages in use. + */ + + if (!selected) { + u32 pages_used; + int n_blocks = + dev->internal_end_block - dev->internal_start_block + 1; + if (aggressive) { + threshold = dev->param.chunks_per_block; + iterations = n_blocks; + } else { + u32 max_threshold; + + if (background) + max_threshold = dev->param.chunks_per_block / 2; + else + max_threshold = dev->param.chunks_per_block / 8; + + if (max_threshold < YAFFS_GC_PASSIVE_THRESHOLD) + max_threshold = YAFFS_GC_PASSIVE_THRESHOLD; + + threshold = background ? (dev->gc_not_done + 2) * 2 : 0; + if (threshold < YAFFS_GC_PASSIVE_THRESHOLD) + threshold = YAFFS_GC_PASSIVE_THRESHOLD; + if (threshold > max_threshold) + threshold = max_threshold; + + iterations = n_blocks / 16 + 1; + if (iterations > 100) + iterations = 100; + } + + for (i = 0; + i < iterations && + (dev->gc_dirtiest < 1 || + dev->gc_pages_in_use > YAFFS_GC_GOOD_ENOUGH); + i++) { + dev->gc_block_finder++; + if (dev->gc_block_finder < dev->internal_start_block || + dev->gc_block_finder > dev->internal_end_block) + dev->gc_block_finder = + dev->internal_start_block; + + bi = yaffs_get_block_info(dev, dev->gc_block_finder); + + pages_used = bi->pages_in_use - bi->soft_del_pages; + + if (bi->block_state == YAFFS_BLOCK_STATE_FULL && + pages_used < dev->param.chunks_per_block && + (dev->gc_dirtiest < 1 || + pages_used < dev->gc_pages_in_use) && + yaffs_block_ok_for_gc(dev, bi)) { + dev->gc_dirtiest = dev->gc_block_finder; + dev->gc_pages_in_use = pages_used; + } + } + + if (dev->gc_dirtiest > 0 && dev->gc_pages_in_use <= threshold) + selected = dev->gc_dirtiest; + } + + /* + * If nothing has been selected for a while, try the oldest dirty + * because that's gumming up the works. + */ + + if (!selected && dev->param.is_yaffs2 && + dev->gc_not_done >= (background ? 10 : 20)) { + yaffs2_find_oldest_dirty_seq(dev); + if (dev->oldest_dirty_block > 0) { + selected = dev->oldest_dirty_block; + dev->gc_dirtiest = selected; + dev->oldest_dirty_gc_count++; + bi = yaffs_get_block_info(dev, selected); + dev->gc_pages_in_use = + bi->pages_in_use - bi->soft_del_pages; + } else { + dev->gc_not_done = 0; + } + } + + if (selected) { + yaffs_trace(YAFFS_TRACE_GC, + "GC Selected block %d with %d free, prioritised:%d", + selected, + dev->param.chunks_per_block - dev->gc_pages_in_use, + prioritised); + + dev->n_gc_blocks++; + if (background) + dev->bg_gcs++; + + dev->gc_dirtiest = 0; + dev->gc_pages_in_use = 0; + dev->gc_not_done = 0; + if (dev->refresh_skip > 0) + dev->refresh_skip--; + } else { + dev->gc_not_done++; + yaffs_trace(YAFFS_TRACE_GC, + "GC none: finder %d skip %d threshold %d dirtiest %d using %d oldest %d%s", + dev->gc_block_finder, dev->gc_not_done, threshold, + dev->gc_dirtiest, dev->gc_pages_in_use, + dev->oldest_dirty_block, background ? " bg" : ""); + } + + return selected; +} + +/* New garbage collector + * If we're very low on erased blocks then we do aggressive garbage collection + * otherwise we do "leasurely" garbage collection. + * Aggressive gc looks further (whole array) and will accept less dirty blocks. + * Passive gc only inspects smaller areas and only accepts more dirty blocks. + * + * The idea is to help clear out space in a more spread-out manner. + * Dunno if it really does anything useful. + */ +static int yaffs_check_gc(struct yaffs_dev *dev, int background) +{ + int aggressive = 0; + int gc_ok = YAFFS_OK; + int max_tries = 0; + int min_erased; + int erased_chunks; + int checkpt_block_adjust; + + if (dev->param.gc_control_fn && + (dev->param.gc_control_fn(dev) & 1) == 0) + return YAFFS_OK; + + if (dev->gc_disable) + /* Bail out so we don't get recursive gc */ + return YAFFS_OK; + + /* This loop should pass the first time. + * Only loops here if the collection does not increase space. + */ + + do { + max_tries++; + + checkpt_block_adjust = yaffs_calc_checkpt_blocks_required(dev); + + min_erased = + dev->param.n_reserved_blocks + checkpt_block_adjust + 1; + erased_chunks = + dev->n_erased_blocks * dev->param.chunks_per_block; + + /* If we need a block soon then do aggressive gc. */ + if (dev->n_erased_blocks < min_erased) + aggressive = 1; + else { + if (!background + && erased_chunks > (dev->n_free_chunks / 4)) + break; + + if (dev->gc_skip > 20) + dev->gc_skip = 20; + if (erased_chunks < dev->n_free_chunks / 2 || + dev->gc_skip < 1 || background) + aggressive = 0; + else { + dev->gc_skip--; + break; + } + } + + dev->gc_skip = 5; + + /* If we don't already have a block being gc'd then see if we + * should start another */ + + if (dev->gc_block < 1 && !aggressive) { + dev->gc_block = yaffs2_find_refresh_block(dev); + dev->gc_chunk = 0; + dev->n_clean_ups = 0; + } + if (dev->gc_block < 1) { + dev->gc_block = + yaffs_find_gc_block(dev, aggressive, background); + dev->gc_chunk = 0; + dev->n_clean_ups = 0; + } + + if (dev->gc_block > 0) { + dev->all_gcs++; + if (!aggressive) + dev->passive_gc_count++; + + yaffs_trace(YAFFS_TRACE_GC, + "yaffs: GC n_erased_blocks %d aggressive %d", + dev->n_erased_blocks, aggressive); + + gc_ok = yaffs_gc_block(dev, dev->gc_block, aggressive); + } + + if (dev->n_erased_blocks < (int)dev->param.n_reserved_blocks && + dev->gc_block > 0) { + yaffs_trace(YAFFS_TRACE_GC, + "yaffs: GC !!!no reclaim!!! n_erased_blocks %d after try %d block %d", + dev->n_erased_blocks, max_tries, + dev->gc_block); + } + } while ((dev->n_erased_blocks < (int)dev->param.n_reserved_blocks) && + (dev->gc_block > 0) && (max_tries < 2)); + + return aggressive ? gc_ok : YAFFS_OK; +} + +/* + * yaffs_bg_gc() + * Garbage collects. Intended to be called from a background thread. + * Returns non-zero if at least half the free chunks are erased. + */ +int yaffs_bg_gc(struct yaffs_dev *dev, unsigned urgency) +{ + int erased_chunks = dev->n_erased_blocks * dev->param.chunks_per_block; + + yaffs_trace(YAFFS_TRACE_BACKGROUND, "Background gc %u", urgency); + + yaffs_check_gc(dev, 1); + return erased_chunks > dev->n_free_chunks / 2; +} + +/*-------------------- Data file manipulation -----------------*/ + +static int yaffs_rd_data_obj(struct yaffs_obj *in, int inode_chunk, u8 * buffer) +{ + int nand_chunk = yaffs_find_chunk_in_file(in, inode_chunk, NULL); + + if (nand_chunk >= 0) + return yaffs_rd_chunk_tags_nand(in->my_dev, nand_chunk, + buffer, NULL); + else { + yaffs_trace(YAFFS_TRACE_NANDACCESS, + "Chunk %d not found zero instead", + nand_chunk); + /* get sane (zero) data if you read a hole */ + memset(buffer, 0, in->my_dev->data_bytes_per_chunk); + return 0; + } + +} + +void yaffs_chunk_del(struct yaffs_dev *dev, int chunk_id, int mark_flash, + int lyn) +{ + int block; + int page; + struct yaffs_ext_tags tags; + struct yaffs_block_info *bi; + + if (chunk_id <= 0) + return; + + dev->n_deletions++; + block = chunk_id / dev->param.chunks_per_block; + page = chunk_id % dev->param.chunks_per_block; + + if (!yaffs_check_chunk_bit(dev, block, page)) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Deleting invalid chunk %d", chunk_id); + + bi = yaffs_get_block_info(dev, block); + + yaffs2_update_oldest_dirty_seq(dev, block, bi); + + yaffs_trace(YAFFS_TRACE_DELETION, + "line %d delete of chunk %d", + lyn, chunk_id); + + if (!dev->param.is_yaffs2 && mark_flash && + bi->block_state != YAFFS_BLOCK_STATE_COLLECTING) { + + memset(&tags, 0, sizeof(tags)); + tags.is_deleted = 1; + yaffs_wr_chunk_tags_nand(dev, chunk_id, NULL, &tags); + yaffs_handle_chunk_update(dev, chunk_id, &tags); + } else { + dev->n_unmarked_deletions++; + } + + /* Pull out of the management area. + * If the whole block became dirty, this will kick off an erasure. + */ + if (bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING || + bi->block_state == YAFFS_BLOCK_STATE_FULL || + bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN || + bi->block_state == YAFFS_BLOCK_STATE_COLLECTING) { + dev->n_free_chunks++; + yaffs_clear_chunk_bit(dev, block, page); + bi->pages_in_use--; + + if (bi->pages_in_use == 0 && + !bi->has_shrink_hdr && + bi->block_state != YAFFS_BLOCK_STATE_ALLOCATING && + bi->block_state != YAFFS_BLOCK_STATE_NEEDS_SCAN) { + yaffs_block_became_dirty(dev, block); + } + } +} + +static int yaffs_wr_data_obj(struct yaffs_obj *in, int inode_chunk, + const u8 *buffer, int n_bytes, int use_reserve) +{ + /* Find old chunk Need to do this to get serial number + * Write new one and patch into tree. + * Invalidate old tags. + */ + + int prev_chunk_id; + struct yaffs_ext_tags prev_tags; + int new_chunk_id; + struct yaffs_ext_tags new_tags; + struct yaffs_dev *dev = in->my_dev; + loff_t endpos; + + yaffs_check_gc(dev, 0); + + /* Get the previous chunk at this location in the file if it exists. + * If it does not exist then put a zero into the tree. This creates + * the tnode now, rather than later when it is harder to clean up. + */ + prev_chunk_id = yaffs_find_chunk_in_file(in, inode_chunk, &prev_tags); + if (prev_chunk_id < 1 && + !yaffs_put_chunk_in_file(in, inode_chunk, 0, 0)) + return 0; + + /* Set up new tags */ + memset(&new_tags, 0, sizeof(new_tags)); + + new_tags.chunk_id = inode_chunk; + new_tags.obj_id = in->obj_id; + new_tags.serial_number = + (prev_chunk_id > 0) ? prev_tags.serial_number + 1 : 1; + new_tags.n_bytes = n_bytes; + + if (n_bytes < 1 || n_bytes > (int)dev->data_bytes_per_chunk) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Writing %d bytes to chunk!!!!!!!!!", + n_bytes); + BUG(); + } + + /* + * If this is a data chunk and the write goes past the end of the stored + * size then update the stored_size. + */ + if (inode_chunk > 0) { + endpos = (inode_chunk - 1) * dev->data_bytes_per_chunk + + n_bytes; + if (in->variant.file_variant.stored_size < endpos) + in->variant.file_variant.stored_size = endpos; + } + + new_chunk_id = + yaffs_write_new_chunk(dev, buffer, &new_tags, use_reserve); + + if (new_chunk_id > 0) { + yaffs_put_chunk_in_file(in, inode_chunk, new_chunk_id, 0); + + if (prev_chunk_id > 0) + yaffs_chunk_del(dev, prev_chunk_id, 1, __LINE__); + + yaffs_verify_file_sane(in); + } + return new_chunk_id; +} + + + +static int yaffs_do_xattrib_mod(struct yaffs_obj *obj, int set, + const YCHAR *name, const void *value, int size, + int flags) +{ + struct yaffs_xattr_mod xmod; + int result; + + xmod.set = set; + xmod.name = name; + xmod.data = value; + xmod.size = size; + xmod.flags = flags; + xmod.result = -ENOSPC; + + result = yaffs_update_oh(obj, NULL, 0, 0, 0, &xmod); + + if (result > 0) + return xmod.result; + else + return -ENOSPC; +} + +static int yaffs_apply_xattrib_mod(struct yaffs_obj *obj, char *buffer, + struct yaffs_xattr_mod *xmod) +{ + int retval = 0; + int x_offs = sizeof(struct yaffs_obj_hdr); + struct yaffs_dev *dev = obj->my_dev; + int x_size = dev->data_bytes_per_chunk - sizeof(struct yaffs_obj_hdr); + char *x_buffer = buffer + x_offs; + + if (xmod->set) + retval = + nval_set(dev, x_buffer, x_size, xmod->name, xmod->data, + xmod->size, xmod->flags); + else + retval = nval_del(dev, x_buffer, x_size, xmod->name); + + obj->has_xattr = nval_hasvalues(dev, x_buffer, x_size); + obj->xattr_known = 1; + xmod->result = retval; + + return retval; +} + +static int yaffs_do_xattrib_fetch(struct yaffs_obj *obj, const YCHAR *name, + void *value, int size) +{ + char *buffer = NULL; + int result; + struct yaffs_ext_tags tags; + struct yaffs_dev *dev = obj->my_dev; + int x_offs = sizeof(struct yaffs_obj_hdr); + int x_size = dev->data_bytes_per_chunk - sizeof(struct yaffs_obj_hdr); + char *x_buffer; + int retval = 0; + + if (obj->hdr_chunk < 1) + return -ENODATA; + + /* If we know that the object has no xattribs then don't do all the + * reading and parsing. + */ + if (obj->xattr_known && !obj->has_xattr) { + if (name) + return -ENODATA; + else + return 0; + } + + buffer = (char *)yaffs_get_temp_buffer(dev); + if (!buffer) + return -ENOMEM; + + result = + yaffs_rd_chunk_tags_nand(dev, obj->hdr_chunk, (u8 *) buffer, &tags); + + if (result != YAFFS_OK) + retval = -ENOENT; + else { + x_buffer = buffer + x_offs; + + if (!obj->xattr_known) { + obj->has_xattr = nval_hasvalues(dev, x_buffer, x_size); + obj->xattr_known = 1; + } + + if (name) + retval = nval_get(dev, x_buffer, x_size, + name, value, size); + else + retval = nval_list(dev, x_buffer, x_size, value, size); + } + yaffs_release_temp_buffer(dev, (u8 *) buffer); + return retval; +} + +int yaffs_set_xattrib(struct yaffs_obj *obj, const YCHAR * name, + const void *value, int size, int flags) +{ + return yaffs_do_xattrib_mod(obj, 1, name, value, size, flags); +} + +int yaffs_remove_xattrib(struct yaffs_obj *obj, const YCHAR * name) +{ + return yaffs_do_xattrib_mod(obj, 0, name, NULL, 0, 0); +} + +int yaffs_get_xattrib(struct yaffs_obj *obj, const YCHAR * name, void *value, + int size) +{ + return yaffs_do_xattrib_fetch(obj, name, value, size); +} + +int yaffs_list_xattrib(struct yaffs_obj *obj, char *buffer, int size) +{ + return yaffs_do_xattrib_fetch(obj, NULL, buffer, size); +} + +static void yaffs_check_obj_details_loaded(struct yaffs_obj *in) +{ + u8 *buf; + struct yaffs_obj_hdr *oh; + struct yaffs_dev *dev; + struct yaffs_ext_tags tags; + int result; + + if (!in || !in->lazy_loaded || in->hdr_chunk < 1) + return; + + dev = in->my_dev; + buf = yaffs_get_temp_buffer(dev); + + result = yaffs_rd_chunk_tags_nand(dev, in->hdr_chunk, buf, &tags); + + if (result == YAFFS_FAIL) + return; + + oh = (struct yaffs_obj_hdr *)buf; + + yaffs_do_endian_oh(dev, oh); + + in->lazy_loaded = 0; + in->yst_mode = oh->yst_mode; + yaffs_load_attribs(in, oh); + yaffs_set_obj_name_from_oh(in, oh); + + if (in->variant_type == YAFFS_OBJECT_TYPE_SYMLINK) + in->variant.symlink_variant.alias = + yaffs_clone_str(oh->alias); + yaffs_release_temp_buffer(dev, buf); +} + +/* UpdateObjectHeader updates the header on NAND for an object. + * If name is not NULL, then that new name is used. + * + * We're always creating the obj header from scratch (except reading + * the old name) so first set up in cpu endianness then run it through + * endian fixing at the end. + * + * However, a twist: If there are xattribs we leave them as they were. + * + * Careful! The buffer holds the whole chunk. Part of the chunk holds the + * object header and the rest holds the xattribs, therefore we use a buffer + * pointer and an oh pointer to point to the same memory. + */ + +int yaffs_update_oh(struct yaffs_obj *in, const YCHAR *name, int force, + int is_shrink, int shadows, struct yaffs_xattr_mod *xmod) +{ + + struct yaffs_block_info *bi; + struct yaffs_dev *dev = in->my_dev; + int prev_chunk_id; + int ret_val = 0; + int result = 0; + int new_chunk_id; + struct yaffs_ext_tags new_tags; + struct yaffs_ext_tags old_tags; + const YCHAR *alias = NULL; + u8 *buffer = NULL; + YCHAR old_name[YAFFS_MAX_NAME_LENGTH + 1]; + struct yaffs_obj_hdr *oh = NULL; + loff_t file_size = 0; + + strcpy(old_name, _Y("silly old name")); + + if (in->fake && in != dev->root_dir && !force && !xmod) + return ret_val; + + yaffs_check_gc(dev, 0); + yaffs_check_obj_details_loaded(in); + + buffer = yaffs_get_temp_buffer(in->my_dev); + oh = (struct yaffs_obj_hdr *)buffer; + + prev_chunk_id = in->hdr_chunk; + + if (prev_chunk_id > 0) { + /* Access the old obj header just to read the name. */ + result = yaffs_rd_chunk_tags_nand(dev, prev_chunk_id, + buffer, &old_tags); + if (result == YAFFS_OK) { + yaffs_verify_oh(in, oh, &old_tags, 0); + memcpy(old_name, oh->name, sizeof(oh->name)); + + /* + * NB We only wipe the object header area because the rest of + * the buffer might contain xattribs. + */ + memset(oh, 0xff, sizeof(*oh)); + } + } else { + memset(buffer, 0xff, dev->data_bytes_per_chunk); + } + + oh->type = in->variant_type; + oh->yst_mode = in->yst_mode; + oh->shadows_obj = oh->inband_shadowed_obj_id = shadows; + + yaffs_load_attribs_oh(oh, in); + + if (in->parent) + oh->parent_obj_id = in->parent->obj_id; + else + oh->parent_obj_id = 0; + + if (name && *name) { + memset(oh->name, 0, sizeof(oh->name)); + yaffs_load_oh_from_name(dev, oh->name, name); + } else if (prev_chunk_id > 0) { + memcpy(oh->name, old_name, sizeof(oh->name)); + } else { + memset(oh->name, 0, sizeof(oh->name)); + } + + oh->is_shrink = is_shrink; + + switch (in->variant_type) { + case YAFFS_OBJECT_TYPE_UNKNOWN: + /* Should not happen */ + break; + case YAFFS_OBJECT_TYPE_FILE: + if (oh->parent_obj_id != YAFFS_OBJECTID_DELETED && + oh->parent_obj_id != YAFFS_OBJECTID_UNLINKED) + file_size = in->variant.file_variant.stored_size; + yaffs_oh_size_load(dev, oh, file_size, 0); + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + oh->equiv_id = in->variant.hardlink_variant.equiv_id; + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + alias = in->variant.symlink_variant.alias; + if (!alias) + alias = _Y("no alias"); + strncpy(oh->alias, alias, YAFFS_MAX_ALIAS_LENGTH); + oh->alias[YAFFS_MAX_ALIAS_LENGTH] = 0; + break; + } + + /* process any xattrib modifications */ + if (xmod) + yaffs_apply_xattrib_mod(in, (char *)buffer, xmod); + + /* Tags */ + memset(&new_tags, 0, sizeof(new_tags)); + in->serial++; + new_tags.chunk_id = 0; + new_tags.obj_id = in->obj_id; + new_tags.serial_number = in->serial; + + /* Add extra info for file header */ + new_tags.extra_available = 1; + new_tags.extra_parent_id = oh->parent_obj_id; + new_tags.extra_file_size = file_size; + new_tags.extra_is_shrink = oh->is_shrink; + new_tags.extra_equiv_id = oh->equiv_id; + new_tags.extra_shadows = (oh->shadows_obj > 0) ? 1 : 0; + new_tags.extra_obj_type = in->variant_type; + + /* Now endian swizzle the oh if needed. */ + yaffs_do_endian_oh(dev, oh); + + yaffs_verify_oh(in, oh, &new_tags, 1); + + /* Create new chunk in NAND */ + new_chunk_id = + yaffs_write_new_chunk(dev, buffer, &new_tags, + (prev_chunk_id > 0) ? 1 : 0); + + if (buffer) + yaffs_release_temp_buffer(dev, buffer); + + if (new_chunk_id < 0) + return new_chunk_id; + + in->hdr_chunk = new_chunk_id; + + if (prev_chunk_id > 0) + yaffs_chunk_del(dev, prev_chunk_id, 1, __LINE__); + + if (!yaffs_obj_cache_dirty(in)) + in->dirty = 0; + + /* If this was a shrink, then mark the block + * that the chunk lives on */ + if (is_shrink) { + bi = yaffs_get_block_info(in->my_dev, + new_chunk_id / + in->my_dev->param.chunks_per_block); + bi->has_shrink_hdr = 1; + } + + + return new_chunk_id; +} + +/*--------------------- File read/write ------------------------ + * Read and write have very similar structures. + * In general the read/write has three parts to it + * An incomplete chunk to start with (if the read/write is not chunk-aligned) + * Some complete chunks + * An incomplete chunk to end off with + * + * Curve-balls: the first chunk might also be the last chunk. + */ + +int yaffs_file_rd(struct yaffs_obj *in, u8 * buffer, loff_t offset, int n_bytes) +{ + int chunk; + u32 start; + int n_copy; + int n = n_bytes; + int n_done = 0; + struct yaffs_cache *cache; + struct yaffs_dev *dev; + + dev = in->my_dev; + + while (n > 0) { + yaffs_addr_to_chunk(dev, offset, &chunk, &start); + chunk++; + + /* OK now check for the curveball where the start and end are in + * the same chunk. + */ + if ((start + n) < dev->data_bytes_per_chunk) + n_copy = n; + else + n_copy = dev->data_bytes_per_chunk - start; + + cache = yaffs_find_chunk_cache(in, chunk); + + /* If the chunk is already in the cache or it is less than + * a whole chunk or we're using inband tags then use the cache + * (if there is caching) else bypass the cache. + */ + if (cache || n_copy != (int)dev->data_bytes_per_chunk || + dev->param.inband_tags) { + if (dev->param.n_caches > 0) { + + /* If we can't find the data in the cache, + * then load it up. */ + + if (!cache) { + cache = + yaffs_grab_chunk_cache(in->my_dev); + cache->object = in; + cache->chunk_id = chunk; + cache->dirty = 0; + cache->locked = 0; + yaffs_rd_data_obj(in, chunk, + cache->data); + cache->n_bytes = 0; + } + + yaffs_use_cache(dev, cache, 0); + + cache->locked = 1; + + memcpy(buffer, &cache->data[start], n_copy); + + cache->locked = 0; + } else { + /* Read into the local buffer then copy.. */ + + u8 *local_buffer = + yaffs_get_temp_buffer(dev); + yaffs_rd_data_obj(in, chunk, local_buffer); + + memcpy(buffer, &local_buffer[start], n_copy); + + yaffs_release_temp_buffer(dev, local_buffer); + } + } else { + /* A full chunk. Read directly into the buffer. */ + yaffs_rd_data_obj(in, chunk, buffer); + } + n -= n_copy; + offset += n_copy; + buffer += n_copy; + n_done += n_copy; + } + return n_done; +} + +int yaffs_do_file_wr(struct yaffs_obj *in, const u8 *buffer, loff_t offset, + int n_bytes, int write_through) +{ + + int chunk; + u32 start; + int n_copy; + int n = n_bytes; + int n_done = 0; + int n_writeback; + loff_t start_write = offset; + int chunk_written = 0; + u32 n_bytes_read; + loff_t chunk_start; + struct yaffs_dev *dev; + + dev = in->my_dev; + + while (n > 0 && chunk_written >= 0) { + yaffs_addr_to_chunk(dev, offset, &chunk, &start); + + if (((loff_t)chunk) * + dev->data_bytes_per_chunk + start != offset || + start >= dev->data_bytes_per_chunk) { + yaffs_trace(YAFFS_TRACE_ERROR, + "AddrToChunk of offset %lld gives chunk %d start %d", + (long long)offset, chunk, start); + } + chunk++; /* File pos to chunk in file offset */ + + /* OK now check for the curveball where the start and end are in + * the same chunk. + */ + + if ((start + n) < dev->data_bytes_per_chunk) { + n_copy = n; + + /* Now calculate how many bytes to write back.... + * If we're overwriting and not writing to then end of + * file then we need to write back as much as was there + * before. + */ + + chunk_start = (((loff_t)(chunk - 1)) * + dev->data_bytes_per_chunk); + + if (chunk_start > in->variant.file_variant.file_size) + n_bytes_read = 0; /* Past end of file */ + else + n_bytes_read = + in->variant.file_variant.file_size - + chunk_start; + + if (n_bytes_read > dev->data_bytes_per_chunk) + n_bytes_read = dev->data_bytes_per_chunk; + + n_writeback = + (n_bytes_read > + (start + n)) ? n_bytes_read : (start + n); + + if (n_writeback < 0 || + n_writeback > (int)dev->data_bytes_per_chunk) + BUG(); + + } else { + n_copy = dev->data_bytes_per_chunk - start; + n_writeback = dev->data_bytes_per_chunk; + } + + if (n_copy != (int)dev->data_bytes_per_chunk || + !dev->param.cache_bypass_aligned || + dev->param.inband_tags) { + /* An incomplete start or end chunk (or maybe both + * start and end chunk), or we're using inband tags, + * or we're forcing writes through the cache, + * so we want to use the cache buffers. + */ + if (dev->param.n_caches > 0) { + struct yaffs_cache *cache; + + /* If we can't find the data in the cache, then + * load the cache */ + cache = yaffs_find_chunk_cache(in, chunk); + + if (!cache && + yaffs_check_alloc_available(dev, 1)) { + cache = yaffs_grab_chunk_cache(dev); + cache->object = in; + cache->chunk_id = chunk; + cache->dirty = 0; + cache->locked = 0; + yaffs_rd_data_obj(in, chunk, + cache->data); + } else if (cache && + !cache->dirty && + !yaffs_check_alloc_available(dev, + 1)) { + /* Drop the cache if it was a read cache + * item and no space check has been made + * for it. + */ + cache = NULL; + } + + if (cache) { + yaffs_use_cache(dev, cache, 1); + cache->locked = 1; + + memcpy(&cache->data[start], buffer, + n_copy); + + cache->locked = 0; + cache->n_bytes = n_writeback; + + if (write_through) { + chunk_written = + yaffs_wr_data_obj + (cache->object, + cache->chunk_id, + cache->data, + cache->n_bytes, 1); + cache->dirty = 0; + } + } else { + chunk_written = -1; /* fail write */ + } + } else { + /* An incomplete start or end chunk (or maybe + * both start and end chunk). Read into the + * local buffer then copy over and write back. + */ + + u8 *local_buffer = yaffs_get_temp_buffer(dev); + + yaffs_rd_data_obj(in, chunk, local_buffer); + memcpy(&local_buffer[start], buffer, n_copy); + + chunk_written = + yaffs_wr_data_obj(in, chunk, + local_buffer, + n_writeback, 0); + + yaffs_release_temp_buffer(dev, local_buffer); + } + } else { + /* A full chunk. Write directly from the buffer. */ + + chunk_written = + yaffs_wr_data_obj(in, chunk, buffer, + dev->data_bytes_per_chunk, 0); + + /* Since we've overwritten the cached data, + * we better invalidate it. */ + yaffs_invalidate_chunk_cache(in, chunk); + } + + if (chunk_written >= 0) { + n -= n_copy; + offset += n_copy; + buffer += n_copy; + n_done += n_copy; + } + } + + /* Update file object */ + + if ((start_write + n_done) > in->variant.file_variant.file_size) + in->variant.file_variant.file_size = (start_write + n_done); + + in->dirty = 1; + return n_done; +} + +int yaffs_wr_file(struct yaffs_obj *in, const u8 *buffer, loff_t offset, + int n_bytes, int write_through) +{ + yaffs2_handle_hole(in, offset); + return yaffs_do_file_wr(in, buffer, offset, n_bytes, write_through); +} + +/* ---------------------- File resizing stuff ------------------ */ + +static void yaffs_prune_chunks(struct yaffs_obj *in, loff_t new_size) +{ + + struct yaffs_dev *dev = in->my_dev; + loff_t old_size = in->variant.file_variant.file_size; + int i; + int chunk_id; + u32 dummy; + int last_del; + int start_del; + + if (old_size > 0) + yaffs_addr_to_chunk(dev, old_size - 1, &last_del, &dummy); + else + last_del = 0; + + yaffs_addr_to_chunk(dev, new_size + dev->data_bytes_per_chunk - 1, + &start_del, &dummy); + last_del++; + start_del++; + + /* Delete backwards so that we don't end up with holes if + * power is lost part-way through the operation. + */ + for (i = last_del; i >= start_del; i--) { + /* NB this could be optimised somewhat, + * eg. could retrieve the tags and write them without + * using yaffs_chunk_del + */ + + chunk_id = yaffs_find_del_file_chunk(in, i, NULL); + + if (chunk_id < 1) + continue; + + if ((u32)chunk_id < + (dev->internal_start_block * dev->param.chunks_per_block) || + (u32)chunk_id >= + ((dev->internal_end_block + 1) * + dev->param.chunks_per_block)) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Found daft chunk_id %d for %d", + chunk_id, i); + } else { + in->n_data_chunks--; + yaffs_chunk_del(dev, chunk_id, 1, __LINE__); + } + } +} + +void yaffs_resize_file_down(struct yaffs_obj *obj, loff_t new_size) +{ + int new_full; + u32 new_partial; + struct yaffs_dev *dev = obj->my_dev; + + yaffs_addr_to_chunk(dev, new_size, &new_full, &new_partial); + + yaffs_prune_chunks(obj, new_size); + + if (new_partial != 0) { + int last_chunk = 1 + new_full; + u8 *local_buffer = yaffs_get_temp_buffer(dev); + + /* Rewrite the last chunk with its new size and zero pad */ + yaffs_rd_data_obj(obj, last_chunk, local_buffer); + memset(local_buffer + new_partial, 0, + dev->data_bytes_per_chunk - new_partial); + + yaffs_wr_data_obj(obj, last_chunk, local_buffer, + new_partial, 1); + + yaffs_release_temp_buffer(dev, local_buffer); + } + + obj->variant.file_variant.file_size = new_size; + obj->variant.file_variant.stored_size = new_size; + + yaffs_prune_tree(dev, &obj->variant.file_variant); +} + +int yaffs_resize_file(struct yaffs_obj *in, loff_t new_size) +{ + struct yaffs_dev *dev = in->my_dev; + loff_t old_size = in->variant.file_variant.file_size; + + yaffs_flush_file_cache(in, 1); + yaffs_invalidate_whole_cache(in); + + yaffs_check_gc(dev, 0); + + if (in->variant_type != YAFFS_OBJECT_TYPE_FILE) + return YAFFS_FAIL; + + if (new_size == old_size) + return YAFFS_OK; + + if (new_size > old_size) { + yaffs2_handle_hole(in, new_size); + in->variant.file_variant.file_size = new_size; + } else { + /* new_size < old_size */ + yaffs_resize_file_down(in, new_size); + } + + /* Write a new object header to reflect the resize. + * show we've shrunk the file, if need be + * Do this only if the file is not in the deleted directories + * and is not shadowed. + */ + if (in->parent && + !in->is_shadowed && + in->parent->obj_id != YAFFS_OBJECTID_UNLINKED && + in->parent->obj_id != YAFFS_OBJECTID_DELETED) + yaffs_update_oh(in, NULL, 0, 0, 0, NULL); + + return YAFFS_OK; +} + +int yaffs_flush_file(struct yaffs_obj *in, + int update_time, + int data_sync, + int discard_cache) +{ + if (!in->dirty) + return YAFFS_OK; + + yaffs_flush_file_cache(in, discard_cache); + + if (data_sync) + return YAFFS_OK; + + if (update_time) + yaffs_load_current_time(in, 0, 0); + + return (yaffs_update_oh(in, NULL, 0, 0, 0, NULL) >= 0) ? + YAFFS_OK : YAFFS_FAIL; +} + + +/* yaffs_del_file deletes the whole file data + * and the inode associated with the file. + * It does not delete the links associated with the file. + */ +static int yaffs_unlink_file_if_needed(struct yaffs_obj *in) +{ + int ret_val; + int del_now = 0; + struct yaffs_dev *dev = in->my_dev; + + if (!in->my_inode) + del_now = 1; + + if (del_now) { + ret_val = + yaffs_change_obj_name(in, in->my_dev->del_dir, + _Y("deleted"), 0, 0); + yaffs_trace(YAFFS_TRACE_TRACING, + "yaffs: immediate deletion of file %d", + in->obj_id); + in->deleted = 1; + in->my_dev->n_deleted_files++; + if (dev->param.disable_soft_del || dev->param.is_yaffs2) + yaffs_resize_file(in, 0); + yaffs_soft_del_file(in); + } else { + ret_val = + yaffs_change_obj_name(in, in->my_dev->unlinked_dir, + _Y("unlinked"), 0, 0); + } + return ret_val; +} + +static int yaffs_del_file(struct yaffs_obj *in) +{ + int ret_val = YAFFS_OK; + int deleted; /* Need to cache value on stack if in is freed */ + struct yaffs_dev *dev = in->my_dev; + + if (dev->param.disable_soft_del || dev->param.is_yaffs2) + yaffs_resize_file(in, 0); + + if (in->n_data_chunks > 0) { + /* Use soft deletion if there is data in the file. + * That won't be the case if it has been resized to zero. + */ + if (!in->unlinked) + ret_val = yaffs_unlink_file_if_needed(in); + + deleted = in->deleted; + + if (ret_val == YAFFS_OK && in->unlinked && !in->deleted) { + in->deleted = 1; + deleted = 1; + in->my_dev->n_deleted_files++; + yaffs_soft_del_file(in); + } + return deleted ? YAFFS_OK : YAFFS_FAIL; + } else { + /* The file has no data chunks so we toss it immediately */ + yaffs_free_tnode(in->my_dev, in->variant.file_variant.top); + in->variant.file_variant.top = NULL; + yaffs_generic_obj_del(in); + + return YAFFS_OK; + } +} + +int yaffs_is_non_empty_dir(struct yaffs_obj *obj) +{ + return (obj && + obj->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY) && + !(list_empty(&obj->variant.dir_variant.children)); +} + +static int yaffs_del_dir(struct yaffs_obj *obj) +{ + /* First check that the directory is empty. */ + if (yaffs_is_non_empty_dir(obj)) + return YAFFS_FAIL; + + return yaffs_generic_obj_del(obj); +} + +static int yaffs_del_symlink(struct yaffs_obj *in) +{ + kfree(in->variant.symlink_variant.alias); + in->variant.symlink_variant.alias = NULL; + + return yaffs_generic_obj_del(in); +} + +static int yaffs_del_link(struct yaffs_obj *in) +{ + /* remove this hardlink from the list associated with the equivalent + * object + */ + list_del_init(&in->hard_links); + return yaffs_generic_obj_del(in); +} + +int yaffs_del_obj(struct yaffs_obj *obj) +{ + int ret_val = -1; + + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + ret_val = yaffs_del_file(obj); + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + if (!list_empty(&obj->variant.dir_variant.dirty)) { + yaffs_trace(YAFFS_TRACE_BACKGROUND, + "Remove object %d from dirty directories", + obj->obj_id); + list_del_init(&obj->variant.dir_variant.dirty); + } + return yaffs_del_dir(obj); + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + ret_val = yaffs_del_symlink(obj); + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + ret_val = yaffs_del_link(obj); + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + ret_val = yaffs_generic_obj_del(obj); + break; + case YAFFS_OBJECT_TYPE_UNKNOWN: + ret_val = 0; + break; /* should not happen. */ + } + return ret_val; +} + + +static void yaffs_empty_dir_to_dir(struct yaffs_obj *from_dir, + struct yaffs_obj *to_dir) +{ + struct yaffs_obj *obj; + struct list_head *lh; + struct list_head *n; + + list_for_each_safe(lh, n, &from_dir->variant.dir_variant.children) { + obj = list_entry(lh, struct yaffs_obj, siblings); + yaffs_add_obj_to_dir(to_dir, obj); + } +} + +struct yaffs_obj *yaffs_retype_obj(struct yaffs_obj *obj, + enum yaffs_obj_type type) +{ + /* Tear down the old variant */ + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + /* Nuke file data */ + yaffs_resize_file(obj, 0); + yaffs_free_tnode(obj->my_dev, obj->variant.file_variant.top); + obj->variant.file_variant.top = NULL; + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + /* Put the children in lost and found. */ + yaffs_empty_dir_to_dir(obj, obj->my_dev->lost_n_found); + if (!list_empty(&obj->variant.dir_variant.dirty)) + list_del_init(&obj->variant.dir_variant.dirty); + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + /* Nuke symplink data */ + kfree(obj->variant.symlink_variant.alias); + obj->variant.symlink_variant.alias = NULL; + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + list_del_init(&obj->hard_links); + break; + default: + break; + } + + memset(&obj->variant, 0, sizeof(obj->variant)); + + /*Set up new variant if the memset is not enough. */ + switch (type) { + case YAFFS_OBJECT_TYPE_DIRECTORY: + INIT_LIST_HEAD(&obj->variant.dir_variant.children); + INIT_LIST_HEAD(&obj->variant.dir_variant.dirty); + break; + case YAFFS_OBJECT_TYPE_FILE: + case YAFFS_OBJECT_TYPE_SYMLINK: + case YAFFS_OBJECT_TYPE_HARDLINK: + default: + break; + } + + obj->variant_type = type; + + return obj; + +} + +static int yaffs_unlink_worker(struct yaffs_obj *obj) +{ + int del_now = 0; + + if (!obj) + return YAFFS_FAIL; + + if (!obj->my_inode) + del_now = 1; + + yaffs_update_parent(obj->parent); + + if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) { + return yaffs_del_link(obj); + } else if (!list_empty(&obj->hard_links)) { + /* Curve ball: We're unlinking an object that has a hardlink. + * + * This problem arises because we are not strictly following + * The Linux link/inode model. + * + * We can't really delete the object. + * Instead, we do the following: + * - Select a hardlink. + * - Unhook it from the hard links + * - Move it from its parent directory so that the rename works. + * - Rename the object to the hardlink's name. + * - Delete the hardlink + */ + + struct yaffs_obj *hl; + struct yaffs_obj *parent; + int ret_val; + YCHAR name[YAFFS_MAX_NAME_LENGTH + 1]; + + hl = list_entry(obj->hard_links.next, struct yaffs_obj, + hard_links); + + yaffs_get_obj_name(hl, name, YAFFS_MAX_NAME_LENGTH + 1); + parent = hl->parent; + + list_del_init(&hl->hard_links); + + yaffs_add_obj_to_dir(obj->my_dev->unlinked_dir, hl); + + ret_val = yaffs_change_obj_name(obj, parent, name, 0, 0); + + if (ret_val == YAFFS_OK) + ret_val = yaffs_generic_obj_del(hl); + + return ret_val; + + } else if (del_now) { + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + return yaffs_del_file(obj); + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + list_del_init(&obj->variant.dir_variant.dirty); + return yaffs_del_dir(obj); + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + return yaffs_del_symlink(obj); + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + return yaffs_generic_obj_del(obj); + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + case YAFFS_OBJECT_TYPE_UNKNOWN: + default: + return YAFFS_FAIL; + } + } else if (yaffs_is_non_empty_dir(obj)) { + return YAFFS_FAIL; + } else { + return yaffs_change_obj_name(obj, obj->my_dev->unlinked_dir, + _Y("unlinked"), 0, 0); + } +} + +int yaffs_unlink_obj(struct yaffs_obj *obj) +{ + if (obj && obj->unlink_allowed) + return yaffs_unlink_worker(obj); + + return YAFFS_FAIL; +} + +int yaffs_unlinker(struct yaffs_obj *dir, const YCHAR *name) +{ + struct yaffs_obj *obj; + + obj = yaffs_find_by_name(dir, name); + return yaffs_unlink_obj(obj); +} + +/* Note: + * If old_name is NULL then we take old_dir as the object to be renamed. + */ +int yaffs_rename_obj(struct yaffs_obj *old_dir, const YCHAR *old_name, + struct yaffs_obj *new_dir, const YCHAR *new_name) +{ + struct yaffs_obj *obj = NULL; + struct yaffs_obj *existing_target = NULL; + int force = 0; + int result; + struct yaffs_dev *dev; + + if (!old_dir || old_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + BUG(); + return YAFFS_FAIL; + } + if (!new_dir || new_dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + BUG(); + return YAFFS_FAIL; + } + + dev = old_dir->my_dev; + +#ifdef CONFIG_YAFFS_CASE_INSENSITIVE + /* Special case for case insemsitive systems. + * While look-up is case insensitive, the name isn't. + * Therefore we might want to change x.txt to X.txt + */ + if (old_dir == new_dir && + old_name && new_name && + strcmp(old_name, new_name) == 0) + force = 1; +#endif + + if (strnlen(new_name, YAFFS_MAX_NAME_LENGTH + 1) > + YAFFS_MAX_NAME_LENGTH) + /* ENAMETOOLONG */ + return YAFFS_FAIL; + + if (old_name) + obj = yaffs_find_by_name(old_dir, old_name); + else{ + obj = old_dir; + old_dir = obj->parent; + } + + if (obj && obj->rename_allowed) { + /* Now handle an existing target, if there is one */ + existing_target = yaffs_find_by_name(new_dir, new_name); + if (yaffs_is_non_empty_dir(existing_target)) { + return YAFFS_FAIL; /* ENOTEMPTY */ + } else if (existing_target && existing_target != obj) { + /* Nuke the target first, using shadowing, + * but only if it isn't the same object. + * + * Note we must disable gc here otherwise it can mess + * up the shadowing. + * + */ + dev->gc_disable = 1; + yaffs_change_obj_name(obj, new_dir, new_name, force, + existing_target->obj_id); + existing_target->is_shadowed = 1; + yaffs_unlink_obj(existing_target); + dev->gc_disable = 0; + } + + result = yaffs_change_obj_name(obj, new_dir, new_name, 1, 0); + + yaffs_update_parent(old_dir); + if (new_dir != old_dir) + yaffs_update_parent(new_dir); + + return result; + } + return YAFFS_FAIL; +} + +/*----------------------- Initialisation Scanning ---------------------- */ + +void yaffs_handle_shadowed_obj(struct yaffs_dev *dev, int obj_id, + int backward_scanning) +{ + struct yaffs_obj *obj; + + if (backward_scanning) { + /* Handle YAFFS2 case (backward scanning) + * If the shadowed object exists then ignore. + */ + obj = yaffs_find_by_number(dev, obj_id); + if (obj) + return; + } + + /* Let's create it (if it does not exist) assuming it is a file so that + * it can do shrinking etc. + * We put it in unlinked dir to be cleaned up after the scanning + */ + obj = + yaffs_find_or_create_by_number(dev, obj_id, YAFFS_OBJECT_TYPE_FILE); + if (!obj) + return; + obj->is_shadowed = 1; + yaffs_add_obj_to_dir(dev->unlinked_dir, obj); + obj->variant.file_variant.shrink_size = 0; + obj->valid = 1; /* So that we don't read any other info. */ +} + +void yaffs_link_fixup(struct yaffs_dev *dev, struct list_head *hard_list) +{ + struct list_head *lh; + struct list_head *save; + struct yaffs_obj *hl; + struct yaffs_obj *in; + + list_for_each_safe(lh, save, hard_list) { + hl = list_entry(lh, struct yaffs_obj, hard_links); + in = yaffs_find_by_number(dev, + hl->variant.hardlink_variant.equiv_id); + + if (in) { + /* Add the hardlink pointers */ + hl->variant.hardlink_variant.equiv_obj = in; + list_add(&hl->hard_links, &in->hard_links); + } else { + /* Todo Need to report/handle this better. + * Got a problem... hardlink to a non-existant object + */ + hl->variant.hardlink_variant.equiv_obj = NULL; + INIT_LIST_HEAD(&hl->hard_links); + } + } +} + +static void yaffs_strip_deleted_objs(struct yaffs_dev *dev) +{ + /* + * Sort out state of unlinked and deleted objects after scanning. + */ + struct list_head *i; + struct list_head *n; + struct yaffs_obj *l; + + if (dev->read_only) + return; + + /* Soft delete all the unlinked files */ + list_for_each_safe(i, n, + &dev->unlinked_dir->variant.dir_variant.children) { + l = list_entry(i, struct yaffs_obj, siblings); + yaffs_del_obj(l); + } + + list_for_each_safe(i, n, &dev->del_dir->variant.dir_variant.children) { + l = list_entry(i, struct yaffs_obj, siblings); + yaffs_del_obj(l); + } +} + +/* + * This code iterates through all the objects making sure that they are rooted. + * Any unrooted objects are re-rooted in lost+found. + * An object needs to be in one of: + * - Directly under deleted, unlinked + * - Directly or indirectly under root. + * + * Note: + * This code assumes that we don't ever change the current relationships + * between directories: + * root_dir->parent == unlinked_dir->parent == del_dir->parent == NULL + * lost-n-found->parent == root_dir + * + * This fixes the problem where directories might have inadvertently been + * deleted leaving the object "hanging" without being rooted in the + * directory tree. + */ + +static int yaffs_has_null_parent(struct yaffs_dev *dev, struct yaffs_obj *obj) +{ + return (obj == dev->del_dir || + obj == dev->unlinked_dir || obj == dev->root_dir); +} + +static void yaffs_fix_hanging_objs(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj; + struct yaffs_obj *parent; + int i; + struct list_head *lh; + struct list_head *n; + int depth_limit; + int hanging; + + if (dev->read_only) + return; + + /* Iterate through the objects in each hash entry, + * looking at each object. + * Make sure it is rooted. + */ + + for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) { + list_for_each_safe(lh, n, &dev->obj_bucket[i].list) { + obj = list_entry(lh, struct yaffs_obj, hash_link); + parent = obj->parent; + + if (yaffs_has_null_parent(dev, obj)) { + /* These directories are not hanging */ + hanging = 0; + } else if (!parent || + parent->variant_type != + YAFFS_OBJECT_TYPE_DIRECTORY) { + hanging = 1; + } else if (yaffs_has_null_parent(dev, parent)) { + hanging = 0; + } else { + /* + * Need to follow the parent chain to + * see if it is hanging. + */ + hanging = 0; + depth_limit = 100; + + while (parent != dev->root_dir && + parent->parent && + parent->parent->variant_type == + YAFFS_OBJECT_TYPE_DIRECTORY && + depth_limit > 0) { + parent = parent->parent; + depth_limit--; + } + if (parent != dev->root_dir) + hanging = 1; + } + if (hanging) { + yaffs_trace(YAFFS_TRACE_SCAN, + "Hanging object %d moved to lost and found", + obj->obj_id); + yaffs_add_obj_to_dir(dev->lost_n_found, obj); + } + } + } +} + +/* + * Delete directory contents for cleaning up lost and found. + */ +static void yaffs_del_dir_contents(struct yaffs_obj *dir) +{ + struct yaffs_obj *obj; + struct list_head *lh; + struct list_head *n; + + if (dir->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) + BUG(); + + list_for_each_safe(lh, n, &dir->variant.dir_variant.children) { + obj = list_entry(lh, struct yaffs_obj, siblings); + if (obj->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY) + yaffs_del_dir_contents(obj); + yaffs_trace(YAFFS_TRACE_SCAN, + "Deleting lost_found object %d", + obj->obj_id); + yaffs_unlink_obj(obj); + } +} + +static void yaffs_empty_l_n_f(struct yaffs_dev *dev) +{ + yaffs_del_dir_contents(dev->lost_n_found); +} + + +struct yaffs_obj *yaffs_find_by_name(struct yaffs_obj *directory, + const YCHAR *name) +{ + int sum; + struct list_head *i; + YCHAR buffer[YAFFS_MAX_NAME_LENGTH + 1]; + struct yaffs_obj *l; + + if (!name) + return NULL; + + if (!directory) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "tragedy: yaffs_find_by_name: null pointer directory" + ); + BUG(); + return NULL; + } + if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "tragedy: yaffs_find_by_name: non-directory" + ); + BUG(); + } + + sum = yaffs_calc_name_sum(name); + + list_for_each(i, &directory->variant.dir_variant.children) { + l = list_entry(i, struct yaffs_obj, siblings); + + if (l->parent != directory) + BUG(); + + yaffs_check_obj_details_loaded(l); + + /* Special case for lost-n-found */ + if (l->obj_id == YAFFS_OBJECTID_LOSTNFOUND) { + if (!strcmp(name, YAFFS_LOSTNFOUND_NAME)) + return l; + } else if (l->sum == sum || l->hdr_chunk <= 0) { + /* LostnFound chunk called Objxxx + * Do a real check + */ + yaffs_get_obj_name(l, buffer, + YAFFS_MAX_NAME_LENGTH + 1); + if (!strncmp(name, buffer, YAFFS_MAX_NAME_LENGTH)) + return l; + } + } + return NULL; +} + +/* GetEquivalentObject dereferences any hard links to get to the + * actual object. + */ + +struct yaffs_obj *yaffs_get_equivalent_obj(struct yaffs_obj *obj) +{ + if (obj && obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) { + obj = obj->variant.hardlink_variant.equiv_obj; + yaffs_check_obj_details_loaded(obj); + } + return obj; +} + +/* + * A note or two on object names. + * * If the object name is missing, we then make one up in the form objnnn + * + * * ASCII names are stored in the object header's name field from byte zero + * * Unicode names are historically stored starting from byte zero. + * + * Then there are automatic Unicode names... + * The purpose of these is to save names in a way that can be read as + * ASCII or Unicode names as appropriate, thus allowing a Unicode and ASCII + * system to share files. + * + * These automatic unicode are stored slightly differently... + * - If the name can fit in the ASCII character space then they are saved as + * ascii names as per above. + * - If the name needs Unicode then the name is saved in Unicode + * starting at oh->name[1]. + + */ +static void yaffs_fix_null_name(struct yaffs_obj *obj, YCHAR *name, + int buffer_size) +{ + /* Create an object name if we could not find one. */ + if (strnlen(name, YAFFS_MAX_NAME_LENGTH) == 0) { + YCHAR local_name[20]; + YCHAR num_string[20]; + YCHAR *x = &num_string[19]; + unsigned v = obj->obj_id; + num_string[19] = 0; + while (v > 0) { + x--; + *x = '0' + (v % 10); + v /= 10; + } + /* make up a name */ + strcpy(local_name, YAFFS_LOSTNFOUND_PREFIX); + strcat(local_name, x); + strncpy(name, local_name, buffer_size - 1); + } +} + +int yaffs_get_obj_name(struct yaffs_obj *obj, YCHAR *name, int buffer_size) +{ + memset(name, 0, buffer_size * sizeof(YCHAR)); + yaffs_check_obj_details_loaded(obj); + if (obj->obj_id == YAFFS_OBJECTID_LOSTNFOUND) { + strncpy(name, YAFFS_LOSTNFOUND_NAME, buffer_size - 1); + } else if (obj->short_name[0]) { + strcpy(name, obj->short_name); + } else if (obj->hdr_chunk > 0) { + int result; + u8 *buffer = yaffs_get_temp_buffer(obj->my_dev); + + struct yaffs_obj_hdr *oh = (struct yaffs_obj_hdr *)buffer; + + memset(buffer, 0, obj->my_dev->data_bytes_per_chunk); + + if (obj->hdr_chunk > 0) { + result = yaffs_rd_chunk_tags_nand(obj->my_dev, + obj->hdr_chunk, buffer, NULL); + if (result == YAFFS_OK) + yaffs_load_name_from_oh(obj->my_dev, name, + oh->name, buffer_size); + } + yaffs_release_temp_buffer(obj->my_dev, buffer); + } + + yaffs_fix_null_name(obj, name, buffer_size); + + return strnlen(name, YAFFS_MAX_NAME_LENGTH); +} + +loff_t yaffs_get_obj_length(struct yaffs_obj *obj) +{ + /* Dereference any hard linking */ + obj = yaffs_get_equivalent_obj(obj); + + if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE) + return obj->variant.file_variant.file_size; + if (obj->variant_type == YAFFS_OBJECT_TYPE_SYMLINK) { + if (!obj->variant.symlink_variant.alias) + return 0; + return strnlen(obj->variant.symlink_variant.alias, + YAFFS_MAX_ALIAS_LENGTH); + } else { + /* Only a directory should drop through to here */ + return obj->my_dev->data_bytes_per_chunk; + } +} + +int yaffs_get_obj_link_count(struct yaffs_obj *obj) +{ + int count = 0; + struct list_head *i; + + if (!obj->unlinked) + count++; /* the object itself */ + + list_for_each(i, &obj->hard_links) + count++; /* add the hard links; */ + + return count; +} + +int yaffs_get_obj_inode(struct yaffs_obj *obj) +{ + obj = yaffs_get_equivalent_obj(obj); + + return obj->obj_id; +} + +unsigned yaffs_get_obj_type(struct yaffs_obj *obj) +{ + obj = yaffs_get_equivalent_obj(obj); + + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + return DT_REG; + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + return DT_DIR; + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + return DT_LNK; + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + return DT_REG; + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + if (S_ISFIFO(obj->yst_mode)) + return DT_FIFO; + if (S_ISCHR(obj->yst_mode)) + return DT_CHR; + if (S_ISBLK(obj->yst_mode)) + return DT_BLK; + if (S_ISSOCK(obj->yst_mode)) + return DT_SOCK; + return DT_REG; + break; + default: + return DT_REG; + break; + } +} + +YCHAR *yaffs_get_symlink_alias(struct yaffs_obj *obj) +{ + obj = yaffs_get_equivalent_obj(obj); + if (obj->variant_type == YAFFS_OBJECT_TYPE_SYMLINK) + return yaffs_clone_str(obj->variant.symlink_variant.alias); + else + return yaffs_clone_str(_Y("")); +} + +/*--------------------------- Initialisation code -------------------------- */ + +static int yaffs_check_dev_fns(struct yaffs_dev *dev) +{ + struct yaffs_driver *drv = &dev->drv; + struct yaffs_tags_handler *tagger = &dev->tagger; + + /* Common functions, gotta have */ + if (!drv->drv_read_chunk_fn || + !drv->drv_write_chunk_fn || + !drv->drv_erase_fn) + return 0; + + if (dev->param.is_yaffs2 && + (!drv->drv_mark_bad_fn || !drv->drv_check_bad_fn)) + return 0; + + /* Install the default tags marshalling functions if needed. */ + yaffs_tags_compat_install(dev); + yaffs_tags_marshall_install(dev); + + /* Check we now have the marshalling functions required. */ + if (!tagger->write_chunk_tags_fn || + !tagger->read_chunk_tags_fn || + !tagger->query_block_fn || + !tagger->mark_bad_fn) + return 0; + + return 1; +} + +static int yaffs_create_initial_dir(struct yaffs_dev *dev) +{ + /* Initialise the unlinked, deleted, root and lost+found directories */ + dev->lost_n_found = NULL; + dev->root_dir = NULL; + dev->unlinked_dir = NULL; + dev->del_dir = NULL; + + dev->unlinked_dir = + yaffs_create_fake_dir(dev, YAFFS_OBJECTID_UNLINKED, S_IFDIR); + dev->del_dir = + yaffs_create_fake_dir(dev, YAFFS_OBJECTID_DELETED, S_IFDIR); + dev->root_dir = + yaffs_create_fake_dir(dev, YAFFS_OBJECTID_ROOT, + YAFFS_ROOT_MODE | S_IFDIR); + dev->lost_n_found = + yaffs_create_fake_dir(dev, YAFFS_OBJECTID_LOSTNFOUND, + YAFFS_LOSTNFOUND_MODE | S_IFDIR); + + if (dev->lost_n_found && + dev->root_dir && + dev->unlinked_dir && + dev->del_dir) { + /* If lost-n-found is hidden then yank it out of the directory tree. */ + if (dev->param.hide_lost_n_found) + list_del_init(&dev->lost_n_found->siblings); + else + yaffs_add_obj_to_dir(dev->root_dir, dev->lost_n_found); + return YAFFS_OK; + } + return YAFFS_FAIL; +} + +/* Low level init. + * Typically only used by yaffs_guts_initialise, but also used by the + * Low level yaffs driver tests. + */ + +int yaffs_guts_ll_init(struct yaffs_dev *dev) +{ + + + yaffs_trace(YAFFS_TRACE_TRACING, "yaffs: yaffs_ll_init()"); + + if (!dev) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: Need a device" + ); + return YAFFS_FAIL; + } + + if (dev->ll_init) + return YAFFS_OK; + + dev->internal_start_block = dev->param.start_block; + dev->internal_end_block = dev->param.end_block; + dev->block_offset = 0; + dev->chunk_offset = 0; + dev->n_free_chunks = 0; + + dev->gc_block = 0; + + if (dev->param.start_block == 0) { + dev->internal_start_block = dev->param.start_block + 1; + dev->internal_end_block = dev->param.end_block + 1; + dev->block_offset = 1; + dev->chunk_offset = dev->param.chunks_per_block; + } + + /* Check geometry parameters. */ + + if ((!dev->param.inband_tags && dev->param.is_yaffs2 && + dev->param.total_bytes_per_chunk < 1024) || + (!dev->param.is_yaffs2 && + dev->param.total_bytes_per_chunk < 512) || + (dev->param.inband_tags && !dev->param.is_yaffs2) || + dev->param.chunks_per_block < 2 || + dev->param.n_reserved_blocks < 2 || + dev->internal_start_block <= 0 || + dev->internal_end_block <= 0 || + dev->internal_end_block <= + (dev->internal_start_block + dev->param.n_reserved_blocks + 2) + ) { + /* otherwise it is too small */ + yaffs_trace(YAFFS_TRACE_ALWAYS, + "NAND geometry problems: chunk size %d, type is yaffs%s, inband_tags %d ", + dev->param.total_bytes_per_chunk, + dev->param.is_yaffs2 ? "2" : "", + dev->param.inband_tags); + return YAFFS_FAIL; + } + + /* Sort out space for inband tags, if required */ + if (dev->param.inband_tags) + dev->data_bytes_per_chunk = + dev->param.total_bytes_per_chunk - + sizeof(struct yaffs_packed_tags2_tags_only); + else + dev->data_bytes_per_chunk = dev->param.total_bytes_per_chunk; + + /* Got the right mix of functions? */ + if (!yaffs_check_dev_fns(dev)) { + /* Function missing */ + yaffs_trace(YAFFS_TRACE_ALWAYS, + "device function(s) missing or wrong"); + + return YAFFS_FAIL; + } + + if (yaffs_init_nand(dev) != YAFFS_OK) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "InitialiseNAND failed"); + return YAFFS_FAIL; + } + + return YAFFS_OK; +} + + +int yaffs_guts_format_dev(struct yaffs_dev *dev) +{ + u32 i; + enum yaffs_block_state state; + u32 dummy; + + if(yaffs_guts_ll_init(dev) != YAFFS_OK) + return YAFFS_FAIL; + + if(dev->is_mounted) + return YAFFS_FAIL; + + for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + yaffs_query_init_block_state(dev, i, &state, &dummy); + if (state != YAFFS_BLOCK_STATE_DEAD) + yaffs_erase_block(dev, i); + } + + return YAFFS_OK; +} + + +int yaffs_guts_initialise(struct yaffs_dev *dev) +{ + int init_failed = 0; + u32 x; + u32 bits; + + if(yaffs_guts_ll_init(dev) != YAFFS_OK) + return YAFFS_FAIL; + + if (dev->is_mounted) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "device already mounted"); + return YAFFS_FAIL; + } + + dev->is_mounted = 1; + + /* OK now calculate a few things for the device */ + + /* + * Calculate all the chunk size manipulation numbers: + */ + x = dev->data_bytes_per_chunk; + /* We always use dev->chunk_shift and dev->chunk_div */ + dev->chunk_shift = calc_shifts(x); + x >>= dev->chunk_shift; + dev->chunk_div = x; + /* We only use chunk mask if chunk_div is 1 */ + dev->chunk_mask = (1 << dev->chunk_shift) - 1; + + /* + * Calculate chunk_grp_bits. + * We need to find the next power of 2 > than internal_end_block + */ + + x = dev->param.chunks_per_block * (dev->internal_end_block + 1); + + bits = calc_shifts_ceiling(x); + + /* Set up tnode width if wide tnodes are enabled. */ + if (!dev->param.wide_tnodes_disabled) { + /* bits must be even so that we end up with 32-bit words */ + if (bits & 1) + bits++; + if (bits < 16) + dev->tnode_width = 16; + else + dev->tnode_width = bits; + } else { + dev->tnode_width = 16; + } + + dev->tnode_mask = (1 << dev->tnode_width) - 1; + + /* Level0 Tnodes are 16 bits or wider (if wide tnodes are enabled), + * so if the bitwidth of the + * chunk range we're using is greater than 16 we need + * to figure out chunk shift and chunk_grp_size + */ + + if (bits <= dev->tnode_width) + dev->chunk_grp_bits = 0; + else + dev->chunk_grp_bits = bits - dev->tnode_width; + + dev->tnode_size = (dev->tnode_width * YAFFS_NTNODES_LEVEL0) / 8; + if (dev->tnode_size < sizeof(struct yaffs_tnode)) + dev->tnode_size = sizeof(struct yaffs_tnode); + + dev->chunk_grp_size = 1 << dev->chunk_grp_bits; + + if (dev->param.chunks_per_block < dev->chunk_grp_size) { + /* We have a problem because the soft delete won't work if + * the chunk group size > chunks per block. + * This can be remedied by using larger "virtual blocks". + */ + yaffs_trace(YAFFS_TRACE_ALWAYS, "chunk group too large"); + + return YAFFS_FAIL; + } + + /* Finished verifying the device, continue with initialisation */ + + /* More device initialisation */ + dev->all_gcs = 0; + dev->passive_gc_count = 0; + dev->oldest_dirty_gc_count = 0; + dev->bg_gcs = 0; + dev->gc_block_finder = 0; + dev->buffered_block = -1; + dev->doing_buffered_block_rewrite = 0; + dev->n_deleted_files = 0; + dev->n_bg_deletions = 0; + dev->n_unlinked_files = 0; + dev->n_ecc_fixed = 0; + dev->n_ecc_unfixed = 0; + dev->n_tags_ecc_fixed = 0; + dev->n_tags_ecc_unfixed = 0; + dev->n_erase_failures = 0; + dev->n_erased_blocks = 0; + dev->gc_disable = 0; + dev->has_pending_prioritised_gc = 1; /* Assume the worst for now, + * will get fixed on first GC */ + INIT_LIST_HEAD(&dev->dirty_dirs); + dev->oldest_dirty_seq = 0; + dev->oldest_dirty_block = 0; + + yaffs_endian_config(dev); + + /* Initialise temporary buffers and caches. */ + if (!yaffs_init_tmp_buffers(dev)) + init_failed = 1; + + dev->cache = NULL; + dev->gc_cleanup_list = NULL; + + if (!init_failed && dev->param.n_caches > 0) { + u32 i; + void *buf; + u32 cache_bytes = + dev->param.n_caches * sizeof(struct yaffs_cache); + + if (dev->param.n_caches > YAFFS_MAX_SHORT_OP_CACHES) + dev->param.n_caches = YAFFS_MAX_SHORT_OP_CACHES; + + dev->cache = kmalloc(cache_bytes, GFP_NOFS); + + buf = (u8 *) dev->cache; + + if (dev->cache) + memset(dev->cache, 0, cache_bytes); + + for (i = 0; i < dev->param.n_caches && buf; i++) { + dev->cache[i].object = NULL; + dev->cache[i].last_use = 0; + dev->cache[i].dirty = 0; + dev->cache[i].data = buf = + kmalloc(dev->param.total_bytes_per_chunk, GFP_NOFS); + } + if (!buf) + init_failed = 1; + + dev->cache_last_use = 0; + } + + dev->cache_hits = 0; + + if (!init_failed) { + dev->gc_cleanup_list = + kmalloc(dev->param.chunks_per_block * sizeof(u32), + GFP_NOFS); + if (!dev->gc_cleanup_list) + init_failed = 1; + } + + if (dev->param.is_yaffs2) + dev->param.use_header_file_size = 1; + + if (!init_failed && !yaffs_init_blocks(dev)) + init_failed = 1; + + yaffs_init_tnodes_and_objs(dev); + + if (!init_failed && !yaffs_create_initial_dir(dev)) + init_failed = 1; + + if (!init_failed && dev->param.is_yaffs2 && + !dev->param.disable_summary && + !yaffs_summary_init(dev)) + init_failed = 1; + + if (!init_failed) { + /* Now scan the flash. */ + if (dev->param.is_yaffs2) { + if (yaffs2_checkpt_restore(dev)) { + yaffs_check_obj_details_loaded(dev->root_dir); + yaffs_trace(YAFFS_TRACE_CHECKPOINT | + YAFFS_TRACE_MOUNT, + "yaffs: restored from checkpoint" + ); + } else { + + /* Clean up the mess caused by an aborted + * checkpoint load then scan backwards. + */ + yaffs_deinit_blocks(dev); + + yaffs_deinit_tnodes_and_objs(dev); + + dev->n_erased_blocks = 0; + dev->n_free_chunks = 0; + dev->alloc_block = -1; + dev->alloc_page = -1; + dev->n_deleted_files = 0; + dev->n_unlinked_files = 0; + dev->n_bg_deletions = 0; + + if (!init_failed && !yaffs_init_blocks(dev)) + init_failed = 1; + + yaffs_init_tnodes_and_objs(dev); + + if (!init_failed + && !yaffs_create_initial_dir(dev)) + init_failed = 1; + + if (!init_failed && !yaffs2_scan_backwards(dev)) + init_failed = 1; + } + } else if (!yaffs1_scan(dev)) { + init_failed = 1; + } + + yaffs_strip_deleted_objs(dev); + yaffs_fix_hanging_objs(dev); + if (dev->param.empty_lost_n_found) + yaffs_empty_l_n_f(dev); + } + + if (init_failed) { + /* Clean up the mess */ + yaffs_trace(YAFFS_TRACE_TRACING, + "yaffs: yaffs_guts_initialise() aborted."); + + yaffs_deinitialise(dev); + return YAFFS_FAIL; + } + + /* Zero out stats */ + dev->n_page_reads = 0; + dev->n_page_writes = 0; + dev->n_erasures = 0; + dev->n_gc_copies = 0; + dev->n_retried_writes = 0; + + dev->n_retired_blocks = 0; + + yaffs_verify_free_chunks(dev); + yaffs_verify_blocks(dev); + + /* Clean up any aborted checkpoint data */ + if (!dev->is_checkpointed && dev->blocks_in_checkpt > 0) + yaffs2_checkpt_invalidate(dev); + + yaffs_trace(YAFFS_TRACE_TRACING, + "yaffs: yaffs_guts_initialise() done."); + return YAFFS_OK; +} + +void yaffs_deinitialise(struct yaffs_dev *dev) +{ + if (dev->is_mounted) { + u32 i; + + yaffs_deinit_blocks(dev); + yaffs_deinit_tnodes_and_objs(dev); + yaffs_summary_deinit(dev); + + if (dev->param.n_caches > 0 && dev->cache) { + + for (i = 0; i < dev->param.n_caches; i++) { + kfree(dev->cache[i].data); + dev->cache[i].data = NULL; + } + + kfree(dev->cache); + dev->cache = NULL; + } + + kfree(dev->gc_cleanup_list); + + for (i = 0; i < YAFFS_N_TEMP_BUFFERS; i++) { + kfree(dev->temp_buffer[i].buffer); + dev->temp_buffer[i].buffer = NULL; + } + + kfree(dev->checkpt_buffer); + dev->checkpt_buffer = NULL; + kfree(dev->checkpt_block_list); + dev->checkpt_block_list = NULL; + + dev->is_mounted = 0; + + yaffs_deinit_nand(dev); + } +} + +int yaffs_count_free_chunks(struct yaffs_dev *dev) +{ + int n_free = 0; + u32 b; + struct yaffs_block_info *blk; + + blk = dev->block_info; + for (b = dev->internal_start_block; b <= dev->internal_end_block; b++) { + switch (blk->block_state) { + case YAFFS_BLOCK_STATE_EMPTY: + case YAFFS_BLOCK_STATE_ALLOCATING: + case YAFFS_BLOCK_STATE_COLLECTING: + case YAFFS_BLOCK_STATE_FULL: + n_free += + (dev->param.chunks_per_block - blk->pages_in_use + + blk->soft_del_pages); + break; + default: + break; + } + blk++; + } + return n_free; +} + +int yaffs_get_n_free_chunks(struct yaffs_dev *dev) +{ + /* This is what we report to the outside world */ + int n_free; + int n_dirty_caches; + int blocks_for_checkpt; + u32 i; + + n_free = dev->n_free_chunks; + n_free += dev->n_deleted_files; + + /* Now count and subtract the number of dirty chunks in the cache. */ + + for (n_dirty_caches = 0, i = 0; i < dev->param.n_caches; i++) { + if (dev->cache[i].dirty) + n_dirty_caches++; + } + + n_free -= n_dirty_caches; + + n_free -= + ((dev->param.n_reserved_blocks + 1) * dev->param.chunks_per_block); + + /* Now figure checkpoint space and report that... */ + blocks_for_checkpt = yaffs_calc_checkpt_blocks_required(dev); + + n_free -= (blocks_for_checkpt * dev->param.chunks_per_block); + + if (n_free < 0) + n_free = 0; + + return n_free; +} + + +/* + * Marshalling functions to get loff_t file sizes into and out of + * object headers. + */ +void yaffs_oh_size_load(struct yaffs_dev *dev, + struct yaffs_obj_hdr *oh, + loff_t fsize, + int do_endian) +{ + oh->file_size_low = FSIZE_LOW(fsize); + + oh->file_size_high = FSIZE_HIGH(fsize); + + if (do_endian) { + yaffs_do_endian_u32(dev, &oh->file_size_low); + yaffs_do_endian_u32(dev, &oh->file_size_high); + } +} + +loff_t yaffs_oh_to_size(struct yaffs_dev *dev, struct yaffs_obj_hdr *oh, + int do_endian) +{ + loff_t retval; + + + if (sizeof(loff_t) >= 8 && ~(oh->file_size_high)) { + u32 low = oh->file_size_low; + u32 high = oh->file_size_high; + + if (do_endian) { + yaffs_do_endian_u32 (dev, &low); + yaffs_do_endian_u32 (dev, &high); + } + retval = FSIZE_COMBINE(high, low); + } else { + u32 low = oh->file_size_low; + + if (do_endian) + yaffs_do_endian_u32(dev, &low); + retval = (loff_t)low; + } + + return retval; +} + + +void yaffs_count_blocks_by_state(struct yaffs_dev *dev, int bs[10]) +{ + u32 i; + struct yaffs_block_info *bi; + int s; + + for(i = 0; i < 10; i++) + bs[i] = 0; + + for(i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + bi = yaffs_get_block_info(dev, i); + s = bi->block_state; + if(s > YAFFS_BLOCK_STATE_DEAD || s < YAFFS_BLOCK_STATE_UNKNOWN) + bs[0]++; + else + bs[s]++; + } +} diff --git a/fs/yaffs2/yaffs_guts.h b/fs/yaffs2/yaffs_guts.h new file mode 100644 index 000000000000..5ebc3787b4d4 --- /dev/null +++ b/fs/yaffs2/yaffs_guts.h @@ -0,0 +1,1069 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_GUTS_H__ +#define __YAFFS_GUTS_H__ + +#include "yportenv.h" + +#define YAFFS_OK 1 +#define YAFFS_FAIL 0 + +/* Give us a Y=0x59, + * Give us an A=0x41, + * Give us an FF=0xff + * Give us an S=0x53 + * And what have we got... + */ +#define YAFFS_MAGIC 0x5941ff53 + +/* + * Tnodes form a tree with the tnodes in "levels" + * Levels greater than 0 hold 8 slots which point to other tnodes. + * Those at level 0 hold 16 slots which point to chunks in NAND. + * + * A maximum level of 8 thust supports files of size up to: + * + * 2^(3*MAX_LEVEL+4) + * + * Thus a max level of 8 supports files with up to 2^^28 chunks which gives + * a maximum file size of around 512Gbytees with 2k chunks. + */ +#define YAFFS_NTNODES_LEVEL0 16 +#define YAFFS_TNODES_LEVEL0_BITS 4 +#define YAFFS_TNODES_LEVEL0_MASK 0xf + +#define YAFFS_NTNODES_INTERNAL (YAFFS_NTNODES_LEVEL0 / 2) +#define YAFFS_TNODES_INTERNAL_BITS (YAFFS_TNODES_LEVEL0_BITS - 1) +#define YAFFS_TNODES_INTERNAL_MASK 0x7 +#define YAFFS_TNODES_MAX_LEVEL 8 +#define YAFFS_TNODES_MAX_BITS (YAFFS_TNODES_LEVEL0_BITS + \ + YAFFS_TNODES_INTERNAL_BITS * \ + YAFFS_TNODES_MAX_LEVEL) +#define YAFFS_MAX_CHUNK_ID ((1 << YAFFS_TNODES_MAX_BITS) - 1) + +#define YAFFS_MAX_FILE_SIZE_32 0x7fffffff + +/* Constants for YAFFS1 mode */ +#define YAFFS_BYTES_PER_SPARE 16 +#define YAFFS_BYTES_PER_CHUNK 512 +#define YAFFS_CHUNK_SIZE_SHIFT 9 +#define YAFFS_CHUNKS_PER_BLOCK 32 +#define YAFFS_BYTES_PER_BLOCK (YAFFS_CHUNKS_PER_BLOCK*YAFFS_BYTES_PER_CHUNK) + +#define YAFFS_MIN_YAFFS2_CHUNK_SIZE 1024 +#define YAFFS_MIN_YAFFS2_SPARE_SIZE 32 + + + +#define YAFFS_ALLOCATION_NOBJECTS 100 +#define YAFFS_ALLOCATION_NTNODES 100 +#define YAFFS_ALLOCATION_NLINKS 100 + +#define YAFFS_NOBJECT_BUCKETS 256 + +#define YAFFS_OBJECT_SPACE 0x40000 +#define YAFFS_MAX_OBJECT_ID (YAFFS_OBJECT_SPACE - 1) + +/* Binary data version stamps */ +#define YAFFS_SUMMARY_VERSION 1 + +#ifdef CONFIG_YAFFS_UNICODE +#define YAFFS_MAX_NAME_LENGTH 127 +#define YAFFS_MAX_ALIAS_LENGTH 79 +#else +#define YAFFS_MAX_NAME_LENGTH 255 +#define YAFFS_MAX_ALIAS_LENGTH 159 +#endif + +#define YAFFS_SHORT_NAME_LENGTH 15 + +/* Some special object ids for pseudo objects */ +#define YAFFS_OBJECTID_ROOT 1 +#define YAFFS_OBJECTID_LOSTNFOUND 2 +#define YAFFS_OBJECTID_UNLINKED 3 +#define YAFFS_OBJECTID_DELETED 4 + +/* Fake object Id for summary data */ +#define YAFFS_OBJECTID_SUMMARY 0x10 + +/* Pseudo object ids for checkpointing */ +#define YAFFS_OBJECTID_CHECKPOINT_DATA 0x20 +#define YAFFS_SEQUENCE_CHECKPOINT_DATA 0x21 + +#define YAFFS_MAX_SHORT_OP_CACHES 20 + +#define YAFFS_N_TEMP_BUFFERS 6 + +/* We limit the number attempts at sucessfully saving a chunk of data. + * Small-page devices have 32 pages per block; large-page devices have 64. + * Default to something in the order of 5 to 10 blocks worth of chunks. + */ +#define YAFFS_WR_ATTEMPTS (5*64) + +/* Sequence numbers are used in YAFFS2 to determine block allocation order. + * The range is limited slightly to help distinguish bad numbers from good. + * This also allows us to perhaps in the future use special numbers for + * special purposes. + * EFFFFF00 allows the allocation of 8 blocks/second (~1Mbytes) for 15 years, + * and is a larger number than the lifetime of a 2GB device. + */ +#define YAFFS_LOWEST_SEQUENCE_NUMBER 0x00001000 +#define YAFFS_HIGHEST_SEQUENCE_NUMBER 0xefffff00 + +/* Special sequence number for bad block that failed to be marked bad */ +#define YAFFS_SEQUENCE_BAD_BLOCK 0xffff0000 + +/* ChunkCache is used for short read/write operations.*/ +struct yaffs_cache { + struct yaffs_obj *object; + int chunk_id; + int last_use; + int dirty; + int n_bytes; /* Only valid if the cache is dirty */ + int locked; /* Can't push out or flush while locked. */ + u8 *data; +}; + +/* yaffs1 tags structures in RAM + * NB This uses bitfield. Bitfields should not straddle a u32 boundary + * otherwise the structure size will get blown out. + */ + +struct yaffs_tags { + u32 chunk_id:20; + u32 serial_number:2; + u32 n_bytes_lsb:10; + u32 obj_id:18; + u32 ecc:12; + u32 n_bytes_msb:2; +}; + +union yaffs_tags_union { + struct yaffs_tags as_tags; + u8 as_bytes[8]; + u32 as_u32[2]; +}; + + +/* Stuff used for extended tags in YAFFS2 */ + +enum yaffs_ecc_result { + YAFFS_ECC_RESULT_UNKNOWN, + YAFFS_ECC_RESULT_NO_ERROR, + YAFFS_ECC_RESULT_FIXED, + YAFFS_ECC_RESULT_UNFIXED +}; + +/* + * Object type enum: + * When this is stored in flash we store it as a u32 instead + * to prevent any alignment change issues as compiler variants change. + */ + +enum yaffs_obj_type { + YAFFS_OBJECT_TYPE_UNKNOWN, + YAFFS_OBJECT_TYPE_FILE, + YAFFS_OBJECT_TYPE_SYMLINK, + YAFFS_OBJECT_TYPE_DIRECTORY, + YAFFS_OBJECT_TYPE_HARDLINK, + YAFFS_OBJECT_TYPE_SPECIAL +}; + +#define YAFFS_OBJECT_TYPE_MAX YAFFS_OBJECT_TYPE_SPECIAL + +struct yaffs_ext_tags { + unsigned chunk_used; /* Status of the chunk: used or unused */ + unsigned obj_id; /* If 0 this is not used */ + unsigned chunk_id; /* If 0 this is a header, else a data chunk */ + unsigned n_bytes; /* Only valid for data chunks */ + + /* The following stuff only has meaning when we read */ + enum yaffs_ecc_result ecc_result; + unsigned block_bad; + + /* YAFFS 1 stuff */ + unsigned is_deleted; /* The chunk is marked deleted */ + unsigned serial_number; /* Yaffs1 2-bit serial number */ + + /* YAFFS2 stuff */ + unsigned seq_number; /* The sequence number of this block */ + + /* Extra info if this is an object header (YAFFS2 only) */ + + unsigned extra_available; /* Extra info available if not zero */ + unsigned extra_parent_id; /* The parent object */ + unsigned extra_is_shrink; /* Is it a shrink header? */ + unsigned extra_shadows; /* Does this shadow another object? */ + + enum yaffs_obj_type extra_obj_type; /* What object type? */ + + loff_t extra_file_size; /* Length if it is a file */ + unsigned extra_equiv_id; /* Equivalent object for a hard link */ +}; + +/* Spare structure for YAFFS1 */ +struct yaffs_spare { + u8 tb0; + u8 tb1; + u8 tb2; + u8 tb3; + u8 page_status; /* set to 0 to delete the chunk */ + u8 block_status; + u8 tb4; + u8 tb5; + u8 ecc1[3]; + u8 tb6; + u8 tb7; + u8 ecc2[3]; +}; + +/*Special structure for passing through to mtd */ +struct yaffs_nand_spare { + struct yaffs_spare spare; + int eccres1; + int eccres2; +}; + +/* Block data in RAM */ + +enum yaffs_block_state { + YAFFS_BLOCK_STATE_UNKNOWN = 0, + + YAFFS_BLOCK_STATE_SCANNING, + /* Being scanned */ + + YAFFS_BLOCK_STATE_NEEDS_SCAN, + /* The block might have something on it (ie it is allocating or full, + * perhaps empty) but it needs to be scanned to determine its true + * state. + * This state is only valid during scanning. + * NB We tolerate empty because the pre-scanner might be incapable of + * deciding + * However, if this state is returned on a YAFFS2 device, + * then we expect a sequence number + */ + + YAFFS_BLOCK_STATE_EMPTY, + /* This block is empty */ + + YAFFS_BLOCK_STATE_ALLOCATING, + /* This block is partially allocated. + * At least one page holds valid data. + * This is the one currently being used for page + * allocation. Should never be more than one of these. + * If a block is only partially allocated at mount it is treated as + * full. + */ + + YAFFS_BLOCK_STATE_FULL, + /* All the pages in this block have been allocated. + * If a block was only partially allocated when mounted we treat + * it as fully allocated. + */ + + YAFFS_BLOCK_STATE_DIRTY, + /* The block was full and now all chunks have been deleted. + * Erase me, reuse me. + */ + + YAFFS_BLOCK_STATE_CHECKPOINT, + /* This block is assigned to holding checkpoint data. */ + + YAFFS_BLOCK_STATE_COLLECTING, + /* This block is being garbage collected */ + + YAFFS_BLOCK_STATE_DEAD + /* This block has failed and is not in use */ +}; + +#define YAFFS_NUMBER_OF_BLOCK_STATES (YAFFS_BLOCK_STATE_DEAD + 1) + +struct yaffs_block_info { + + s32 soft_del_pages:10; /* number of soft deleted pages */ + s32 pages_in_use:10; /* number of pages in use */ + u32 block_state:4; /* One of the above block states. */ + /* NB use unsigned because enum is sometimes + * an int */ + u32 needs_retiring:1; /* Data has failed on this block, */ + /*need to get valid data off and retire*/ + u32 skip_erased_check:1;/* Skip the erased check on this block */ + u32 gc_prioritise:1; /* An ECC check or blank check has failed. + Block should be prioritised for GC */ + u32 chunk_error_strikes:3; /* How many times we've had ecc etc + failures on this block and tried to reuse it */ + u32 has_summary:1; /* The block has a summary */ + + u32 has_shrink_hdr:1; /* This block has at least one shrink header */ + u32 seq_number; /* block sequence number for yaffs2 */ + +}; + +union yaffs_block_info_union { + struct yaffs_block_info bi; + u32 as_u32[2]; +}; + +/* -------------------------- Object structure -------------------------------*/ +/* This is the object structure as stored on NAND */ + +struct yaffs_obj_hdr { + u32 type; /* enum yaffs_obj_type */ + + /* Apply to everything */ + u32 parent_obj_id; + u16 sum_no_longer_used; /* checksum of name. No longer used */ + YCHAR name[YAFFS_MAX_NAME_LENGTH + 1]; + + /* The following apply to all object types except for hard links */ + u32 yst_mode; /* protection */ + + u32 yst_uid; + u32 yst_gid; + u32 yst_atime; + u32 yst_mtime; + u32 yst_ctime; + + /* File size applies to files only */ + u32 file_size_low; + + /* Equivalent object id applies to hard links only. */ + int equiv_id; + + /* Alias is for symlinks only. */ + YCHAR alias[YAFFS_MAX_ALIAS_LENGTH + 1]; + + u32 yst_rdev; /* stuff for block and char devices (major/min) */ + + u32 win_ctime[2]; + u32 win_atime[2]; + u32 win_mtime[2]; + + u32 inband_shadowed_obj_id; + u32 inband_is_shrink; + + u32 file_size_high; + u32 reserved[1]; + int shadows_obj; /* This object header shadows the + specified object if > 0 */ + + /* is_shrink applies to object headers written when wemake a hole. */ + u32 is_shrink; + +}; + +/*--------------------------- Tnode -------------------------- */ + +struct yaffs_tnode { + struct yaffs_tnode *internal[YAFFS_NTNODES_INTERNAL]; +}; + +/*------------------------ Object -----------------------------*/ +/* An object can be one of: + * - a directory (no data, has children links + * - a regular file (data.... not prunes :->). + * - a symlink [symbolic link] (the alias). + * - a hard link + */ + +/* The file variant has three file sizes: + * - file_size : size of file as written into Yaffs - including data in cache. + * - stored_size - size of file as stored on media. + * - shrink_size - size of file that has been shrunk back to. + * + * The stored_size and file_size might be different because the data written + * into the cache will increase the file_size but the stored_size will only + * change when the data is actually stored. + * + */ +struct yaffs_file_var { + loff_t file_size; + loff_t stored_size; + loff_t shrink_size; + int top_level; + struct yaffs_tnode *top; +}; + +struct yaffs_dir_var { + struct list_head children; /* list of child links */ + struct list_head dirty; /* Entry for list of dirty directories */ +}; + +struct yaffs_symlink_var { + YCHAR *alias; +}; + +struct yaffs_hardlink_var { + struct yaffs_obj *equiv_obj; + u32 equiv_id; +}; + +union yaffs_obj_var { + struct yaffs_file_var file_variant; + struct yaffs_dir_var dir_variant; + struct yaffs_symlink_var symlink_variant; + struct yaffs_hardlink_var hardlink_variant; +}; + +struct yaffs_obj { + u8 deleted:1; /* This should only apply to unlinked files. */ + u8 soft_del:1; /* it has also been soft deleted */ + u8 unlinked:1; /* An unlinked file.*/ + u8 fake:1; /* A fake object has no presence on NAND. */ + u8 rename_allowed:1; /* Some objects cannot be renamed. */ + u8 unlink_allowed:1; + u8 dirty:1; /* the object needs to be written to flash */ + u8 valid:1; /* When the file system is being loaded up, this + * object might be created before the data + * is available + * ie. file data chunks encountered before + * the header. + */ + u8 lazy_loaded:1; /* This object has been lazy loaded and + * is missing some detail */ + + u8 defered_free:1; /* Object is removed from NAND, but is + * still in the inode cache. + * Free of object is defered. + * until the inode is released. + */ + u8 being_created:1; /* This object is still being created + * so skip some verification checks. */ + u8 is_shadowed:1; /* This object is shadowed on the way + * to being renamed. */ + + u8 xattr_known:1; /* We know if this has object has xattribs + * or not. */ + u8 has_xattr:1; /* This object has xattribs. + * Only valid if xattr_known. */ + + u8 serial; /* serial number of chunk in NAND.*/ + u16 sum; /* sum of the name to speed searching */ + + struct yaffs_dev *my_dev; /* The device I'm on */ + + struct list_head hash_link; /* list of objects in hash bucket */ + + struct list_head hard_links; /* hard linked object chain*/ + + /* directory structure stuff */ + /* also used for linking up the free list */ + struct yaffs_obj *parent; + struct list_head siblings; + + /* Where's my object header in NAND? */ + int hdr_chunk; + + int n_data_chunks; /* Number of data chunks for this file. */ + + u32 obj_id; /* the object id value */ + + u32 yst_mode; + + YCHAR short_name[YAFFS_SHORT_NAME_LENGTH + 1]; + +#ifdef CONFIG_YAFFS_WINCE + u32 win_ctime[2]; + u32 win_mtime[2]; + u32 win_atime[2]; +#else + u32 yst_uid; + u32 yst_gid; + u32 yst_atime; + u32 yst_mtime; + u32 yst_ctime; +#endif + + u32 yst_rdev; + + void *my_inode; + + u32 variant_type; /* enum yaffs_object_type */ + + union yaffs_obj_var variant; + +}; + +struct yaffs_obj_bucket { + struct list_head list; + int count; +}; + + +/*--------------------- Temporary buffers ---------------- + * + * These are chunk-sized working buffers. Each device has a few. + */ + +struct yaffs_buffer { + u8 *buffer; + int in_use; +}; + +/*----------------- Device ---------------------------------*/ + +struct yaffs_param { + const YCHAR *name; + + /* + * Entry parameters set up way early. Yaffs sets up the rest. + * The structure should be zeroed out before use so that unused + * and default values are zero. + */ + + int inband_tags; /* Use unband tags */ + u32 total_bytes_per_chunk; /* Should be >= 512, does not need to + be a power of 2 */ + u32 chunks_per_block; /* does not need to be a power of 2 */ + u32 spare_bytes_per_chunk; /* spare area size */ + u32 start_block; /* Start block we're allowed to use */ + u32 end_block; /* End block we're allowed to use */ + u32 n_reserved_blocks; /* Tuneable so that we can reduce + * reserved blocks on NOR and RAM. */ + + u32 n_caches; /* If == 0, then short op caching is disabled, + * else the number of short op caches. + */ + int cache_bypass_aligned; /* If non-zero then bypass the cache for + * aligned writes. + */ + + int use_nand_ecc; /* Flag to decide whether or not to use + * NAND driver ECC on data (yaffs1) */ + int tags_9bytes; /* Use 9 byte tags */ + int no_tags_ecc; /* Flag to decide whether or not to do ECC + * on packed tags (yaffs2) */ + + int is_yaffs2; /* Use yaffs2 mode on this device */ + + int empty_lost_n_found; /* Auto-empty lost+found directory on mount */ + + int refresh_period; /* How often to check for a block refresh */ + + /* Checkpoint control. Can be set before or after initialisation */ + u8 skip_checkpt_rd; + u8 skip_checkpt_wr; + + int enable_xattr; /* Enable xattribs */ + + int max_objects; /* + * Set to limit the number of objects created. + * 0 = no limit. + */ + + int hide_lost_n_found; /* Set non-zero to hide the lost-n-found dir. */ + + int stored_endian; /* 0=cpu endian, 1=little endian, 2=big endian */ + + /* The remove_obj_fn function must be supplied by OS flavours that + * need it. + * yaffs direct uses it to implement the faster readdir. + * Linux uses it to protect the directory during unlocking. + */ + void (*remove_obj_fn) (struct yaffs_obj *obj); + + /* Callback to mark the superblock dirty */ + void (*sb_dirty_fn) (struct yaffs_dev *dev); + + /* Callback to control garbage collection. */ + unsigned (*gc_control_fn) (struct yaffs_dev *dev); + + /* Debug control flags. Don't use unless you know what you're doing */ + int use_header_file_size; /* Flag to determine if we should use + * file sizes from the header */ + int disable_lazy_load; /* Disable lazy loading on this device */ + int wide_tnodes_disabled; /* Set to disable wide tnodes */ + int disable_soft_del; /* yaffs 1 only: Set to disable the use of + * softdeletion. */ + + int defered_dir_update; /* Set to defer directory updates */ + +#ifdef CONFIG_YAFFS_AUTO_UNICODE + int auto_unicode; +#endif + int always_check_erased; /* Force chunk erased check always on */ + + int disable_summary; + int disable_bad_block_marking; + +}; + +struct yaffs_driver { + int (*drv_write_chunk_fn) (struct yaffs_dev *dev, int nand_chunk, + const u8 *data, int data_len, + const u8 *oob, int oob_len); + int (*drv_read_chunk_fn) (struct yaffs_dev *dev, int nand_chunk, + u8 *data, int data_len, + u8 *oob, int oob_len, + enum yaffs_ecc_result *ecc_result); + int (*drv_erase_fn) (struct yaffs_dev *dev, int block_no); + int (*drv_mark_bad_fn) (struct yaffs_dev *dev, int block_no); + int (*drv_check_bad_fn) (struct yaffs_dev *dev, int block_no); + int (*drv_initialise_fn) (struct yaffs_dev *dev); + int (*drv_deinitialise_fn) (struct yaffs_dev *dev); +}; + +struct yaffs_tags_handler { + int (*write_chunk_tags_fn) (struct yaffs_dev *dev, + int nand_chunk, const u8 *data, + const struct yaffs_ext_tags *tags); + int (*read_chunk_tags_fn) (struct yaffs_dev *dev, + int nand_chunk, u8 *data, + struct yaffs_ext_tags *tags); + + int (*query_block_fn) (struct yaffs_dev *dev, int block_no, + enum yaffs_block_state *state, + u32 *seq_number); + int (*mark_bad_fn) (struct yaffs_dev *dev, int block_no); +}; + +struct yaffs_dev { + struct yaffs_param param; + struct yaffs_driver drv; + struct yaffs_tags_handler tagger; + + /* Context storage. Holds extra OS specific data for this device */ + + void *os_context; + void *driver_context; + + struct list_head dev_list; + + int ll_init; + /* Runtime parameters. Set up by YAFFS. */ + u32 data_bytes_per_chunk; + + /* Non-wide tnode stuff */ + u16 chunk_grp_bits; /* Number of bits that need to be resolved if + * the tnodes are not wide enough. + */ + u16 chunk_grp_size; /* == 2^^chunk_grp_bits */ + + struct yaffs_tnode *tn_swap_buffer; + + /* Stuff to support wide tnodes */ + u32 tnode_width; + u32 tnode_mask; + u32 tnode_size; + + /* Stuff for figuring out file offset to chunk conversions */ + u32 chunk_shift; /* Shift value */ + u32 chunk_div; /* Divisor after shifting: 1 for 2^n sizes */ + u32 chunk_mask; /* Mask to use for power-of-2 case */ + + int is_mounted; + int read_only; + int is_checkpointed; + int swap_endian; /* Stored endian needs endian swap. */ + + /* Stuff to support block offsetting to support start block zero */ + u32 internal_start_block; + u32 internal_end_block; + int block_offset; + int chunk_offset; + + /* Runtime checkpointing stuff */ + int checkpt_page_seq; /* running sequence number of checkpt pages */ + int checkpt_byte_count; + int checkpt_byte_offs; + u8 *checkpt_buffer; + int checkpt_open_write; + u32 blocks_in_checkpt; + int checkpt_cur_chunk; + int checkpt_cur_block; + int checkpt_next_block; + int *checkpt_block_list; + u32 checkpt_max_blocks; + u32 checkpt_sum; + u32 checkpt_xor; + + int checkpoint_blocks_required; /* Number of blocks needed to store + * current checkpoint set */ + + /* Block Info */ + struct yaffs_block_info *block_info; + u8 *chunk_bits; /* bitmap of chunks in use */ + u8 block_info_alt:1; /* allocated using alternative alloc */ + u8 chunk_bits_alt:1; /* allocated using alternative alloc */ + int chunk_bit_stride; /* Number of bytes of chunk_bits per block. + * Must be consistent with chunks_per_block. + */ + + int n_erased_blocks; + int alloc_block; /* Current block being allocated off */ + u32 alloc_page; + int alloc_block_finder; /* Used to search for next allocation block */ + + /* Object and Tnode memory management */ + void *allocator; + int n_obj; + int n_tnodes; + + int n_hardlinks; + + struct yaffs_obj_bucket obj_bucket[YAFFS_NOBJECT_BUCKETS]; + u32 bucket_finder; + + int n_free_chunks; + + /* Garbage collection control */ + u32 *gc_cleanup_list; /* objects to delete at the end of a GC. */ + u32 n_clean_ups; + + unsigned has_pending_prioritised_gc; /* We think this device might + have pending prioritised gcs */ + unsigned gc_disable; + unsigned gc_block_finder; + unsigned gc_dirtiest; + unsigned gc_pages_in_use; + unsigned gc_not_done; + unsigned gc_block; + unsigned gc_chunk; + unsigned gc_skip; + struct yaffs_summary_tags *gc_sum_tags; + + /* Special directories */ + struct yaffs_obj *root_dir; + struct yaffs_obj *lost_n_found; + + int buffered_block; /* Which block is buffered here? */ + int doing_buffered_block_rewrite; + + struct yaffs_cache *cache; + int cache_last_use; + + /* Stuff for background deletion and unlinked files. */ + struct yaffs_obj *unlinked_dir; /* Directory where unlinked and deleted + files live. */ + struct yaffs_obj *del_dir; /* Directory where deleted objects are + sent to disappear. */ + struct yaffs_obj *unlinked_deletion; /* Current file being + background deleted. */ + int n_deleted_files; /* Count of files awaiting deletion; */ + int n_unlinked_files; /* Count of unlinked files. */ + int n_bg_deletions; /* Count of background deletions. */ + + /* Temporary buffer management */ + struct yaffs_buffer temp_buffer[YAFFS_N_TEMP_BUFFERS]; + int max_temp; + int temp_in_use; + int unmanaged_buffer_allocs; + int unmanaged_buffer_deallocs; + + /* yaffs2 runtime stuff */ + unsigned seq_number; /* Sequence number of currently + allocating block */ + unsigned oldest_dirty_seq; + unsigned oldest_dirty_block; + + /* Block refreshing */ + int refresh_skip; /* A skip down counter. + * Refresh happens when this gets to zero. */ + + /* Dirty directory handling */ + struct list_head dirty_dirs; /* List of dirty directories */ + + /* Summary */ + int chunks_per_summary; + struct yaffs_summary_tags *sum_tags; + + /* Statistics */ + u32 n_page_writes; + u32 n_page_reads; + u32 n_erasures; + u32 n_bad_queries; + u32 n_bad_markings; + u32 n_erase_failures; + u32 n_gc_copies; + u32 all_gcs; + u32 passive_gc_count; + u32 oldest_dirty_gc_count; + u32 n_gc_blocks; + u32 bg_gcs; + u32 n_retried_writes; + u32 n_retired_blocks; + u32 n_ecc_fixed; + u32 n_ecc_unfixed; + u32 n_tags_ecc_fixed; + u32 n_tags_ecc_unfixed; + u32 n_deletions; + u32 n_unmarked_deletions; + u32 refresh_count; + u32 cache_hits; + u32 tags_used; + u32 summary_used; + +}; + +/* + * Checkpointing definitions. + */ + +#define YAFFS_CHECKPOINT_VERSION 8 + +/* yaffs_checkpt_obj holds the definition of an object as dumped + * by checkpointing. + */ + + +/* Checkpint object bits in bitfield: offset, length */ +#define CHECKPOINT_VARIANT_BITS 0, 3 +#define CHECKPOINT_DELETED_BITS 3, 1 +#define CHECKPOINT_SOFT_DEL_BITS 4, 1 +#define CHECKPOINT_UNLINKED_BITS 5, 1 +#define CHECKPOINT_FAKE_BITS 6, 1 +#define CHECKPOINT_RENAME_ALLOWED_BITS 7, 1 +#define CHECKPOINT_UNLINK_ALLOWED_BITS 8, 1 +#define CHECKPOINT_SERIAL_BITS 9, 8 + +struct yaffs_checkpt_obj { + int struct_type; + u32 obj_id; + u32 parent_id; + int hdr_chunk; + u32 bit_field; + int n_data_chunks; + loff_t size_or_equiv_obj; +}; + +/* The CheckpointDevice structure holds the device information that changes + *at runtime and must be preserved over unmount/mount cycles. + */ +struct yaffs_checkpt_dev { + int struct_type; + int n_erased_blocks; + int alloc_block; /* Current block being allocated off */ + u32 alloc_page; + int n_free_chunks; + + int n_deleted_files; /* Count of files awaiting deletion; */ + int n_unlinked_files; /* Count of unlinked files. */ + int n_bg_deletions; /* Count of background deletions. */ + + /* yaffs2 runtime stuff */ + unsigned seq_number; /* Sequence number of currently + * allocating block */ + +}; + +struct yaffs_checkpt_validity { + int struct_type; + u32 magic; + u32 version; + u32 head; +}; + +struct yaffs_shadow_fixer { + int obj_id; + int shadowed_id; + struct yaffs_shadow_fixer *next; +}; + +/* Structure for doing xattr modifications */ +struct yaffs_xattr_mod { + int set; /* If 0 then this is a deletion */ + const YCHAR *name; + const void *data; + int size; + int flags; + int result; +}; + +/*----------------------- YAFFS Functions -----------------------*/ + +int yaffs_guts_initialise(struct yaffs_dev *dev); +void yaffs_deinitialise(struct yaffs_dev *dev); + +int yaffs_get_n_free_chunks(struct yaffs_dev *dev); + +int yaffs_rename_obj(struct yaffs_obj *old_dir, const YCHAR * old_name, + struct yaffs_obj *new_dir, const YCHAR * new_name); + +int yaffs_unlink_obj(struct yaffs_obj *obj); + +int yaffs_unlinker(struct yaffs_obj *dir, const YCHAR * name); +int yaffs_del_obj(struct yaffs_obj *obj); +struct yaffs_obj *yaffs_retype_obj(struct yaffs_obj *obj, + enum yaffs_obj_type type); + + +int yaffs_get_obj_name(struct yaffs_obj *obj, YCHAR * name, int buffer_size); +loff_t yaffs_get_obj_length(struct yaffs_obj *obj); +int yaffs_get_obj_inode(struct yaffs_obj *obj); +unsigned yaffs_get_obj_type(struct yaffs_obj *obj); +int yaffs_get_obj_link_count(struct yaffs_obj *obj); + +/* File operations */ +int yaffs_file_rd(struct yaffs_obj *obj, u8 * buffer, loff_t offset, + int n_bytes); +int yaffs_wr_file(struct yaffs_obj *obj, const u8 * buffer, loff_t offset, + int n_bytes, int write_trhrough); +int yaffs_resize_file(struct yaffs_obj *obj, loff_t new_size); + +struct yaffs_obj *yaffs_create_file(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid); + +int yaffs_flush_file(struct yaffs_obj *in, + int update_time, + int data_sync, + int discard_cache); + +/* Flushing and checkpointing */ +void yaffs_flush_whole_cache(struct yaffs_dev *dev, int discard); + +int yaffs_checkpoint_save(struct yaffs_dev *dev); +int yaffs_checkpoint_restore(struct yaffs_dev *dev); + +/* Directory operations */ +struct yaffs_obj *yaffs_create_dir(struct yaffs_obj *parent, const YCHAR *name, + u32 mode, u32 uid, u32 gid); +struct yaffs_obj *yaffs_find_by_name(struct yaffs_obj *the_dir, + const YCHAR *name); +struct yaffs_obj *yaffs_find_by_number(struct yaffs_dev *dev, u32 number); + +/* Link operations */ +struct yaffs_obj *yaffs_link_obj(struct yaffs_obj *parent, const YCHAR *name, + struct yaffs_obj *equiv_obj); + +struct yaffs_obj *yaffs_get_equivalent_obj(struct yaffs_obj *obj); + +/* Symlink operations */ +struct yaffs_obj *yaffs_create_symlink(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid, const YCHAR *alias); +YCHAR *yaffs_get_symlink_alias(struct yaffs_obj *obj); + +/* Special inodes (fifos, sockets and devices) */ +struct yaffs_obj *yaffs_create_special(struct yaffs_obj *parent, + const YCHAR *name, u32 mode, u32 uid, + u32 gid, u32 rdev); + +int yaffs_set_xattrib(struct yaffs_obj *obj, const YCHAR *name, + const void *value, int size, int flags); +int yaffs_get_xattrib(struct yaffs_obj *obj, const YCHAR *name, void *value, + int size); +int yaffs_list_xattrib(struct yaffs_obj *obj, char *buffer, int size); +int yaffs_remove_xattrib(struct yaffs_obj *obj, const YCHAR *name); + +/* Special directories */ +struct yaffs_obj *yaffs_root(struct yaffs_dev *dev); +struct yaffs_obj *yaffs_lost_n_found(struct yaffs_dev *dev); + +void yaffs_handle_defered_free(struct yaffs_obj *obj); + +void yaffs_update_dirty_dirs(struct yaffs_dev *dev); + +int yaffs_bg_gc(struct yaffs_dev *dev, unsigned urgency); + +/* Debug dump */ +int yaffs_dump_obj(struct yaffs_obj *obj); + +void yaffs_guts_test(struct yaffs_dev *dev); +int yaffs_guts_ll_init(struct yaffs_dev *dev); + + +/* A few useful functions to be used within the core files*/ +void yaffs_chunk_del(struct yaffs_dev *dev, int chunk_id, int mark_flash, + int lyn); +int yaffs_check_ff(u8 *buffer, int n_bytes); +void yaffs_handle_chunk_error(struct yaffs_dev *dev, + struct yaffs_block_info *bi); + +u8 *yaffs_get_temp_buffer(struct yaffs_dev *dev); +void yaffs_release_temp_buffer(struct yaffs_dev *dev, u8 *buffer); + +struct yaffs_obj *yaffs_find_or_create_by_number(struct yaffs_dev *dev, + int number, + enum yaffs_obj_type type); +int yaffs_put_chunk_in_file(struct yaffs_obj *in, int inode_chunk, + int nand_chunk, int in_scan); +void yaffs_set_obj_name(struct yaffs_obj *obj, const YCHAR *name); +void yaffs_set_obj_name_from_oh(struct yaffs_obj *obj, + const struct yaffs_obj_hdr *oh); +void yaffs_add_obj_to_dir(struct yaffs_obj *directory, struct yaffs_obj *obj); +YCHAR *yaffs_clone_str(const YCHAR *str); +void yaffs_link_fixup(struct yaffs_dev *dev, struct list_head *hard_list); +void yaffs_block_became_dirty(struct yaffs_dev *dev, int block_no); +int yaffs_update_oh(struct yaffs_obj *in, const YCHAR *name, + int force, int is_shrink, int shadows, + struct yaffs_xattr_mod *xop); +void yaffs_handle_shadowed_obj(struct yaffs_dev *dev, int obj_id, + int backward_scanning); +int yaffs_check_alloc_available(struct yaffs_dev *dev, int n_chunks); +struct yaffs_tnode *yaffs_get_tnode(struct yaffs_dev *dev); +struct yaffs_tnode *yaffs_add_find_tnode_0(struct yaffs_dev *dev, + struct yaffs_file_var *file_struct, + u32 chunk_id, + struct yaffs_tnode *passed_tn); + +int yaffs_do_file_wr(struct yaffs_obj *in, const u8 *buffer, loff_t offset, + int n_bytes, int write_trhrough); +void yaffs_resize_file_down(struct yaffs_obj *obj, loff_t new_size); +void yaffs_skip_rest_of_block(struct yaffs_dev *dev); + +int yaffs_count_free_chunks(struct yaffs_dev *dev); + +struct yaffs_tnode *yaffs_find_tnode_0(struct yaffs_dev *dev, + struct yaffs_file_var *file_struct, + u32 chunk_id); + +u32 yaffs_get_group_base(struct yaffs_dev *dev, struct yaffs_tnode *tn, + unsigned pos); + +int yaffs_is_non_empty_dir(struct yaffs_obj *obj); + +int yaffs_guts_format_dev(struct yaffs_dev *dev); + +void yaffs_addr_to_chunk(struct yaffs_dev *dev, loff_t addr, + int *chunk_out, u32 *offset_out); +/* + * Marshalling functions to get loff_t file sizes into and out of + * object headers. + */ +void yaffs_oh_size_load(struct yaffs_dev *dev, struct yaffs_obj_hdr *oh, + loff_t fsize, int do_endian); +loff_t yaffs_oh_to_size(struct yaffs_dev *dev, struct yaffs_obj_hdr *oh, + int do_endian); +loff_t yaffs_max_file_size(struct yaffs_dev *dev); + +/* + * Debug function to count number of blocks in each state + * NB Needs to be called with correct number of integers + */ + +void yaffs_count_blocks_by_state(struct yaffs_dev *dev, int bs[10]); + +int yaffs_find_chunk_in_file(struct yaffs_obj *in, int inode_chunk, + struct yaffs_ext_tags *tags); + +/* + * Define LOFF_T_32_BIT if a 32-bit LOFF_T is being used. + * Not serious if you get this wrong - you might just get some warnings. +*/ + +#ifdef LOFF_T_32_BIT +#define FSIZE_LOW(fsize) (fsize) +#define FSIZE_HIGH(fsize) 0 +#define FSIZE_COMBINE(high, low) (low) +#else +#define FSIZE_LOW(fsize) ((fsize) & 0xffffffff) +#define FSIZE_HIGH(fsize)(((fsize) >> 32) & 0xffffffff) +#define FSIZE_COMBINE(high, low) ((((loff_t) (high)) << 32) | \ + (((loff_t) (low)) & 0xFFFFFFFF)) +#endif + + +#endif diff --git a/fs/yaffs2/yaffs_linux.h b/fs/yaffs2/yaffs_linux.h new file mode 100644 index 000000000000..68e33f10c3f0 --- /dev/null +++ b/fs/yaffs2/yaffs_linux.h @@ -0,0 +1,47 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_LINUX_H__ +#define __YAFFS_LINUX_H__ + +#include "yportenv.h" + +struct yaffs_linux_context { + struct list_head context_list; /* List of these we have mounted */ + struct yaffs_dev *dev; + struct super_block *super; + struct task_struct *bg_thread; /* Background thread for this device */ + int bg_running; + struct mutex gross_lock; /* Gross locking mutex*/ + u8 *spare_buffer; /* For mtdif2 use. Don't know the buffer size + * at compile time so we have to allocate it. + */ + struct list_head search_contexts; + struct task_struct *readdir_process; + unsigned mount_id; + int dirty; +}; + +#define yaffs_dev_to_lc(dev) ((struct yaffs_linux_context *)((dev)->os_context)) +#define yaffs_dev_to_mtd(dev) ((struct mtd_info *)((dev)->driver_context)) + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +#define WRITE_SIZE_STR "writesize" +#define WRITE_SIZE(mtd) ((mtd)->writesize) +#else +#define WRITE_SIZE_STR "oobblock" +#define WRITE_SIZE(mtd) ((mtd)->oobblock) +#endif + +#endif diff --git a/fs/yaffs2/yaffs_mtdif.c b/fs/yaffs2/yaffs_mtdif.c new file mode 100644 index 000000000000..ecc53f6814b6 --- /dev/null +++ b/fs/yaffs2/yaffs_mtdif.c @@ -0,0 +1,321 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yportenv.h" + +#include "yaffs_mtdif.h" + +#include "linux/mtd/mtd.h" +#include "linux/types.h" +#include "linux/time.h" +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 14, 0)) +#include "linux/mtd/nand.h" +#else +#include "linux/mtd/rawnand.h" +#endif +#include "linux/kernel.h" +#include "linux/version.h" +#include "linux/types.h" +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 14, 0)) +#include "uapi/linux/major.h" +#endif + +#include "yaffs_trace.h" +#include "yaffs_guts.h" +#include "yaffs_linux.h" +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 2, 0)) +#define MTD_OPS_AUTO_OOB MTD_OOB_AUTO +#endif + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)) +#define mtd_erase(m, ei) (m)->erase(m, ei) +#define mtd_write_oob(m, addr, pops) (m)->write_oob(m, addr, pops) +#define mtd_read_oob(m, addr, pops) (m)->read_oob(m, addr, pops) +#define mtd_block_isbad(m, offs) (m)->block_isbad(m, offs) +#define mtd_block_markbad(m, offs) (m)->block_markbad(m, offs) +#endif + +int nandmtd_erase_block(struct yaffs_dev *dev, int block_no) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + u32 addr = ((loff_t) block_no) * dev->param.total_bytes_per_chunk * + dev->param.chunks_per_block; + struct erase_info ei; + int retval = 0; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 17, 0)) + ei.mtd = mtd; +#endif + ei.addr = addr; + ei.len = dev->param.total_bytes_per_chunk * dev->param.chunks_per_block; +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 17, 0)) + ei.time = 1000; + ei.retries = 2; + ei.callback = NULL; + ei.priv = (u_long) dev; +#endif + + retval = mtd_erase(mtd, &ei); + + if (retval == 0) + return YAFFS_OK; + + return YAFFS_FAIL; +} + +static int yaffs_mtd_write(struct yaffs_dev *dev, int nand_chunk, + const u8 *data, int data_len, + const u8 *oob, int oob_len) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + loff_t addr; + struct mtd_oob_ops ops; + int retval; + + yaffs_trace(YAFFS_TRACE_MTD, + "yaffs_mtd_write(%p, %d, %p, %d, %p, %d)\n", + dev, nand_chunk, data, data_len, oob, oob_len); + + if (!data || !data_len) { + data = NULL; + data_len = 0; + } + + if (!oob || !oob_len) { + oob = NULL; + oob_len = 0; + } + + addr = ((loff_t) nand_chunk) * dev->param.total_bytes_per_chunk; + memset(&ops, 0, sizeof(ops)); + ops.mode = MTD_OPS_AUTO_OOB; + ops.len = (data) ? data_len : 0; + ops.ooblen = oob_len; + ops.datbuf = (u8 *)data; + ops.oobbuf = (u8 *)oob; + + retval = mtd_write_oob(mtd, addr, &ops); + if (retval) { + yaffs_trace(YAFFS_TRACE_MTD, + "write_oob failed, chunk %d, mtd error %d", + nand_chunk, retval); + } + return retval ? YAFFS_FAIL : YAFFS_OK; +} + +static int yaffs_mtd_read(struct yaffs_dev *dev, int nand_chunk, + u8 *data, int data_len, + u8 *oob, int oob_len, + enum yaffs_ecc_result *ecc_result) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + loff_t addr; + struct mtd_oob_ops ops; + int retval; + + addr = ((loff_t) nand_chunk) * dev->param.total_bytes_per_chunk; + memset(&ops, 0, sizeof(ops)); + ops.mode = MTD_OPS_AUTO_OOB; + ops.len = (data) ? data_len : 0; + ops.ooblen = oob_len; + ops.datbuf = data; + ops.oobbuf = oob; + +#if (MTD_VERSION_CODE < MTD_VERSION(2, 6, 20)) + /* In MTD 2.6.18 to 2.6.19 nand_base.c:nand_do_read_oob() has a bug; + * help it out with ops.len = ops.ooblen when ops.datbuf == NULL. + */ + ops.len = (ops.datbuf) ? ops.len : ops.ooblen; +#endif + /* Read page and oob using MTD. + * Check status and determine ECC result. + */ + retval = mtd_read_oob(mtd, addr, &ops); + if (retval) + yaffs_trace(YAFFS_TRACE_MTD, + "read_oob failed, chunk %d, mtd error %d", + nand_chunk, retval); + + switch (retval) { + case 0: + /* no error */ + if(ecc_result) + *ecc_result = YAFFS_ECC_RESULT_NO_ERROR; + break; + + case -EUCLEAN: + /* MTD's ECC fixed the data */ + if(ecc_result) + *ecc_result = YAFFS_ECC_RESULT_FIXED; + dev->n_ecc_fixed++; + break; + + case -EBADMSG: + default: + /* MTD's ECC could not fix the data */ + dev->n_ecc_unfixed++; + if(ecc_result) + *ecc_result = YAFFS_ECC_RESULT_UNFIXED; + return YAFFS_FAIL; + } + + return YAFFS_OK; +} + +static int yaffs_mtd_erase(struct yaffs_dev *dev, int block_no) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + + loff_t addr; + struct erase_info ei; + int retval = 0; + u32 block_size; + + block_size = dev->param.total_bytes_per_chunk * + dev->param.chunks_per_block; + addr = ((loff_t) block_no) * block_size; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 17, 0)) + ei.mtd = mtd; +#endif + ei.addr = addr; + ei.len = block_size; +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 17, 0)) + ei.time = 1000; + ei.retries = 2; + ei.callback = NULL; + ei.priv = (u_long) dev; +#endif + + retval = mtd_erase(mtd, &ei); + + if (retval == 0) + return YAFFS_OK; + + return YAFFS_FAIL; +} + +static int yaffs_mtd_mark_bad(struct yaffs_dev *dev, int block_no) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + int blocksize = dev->param.chunks_per_block * dev->param.total_bytes_per_chunk; + int retval; + + yaffs_trace(YAFFS_TRACE_BAD_BLOCKS, "marking block %d bad", block_no); + + retval = mtd_block_markbad(mtd, (loff_t) blocksize * block_no); + return (retval) ? YAFFS_FAIL : YAFFS_OK; +} + +static int yaffs_mtd_check_bad(struct yaffs_dev *dev, int block_no) +{ + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + int blocksize = dev->param.chunks_per_block * dev->param.total_bytes_per_chunk; + int retval; + + yaffs_trace(YAFFS_TRACE_MTD, "checking block %d bad", block_no); + + retval = mtd_block_isbad(mtd, (loff_t) blocksize * block_no); + return (retval) ? YAFFS_FAIL : YAFFS_OK; +} + +static int yaffs_mtd_initialise(struct yaffs_dev *dev) +{ + return YAFFS_OK; +} + +static int yaffs_mtd_deinitialise(struct yaffs_dev *dev) +{ + return YAFFS_OK; +} + +void yaffs_mtd_drv_install(struct yaffs_dev *dev) +{ + struct yaffs_driver *drv = &dev->drv; + + drv->drv_write_chunk_fn = yaffs_mtd_write; + drv->drv_read_chunk_fn = yaffs_mtd_read; + drv->drv_erase_fn = yaffs_mtd_erase; + drv->drv_mark_bad_fn = yaffs_mtd_mark_bad; + drv->drv_check_bad_fn = yaffs_mtd_check_bad; + drv->drv_initialise_fn = yaffs_mtd_initialise; + drv->drv_deinitialise_fn = yaffs_mtd_deinitialise; +} + +struct mtd_info * yaffs_get_mtd_device(dev_t sdev) +{ + struct mtd_info *mtd; + + /* Check it's an mtd device..... */ + if (MAJOR(sdev) != MTD_BLOCK_MAJOR) + return NULL; /* This isn't an mtd device */ + + /* Get the device */ + mtd = get_mtd_device(NULL, MINOR(sdev)); + if (IS_ERR_OR_NULL(mtd)) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: MTD device %u either not valid or unavailable", + MINOR(sdev)); + return NULL; + } + + /* Check it's NAND */ + if (mtd->type != MTD_NANDFLASH) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: MTD device is not NAND it's type %d", + mtd->type); + put_mtd_device(mtd); + return NULL; + } + + yaffs_trace(YAFFS_TRACE_OS, " %s %d", WRITE_SIZE_STR, WRITE_SIZE(mtd)); + yaffs_trace(YAFFS_TRACE_OS, " oobsize %d", mtd->oobsize); + yaffs_trace(YAFFS_TRACE_OS, " erasesize %d", mtd->erasesize); +#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 29) + yaffs_trace(YAFFS_TRACE_OS, " size %u", mtd->size); +#else + yaffs_trace(YAFFS_TRACE_OS, " size %lld", mtd->size); +#endif + + return mtd; +} + +int yaffs_verify_mtd(struct mtd_info *mtd, int yaffs_version, int inband_tags) +{ + if (yaffs_version == 2) { + if ((WRITE_SIZE(mtd) < YAFFS_MIN_YAFFS2_CHUNK_SIZE || + mtd->oobsize < YAFFS_MIN_YAFFS2_SPARE_SIZE) && + !inband_tags) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "MTD device does not have the right page sizes" + ); + return -1; + } + } else { + if (WRITE_SIZE(mtd) < YAFFS_BYTES_PER_CHUNK || + mtd->oobsize != YAFFS_BYTES_PER_SPARE) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "MTD device does not support have the right page sizes" + ); + return -1; + } + } + + return 0; +} + +void yaffs_put_mtd_device(struct mtd_info *mtd) +{ + if (mtd) + put_mtd_device(mtd); +} diff --git a/fs/yaffs2/yaffs_mtdif.h b/fs/yaffs2/yaffs_mtdif.h new file mode 100644 index 000000000000..54d0d62b0cde --- /dev/null +++ b/fs/yaffs2/yaffs_mtdif.h @@ -0,0 +1,24 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_MTDIF_H__ +#define __YAFFS_MTDIF_H__ + +#include "yaffs_guts.h" + +void yaffs_mtd_drv_install(struct yaffs_dev *dev); +struct mtd_info * yaffs_get_mtd_device(dev_t sdev); +void yaffs_put_mtd_device(struct mtd_info *mtd); +int yaffs_verify_mtd(struct mtd_info *mtd, int yaffs_version, int inband_tags); +#endif diff --git a/fs/yaffs2/yaffs_nameval.c b/fs/yaffs2/yaffs_nameval.c new file mode 100644 index 000000000000..b85536522ebe --- /dev/null +++ b/fs/yaffs2/yaffs_nameval.c @@ -0,0 +1,229 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * This simple implementation of a name-value store assumes a small number of +* values and fits into a small finite buffer. + * + * Each attribute is stored as a record: + * sizeof(size) bytes record size. + * strnlen+1 bytes name null terminated. + * nbytes value. + * ---------- + * total size stored in record size + * + * This code has not been tested with unicode yet. + */ + +#include "yaffs_nameval.h" +#include "yaffs_guts.h" +#include "yportenv.h" +#include "yaffs_endian.h" + +static int nval_find(struct yaffs_dev *dev, + const char *xb, int xb_size, const YCHAR *name, + int *exist_size) +{ + int pos = 0; + s32 size; + + memcpy(&size, xb, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + + while (size > 0 && (size < xb_size) && (pos + size < xb_size)) { + if (!strncmp((YCHAR *) (xb + pos + sizeof(size)), + name, size)) { + if (exist_size) + *exist_size = size; + return pos; + } + pos += size; + if (pos < (int)(xb_size - sizeof(size))) { + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + + } else + size = 0; + } + if (exist_size) + *exist_size = 0; + return -ENODATA; +} + +static int nval_used(struct yaffs_dev *dev, const char *xb, int xb_size) +{ + int pos = 0; + s32 size; + + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + + while (size > 0 && (size < xb_size) && (pos + size < xb_size)) { + pos += size; + if (pos < (int)(xb_size - sizeof(size))) { + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + } else + size = 0; + } + return pos; +} + +int nval_del(struct yaffs_dev *dev, char *xb, int xb_size, const YCHAR *name) +{ + int pos = nval_find(dev, xb, xb_size, name, NULL); + s32 size; + + if (pos < 0 || pos >= xb_size) + return -ENODATA; + + /* Find size, shift rest over this record, + * then zero out the rest of buffer */ + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + + memcpy(xb + pos, xb + pos + size, xb_size - (pos + size)); + memset(xb + (xb_size - size), 0, size); + return 0; +} + +int nval_set(struct yaffs_dev *dev, + char *xb, int xb_size, const YCHAR *name, const char *buf, + int bsize, int flags) +{ + int pos; + int namelen = strnlen(name, xb_size); + int size_exist = 0; + int space; + int start; + s32 reclen; + s32 reclen_endianised; + + pos = nval_find(dev, xb, xb_size, name, &size_exist); + + if (flags & XATTR_CREATE && pos >= 0) + return -EEXIST; + if (flags & XATTR_REPLACE && pos < 0) + return -ENODATA; + + start = nval_used(dev, xb, xb_size); + space = xb_size - start + size_exist; + + reclen = (sizeof(reclen) + namelen + 1 + bsize); + + if (reclen > space) + return -ENOSPC; + + if (pos >= 0) { + /* Exists, so delete it. */ + nval_del(dev, xb, xb_size, name); + start = nval_used(dev, xb, xb_size); + } + + pos = start; + + reclen_endianised = reclen; + yaffs_do_endian_s32(dev, &reclen_endianised); + memcpy(xb + pos, &reclen_endianised, sizeof(reclen_endianised)); + pos += sizeof(reclen_endianised); + strncpy((YCHAR *) (xb + pos), name, reclen); + pos += (namelen + 1); + memcpy(xb + pos, buf, bsize); + return 0; +} + +int nval_get(struct yaffs_dev *dev, + const char *xb, int xb_size, const YCHAR * name, char *buf, + int bsize) +{ + int pos = nval_find(dev, xb, xb_size, name, NULL); + s32 size; + + if (pos >= 0 && pos < xb_size) { + + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + pos += sizeof(size); /* advance past record length */ + size -= sizeof(size); + + /* Advance over name string */ + while (xb[pos] && size > 0 && pos < xb_size) { + pos++; + size--; + } + /*Advance over NUL */ + pos++; + size--; + + /* If bsize is zero then this is a size query. + * Return the size, but don't copy. + */ + if (!bsize) + return size; + + if (size <= bsize) { + memcpy(buf, xb + pos, size); + return size; + } + } + if (pos >= 0) + return -ERANGE; + + return -ENODATA; +} + +int nval_list(struct yaffs_dev *dev, const char *xb, int xb_size, char *buf, int bsize) +{ + int pos = 0; + s32 size; + int name_len; + int ncopied = 0; + int filled = 0; + + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + + while (size > (int)(sizeof(size)) && + size <= xb_size && + (pos + size) < xb_size && + !filled) { + pos += sizeof(size); + size -= sizeof(size); + name_len = strnlen((YCHAR *) (xb + pos), size); + if (ncopied + name_len + 1 < bsize) { + memcpy(buf, xb + pos, name_len * sizeof(YCHAR)); + buf += name_len; + *buf = '\0'; + buf++; + if (sizeof(YCHAR) > 1) { + *buf = '\0'; + buf++; + } + ncopied += (name_len + 1); + } else { + filled = 1; + } + pos += size; + if (pos < (int)(xb_size - sizeof(size))) { + memcpy(&size, xb + pos, sizeof(size)); + yaffs_do_endian_s32(dev, &size); + } + else + size = 0; + } + return ncopied; +} + +int nval_hasvalues(struct yaffs_dev *dev, const char *xb, int xb_size) +{ + return nval_used(dev, xb, xb_size) > 0; +} diff --git a/fs/yaffs2/yaffs_nameval.h b/fs/yaffs2/yaffs_nameval.h new file mode 100644 index 000000000000..7dbdbb68aa2d --- /dev/null +++ b/fs/yaffs2/yaffs_nameval.h @@ -0,0 +1,32 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __NAMEVAL_H__ +#define __NAMEVAL_H__ + +#include "yportenv.h" + +struct yaffs_dev; + +int nval_del(struct yaffs_dev *dev, char *xb, int xb_size, const YCHAR * name); +int nval_set(struct yaffs_dev *dev, + char *xb, int xb_size, const YCHAR * name, const char *buf, + int bsize, int flags); +int nval_get(struct yaffs_dev *dev, + const char *xb, int xb_size, const YCHAR * name, char *buf, + int bsize); +int nval_list(struct yaffs_dev *dev, + const char *xb, int xb_size, char *buf, int bsize); +int nval_hasvalues(struct yaffs_dev *dev, const char *xb, int xb_size); +#endif diff --git a/fs/yaffs2/yaffs_nand.c b/fs/yaffs2/yaffs_nand.c new file mode 100644 index 000000000000..fe1219095c52 --- /dev/null +++ b/fs/yaffs2/yaffs_nand.c @@ -0,0 +1,121 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_nand.h" +#include "yaffs_tagscompat.h" + +#include "yaffs_getblockinfo.h" +#include "yaffs_summary.h" + +static int apply_chunk_offset(struct yaffs_dev *dev, int chunk) +{ + return chunk - dev->chunk_offset; +} + +int yaffs_rd_chunk_tags_nand(struct yaffs_dev *dev, int nand_chunk, + u8 *buffer, struct yaffs_ext_tags *tags) +{ + int result; + struct yaffs_ext_tags local_tags; + int flash_chunk = apply_chunk_offset(dev, nand_chunk); + + dev->n_page_reads++; + + /* If there are no tags provided use local tags. */ + if (!tags) + tags = &local_tags; + + result = dev->tagger.read_chunk_tags_fn(dev, flash_chunk, buffer, tags); + if (tags && tags->ecc_result > YAFFS_ECC_RESULT_NO_ERROR) { + + struct yaffs_block_info *bi; + bi = yaffs_get_block_info(dev, + nand_chunk / + dev->param.chunks_per_block); + yaffs_handle_chunk_error(dev, bi); + } + return result; +} + +int yaffs_wr_chunk_tags_nand(struct yaffs_dev *dev, + int nand_chunk, + const u8 *buffer, struct yaffs_ext_tags *tags) +{ + int result; + int flash_chunk = apply_chunk_offset(dev, nand_chunk); + + dev->n_page_writes++; + + if (!tags) { + yaffs_trace(YAFFS_TRACE_ERROR, "Writing with no tags"); + BUG(); + return YAFFS_FAIL; + } + + tags->seq_number = dev->seq_number; + tags->chunk_used = 1; + yaffs_trace(YAFFS_TRACE_WRITE, + "Writing chunk %d tags %d %d", + nand_chunk, tags->obj_id, tags->chunk_id); + + result = dev->tagger.write_chunk_tags_fn(dev, flash_chunk, + buffer, tags); + + yaffs_summary_add(dev, tags, nand_chunk); + + return result; +} + +int yaffs_mark_bad(struct yaffs_dev *dev, int block_no) +{ + block_no -= dev->block_offset; + dev->n_bad_markings++; + + if (dev->param.disable_bad_block_marking) + return YAFFS_OK; + + return dev->tagger.mark_bad_fn(dev, block_no); +} + + +int yaffs_query_init_block_state(struct yaffs_dev *dev, + int block_no, + enum yaffs_block_state *state, + u32 *seq_number) +{ + block_no -= dev->block_offset; + return dev->tagger.query_block_fn(dev, block_no, state, seq_number); +} + +int yaffs_erase_block(struct yaffs_dev *dev, int block_no) +{ + int result; + + block_no -= dev->block_offset; + dev->n_erasures++; + result = dev->drv.drv_erase_fn(dev, block_no); + return result; +} + +int yaffs_init_nand(struct yaffs_dev *dev) +{ + if (dev->drv.drv_initialise_fn) + return dev->drv.drv_initialise_fn(dev); + return YAFFS_OK; +} + +int yaffs_deinit_nand(struct yaffs_dev *dev) +{ + if (dev->drv.drv_deinitialise_fn) + return dev->drv.drv_deinitialise_fn(dev); + return YAFFS_OK; +} diff --git a/fs/yaffs2/yaffs_nand.h b/fs/yaffs2/yaffs_nand.h new file mode 100644 index 000000000000..8964db0a8fdb --- /dev/null +++ b/fs/yaffs2/yaffs_nand.h @@ -0,0 +1,38 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_NAND_H__ +#define __YAFFS_NAND_H__ +#include "yaffs_guts.h" + +int yaffs_rd_chunk_tags_nand(struct yaffs_dev *dev, int nand_chunk, + u8 *buffer, struct yaffs_ext_tags *tags); + +int yaffs_wr_chunk_tags_nand(struct yaffs_dev *dev, + int nand_chunk, + const u8 *buffer, struct yaffs_ext_tags *tags); + +int yaffs_mark_bad(struct yaffs_dev *dev, int block_no); + +int yaffs_query_init_block_state(struct yaffs_dev *dev, + int block_no, + enum yaffs_block_state *state, + unsigned *seq_number); + +int yaffs_erase_block(struct yaffs_dev *dev, int flash_block); + +int yaffs_init_nand(struct yaffs_dev *dev); +int yaffs_deinit_nand(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_packedtags1.c b/fs/yaffs2/yaffs_packedtags1.c new file mode 100644 index 000000000000..fab4fc14e3e6 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags1.c @@ -0,0 +1,54 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_packedtags1.h" +#include "yportenv.h" + +static const u8 all_ff[20] = { + 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff +}; + +void yaffs_pack_tags1(struct yaffs_packed_tags1 *pt, + const struct yaffs_ext_tags *t) +{ + pt->chunk_id = t->chunk_id; + pt->serial_number = t->serial_number; + pt->n_bytes = t->n_bytes; + pt->obj_id = t->obj_id; + pt->ecc = 0; + pt->deleted = (t->is_deleted) ? 0 : 1; + pt->unused_stuff = 0; + pt->should_be_ff = 0xffffffff; +} + +void yaffs_unpack_tags1(struct yaffs_ext_tags *t, + const struct yaffs_packed_tags1 *pt) +{ + if (memcmp(all_ff, pt, sizeof(struct yaffs_packed_tags1))) { + t->block_bad = 0; + if (pt->should_be_ff != 0xffffffff) + t->block_bad = 1; + t->chunk_used = 1; + t->obj_id = pt->obj_id; + t->chunk_id = pt->chunk_id; + t->n_bytes = pt->n_bytes; + t->ecc_result = YAFFS_ECC_RESULT_NO_ERROR; + t->is_deleted = (pt->deleted) ? 0 : 1; + t->serial_number = pt->serial_number; + } else { + memset(t, 0, sizeof(struct yaffs_ext_tags)); + } +} diff --git a/fs/yaffs2/yaffs_packedtags1.h b/fs/yaffs2/yaffs_packedtags1.h new file mode 100644 index 000000000000..aef36d910479 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags1.h @@ -0,0 +1,38 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +/* This is used to pack YAFFS1 tags, not YAFFS2 tags. */ + +#ifndef __YAFFS_PACKEDTAGS1_H__ +#define __YAFFS_PACKEDTAGS1_H__ + +#include "yaffs_guts.h" + +struct yaffs_packed_tags1 { + u32 chunk_id:20; + u32 serial_number:2; + u32 n_bytes:10; + u32 obj_id:18; + u32 ecc:12; + u32 deleted:1; + u32 unused_stuff:1; + unsigned should_be_ff; + +}; + +void yaffs_pack_tags1(struct yaffs_packed_tags1 *pt, + const struct yaffs_ext_tags *t); +void yaffs_unpack_tags1(struct yaffs_ext_tags *t, + const struct yaffs_packed_tags1 *pt); +#endif diff --git a/fs/yaffs2/yaffs_packedtags2.c b/fs/yaffs2/yaffs_packedtags2.c new file mode 100644 index 000000000000..e8fd94578e95 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags2.c @@ -0,0 +1,207 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_packedtags2.h" +#include "yportenv.h" +#include "yaffs_trace.h" +#include "yaffs_endian.h" + +/* This code packs a set of extended tags into a binary structure for + * NAND storage + */ + +/* Some of the information is "extra" struff which can be packed in to + * speed scanning + * This is defined by having the EXTRA_HEADER_INFO_FLAG set. + */ + +/* Extra flags applied to chunk_id */ + +#define EXTRA_HEADER_INFO_FLAG 0x80000000 +#define EXTRA_SHRINK_FLAG 0x40000000 +#define EXTRA_SHADOWS_FLAG 0x20000000 +#define EXTRA_SPARE_FLAGS 0x10000000 + +#define ALL_EXTRA_FLAGS 0xf0000000 + +/* Also, the top 4 bits of the object Id are set to the object type. */ +#define EXTRA_OBJECT_TYPE_SHIFT (28) +#define EXTRA_OBJECT_TYPE_MASK ((0x0f) << EXTRA_OBJECT_TYPE_SHIFT) + +static void yaffs_dump_packed_tags2_tags_only( + const struct yaffs_packed_tags2_tags_only *ptt) +{ + yaffs_trace(YAFFS_TRACE_MTD, + "packed tags obj %d chunk %d byte %d seq %d", + ptt->obj_id, ptt->chunk_id, ptt->n_bytes, ptt->seq_number); +} + +static void yaffs_dump_packed_tags2(const struct yaffs_packed_tags2 *pt) +{ + yaffs_dump_packed_tags2_tags_only(&pt->t); +} + +static void yaffs_dump_tags2(const struct yaffs_ext_tags *t) +{ + yaffs_trace(YAFFS_TRACE_MTD, + "ext.tags eccres %d blkbad %d chused %d obj %d chunk%d byte %d del %d ser %d seq %d", + t->ecc_result, t->block_bad, t->chunk_used, t->obj_id, + t->chunk_id, t->n_bytes, t->is_deleted, t->serial_number, + t->seq_number); + +} + +static int yaffs_check_tags_extra_packable(const struct yaffs_ext_tags *t) +{ + if (t->chunk_id != 0 || !t->extra_available) + return 0; + + /* Check if the file size is too long to store */ + if (t->extra_obj_type == YAFFS_OBJECT_TYPE_FILE && + (t->extra_file_size >> 31) != 0) + return 0; + return 1; +} + +void yaffs_pack_tags2_tags_only(struct yaffs_dev *dev, + struct yaffs_packed_tags2_tags_only *ptt, + const struct yaffs_ext_tags *t) +{ + ptt->chunk_id = t->chunk_id; + ptt->seq_number = t->seq_number; + ptt->n_bytes = t->n_bytes; + ptt->obj_id = t->obj_id; + + /* Only store extra tags for object headers. + * If it is a file then only store if the file size is short\ + * enough to fit. + */ + if (yaffs_check_tags_extra_packable(t)) { + /* Store the extra header info instead */ + /* We save the parent object in the chunk_id */ + ptt->chunk_id = EXTRA_HEADER_INFO_FLAG | t->extra_parent_id; + if (t->extra_is_shrink) + ptt->chunk_id |= EXTRA_SHRINK_FLAG; + if (t->extra_shadows) + ptt->chunk_id |= EXTRA_SHADOWS_FLAG; + + ptt->obj_id &= ~EXTRA_OBJECT_TYPE_MASK; + ptt->obj_id |= (t->extra_obj_type << EXTRA_OBJECT_TYPE_SHIFT); + + if (t->extra_obj_type == YAFFS_OBJECT_TYPE_HARDLINK) + ptt->n_bytes = t->extra_equiv_id; + else if (t->extra_obj_type == YAFFS_OBJECT_TYPE_FILE) + ptt->n_bytes = (unsigned) t->extra_file_size; + else + ptt->n_bytes = 0; + } + + yaffs_dump_packed_tags2_tags_only(ptt); + yaffs_dump_tags2(t); + yaffs_do_endian_packed_tags2(dev, ptt); +} + +void yaffs_pack_tags2(struct yaffs_dev *dev, + struct yaffs_packed_tags2 *pt, + const struct yaffs_ext_tags *t, int tags_ecc) +{ + yaffs_pack_tags2_tags_only(dev, &pt->t, t); + + if (tags_ecc) + yaffs_ecc_calc_other((unsigned char *)&pt->t, + sizeof(struct yaffs_packed_tags2_tags_only), + &pt->ecc); +} + +void yaffs_unpack_tags2_tags_only(struct yaffs_dev *dev, + struct yaffs_ext_tags *t, + struct yaffs_packed_tags2_tags_only *ptt_ptr) +{ + struct yaffs_packed_tags2_tags_only ptt_copy = *ptt_ptr; + + memset(t, 0, sizeof(struct yaffs_ext_tags)); + + if (ptt_copy.seq_number == 0xffffffff) + return; + + yaffs_do_endian_packed_tags2(dev, &ptt_copy); + + t->block_bad = 0; + t->chunk_used = 1; + t->obj_id = ptt_copy.obj_id; + t->chunk_id = ptt_copy.chunk_id; + t->n_bytes = ptt_copy.n_bytes; + t->is_deleted = 0; + t->serial_number = 0; + t->seq_number = ptt_copy.seq_number; + + /* Do extra header info stuff */ + if (ptt_copy.chunk_id & EXTRA_HEADER_INFO_FLAG) { + t->chunk_id = 0; + t->n_bytes = 0; + + t->extra_available = 1; + t->extra_parent_id = ptt_copy.chunk_id & (~(ALL_EXTRA_FLAGS)); + t->extra_is_shrink = ptt_copy.chunk_id & EXTRA_SHRINK_FLAG ? 1 : 0; + t->extra_shadows = ptt_copy.chunk_id & EXTRA_SHADOWS_FLAG ? 1 : 0; + t->extra_obj_type = ptt_copy.obj_id >> EXTRA_OBJECT_TYPE_SHIFT; + t->obj_id &= ~EXTRA_OBJECT_TYPE_MASK; + + if (t->extra_obj_type == YAFFS_OBJECT_TYPE_HARDLINK) + t->extra_equiv_id = ptt_copy.n_bytes; + else + t->extra_file_size = ptt_copy.n_bytes; + } + yaffs_dump_packed_tags2_tags_only(ptt_ptr); + yaffs_dump_tags2(t); +} + +void yaffs_unpack_tags2(struct yaffs_dev *dev, + struct yaffs_ext_tags *t, + struct yaffs_packed_tags2 *pt, + int tags_ecc) +{ + enum yaffs_ecc_result ecc_result = YAFFS_ECC_RESULT_NO_ERROR; + + if (pt->t.seq_number != 0xffffffff && tags_ecc) { + /* Chunk is in use and we need to do ECC */ + + struct yaffs_ecc_other ecc; + int result; + yaffs_ecc_calc_other((unsigned char *)&pt->t, + sizeof(struct yaffs_packed_tags2_tags_only), + &ecc); + result = + yaffs_ecc_correct_other((unsigned char *)&pt->t, + sizeof(struct yaffs_packed_tags2_tags_only), + &pt->ecc, &ecc); + switch (result) { + case 0: + ecc_result = YAFFS_ECC_RESULT_NO_ERROR; + break; + case 1: + ecc_result = YAFFS_ECC_RESULT_FIXED; + break; + case -1: + ecc_result = YAFFS_ECC_RESULT_UNFIXED; + break; + default: + ecc_result = YAFFS_ECC_RESULT_UNKNOWN; + } + } + yaffs_unpack_tags2_tags_only(dev, t, &pt->t); + + t->ecc_result = ecc_result; + + yaffs_dump_packed_tags2(pt); + yaffs_dump_tags2(t); +} diff --git a/fs/yaffs2/yaffs_packedtags2.h b/fs/yaffs2/yaffs_packedtags2.h new file mode 100644 index 000000000000..598032601f78 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags2.h @@ -0,0 +1,50 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +/* This is used to pack YAFFS2 tags, not YAFFS1tags. */ + +#ifndef __YAFFS_PACKEDTAGS2_H__ +#define __YAFFS_PACKEDTAGS2_H__ + +#include "yaffs_guts.h" +#include "yaffs_ecc.h" + +struct yaffs_packed_tags2_tags_only { + unsigned seq_number; + unsigned obj_id; + unsigned chunk_id; + unsigned n_bytes; +}; + +struct yaffs_packed_tags2 { + struct yaffs_packed_tags2_tags_only t; + struct yaffs_ecc_other ecc; +}; + +/* Full packed tags with ECC, used for oob tags */ +void yaffs_pack_tags2(struct yaffs_dev *dev, + struct yaffs_packed_tags2 *pt, + const struct yaffs_ext_tags *t, int tags_ecc); +void yaffs_unpack_tags2(struct yaffs_dev *dev, + struct yaffs_ext_tags *t, struct yaffs_packed_tags2 *pt, + int tags_ecc); + +/* Only the tags part (no ECC for use with inband tags */ +void yaffs_pack_tags2_tags_only(struct yaffs_dev *dev, + struct yaffs_packed_tags2_tags_only *pt, + const struct yaffs_ext_tags *t); +void yaffs_unpack_tags2_tags_only(struct yaffs_dev *dev, + struct yaffs_ext_tags *t, + struct yaffs_packed_tags2_tags_only *pt); +#endif diff --git a/fs/yaffs2/yaffs_summary.c b/fs/yaffs2/yaffs_summary.c new file mode 100644 index 000000000000..50a6919aa97a --- /dev/null +++ b/fs/yaffs2/yaffs_summary.c @@ -0,0 +1,309 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Summaries write the useful part of the tags for the chunks in a block into an + * an array which is written to the last n chunks of the block. + * Reading the summaries gives all the tags for the block in one read. Much + * faster. + * + * Chunks holding summaries are marked with tags making it look like + * they are part of a fake file. + * + * The summary could also be used during gc. + * + */ + +#include "yaffs_summary.h" +#include "yaffs_packedtags2.h" +#include "yaffs_nand.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_bitmap.h" + +/* + * The summary is built up in an array of summary tags. + * This gets written to the last one or two (maybe more) chunks in a block. + * A summary header is written as the first part of each chunk of summary data. + * The summary header must match or the summary is rejected. + */ + +/* Summary tags don't need the sequence number because that is redundant. */ +struct yaffs_summary_tags { + unsigned obj_id; + unsigned chunk_id; + unsigned n_bytes; +}; + +/* Summary header */ +struct yaffs_summary_header { + unsigned version; /* Must match current version */ + unsigned block; /* Must be this block */ + unsigned seq; /* Must be this sequence number */ + unsigned sum; /* Just add up all the bytes in the tags */ +}; + + +static void yaffs_summary_clear(struct yaffs_dev *dev) +{ + if (!dev->sum_tags) + return; + memset(dev->sum_tags, 0, dev->chunks_per_summary * + sizeof(struct yaffs_summary_tags)); +} + + +void yaffs_summary_deinit(struct yaffs_dev *dev) +{ + kfree(dev->sum_tags); + dev->sum_tags = NULL; + kfree(dev->gc_sum_tags); + dev->gc_sum_tags = NULL; + dev->chunks_per_summary = 0; +} + +int yaffs_summary_init(struct yaffs_dev *dev) +{ + int sum_bytes; + int chunks_used; /* Number of chunks used by summary */ + int sum_tags_bytes; + + sum_bytes = dev->param.chunks_per_block * + sizeof(struct yaffs_summary_tags); + + chunks_used = (sum_bytes + dev->data_bytes_per_chunk - 1)/ + (dev->data_bytes_per_chunk - + sizeof(struct yaffs_summary_header)); + + dev->chunks_per_summary = dev->param.chunks_per_block - chunks_used; + sum_tags_bytes = sizeof(struct yaffs_summary_tags) * + dev->chunks_per_summary; + dev->sum_tags = kmalloc(sum_tags_bytes, GFP_NOFS); + dev->gc_sum_tags = kmalloc(sum_tags_bytes, GFP_NOFS); + if (!dev->sum_tags || !dev->gc_sum_tags) { + yaffs_summary_deinit(dev); + return YAFFS_FAIL; + } + + yaffs_summary_clear(dev); + + return YAFFS_OK; +} + +static unsigned yaffs_summary_sum(struct yaffs_dev *dev) +{ + u8 *sum_buffer = (u8 *)dev->sum_tags; + int i; + unsigned sum = 0; + + i = sizeof(struct yaffs_summary_tags) * + dev->chunks_per_summary; + while (i > 0) { + sum += *sum_buffer; + sum_buffer++; + i--; + } + + return sum; +} + +static int yaffs_summary_write(struct yaffs_dev *dev, int blk) +{ + struct yaffs_ext_tags tags; + u8 *buffer; + u8 *sum_buffer = (u8 *)dev->sum_tags; + int n_bytes; + int chunk_in_nand; + int chunk_in_block; + int result; + int this_tx; + struct yaffs_summary_header hdr; + int sum_bytes_per_chunk = dev->data_bytes_per_chunk - sizeof(hdr); + struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk); + + buffer = yaffs_get_temp_buffer(dev); + n_bytes = sizeof(struct yaffs_summary_tags) * + dev->chunks_per_summary; + memset(&tags, 0, sizeof(struct yaffs_ext_tags)); + tags.obj_id = YAFFS_OBJECTID_SUMMARY; + tags.chunk_id = 1; + chunk_in_block = dev->chunks_per_summary; + chunk_in_nand = dev->alloc_block * dev->param.chunks_per_block + + dev->chunks_per_summary; + hdr.version = YAFFS_SUMMARY_VERSION; + hdr.block = blk; + hdr.seq = bi->seq_number; + hdr.sum = yaffs_summary_sum(dev); + + do { + this_tx = n_bytes; + if (this_tx > sum_bytes_per_chunk) + this_tx = sum_bytes_per_chunk; + memcpy(buffer, &hdr, sizeof(hdr)); + memcpy(buffer + sizeof(hdr), sum_buffer, this_tx); + tags.n_bytes = this_tx + sizeof(hdr); + result = yaffs_wr_chunk_tags_nand(dev, chunk_in_nand, + buffer, &tags); + + if (result != YAFFS_OK) + break; + yaffs_set_chunk_bit(dev, blk, chunk_in_block); + bi->pages_in_use++; + dev->n_free_chunks--; + + n_bytes -= this_tx; + sum_buffer += this_tx; + chunk_in_nand++; + chunk_in_block++; + tags.chunk_id++; + } while (result == YAFFS_OK && n_bytes > 0); + yaffs_release_temp_buffer(dev, buffer); + + + if (result == YAFFS_OK) + bi->has_summary = 1; + + + return result; +} + +int yaffs_summary_read(struct yaffs_dev *dev, + struct yaffs_summary_tags *st, + int blk) +{ + struct yaffs_ext_tags tags; + u8 *buffer; + u8 *sum_buffer = (u8 *)st; + int n_bytes; + u32 chunk_id; + int chunk_in_nand; + int chunk_in_block; + int result; + int this_tx; + struct yaffs_summary_header hdr; + struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk); + int sum_bytes_per_chunk = dev->data_bytes_per_chunk - sizeof(hdr); + + buffer = yaffs_get_temp_buffer(dev); + n_bytes = sizeof(struct yaffs_summary_tags) * dev->chunks_per_summary; + chunk_in_block = dev->chunks_per_summary; + chunk_in_nand = blk * dev->param.chunks_per_block + + dev->chunks_per_summary; + chunk_id = 1; + do { + this_tx = n_bytes; + if (this_tx > sum_bytes_per_chunk) + this_tx = sum_bytes_per_chunk; + result = yaffs_rd_chunk_tags_nand(dev, chunk_in_nand, + buffer, &tags); + + if (tags.chunk_id != chunk_id || + tags.obj_id != YAFFS_OBJECTID_SUMMARY || + tags.chunk_used == 0 || + tags.ecc_result > YAFFS_ECC_RESULT_FIXED || + tags.n_bytes != (this_tx + sizeof(hdr))) + result = YAFFS_FAIL; + if (result != YAFFS_OK) + break; + + if (st == dev->sum_tags) { + /* If we're scanning then update the block info */ + yaffs_set_chunk_bit(dev, blk, chunk_in_block); + bi->pages_in_use++; + } + memcpy(&hdr, buffer, sizeof(hdr)); + memcpy(sum_buffer, buffer + sizeof(hdr), this_tx); + n_bytes -= this_tx; + sum_buffer += this_tx; + chunk_in_nand++; + chunk_in_block++; + chunk_id++; + } while (result == YAFFS_OK && n_bytes > 0); + yaffs_release_temp_buffer(dev, buffer); + + if (result == YAFFS_OK) { + /* Verify header */ + if (hdr.version != YAFFS_SUMMARY_VERSION || + hdr.seq != bi->seq_number || + hdr.sum != yaffs_summary_sum(dev)) + result = YAFFS_FAIL; + } + + if (st == dev->sum_tags && result == YAFFS_OK) + bi->has_summary = 1; + + return result; +} + +int yaffs_summary_add(struct yaffs_dev *dev, + struct yaffs_ext_tags *tags, + int chunk_in_nand) +{ + struct yaffs_packed_tags2_tags_only tags_only; + struct yaffs_summary_tags *sum_tags; + int block_in_nand = chunk_in_nand / dev->param.chunks_per_block; + int chunk_in_block = chunk_in_nand % dev->param.chunks_per_block; + + if (!dev->sum_tags) + return YAFFS_OK; + + if (chunk_in_block >= 0 && chunk_in_block < dev->chunks_per_summary) { + yaffs_pack_tags2_tags_only(dev, &tags_only, tags); + sum_tags = &dev->sum_tags[chunk_in_block]; + + sum_tags->chunk_id = tags_only.chunk_id; + sum_tags->n_bytes = tags_only.n_bytes; + sum_tags->obj_id = tags_only.obj_id; + + if (chunk_in_block == dev->chunks_per_summary - 1) { + /* Time to write out the summary */ + yaffs_summary_write(dev, block_in_nand); + yaffs_summary_clear(dev); + yaffs_skip_rest_of_block(dev); + } + } + return YAFFS_OK; +} + +int yaffs_summary_fetch(struct yaffs_dev *dev, + struct yaffs_ext_tags *tags, + int chunk_in_block) +{ + struct yaffs_packed_tags2_tags_only tags_only; + struct yaffs_summary_tags *sum_tags; + if (chunk_in_block >= 0 && chunk_in_block < dev->chunks_per_summary) { + sum_tags = &dev->sum_tags[chunk_in_block]; + tags_only.chunk_id = sum_tags->chunk_id; + tags_only.n_bytes = sum_tags->n_bytes; + tags_only.obj_id = sum_tags->obj_id; + yaffs_unpack_tags2_tags_only(dev, tags, &tags_only); + return YAFFS_OK; + } + return YAFFS_FAIL; +} + +void yaffs_summary_gc(struct yaffs_dev *dev, int blk) +{ + struct yaffs_block_info *bi = yaffs_get_block_info(dev, blk); + u32 i; + + if (!bi->has_summary) + return; + + for (i = dev->chunks_per_summary; + i < dev->param.chunks_per_block; + i++) { + if (yaffs_check_chunk_bit(dev, blk, i)) { + yaffs_clear_chunk_bit(dev, blk, i); + bi->pages_in_use--; + dev->n_free_chunks++; + } + } +} diff --git a/fs/yaffs2/yaffs_summary.h b/fs/yaffs2/yaffs_summary.h new file mode 100644 index 000000000000..0d0a26a9713f --- /dev/null +++ b/fs/yaffs2/yaffs_summary.h @@ -0,0 +1,36 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_SUMMARY_H__ +#define __YAFFS_SUMMARY_H__ + +#include "yaffs_packedtags2.h" + + +int yaffs_summary_init(struct yaffs_dev *dev); +void yaffs_summary_deinit(struct yaffs_dev *dev); + +int yaffs_summary_add(struct yaffs_dev *dev, + struct yaffs_ext_tags *tags, + int chunk_in_block); +int yaffs_summary_fetch(struct yaffs_dev *dev, + struct yaffs_ext_tags *tags, + int chunk_in_block); +int yaffs_summary_read(struct yaffs_dev *dev, + struct yaffs_summary_tags *st, + int blk); +void yaffs_summary_gc(struct yaffs_dev *dev, int blk); + + +#endif diff --git a/fs/yaffs2/yaffs_tagscompat.c b/fs/yaffs2/yaffs_tagscompat.c new file mode 100644 index 000000000000..14532b9483b6 --- /dev/null +++ b/fs/yaffs2/yaffs_tagscompat.c @@ -0,0 +1,399 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This file handles yaffs1-style tags to allow compatibility with Yaffs1 style + * flash layouts. + */ + +#include "yaffs_guts.h" +#include "yaffs_tagscompat.h" +#include "yaffs_ecc.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_trace.h" +#include "yaffs_endian.h" + +static void yaffs_handle_rd_data_error(struct yaffs_dev *dev, int nand_chunk); + + +/********** Tags ECC calculations *********/ + +void yaffs_calc_tags_ecc(struct yaffs_tags *tags) +{ + /* Calculate an ecc */ + unsigned char *b = ((union yaffs_tags_union *)tags)->as_bytes; + unsigned i, j; + unsigned ecc = 0; + unsigned bit = 0; + + tags->ecc = 0; + + for (i = 0; i < 8; i++) { + for (j = 1; j & 0xff; j <<= 1) { + bit++; + if (b[i] & j) + ecc ^= bit; + } + } + tags->ecc = ecc; +} + +int yaffs_check_tags_ecc(struct yaffs_tags *tags) +{ + unsigned ecc = tags->ecc; + + yaffs_calc_tags_ecc(tags); + + ecc ^= tags->ecc; + + if (ecc && ecc <= 64) { + /* TODO: Handle the failure better. Retire? */ + unsigned char *b = ((union yaffs_tags_union *)tags)->as_bytes; + + ecc--; + + b[ecc / 8] ^= (1 << (ecc & 7)); + + /* Now recvalc the ecc */ + yaffs_calc_tags_ecc(tags); + + return 1; /* recovered error */ + } else if (ecc) { + /* Wierd ecc failure value */ + /* TODO Need to do somethiong here */ + return -1; /* unrecovered error */ + } + return 0; +} + +/********** Tags **********/ + +/* + * During tags storing/retireval we use a copy of the tags so that + * we can modify the endian etc without damaging the previous structure. + */ +static void yaffs_load_tags_to_spare(struct yaffs_dev *dev, + struct yaffs_spare *spare_ptr, + struct yaffs_tags *tags_ptr) +{ + union yaffs_tags_union *tu_ptr = (union yaffs_tags_union *)tags_ptr; + union yaffs_tags_union tags_stored = *tu_ptr; + + yaffs_calc_tags_ecc(&tags_stored.as_tags); + + yaffs_do_endian_u32(dev, &tags_stored.as_u32[0]); + yaffs_do_endian_u32(dev, &tags_stored.as_u32[1]); + + spare_ptr->tb0 = tags_stored.as_bytes[0]; + spare_ptr->tb1 = tags_stored.as_bytes[1]; + spare_ptr->tb2 = tags_stored.as_bytes[2]; + spare_ptr->tb3 = tags_stored.as_bytes[3]; + spare_ptr->tb4 = tags_stored.as_bytes[4]; + spare_ptr->tb5 = tags_stored.as_bytes[5]; + spare_ptr->tb6 = tags_stored.as_bytes[6]; + spare_ptr->tb7 = tags_stored.as_bytes[7]; +} + +static void yaffs_get_tags_from_spare(struct yaffs_dev *dev, + struct yaffs_spare *spare_ptr, + struct yaffs_tags *tags_ptr) +{ + union yaffs_tags_union *tu = (union yaffs_tags_union *)tags_ptr; + union yaffs_tags_union tags_stored; + int result; + + tags_stored.as_bytes[0] = spare_ptr->tb0; + tags_stored.as_bytes[1] = spare_ptr->tb1; + tags_stored.as_bytes[2] = spare_ptr->tb2; + tags_stored.as_bytes[3] = spare_ptr->tb3; + tags_stored.as_bytes[4] = spare_ptr->tb4; + tags_stored.as_bytes[5] = spare_ptr->tb5; + tags_stored.as_bytes[6] = spare_ptr->tb6; + tags_stored.as_bytes[7] = spare_ptr->tb7; + + yaffs_do_endian_u32(dev, &tags_stored.as_u32[0]); + yaffs_do_endian_u32(dev, &tags_stored.as_u32[1]); + + *tu = tags_stored; + + result = yaffs_check_tags_ecc(tags_ptr); + if (result > 0) + dev->n_tags_ecc_fixed++; + else if (result < 0) + dev->n_tags_ecc_unfixed++; +} + +static void yaffs_spare_init(struct yaffs_spare *spare) +{ + memset(spare, 0xff, sizeof(struct yaffs_spare)); +} + +static int yaffs_wr_nand(struct yaffs_dev *dev, + int nand_chunk, const u8 *data, + struct yaffs_spare *spare) +{ + int data_size = dev->data_bytes_per_chunk; + + return dev->drv.drv_write_chunk_fn(dev, nand_chunk, + data, data_size, + (u8 *) spare, sizeof(*spare)); +} + +static int yaffs_rd_chunk_nand(struct yaffs_dev *dev, + int nand_chunk, + u8 *data, + struct yaffs_spare *spare, + enum yaffs_ecc_result *ecc_result, + int correct_errors) +{ + int ret_val; + struct yaffs_spare local_spare; + int data_size; + int spare_size; + int ecc_result1, ecc_result2; + u8 calc_ecc[3]; + + if (!spare) { + /* If we don't have a real spare, then we use a local one. */ + /* Need this for the calculation of the ecc */ + spare = &local_spare; + } + data_size = dev->data_bytes_per_chunk; + spare_size = sizeof(struct yaffs_spare); + + if (dev->param.use_nand_ecc) + return dev->drv.drv_read_chunk_fn(dev, nand_chunk, + data, data_size, + (u8 *) spare, spare_size, + ecc_result); + + + /* Handle the ECC at this level. */ + + ret_val = dev->drv.drv_read_chunk_fn(dev, nand_chunk, + data, data_size, + (u8 *)spare, spare_size, + NULL); + if (!data || !correct_errors) + return ret_val; + + /* Do ECC correction if needed. */ + yaffs_ecc_calc(data, calc_ecc); + ecc_result1 = yaffs_ecc_correct(data, spare->ecc1, calc_ecc); + yaffs_ecc_calc(&data[256], calc_ecc); + ecc_result2 = yaffs_ecc_correct(&data[256], spare->ecc2, calc_ecc); + + if (ecc_result1 > 0) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>>yaffs ecc error fix performed on chunk %d:0", + nand_chunk); + dev->n_ecc_fixed++; + } else if (ecc_result1 < 0) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>>yaffs ecc error unfixed on chunk %d:0", + nand_chunk); + dev->n_ecc_unfixed++; + } + + if (ecc_result2 > 0) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>>yaffs ecc error fix performed on chunk %d:1", + nand_chunk); + dev->n_ecc_fixed++; + } else if (ecc_result2 < 0) { + yaffs_trace(YAFFS_TRACE_ERROR, + "**>>yaffs ecc error unfixed on chunk %d:1", + nand_chunk); + dev->n_ecc_unfixed++; + } + + if (ecc_result1 || ecc_result2) { + /* We had a data problem on this page */ + yaffs_handle_rd_data_error(dev, nand_chunk); + } + + if (ecc_result1 < 0 || ecc_result2 < 0) + *ecc_result = YAFFS_ECC_RESULT_UNFIXED; + else if (ecc_result1 > 0 || ecc_result2 > 0) + *ecc_result = YAFFS_ECC_RESULT_FIXED; + else + *ecc_result = YAFFS_ECC_RESULT_NO_ERROR; + + return ret_val; +} + +/* + * Functions for robustisizing + */ + +static void yaffs_handle_rd_data_error(struct yaffs_dev *dev, int nand_chunk) +{ + int flash_block = nand_chunk / dev->param.chunks_per_block; + + /* Mark the block for retirement */ + yaffs_get_block_info(dev, flash_block + dev->block_offset)-> + needs_retiring = 1; + yaffs_trace(YAFFS_TRACE_ERROR | YAFFS_TRACE_BAD_BLOCKS, + "**>>Block %d marked for retirement", + flash_block); + + /* TODO: + * Just do a garbage collection on the affected block + * then retire the block + * NB recursion + */ +} + +static int yaffs_tags_compat_wr(struct yaffs_dev *dev, + int nand_chunk, + const u8 *data, const struct yaffs_ext_tags *ext_tags) +{ + struct yaffs_spare spare; + struct yaffs_tags tags; + + yaffs_spare_init(&spare); + + if (ext_tags->is_deleted) + spare.page_status = 0; + else { + tags.obj_id = ext_tags->obj_id; + tags.chunk_id = ext_tags->chunk_id; + + tags.n_bytes_lsb = ext_tags->n_bytes & (1024 - 1); + + if (dev->data_bytes_per_chunk >= 1024) + tags.n_bytes_msb = (ext_tags->n_bytes >> 10) & 3; + else + tags.n_bytes_msb = 3; + + tags.serial_number = ext_tags->serial_number; + + if (!dev->param.use_nand_ecc && data) { + yaffs_ecc_calc(data, spare.ecc1); + yaffs_ecc_calc(&data[256], spare.ecc2); + } + + yaffs_load_tags_to_spare(dev, &spare, &tags); + } + return yaffs_wr_nand(dev, nand_chunk, data, &spare); +} + +static int yaffs_tags_compat_rd(struct yaffs_dev *dev, + int nand_chunk, + u8 *data, struct yaffs_ext_tags *ext_tags) +{ + struct yaffs_spare spare; + struct yaffs_tags tags; + enum yaffs_ecc_result ecc_result = YAFFS_ECC_RESULT_UNKNOWN; + static struct yaffs_spare spare_ff; + static int init; + int deleted; + + if (!init) { + memset(&spare_ff, 0xff, sizeof(spare_ff)); + init = 1; + } + + if (!yaffs_rd_chunk_nand(dev, nand_chunk, + data, &spare, &ecc_result, 1)) + return YAFFS_FAIL; + + /* ext_tags may be NULL */ + if (!ext_tags) + return YAFFS_OK; + + deleted = (hweight8(spare.page_status) < 7) ? 1 : 0; + + ext_tags->is_deleted = deleted; + ext_tags->ecc_result = ecc_result; + ext_tags->block_bad = 0; /* We're reading it */ + /* therefore it is not a bad block */ + ext_tags->chunk_used = + memcmp(&spare_ff, &spare, sizeof(spare_ff)) ? 1 : 0; + + if (ext_tags->chunk_used) { + yaffs_get_tags_from_spare(dev, &spare, &tags); + + ext_tags->obj_id = tags.obj_id; + ext_tags->chunk_id = tags.chunk_id; + ext_tags->n_bytes = tags.n_bytes_lsb; + + if (dev->data_bytes_per_chunk >= 1024) + ext_tags->n_bytes |= + (((unsigned)tags.n_bytes_msb) << 10); + + ext_tags->serial_number = tags.serial_number; + } + + return YAFFS_OK; +} + +static int yaffs_tags_compat_mark_bad(struct yaffs_dev *dev, int flash_block) +{ + struct yaffs_spare spare; + + memset(&spare, 0xff, sizeof(struct yaffs_spare)); + + spare.block_status = 'Y'; + + yaffs_wr_nand(dev, flash_block * dev->param.chunks_per_block, NULL, + &spare); + yaffs_wr_nand(dev, flash_block * dev->param.chunks_per_block + 1, + NULL, &spare); + + return YAFFS_OK; +} + +static int yaffs_tags_compat_query_block(struct yaffs_dev *dev, + int block_no, + enum yaffs_block_state *state, + u32 *seq_number) +{ + struct yaffs_spare spare0, spare1; + static struct yaffs_spare spare_ff; + static int init; + enum yaffs_ecc_result dummy; + + if (!init) { + memset(&spare_ff, 0xff, sizeof(spare_ff)); + init = 1; + } + + *seq_number = 0; + + /* Look for bad block markers in the first two chunks */ + yaffs_rd_chunk_nand(dev, block_no * dev->param.chunks_per_block, + NULL, &spare0, &dummy, 0); + yaffs_rd_chunk_nand(dev, block_no * dev->param.chunks_per_block + 1, + NULL, &spare1, &dummy, 0); + + if (hweight8(spare0.block_status & spare1.block_status) < 7) + *state = YAFFS_BLOCK_STATE_DEAD; + else if (memcmp(&spare_ff, &spare0, sizeof(spare_ff)) == 0) + *state = YAFFS_BLOCK_STATE_EMPTY; + else + *state = YAFFS_BLOCK_STATE_NEEDS_SCAN; + + return YAFFS_OK; +} + +void yaffs_tags_compat_install(struct yaffs_dev *dev) +{ + if(dev->param.is_yaffs2) + return; + if(!dev->tagger.write_chunk_tags_fn) + dev->tagger.write_chunk_tags_fn = yaffs_tags_compat_wr; + if(!dev->tagger.read_chunk_tags_fn) + dev->tagger.read_chunk_tags_fn = yaffs_tags_compat_rd; + if(!dev->tagger.query_block_fn) + dev->tagger.query_block_fn = yaffs_tags_compat_query_block; + if(!dev->tagger.mark_bad_fn) + dev->tagger.mark_bad_fn = yaffs_tags_compat_mark_bad; +} diff --git a/fs/yaffs2/yaffs_tagscompat.h b/fs/yaffs2/yaffs_tagscompat.h new file mode 100644 index 000000000000..a3cbf8dbc2fa --- /dev/null +++ b/fs/yaffs2/yaffs_tagscompat.h @@ -0,0 +1,43 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_TAGSCOMPAT_H__ +#define __YAFFS_TAGSCOMPAT_H__ + + +#include "yaffs_guts.h" + +#if 0 + + +int yaffs_tags_compat_wr(struct yaffs_dev *dev, + int nand_chunk, + const u8 *data, const struct yaffs_ext_tags *tags); +int yaffs_tags_compat_rd(struct yaffs_dev *dev, + int nand_chunk, + u8 *data, struct yaffs_ext_tags *tags); +int yaffs_tags_compat_mark_bad(struct yaffs_dev *dev, int block_no); +int yaffs_tags_compat_query_block(struct yaffs_dev *dev, + int block_no, + enum yaffs_block_state *state, + u32 *seq_number); + +#endif + + +void yaffs_tags_compat_install(struct yaffs_dev *dev); +void yaffs_calc_tags_ecc(struct yaffs_tags *tags); +int yaffs_check_tags_ecc(struct yaffs_tags *tags); + +#endif diff --git a/fs/yaffs2/yaffs_tagsmarshall.c b/fs/yaffs2/yaffs_tagsmarshall.c new file mode 100644 index 000000000000..cded165b367c --- /dev/null +++ b/fs/yaffs2/yaffs_tagsmarshall.c @@ -0,0 +1,205 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This file handles the marshalling (ie internal<-->external structure + * translation between the internal tags and the stored tags in Yaffs2-style + * tags storage. + */ + +#include "yaffs_guts.h" +#include "yaffs_trace.h" +#include "yaffs_packedtags2.h" + +static int yaffs_tags_marshall_write(struct yaffs_dev *dev, + int nand_chunk, const u8 *data, + const struct yaffs_ext_tags *tags) +{ + struct yaffs_packed_tags2 pt; + int retval; + + int packed_tags_size = + dev->param.no_tags_ecc ? sizeof(pt.t) : sizeof(pt); + void *packed_tags_ptr = + dev->param.no_tags_ecc ? (void *)&pt.t : (void *)&pt; + + yaffs_trace(YAFFS_TRACE_MTD, + "yaffs_tags_marshall_write chunk %d data %p tags %p", + nand_chunk, data, tags); + + /* For yaffs2 writing there must be both data and tags. + * If we're using inband tags, then the tags are stuffed into + * the end of the data buffer. + */ + if (!data || !tags) + BUG(); + else if (dev->param.inband_tags) { + struct yaffs_packed_tags2_tags_only *pt2tp; + pt2tp = + (struct yaffs_packed_tags2_tags_only *)(data + + dev-> + data_bytes_per_chunk); + yaffs_pack_tags2_tags_only(dev, pt2tp, tags); + } else { + yaffs_pack_tags2(dev, &pt, tags, !dev->param.no_tags_ecc); + } + + retval = dev->drv.drv_write_chunk_fn(dev, nand_chunk, + data, dev->param.total_bytes_per_chunk, + (dev->param.inband_tags) ? NULL : packed_tags_ptr, + (dev->param.inband_tags) ? 0 : packed_tags_size); + + return retval; +} + +static int yaffs_tags_marshall_read(struct yaffs_dev *dev, + int nand_chunk, u8 *data, + struct yaffs_ext_tags *tags) +{ + int retval = 0; + int local_data = 0; + u8 spare_buffer[100]; + enum yaffs_ecc_result ecc_result; + + struct yaffs_packed_tags2 pt; + + int packed_tags_size = + dev->param.no_tags_ecc ? sizeof(pt.t) : sizeof(pt); + void *packed_tags_ptr = + dev->param.no_tags_ecc ? (void *)&pt.t : (void *)&pt; + + yaffs_trace(YAFFS_TRACE_MTD, + "yaffs_tags_marshall_read chunk %d data %p tags %p", + nand_chunk, data, tags); + + if (dev->param.inband_tags) { + if (!data) { + local_data = 1; + data = yaffs_get_temp_buffer(dev); + } + } + + if (dev->param.inband_tags || (data && !tags)) + retval = dev->drv.drv_read_chunk_fn(dev, nand_chunk, + data, dev->param.total_bytes_per_chunk, + NULL, 0, + &ecc_result); + else if (tags) + retval = dev->drv.drv_read_chunk_fn(dev, nand_chunk, + data, dev->param.total_bytes_per_chunk, + spare_buffer, packed_tags_size, + &ecc_result); + else + BUG(); + + + if (retval == YAFFS_FAIL) + return YAFFS_FAIL; + + if (dev->param.inband_tags) { + if (tags) { + struct yaffs_packed_tags2_tags_only *pt2tp; + pt2tp = + (struct yaffs_packed_tags2_tags_only *) + &data[dev->data_bytes_per_chunk]; + yaffs_unpack_tags2_tags_only(dev, tags, pt2tp); + } + } else if (tags) { + memcpy(packed_tags_ptr, spare_buffer, packed_tags_size); + yaffs_unpack_tags2(dev, tags, &pt, !dev->param.no_tags_ecc); + } + + if (local_data) + yaffs_release_temp_buffer(dev, data); + + if (tags && ecc_result == YAFFS_ECC_RESULT_UNFIXED) { + tags->ecc_result = YAFFS_ECC_RESULT_UNFIXED; + dev->n_ecc_unfixed++; + } + + if (tags && ecc_result == YAFFS_ECC_RESULT_FIXED) { + if (tags->ecc_result <= YAFFS_ECC_RESULT_NO_ERROR) + tags->ecc_result = YAFFS_ECC_RESULT_FIXED; + dev->n_ecc_fixed++; + } + + if (ecc_result < YAFFS_ECC_RESULT_UNFIXED) + return YAFFS_OK; + else + return YAFFS_FAIL; +} + +static int yaffs_tags_marshall_query_block(struct yaffs_dev *dev, int block_no, + enum yaffs_block_state *state, + u32 *seq_number) +{ + int retval; + + yaffs_trace(YAFFS_TRACE_MTD, "yaffs_tags_marshall_query_block %d", + block_no); + + retval = dev->drv.drv_check_bad_fn(dev, block_no); + + if (retval== YAFFS_FAIL) { + yaffs_trace(YAFFS_TRACE_MTD, "block is bad"); + + *state = YAFFS_BLOCK_STATE_DEAD; + *seq_number = 0; + } else { + struct yaffs_ext_tags t; + + yaffs_tags_marshall_read(dev, + block_no * dev->param.chunks_per_block, + NULL, &t); + + if (t.chunk_used) { + *seq_number = t.seq_number; + *state = YAFFS_BLOCK_STATE_NEEDS_SCAN; + } else { + *seq_number = 0; + *state = YAFFS_BLOCK_STATE_EMPTY; + } + } + + yaffs_trace(YAFFS_TRACE_MTD, + "block query returns seq %d state %d", + *seq_number, *state); + + if (retval == 0) + return YAFFS_OK; + else + return YAFFS_FAIL; +} + +static int yaffs_tags_marshall_mark_bad(struct yaffs_dev *dev, int block_no) +{ + return dev->drv.drv_mark_bad_fn(dev, block_no); + +} + + +void yaffs_tags_marshall_install(struct yaffs_dev *dev) +{ + if (!dev->param.is_yaffs2) + return; + + if (!dev->tagger.write_chunk_tags_fn) + dev->tagger.write_chunk_tags_fn = yaffs_tags_marshall_write; + + if (!dev->tagger.read_chunk_tags_fn) + dev->tagger.read_chunk_tags_fn = yaffs_tags_marshall_read; + + if (!dev->tagger.query_block_fn) + dev->tagger.query_block_fn = yaffs_tags_marshall_query_block; + + if (!dev->tagger.mark_bad_fn) + dev->tagger.mark_bad_fn = yaffs_tags_marshall_mark_bad; + +} diff --git a/fs/yaffs2/yaffs_tagsmarshall.h b/fs/yaffs2/yaffs_tagsmarshall.h new file mode 100644 index 000000000000..e6c0ef652452 --- /dev/null +++ b/fs/yaffs2/yaffs_tagsmarshall.h @@ -0,0 +1,21 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_TAGSMARSHALL_H__ +#define __YAFFS_TAGSMARSHALL_H__ + +#include "yaffs_guts.h" +void yaffs_tags_marshall_install(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_trace.h b/fs/yaffs2/yaffs_trace.h new file mode 100644 index 000000000000..5a6aeed23cfb --- /dev/null +++ b/fs/yaffs2/yaffs_trace.h @@ -0,0 +1,56 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YTRACE_H__ +#define __YTRACE_H__ + +extern unsigned int yaffs_trace_mask; +extern unsigned int yaffs_wr_attempts; + +/* + * Tracing flags. + * The flags masked in YAFFS_TRACE_ALWAYS are always traced. + */ + +#define YAFFS_TRACE_OS 0x00000002 +#define YAFFS_TRACE_ALLOCATE 0x00000004 +#define YAFFS_TRACE_SCAN 0x00000008 +#define YAFFS_TRACE_BAD_BLOCKS 0x00000010 +#define YAFFS_TRACE_ERASE 0x00000020 +#define YAFFS_TRACE_GC 0x00000040 +#define YAFFS_TRACE_WRITE 0x00000080 +#define YAFFS_TRACE_TRACING 0x00000100 +#define YAFFS_TRACE_DELETION 0x00000200 +#define YAFFS_TRACE_BUFFERS 0x00000400 +#define YAFFS_TRACE_NANDACCESS 0x00000800 +#define YAFFS_TRACE_GC_DETAIL 0x00001000 +#define YAFFS_TRACE_SCAN_DEBUG 0x00002000 +#define YAFFS_TRACE_MTD 0x00004000 +#define YAFFS_TRACE_CHECKPOINT 0x00008000 + +#define YAFFS_TRACE_VERIFY 0x00010000 +#define YAFFS_TRACE_VERIFY_NAND 0x00020000 +#define YAFFS_TRACE_VERIFY_FULL 0x00040000 +#define YAFFS_TRACE_VERIFY_ALL 0x000f0000 + +#define YAFFS_TRACE_SYNC 0x00100000 +#define YAFFS_TRACE_BACKGROUND 0x00200000 +#define YAFFS_TRACE_LOCK 0x00400000 +#define YAFFS_TRACE_MOUNT 0x00800000 + +#define YAFFS_TRACE_ERROR 0x40000000 +#define YAFFS_TRACE_BUG 0x80000000 +#define YAFFS_TRACE_ALWAYS 0xf0000000 + +#endif diff --git a/fs/yaffs2/yaffs_verify.c b/fs/yaffs2/yaffs_verify.c new file mode 100644 index 000000000000..9141eb5dbd2d --- /dev/null +++ b/fs/yaffs2/yaffs_verify.c @@ -0,0 +1,539 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_verify.h" +#include "yaffs_trace.h" +#include "yaffs_bitmap.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_nand.h" + +int yaffs_skip_verification(struct yaffs_dev *dev) +{ + (void) dev; + return !(yaffs_trace_mask & + (YAFFS_TRACE_VERIFY | YAFFS_TRACE_VERIFY_FULL)); +} + +static int yaffs_skip_full_verification(struct yaffs_dev *dev) +{ + (void) dev; + return !(yaffs_trace_mask & (YAFFS_TRACE_VERIFY_FULL)); +} + +static int yaffs_skip_nand_verification(struct yaffs_dev *dev) +{ + (void) dev; + return !(yaffs_trace_mask & (YAFFS_TRACE_VERIFY_NAND)); +} + +static const char * const block_state_name[] = { + "Unknown", + "Needs scan", + "Scanning", + "Empty", + "Allocating", + "Full", + "Dirty", + "Checkpoint", + "Collecting", + "Dead" +}; + +void yaffs_verify_blk(struct yaffs_dev *dev, struct yaffs_block_info *bi, int n) +{ + int actually_used; + int in_use; + + if (yaffs_skip_verification(dev)) + return; + + /* Report illegal runtime states */ + if (bi->block_state >= YAFFS_NUMBER_OF_BLOCK_STATES) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Block %d has undefined state %d", + n, bi->block_state); + + switch (bi->block_state) { + case YAFFS_BLOCK_STATE_UNKNOWN: + case YAFFS_BLOCK_STATE_SCANNING: + case YAFFS_BLOCK_STATE_NEEDS_SCAN: + yaffs_trace(YAFFS_TRACE_VERIFY, + "Block %d has bad run-state %s", + n, block_state_name[bi->block_state]); + } + + /* Check pages in use and soft deletions are legal */ + + actually_used = bi->pages_in_use - bi->soft_del_pages; + + if (bi->pages_in_use < 0 || + bi->pages_in_use > (int)dev->param.chunks_per_block || + bi->soft_del_pages < 0 || + bi->soft_del_pages > (int)dev->param.chunks_per_block || + actually_used < 0 || actually_used > (int)dev->param.chunks_per_block) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Block %d has illegal values pages_in_used %d soft_del_pages %d", + n, bi->pages_in_use, bi->soft_del_pages); + + /* Check chunk bitmap legal */ + in_use = yaffs_count_chunk_bits(dev, n); + if (in_use != bi->pages_in_use) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Block %d has inconsistent values pages_in_use %d counted chunk bits %d", + n, bi->pages_in_use, in_use); +} + +void yaffs_verify_collected_blk(struct yaffs_dev *dev, + struct yaffs_block_info *bi, int n) +{ + yaffs_verify_blk(dev, bi, n); + + /* After collection the block should be in the erased state */ + + if (bi->block_state != YAFFS_BLOCK_STATE_COLLECTING && + bi->block_state != YAFFS_BLOCK_STATE_EMPTY) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Block %d is in state %d after gc, should be erased", + n, bi->block_state); + } +} + +void yaffs_verify_blocks(struct yaffs_dev *dev) +{ + u32 i; + u32 state_count[YAFFS_NUMBER_OF_BLOCK_STATES]; + int illegal_states = 0; + + if (yaffs_skip_verification(dev)) + return; + + memset(state_count, 0, sizeof(state_count)); + + for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + struct yaffs_block_info *bi = yaffs_get_block_info(dev, i); + yaffs_verify_blk(dev, bi, i); + + if (bi->block_state < YAFFS_NUMBER_OF_BLOCK_STATES) + state_count[bi->block_state]++; + else + illegal_states++; + } + + yaffs_trace(YAFFS_TRACE_VERIFY, "Block summary"); + + yaffs_trace(YAFFS_TRACE_VERIFY, + "%d blocks have illegal states", + illegal_states); + if (state_count[YAFFS_BLOCK_STATE_ALLOCATING] > 1) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Too many allocating blocks"); + + for (i = 0; i < YAFFS_NUMBER_OF_BLOCK_STATES; i++) + yaffs_trace(YAFFS_TRACE_VERIFY, + "%s %d blocks", + block_state_name[i], state_count[i]); + + if (dev->blocks_in_checkpt != state_count[YAFFS_BLOCK_STATE_CHECKPOINT]) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Checkpoint block count wrong dev %d count %d", + dev->blocks_in_checkpt, + state_count[YAFFS_BLOCK_STATE_CHECKPOINT]); + + if (dev->n_erased_blocks != (int)state_count[YAFFS_BLOCK_STATE_EMPTY]) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Erased block count wrong dev %d count %d", + dev->n_erased_blocks, + state_count[YAFFS_BLOCK_STATE_EMPTY]); + + if (state_count[YAFFS_BLOCK_STATE_COLLECTING] > 1) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Too many collecting blocks %d (max is 1)", + state_count[YAFFS_BLOCK_STATE_COLLECTING]); +} + +/* + * Verify the object header. oh must be valid, but obj and tags may be NULL in + * which case those tests will not be performed. + */ +void yaffs_verify_oh(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh, + struct yaffs_ext_tags *tags, int parent_check) +{ + if (obj && yaffs_skip_verification(obj->my_dev)) + return; + + if (!(tags && obj && oh)) { + yaffs_trace(YAFFS_TRACE_VERIFY, + "Verifying object header tags %p obj %p oh %p", + tags, obj, oh); + return; + } + + if (oh->type <= YAFFS_OBJECT_TYPE_UNKNOWN || + oh->type > YAFFS_OBJECT_TYPE_MAX) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header type is illegal value 0x%x", + tags->obj_id, oh->type); + + if (tags->obj_id != obj->obj_id) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header mismatch obj_id %d", + tags->obj_id, obj->obj_id); + + /* + * Check that the object's parent ids match if parent_check requested. + * + * Tests do not apply to the root object. + */ + + if (parent_check && tags->obj_id > 1 && !obj->parent) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header mismatch parent_id %d obj->parent is NULL", + tags->obj_id, oh->parent_obj_id); + + if (parent_check && obj->parent && + oh->parent_obj_id != obj->parent->obj_id && + (oh->parent_obj_id != YAFFS_OBJECTID_UNLINKED || + obj->parent->obj_id != YAFFS_OBJECTID_DELETED)) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header mismatch parent_id %d parent_obj_id %d", + tags->obj_id, oh->parent_obj_id, + obj->parent->obj_id); + + if (tags->obj_id > 1 && oh->name[0] == 0) /* Null name */ + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header name is NULL", + obj->obj_id); + + if (tags->obj_id > 1 && ((u8) (oh->name[0])) == 0xff) /* Junk name */ + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d header name is 0xff", + obj->obj_id); +} + +void yaffs_verify_file(struct yaffs_obj *obj) +{ + u32 x; + int required_depth; + int last_chunk; + u32 offset_in_chunk; + u32 the_chunk; + + int i; + struct yaffs_dev *dev; + struct yaffs_ext_tags tags; + struct yaffs_tnode *tn; + u32 obj_id; + + if (!obj) + return; + + if (yaffs_skip_verification(obj->my_dev)) + return; + + dev = obj->my_dev; + obj_id = obj->obj_id; + + + /* Check file size is consistent with tnode depth */ + yaffs_addr_to_chunk(dev, obj->variant.file_variant.file_size, + &last_chunk, &offset_in_chunk); + last_chunk++; + x = last_chunk >> YAFFS_TNODES_LEVEL0_BITS; + required_depth = 0; + while (x > 0) { + x >>= YAFFS_TNODES_INTERNAL_BITS; + required_depth++; + } + + /* Check that the chunks in the tnode tree are all correct. + * We do this by scanning through the tnode tree and + * checking the tags for every chunk match. + */ + + if (yaffs_skip_nand_verification(dev)) + return; + + for (i = 1; i <= last_chunk; i++) { + tn = yaffs_find_tnode_0(dev, &obj->variant.file_variant, i); + + if (!tn) + continue; + + the_chunk = yaffs_get_group_base(dev, tn, i); + if (the_chunk > 0) { + yaffs_rd_chunk_tags_nand(dev, the_chunk, NULL, + &tags); + if (tags.obj_id != obj_id || tags.chunk_id != (u32)i) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Object %d chunk_id %d NAND mismatch chunk %d tags (%d:%d)", + obj_id, i, the_chunk, + tags.obj_id, tags.chunk_id); + } + } +} + +void yaffs_verify_link(struct yaffs_obj *obj) +{ + if (obj && yaffs_skip_verification(obj->my_dev)) + return; + + /* Verify sane equivalent object */ +} + +void yaffs_verify_symlink(struct yaffs_obj *obj) +{ + if (obj && yaffs_skip_verification(obj->my_dev)) + return; + + /* Verify symlink string */ +} + +void yaffs_verify_special(struct yaffs_obj *obj) +{ + if (obj && yaffs_skip_verification(obj->my_dev)) + return; +} + +void yaffs_verify_obj(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev; + u32 chunk_min; + u32 chunk_max; + u32 chunk_id_ok; + u32 chunk_in_range; + u32 chunk_wrongly_deleted; + u32 chunk_valid; + + if (!obj) + return; + + if (obj->being_created) + return; + + dev = obj->my_dev; + + if (yaffs_skip_verification(dev)) + return; + + /* Check sane object header chunk */ + + chunk_min = dev->internal_start_block * dev->param.chunks_per_block; + chunk_max = + (dev->internal_end_block + 1) * dev->param.chunks_per_block - 1; + + chunk_in_range = (((unsigned)(obj->hdr_chunk)) >= chunk_min && + ((unsigned)(obj->hdr_chunk)) <= chunk_max); + chunk_id_ok = chunk_in_range || (obj->hdr_chunk == 0); + chunk_valid = chunk_in_range && + yaffs_check_chunk_bit(dev, + obj->hdr_chunk / dev->param.chunks_per_block, + obj->hdr_chunk % dev->param.chunks_per_block); + chunk_wrongly_deleted = chunk_in_range && !chunk_valid; + + if (!obj->fake && (!chunk_id_ok || chunk_wrongly_deleted)) + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d has chunk_id %d %s %s", + obj->obj_id, obj->hdr_chunk, + chunk_id_ok ? "" : ",out of range", + chunk_wrongly_deleted ? ",marked as deleted" : ""); + + if (chunk_valid && !yaffs_skip_nand_verification(dev)) { + struct yaffs_ext_tags tags; + struct yaffs_obj_hdr *oh; + u8 *buffer = yaffs_get_temp_buffer(dev); + + oh = (struct yaffs_obj_hdr *)buffer; + + yaffs_rd_chunk_tags_nand(dev, obj->hdr_chunk, buffer, &tags); + + yaffs_verify_oh(obj, oh, &tags, 1); + + yaffs_release_temp_buffer(dev, buffer); + } + + /* Verify it has a parent */ + if (obj && !obj->fake && (!obj->parent || obj->parent->my_dev != dev)) { + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d has parent pointer %p which does not look like an object", + obj->obj_id, obj->parent); + } + + /* Verify parent is a directory */ + if (obj->parent && + obj->parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d's parent is not a directory (type %d)", + obj->obj_id, obj->parent->variant_type); + } + + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + yaffs_verify_file(obj); + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + yaffs_verify_symlink(obj); + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + yaffs_verify_dir(obj); + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + yaffs_verify_link(obj); + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + yaffs_verify_special(obj); + break; + case YAFFS_OBJECT_TYPE_UNKNOWN: + default: + yaffs_trace(YAFFS_TRACE_VERIFY, + "Obj %d has illegaltype %d", + obj->obj_id, obj->variant_type); + break; + } +} + +void yaffs_verify_objects(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj; + int i; + struct list_head *lh; + + if (yaffs_skip_verification(dev)) + return; + + /* Iterate through the objects in each hash entry */ + + for (i = 0; i < YAFFS_NOBJECT_BUCKETS; i++) { + list_for_each(lh, &dev->obj_bucket[i].list) { + obj = list_entry(lh, struct yaffs_obj, hash_link); + yaffs_verify_obj(obj); + } + } +} + +void yaffs_verify_obj_in_dir(struct yaffs_obj *obj) +{ + struct list_head *lh; + struct yaffs_obj *list_obj; + int count = 0; + + if (!obj) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "No object to verify"); + BUG(); + return; + } + + if (yaffs_skip_verification(obj->my_dev)) + return; + + if (!obj->parent) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "Object does not have parent"); + BUG(); + return; + } + + if (obj->parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "Parent is not directory"); + BUG(); + } + + /* Iterate through the objects in each hash entry */ + + list_for_each(lh, &obj->parent->variant.dir_variant.children) { + list_obj = list_entry(lh, struct yaffs_obj, siblings); + yaffs_verify_obj(list_obj); + if (obj == list_obj) + count++; + } + + if (count != 1) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Object in directory %d times", + count); + BUG(); + } +} + +void yaffs_verify_dir(struct yaffs_obj *directory) +{ + struct list_head *lh; + struct yaffs_obj *list_obj; + struct yaffs_dev *dev; + + if (!directory) { + BUG(); + return; + } + + dev = directory->my_dev; + + if (!dev) { + BUG(); + return; + } + + if (directory == dev->root_dir || + directory == dev->lost_n_found || + directory == dev->unlinked_dir || + directory == dev->del_dir) + return; + + if (yaffs_skip_full_verification(directory->my_dev)) + return; + + if (directory->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Directory has wrong type: %d", + directory->variant_type); + BUG(); + } + + /* Iterate through the objects in each hash entry */ + + list_for_each(lh, &directory->variant.dir_variant.children) { + list_obj = list_entry(lh, struct yaffs_obj, siblings); + if (list_obj->parent != directory) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Object in directory list has wrong parent %p", + list_obj->parent); + BUG(); + } + yaffs_verify_obj_in_dir(list_obj); + } +} + +static int yaffs_free_verification_failures; + +void yaffs_verify_free_chunks(struct yaffs_dev *dev) +{ + int counted; + int difference; + + if (yaffs_skip_verification(dev)) + return; + + counted = yaffs_count_free_chunks(dev); + + difference = dev->n_free_chunks - counted; + + if (difference) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Freechunks verification failure %d %d %d", + dev->n_free_chunks, counted, difference); + yaffs_free_verification_failures++; + } +} + +int yaffs_verify_file_sane(struct yaffs_obj *in) +{ + (void) in; + return YAFFS_OK; +} diff --git a/fs/yaffs2/yaffs_verify.h b/fs/yaffs2/yaffs_verify.h new file mode 100644 index 000000000000..7571201a8616 --- /dev/null +++ b/fs/yaffs2/yaffs_verify.h @@ -0,0 +1,42 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_VERIFY_H__ +#define __YAFFS_VERIFY_H__ + +#include "yaffs_guts.h" + +void yaffs_verify_blk(struct yaffs_dev *dev, struct yaffs_block_info *bi, + int n); +void yaffs_verify_collected_blk(struct yaffs_dev *dev, + struct yaffs_block_info *bi, int n); +void yaffs_verify_blocks(struct yaffs_dev *dev); + +void yaffs_verify_oh(struct yaffs_obj *obj, struct yaffs_obj_hdr *oh, + struct yaffs_ext_tags *tags, int parent_check); +void yaffs_verify_file(struct yaffs_obj *obj); +void yaffs_verify_link(struct yaffs_obj *obj); +void yaffs_verify_symlink(struct yaffs_obj *obj); +void yaffs_verify_special(struct yaffs_obj *obj); +void yaffs_verify_obj(struct yaffs_obj *obj); +void yaffs_verify_objects(struct yaffs_dev *dev); +void yaffs_verify_obj_in_dir(struct yaffs_obj *obj); +void yaffs_verify_dir(struct yaffs_obj *directory); +void yaffs_verify_free_chunks(struct yaffs_dev *dev); + +int yaffs_verify_file_sane(struct yaffs_obj *obj); + +int yaffs_skip_verification(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_vfs.c b/fs/yaffs2/yaffs_vfs.c new file mode 100644 index 000000000000..3ffdc0129637 --- /dev/null +++ b/fs/yaffs2/yaffs_vfs.c @@ -0,0 +1,3806 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * Acknowledgements: + * Luc van OostenRyck for numerous patches. + * Nick Bane for numerous patches. + * Nick Bane for 2.5/2.6 integration. + * Andras Toth for mknod rdev issue. + * Michael Fischer for finding the problem with inode inconsistency. + * Some code bodily lifted from JFFS + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * + * This is the file system front-end to YAFFS that hooks it up to + * the VFS. + * + * Special notes: + * >> 2.4: sb->u.generic_sbp points to the struct yaffs_dev associated with + * this superblock + * >> 2.6: sb->s_fs_info points to the struct yaffs_dev associated with this + * superblock + * >> inode->u.generic_ip points to the associated struct yaffs_obj. + */ + +/* + * There are two variants of the VFS glue code. This variant should compile + * for any version of Linux. + */ +#include <linux/version.h> +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 16, 0)) +#include <linux/iversion.h> +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 10)) +#define YAFFS_COMPILE_BACKGROUND +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 23)) +#define YAFFS_COMPILE_FREEZER +#endif +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 28)) +#define YAFFS_COMPILE_EXPORTFS +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 35)) +#define YAFFS_USE_SETATTR_COPY +#define YAFFS_USE_TRUNCATE_SETSIZE +#endif +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 35)) +#define YAFFS_HAS_EVICT_INODE +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 13)) && \ + (LINUX_VERSION_CODE < KERNEL_VERSION(4, 8, 0)) +#define YAFFS_NEW_FOLLOW_LINK 1 +#else +#define YAFFS_NEW_FOLLOW_LINK 0 +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 6, 0)) +#define YAFFS_HAS_WRITE_SUPER +#endif + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19)) +#include <linux/config.h> +#endif + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/fs.h> +#include <linux/proc_fs.h> +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)) +#include <linux/smp_lock.h> +#endif +#include <linux/pagemap.h> +#include <linux/mtd/mtd.h> +#include <linux/interrupt.h> +#include <linux/string.h> +#include <linux/ctype.h> + +#if (YAFFS_NEW_FOLLOW_LINK == 1) +#include <linux/namei.h> +#endif + +#ifdef YAFFS_COMPILE_EXPORTFS +#include <linux/exportfs.h> +#endif + +#ifdef YAFFS_COMPILE_BACKGROUND +#include <linux/kthread.h> +#include <linux/delay.h> +#endif +#ifdef YAFFS_COMPILE_FREEZER +#include <linux/freezer.h> +#endif + +#include <asm/div64.h> + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + +#include <linux/statfs.h> + +#define UnlockPage(p) unlock_page(p) +#define Page_Uptodate(page) test_bit(PG_uptodate, &(page)->flags) + +/* FIXME: use sb->s_id instead ? */ +#define yaffs_devname(sb, buf) bdevname(sb->s_bdev, buf) + +#else + +#include <linux/locks.h> +#define BDEVNAME_SIZE 0 +#define yaffs_devname(sb, buf) kdevname(sb->s_dev) + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 5, 0)) +/* added NCB 26/5/2006 for 2.4.25-vrs2-tcl1 kernel */ +#define __user +#endif + +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 26)) +#define YPROC_ROOT (&proc_root) +#else +#define YPROC_ROOT NULL +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 26)) +#define Y_INIT_TIMER(a) init_timer(a) +#elif LINUX_VERSION_CODE < KERNEL_VERSION(4, 15, 0) +#define Y_INIT_TIMER(a) init_timer_on_stack(a) +#else +#define Y_INIT_TIMER(a,cb) timer_setup_on_stack(a,cb,0) +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 27)) +#define YAFFS_USE_WRITE_BEGIN_END 1 +#else +#define YAFFS_USE_WRITE_BEGIN_END 0 +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 6, 0)) +#define YAFFS_SUPER_HAS_DIRTY +#endif + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 2, 0)) +#define set_nlink(inode, count) do { (inode)->i_nlink = (count); } while(0) +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 28)) +static uint32_t YCALCBLOCKS(uint64_t partition_size, uint32_t block_size) +{ + uint64_t result = partition_size; + do_div(result, block_size); + return (uint32_t) result; +} +#else +#define YCALCBLOCKS(s, b) ((s)/(b)) +#endif + +#include <linux/uaccess.h> +#include <linux/mtd/mtd.h> + +#include <uapi/linux/mount.h> + +#include "yportenv.h" +#include "yaffs_trace.h" +#include "yaffs_guts.h" +#include "yaffs_attribs.h" +#include "yaffs_linux.h" +#include "yaffs_mtdif.h" +#include "yaffs_packedtags2.h" +#include "yaffs_getblockinfo.h" + +unsigned int yaffs_trace_mask = YAFFS_TRACE_BAD_BLOCKS | YAFFS_TRACE_ALWAYS | 0; +unsigned int yaffs_wr_attempts = YAFFS_WR_ATTEMPTS; +unsigned int yaffs_auto_checkpoint = 1; +unsigned int yaffs_gc_control = 1; +unsigned int yaffs_bg_enable = 1; +unsigned int yaffs_auto_select = 1; +/* Module Parameters */ +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +module_param(yaffs_trace_mask, uint, 0644); +module_param(yaffs_wr_attempts, uint, 0644); +module_param(yaffs_auto_checkpoint, uint, 0644); +module_param(yaffs_gc_control, uint, 0644); +module_param(yaffs_bg_enable, uint, 0644); +#else +MODULE_PARM(yaffs_trace_mask, "i"); +MODULE_PARM(yaffs_wr_attempts, "i"); +MODULE_PARM(yaffs_auto_checkpoint, "i"); +MODULE_PARM(yaffs_gc_control, "i"); +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 25)) +/* use iget and read_inode */ +#define Y_IGET(sb, inum) iget((sb), (inum)) + +#else +/* Call local equivalent */ +#define YAFFS_USE_OWN_IGET +#define Y_IGET(sb, inum) yaffs_iget((sb), (inum)) + +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 18)) +#define yaffs_inode_to_obj_lv(iptr) ((iptr)->i_private) +#else +#define yaffs_inode_to_obj_lv(iptr) ((iptr)->u.generic_ip) +#endif + +#define yaffs_inode_to_obj(iptr) \ + ((struct yaffs_obj *)(yaffs_inode_to_obj_lv(iptr))) +#define yaffs_dentry_to_obj(dptr) yaffs_inode_to_obj((dptr)->d_inode) + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +#define yaffs_super_to_dev(sb) ((struct yaffs_dev *)sb->s_fs_info) +#else +#define yaffs_super_to_dev(sb) ((struct yaffs_dev *)sb->u.generic_sbp) +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 5, 0)) +#define Y_CLEAR_INODE(i) clear_inode(i) +#else +#define Y_CLEAR_INODE(i) end_writeback(i) +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 12, 0)) +#define YAFFS_USE_DIR_ITERATE +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 9, 0)) +#define YAFFS_USE_XATTR +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,12,0)) +#define YAFFS_NEW_PROCFS +#include <linux/seq_file.h> +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 4, 0)) +#define PAGE_CACHE_SIZE PAGE_SIZE +#define PAGE_CACHE_SHIFT PAGE_SHIFT +#define Y_GET_DENTRY(f) ((f)->f_path.dentry) +#define YAFFS_NEW_XATTR 1 +#define YAFFS_NEW_GET_LINK 1 +#else +#define Y_GET_DENTRY(f) ((f)->f_dentry) +#define YAFFS_NEW_XATTR 0 +#define YAFFS_NEW_GET_LINK 0 +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 8, 0)) +#define page_cache_release put_page +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4,12,0)) +#define update_dir_time(dir) do {\ + (dir)->i_ctime = (dir)->i_mtime = current_time(dir); \ + } while (0) +#elif (LINUX_VERSION_CODE < KERNEL_VERSION(4,18,0)) +#define update_dir_time(dir) do {\ + (dir)->i_ctime = (dir)->i_mtime = current_kernel_time(); \ + } while (0) +#else +#define update_dir_time(dir) do {\ + (dir)->i_ctime = (dir)->i_mtime = current_time(dir); \ + } while (0) +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 9, 0)) +static inline int setattr_prepare(struct dentry *dentry, struct iattr *attr) +{ + return inode_change_ok(dentry->d_inode, attr); +} +#endif + +static void yaffs_fill_inode_from_obj(struct inode *inode, + struct yaffs_obj *obj); + + +static void yaffs_gross_lock(struct yaffs_dev *dev) +{ + yaffs_trace(YAFFS_TRACE_LOCK, "yaffs locking %p", current); + mutex_lock(&(yaffs_dev_to_lc(dev)->gross_lock)); + yaffs_trace(YAFFS_TRACE_LOCK, "yaffs locked %p", current); +} + +static void yaffs_gross_unlock(struct yaffs_dev *dev) +{ + yaffs_trace(YAFFS_TRACE_LOCK, "yaffs unlocking %p", current); + mutex_unlock(&(yaffs_dev_to_lc(dev)->gross_lock)); +} + + +static int yaffs_readpage_nolock(struct file *f, struct page *pg) +{ + /* Lifted from jffs2 */ + + struct yaffs_obj *obj; + unsigned char *pg_buf; + int ret; + loff_t pos = ((loff_t) pg->index) << PAGE_SHIFT; + struct yaffs_dev *dev; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readpage_nolock at %lld, size %08x", + (long long)pos, + (unsigned)PAGE_SIZE); + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + + dev = obj->my_dev; + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + BUG_ON(!PageLocked(pg)); +#else + if (!PageLocked(pg)) + PAGE_BUG(pg); +#endif + + pg_buf = kmap(pg); + /* FIXME: Can kmap fail? */ + + yaffs_gross_lock(dev); + + ret = yaffs_file_rd(obj, pg_buf, pos, PAGE_CACHE_SIZE); + + yaffs_gross_unlock(dev); + + if (ret >= 0) + ret = 0; + + if (ret) { + ClearPageUptodate(pg); + SetPageError(pg); + } else { + SetPageUptodate(pg); + ClearPageError(pg); + } + + flush_dcache_page(pg); + kunmap(pg); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage_nolock done"); + return ret; +} + +static int yaffs_readpage_unlock(struct file *f, struct page *pg) +{ + int ret = yaffs_readpage_nolock(f, pg); + UnlockPage(pg); + return ret; +} + +static int yaffs_readpage(struct file *f, struct page *pg) +{ + int ret; + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage"); + ret = yaffs_readpage_unlock(f, pg); + yaffs_trace(YAFFS_TRACE_OS, "yaffs_readpage done"); + return ret; +} + + +static void yaffs_set_super_dirty_val(struct yaffs_dev *dev, int val) +{ + struct yaffs_linux_context *lc = yaffs_dev_to_lc(dev); + + if (lc) + lc->dirty = val; + +# ifdef YAFFS_SUPER_HAS_DIRTY + { + struct super_block *sb = lc->super; + + if (sb) + sb->s_dirt = val; + } +#endif + +} + +static void yaffs_set_super_dirty(struct yaffs_dev *dev) +{ + yaffs_set_super_dirty_val(dev, 1); +} + +static void yaffs_clear_super_dirty(struct yaffs_dev *dev) +{ + yaffs_set_super_dirty_val(dev, 0); +} + +static int yaffs_check_super_dirty(struct yaffs_dev *dev) +{ + struct yaffs_linux_context *lc = yaffs_dev_to_lc(dev); + + if (lc && lc->dirty) + return 1; + +# ifdef YAFFS_SUPER_HAS_DIRTY + { + struct super_block *sb = lc->super; + + if (sb && sb->s_dirt) + return 1; + } +#endif + return 0; + +} + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs_writepage(struct page *page, struct writeback_control *wbc) +#else +static int yaffs_writepage(struct page *page) +#endif +{ + struct yaffs_dev *dev; + struct address_space *mapping = page->mapping; + struct inode *inode; + unsigned long end_index; + char *buffer; + struct yaffs_obj *obj; + int n_written = 0; + unsigned n_bytes; + loff_t i_size; + + if (!mapping) + BUG(); + inode = mapping->host; + if (!inode) + BUG(); + i_size = i_size_read(inode); + + end_index = i_size >> PAGE_CACHE_SHIFT; + + if (page->index < end_index) + n_bytes = PAGE_CACHE_SIZE; + else { + n_bytes = i_size & (PAGE_CACHE_SIZE - 1); + + if (page->index > end_index || !n_bytes) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_writepage at %lld, inode size = %lld!!", + ((loff_t)page->index) << PAGE_CACHE_SHIFT, + inode->i_size); + yaffs_trace(YAFFS_TRACE_OS, + " -> don't care!!"); + + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + return 0; + } + } + + if (n_bytes != PAGE_CACHE_SIZE) + zero_user_segment(page, n_bytes, PAGE_CACHE_SIZE); + + get_page(page); + + buffer = kmap(page); + + obj = yaffs_inode_to_obj(inode); + dev = obj->my_dev; + yaffs_gross_lock(dev); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_writepage at %lld, size %08x", + ((loff_t)page->index) << PAGE_CACHE_SHIFT, n_bytes); + yaffs_trace(YAFFS_TRACE_OS, + "writepag0: obj = %lld, ino = %lld", + obj->variant.file_variant.file_size, inode->i_size); + + n_written = yaffs_wr_file(obj, buffer, + ((loff_t)page->index) << PAGE_CACHE_SHIFT, n_bytes, 0); + + yaffs_set_super_dirty(dev); + + yaffs_trace(YAFFS_TRACE_OS, + "writepag1: obj = %lld, ino = %lld", + obj->variant.file_variant.file_size, inode->i_size); + + yaffs_gross_unlock(dev); + + kunmap(page); + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + put_page(page); + + return (n_written == n_bytes) ? 0 : -ENOSPC; +} + +/* Space holding and freeing is done to ensure we have space available for write_begin/end */ +/* For now we just assume few parallel writes and check against a small number. */ +/* Todo: need to do this with a counter to handle parallel reads better */ + +static ssize_t yaffs_hold_space(struct file *f) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + + int n_free_chunks; + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + n_free_chunks = yaffs_get_n_free_chunks(dev); + + yaffs_gross_unlock(dev); + + return (n_free_chunks > 20) ? 1 : 0; +} + +static void yaffs_release_space(struct file *f) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + yaffs_gross_unlock(dev); +} + +#if (YAFFS_USE_WRITE_BEGIN_END > 0) +static int yaffs_write_begin(struct file *filp, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + struct page *pg = NULL; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + + int ret = 0; + int space_held = 0; + + /* Get a page */ +#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 28) + pg = grab_cache_page_write_begin(mapping, index, flags); +#else + pg = __grab_cache_page(mapping, index); +#endif + + *pagep = pg; + if (!pg) { + ret = -ENOMEM; + goto out; + } + yaffs_trace(YAFFS_TRACE_OS, + "start yaffs_write_begin index %d(%x) uptodate %d", + (int)index, (int)index, Page_Uptodate(pg) ? 1 : 0); + + /* Get fs space */ + space_held = yaffs_hold_space(filp); + + if (!space_held) { + ret = -ENOSPC; + goto out; + } + + /* Update page if required */ + + if (!Page_Uptodate(pg)) + ret = yaffs_readpage_nolock(filp, pg); + + if (ret) + goto out; + + /* Happy path return */ + yaffs_trace(YAFFS_TRACE_OS, "end yaffs_write_begin - ok"); + + return 0; + +out: + yaffs_trace(YAFFS_TRACE_OS, + "end yaffs_write_begin fail returning %d", ret); + if (space_held) + yaffs_release_space(filp); + if (pg) { + unlock_page(pg); + page_cache_release(pg); + } + return ret; +} + +#else + +static int yaffs_prepare_write(struct file *f, struct page *pg, + unsigned offset, unsigned to) +{ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_prepair_write"); + + if (!Page_Uptodate(pg)) + return yaffs_readpage_nolock(f, pg); + return 0; +} +#endif + + +static ssize_t yaffs_file_write(struct file *f, const char *buf, size_t n, + loff_t * pos) +{ + struct yaffs_obj *obj; + int n_written; + loff_t ipos; + struct inode *inode; + struct yaffs_dev *dev; + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + + if (!obj) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_file_write: hey obj is null!"); + return -EINVAL; + } + + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + inode = Y_GET_DENTRY(f)->d_inode; + + if (!S_ISBLK(inode->i_mode) && f->f_flags & O_APPEND) + ipos = inode->i_size; + else + ipos = *pos; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_file_write about to write writing %u(%x) bytes to object %d at %lld", + (unsigned)n, (unsigned)n, obj->obj_id, ipos); + + n_written = yaffs_wr_file(obj, buf, ipos, n, 0); + + yaffs_set_super_dirty(dev); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_file_write: %d(%x) bytes written", + (unsigned)n, (unsigned)n); + + if (n_written > 0) { + ipos += n_written; + *pos = ipos; + if (ipos > inode->i_size) { + inode->i_size = ipos; + inode->i_blocks = (ipos + 511) >> 9; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_file_write size updated to %lld bytes, %d blocks", + ipos, (int)(inode->i_blocks)); + } + + } + yaffs_gross_unlock(dev); + return (n_written == 0) && (n > 0) ? -ENOSPC : n_written; +} + + +#if (YAFFS_USE_WRITE_BEGIN_END > 0) +static int yaffs_write_end(struct file *filp, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *pg, void *fsdadata) +{ + int ret = 0; + void *addr, *kva; + uint32_t offset_into_page = pos & (PAGE_CACHE_SIZE - 1); + + kva = kmap(pg); + addr = kva + offset_into_page; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_write_end addr %p pos %lld n_bytes %d", + addr, pos, copied); + + ret = yaffs_file_write(filp, addr, copied, &pos); + + if (ret != copied) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_write_end not same size ret %d copied %d", + ret, copied); + SetPageError(pg); + } + + kunmap(pg); + + yaffs_release_space(filp); + unlock_page(pg); + page_cache_release(pg); + return ret; +} +#else + +static int yaffs_commit_write(struct file *f, struct page *pg, unsigned offset, + unsigned to) +{ + void *addr, *kva; + + loff_t pos = (((loff_t) pg->index) << PAGE_CACHE_SHIFT) + offset; + int n_bytes = to - offset; + int n_written; + + kva = kmap(pg); + addr = kva + offset; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_commit_write addr %p pos %lld n_bytes %d", + addr, pos, n_bytes); + + n_written = yaffs_file_write(f, addr, n_bytes, &pos); + + if (n_written != n_bytes) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_commit_write not same size n_written %d n_bytes %d", + n_written, n_bytes); + SetPageError(pg); + } + kunmap(pg); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_commit_write returning %d", + n_written == n_bytes ? 0 : n_written); + + return n_written == n_bytes ? 0 : n_written; +} +#endif + +static struct address_space_operations yaffs_file_address_operations = { + .readpage = yaffs_readpage, + .writepage = yaffs_writepage, +#if (YAFFS_USE_WRITE_BEGIN_END > 0) + .write_begin = yaffs_write_begin, + .write_end = yaffs_write_end, +#else + .prepare_write = yaffs_prepare_write, + .commit_write = yaffs_commit_write, +#endif +}; + + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static int yaffs_file_flush(struct file *file, fl_owner_t id) +#else +static int yaffs_file_flush(struct file *file) +#endif +{ + struct yaffs_obj *obj = yaffs_dentry_to_obj(Y_GET_DENTRY(file)); + + struct yaffs_dev *dev = obj->my_dev; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_file_flush object %d (%s)", + obj->obj_id, + obj->dirty ? "dirty" : "clean"); + + yaffs_gross_lock(dev); + + yaffs_flush_file(obj, 1, 0, 0); + + yaffs_gross_unlock(dev); + + return 0; +} + + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)) +static int yaffs_sync_object(struct file *file, loff_t start, loff_t end, int datasync) +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 34)) +static int yaffs_sync_object(struct file *file, int datasync) +#else +static int yaffs_sync_object(struct file *file, struct dentry *dentry, + int datasync) +#endif +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 34)) + struct dentry *dentry = file->f_path.dentry; +#endif + + obj = yaffs_dentry_to_obj(dentry); + + dev = obj->my_dev; + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC, + "yaffs_sync_object"); + yaffs_gross_lock(dev); + yaffs_flush_file(obj, 1, datasync, 0); + yaffs_gross_unlock(dev); + return 0; +} + + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 22)) +static const struct file_operations yaffs_file_operations = { +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 16, 0) +#if LINUX_VERSION_CODE < KERNEL_VERSION(4, 4, 0) + .read = new_sync_read, + .write = new_sync_write, +#endif + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, +#else + .read = do_sync_read, + .write = do_sync_write, + .aio_read = generic_file_aio_read, + .aio_write = generic_file_aio_write, +#endif + .mmap = generic_file_mmap, + .flush = yaffs_file_flush, + .fsync = yaffs_sync_object, + .splice_read = generic_file_splice_read, +#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 16, 0) + .splice_write = iter_file_splice_write, +#else + .splice_write = generic_file_splice_write, +#endif + .llseek = generic_file_llseek, +}; + +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 18)) + +static const struct file_operations yaffs_file_operations = { + .read = do_sync_read, + .write = do_sync_write, + .aio_read = generic_file_aio_read, + .aio_write = generic_file_aio_write, + .mmap = generic_file_mmap, + .flush = yaffs_file_flush, + .fsync = yaffs_sync_object, + .sendfile = generic_file_sendfile, +}; + +#else + +static const struct file_operations yaffs_file_operations = { + .read = generic_file_read, + .write = generic_file_write, + .mmap = generic_file_mmap, + .flush = yaffs_file_flush, + .fsync = yaffs_sync_object, +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + .sendfile = generic_file_sendfile, +#endif +}; +#endif + + + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 25)) +static void zero_user_segment(struct page *page, unsigned start, unsigned end) +{ + void *kaddr = kmap_atomic(page, KM_USER0); + memset(kaddr + start, 0, end - start); + kunmap_atomic(kaddr, KM_USER0); + flush_dcache_page(page); +} +#endif + + +static int yaffs_vfs_setsize(struct inode *inode, loff_t newsize) +{ +#ifdef YAFFS_USE_TRUNCATE_SETSIZE + truncate_setsize(inode, newsize); + return 0; +#else + truncate_inode_pages(&inode->i_data, newsize); + return 0; +#endif + +} + + +static int yaffs_vfs_setattr(struct inode *inode, struct iattr *attr) +{ +#ifdef YAFFS_USE_SETATTR_COPY + setattr_copy(inode, attr); + return 0; +#else + return inode_setattr(inode, attr); +#endif + +} + +static int yaffs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + int error = 0; + struct yaffs_dev *dev; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_setattr of object %d", + yaffs_inode_to_obj(inode)->obj_id); +#if 0 + /* Fail if a requested resize >= 2GB */ + if (attr->ia_valid & ATTR_SIZE && (attr->ia_size >> 31)) + error = -EINVAL; +#endif + + if (error == 0) + error = setattr_prepare(dentry, attr); + if (error == 0) { + int result; + if (!error) { + error = yaffs_vfs_setattr(inode, attr); + yaffs_trace(YAFFS_TRACE_OS, "inode_setattr called"); + if (attr->ia_valid & ATTR_SIZE) { + yaffs_vfs_setsize(inode, attr->ia_size); + inode->i_blocks = (inode->i_size + 511) >> 9; + } + } + dev = yaffs_inode_to_obj(inode)->my_dev; + if (attr->ia_valid & ATTR_SIZE) { + yaffs_trace(YAFFS_TRACE_OS, + "resize to %d(%x)", + (int)(attr->ia_size), + (int)(attr->ia_size)); + } + yaffs_gross_lock(dev); + result = yaffs_set_attribs(yaffs_inode_to_obj(inode), attr); + if (result == YAFFS_OK) { + error = 0; + } else { + error = -EPERM; + } + yaffs_gross_unlock(dev); + + } + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_setattr done returning %d", error); + + return error; +} + +#ifdef YAFFS_USE_XATTR +#if (YAFFS_NEW_XATTR > 0) +static int yaffs_setxattr(struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, int flags) +{ +#else +static int yaffs_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct inode *inode = dentry->d_inode; +#endif + int error = 0; + struct yaffs_dev *dev; + struct yaffs_obj *obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_setxattr of object %d", obj->obj_id); + + /* Currently we don't support posix ACL so never accept any settings + * start with "system.posix_acl_". + */ + if (strncmp(name, "system.posix_acl_", 17)) + error = -EOPNOTSUPP; + + if (error == 0) { + int result; + dev = obj->my_dev; + yaffs_gross_lock(dev); + result = yaffs_set_xattrib(obj, name, value, size, flags); + if (result == YAFFS_OK) + error = 0; + else if (result < 0) + error = result; + yaffs_gross_unlock(dev); + + } + yaffs_trace(YAFFS_TRACE_OS, "yaffs_setxattr done returning %d", error); + + return error; +} + +#if (YAFFS_NEW_XATTR > 0) +static ssize_t yaffs_getxattr(struct dentry * dentry, struct inode *inode, + const char *name, void *buff, size_t size) +{ +#else +static ssize_t yaffs_getxattr(struct dentry * dentry, const char *name, + void *buff, size_t size) +{ + struct inode *inode = dentry->d_inode; +#endif + int error = 0; + struct yaffs_dev *dev; + struct yaffs_obj *obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_getxattr \"%s\" from object %d", + name, obj->obj_id); + + if (error == 0) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + error = yaffs_get_xattrib(obj, name, buff, size); + yaffs_gross_unlock(dev); + + } + yaffs_trace(YAFFS_TRACE_OS, "yaffs_getxattr done returning %d", error); + + return error; +} + +static int yaffs_removexattr(struct dentry *dentry, const char *name) +{ + struct inode *inode = dentry->d_inode; + int error = 0; + struct yaffs_dev *dev; + struct yaffs_obj *obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_removexattr of object %d", obj->obj_id); + + if (error == 0) { + int result; + dev = obj->my_dev; + yaffs_gross_lock(dev); + result = yaffs_remove_xattrib(obj, name); + if (result == YAFFS_OK) + error = 0; + else if (result < 0) + error = result; + yaffs_gross_unlock(dev); + + } + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_removexattr done returning %d", error); + + return error; +} +#endif + +static ssize_t yaffs_listxattr(struct dentry * dentry, char *buff, size_t size) +{ + struct inode *inode = dentry->d_inode; + int error = 0; + struct yaffs_dev *dev; + struct yaffs_obj *obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_listxattr of object %d", obj->obj_id); + + if (error == 0) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + error = yaffs_list_xattrib(obj, buff, size); + yaffs_gross_unlock(dev); + + } + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_listxattr done returning %d", error); + + return error; +} + + +static const struct inode_operations yaffs_file_inode_operations = { + .setattr = yaffs_setattr, +#ifdef YAFFS_USE_XATTR + .setxattr = yaffs_setxattr, + .getxattr = yaffs_getxattr, + .removexattr = yaffs_removexattr, +#endif + .listxattr = yaffs_listxattr, +}; + + +static int yaffs_readlink(struct dentry *dentry, char __user * buffer, + int buflen) +{ + unsigned char *alias; + int ret; + + struct yaffs_dev *dev = yaffs_dentry_to_obj(dentry)->my_dev; + + yaffs_gross_lock(dev); + + alias = yaffs_get_symlink_alias(yaffs_dentry_to_obj(dentry)); + + yaffs_gross_unlock(dev); + + if (!alias) + return -ENOMEM; + +#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0) + ret = vfs_readlink(dentry, buffer, buflen, alias); +#else + ret = readlink_copy(buffer, buflen, alias); +#endif + kfree(alias); + return ret; +} + +#if (YAFFS_NEW_GET_LINK == 0) +#if (YAFFS_NEW_FOLLOW_LINK == 1) +static void *yaffs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + void *ret; +#else +static int yaffs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + int ret +#endif + unsigned char *alias; + int ret_int = 0; + struct yaffs_dev *dev = yaffs_dentry_to_obj(dentry)->my_dev; + + yaffs_gross_lock(dev); + + alias = yaffs_get_symlink_alias(yaffs_dentry_to_obj(dentry)); + yaffs_gross_unlock(dev); + + if (!alias) { + ret_int = -ENOMEM; + goto out; + } +#if (YAFFS_NEW_FOLLOW_LINK == 1) + nd_set_link(nd, alias); + ret = alias; +out: + if (ret_int) + ret = ERR_PTR(ret_int); + return ret; +#else + ret = vfs_follow_link(nd, alias); + kfree(alias); +out: + if (ret_int) + ret = ret_int; + return ret; +#endif +} +#else +static const char *yaffs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) +{ + unsigned char *alias; + struct yaffs_dev *dev; + + if (!dentry) + return ERR_PTR(-ECHILD); + + dev = yaffs_dentry_to_obj(dentry)->my_dev; + + yaffs_gross_lock(dev); + + alias = yaffs_get_symlink_alias(yaffs_dentry_to_obj(dentry)); + yaffs_gross_unlock(dev); + + if (!alias) + return ERR_PTR(-ENOMEM); + set_delayed_call(done, kfree_link, alias); + return alias; +} +#endif + +#ifdef YAFFS_HAS_PUT_INODE + +/* For now put inode is just for debugging + * Put inode is called when the inode **structure** is put. + */ +static void yaffs_put_inode(struct inode *inode) +{ + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_put_inode: ino %d, count %d"), + (int)inode->i_ino, atomic_read(&inode->i_count); + +} +#endif + +#if (YAFFS_NEW_FOLLOW_LINK == 1) +void yaffs_put_link(struct dentry *dentry, struct nameidata *nd, void *alias) +{ + kfree(alias); +} +#endif + +static const struct inode_operations yaffs_symlink_inode_operations = { + .readlink = yaffs_readlink, +#if (YAFFS_NEW_GET_LINK == 1) + .get_link = yaffs_get_link, +#else + .follow_link = yaffs_follow_link, +#endif +#if (YAFFS_NEW_FOLLOW_LINK == 1) + .put_link = yaffs_put_link, +#endif + .setattr = yaffs_setattr, +#ifdef YAFFS_USE_XATTR + .setxattr = yaffs_setxattr, + .getxattr = yaffs_getxattr, + .removexattr = yaffs_removexattr, +#endif + .listxattr = yaffs_listxattr, +}; + +#ifdef YAFFS_USE_OWN_IGET + +static struct inode *yaffs_iget(struct super_block *sb, unsigned long ino) +{ + struct inode *inode; + struct yaffs_obj *obj; + struct yaffs_dev *dev = yaffs_super_to_dev(sb); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_iget for %lu", ino); + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + /* NB This is called as a side effect of other functions, but + * we had to release the lock to prevent deadlocks, so + * need to lock again. + */ + + yaffs_gross_lock(dev); + + obj = yaffs_find_by_number(dev, inode->i_ino); + + yaffs_fill_inode_from_obj(inode, obj); + + yaffs_gross_unlock(dev); + + unlock_new_inode(inode); + return inode; +} + +#else + +static void yaffs_read_inode(struct inode *inode) +{ + /* NB This is called as a side effect of other functions, but + * we had to release the lock to prevent deadlocks, so + * need to lock again. + */ + + struct yaffs_obj *obj; + struct yaffs_dev *dev = yaffs_super_to_dev(inode->i_sb); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_read_inode for %d", (int)inode->i_ino); + + if (current != yaffs_dev_to_lc(dev)->readdir_process) + yaffs_gross_lock(dev); + + obj = yaffs_find_by_number(dev, inode->i_ino); + + yaffs_fill_inode_from_obj(inode, obj); + + if (current != yaffs_dev_to_lc(dev)->readdir_process) + yaffs_gross_unlock(dev); +} + +#endif + + + +struct inode *yaffs_get_inode(struct super_block *sb, int mode, int dev, + struct yaffs_obj *obj) +{ + struct inode *inode; + + if (!sb) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_get_inode for NULL super_block!!"); + return NULL; + + } + + if (!obj) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_get_inode for NULL object!!"); + return NULL; + + } + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_get_inode for object %d", obj->obj_id); + + inode = Y_IGET(sb, obj->obj_id); + if (IS_ERR(inode)) + return NULL; + + /* NB Side effect: iget calls back to yaffs_read_inode(). */ + /* iget also increments the inode's i_count */ + /* NB You can't be holding gross_lock or deadlock will happen! */ + + return inode; +} + + + +#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 29) +#define YCRED(x) x +#else +#define YCRED(x) (x->cred) +#endif + +#if LINUX_VERSION_CODE < KERNEL_VERSION(3,14,0) +#define YPROC_uid(p) (YCRED(p)->fsuid) +#define YPROC_gid(p) (YCRED(p)->fsgid) +#define EXTRACT_gid(x) x +#define EXTRACT_uid(x) x +#define MAKE_gid(x) x +#define MAKE_uid(x) x +#else +#define YPROC_uid(p) from_kuid(&init_user_ns, YCRED(p)->fsuid) +#define YPROC_gid(p) from_kgid(&init_user_ns, YCRED(p)->fsgid) +#define EXTRACT_gid(x) from_kgid(&init_user_ns, x) +#define EXTRACT_uid(x) from_kuid(&init_user_ns, x) +#define MAKE_gid(x) make_kgid(&init_user_ns, x) +#define MAKE_uid(x) make_kuid(&init_user_ns, x) +#endif + + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)) +static int yaffs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t rdev) +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs_mknod(struct inode *dir, struct dentry *dentry, int mode, + dev_t rdev) +#else +static int yaffs_mknod(struct inode *dir, struct dentry *dentry, int mode, + int rdev) +#endif +{ + struct inode *inode; + + struct yaffs_obj *obj = NULL; + struct yaffs_dev *dev; + + struct yaffs_obj *parent = yaffs_inode_to_obj(dir); + + int error = -ENOSPC; + uid_t uid = YPROC_uid(current); + gid_t gid = + (dir->i_mode & S_ISGID) ? EXTRACT_gid(dir->i_gid) : YPROC_gid(current); + + if ((dir->i_mode & S_ISGID) && S_ISDIR(mode)) + mode |= S_ISGID; + + if (parent) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_mknod: parent object %d type %d", + parent->obj_id, parent->variant_type); + } else { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_mknod: could not get parent object"); + return -EPERM; + } + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_mknod: making oject for %s, mode %x dev %x", + dentry->d_name.name, mode, rdev); + + dev = parent->my_dev; + + yaffs_gross_lock(dev); + + switch (mode & S_IFMT) { + default: + /* Special (socket, fifo, device...) */ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making special"); +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + obj = + yaffs_create_special(parent, dentry->d_name.name, mode, uid, + gid, old_encode_dev(rdev)); +#else + obj = + yaffs_create_special(parent, dentry->d_name.name, mode, uid, + gid, rdev); +#endif + break; + case S_IFREG: /* file */ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making file"); + obj = yaffs_create_file(parent, dentry->d_name.name, mode, uid, + gid); + break; + case S_IFDIR: /* directory */ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making directory"); + obj = yaffs_create_dir(parent, dentry->d_name.name, mode, + uid, gid); + break; + case S_IFLNK: /* symlink */ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod: making symlink"); + obj = NULL; /* Do we ever get here? */ + break; + } + + /* Can not call yaffs_get_inode() with gross lock held */ + yaffs_gross_unlock(dev); + + if (obj) { + inode = yaffs_get_inode(dir->i_sb, mode, rdev, obj); + d_instantiate(dentry, inode); + update_dir_time(dir); + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_mknod created object %d count = %d", + obj->obj_id, atomic_read(&inode->i_count)); + error = 0; + yaffs_fill_inode_from_obj(dir, parent); + } else { + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mknod failed making object"); + error = -ENOMEM; + } + + return error; +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)) +static int yaffs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +#else +static int yaffs_mkdir(struct inode *dir, struct dentry *dentry, int mode) +#endif +{ + int ret_val; + yaffs_trace(YAFFS_TRACE_OS, "yaffs_mkdir"); + ret_val = yaffs_mknod(dir, dentry, mode | S_IFDIR, 0); + return ret_val; +} + + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 6, 0)) +static int yaffs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool dummy) +#elif (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)) +static int yaffs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + struct nameidata *n) +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs_create(struct inode *dir, struct dentry *dentry, int mode, + struct nameidata *n) +#else +static int yaffs_create(struct inode *dir, struct dentry *dentry, int mode) +#endif +{ + yaffs_trace(YAFFS_TRACE_OS, "yaffs_create"); + return yaffs_mknod(dir, dentry, mode | S_IFREG, 0); +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 6, 0)) +static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int dummy) +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry, + struct nameidata *n) +#else +static struct dentry *yaffs_lookup(struct inode *dir, struct dentry *dentry) +#endif +{ + struct yaffs_obj *obj; + struct inode *inode = NULL; /* NCB 2.5/2.6 needs NULL here */ + + struct yaffs_dev *dev = yaffs_inode_to_obj(dir)->my_dev; + + if (current != yaffs_dev_to_lc(dev)->readdir_process) + yaffs_gross_lock(dev); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_lookup for %d:%s", + yaffs_inode_to_obj(dir)->obj_id, dentry->d_name.name); + + obj = yaffs_find_by_name(yaffs_inode_to_obj(dir), dentry->d_name.name); + + obj = yaffs_get_equivalent_obj(obj); /* in case it was a hardlink */ + + /* Can't hold gross lock when calling yaffs_get_inode() */ + if (current != yaffs_dev_to_lc(dev)->readdir_process) + yaffs_gross_unlock(dev); + + if (obj) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_lookup found %d", obj->obj_id); + + inode = yaffs_get_inode(dir->i_sb, obj->yst_mode, 0, obj); + } else { + yaffs_trace(YAFFS_TRACE_OS, "yaffs_lookup not found"); + + } + +/* added NCB for 2.5/6 compatability - forces add even if inode is + * NULL which creates dentry hash */ + d_add(dentry, inode); + + return NULL; +} + +/* + * Create a link... + */ +static int yaffs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *dentry) +{ + struct inode *inode = old_dentry->d_inode; + struct yaffs_obj *obj = NULL; + struct yaffs_obj *link = NULL; + struct yaffs_dev *dev; + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_link"); + + obj = yaffs_inode_to_obj(inode); + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + if (!S_ISDIR(inode->i_mode)) /* Don't link directories */ + link = + yaffs_link_obj(yaffs_inode_to_obj(dir), dentry->d_name.name, + obj); + + if (link) { + set_nlink(old_dentry->d_inode, yaffs_get_obj_link_count(obj)); + d_instantiate(dentry, old_dentry->d_inode); + atomic_inc(&old_dentry->d_inode->i_count); + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_link link count %d i_count %d", + old_dentry->d_inode->i_nlink, + atomic_read(&old_dentry->d_inode->i_count)); + } + + yaffs_gross_unlock(dev); + + if (link) { + update_dir_time(dir); + return 0; + } + + return -EPERM; +} + +static int yaffs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + uid_t uid = YPROC_uid(current); + gid_t gid = + (dir->i_mode & S_ISGID) ? EXTRACT_gid(dir->i_gid) : YPROC_gid(current); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_symlink"); + + if (strnlen(dentry->d_name.name, YAFFS_MAX_NAME_LENGTH + 1) > + YAFFS_MAX_NAME_LENGTH) + return -ENAMETOOLONG; + + if (strnlen(symname, YAFFS_MAX_ALIAS_LENGTH + 1) > + YAFFS_MAX_ALIAS_LENGTH) + return -ENAMETOOLONG; + + dev = yaffs_inode_to_obj(dir)->my_dev; + yaffs_gross_lock(dev); + obj = yaffs_create_symlink(yaffs_inode_to_obj(dir), dentry->d_name.name, + S_IFLNK | S_IRWXUGO, uid, gid, symname); + yaffs_gross_unlock(dev); + + if (obj) { + struct inode *inode; + + inode = yaffs_get_inode(dir->i_sb, obj->yst_mode, 0, obj); + d_instantiate(dentry, inode); + update_dir_time(dir); + yaffs_trace(YAFFS_TRACE_OS, "symlink created OK"); + return 0; + } else { + yaffs_trace(YAFFS_TRACE_OS, "symlink not created"); + } + + return -ENOMEM; +} + +/* + * The VFS layer already does all the dentry stuff for rename. + * + * NB: POSIX says you can rename an object over an old object of the same name + */ +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 9, 0)) +static int yaffs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, unsigned int unused) +#else +static int yaffs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +#endif +{ + struct yaffs_dev *dev; + int ret_val = YAFFS_FAIL; + struct yaffs_obj *target; + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_rename"); + dev = yaffs_inode_to_obj(old_dir)->my_dev; + + yaffs_gross_lock(dev); + + /* Check if the target is an existing directory that is not empty. */ + target = yaffs_find_by_name(yaffs_inode_to_obj(new_dir), + new_dentry->d_name.name); + + if (target && target->variant_type == YAFFS_OBJECT_TYPE_DIRECTORY && + !list_empty(&target->variant.dir_variant.children)) { + + yaffs_trace(YAFFS_TRACE_OS, "target is non-empty dir"); + + ret_val = YAFFS_FAIL; + } else { + /* Now does unlinking internally using shadowing mechanism */ + yaffs_trace(YAFFS_TRACE_OS, "calling yaffs_rename_obj"); + + ret_val = yaffs_rename_obj(yaffs_inode_to_obj(old_dir), + old_dentry->d_name.name, + yaffs_inode_to_obj(new_dir), + new_dentry->d_name.name); + } + yaffs_gross_unlock(dev); + + if (ret_val == YAFFS_OK) { + if (target) + inode_dec_link_count(new_dentry->d_inode); + + update_dir_time(old_dir); + if (old_dir != new_dir) + update_dir_time(new_dir); + return 0; + } else { + return -ENOTEMPTY; + } +} + + + + +static int yaffs_unlink(struct inode *dir, struct dentry *dentry) +{ + int ret_val; + + struct yaffs_dev *dev; + struct yaffs_obj *obj; + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_unlink %d:%s", + (int)(dir->i_ino), dentry->d_name.name); + obj = yaffs_inode_to_obj(dir); + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + ret_val = yaffs_unlinker(obj, dentry->d_name.name); + + if (ret_val == YAFFS_OK) { + inode_dec_link_count(dentry->d_inode); +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 16, 0)) + inode_inc_iversion(dir); +#else + atomic64_inc(&dir->i_version); +#endif + yaffs_gross_unlock(dev); + update_dir_time(dir); + return 0; + } + yaffs_gross_unlock(dev); + return -ENOTEMPTY; +} + + + +static const struct inode_operations yaffs_dir_inode_operations = { + .create = yaffs_create, + .lookup = yaffs_lookup, + .link = yaffs_link, + .unlink = yaffs_unlink, + .symlink = yaffs_symlink, + .mkdir = yaffs_mkdir, + .rmdir = yaffs_unlink, + .mknod = yaffs_mknod, + .rename = yaffs_rename, + .setattr = yaffs_setattr, + .listxattr = yaffs_listxattr, +#ifdef YAFFS_USE_XATTR + .setxattr = yaffs_setxattr, + .getxattr = yaffs_getxattr, + .removexattr = yaffs_removexattr, +#endif +}; + +/*-----------------------------------------------------------------*/ +/* Directory search context allows us to unlock access to yaffs during + * filldir without causing problems with the directory being modified. + * This is similar to the tried and tested mechanism used in yaffs direct. + * + * A search context iterates along a doubly linked list of siblings in the + * directory. If the iterating object is deleted then this would corrupt + * the list iteration, likely causing a crash. The search context avoids + * this by using the remove_obj_fn to move the search context to the + * next object before the object is deleted. + * + * Many readdirs (and thus seach conexts) may be alive simulateously so + * each struct yaffs_dev has a list of these. + * + * A seach context lives for the duration of a readdir. + * + * All these functions must be called while yaffs is locked. + */ + +struct yaffs_search_context { + struct yaffs_dev *dev; + struct yaffs_obj *dir_obj; + struct yaffs_obj *next_return; + struct list_head others; +}; + +/* + * yaffs_new_search() creates a new search context, initialises it and + * adds it to the device's search context list. + * + * Called at start of readdir. + */ +static struct yaffs_search_context *yaffs_new_search(struct yaffs_obj *dir) +{ + struct yaffs_dev *dev = dir->my_dev; + struct yaffs_search_context *sc = + kmalloc(sizeof(struct yaffs_search_context), GFP_NOFS); + if (sc) { + sc->dir_obj = dir; + sc->dev = dev; + if (list_empty(&sc->dir_obj->variant.dir_variant.children)) + sc->next_return = NULL; + else + sc->next_return = + list_entry(dir->variant.dir_variant.children.next, + struct yaffs_obj, siblings); + INIT_LIST_HEAD(&sc->others); + list_add(&sc->others, &(yaffs_dev_to_lc(dev)->search_contexts)); + } + return sc; +} + +/* + * yaffs_search_end() disposes of a search context and cleans up. + */ +static void yaffs_search_end(struct yaffs_search_context *sc) +{ + if (sc) { + list_del(&sc->others); + kfree(sc); + } +} + +/* + * yaffs_search_advance() moves a search context to the next object. + * Called when the search iterates or when an object removal causes + * the search context to be moved to the next object. + */ +static void yaffs_search_advance(struct yaffs_search_context *sc) +{ + if (!sc) + return; + + if (sc->next_return == NULL || + list_empty(&sc->dir_obj->variant.dir_variant.children)) + sc->next_return = NULL; + else { + struct list_head *next = sc->next_return->siblings.next; + + if (next == &sc->dir_obj->variant.dir_variant.children) + sc->next_return = NULL; /* end of list */ + else + sc->next_return = + list_entry(next, struct yaffs_obj, siblings); + } +} + +/* + * yaffs_remove_obj_callback() is called when an object is unlinked. + * We check open search contexts and advance any which are currently + * on the object being iterated. + */ +static void yaffs_remove_obj_callback(struct yaffs_obj *obj) +{ + + struct list_head *i; + struct yaffs_search_context *sc; + struct list_head *search_contexts = + &(yaffs_dev_to_lc(obj->my_dev)->search_contexts); + + /* Iterate through the directory search contexts. + * If any are currently on the object being removed, then advance + * the search context to the next object to prevent a hanging pointer. + */ + list_for_each(i, search_contexts) { + sc = list_entry(i, struct yaffs_search_context, others); + if (sc->next_return == obj) + yaffs_search_advance(sc); + } + +} + + +/*-----------------------------------------------------------------*/ + +#ifdef YAFFS_USE_DIR_ITERATE +static int yaffs_iterate(struct file *f, struct dir_context *dc) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + struct yaffs_search_context *sc; + unsigned long curoffs; + struct yaffs_obj *l; + int ret_val = 0; + + char name[YAFFS_MAX_NAME_LENGTH + 1]; + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + yaffs_dev_to_lc(dev)->readdir_process = current; + + sc = yaffs_new_search(obj); + if (!sc) { + ret_val = -ENOMEM; + goto out; + } + + if (!dir_emit_dots(f, dc)) { + yaffs_gross_unlock(dev); + return 0; + } + + curoffs = 1; + + while (sc->next_return) { + curoffs++; + l = sc->next_return; + if (curoffs >= dc->pos) { + int this_inode = yaffs_get_obj_inode(l); + int this_type = yaffs_get_obj_type(l); + + yaffs_get_obj_name(l, name, YAFFS_MAX_NAME_LENGTH + 1); + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: %s inode %d", + name, yaffs_get_obj_inode(l)); + + yaffs_gross_unlock(dev); + + if (!dir_emit(dc, + name, + strlen(name), + this_inode, + this_type)) { + yaffs_gross_lock(dev); + goto out; + } + + yaffs_gross_lock(dev); + + dc->pos++; + f->f_pos++; + } + yaffs_search_advance(sc); + } + +out: + yaffs_search_end(sc); + yaffs_dev_to_lc(dev)->readdir_process = NULL; + yaffs_gross_unlock(dev); + + return ret_val; +} + +#else + +static int yaffs_readdir(struct file *f, void *dirent, filldir_t filldir) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + struct yaffs_search_context *sc; + struct inode *inode = Y_GET_DENTRY(f)->d_inode; + unsigned long offset, curoffs; + struct yaffs_obj *l; + int ret_val = 0; + u64 i_version; + + char name[YAFFS_MAX_NAME_LENGTH + 1]; + + obj = yaffs_dentry_to_obj(Y_GET_DENTRY(f)); + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + yaffs_dev_to_lc(dev)->readdir_process = current; + + offset = f->f_pos; + + sc = yaffs_new_search(obj); + if (!sc) { + ret_val = -ENOMEM; + goto out; + } + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: starting at %d", (int)offset); + + if (offset == 0) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: entry . ino %d", + (int)inode->i_ino); + yaffs_gross_unlock(dev); + if (filldir(dirent, ".", 1, offset, inode->i_ino, DT_DIR) < 0) { + yaffs_gross_lock(dev); + goto out; + } + yaffs_gross_lock(dev); + offset++; + f->f_pos++; + } + if (offset == 1) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: entry .. ino %d", + (int)f->f_dentry->d_parent->d_inode->i_ino); + yaffs_gross_unlock(dev); + if (filldir(dirent, "..", 2, offset, + f->f_dentry->d_parent->d_inode->i_ino, + DT_DIR) < 0) { + yaffs_gross_lock(dev); + goto out; + } + yaffs_gross_lock(dev); + offset++; + f->f_pos++; + } + + curoffs = 1; + + /* If the directory has changed since the open or last call to + readdir, rewind to after the 2 canned entries. */ + i_version = atomic64_read(&inode->i_version); + if (f->f_version != i_version) { + offset = 2; + f->f_pos = offset; + f->f_version = i_version; + } + + while (sc->next_return) { + curoffs++; + l = sc->next_return; + if (curoffs >= offset) { + int this_inode = yaffs_get_obj_inode(l); + int this_type = yaffs_get_obj_type(l); + + yaffs_get_obj_name(l, name, YAFFS_MAX_NAME_LENGTH + 1); + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: %s inode %d", + name, yaffs_get_obj_inode(l)); + + yaffs_gross_unlock(dev); + + if (filldir(dirent, + name, + strlen(name), + offset, this_inode, this_type) < 0) { + yaffs_gross_lock(dev); + goto out; + } + + yaffs_gross_lock(dev); + + offset++; + f->f_pos++; + } + yaffs_search_advance(sc); + } + +out: + yaffs_search_end(sc); + yaffs_dev_to_lc(dev)->readdir_process = NULL; + yaffs_gross_unlock(dev); + + return ret_val; +} + +#endif + +static const struct file_operations yaffs_dir_operations = { + .read = generic_read_dir, +#ifdef YAFFS_USE_DIR_ITERATE + .iterate = yaffs_iterate, +#else + .readdir = yaffs_readdir, +#endif + .fsync = yaffs_sync_object, + .llseek = generic_file_llseek, +}; + +static void yaffs_fill_inode_from_obj(struct inode *inode, + struct yaffs_obj *obj) +{ + if (inode && obj) { + + /* Check mode against the variant type and attempt to repair if broken. */ + u32 mode = obj->yst_mode; + switch (obj->variant_type) { + case YAFFS_OBJECT_TYPE_FILE: + if (!S_ISREG(mode)) { + obj->yst_mode &= ~S_IFMT; + obj->yst_mode |= S_IFREG; + } + + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + if (!S_ISLNK(mode)) { + obj->yst_mode &= ~S_IFMT; + obj->yst_mode |= S_IFLNK; + } + + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + if (!S_ISDIR(mode)) { + obj->yst_mode &= ~S_IFMT; + obj->yst_mode |= S_IFDIR; + } + + break; + case YAFFS_OBJECT_TYPE_UNKNOWN: + case YAFFS_OBJECT_TYPE_HARDLINK: + case YAFFS_OBJECT_TYPE_SPECIAL: + default: + /* TODO? */ + break; + } + + inode->i_flags |= S_NOATIME; + + inode->i_ino = obj->obj_id; + inode->i_mode = obj->yst_mode; + inode->i_uid = MAKE_uid(obj->yst_uid); + inode->i_gid = MAKE_gid(obj->yst_gid); +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19)) + inode->i_blksize = inode->i_sb->s_blocksize; +#endif +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + + inode->i_rdev = old_decode_dev(obj->yst_rdev); + inode->i_atime.tv_sec = (time64_t) (obj->yst_atime); + inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = (time64_t) obj->yst_mtime; + inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = (time64_t) obj->yst_ctime; + inode->i_ctime.tv_nsec = 0; +#else + inode->i_rdev = obj->yst_rdev; + inode->i_atime = obj->yst_atime; + inode->i_mtime = obj->yst_mtime; + inode->i_ctime = obj->yst_ctime; +#endif + inode->i_size = yaffs_get_obj_length(obj); + inode->i_blocks = (inode->i_size + 511) >> 9; + + set_nlink(inode, yaffs_get_obj_link_count(obj)); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_fill_inode mode %x uid %d gid %d size %lld count %d", + inode->i_mode, obj->yst_uid, obj->yst_gid, + inode->i_size, atomic_read(&inode->i_count)); + + switch (obj->yst_mode & S_IFMT) { + default: /* fifo, device or socket */ +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + init_special_inode(inode, obj->yst_mode, + old_decode_dev(obj->yst_rdev)); +#else + init_special_inode(inode, obj->yst_mode, + (dev_t) (obj->yst_rdev)); +#endif + break; + case S_IFREG: /* file */ + inode->i_op = &yaffs_file_inode_operations; + inode->i_fop = &yaffs_file_operations; + inode->i_mapping->a_ops = + &yaffs_file_address_operations; + break; + case S_IFDIR: /* directory */ + inode->i_op = &yaffs_dir_inode_operations; + inode->i_fop = &yaffs_dir_operations; + break; + case S_IFLNK: /* symlink */ + inode->i_op = &yaffs_symlink_inode_operations; + break; + } + + yaffs_inode_to_obj_lv(inode) = obj; + + obj->my_inode = inode; + + } else { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_fill_inode invalid parameters"); + } + +} + + + +/* + * yaffs background thread functions . + * yaffs_bg_thread_fn() the thread function + * yaffs_bg_start() launches the background thread. + * yaffs_bg_stop() cleans up the background thread. + * + * NB: + * The thread should only run after the yaffs is initialised + * The thread should be stopped before yaffs is unmounted. + * The thread should not do any writing while the fs is in read only. + */ + +static unsigned yaffs_bg_gc_urgency(struct yaffs_dev *dev) +{ + unsigned erased_chunks = + dev->n_erased_blocks * dev->param.chunks_per_block; + struct yaffs_linux_context *context = yaffs_dev_to_lc(dev); + unsigned scattered = 0; /* Free chunks not in an erased block */ + + if (erased_chunks < dev->n_free_chunks) + scattered = (dev->n_free_chunks - erased_chunks); + + if (!context->bg_running) + return 0; + else if (scattered < (dev->param.chunks_per_block * 2)) + return 0; + else if (erased_chunks > dev->n_free_chunks / 2) + return 0; + else if (erased_chunks > dev->n_free_chunks / 4) + return 1; + else + return 2; +} + +#ifdef YAFFS_COMPILE_BACKGROUND + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 15, 0)) +struct timer_struct { + struct task_struct *task; + struct timer_list timer; +}; +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 15, 0)) +static void yaffs_background_waker(struct timer_list *t) +{ + struct timer_struct *ts = from_timer(ts, t, timer); + + wake_up_process(ts->task); +} +#else +void yaffs_background_waker(unsigned long data) +{ + wake_up_process((struct task_struct *)data); +} +#endif + +static int yaffs_bg_thread_fn(void *data) +{ + struct yaffs_dev *dev = (struct yaffs_dev *)data; + struct yaffs_linux_context *context = yaffs_dev_to_lc(dev); + unsigned long now = jiffies; + unsigned long next_dir_update = now; + unsigned long next_gc = now; + unsigned long expires; + unsigned int urgency; + + int gc_result; +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 15, 0)) + struct timer_struct timer; +#else + struct timer_list timer; +#endif + + yaffs_trace(YAFFS_TRACE_BACKGROUND, + "yaffs_background starting for dev %p", (void *)dev); + +#ifdef YAFFS_COMPILE_FREEZER + set_freezable(); +#endif + while (context->bg_running) { + yaffs_trace(YAFFS_TRACE_BACKGROUND, "yaffs_background"); + + if (kthread_should_stop()) + break; + +#ifdef YAFFS_COMPILE_FREEZER + if (try_to_freeze()) + continue; +#endif + yaffs_gross_lock(dev); + + now = jiffies; + + if (time_after(now, next_dir_update) && yaffs_bg_enable) { + yaffs_update_dirty_dirs(dev); + next_dir_update = now + HZ; + } + + if (time_after(now, next_gc) && yaffs_bg_enable) { + if (!dev->is_checkpointed) { + urgency = yaffs_bg_gc_urgency(dev); + gc_result = yaffs_bg_gc(dev, urgency); + if (urgency > 1) + next_gc = now + HZ / 20 + 1; + else if (urgency > 0) + next_gc = now + HZ / 10 + 1; + else + next_gc = now + HZ * 2; + } else { + /* + * gc not running so set to next_dir_update + * to cut down on wake ups + */ + next_gc = next_dir_update; + } + } + yaffs_gross_unlock(dev); + expires = next_dir_update; + if (time_before(next_gc, expires)) + expires = next_gc; + if (time_before(expires, now)) + expires = now + HZ; + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 15, 0)) + Y_INIT_TIMER(&timer.timer, yaffs_background_waker); + timer.timer.expires = expires + 1; + timer.task = current; +#else + Y_INIT_TIMER(&timer); + timer.expires = expires + 1; + timer.data = (unsigned long)current; + timer.function = yaffs_background_waker; +#endif + + set_current_state(TASK_INTERRUPTIBLE); +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4, 15, 0)) + add_timer(&timer.timer); + schedule(); + del_timer_sync(&timer.timer); +#else + add_timer(&timer); + schedule(); + del_timer_sync(&timer); +#endif + } + + return 0; +} + +static int yaffs_bg_start(struct yaffs_dev *dev) +{ + int retval = 0; + struct yaffs_linux_context *context = yaffs_dev_to_lc(dev); + + if (dev->read_only) + return -1; + + context->bg_running = 1; + + context->bg_thread = kthread_run(yaffs_bg_thread_fn, + (void *)dev, "yaffs-bg-%d", + context->mount_id); + + if (IS_ERR(context->bg_thread)) { + retval = PTR_ERR(context->bg_thread); + context->bg_thread = NULL; + context->bg_running = 0; + } + return retval; +} + +static void yaffs_bg_stop(struct yaffs_dev *dev) +{ + struct yaffs_linux_context *ctxt = yaffs_dev_to_lc(dev); + + ctxt->bg_running = 0; + + if (ctxt->bg_thread) { + kthread_stop(ctxt->bg_thread); + ctxt->bg_thread = NULL; + } +} +#else +static int yaffs_bg_thread_fn(void *data) +{ + return 0; +} + +static int yaffs_bg_start(struct yaffs_dev *dev) +{ + return 0; +} + +static void yaffs_bg_stop(struct yaffs_dev *dev) +{ +} +#endif + + +static void yaffs_flush_inodes(struct super_block *sb) +{ + struct inode *iptr; + struct yaffs_obj *obj; + + list_for_each_entry(iptr, &sb->s_inodes, i_sb_list) { + obj = yaffs_inode_to_obj(iptr); + if (obj) { + yaffs_trace(YAFFS_TRACE_OS, + "flushing obj %d", + obj->obj_id); + yaffs_flush_file(obj, 1, 0, 0); + } + } +} + +static void yaffs_flush_super(struct super_block *sb, int do_checkpoint) +{ + struct yaffs_dev *dev = yaffs_super_to_dev(sb); + if (!dev) + return; + + yaffs_flush_inodes(sb); + yaffs_update_dirty_dirs(dev); + yaffs_flush_whole_cache(dev, 1); + if (do_checkpoint) + yaffs_checkpoint_save(dev); +} + +static LIST_HEAD(yaffs_context_list); +struct mutex yaffs_context_lock; + +static void yaffs_put_super(struct super_block *sb) +{ + struct yaffs_dev *dev = yaffs_super_to_dev(sb); + struct mtd_info *mtd = yaffs_dev_to_mtd(dev); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_ALWAYS, + "yaffs_put_super"); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_BACKGROUND, + "Shutting down yaffs background thread"); + yaffs_bg_stop(dev); + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_BACKGROUND, + "yaffs background thread shut down"); + + yaffs_gross_lock(dev); + + yaffs_flush_super(sb, 1); + + yaffs_deinitialise(dev); + + yaffs_gross_unlock(dev); + + mutex_lock(&yaffs_context_lock); + list_del_init(&(yaffs_dev_to_lc(dev)->context_list)); + mutex_unlock(&yaffs_context_lock); + + if (yaffs_dev_to_lc(dev)->spare_buffer) { + kfree(yaffs_dev_to_lc(dev)->spare_buffer); + yaffs_dev_to_lc(dev)->spare_buffer = NULL; + } + + if (dev->os_context) + kfree(dev->os_context); + + kfree(dev); + + yaffs_put_mtd_device(mtd); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_ALWAYS, + "yaffs_put_super done"); +} + + +static unsigned yaffs_gc_control_callback(struct yaffs_dev *dev) +{ + return yaffs_gc_control; +} + + +#ifdef YAFFS_COMPILE_EXPORTFS + +static struct inode *yaffs2_nfs_get_inode(struct super_block *sb, uint64_t ino, + uint32_t generation) +{ + return Y_IGET(sb, ino); +} + +static struct dentry *yaffs2_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + yaffs2_nfs_get_inode); +} + +static struct dentry *yaffs2_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + yaffs2_nfs_get_inode); +} + +struct dentry *yaffs2_get_parent(struct dentry *dentry) +{ + + struct super_block *sb = dentry->d_inode->i_sb; + struct dentry *parent = ERR_PTR(-ENOENT); + struct inode *inode; + unsigned long parent_ino; + struct yaffs_obj *d_obj; + struct yaffs_obj *parent_obj; + + d_obj = yaffs_inode_to_obj(dentry->d_inode); + + if (d_obj) { + parent_obj = d_obj->parent; + if (parent_obj) { + parent_ino = yaffs_get_obj_inode(parent_obj); + inode = Y_IGET(sb, parent_ino); + + if (IS_ERR(inode)) { + parent = ERR_CAST(inode); + } else { + parent = d_obtain_alias(inode); + if (!IS_ERR(parent)) { + parent = ERR_PTR(-ENOMEM); + iput(inode); + } + } + } + } + + return parent; +} + +/* Just declare a zero structure as a NULL value implies + * using the default functions of exportfs. + */ + +static struct export_operations yaffs_export_ops = { + .fh_to_dentry = yaffs2_fh_to_dentry, + .fh_to_parent = yaffs2_fh_to_parent, + .get_parent = yaffs2_get_parent, +}; + +#endif + +static void yaffs_unstitch_obj(struct inode *inode, struct yaffs_obj *obj) +{ + /* Clear the association between the inode and + * the struct yaffs_obj. + */ + obj->my_inode = NULL; + yaffs_inode_to_obj_lv(inode) = NULL; + + /* If the object freeing was deferred, then the real + * free happens now. + * This should fix the inode inconsistency problem. + */ + yaffs_handle_defered_free(obj); +} + +#ifdef YAFFS_HAS_EVICT_INODE +/* yaffs_evict_inode combines into one operation what was previously done in + * yaffs_clear_inode() and yaffs_delete_inode() + * + */ +static void yaffs_evict_inode(struct inode *inode) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + int deleteme = 0; + + obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_evict_inode: ino %d, count %d %s", + (int)inode->i_ino, atomic_read(&inode->i_count), + obj ? "object exists" : "null object"); + + if (!inode->i_nlink && !is_bad_inode(inode)) + deleteme = 1; + truncate_inode_pages(&inode->i_data, 0); + Y_CLEAR_INODE(inode); + + if (deleteme && obj) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + yaffs_del_obj(obj); + yaffs_gross_unlock(dev); + } + if (obj) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + yaffs_unstitch_obj(inode, obj); + yaffs_gross_unlock(dev); + } +} +#else + +/* clear is called to tell the fs to release any per-inode data it holds. + * The object might still exist on disk and is just being thrown out of the cache + * or else the object has actually been deleted and we're being called via + * the chain + * yaffs_delete_inode() -> clear_inode()->yaffs_clear_inode() + */ + +static void yaffs_clear_inode(struct inode *inode) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + + obj = yaffs_inode_to_obj(inode); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_clear_inode: ino %d, count %d %s", + (int)inode->i_ino, atomic_read(&inode->i_count), + obj ? "object exists" : "null object"); + + if (obj) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + yaffs_unstitch_obj(inode, obj); + yaffs_gross_unlock(dev); + } + +} + +/* delete is called when the link count is zero and the inode + * is put (ie. nobody wants to know about it anymore, time to + * delete the file). + * NB Must call clear_inode() + */ +static void yaffs_delete_inode(struct inode *inode) +{ + struct yaffs_obj *obj = yaffs_inode_to_obj(inode); + struct yaffs_dev *dev; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_delete_inode: ino %d, count %d %s", + (int)inode->i_ino, atomic_read(&inode->i_count), + obj ? "object exists" : "null object"); + + if (obj) { + dev = obj->my_dev; + yaffs_gross_lock(dev); + yaffs_del_obj(obj); + yaffs_gross_unlock(dev); + } +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 13)) + truncate_inode_pages(&inode->i_data, 0); +#endif + clear_inode(inode); +} +#endif + + + + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static int yaffs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct yaffs_dev *dev = yaffs_dentry_to_obj(dentry)->my_dev; + struct super_block *sb = dentry->d_sb; +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs_statfs(struct super_block *sb, struct kstatfs *buf) +{ + struct yaffs_dev *dev = yaffs_super_to_dev(sb); +#else +static int yaffs_statfs(struct super_block *sb, struct statfs *buf) +{ + struct yaffs_dev *dev = yaffs_super_to_dev(sb); +#endif + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_statfs"); + + yaffs_gross_lock(dev); + + buf->f_type = YAFFS_MAGIC; + buf->f_bsize = sb->s_blocksize; + buf->f_namelen = 255; + + if (dev->data_bytes_per_chunk & (dev->data_bytes_per_chunk - 1)) { + /* Do this if chunk size is not a power of 2 */ + + uint64_t bytes_in_dev; + uint64_t bytes_free; + + bytes_in_dev = + ((uint64_t) + ((dev->param.end_block - dev->param.start_block + + 1))) * ((uint64_t) (dev->param.chunks_per_block * + dev->data_bytes_per_chunk)); + + do_div(bytes_in_dev, sb->s_blocksize); /* bytes_in_dev becomes the number of blocks */ + buf->f_blocks = bytes_in_dev; + + bytes_free = ((uint64_t) (yaffs_get_n_free_chunks(dev))) * + ((uint64_t) (dev->data_bytes_per_chunk)); + + do_div(bytes_free, sb->s_blocksize); + + buf->f_bfree = bytes_free; + + } else if (sb->s_blocksize > dev->data_bytes_per_chunk) { + + buf->f_blocks = + (dev->param.end_block - dev->param.start_block + 1) * + dev->param.chunks_per_block / + (sb->s_blocksize / dev->data_bytes_per_chunk); + buf->f_bfree = + yaffs_get_n_free_chunks(dev) / + (sb->s_blocksize / dev->data_bytes_per_chunk); + } else { + buf->f_blocks = + (dev->param.end_block - dev->param.start_block + 1) * + dev->param.chunks_per_block * + (dev->data_bytes_per_chunk / sb->s_blocksize); + + buf->f_bfree = + yaffs_get_n_free_chunks(dev) * + (dev->data_bytes_per_chunk / sb->s_blocksize); + } + + buf->f_files = 0; + buf->f_ffree = 0; + buf->f_bavail = buf->f_bfree; + + yaffs_gross_unlock(dev); + return 0; +} + + + +static int yaffs_do_sync_fs(struct super_block *sb, int request_checkpoint) +{ + + struct yaffs_dev *dev = yaffs_super_to_dev(sb); + unsigned int oneshot_checkpoint = (yaffs_auto_checkpoint & 4); + unsigned gc_urgent = yaffs_bg_gc_urgency(dev); + int do_checkpoint; + int dirty = yaffs_check_super_dirty(dev); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC | YAFFS_TRACE_BACKGROUND, + "yaffs_do_sync_fs: gc-urgency %d %s %s%s", + gc_urgent, + dirty ? "dirty" : "clean", + request_checkpoint ? "checkpoint requested" : "no checkpoint", + oneshot_checkpoint ? " one-shot" : ""); + + yaffs_gross_lock(dev); + do_checkpoint = ((request_checkpoint && !gc_urgent) || + oneshot_checkpoint) && !dev->is_checkpointed; + + if (dirty || do_checkpoint) { + yaffs_flush_super(sb, !dev->is_checkpointed && do_checkpoint); + yaffs_clear_super_dirty(dev); + if (oneshot_checkpoint) + yaffs_auto_checkpoint &= ~4; + } + yaffs_gross_unlock(dev); + + return 0; +} + + +#ifdef YAFFS_HAS_WRITE_SUPER +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static void yaffs_write_super(struct super_block *sb) +#else +static int yaffs_write_super(struct super_block *sb) +#endif +{ + unsigned request_checkpoint = (yaffs_auto_checkpoint >= 2); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC | YAFFS_TRACE_BACKGROUND, + "yaffs_write_super %s", + request_checkpoint ? " checkpt" : ""); + + yaffs_do_sync_fs(sb, request_checkpoint); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 18)) + return 0; +#endif +} +#endif + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static int yaffs_sync_fs(struct super_block *sb, int wait) +#else +static int yaffs_sync_fs(struct super_block *sb) +#endif +{ + unsigned request_checkpoint = (yaffs_auto_checkpoint >= 1); + + yaffs_trace(YAFFS_TRACE_OS | YAFFS_TRACE_SYNC, + "yaffs_sync_fs%s", request_checkpoint ? " checkpt" : ""); + + yaffs_do_sync_fs(sb, request_checkpoint); + + return 0; +} + +/* the function only is used to change dev->read_only when this file system + * is remounted. + */ +static int yaffs_remount_fs(struct super_block *sb, int *flags, char *data) +{ + int read_only = 0; + struct mtd_info *mtd; + struct yaffs_dev *dev = 0; + + /* Get the device */ + mtd = get_mtd_device(NULL, MINOR(sb->s_dev)); + if (!mtd) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "MTD device #%u doesn't appear to exist", + MINOR(sb->s_dev)); + return 1; + } + + /* Check it's NAND */ + if (mtd->type != MTD_NANDFLASH) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "MTD device is not NAND it's type %d", + mtd->type); + return 1; + } + + read_only = ((*flags & MS_RDONLY) != 0); + if (!read_only && !(mtd->flags & MTD_WRITEABLE)) { + read_only = 1; + printk(KERN_INFO + "yaffs: mtd is read only, setting superblock read only"); + *flags |= MS_RDONLY; + } + + dev = sb->s_fs_info; + dev->read_only = read_only; + + return 0; +} + +static const struct super_operations yaffs_super_ops = { + .statfs = yaffs_statfs, + +#ifndef YAFFS_USE_OWN_IGET + .read_inode = yaffs_read_inode, +#endif +#ifdef YAFFS_HAS_PUT_INODE + .put_inode = yaffs_put_inode, +#endif + .put_super = yaffs_put_super, +#ifdef YAFFS_HAS_EVICT_INODE + .evict_inode = yaffs_evict_inode, +#else + .delete_inode = yaffs_delete_inode, + .clear_inode = yaffs_clear_inode, +#endif + .sync_fs = yaffs_sync_fs, +#ifdef YAFFS_HAS_WRITE_SUPER + .write_super = yaffs_write_super, +#endif + .remount_fs = yaffs_remount_fs, +}; + +struct yaffs_options { + int inband_tags; + int skip_checkpoint_read; + int skip_checkpoint_write; + int no_cache; + int tags_ecc_on; + int tags_ecc_overridden; + int lazy_loading_enabled; + int lazy_loading_overridden; + int empty_lost_and_found; + int empty_lost_and_found_overridden; + int disable_summary; +}; + +#define MAX_OPT_LEN 30 +static int yaffs_parse_options(struct yaffs_options *options, + const char *options_str) +{ + char cur_opt[MAX_OPT_LEN + 1]; + int p; + int error = 0; + + /* Parse through the options which is a comma seperated list */ + + while (options_str && *options_str && !error) { + memset(cur_opt, 0, MAX_OPT_LEN + 1); + p = 0; + + while (*options_str == ',') + options_str++; + + while (*options_str && *options_str != ',') { + if (p < MAX_OPT_LEN) { + cur_opt[p] = *options_str; + p++; + } + options_str++; + } + + if (!strcmp(cur_opt, "inband-tags")) { + options->inband_tags = 1; + } else if (!strcmp(cur_opt, "tags-ecc-off")) { + options->tags_ecc_on = 0; + options->tags_ecc_overridden = 1; + } else if (!strcmp(cur_opt, "tags-ecc-on")) { + options->tags_ecc_on = 1; + options->tags_ecc_overridden = 1; + } else if (!strcmp(cur_opt, "lazy-loading-off")) { + options->lazy_loading_enabled = 0; + options->lazy_loading_overridden = 1; + } else if (!strcmp(cur_opt, "lazy-loading-on")) { + options->lazy_loading_enabled = 1; + options->lazy_loading_overridden = 1; + } else if (!strcmp(cur_opt, "disable-summary")) { + options->disable_summary = 1; + } else if (!strcmp(cur_opt, "empty-lost-and-found-off")) { + options->empty_lost_and_found = 0; + options->empty_lost_and_found_overridden = 1; + } else if (!strcmp(cur_opt, "empty-lost-and-found-on")) { + options->empty_lost_and_found = 1; + options->empty_lost_and_found_overridden = 1; + } else if (!strcmp(cur_opt, "no-cache")) { + options->no_cache = 1; + } else if (!strcmp(cur_opt, "no-checkpoint-read")) { + options->skip_checkpoint_read = 1; + } else if (!strcmp(cur_opt, "no-checkpoint-write")) { + options->skip_checkpoint_write = 1; + } else if (!strcmp(cur_opt, "no-checkpoint")) { + options->skip_checkpoint_read = 1; + options->skip_checkpoint_write = 1; + } else { + printk(KERN_INFO "yaffs: Bad mount option \"%s\"\n", + cur_opt); + error = 1; + } + } + + return error; +} + + +static struct dentry *yaffs_make_root(struct inode *inode) +{ +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)) + struct dentry *root = d_alloc_root(inode); + + if (!root) + iput(inode); + + return root; +#else + return d_make_root(inode); +#endif +} + + + + +static struct super_block *yaffs_internal_read_super(int yaffs_version, + struct super_block *sb, + void *data, int silent) +{ + int n_blocks; + struct inode *inode = NULL; + struct dentry *root; + struct yaffs_dev *dev = 0; + char devname_buf[BDEVNAME_SIZE + 1]; + struct mtd_info *mtd; + int err; + char *data_str = (char *)data; + struct yaffs_linux_context *context = NULL; + struct yaffs_param *param; + + int read_only = 0; + int inband_tags = 0; + + struct yaffs_options options; + + unsigned mount_id; + int found; + struct yaffs_linux_context *context_iterator; + struct list_head *l; + + if (!sb) { + printk(KERN_INFO "yaffs: sb is NULL\n"); + return NULL; + } + + sb->s_magic = YAFFS_MAGIC; + sb->s_op = &yaffs_super_ops; + sb->s_flags |= MS_NOATIME; + + read_only = ((sb->s_flags & MS_RDONLY) != 0); + +#ifdef YAFFS_COMPILE_EXPORTFS + sb->s_export_op = &yaffs_export_ops; +#endif + + if (!sb->s_dev) + printk(KERN_INFO "yaffs: sb->s_dev is NULL\n"); + else if (!yaffs_devname(sb, devname_buf)) + printk(KERN_INFO "yaffs: devname is NULL\n"); + else + printk(KERN_INFO "yaffs: dev is %d name is \"%s\" %s\n", + sb->s_dev, + yaffs_devname(sb, devname_buf), read_only ? "ro" : "rw"); + + if (!data_str) + data_str = ""; + + printk(KERN_INFO "yaffs: passed flags \"%s\"\n", data_str); + + memset(&options, 0, sizeof(options)); + + if (yaffs_parse_options(&options, data_str)) { + /* Option parsing failed */ + return NULL; + } + + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_read_super: Using yaffs%d", yaffs_version); + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_read_super: block size %d", (int)(sb->s_blocksize)); + + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs: Attempting MTD mount of %u.%u,\"%s\"", + MAJOR(sb->s_dev), MINOR(sb->s_dev), + yaffs_devname(sb, devname_buf)); + + + mtd = yaffs_get_mtd_device(sb->s_dev); + if (IS_ERR(mtd)) { + return NULL; + } + + if (yaffs_auto_select && yaffs_version == 1 && WRITE_SIZE(mtd) >= 2048) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "auto selecting yaffs2"); + yaffs_version = 2; + } + + if (mtd->oobavail < sizeof(struct yaffs_packed_tags2) || + options.inband_tags) + inband_tags = 1; + + /* Added NCB 26/5/2006 for completeness */ + if (yaffs_version == 2 && !inband_tags + && WRITE_SIZE(mtd) == 512) { + yaffs_trace(YAFFS_TRACE_ALWAYS, "auto selecting yaffs1"); + yaffs_version = 1; + } + + if(yaffs_verify_mtd(mtd, yaffs_version, inband_tags) < 0) + return NULL; + + /* OK, so if we got here, we have an MTD that's NAND and looks + * like it has the right capabilities + * Set the struct yaffs_dev up for mtd + */ + + if (!read_only && !(mtd->flags & MTD_WRITEABLE)) { + read_only = 1; + printk(KERN_INFO + "yaffs: mtd is read only, setting superblock read only\n" + ); + sb->s_flags |= MS_RDONLY; + } + + dev = kmalloc(sizeof(struct yaffs_dev), GFP_KERNEL); + context = kmalloc(sizeof(struct yaffs_linux_context), GFP_KERNEL); + + if (!dev || !context) { + kfree(dev); + kfree(context); + dev = NULL; + context = NULL; + + /* Deep shit could not allocate device structure */ + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs_read_super: Failed trying to allocate struct yaffs_dev." + ); + return NULL; + } + memset(dev, 0, sizeof(struct yaffs_dev)); + param = &(dev->param); + + memset(context, 0, sizeof(struct yaffs_linux_context)); + dev->os_context = context; + INIT_LIST_HEAD(&(context->context_list)); + context->dev = dev; + context->super = sb; + + dev->read_only = read_only; + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) + sb->s_fs_info = dev; +#else + sb->u.generic_sbp = dev; +#endif + + + dev->driver_context = mtd; + param->name = mtd->name; + + /* Set up the memory size parameters.... */ + + + param->n_reserved_blocks = 5; + param->n_caches = (options.no_cache) ? 0 : 10; + param->inband_tags = inband_tags; + + param->enable_xattr = 1; + if (options.lazy_loading_overridden) + param->disable_lazy_load = !options.lazy_loading_enabled; + + param->defered_dir_update = 1; + + if (options.tags_ecc_overridden) + param->no_tags_ecc = !options.tags_ecc_on; + + param->empty_lost_n_found = 1; + param->refresh_period = 500; + param->disable_summary = options.disable_summary; + + +#ifdef CONFIG_YAFFS_DISABLE_BAD_BLOCK_MARKING + param->disable_bad_block_marking = 1; +#endif + if (options.empty_lost_and_found_overridden) + param->empty_lost_n_found = options.empty_lost_and_found; + + /* ... and the functions. */ + if (yaffs_version == 2) { + param->is_yaffs2 = 1; +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) + param->total_bytes_per_chunk = mtd->writesize; + param->chunks_per_block = mtd->erasesize / mtd->writesize; +#else + param->total_bytes_per_chunk = mtd->oobblock; + param->chunks_per_block = mtd->erasesize / mtd->oobblock; +#endif + n_blocks = YCALCBLOCKS(mtd->size, mtd->erasesize); + + param->start_block = 0; + param->end_block = n_blocks - 1; + } else { + param->is_yaffs2 = 0; + n_blocks = YCALCBLOCKS(mtd->size, + YAFFS_CHUNKS_PER_BLOCK * YAFFS_BYTES_PER_CHUNK); + + param->chunks_per_block = YAFFS_CHUNKS_PER_BLOCK; + param->total_bytes_per_chunk = YAFFS_BYTES_PER_CHUNK; + } + + param->start_block = 0; + param->end_block = n_blocks - 1; + + yaffs_mtd_drv_install(dev); + + param->sb_dirty_fn = yaffs_set_super_dirty; + param->gc_control_fn = yaffs_gc_control_callback; + + yaffs_dev_to_lc(dev)->super = sb; + + param->use_nand_ecc = 1; + + param->skip_checkpt_rd = options.skip_checkpoint_read; + param->skip_checkpt_wr = options.skip_checkpoint_write; + + mutex_lock(&yaffs_context_lock); + /* Get a mount id */ + found = 0; + for (mount_id = 0; !found; mount_id++) { + found = 1; + list_for_each(l, &yaffs_context_list) { + context_iterator = + list_entry(l, struct yaffs_linux_context, + context_list); + if (context_iterator->mount_id == mount_id) + found = 0; + } + } + context->mount_id = mount_id; + + list_add_tail(&(yaffs_dev_to_lc(dev)->context_list), + &yaffs_context_list); + mutex_unlock(&yaffs_context_lock); + + /* Directory search handling... */ + INIT_LIST_HEAD(&(yaffs_dev_to_lc(dev)->search_contexts)); + param->remove_obj_fn = yaffs_remove_obj_callback; + + mutex_init(&(yaffs_dev_to_lc(dev)->gross_lock)); + + yaffs_gross_lock(dev); + + err = yaffs_guts_initialise(dev); + + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_read_super: guts initialised %s", + (err == YAFFS_OK) ? "OK" : "FAILED"); + + if (err == YAFFS_OK) + yaffs_bg_start(dev); + + if (!context->bg_thread) + param->defered_dir_update = 0; + + sb->s_maxbytes = yaffs_max_file_size(dev); + + /* Release lock before yaffs_get_inode() */ + yaffs_gross_unlock(dev); + + /* Create root inode */ + if (err == YAFFS_OK) + inode = yaffs_get_inode(sb, S_IFDIR | 0755, 0, yaffs_root(dev)); + + if (!inode) + return NULL; + + inode->i_op = &yaffs_dir_inode_operations; + inode->i_fop = &yaffs_dir_operations; + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_read_super: got root inode"); + + root = yaffs_make_root(inode); + + if (!root) + return NULL; + + sb->s_root = root; + if(!dev->is_checkpointed) + yaffs_set_super_dirty(dev); + + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs_read_super: is_checkpointed %d", + dev->is_checkpointed); + + yaffs_trace(YAFFS_TRACE_OS, "yaffs_read_super: done"); + return sb; +} + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs_internal_read_super_mtd(struct super_block *sb, void *data, + int silent) +{ + return yaffs_internal_read_super(1, sb, data, silent) ? 0 : -EINVAL; +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)) +static struct dentry *yaffs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, yaffs_internal_read_super_mtd); +} +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static int yaffs_read_super(struct file_system_type *fs, + int flags, const char *dev_name, + void *data, struct vfsmount *mnt) +{ + + return get_sb_bdev(fs, flags, dev_name, data, + yaffs_internal_read_super_mtd, mnt); +} +#else +static struct super_block *yaffs_read_super(struct file_system_type *fs, + int flags, const char *dev_name, + void *data) +{ + + return get_sb_bdev(fs, flags, dev_name, data, + yaffs_internal_read_super_mtd); +} +#endif + +static struct file_system_type yaffs_fs_type = { + .owner = THIS_MODULE, + .name = "yaffs", +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)) + .mount = yaffs_mount, +#else + .get_sb = yaffs_read_super, +#endif + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +#else +static struct super_block *yaffs_read_super(struct super_block *sb, void *data, + int silent) +{ + return yaffs_internal_read_super(1, sb, data, silent); +} + +static DECLARE_FSTYPE(yaffs_fs_type, "yaffs", yaffs_read_super, + FS_REQUIRES_DEV); +#endif + + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +static int yaffs2_internal_read_super_mtd(struct super_block *sb, void *data, + int silent) +{ + return yaffs_internal_read_super(2, sb, data, silent) ? 0 : -EINVAL; +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)) +static struct dentry *yaffs2_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, yaffs2_internal_read_super_mtd); +} +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 17)) +static int yaffs2_read_super(struct file_system_type *fs, + int flags, const char *dev_name, void *data, + struct vfsmount *mnt) +{ + return get_sb_bdev(fs, flags, dev_name, data, + yaffs2_internal_read_super_mtd, mnt); +} +#else +static struct super_block *yaffs2_read_super(struct file_system_type *fs, + int flags, const char *dev_name, + void *data) +{ + + return get_sb_bdev(fs, flags, dev_name, data, + yaffs2_internal_read_super_mtd); +} +#endif + +static struct file_system_type yaffs2_fs_type = { + .owner = THIS_MODULE, + .name = "yaffs2", +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)) + .mount = yaffs2_mount, +#else + .get_sb = yaffs2_read_super, +#endif + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +#else +static struct super_block *yaffs2_read_super(struct super_block *sb, + void *data, int silent) +{ + return yaffs_internal_read_super(2, sb, data, silent); +} + +static DECLARE_FSTYPE(yaffs2_fs_type, "yaffs2", yaffs2_read_super, + FS_REQUIRES_DEV); +#endif + + +static struct proc_dir_entry *my_proc_entry; + +static char *yaffs_dump_dev_part0(char *buf, struct yaffs_dev *dev) +{ + struct yaffs_param *param = &dev->param; + int bs[10]; + + yaffs_count_blocks_by_state(dev,bs); + + buf += sprintf(buf, "start_block.......... %d\n", param->start_block); + buf += sprintf(buf, "end_block............ %d\n", param->end_block); + buf += sprintf(buf, "total_bytes_per_chunk %d\n", + param->total_bytes_per_chunk); + buf += sprintf(buf, "use_nand_ecc......... %d\n", param->use_nand_ecc); + buf += sprintf(buf, "no_tags_ecc.......... %d\n", param->no_tags_ecc); + buf += sprintf(buf, "is_yaffs2............ %d\n", param->is_yaffs2); + buf += sprintf(buf, "inband_tags.......... %d\n", param->inband_tags); + buf += sprintf(buf, "empty_lost_n_found... %d\n", + param->empty_lost_n_found); + buf += sprintf(buf, "disable_lazy_load.... %d\n", + param->disable_lazy_load); + buf += sprintf(buf, "disable_bad_block_mrk %d\n", + param->disable_bad_block_marking); + buf += sprintf(buf, "refresh_period....... %d\n", + param->refresh_period); + buf += sprintf(buf, "n_caches............. %d\n", param->n_caches); + buf += sprintf(buf, "n_reserved_blocks.... %d\n", + param->n_reserved_blocks); + buf += sprintf(buf, "always_check_erased.. %d\n", + param->always_check_erased); + buf += sprintf(buf, "\n"); + buf += sprintf(buf, "block count by state\n"); + buf += sprintf(buf, "0:%d 1:%d 2:%d 3:%d 4:%d\n", + bs[0], bs[1], bs[2], bs[3], bs[4]); + buf += sprintf(buf, "5:%d 6:%d 7:%d 8:%d 9:%d\n", + bs[5], bs[6], bs[7], bs[8], bs[9]); + + return buf; +} + +static char *yaffs_dump_dev_part1(char *buf, struct yaffs_dev *dev) +{ + buf += sprintf(buf, "max file size....... %lld\n", + (long long) yaffs_max_file_size(dev)); + buf += sprintf(buf, "data_bytes_per_chunk. %d\n", + dev->data_bytes_per_chunk); + buf += sprintf(buf, "chunk_grp_bits....... %d\n", dev->chunk_grp_bits); + buf += sprintf(buf, "chunk_grp_size....... %d\n", dev->chunk_grp_size); + buf += sprintf(buf, "n_erased_blocks...... %d\n", dev->n_erased_blocks); + buf += sprintf(buf, "blocks_in_checkpt.... %d\n", + dev->blocks_in_checkpt); + buf += sprintf(buf, "\n"); + buf += sprintf(buf, "n_tnodes............. %d\n", dev->n_tnodes); + buf += sprintf(buf, "n_obj................ %d\n", dev->n_obj); + buf += sprintf(buf, "n_free_chunks........ %d\n", dev->n_free_chunks); + buf += sprintf(buf, "\n"); + buf += sprintf(buf, "n_page_writes........ %u\n", dev->n_page_writes); + buf += sprintf(buf, "n_page_reads......... %u\n", dev->n_page_reads); + buf += sprintf(buf, "n_erasures........... %u\n", dev->n_erasures); + buf += sprintf(buf, "n_gc_copies.......... %u\n", dev->n_gc_copies); + buf += sprintf(buf, "all_gcs.............. %u\n", dev->all_gcs); + buf += sprintf(buf, "passive_gc_count..... %u\n", + dev->passive_gc_count); + buf += sprintf(buf, "oldest_dirty_gc_count %u\n", + dev->oldest_dirty_gc_count); + buf += sprintf(buf, "n_gc_blocks.......... %u\n", dev->n_gc_blocks); + buf += sprintf(buf, "bg_gcs............... %u\n", dev->bg_gcs); + buf += sprintf(buf, "n_retried_writes..... %u\n", + dev->n_retried_writes); + buf += sprintf(buf, "n_retired_blocks..... %u\n", + dev->n_retired_blocks); + buf += sprintf(buf, "n_ecc_fixed.......... %u\n", dev->n_ecc_fixed); + buf += sprintf(buf, "n_ecc_unfixed........ %u\n", dev->n_ecc_unfixed); + buf += sprintf(buf, "n_tags_ecc_fixed..... %u\n", + dev->n_tags_ecc_fixed); + buf += sprintf(buf, "n_tags_ecc_unfixed... %u\n", + dev->n_tags_ecc_unfixed); + buf += sprintf(buf, "cache_hits........... %u\n", dev->cache_hits); + buf += sprintf(buf, "n_deleted_files...... %u\n", dev->n_deleted_files); + buf += sprintf(buf, "n_unlinked_files..... %u\n", + dev->n_unlinked_files); + buf += sprintf(buf, "refresh_count........ %u\n", dev->refresh_count); + buf += sprintf(buf, "n_bg_deletions....... %u\n", dev->n_bg_deletions); + buf += sprintf(buf, "tags_used............ %u\n", dev->tags_used); + buf += sprintf(buf, "summary_used......... %u\n", dev->summary_used); + + return buf; +} + +static int yaffs_proc_read(char *page, + char **start, + off_t offset, int count, int *eof, void *data) +{ + struct list_head *item; + char *buf = page; + int step = offset; + int n = 0; + + /* Get proc_file_read() to step 'offset' by one on each sucessive call. + * We use 'offset' (*ppos) to indicate where we are in dev_list. + * This also assumes the user has posted a read buffer large + * enough to hold the complete output; but that's life in /proc. + */ + + *(int *)start = 1; + + /* Print header first */ + if (step == 0) + buf += + sprintf(buf, "Multi-version YAFFS\n"); + else if (step == 1) + buf += sprintf(buf, "\n"); + else { + step -= 2; + + mutex_lock(&yaffs_context_lock); + + /* Locate and print the Nth entry. Order N-squared but N is small. */ + list_for_each(item, &yaffs_context_list) { + struct yaffs_linux_context *dc = + list_entry(item, struct yaffs_linux_context, + context_list); + struct yaffs_dev *dev = dc->dev; + + if (n < (step & ~1)) { + n += 2; + continue; + } + if ((step & 1) == 0) { + buf += + sprintf(buf, "\nDevice %d \"%s\"\n", n, + dev->param.name); + buf = yaffs_dump_dev_part0(buf, dev); + } else { + buf = yaffs_dump_dev_part1(buf, dev); + } + + break; + } + mutex_unlock(&yaffs_context_lock); + } + + return buf - page < count ? buf - page : count; +} + +/** + * Set the verbosity of the warnings and error messages. + * + * Note that the names can only be a..z or _ with the current code. + */ + +static struct { + char *mask_name; + unsigned mask_bitfield; +} mask_flags[] = { + {"allocate", YAFFS_TRACE_ALLOCATE}, + {"always", YAFFS_TRACE_ALWAYS}, + {"background", YAFFS_TRACE_BACKGROUND}, + {"bad_blocks", YAFFS_TRACE_BAD_BLOCKS}, + {"buffers", YAFFS_TRACE_BUFFERS}, + {"bug", YAFFS_TRACE_BUG}, + {"checkpt", YAFFS_TRACE_CHECKPOINT}, + {"deletion", YAFFS_TRACE_DELETION}, + {"erase", YAFFS_TRACE_ERASE}, + {"error", YAFFS_TRACE_ERROR}, + {"gc_detail", YAFFS_TRACE_GC_DETAIL}, + {"gc", YAFFS_TRACE_GC}, + {"lock", YAFFS_TRACE_LOCK}, + {"mtd", YAFFS_TRACE_MTD}, + {"nandaccess", YAFFS_TRACE_NANDACCESS}, + {"os", YAFFS_TRACE_OS}, + {"scan_debug", YAFFS_TRACE_SCAN_DEBUG}, + {"scan", YAFFS_TRACE_SCAN}, + {"mount", YAFFS_TRACE_MOUNT}, + {"tracing", YAFFS_TRACE_TRACING}, + {"sync", YAFFS_TRACE_SYNC}, + {"write", YAFFS_TRACE_WRITE}, + {"verify", YAFFS_TRACE_VERIFY}, + {"verify_nand", YAFFS_TRACE_VERIFY_NAND}, + {"verify_full", YAFFS_TRACE_VERIFY_FULL}, + {"verify_all", YAFFS_TRACE_VERIFY_ALL}, + {"all", 0xffffffff}, + {"none", 0}, + {NULL, 0}, +}; + +#define MAX_MASK_NAME_LENGTH 40 +static int yaffs_proc_write_trace_options(struct file *file, const char *buf, + unsigned long count) +{ + unsigned rg = 0, mask_bitfield; + char *end; + char *mask_name; + const char *x; + char substring[MAX_MASK_NAME_LENGTH + 1]; + int i; + int done = 0; + int add, len = 0; + int pos = 0; + + rg = yaffs_trace_mask; + + while (!done && (pos < count)) { + done = 1; + while ((pos < count) && isspace(buf[pos])) + pos++; + + switch (buf[pos]) { + case '+': + case '-': + case '=': + add = buf[pos]; + pos++; + break; + + default: + add = ' '; + break; + } + mask_name = NULL; + + mask_bitfield = simple_strtoul(buf + pos, &end, 0); + + if (end > buf + pos) { + mask_name = "numeral"; + len = end - (buf + pos); + pos += len; + done = 0; + } else { + for (x = buf + pos, i = 0; + (*x == '_' || (*x >= 'a' && *x <= 'z')) && + i < MAX_MASK_NAME_LENGTH; x++, i++, pos++) + substring[i] = *x; + substring[i] = '\0'; + + for (i = 0; mask_flags[i].mask_name != NULL; i++) { + if (strcmp(substring, mask_flags[i].mask_name) + == 0) { + mask_name = mask_flags[i].mask_name; + mask_bitfield = + mask_flags[i].mask_bitfield; + done = 0; + break; + } + } + } + + if (mask_name != NULL) { + done = 0; + switch (add) { + case '-': + rg &= ~mask_bitfield; + break; + case '+': + rg |= mask_bitfield; + break; + case '=': + rg = mask_bitfield; + break; + default: + rg |= mask_bitfield; + break; + } + } + } + + yaffs_trace_mask = rg | YAFFS_TRACE_ALWAYS; + + printk(KERN_DEBUG "new trace = 0x%08X\n", yaffs_trace_mask); + + if (rg & YAFFS_TRACE_ALWAYS) { + for (i = 0; mask_flags[i].mask_name != NULL; i++) { + char flag; + flag = ((rg & mask_flags[i].mask_bitfield) == + mask_flags[i].mask_bitfield) ? '+' : '-'; + printk(KERN_DEBUG "%c%s\n", flag, + mask_flags[i].mask_name); + } + } + + return count; +} + +/* Debug strings are of the form: + * .bnnn print info on block n + * .cobjn,chunkn print nand chunk id for objn:chunkn + */ + +static int yaffs_proc_debug_write(struct file *file, const char *buf, + unsigned long count) +{ + + char str[100]; + char *p0; + char *p1; + long p1_val; + long p0_val; + char cmd; + struct list_head *item; + + memset(str, 0, sizeof(str)); + memcpy(str, buf, min((size_t)count, sizeof(str) -1)); + + cmd = str[1]; + + p0 = str + 2; + + p1 = p0; + + while (*p1 && *p1 != ',') { + p1++; + } + *p1 = '\0'; + p1++; + + p0_val = simple_strtol(p0, NULL, 0); + p1_val = simple_strtol(p1, NULL, 0); + + + mutex_lock(&yaffs_context_lock); + + /* Locate and print the Nth entry. Order N-squared but N is small. */ + list_for_each(item, &yaffs_context_list) { + struct yaffs_linux_context *dc = + list_entry(item, struct yaffs_linux_context, + context_list); + struct yaffs_dev *dev = dc->dev; + + if (cmd == 'b') { + struct yaffs_block_info *bi; + + bi = yaffs_get_block_info(dev,p0_val); + + if(bi) { + printk("Block %d: state %d, retire %d, use %d, seq %d\n", + (int)p0_val, bi->block_state, + bi->needs_retiring, bi->pages_in_use, + bi->seq_number); + } + } else if (cmd == 'c') { + struct yaffs_obj *obj; + int nand_chunk; + + obj = yaffs_find_by_number(dev, p0_val); + if (!obj) + printk("No obj %d\n", (int)p0_val); + else { + if(p1_val == 0) + nand_chunk = obj->hdr_chunk; + else + nand_chunk = + yaffs_find_chunk_in_file(obj, + p1_val, NULL); + printk("Nand chunk for %d:%d is %d\n", + (int)p0_val, (int)p1_val, nand_chunk); + } + } + } + + mutex_unlock(&yaffs_context_lock); + + return count; +} + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 14, 0)) +static int yaffs_proc_write(struct file *file, const char *buf, + unsigned long count, void *ppos) +#else +static ssize_t yaffs_proc_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +#endif +{ + if (buf[0] == '.') + return yaffs_proc_debug_write(file, buf, count); + return yaffs_proc_write_trace_options(file, buf, count); +} + +/* Stuff to handle installation of file systems */ +struct file_system_to_install { + struct file_system_type *fst; + int installed; +}; + +static struct file_system_to_install fs_to_install[] = { + {&yaffs_fs_type, 0}, + {&yaffs2_fs_type, 0}, + {NULL, 0} +}; + + +#ifdef YAFFS_NEW_PROCFS +static int yaffs_proc_show(struct seq_file *m, void *v) +{ + /* FIXME: Unify in a better way? */ + char buffer[512]; + char *start; + int len; + + len = yaffs_proc_read(buffer, &start, 0, sizeof(buffer), NULL, NULL); + seq_puts(m, buffer); + return 0; +} + +static int yaffs_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, yaffs_proc_show, NULL); +} + +static struct proc_ops procfs_ops = { + .proc_open = yaffs_proc_open, + .proc_read = seq_read, + .proc_write = yaffs_proc_write, + .proc_release = single_release, +}; + +static int yaffs_procfs_init(void) +{ + /* Install the proc_fs entries */ + my_proc_entry = proc_create("yaffs", + S_IRUGO | S_IFREG, + YPROC_ROOT, + &procfs_ops); + + if (my_proc_entry) { + return 0; + } else { + return -ENOMEM; + } +} + +#else + + +static int yaffs_procfs_init(void) +{ + /* Install the proc_fs entries */ + my_proc_entry = create_proc_entry("yaffs", + S_IRUGO | S_IFREG, YPROC_ROOT); + + if (my_proc_entry) { + my_proc_entry->write_proc = yaffs_proc_write; + my_proc_entry->read_proc = yaffs_proc_read; + my_proc_entry->data = NULL; + return 0; + } else { + return -ENOMEM; + } +} + +#endif + + +static int __init init_yaffs_fs(void) +{ + int error = 0; + struct file_system_to_install *fsinst; + + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs Installing."); + + mutex_init(&yaffs_context_lock); + + error = yaffs_procfs_init(); + if (error) + return error; + + /* Now add the file system entries */ + + fsinst = fs_to_install; + + while (fsinst->fst && !error) { + error = register_filesystem(fsinst->fst); + if (!error) + fsinst->installed = 1; + fsinst++; + } + + /* Any errors? uninstall */ + if (error) { + fsinst = fs_to_install; + + while (fsinst->fst) { + if (fsinst->installed) { + unregister_filesystem(fsinst->fst); + fsinst->installed = 0; + } + fsinst++; + } + } + + return error; +} + +static void __exit exit_yaffs_fs(void) +{ + + struct file_system_to_install *fsinst; + + yaffs_trace(YAFFS_TRACE_ALWAYS, + "yaffs removing."); + + remove_proc_entry("yaffs", YPROC_ROOT); + + fsinst = fs_to_install; + + while (fsinst->fst) { + if (fsinst->installed) { + unregister_filesystem(fsinst->fst); + fsinst->installed = 0; + } + fsinst++; + } +} + +module_init(init_yaffs_fs) +module_exit(exit_yaffs_fs) + +MODULE_DESCRIPTION("YAFFS2 - a NAND specific flash file system"); +MODULE_AUTHOR("Charles Manning, Aleph One Ltd., 2002-2011"); +MODULE_LICENSE("GPL"); diff --git a/fs/yaffs2/yaffs_yaffs1.c b/fs/yaffs2/yaffs_yaffs1.c new file mode 100644 index 000000000000..1dd4db937fcc --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs1.c @@ -0,0 +1,423 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_yaffs1.h" +#include "yportenv.h" +#include "yaffs_trace.h" +#include "yaffs_bitmap.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_nand.h" +#include "yaffs_attribs.h" + +int yaffs1_scan(struct yaffs_dev *dev) +{ + struct yaffs_ext_tags tags; + u32 blk; + int result; + int chunk; + u32 c; + int deleted; + enum yaffs_block_state state; + LIST_HEAD(hard_list); + struct yaffs_block_info *bi; + u32 seq_number; + struct yaffs_obj_hdr *oh; + struct yaffs_obj *in; + struct yaffs_obj *parent; + int alloc_failed = 0; + struct yaffs_shadow_fixer *shadow_fixers = NULL; + u8 *chunk_data; + + yaffs_trace(YAFFS_TRACE_SCAN, + "yaffs1_scan starts intstartblk %d intendblk %d...", + dev->internal_start_block, dev->internal_end_block); + + chunk_data = yaffs_get_temp_buffer(dev); + + dev->seq_number = YAFFS_LOWEST_SEQUENCE_NUMBER; + + /* Scan all the blocks to determine their state */ + bi = dev->block_info; + for (blk = dev->internal_start_block; blk <= dev->internal_end_block; + blk++) { + yaffs_clear_chunk_bits(dev, blk); + bi->pages_in_use = 0; + bi->soft_del_pages = 0; + + yaffs_query_init_block_state(dev, blk, &state, &seq_number); + + bi->block_state = state; + bi->seq_number = seq_number; + + if (bi->seq_number == YAFFS_SEQUENCE_BAD_BLOCK) + bi->block_state = state = YAFFS_BLOCK_STATE_DEAD; + + yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, + "Block scanning block %d state %d seq %d", + blk, state, seq_number); + + if (state == YAFFS_BLOCK_STATE_DEAD) { + yaffs_trace(YAFFS_TRACE_BAD_BLOCKS, + "block %d is bad", blk); + } else if (state == YAFFS_BLOCK_STATE_EMPTY) { + yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "Block empty "); + dev->n_erased_blocks++; + dev->n_free_chunks += dev->param.chunks_per_block; + } + bi++; + } + + /* For each block.... */ + for (blk = dev->internal_start_block; + !alloc_failed && blk <= dev->internal_end_block; blk++) { + + cond_resched(); + + bi = yaffs_get_block_info(dev, blk); + state = bi->block_state; + + deleted = 0; + + /* For each chunk in each block that needs scanning.... */ + for (c = 0; + !alloc_failed && c < dev->param.chunks_per_block && + state == YAFFS_BLOCK_STATE_NEEDS_SCAN; c++) { + /* Read the tags and decide what to do */ + chunk = blk * dev->param.chunks_per_block + c; + + result = yaffs_rd_chunk_tags_nand(dev, chunk, NULL, + &tags); + + if (result != YAFFS_OK) + continue; + /* Let's have a good look at this chunk... */ + + if (tags.ecc_result == YAFFS_ECC_RESULT_UNFIXED || + tags.is_deleted) { + /* YAFFS1 only... + * A deleted chunk + */ + deleted++; + dev->n_free_chunks++; + } else if (!tags.chunk_used) { + /* An unassigned chunk in the block + * This means that either the block is empty or + * this is the one being allocated from + */ + + if (c == 0) { + /* We're looking at the first chunk in + *the block so the block is unused */ + state = YAFFS_BLOCK_STATE_EMPTY; + dev->n_erased_blocks++; + } else { + /* this is the block being allocated */ + yaffs_trace(YAFFS_TRACE_SCAN, + " Allocating from %d %d", + blk, c); + state = YAFFS_BLOCK_STATE_ALLOCATING; + dev->alloc_block = blk; + dev->alloc_page = c; + dev->alloc_block_finder = blk; + + } + + dev->n_free_chunks += + (dev->param.chunks_per_block - c); + } else if (tags.chunk_id > 0) { + /* chunk_id > 0 so it is a data chunk... */ + unsigned int endpos; + + yaffs_set_chunk_bit(dev, blk, c); + bi->pages_in_use++; + + in = yaffs_find_or_create_by_number(dev, + tags.obj_id, + YAFFS_OBJECT_TYPE_FILE); + /* PutChunkIntoFile checks for a clash + * (two data chunks with the same chunk_id). + */ + + if (!in) + alloc_failed = 1; + + if (in) { + if (!yaffs_put_chunk_in_file + (in, tags.chunk_id, chunk, 1)) + alloc_failed = 1; + } + + endpos = + (tags.chunk_id - 1) * + dev->data_bytes_per_chunk + + tags.n_bytes; + if (in && + in->variant_type == + YAFFS_OBJECT_TYPE_FILE && + in->variant.file_variant.stored_size < + endpos) { + in->variant.file_variant.stored_size = + endpos; + if (!dev->param.use_header_file_size) { + in->variant. + file_variant.file_size = + in->variant. + file_variant.stored_size; + } + + } + } else { + /* chunk_id == 0, so it is an ObjectHeader. + * Make the object + */ + yaffs_set_chunk_bit(dev, blk, c); + bi->pages_in_use++; + + result = yaffs_rd_chunk_tags_nand(dev, chunk, + chunk_data, + NULL); + + oh = (struct yaffs_obj_hdr *)chunk_data; + + in = yaffs_find_by_number(dev, tags.obj_id); + if (in && in->variant_type != oh->type) { + /* This should not happen, but somehow + * Wev'e ended up with an obj_id that + * has been reused but not yet deleted, + * and worse still it has changed type. + * Delete the old object. + */ + + yaffs_del_obj(in); + in = NULL; + } + + in = yaffs_find_or_create_by_number(dev, + tags.obj_id, + oh->type); + + if (!in) + alloc_failed = 1; + + if (in && oh->shadows_obj > 0) { + + struct yaffs_shadow_fixer *fixer; + fixer = + kmalloc(sizeof + (struct yaffs_shadow_fixer), + GFP_NOFS); + if (fixer) { + fixer->next = shadow_fixers; + shadow_fixers = fixer; + fixer->obj_id = tags.obj_id; + fixer->shadowed_id = + oh->shadows_obj; + yaffs_trace(YAFFS_TRACE_SCAN, + " Shadow fixer: %d shadows %d", + fixer->obj_id, + fixer->shadowed_id); + + } + + } + + if (in && in->valid) { + /* We have already filled this one. + * We have a duplicate and need to + * resolve it. */ + + unsigned existing_serial = in->serial; + unsigned new_serial = + tags.serial_number; + + if (((existing_serial + 1) & 3) == + new_serial) { + /* Use new one - destroy the + * exisiting one */ + yaffs_chunk_del(dev, + in->hdr_chunk, + 1, __LINE__); + in->valid = 0; + } else { + /* Use existing - destroy + * this one. */ + yaffs_chunk_del(dev, chunk, 1, + __LINE__); + } + } + + if (in && !in->valid && + (tags.obj_id == YAFFS_OBJECTID_ROOT || + tags.obj_id == + YAFFS_OBJECTID_LOSTNFOUND)) { + /* We only load some info, don't fiddle + * with directory structure */ + in->valid = 1; + in->variant_type = oh->type; + + in->yst_mode = oh->yst_mode; + yaffs_load_attribs(in, oh); + in->hdr_chunk = chunk; + in->serial = tags.serial_number; + + } else if (in && !in->valid) { + /* we need to load this info */ + + in->valid = 1; + in->variant_type = oh->type; + + in->yst_mode = oh->yst_mode; + yaffs_load_attribs(in, oh); + in->hdr_chunk = chunk; + in->serial = tags.serial_number; + + yaffs_set_obj_name_from_oh(in, oh); + in->dirty = 0; + + /* directory stuff... + * hook up to parent + */ + + parent = + yaffs_find_or_create_by_number + (dev, oh->parent_obj_id, + YAFFS_OBJECT_TYPE_DIRECTORY); + if (!parent) + alloc_failed = 1; + if (parent && parent->variant_type == + YAFFS_OBJECT_TYPE_UNKNOWN) { + /* Set up as a directory */ + parent->variant_type = + YAFFS_OBJECT_TYPE_DIRECTORY; + INIT_LIST_HEAD(&parent-> + variant.dir_variant. + children); + } else if (!parent || + parent->variant_type != + YAFFS_OBJECT_TYPE_DIRECTORY) { + /* Hoosterman, a problem.... + * We're trying to use a + * non-directory as a directory + */ + + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: attempting to use non-directory as a directory in scan. Put in lost+found." + ); + parent = dev->lost_n_found; + } + + yaffs_add_obj_to_dir(parent, in); + + switch (in->variant_type) { + case YAFFS_OBJECT_TYPE_UNKNOWN: + /* Todo got a problem */ + break; + case YAFFS_OBJECT_TYPE_FILE: + if (dev->param. + use_header_file_size) + in->variant. + file_variant.file_size + = yaffs_oh_to_size(dev, oh, 0); + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + in->variant. + hardlink_variant.equiv_id = + oh->equiv_id; + list_add(&in->hard_links, + &hard_list); + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + in->variant.symlink_variant. + alias = + yaffs_clone_str(oh->alias); + if (!in->variant. + symlink_variant.alias) + alloc_failed = 1; + break; + } + } + } + } + + if (state == YAFFS_BLOCK_STATE_NEEDS_SCAN) { + /* If we got this far while scanning, + * then the block is fully allocated. */ + state = YAFFS_BLOCK_STATE_FULL; + } + + if (state == YAFFS_BLOCK_STATE_ALLOCATING) { + /* If the block was partially allocated then + * treat it as fully allocated. */ + state = YAFFS_BLOCK_STATE_FULL; + dev->alloc_block = -1; + } + + bi->block_state = state; + + /* Now let's see if it was dirty */ + if (bi->pages_in_use == 0 && + !bi->has_shrink_hdr && + bi->block_state == YAFFS_BLOCK_STATE_FULL) + yaffs_block_became_dirty(dev, blk); + } + + /* Ok, we've done all the scanning. + * Fix up the hard link chains. + * We should now have scanned all the objects, now it's time to add + * these hardlinks. + */ + + yaffs_link_fixup(dev, &hard_list); + + /* + * Fix up any shadowed objects. + * There should not be more than one of these. + */ + { + struct yaffs_shadow_fixer *fixer; + struct yaffs_obj *obj; + + while (shadow_fixers) { + fixer = shadow_fixers; + shadow_fixers = fixer->next; + /* Complete the rename transaction by deleting the + * shadowed object then setting the object header + to unshadowed. + */ + obj = yaffs_find_by_number(dev, fixer->shadowed_id); + if (obj) + yaffs_del_obj(obj); + + obj = yaffs_find_by_number(dev, fixer->obj_id); + + if (obj) + yaffs_update_oh(obj, NULL, 1, 0, 0, NULL); + + kfree(fixer); + } + } + + yaffs_release_temp_buffer(dev, chunk_data); + + if (alloc_failed) + return YAFFS_FAIL; + + yaffs_trace(YAFFS_TRACE_SCAN, "yaffs1_scan ends"); + + return YAFFS_OK; +} diff --git a/fs/yaffs2/yaffs_yaffs1.h b/fs/yaffs2/yaffs_yaffs1.h new file mode 100644 index 000000000000..051e41c23e1d --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs1.h @@ -0,0 +1,21 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_YAFFS1_H__ +#define __YAFFS_YAFFS1_H__ + +#include "yaffs_guts.h" +int yaffs1_scan(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yaffs_yaffs2.c b/fs/yaffs2/yaffs_yaffs2.c new file mode 100644 index 000000000000..9eb42f7ff54d --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs2.c @@ -0,0 +1,1711 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include "yaffs_guts.h" +#include "yaffs_trace.h" +#include "yaffs_yaffs2.h" +#include "yaffs_checkptrw.h" +#include "yaffs_bitmap.h" +#include "yaffs_nand.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_verify.h" +#include "yaffs_attribs.h" +#include "yaffs_summary.h" +#include "yaffs_endian.h" + +/* + * Checkpoints are really no benefit on very small partitions. + * + * To save space on small partitions don't bother with checkpoints unless + * the partition is at least this big. + */ +#define YAFFS_CHECKPOINT_MIN_BLOCKS 60 +#define YAFFS_SMALL_HOLE_THRESHOLD 4 + +/* + * Oldest Dirty Sequence Number handling. + */ + +/* yaffs_calc_oldest_dirty_seq() + * yaffs2_find_oldest_dirty_seq() + * Calculate the oldest dirty sequence number if we don't know it. + */ +void yaffs_calc_oldest_dirty_seq(struct yaffs_dev *dev) +{ + u32 i; + unsigned seq; + unsigned block_no = 0; + struct yaffs_block_info *b; + + if (!dev->param.is_yaffs2) + return; + + /* Find the oldest dirty sequence number. */ + seq = dev->seq_number + 1; + b = dev->block_info; + for (i = dev->internal_start_block; i <= dev->internal_end_block; i++) { + if (b->block_state == YAFFS_BLOCK_STATE_FULL && + (u32)(b->pages_in_use - b->soft_del_pages) < + dev->param.chunks_per_block && + b->seq_number < seq) { + seq = b->seq_number; + block_no = i; + } + b++; + } + + if (block_no) { + dev->oldest_dirty_seq = seq; + dev->oldest_dirty_block = block_no; + } +} + +void yaffs2_find_oldest_dirty_seq(struct yaffs_dev *dev) +{ + if (!dev->param.is_yaffs2) + return; + + if (!dev->oldest_dirty_seq) + yaffs_calc_oldest_dirty_seq(dev); +} + +/* + * yaffs_clear_oldest_dirty_seq() + * Called when a block is erased or marked bad. (ie. when its seq_number + * becomes invalid). If the value matches the oldest then we clear + * dev->oldest_dirty_seq to force its recomputation. + */ +void yaffs2_clear_oldest_dirty_seq(struct yaffs_dev *dev, + struct yaffs_block_info *bi) +{ + + if (!dev->param.is_yaffs2) + return; + + if (!bi || bi->seq_number == dev->oldest_dirty_seq) { + dev->oldest_dirty_seq = 0; + dev->oldest_dirty_block = 0; + } +} + +/* + * yaffs2_update_oldest_dirty_seq() + * Update the oldest dirty sequence number whenever we dirty a block. + * Only do this if the oldest_dirty_seq is actually being tracked. + */ +void yaffs2_update_oldest_dirty_seq(struct yaffs_dev *dev, unsigned block_no, + struct yaffs_block_info *bi) +{ + if (!dev->param.is_yaffs2) + return; + + if (dev->oldest_dirty_seq) { + if (dev->oldest_dirty_seq > bi->seq_number) { + dev->oldest_dirty_seq = bi->seq_number; + dev->oldest_dirty_block = block_no; + } + } +} + +int yaffs_block_ok_for_gc(struct yaffs_dev *dev, struct yaffs_block_info *bi) +{ + + if (!dev->param.is_yaffs2) + return 1; /* disqualification only applies to yaffs2. */ + + if (!bi->has_shrink_hdr) + return 1; /* can gc */ + + yaffs2_find_oldest_dirty_seq(dev); + + /* Can't do gc of this block if there are any blocks older than this + * one that have discarded pages. + */ + return (bi->seq_number <= dev->oldest_dirty_seq); +} + +/* + * yaffs2_find_refresh_block() + * periodically finds the oldest full block by sequence number for refreshing. + * Only for yaffs2. + */ +u32 yaffs2_find_refresh_block(struct yaffs_dev *dev) +{ + u32 b; + u32 oldest = 0; + u32 oldest_seq = 0; + struct yaffs_block_info *bi; + + if (!dev->param.is_yaffs2) + return oldest; + + /* + * If refresh period < 10 then refreshing is disabled. + */ + if (dev->param.refresh_period < 10) + return oldest; + + /* + * Fix broken values. + */ + if (dev->refresh_skip > dev->param.refresh_period) + dev->refresh_skip = dev->param.refresh_period; + + if (dev->refresh_skip > 0) + return oldest; + + /* + * Refresh skip is now zero. + * We'll do a refresh this time around.... + * Update the refresh skip and find the oldest block. + */ + dev->refresh_skip = dev->param.refresh_period; + dev->refresh_count++; + bi = dev->block_info; + for (b = dev->internal_start_block; b <= dev->internal_end_block; b++) { + + if (bi->block_state == YAFFS_BLOCK_STATE_FULL) { + + if (oldest < 1 || bi->seq_number < oldest_seq) { + oldest = b; + oldest_seq = bi->seq_number; + } + } + bi++; + } + + if (oldest > 0) { + yaffs_trace(YAFFS_TRACE_GC, + "GC refresh count %d selected block %d with seq_number %d", + dev->refresh_count, oldest, oldest_seq); + } + + return oldest; +} + +int yaffs2_checkpt_required(struct yaffs_dev *dev) +{ + int nblocks; + + if (!dev->param.is_yaffs2) + return 0; + + nblocks = dev->internal_end_block - dev->internal_start_block + 1; + + return !dev->param.skip_checkpt_wr && + !dev->read_only && (nblocks >= YAFFS_CHECKPOINT_MIN_BLOCKS); +} + +int yaffs_calc_checkpt_blocks_required(struct yaffs_dev *dev) +{ + int retval; + int n_bytes = 0; + int n_blocks; + int dev_blocks; + + if (!dev->param.is_yaffs2) + return 0; + + if (!dev->checkpoint_blocks_required && yaffs2_checkpt_required(dev)) { + /* Not a valid value so recalculate */ + dev_blocks = dev->param.end_block - dev->param.start_block + 1; + n_bytes += sizeof(struct yaffs_checkpt_validity); + n_bytes += sizeof(struct yaffs_checkpt_dev); + n_bytes += dev_blocks * sizeof(struct yaffs_block_info); + n_bytes += dev_blocks * dev->chunk_bit_stride; + n_bytes += + (sizeof(struct yaffs_checkpt_obj) + sizeof(u32)) * + dev->n_obj; + n_bytes += (dev->tnode_size + sizeof(u32)) * dev->n_tnodes; + n_bytes += sizeof(struct yaffs_checkpt_validity); + n_bytes += sizeof(u32); /* checksum */ + + /* Round up and add 2 blocks to allow for some bad blocks, + * so add 3 */ + + n_blocks = + (n_bytes / + (dev->data_bytes_per_chunk * + dev->param.chunks_per_block)) + 3; + + dev->checkpoint_blocks_required = n_blocks; + } + + retval = dev->checkpoint_blocks_required - dev->blocks_in_checkpt; + if (retval < 0) + retval = 0; + return retval; +} + +/*--------------------- Checkpointing --------------------*/ + +static void yaffs2_do_endian_validity_marker(struct yaffs_dev *dev, + struct yaffs_checkpt_validity *v) +{ + + if (!dev->swap_endian) + return; + v->struct_type = swap_s32(v->struct_type); + v->magic = swap_u32(v->magic); + v->version = swap_u32(v->version); + v->head = swap_u32(v->head); +} + +static int yaffs2_wr_checkpt_validity_marker(struct yaffs_dev *dev, int head) +{ + struct yaffs_checkpt_validity cp; + + memset(&cp, 0, sizeof(cp)); + + cp.struct_type = sizeof(cp); + cp.magic = YAFFS_MAGIC; + cp.version = YAFFS_CHECKPOINT_VERSION; + cp.head = (head) ? 1 : 0; + + yaffs2_do_endian_validity_marker(dev, &cp); + + return (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp)) ? 1 : 0; +} + +static int yaffs2_rd_checkpt_validity_marker(struct yaffs_dev *dev, int head) +{ + struct yaffs_checkpt_validity cp; + int ok; + + ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp)); + yaffs2_do_endian_validity_marker(dev, &cp); + + if (ok) + ok = (cp.struct_type == sizeof(cp)) && + (cp.magic == YAFFS_MAGIC) && + (cp.version == YAFFS_CHECKPOINT_VERSION) && + (cp.head == ((head) ? 1 : 0)); + return ok ? 1 : 0; +} + +static void yaffs2_dev_to_checkpt_dev(struct yaffs_checkpt_dev *cp, + struct yaffs_dev *dev) +{ + cp->struct_type = sizeof(*cp); + + cp->n_erased_blocks = dev->n_erased_blocks; + cp->alloc_block = dev->alloc_block; + cp->alloc_page = dev->alloc_page; + cp->n_free_chunks = dev->n_free_chunks; + + cp->n_deleted_files = dev->n_deleted_files; + cp->n_unlinked_files = dev->n_unlinked_files; + cp->n_bg_deletions = dev->n_bg_deletions; + cp->seq_number = dev->seq_number; + +} + +static void yaffs_checkpt_dev_to_dev(struct yaffs_dev *dev, + struct yaffs_checkpt_dev *cp) +{ + dev->n_erased_blocks = cp->n_erased_blocks; + dev->alloc_block = cp->alloc_block; + dev->alloc_page = cp->alloc_page; + dev->n_free_chunks = cp->n_free_chunks; + + dev->n_deleted_files = cp->n_deleted_files; + dev->n_unlinked_files = cp->n_unlinked_files; + dev->n_bg_deletions = cp->n_bg_deletions; + dev->seq_number = cp->seq_number; +} + +static void yaffs2_do_endian_checkpt_dev(struct yaffs_dev *dev, + struct yaffs_checkpt_dev *cp) +{ + if (!dev->swap_endian) + return; + cp->struct_type = swap_s32(cp->struct_type); + cp->n_erased_blocks = swap_s32(cp->n_erased_blocks); + cp->alloc_block = swap_s32(cp->alloc_block); + cp->alloc_page = swap_u32(cp->alloc_page); + cp->n_free_chunks = swap_s32(cp->n_free_chunks); + cp->n_deleted_files = swap_s32(cp->n_deleted_files); + cp->n_unlinked_files = swap_s32(cp->n_unlinked_files); + cp->n_bg_deletions = swap_s32(cp->n_bg_deletions); +} + +static int yaffs2_wr_checkpt_dev(struct yaffs_dev *dev) +{ + struct yaffs_checkpt_dev cp; + u32 n_bytes; + u32 n_blocks = dev->internal_end_block - dev->internal_start_block + 1; + int ok; + u32 i; + union yaffs_block_info_union bu; + + /* Write device runtime values */ + yaffs2_dev_to_checkpt_dev(&cp, dev); + yaffs2_do_endian_checkpt_dev(dev, &cp); + + ok = (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp)); + if (!ok) + return 0; + + /* Write block info. */ + if (!dev->swap_endian) { + n_bytes = n_blocks * sizeof(struct yaffs_block_info); + ok = (yaffs2_checkpt_wr(dev, dev->block_info, n_bytes) == + (int)n_bytes); + } else { + /* + * Need to swap the endianisms. We can't do this in place + * since that would damage live data, + * so write one block info at a time using a copy. + */ + for (i = 0; i < n_blocks && ok; i++) { + bu.bi = dev->block_info[i]; + bu.as_u32[0] = swap_u32(bu.as_u32[0]); + bu.as_u32[1] = swap_u32(bu.as_u32[1]); + ok = (yaffs2_checkpt_wr(dev, &bu, sizeof(bu)) == sizeof(bu)); + } + } + + if (!ok) + return 0; + + /* + * Write chunk bits. Chunk bits are in bytes so + * no endian conversion is needed. + */ + n_bytes = n_blocks * dev->chunk_bit_stride; + ok = (yaffs2_checkpt_wr(dev, dev->chunk_bits, n_bytes) == + (int)n_bytes); + + return ok ? 1 : 0; +} + +static int yaffs2_rd_checkpt_dev(struct yaffs_dev *dev) +{ + struct yaffs_checkpt_dev cp; + u32 n_bytes; + u32 n_blocks = + (dev->internal_end_block - dev->internal_start_block + 1); + int ok; + + ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp)); + if (!ok) + return 0; + yaffs2_do_endian_checkpt_dev(dev, &cp); + + if (cp.struct_type != sizeof(cp)) + return 0; + + yaffs_checkpt_dev_to_dev(dev, &cp); + + n_bytes = n_blocks * sizeof(struct yaffs_block_info); + + ok = (yaffs2_checkpt_rd(dev, dev->block_info, n_bytes) == + (int)n_bytes); + + if (!ok) + return 0; + + if (dev->swap_endian) { + /* The block info can just be handled as a list of u32s. */ + u32 *as_u32 = (u32 *) dev->block_info; + u32 n_u32s = n_bytes/sizeof(u32); + u32 i; + + for (i=0; i < n_u32s; i++) + as_u32[i] = swap_u32(as_u32[i]); + } + + n_bytes = n_blocks * dev->chunk_bit_stride; + + ok = (yaffs2_checkpt_rd(dev, dev->chunk_bits, n_bytes) == + (int)n_bytes); + + + return ok ? 1 : 0; +} + + +static void yaffs2_checkpt_obj_bit_assign(struct yaffs_checkpt_obj *cp, + int bit_offset, + int bit_width, + u32 value) +{ + u32 and_mask; + + and_mask = ((1<<bit_width)-1) << bit_offset; + + cp->bit_field &= ~and_mask; + cp->bit_field |= ((value << bit_offset) & and_mask); +} + +static u32 yaffs2_checkpt_obj_bit_get(struct yaffs_checkpt_obj *cp, + int bit_offset, + int bit_width) +{ + u32 and_mask; + + and_mask = ((1<<bit_width)-1); + + return (cp->bit_field >> bit_offset) & and_mask; +} + +static void yaffs2_obj_checkpt_obj(struct yaffs_checkpt_obj *cp, + struct yaffs_obj *obj) +{ + cp->obj_id = obj->obj_id; + cp->parent_id = (obj->parent) ? obj->parent->obj_id : 0; + cp->hdr_chunk = obj->hdr_chunk; + + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_VARIANT_BITS, obj->variant_type); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_DELETED_BITS, obj->deleted); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_SOFT_DEL_BITS, obj->soft_del); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_UNLINKED_BITS, obj->unlinked); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_FAKE_BITS, obj->fake); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_RENAME_ALLOWED_BITS, obj->rename_allowed); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_UNLINK_ALLOWED_BITS, obj->unlink_allowed); + yaffs2_checkpt_obj_bit_assign(cp, CHECKPOINT_SERIAL_BITS, obj->serial); + + cp->n_data_chunks = obj->n_data_chunks; + + if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE) + cp->size_or_equiv_obj = obj->variant.file_variant.file_size; + else if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) + cp->size_or_equiv_obj = obj->variant.hardlink_variant.equiv_id; +} + +static int yaffs2_checkpt_obj_to_obj(struct yaffs_obj *obj, + struct yaffs_checkpt_obj *cp) +{ + struct yaffs_obj *parent; + u32 cp_variant_type = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_VARIANT_BITS); + + if (obj->variant_type != cp_variant_type) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Checkpoint read object %d type %d chunk %d does not match existing object type %d", + cp->obj_id, cp_variant_type, cp->hdr_chunk, + obj->variant_type); + return 0; + } + + obj->obj_id = cp->obj_id; + + if (cp->parent_id) + parent = yaffs_find_or_create_by_number(obj->my_dev, + cp->parent_id, + YAFFS_OBJECT_TYPE_DIRECTORY); + else + parent = NULL; + + if (parent) { + if (parent->variant_type != YAFFS_OBJECT_TYPE_DIRECTORY) { + yaffs_trace(YAFFS_TRACE_ALWAYS, + "Checkpoint read object %d parent %d type %d chunk %d Parent type, %d, not directory", + cp->obj_id, cp->parent_id, + cp_variant_type, cp->hdr_chunk, + parent->variant_type); + return 0; + } + yaffs_add_obj_to_dir(parent, obj); + } + + obj->hdr_chunk = cp->hdr_chunk; + + obj->variant_type = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_VARIANT_BITS); + obj->deleted = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_DELETED_BITS); + obj->soft_del = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_SOFT_DEL_BITS); + obj->unlinked = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_UNLINKED_BITS); + obj->fake = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_FAKE_BITS); + obj->rename_allowed = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_RENAME_ALLOWED_BITS); + obj->unlink_allowed = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_UNLINK_ALLOWED_BITS); + obj->serial = yaffs2_checkpt_obj_bit_get(cp, CHECKPOINT_SERIAL_BITS); + + obj->n_data_chunks = cp->n_data_chunks; + + if (obj->variant_type == YAFFS_OBJECT_TYPE_FILE) { + obj->variant.file_variant.file_size = cp->size_or_equiv_obj; + obj->variant.file_variant.stored_size = cp->size_or_equiv_obj; + } else if (obj->variant_type == YAFFS_OBJECT_TYPE_HARDLINK) { + obj->variant.hardlink_variant.equiv_id = cp->size_or_equiv_obj; + } + if (obj->hdr_chunk > 0) + obj->lazy_loaded = 1; + return 1; +} + +static void yaffs2_do_endian_tnode(struct yaffs_dev *dev, struct yaffs_tnode *tn) +{ + int i; + u32 *as_u32 = (u32 *)tn; + int tnode_size_u32 = dev->tnode_size / sizeof(u32); + + if (!dev->swap_endian) + return; + /* Swap all the tnode data as u32s to fix endianisms. */ + for (i = 0; i<tnode_size_u32; i++) + as_u32[i] = swap_u32(as_u32[i]); +} + +struct yaffs_tnode *yaffs2_do_endian_tnode_copy(struct yaffs_dev *dev, + struct yaffs_tnode *tn) +{ + if (!dev->swap_endian) + return tn; + + memcpy(dev->tn_swap_buffer, tn, dev->tnode_size); + tn = dev->tn_swap_buffer; + + yaffs2_do_endian_tnode(dev, tn); + + return tn; +} + +static int yaffs2_checkpt_tnode_worker(struct yaffs_obj *in, + struct yaffs_tnode *tn, u32 level, + int chunk_offset) +{ + int i; + struct yaffs_dev *dev = in->my_dev; + int ok = 1; + u32 base_offset; + + if (!tn) + return 1; + + if (level > 0) { + for (i = 0; i < YAFFS_NTNODES_INTERNAL && ok; i++) { + if (!tn->internal[i]) + continue; + ok = yaffs2_checkpt_tnode_worker(in, + tn->internal[i], + level - 1, + (chunk_offset << + YAFFS_TNODES_INTERNAL_BITS) + i); + } + return ok; + } + + /* Level 0 tnode */ + base_offset = chunk_offset << YAFFS_TNODES_LEVEL0_BITS; + yaffs_do_endian_u32(dev, &base_offset); + + ok = (yaffs2_checkpt_wr(dev, &base_offset, sizeof(base_offset)) == + sizeof(base_offset)); + if (ok) { + /* + * NB Can't do an in-place endian swizzle since that would + * damage current tnode data. + * If a tnode endian conversion is required we do a copy. + */ + tn = yaffs2_do_endian_tnode_copy(dev, tn); + ok = (yaffs2_checkpt_wr(dev, tn, dev->tnode_size) == + (int)dev->tnode_size); + } + return ok; +} + +static int yaffs2_wr_checkpt_tnodes(struct yaffs_obj *obj) +{ + u32 end_marker = ~0; + int ok = 1; + + if (obj->variant_type != YAFFS_OBJECT_TYPE_FILE) + return ok; + + ok = yaffs2_checkpt_tnode_worker(obj, + obj->variant.file_variant.top, + obj->variant.file_variant. + top_level, 0); + if (ok) + ok = (yaffs2_checkpt_wr(obj->my_dev, &end_marker, + sizeof(end_marker)) == sizeof(end_marker)); + + return ok ? 1 : 0; +} + +static int yaffs2_rd_checkpt_tnodes(struct yaffs_obj *obj) +{ + u32 base_chunk; + int ok = 1; + struct yaffs_dev *dev = obj->my_dev; + struct yaffs_file_var *file_stuct_ptr = &obj->variant.file_variant; + struct yaffs_tnode *tn; + int nread = 0; + + ok = (yaffs2_checkpt_rd(dev, &base_chunk, sizeof(base_chunk)) == + sizeof(base_chunk)); + + yaffs_do_endian_u32(dev, &base_chunk); + + while (ok && (~base_chunk)) { + nread++; + /* Read level 0 tnode */ + + tn = yaffs_get_tnode(dev); + if (tn) { + ok = (yaffs2_checkpt_rd(dev, tn, dev->tnode_size) == + (int)dev->tnode_size); + yaffs2_do_endian_tnode(dev, tn); + } + else + ok = 0; + + if (tn && ok) + ok = yaffs_add_find_tnode_0(dev, + file_stuct_ptr, + base_chunk, tn) ? 1 : 0; + + if (ok) { + ok = (yaffs2_checkpt_rd + (dev, &base_chunk, + sizeof(base_chunk)) == sizeof(base_chunk)); + yaffs_do_endian_u32(dev, &base_chunk); + } + + } + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "Checkpoint read tnodes %d records, last %d. ok %d", + nread, base_chunk, ok); + + return ok ? 1 : 0; +} + + +static void yaffs2_do_endian_checkpt_obj(struct yaffs_dev *dev, + struct yaffs_checkpt_obj *cp) +{ + if (!dev->swap_endian) + return; + cp->struct_type = swap_s32(cp->struct_type); + cp->obj_id = swap_u32(cp->obj_id); + cp->parent_id = swap_u32(cp->parent_id); + cp->hdr_chunk = swap_s32(cp->hdr_chunk); + cp->bit_field = swap_u32(cp->bit_field); + cp->n_data_chunks = swap_s32(cp->n_data_chunks); + cp->size_or_equiv_obj = swap_loff_t(cp->size_or_equiv_obj); +} + +static int yaffs2_wr_checkpt_objs(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj; + struct yaffs_checkpt_obj cp; + int i; + int ok = 1; + struct list_head *lh; + u32 cp_variant_type; + + /* Iterate through the objects in each hash entry, + * dumping them to the checkpointing stream. + */ + + for (i = 0; ok && i < YAFFS_NOBJECT_BUCKETS; i++) { + list_for_each(lh, &dev->obj_bucket[i].list) { + obj = list_entry(lh, struct yaffs_obj, hash_link); + if (!obj->defered_free) { + yaffs2_obj_checkpt_obj(&cp, obj); + cp.struct_type = sizeof(cp); + cp_variant_type = yaffs2_checkpt_obj_bit_get( + &cp, CHECKPOINT_VARIANT_BITS); + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "Checkpoint write object %d parent %d type %d chunk %d obj addr %p", + cp.obj_id, cp.parent_id, + cp_variant_type, cp.hdr_chunk, obj); + + yaffs2_do_endian_checkpt_obj (dev, &cp); + ok = (yaffs2_checkpt_wr(dev, &cp, + sizeof(cp)) == sizeof(cp)); + + if (ok && + obj->variant_type == + YAFFS_OBJECT_TYPE_FILE) + ok = yaffs2_wr_checkpt_tnodes(obj); + } + } + } + + /* Dump end of list */ + memset(&cp, 0xff, sizeof(struct yaffs_checkpt_obj)); + cp.struct_type = sizeof(cp); + yaffs2_do_endian_checkpt_obj (dev, &cp); + + if (ok) + ok = (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp)); + + return ok ? 1 : 0; +} + +static int yaffs2_rd_checkpt_objs(struct yaffs_dev *dev) +{ + struct yaffs_obj *obj; + struct yaffs_checkpt_obj cp; + int ok = 1; + int done = 0; + u32 cp_variant_type; + LIST_HEAD(hard_list); + + + while (ok && !done) { + ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(cp)); + yaffs2_do_endian_checkpt_obj (dev, &cp); + + if (cp.struct_type != sizeof(cp)) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "struct size %d instead of %d ok %d", + cp.struct_type, (int)sizeof(cp), ok); + ok = 0; + } + + cp_variant_type = yaffs2_checkpt_obj_bit_get( + &cp, CHECKPOINT_VARIANT_BITS); + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "Checkpoint read object %d parent %d type %d chunk %d ", + cp.obj_id, cp.parent_id, cp_variant_type, + cp.hdr_chunk); + + if (ok && cp.obj_id == (u32)(~0)) { + done = 1; + } else if (ok) { + obj = + yaffs_find_or_create_by_number(dev, cp.obj_id, + cp_variant_type); + if (obj) { + ok = yaffs2_checkpt_obj_to_obj(obj, &cp); + if (!ok) + break; + if (obj->variant_type == + YAFFS_OBJECT_TYPE_FILE) { + ok = yaffs2_rd_checkpt_tnodes(obj); + } else if (obj->variant_type == + YAFFS_OBJECT_TYPE_HARDLINK) { + list_add(&obj->hard_links, &hard_list); + } + } else { + ok = 0; + } + } + } + + if (ok) + yaffs_link_fixup(dev, &hard_list); + + return ok ? 1 : 0; +} + +static int yaffs2_wr_checkpt_sum(struct yaffs_dev *dev) +{ + u32 checkpt_sum; + int ok; + + yaffs2_get_checkpt_sum(dev, &checkpt_sum); + + yaffs_do_endian_u32(dev, &checkpt_sum); + + ok = (yaffs2_checkpt_wr(dev, &checkpt_sum, sizeof(checkpt_sum)) == + sizeof(checkpt_sum)); + + if (!ok) + return 0; + + return 1; +} + +static int yaffs2_rd_checkpt_sum(struct yaffs_dev *dev) +{ + u32 checkpt_sum0; + u32 checkpt_sum1; + int ok; + + yaffs2_get_checkpt_sum(dev, &checkpt_sum0); + + ok = (yaffs2_checkpt_rd(dev, &checkpt_sum1, sizeof(checkpt_sum1)) == + sizeof(checkpt_sum1)); + + if (!ok) + return 0; + yaffs_do_endian_u32(dev, &checkpt_sum1); + + if (checkpt_sum0 != checkpt_sum1) + return 0; + + return 1; +} + +static int yaffs2_wr_checkpt_data(struct yaffs_dev *dev) +{ + int ok = 1; + + if (!yaffs2_checkpt_required(dev)) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "skipping checkpoint write"); + ok = 0; + } + + if (ok) + ok = yaffs2_checkpt_open(dev, 1); + + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "write checkpoint validity"); + ok = yaffs2_wr_checkpt_validity_marker(dev, 1); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "write checkpoint device"); + ok = yaffs2_wr_checkpt_dev(dev); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "write checkpoint objects"); + ok = yaffs2_wr_checkpt_objs(dev); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "write checkpoint validity"); + ok = yaffs2_wr_checkpt_validity_marker(dev, 0); + } + + if (ok) + ok = yaffs2_wr_checkpt_sum(dev); + + if (!yaffs_checkpt_close(dev)) + ok = 0; + + if (ok) + dev->is_checkpointed = 1; + else + dev->is_checkpointed = 0; + + return dev->is_checkpointed; +} + +static int yaffs2_rd_checkpt_data(struct yaffs_dev *dev) +{ + int ok = 1; + + if (!dev->param.is_yaffs2) + ok = 0; + + if (ok && dev->param.skip_checkpt_rd) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "skipping checkpoint read"); + ok = 0; + } + + if (ok) + ok = yaffs2_checkpt_open(dev, 0); /* open for read */ + + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "read checkpoint validity"); + ok = yaffs2_rd_checkpt_validity_marker(dev, 1); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "read checkpoint device"); + ok = yaffs2_rd_checkpt_dev(dev); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "read checkpoint objects"); + ok = yaffs2_rd_checkpt_objs(dev); + } + if (ok) { + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "read checkpoint validity"); + ok = yaffs2_rd_checkpt_validity_marker(dev, 0); + } + + if (ok) { + ok = yaffs2_rd_checkpt_sum(dev); + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "read checkpoint checksum %d", ok); + } + + if (!yaffs_checkpt_close(dev)) + ok = 0; + + if (ok) + dev->is_checkpointed = 1; + else + dev->is_checkpointed = 0; + + return ok ? 1 : 0; +} + +void yaffs2_checkpt_invalidate(struct yaffs_dev *dev) +{ + if (dev->is_checkpointed || dev->blocks_in_checkpt > 0) { + dev->is_checkpointed = 0; + yaffs2_checkpt_invalidate_stream(dev); + } + if (dev->param.sb_dirty_fn) + dev->param.sb_dirty_fn(dev); +} + +int yaffs_checkpoint_save(struct yaffs_dev *dev) +{ + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "save entry: is_checkpointed %d", + dev->is_checkpointed); + + yaffs_verify_objects(dev); + yaffs_verify_blocks(dev); + yaffs_verify_free_chunks(dev); + + if (!dev->is_checkpointed) { + yaffs2_checkpt_invalidate(dev); + yaffs2_wr_checkpt_data(dev); + } + + yaffs_trace(YAFFS_TRACE_CHECKPOINT | YAFFS_TRACE_MOUNT, + "save exit: is_checkpointed %d", + dev->is_checkpointed); + + return dev->is_checkpointed; +} + +int yaffs2_checkpt_restore(struct yaffs_dev *dev) +{ + int retval; + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "restore entry: is_checkpointed %d", + dev->is_checkpointed); + + retval = yaffs2_rd_checkpt_data(dev); + + if (dev->is_checkpointed) { + yaffs_verify_objects(dev); + yaffs_verify_blocks(dev); + yaffs_verify_free_chunks(dev); + } + + yaffs_trace(YAFFS_TRACE_CHECKPOINT, + "restore exit: is_checkpointed %d", + dev->is_checkpointed); + + return retval; +} + +/* End of checkpointing */ + +/* Hole handling logic for truncate past end of file */ + +int yaffs2_handle_hole(struct yaffs_obj *obj, loff_t new_size) +{ + /* if new_size > old_file_size. + * We're going to be writing a hole. + * If the hole is small then write zeros otherwise write a start + * of hole marker. + */ + loff_t old_file_size; + loff_t increase; + int small_hole; + int result = YAFFS_OK; + struct yaffs_dev *dev = NULL; + u8 *local_buffer = NULL; + int small_increase_ok = 0; + + if (!obj) + return YAFFS_FAIL; + + if (obj->variant_type != YAFFS_OBJECT_TYPE_FILE) + return YAFFS_FAIL; + + dev = obj->my_dev; + + /* Bail out if not yaffs2 mode */ + if (!dev->param.is_yaffs2) + return YAFFS_OK; + + old_file_size = obj->variant.file_variant.file_size; + + if (new_size <= old_file_size) + return YAFFS_OK; + + increase = new_size - old_file_size; + + if (increase < YAFFS_SMALL_HOLE_THRESHOLD * dev->data_bytes_per_chunk && + yaffs_check_alloc_available(dev, YAFFS_SMALL_HOLE_THRESHOLD + 1)) + small_hole = 1; + else + small_hole = 0; + + if (small_hole) + local_buffer = yaffs_get_temp_buffer(dev); + + if (local_buffer) { + /* fill hole with zero bytes */ + loff_t pos = old_file_size; + int this_write; + int written; + memset(local_buffer, 0, dev->data_bytes_per_chunk); + small_increase_ok = 1; + + while (increase > 0 && small_increase_ok) { + this_write = increase; + if (this_write > (int)dev->data_bytes_per_chunk) + this_write = dev->data_bytes_per_chunk; + written = + yaffs_do_file_wr(obj, local_buffer, pos, this_write, + 0); + if (written == this_write) { + pos += this_write; + increase -= this_write; + } else { + small_increase_ok = 0; + } + } + + yaffs_release_temp_buffer(dev, local_buffer); + + /* If out of space then reverse any chunks we've added */ + if (!small_increase_ok) + yaffs_resize_file_down(obj, old_file_size); + } + + if (!small_increase_ok && + obj->parent && + obj->parent->obj_id != YAFFS_OBJECTID_UNLINKED && + obj->parent->obj_id != YAFFS_OBJECTID_DELETED) { + /* Write a hole start header with the old file size */ + yaffs_update_oh(obj, NULL, 0, 1, 0, NULL); + } + + return result; +} + +/* Yaffs2 scanning */ + +struct yaffs_block_index { + int seq; + int block; +}; + +static int yaffs2_ybicmp(const void *a, const void *b) +{ + int aseq = ((struct yaffs_block_index *)a)->seq; + int bseq = ((struct yaffs_block_index *)b)->seq; + int ablock = ((struct yaffs_block_index *)a)->block; + int bblock = ((struct yaffs_block_index *)b)->block; + + if (aseq == bseq) + return ablock - bblock; + + return aseq - bseq; +} + +static inline int yaffs2_scan_chunk(struct yaffs_dev *dev, + struct yaffs_block_info *bi, + int blk, int chunk_in_block, + int *found_chunks, + u8 *chunk_data, + struct list_head *hard_list, + int summary_available) +{ + struct yaffs_obj_hdr *oh; + struct yaffs_obj *in; + struct yaffs_obj *parent; + int equiv_id; + loff_t file_size; + int is_shrink; + int is_unlinked; + struct yaffs_ext_tags tags; + int result; + int alloc_failed = 0; + int chunk = blk * dev->param.chunks_per_block + chunk_in_block; + struct yaffs_file_var *file_var; + struct yaffs_hardlink_var *hl_var; + struct yaffs_symlink_var *sl_var; + + if (summary_available) { + result = yaffs_summary_fetch(dev, &tags, chunk_in_block); + tags.seq_number = bi->seq_number; + } + + if (!summary_available || tags.obj_id == 0) { + result = yaffs_rd_chunk_tags_nand(dev, chunk, NULL, &tags); + dev->tags_used++; + } else { + dev->summary_used++; + } + + if (result == YAFFS_FAIL) + yaffs_trace(YAFFS_TRACE_SCAN, + "Could not get tags for chunk %d\n", chunk); + /* Let's have a good look at this chunk... */ + + if (!tags.chunk_used) { + /* An unassigned chunk in the block. + * If there are used chunks after this one, then + * it is a chunk that was skipped due to failing + * the erased check. Just skip it so that it can + * be deleted. + * But, more typically, We get here when this is + * an unallocated chunk and his means that + * either the block is empty or this is the one + * being allocated from + */ + + if (*found_chunks) { + /* This is a chunk that was skipped due + * to failing the erased check */ + } else if (chunk_in_block == 0) { + /* We're looking at the first chunk in + * the block so the block is unused */ + bi->block_state = YAFFS_BLOCK_STATE_EMPTY; + dev->n_erased_blocks++; + } else { + if (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN || + bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING) { + if (dev->seq_number == bi->seq_number) { + /* Allocating from this block*/ + yaffs_trace(YAFFS_TRACE_SCAN, + " Allocating from %d %d", + blk, chunk_in_block); + + bi->block_state = + YAFFS_BLOCK_STATE_ALLOCATING; + dev->alloc_block = blk; + dev->alloc_page = chunk_in_block; + dev->alloc_block_finder = blk; + } else { + /* This is a partially written block + * that is not the current + * allocation block. + */ + yaffs_trace(YAFFS_TRACE_SCAN, + "Partially written block %d detected. gc will fix this.", + blk); + } + } + } + + dev->n_free_chunks++; + + } else if (tags.ecc_result == + YAFFS_ECC_RESULT_UNFIXED) { + yaffs_trace(YAFFS_TRACE_SCAN, + " Unfixed ECC in chunk(%d:%d), chunk ignored", + blk, chunk_in_block); + dev->n_free_chunks++; + } else if (tags.obj_id > YAFFS_MAX_OBJECT_ID || + tags.chunk_id > YAFFS_MAX_CHUNK_ID || + tags.obj_id == YAFFS_OBJECTID_SUMMARY || + (tags.chunk_id > 0 && + tags.n_bytes > dev->data_bytes_per_chunk) || + tags.seq_number != bi->seq_number) { + yaffs_trace(YAFFS_TRACE_SCAN, + "Chunk (%d:%d) with bad tags:obj = %d, chunk_id = %d, n_bytes = %d, ignored", + blk, chunk_in_block, tags.obj_id, + tags.chunk_id, tags.n_bytes); + dev->n_free_chunks++; + } else if (tags.chunk_id > 0) { + /* chunk_id > 0 so it is a data chunk... */ + loff_t endpos; + loff_t chunk_base = (tags.chunk_id - 1) * + dev->data_bytes_per_chunk; + + *found_chunks = 1; + + yaffs_set_chunk_bit(dev, blk, chunk_in_block); + bi->pages_in_use++; + + in = yaffs_find_or_create_by_number(dev, + tags.obj_id, + YAFFS_OBJECT_TYPE_FILE); + if (!in) + /* Out of memory */ + alloc_failed = 1; + + if (in && + in->variant_type == YAFFS_OBJECT_TYPE_FILE && + chunk_base < in->variant.file_variant.shrink_size) { + /* This has not been invalidated by + * a resize */ + if (!yaffs_put_chunk_in_file(in, tags.chunk_id, + chunk, -1)) + alloc_failed = 1; + + /* File size is calculated by looking at + * the data chunks if we have not + * seen an object header yet. + * Stop this practice once we find an + * object header. + */ + endpos = chunk_base + tags.n_bytes; + + if (!in->valid && + in->variant.file_variant.stored_size < endpos) { + in->variant.file_variant. + stored_size = endpos; + in->variant.file_variant. + file_size = endpos; + } + } else if (in) { + /* This chunk has been invalidated by a + * resize, or a past file deletion + * so delete the chunk*/ + yaffs_chunk_del(dev, chunk, 1, __LINE__); + } + } else { + /* chunk_id == 0, so it is an ObjectHeader. + * Thus, we read in the object header and make + * the object + */ + *found_chunks = 1; + + yaffs_set_chunk_bit(dev, blk, chunk_in_block); + bi->pages_in_use++; + + oh = NULL; + in = NULL; + + if (tags.extra_available) { + in = yaffs_find_or_create_by_number(dev, + tags.obj_id, + tags.extra_obj_type); + if (!in) + alloc_failed = 1; + } + + if (!in || + (!in->valid && dev->param.disable_lazy_load) || + tags.extra_shadows || + (!in->valid && (tags.obj_id == YAFFS_OBJECTID_ROOT || + tags.obj_id == YAFFS_OBJECTID_LOSTNFOUND))) { + + /* If we don't have valid info then we + * need to read the chunk + * TODO In future we can probably defer + * reading the chunk and living with + * invalid data until needed. + */ + + result = yaffs_rd_chunk_tags_nand(dev, + chunk, + chunk_data, + NULL); + + oh = (struct yaffs_obj_hdr *)chunk_data; + + yaffs_do_endian_oh(dev, oh); + + if (dev->param.inband_tags) { + /* Fix up the header if they got + * corrupted by inband tags */ + oh->shadows_obj = + oh->inband_shadowed_obj_id; + oh->is_shrink = + oh->inband_is_shrink; + } + + if (!in) { + in = yaffs_find_or_create_by_number(dev, + tags.obj_id, oh->type); + if (!in) + alloc_failed = 1; + } + } + + if (!in) { + /* TODO Hoosterman we have a problem! */ + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: Could not make object for object %d at chunk %d during scan", + tags.obj_id, chunk); + return YAFFS_FAIL; + } + + if (in->valid) { + /* We have already filled this one. + * We have a duplicate that will be + * discarded, but we first have to suck + * out resize info if it is a file. + */ + if ((in->variant_type == YAFFS_OBJECT_TYPE_FILE) && + ((oh && oh->type == YAFFS_OBJECT_TYPE_FILE) || + (tags.extra_available && + tags.extra_obj_type == YAFFS_OBJECT_TYPE_FILE) + )) { + loff_t this_size = (oh) ? + yaffs_oh_to_size(dev, oh, 0) : + tags.extra_file_size; + u32 parent_obj_id = (oh) ? + (u32)oh->parent_obj_id : + tags.extra_parent_id; + + is_shrink = (oh) ? + oh->is_shrink : + tags.extra_is_shrink; + + /* If it is deleted (unlinked + * at start also means deleted) + * we treat the file size as + * being zeroed at this point. + */ + if (parent_obj_id == YAFFS_OBJECTID_DELETED || + parent_obj_id == YAFFS_OBJECTID_UNLINKED) { + this_size = 0; + is_shrink = 1; + } + + if (is_shrink && + in->variant.file_variant.shrink_size > + this_size) + in->variant.file_variant.shrink_size = + this_size; + + if (is_shrink) + bi->has_shrink_hdr = 1; + } + /* Use existing - destroy this one. */ + yaffs_chunk_del(dev, chunk, 1, __LINE__); + } + + if (!in->valid && in->variant_type != + (oh ? oh->type : tags.extra_obj_type)) { + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: Bad type, %d != %d, for object %d at chunk %d during scan", + oh ? oh->type : tags.extra_obj_type, + in->variant_type, tags.obj_id, + chunk); + in = yaffs_retype_obj(in, oh ? oh->type : tags.extra_obj_type); + } + + if (!in->valid && + (tags.obj_id == YAFFS_OBJECTID_ROOT || + tags.obj_id == YAFFS_OBJECTID_LOSTNFOUND)) { + /* We only load some info, don't fiddle + * with directory structure */ + in->valid = 1; + + if (oh) { + in->yst_mode = oh->yst_mode; + yaffs_load_attribs(in, oh); + in->lazy_loaded = 0; + } else { + in->lazy_loaded = 1; + } + in->hdr_chunk = chunk; + + } else if (!in->valid) { + /* we need to load this info */ + in->valid = 1; + in->hdr_chunk = chunk; + if (oh) { + in->variant_type = oh->type; + in->yst_mode = oh->yst_mode; + yaffs_load_attribs(in, oh); + + if (oh->shadows_obj > 0) + yaffs_handle_shadowed_obj(dev, + oh->shadows_obj, 1); + + yaffs_set_obj_name_from_oh(in, oh); + parent = yaffs_find_or_create_by_number(dev, + oh->parent_obj_id, + YAFFS_OBJECT_TYPE_DIRECTORY); + file_size = yaffs_oh_to_size(dev, oh, 0); + is_shrink = oh->is_shrink; + equiv_id = oh->equiv_id; + } else { + in->variant_type = tags.extra_obj_type; + parent = yaffs_find_or_create_by_number(dev, + tags.extra_parent_id, + YAFFS_OBJECT_TYPE_DIRECTORY); + file_size = tags.extra_file_size; + is_shrink = tags.extra_is_shrink; + equiv_id = tags.extra_equiv_id; + in->lazy_loaded = 1; + } + in->dirty = 0; + + if (!parent) + alloc_failed = 1; + + /* directory stuff... + * hook up to parent + */ + + if (parent && + parent->variant_type == YAFFS_OBJECT_TYPE_UNKNOWN) { + /* Set up as a directory */ + parent->variant_type = + YAFFS_OBJECT_TYPE_DIRECTORY; + INIT_LIST_HEAD(&parent-> + variant.dir_variant.children); + } else if (!parent || + parent->variant_type != + YAFFS_OBJECT_TYPE_DIRECTORY) { + /* Hoosterman, another problem.... + * Trying to use a non-directory as a directory + */ + + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: attempting to use non-directory as a directory in scan. Put in lost+found." + ); + parent = dev->lost_n_found; + } + yaffs_add_obj_to_dir(parent, in); + + is_unlinked = (parent == dev->del_dir) || + (parent == dev->unlinked_dir); + + if (is_shrink) + /* Mark the block */ + bi->has_shrink_hdr = 1; + + /* Note re hardlinks. + * Since we might scan a hardlink before its equivalent + * object is scanned we put them all in a list. + * After scanning is complete, we should have all the + * objects, so we run through this list and fix up all + * the chains. + */ + + switch (in->variant_type) { + case YAFFS_OBJECT_TYPE_UNKNOWN: + /* Todo got a problem */ + break; + case YAFFS_OBJECT_TYPE_FILE: + file_var = &in->variant.file_variant; + if (file_var->stored_size < file_size) { + /* This covers the case where the file + * size is greater than the data held. + * This will happen if the file is + * resized to be larger than its + * current data extents. + */ + file_var->file_size = file_size; + file_var->stored_size = file_size; + } + + if (file_var->shrink_size > file_size) + file_var->shrink_size = file_size; + + break; + case YAFFS_OBJECT_TYPE_HARDLINK: + hl_var = &in->variant.hardlink_variant; + if (!is_unlinked) { + hl_var->equiv_id = equiv_id; + list_add(&in->hard_links, hard_list); + } + break; + case YAFFS_OBJECT_TYPE_DIRECTORY: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_SPECIAL: + /* Do nothing */ + break; + case YAFFS_OBJECT_TYPE_SYMLINK: + sl_var = &in->variant.symlink_variant; + if (oh) { + sl_var->alias = + yaffs_clone_str(oh->alias); + if (!sl_var->alias) + alloc_failed = 1; + } + break; + } + } + } + return alloc_failed ? YAFFS_FAIL : YAFFS_OK; +} + +int yaffs2_scan_backwards(struct yaffs_dev *dev) +{ + u32 blk; + int block_iter; + int start_iter; + int end_iter; + int n_to_scan = 0; + enum yaffs_block_state state; + int c; + LIST_HEAD(hard_list); + struct yaffs_block_info *bi; + u32 seq_number; + int n_blocks = dev->internal_end_block - dev->internal_start_block + 1; + u8 *chunk_data; + int found_chunks; + int alloc_failed = 0; + struct yaffs_block_index *block_index = NULL; + int alt_block_index = 0; + int summary_available; + + yaffs_trace(YAFFS_TRACE_SCAN, + "yaffs2_scan_backwards starts intstartblk %d intendblk %d...", + dev->internal_start_block, dev->internal_end_block); + + dev->seq_number = YAFFS_LOWEST_SEQUENCE_NUMBER; + + block_index = + kmalloc(n_blocks * sizeof(struct yaffs_block_index), GFP_NOFS); + + if (!block_index) { + block_index = + vmalloc(n_blocks * sizeof(struct yaffs_block_index)); + alt_block_index = 1; + } + + if (!block_index) { + yaffs_trace(YAFFS_TRACE_SCAN, + "yaffs2_scan_backwards() could not allocate block index!" + ); + return YAFFS_FAIL; + } + + dev->blocks_in_checkpt = 0; + + chunk_data = yaffs_get_temp_buffer(dev); + + /* Scan all the blocks to determine their state */ + bi = dev->block_info; + for (blk = dev->internal_start_block; blk <= dev->internal_end_block; + blk++) { + yaffs_clear_chunk_bits(dev, blk); + bi->pages_in_use = 0; + bi->soft_del_pages = 0; + + yaffs_query_init_block_state(dev, blk, &state, &seq_number); + + bi->block_state = state; + bi->seq_number = seq_number; + + if (bi->seq_number == YAFFS_SEQUENCE_CHECKPOINT_DATA) + bi->block_state = YAFFS_BLOCK_STATE_CHECKPOINT; + if (bi->seq_number == YAFFS_SEQUENCE_BAD_BLOCK) + bi->block_state = YAFFS_BLOCK_STATE_DEAD; + + yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, + "Block scanning block %d state %d seq %d", + blk, bi->block_state, seq_number); + + if (bi->block_state == YAFFS_BLOCK_STATE_CHECKPOINT) { + dev->blocks_in_checkpt++; + + } else if (bi->block_state == YAFFS_BLOCK_STATE_DEAD) { + yaffs_trace(YAFFS_TRACE_BAD_BLOCKS, + "block %d is bad", blk); + } else if (bi->block_state == YAFFS_BLOCK_STATE_EMPTY) { + yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "Block empty "); + dev->n_erased_blocks++; + dev->n_free_chunks += dev->param.chunks_per_block; + } else if (bi->block_state == + YAFFS_BLOCK_STATE_NEEDS_SCAN) { + /* Determine the highest sequence number */ + if (seq_number >= YAFFS_LOWEST_SEQUENCE_NUMBER && + seq_number < YAFFS_HIGHEST_SEQUENCE_NUMBER) { + block_index[n_to_scan].seq = seq_number; + block_index[n_to_scan].block = blk; + n_to_scan++; + if (seq_number >= dev->seq_number) + dev->seq_number = seq_number; + } else { + /* TODO: Nasty sequence number! */ + yaffs_trace(YAFFS_TRACE_SCAN, + "Block scanning block %d has bad sequence number %d", + blk, seq_number); + } + } + bi++; + } + + yaffs_trace(YAFFS_TRACE_ALWAYS, "%d blocks to be sorted...", n_to_scan); + + cond_resched(); + + /* Sort the blocks by sequence number */ + sort(block_index, n_to_scan, sizeof(struct yaffs_block_index), + yaffs2_ybicmp, NULL); + + cond_resched(); + + yaffs_trace(YAFFS_TRACE_SCAN, "...done"); + + /* Now scan the blocks looking at the data. */ + start_iter = 0; + end_iter = n_to_scan - 1; + yaffs_trace(YAFFS_TRACE_SCAN_DEBUG, "%d blocks to scan", n_to_scan); + + /* For each block.... backwards */ + for (block_iter = end_iter; + !alloc_failed && block_iter >= start_iter; + block_iter--) { + /* Cooperative multitasking! This loop can run for so + long that watchdog timers expire. */ + cond_resched(); + + /* get the block to scan in the correct order */ + blk = block_index[block_iter].block; + bi = yaffs_get_block_info(dev, blk); + + summary_available = yaffs_summary_read(dev, dev->sum_tags, blk); + + /* For each chunk in each block that needs scanning.... */ + found_chunks = 0; + if (summary_available) + c = dev->chunks_per_summary - 1; + else + c = dev->param.chunks_per_block - 1; + + for (/* c is already initialised */; + !alloc_failed && c >= 0 && + (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN || + bi->block_state == YAFFS_BLOCK_STATE_ALLOCATING); + c--) { + /* Scan backwards... + * Read the tags and decide what to do + */ + if (yaffs2_scan_chunk(dev, bi, blk, c, + &found_chunks, chunk_data, + &hard_list, summary_available) == + YAFFS_FAIL) + alloc_failed = 1; + } + + if (bi->block_state == YAFFS_BLOCK_STATE_NEEDS_SCAN) { + /* If we got this far while scanning, then the block + * is fully allocated. */ + bi->block_state = YAFFS_BLOCK_STATE_FULL; + } + + /* Now let's see if it was dirty */ + if (bi->pages_in_use == 0 && + !bi->has_shrink_hdr && + bi->block_state == YAFFS_BLOCK_STATE_FULL) { + yaffs_block_became_dirty(dev, blk); + } + } + + yaffs_skip_rest_of_block(dev); + + if (alt_block_index) + vfree(block_index); + else + kfree(block_index); + + /* Ok, we've done all the scanning. + * Fix up the hard link chains. + * We have scanned all the objects, now it's time to add these + * hardlinks. + */ + yaffs_link_fixup(dev, &hard_list); + + yaffs_release_temp_buffer(dev, chunk_data); + + if (alloc_failed) + return YAFFS_FAIL; + + yaffs_trace(YAFFS_TRACE_SCAN, "yaffs2_scan_backwards ends"); + + return YAFFS_OK; +} diff --git a/fs/yaffs2/yaffs_yaffs2.h b/fs/yaffs2/yaffs_yaffs2.h new file mode 100644 index 000000000000..4eaa722f272b --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs2.h @@ -0,0 +1,38 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YAFFS_YAFFS2_H__ +#define __YAFFS_YAFFS2_H__ + +#include "yaffs_guts.h" + +void yaffs_calc_oldest_dirty_seq(struct yaffs_dev *dev); +void yaffs2_find_oldest_dirty_seq(struct yaffs_dev *dev); +void yaffs2_clear_oldest_dirty_seq(struct yaffs_dev *dev, + struct yaffs_block_info *bi); +void yaffs2_update_oldest_dirty_seq(struct yaffs_dev *dev, unsigned block_no, + struct yaffs_block_info *bi); +int yaffs_block_ok_for_gc(struct yaffs_dev *dev, struct yaffs_block_info *bi); +u32 yaffs2_find_refresh_block(struct yaffs_dev *dev); +int yaffs2_checkpt_required(struct yaffs_dev *dev); +int yaffs_calc_checkpt_blocks_required(struct yaffs_dev *dev); + +void yaffs2_checkpt_invalidate(struct yaffs_dev *dev); +int yaffs2_checkpt_save(struct yaffs_dev *dev); +int yaffs2_checkpt_restore(struct yaffs_dev *dev); + +int yaffs2_handle_hole(struct yaffs_obj *obj, loff_t new_size); +int yaffs2_scan_backwards(struct yaffs_dev *dev); + +#endif diff --git a/fs/yaffs2/yportenv.h b/fs/yaffs2/yportenv.h new file mode 100644 index 000000000000..0185985cc8fc --- /dev/null +++ b/fs/yaffs2/yportenv.h @@ -0,0 +1,92 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2018 Aleph One Ltd. + * + * Created by Charles Manning <charles@aleph1.co.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 2.1 as + * published by the Free Software Foundation. + * + * Note: Only YAFFS headers are LGPL, YAFFS C code is covered by GPL. + */ + +#ifndef __YPORTENV_H__ +#define __YPORTENV_H__ + +/* + * Define the MTD version in terms of Linux Kernel versions + * This allows yaffs to be used independantly of the kernel + * as well as with it. + */ + +#define MTD_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) + +#ifdef YAFFS_OUT_OF_TREE +#include "moduleconfig.h" +#endif + +#include <linux/version.h> +#define MTD_VERSION_CODE LINUX_VERSION_CODE + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 19)) +#include <linux/config.h> +#endif +#include <linux/version.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/xattr.h> +#include <linux/list.h> +#include <linux/types.h> +#include <linux/fs.h> +#include <linux/stat.h> +#include <linux/sort.h> +#include <linux/bitops.h> + +/* These type wrappings are used to support Unicode names in WinCE. */ +#define YCHAR char +#define YUCHAR unsigned char +#define _Y(x) x + +#define YAFFS_LOSTNFOUND_NAME "lost+found" +#define YAFFS_LOSTNFOUND_PREFIX "obj" + + +#define YAFFS_ROOT_MODE 0755 +#define YAFFS_LOSTNFOUND_MODE 0700 + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 5, 0)) +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4,12,0)) +#define Y_CURRENT_TIME ktime_get_real_seconds() +#else +#define Y_CURRENT_TIME ktime_get_real_seconds() +#endif +#define Y_TIME_CONVERT(x) (x).tv_sec +#else +#if (LINUX_VERSION_CODE < KERNEL_VERSION(4,12,0)) +#define Y_CURRENT_TIME CURRENT_TIME +#else +#define Y_CURRENT_TIME current_kernel_time() +#endif +#define Y_TIME_CONVERT(x) (x) +#endif + +#define compile_time_assertion(assertion) \ + ({ int x = __builtin_choose_expr(assertion, 0, (void)0); (void) x; }) + + +#define yaffs_printf(msk, fmt, ...) \ + printk(KERN_DEBUG "yaffs: " fmt "\n", ##__VA_ARGS__) + +#define yaffs_trace(msk, fmt, ...) do { \ + if (yaffs_trace_mask & (msk)) \ + printk(KERN_DEBUG "yaffs: " fmt "\n", ##__VA_ARGS__); \ +} while (0) + + +#endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ca08db4ffb5f..ce3f5231aa69 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -358,6 +358,7 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ + bool has_tail_call; }; /* single container for all structs diff --git a/include/linux/fs.h b/include/linux/fs.h index ac1e89872db4..429c36bdecb3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1370,6 +1370,7 @@ extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); +extern int setfl(int fd, struct file *filp, unsigned long arg); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); @@ -1858,6 +1859,7 @@ struct file_operations { ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); + int (*setfl)(struct file *, unsigned long); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -1928,6 +1930,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, struct iovec *fast_pointer, struct iovec **ret_pointer); +typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t, + loff_t *); +vfs_readf_t vfs_readf(struct file *file); +vfs_writef_t vfs_writef(struct file *file); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, @@ -2366,6 +2374,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec64 *, int); +extern int update_time(struct inode *, struct timespec64 *, int); /* /sys/fs */ extern struct kobject *fs_kobj; @@ -2647,6 +2656,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return false; } #endif +extern int __sync_filesystem(struct super_block *, int); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; @@ -3011,7 +3021,6 @@ extern int do_pipe_flags(int *, int); id(UNKNOWN, unknown) \ id(FIRMWARE, firmware) \ id(FIRMWARE_PREALLOC_BUFFER, firmware) \ - id(FIRMWARE_EFI_EMBEDDED, firmware) \ id(MODULE, kernel-module) \ id(KEXEC_IMAGE, kexec-image) \ id(KEXEC_INITRAMFS, kexec-initramfs) \ diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h new file mode 100644 index 000000000000..c09135a1ef13 --- /dev/null +++ b/include/linux/io_uring.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_H +#define _LINUX_IO_URING_H + +#include <linux/sched.h> +#include <linux/xarray.h> +#include <linux/percpu-refcount.h> + +struct io_uring_task { + /* submission side */ + struct xarray xa; + struct wait_queue_head wait; + struct file *last; + atomic_long_t req_issue; + + /* completion side */ + bool in_idle ____cacheline_aligned_in_smp; + atomic_long_t req_complete; +}; + +#if defined(CONFIG_IO_URING) +void __io_uring_task_cancel(void); +void __io_uring_files_cancel(struct files_struct *files); +void __io_uring_free(struct task_struct *tsk); + +static inline void io_uring_task_cancel(void) +{ + if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + __io_uring_task_cancel(); +} +static inline void io_uring_files_cancel(struct files_struct *files) +{ + if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + __io_uring_files_cancel(files); +} +static inline void io_uring_free(struct task_struct *tsk) +{ + if (tsk->io_uring) + __io_uring_free(tsk); +} +#else +static inline void io_uring_task_cancel(void) +{ +} +static inline void io_uring_files_cancel(struct files_struct *files) +{ +} +static inline void io_uring_free(struct task_struct *tsk) +{ +} +#endif + +#endif diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 8fce5c98a4b0..c1a3f172e97a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -395,6 +395,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock, return lock->key == key; } +struct lock_class *lockdep_hlock_class(struct held_lock *hlock); + /* * Acquire a lock. * @@ -540,6 +542,7 @@ struct lockdep_map { }; #define lockdep_depth(tsk) (0) +#define lockdep_is_held(lock) (1) #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index a4dc45fbec0a..23bc366f6c3b 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -27,8 +27,7 @@ * bit 16-27: update value * bit 31: 1 - update, 0 - no update */ -#define CMDQ_WFE_OPTION (CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \ - CMDQ_WFE_WAIT_VALUE) +#define CMDQ_WFE_OPTION (CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE) /** cmdq event maximum */ #define CMDQ_MAX_EVENT 0x3ff diff --git a/include/linux/mm.h b/include/linux/mm.h index bc05c3588aa3..6b0a2e7cc87f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1684,6 +1684,28 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } +extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int); +extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[], + int); +extern void vma_do_get_file(struct vm_area_struct *, const char[], int); +extern void vma_do_fput(struct vm_area_struct *, const char[], int); + +#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \ + __LINE__) +#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \ + __LINE__) +#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__) +#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__) + +#ifndef CONFIG_MMU +extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int); +extern void vmr_do_fput(struct vm_region *, const char[], int); + +#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \ + __LINE__) +#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__) +#endif /* !CONFIG_MMU */ + extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 64ede5f150dc..1c899fd6bda4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -276,6 +276,7 @@ struct vm_region { unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ + struct file *vm_prfile; /* the virtual backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for @@ -355,6 +356,7 @@ struct vm_area_struct { unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ + struct file *vm_prfile; /* shadow of vm_file */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_SWAP diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 8f882f5881e8..6b9808f09843 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -7,12 +7,15 @@ struct mnt_namespace; struct fs_struct; struct user_namespace; struct ns_common; +struct vfsmount; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); extern struct ns_common *from_mnt_ns(struct mnt_namespace *); +extern int is_current_mnt_ns(struct vfsmount *mnt); + extern const struct file_operations proc_mounts_operations; extern const struct file_operations proc_mountinfo_operations; extern const struct file_operations proc_mountstats_operations; diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h index 122f3439e1af..c65d7a3be3c6 100644 --- a/include/linux/mtd/pfow.h +++ b/include/linux/mtd/pfow.h @@ -128,7 +128,7 @@ static inline void print_drs_error(unsigned dsr) if (!(dsr & DSR_AVAILABLE)) printk(KERN_NOTICE"DSR.15: (0) Device not Available\n"); - if (prog_status & 0x03) + if ((prog_status & 0x03) == 0x03) printk(KERN_NOTICE"DSR.9,8: (11) Attempt to program invalid " "half with 41h command\n"); else if (prog_status & 0x02) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5fd0a9ef425f..c8fc941e5059 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -12,7 +12,7 @@ * reasonable for NFS over UDP. */ #define NFS_MAX_FILE_IO_SIZE (1048576U) -#define NFS_DEF_FILE_IO_SIZE (4096U) +#define NFS_DEF_FILE_IO_SIZE CONFIG_NFS_DEF_FILE_IO_SIZE #define NFS_MIN_FILE_IO_SIZE (1024U) struct nfs4_string { diff --git a/include/linux/oom.h b/include/linux/oom.h index c696c265f019..b9df34326772 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -55,6 +55,7 @@ struct oom_control { }; extern struct mutex oom_lock; +extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 93fcef105061..ff3c48f0abc5 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -3,6 +3,7 @@ #define __LINUX_OVERFLOW_H #include <linux/compiler.h> +#include <linux/limits.h> /* * In the fallback code below, we need to compute the minimum and diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 8679ccd722e8..3468794f83d2 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -11,7 +11,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); -extern void __split_page_owner(struct page *page, unsigned int order); +extern void __split_page_owner(struct page *page, unsigned int nr); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(struct page *page); @@ -31,10 +31,10 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } -static inline void split_page_owner(struct page *page, unsigned int order) +static inline void split_page_owner(struct page *page, unsigned int nr) { if (static_branch_unlikely(&page_owner_inited)) - __split_page_owner(page, order); + __split_page_owner(page, nr); } static inline void copy_page_owner(struct page *oldpage, struct page *newpage) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 34c1c4f45288..1bc3c020672f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -439,6 +439,7 @@ struct pci_dev { unsigned int is_probed:1; /* Device probing in progress */ unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ + unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index f3eaf9ec00a1..70078be166e3 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -21,6 +21,7 @@ * @dst_id: dst request line * @m_master: memory master for transfers on allocated channel * @p_master: peripheral master for transfers on allocated channel + * @channels: mask of the channels permitted for allocation (zero value means any) * @hs_polarity:set active low polarity of handshake interface */ struct dw_dma_slave { @@ -29,6 +30,7 @@ struct dw_dma_slave { u8 dst_id; u8 m_master; u8 p_master; + u8 channels; bool hs_polarity; }; diff --git a/include/linux/pm.h b/include/linux/pm.h index 121c104a4090..1010bf3d3008 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -584,7 +584,7 @@ struct dev_pm_info { #endif #ifdef CONFIG_PM struct hrtimer suspend_timer; - unsigned long timer_expires; + u64 timer_expires; struct work_struct work; wait_queue_head_t wait_queue; struct wake_irq *wakeirq; diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index dd464943f717..5b90eff50bf6 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -229,6 +229,9 @@ struct geni_se { #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) +/* QUP SE VERSION value for major number 2 and minor number 5 */ +#define QUP_SE_VERSION_2_5 0x20050000 + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); diff --git a/include/linux/sched.h b/include/linux/sched.h index 683372943093..f0f38e86ab1e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -61,6 +61,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct io_uring_task; /* * Task state bitmask. NOTE! These bits are also @@ -923,6 +924,10 @@ struct task_struct { /* Open file information: */ struct files_struct *files; +#ifdef CONFIG_IO_URING + struct io_uring_task *io_uring; +#endif + /* Namespaces: */ struct nsproxy *nsproxy; diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ecdc6542070f..dfd82eab2902 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index a74c1d5acdf3..cb71dca98558 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -105,11 +105,12 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys, /** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet - * @event: the desired event type to "wait and CLEAR" + * @event: the desired event type to wait + * @clear: clear event or not after event arrive * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event); +int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet diff --git a/include/linux/splice.h b/include/linux/splice.h index 5c47013f708e..fef6c59ed92a 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -93,4 +93,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; extern const struct pipe_buf_operations default_pipe_buf_ops; + +extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); +extern long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); #endif diff --git a/include/linux/string.h b/include/linux/string.h index 9b7a0632e87a..b1f3894a0a3e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -161,20 +161,13 @@ extern int bcmp(const void *,const void *,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif -#ifndef __HAVE_ARCH_MEMCPY_MCSAFE -static inline __must_check unsigned long memcpy_mcsafe(void *dst, - const void *src, size_t cnt) -{ - memcpy(dst, src, cnt); - return 0; -} -#endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif + void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 0a76ddc07d59..1ef3ab2343aa 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -163,6 +163,19 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n) } #endif +#ifndef copy_mc_to_kernel +/* + * Without arch opt-in this generic copy_mc_to_kernel() will not handle + * #MC (or arch equivalent) during source read. + */ +static inline unsigned long __must_check +copy_mc_to_kernel(void *dst, const void *src, size_t cnt) +{ + memcpy(dst, src, cnt); + return 0; +} +#endif + static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; diff --git a/include/linux/uio.h b/include/linux/uio.h index 9576fd8158d7..6a97b4d10b2e 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -186,10 +186,10 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif -#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE -size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i); +#ifdef CONFIG_ARCH_HAS_COPY_MC +size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else -#define _copy_to_iter_mcsafe _copy_to_iter +#define _copy_mc_to_iter _copy_to_iter #endif static __always_inline __must_check @@ -202,12 +202,12 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check -size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) +size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else - return _copy_to_iter_mcsafe(addr, bytes, i); + return _copy_mc_to_iter(addr, bytes, i); } size_t iov_iter_zero(size_t bytes, struct iov_iter *); diff --git a/include/net/ip.h b/include/net/ip.h index 04ebe7bf54c6..d61c26ab4ee8 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -439,12 +439,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct net *net = dev_net(dst->dev); + unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); + /* 'forwarding = true' case should always honour route mtu */ + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 0d3920896d50..716db4a0fed8 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -108,6 +108,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, unsigned int logflags); void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, struct sock *sk); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb); void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index ec2cbfab71f3..f09541cba3c9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -896,6 +896,12 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) return (struct nft_expr *)&rule->data[rule->dlen]; } +static inline bool nft_expr_more(const struct nft_rule *rule, + const struct nft_expr *expr) +{ + return expr != nft_expr_last(rule) && expr->ops; +} + static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index e1057b255f69..879fe8cff581 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -56,7 +56,10 @@ static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT struct tcf_tunnel_key *t = to_tunnel_key(a); - struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); + struct tcf_tunnel_key_params *params; + + params = rcu_dereference_protected(t->params, + lockdep_is_held(&a->tcfa_lock)); return ¶ms->tcft_enc_metadata->u.tun_info; #else diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index e3518fd6b95b..9353910915d4 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -95,10 +95,11 @@ static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offs size_t length) { return -EINVAL; } -static inline int ib_umem_find_best_pgsz(struct ib_umem *umem, - unsigned long pgsz_bitmap, - unsigned long virt) { - return -EINVAL; +static inline unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, + unsigned long pgsz_bitmap, + unsigned long virt) +{ + return 0; } #endif /* CONFIG_INFINIBAND_USER_MEM */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index ef2f3986c493..d7809f203715 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2465,7 +2465,7 @@ struct ib_device_ops { int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); - void (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); + int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, @@ -3834,46 +3834,15 @@ static inline int ib_post_recv(struct ib_qp *qp, return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } -struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, - int nr_cqe, int comp_vector, - enum ib_poll_context poll_ctx, - const char *caller, struct ib_udata *udata); - -/** - * ib_alloc_cq_user: Allocate kernel/user CQ - * @dev: The IB device - * @private: Private data attached to the CQE - * @nr_cqe: Number of CQEs in the CQ - * @comp_vector: Completion vector used for the IRQs - * @poll_ctx: Context used for polling the CQ - * @udata: Valid user data or NULL for kernel objects - */ -static inline struct ib_cq *ib_alloc_cq_user(struct ib_device *dev, - void *private, int nr_cqe, - int comp_vector, - enum ib_poll_context poll_ctx, - struct ib_udata *udata) -{ - return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx, - KBUILD_MODNAME, udata); -} - -/** - * ib_alloc_cq: Allocate kernel CQ - * @dev: The IB device - * @private: Private data attached to the CQE - * @nr_cqe: Number of CQEs in the CQ - * @comp_vector: Completion vector used for the IRQs - * @poll_ctx: Context used for polling the CQ - * - * NOTE: for user cq use ib_alloc_cq_user with valid udata! - */ +struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, + int comp_vector, enum ib_poll_context poll_ctx, + const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { - return ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx, - NULL); + return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, + KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, @@ -3895,26 +3864,7 @@ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, KBUILD_MODNAME); } -/** - * ib_free_cq_user - Free kernel/user CQ - * @cq: The CQ to free - * @udata: Valid user data or NULL for kernel objects - * - * NOTE: This function shouldn't be called on shared CQs. - */ -void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata); - -/** - * ib_free_cq - Free kernel CQ - * @cq: The CQ to free - * - * NOTE: for user cq use ib_free_cq_user with valid udata! - */ -static inline void ib_free_cq(struct ib_cq *cq) -{ - ib_free_cq_user(cq, NULL); -} - +void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** @@ -3972,7 +3922,9 @@ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); */ static inline void ib_destroy_cq(struct ib_cq *cq) { - ib_destroy_cq_user(cq, NULL); + int ret = ib_destroy_cq_user(cq, NULL); + + WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h index 731ac09ed231..5b567b43e1b1 100644 --- a/include/scsi/scsi_common.h +++ b/include/scsi/scsi_common.h @@ -25,6 +25,13 @@ scsi_command_size(const unsigned char *cmnd) scsi_varlen_cdb_length(cmnd) : COMMAND_SIZE(cmnd[0]); } +static inline unsigned char +scsi_command_control(const unsigned char *cmnd) +{ + return (cmnd[0] == VARIABLE_LENGTH_CMD) ? + cmnd[1] : cmnd[COMMAND_SIZE(cmnd[0]) - 1]; +} + /* Returns a human-readable name for the device */ extern const char *scsi_device_type(unsigned type); diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index d16a4229209b..a2becf13293a 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -253,6 +253,7 @@ struct hda_codec { unsigned int force_pin_prefix:1; /* Add location prefix */ unsigned int link_down_at_suspend:1; /* link down at runtime suspend */ unsigned int relaxed_resume:1; /* don't resume forcibly for jack */ + unsigned int forced_resume:1; /* forced resume for jack */ unsigned int mst_no_extra_pcms:1; /* no backup PCMs for DP-MST */ #ifdef CONFIG_PM diff --git a/include/trace/events/target.h b/include/trace/events/target.h index 77408edd29d2..67fad2677ed5 100644 --- a/include/trace/events/target.h +++ b/include/trace/events/target.h @@ -141,6 +141,7 @@ TRACE_EVENT(target_sequencer_start, __field( unsigned int, opcode ) __field( unsigned int, data_length ) __field( unsigned int, task_attribute ) + __field( unsigned char, control ) __array( unsigned char, cdb, TCM_MAX_COMMAND_SIZE ) __string( initiator, cmd->se_sess->se_node_acl->initiatorname ) ), @@ -151,6 +152,7 @@ TRACE_EVENT(target_sequencer_start, __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; + __entry->control = scsi_command_control(cmd->t_task_cdb); memcpy(__entry->cdb, cmd->t_task_cdb, TCM_MAX_COMMAND_SIZE); __assign_str(initiator, cmd->se_sess->se_node_acl->initiatorname); ), @@ -160,9 +162,7 @@ TRACE_EVENT(target_sequencer_start, __entry->tag, show_opcode_name(__entry->opcode), __entry->data_length, __print_hex(__entry->cdb, 16), show_task_attribute_name(__entry->task_attribute), - scsi_command_size(__entry->cdb) <= 16 ? - __entry->cdb[scsi_command_size(__entry->cdb) - 1] : - __entry->cdb[1] + __entry->control ) ); @@ -178,6 +178,7 @@ TRACE_EVENT(target_cmd_complete, __field( unsigned int, opcode ) __field( unsigned int, data_length ) __field( unsigned int, task_attribute ) + __field( unsigned char, control ) __field( unsigned char, scsi_status ) __field( unsigned char, sense_length ) __array( unsigned char, cdb, TCM_MAX_COMMAND_SIZE ) @@ -191,6 +192,7 @@ TRACE_EVENT(target_cmd_complete, __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; + __entry->control = scsi_command_control(cmd->t_task_cdb); __entry->scsi_status = cmd->scsi_status; __entry->sense_length = cmd->scsi_status == SAM_STAT_CHECK_CONDITION ? min(18, ((u8 *) cmd->sense_buffer)[SPC_ADD_SENSE_LEN_OFFSET] + 8) : 0; @@ -208,9 +210,7 @@ TRACE_EVENT(target_cmd_complete, show_opcode_name(__entry->opcode), __entry->data_length, __print_hex(__entry->cdb, 16), show_task_attribute_name(__entry->task_attribute), - scsi_command_size(__entry->cdb) <= 16 ? - __entry->cdb[scsi_command_size(__entry->cdb) - 1] : - __entry->cdb[1] + __entry->control ) ); diff --git a/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h new file mode 100644 index 000000000000..34738b8cf349 --- /dev/null +++ b/include/uapi/linux/aufs_type.h @@ -0,0 +1,452 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2005-2020 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __AUFS_TYPE_H__ +#define __AUFS_TYPE_H__ + +#define AUFS_NAME "aufs" + +#ifdef __KERNEL__ +/* + * define it before including all other headers. + * sched.h may use pr_* macros before defining "current", so define the + * no-current version first, and re-define later. + */ +#define pr_fmt(fmt) AUFS_NAME " %s:%d: " fmt, __func__, __LINE__ +#include <linux/sched.h> +#undef pr_fmt +#define pr_fmt(fmt) \ + AUFS_NAME " %s:%d:%.*s[%d]: " fmt, __func__, __LINE__, \ + (int)sizeof(current->comm), current->comm, current->pid +#include <linux/limits.h> +#else +#include <stdint.h> +#include <sys/types.h> +#include <limits.h> +#endif /* __KERNEL__ */ + +#define AUFS_VERSION "5.7-20200622" + +/* todo? move this to linux-2.6.19/include/magic.h */ +#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') + +/* ---------------------------------------------------------------------- */ + +#ifdef __KERNEL__ +#ifdef CONFIG_AUFS_BRANCH_MAX_127 +typedef int8_t aufs_bindex_t; +#define AUFS_BRANCH_MAX 127 +#else +typedef int16_t 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 + +#ifndef AUFS_BRANCH_MAX +#error unknown CONFIG_AUFS_BRANCH_MAX value +#endif +#endif /* __KERNEL__ */ + +/* ---------------------------------------------------------------------- */ + +#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_WH_TMP_LEN 4 +/* a limit for rmdir/rename a dir and copyup */ +#define AUFS_MAX_NAMELEN (NAME_MAX \ + - AUFS_WH_PFX_LEN * 2 /* doubly whiteouted */\ + - 1 /* dot */\ + - AUFS_WH_TMP_LEN) /* hex */ +#define AUFS_XINO_FNAME "." AUFS_NAME ".xino" +#define AUFS_XINO_DEFPATH "/tmp/" AUFS_XINO_FNAME +#define AUFS_XINO_DEF_SEC 30 /* seconds */ +#define AUFS_XINO_DEF_TRUNC 45 /* percentage */ +#define AUFS_DIRWH_DEF 3 +#define AUFS_RDCACHE_DEF 10 /* seconds */ +#define AUFS_RDCACHE_MAX 3600 /* seconds */ +#define AUFS_RDBLK_DEF 512 /* bytes */ +#define AUFS_RDHASH_DEF 32 +#define AUFS_WKQ_NAME AUFS_NAME "d" +#define AUFS_MFS_DEF_SEC 30 /* seconds */ +#define AUFS_MFS_MAX_SEC 3600 /* seconds */ +#define AUFS_FHSM_CACHE_DEF_SEC 30 /* seconds */ +#define AUFS_PLINK_WARN 50 /* number of plinks in a single bucket */ + +/* pseudo-link maintenace under /proc */ +#define AUFS_PLINK_MAINT_NAME "plink_maint" +#define AUFS_PLINK_MAINT_DIR "fs/" AUFS_NAME +#define AUFS_PLINK_MAINT_PATH AUFS_PLINK_MAINT_DIR "/" AUFS_PLINK_MAINT_NAME + +/* dirren, renamed dir */ +#define AUFS_DR_INFO_PFX AUFS_WH_PFX ".dr." +#define AUFS_DR_BRHINO_NAME AUFS_WH_PFX "hino" +/* whiteouted doubly */ +#define AUFS_WH_DR_INFO_PFX AUFS_WH_PFX AUFS_DR_INFO_PFX +#define AUFS_WH_DR_BRHINO AUFS_WH_PFX AUFS_DR_BRHINO_NAME + +#define AUFS_DIROPQ_NAME AUFS_WH_PFX ".opq" /* whiteouted doubly */ +#define AUFS_WH_DIROPQ AUFS_WH_PFX AUFS_DIROPQ_NAME + +#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 permissions and attributes */ +#define AUFS_BRPERM_RW "rw" +#define AUFS_BRPERM_RO "ro" +#define AUFS_BRPERM_RR "rr" +#define AUFS_BRATTR_COO_REG "coo_reg" +#define AUFS_BRATTR_COO_ALL "coo_all" +#define AUFS_BRATTR_FHSM "fhsm" +#define AUFS_BRATTR_UNPIN "unpin" +#define AUFS_BRATTR_ICEX "icex" +#define AUFS_BRATTR_ICEX_SEC "icexsec" +#define AUFS_BRATTR_ICEX_SYS "icexsys" +#define AUFS_BRATTR_ICEX_TR "icextr" +#define AUFS_BRATTR_ICEX_USR "icexusr" +#define AUFS_BRATTR_ICEX_OTH "icexoth" +#define AUFS_BRRATTR_WH "wh" +#define AUFS_BRWATTR_NLWH "nolwh" +#define AUFS_BRWATTR_MOO "moo" + +#define AuBrPerm_RW 1 /* writable, hardlinkable wh */ +#define AuBrPerm_RO (1 << 1) /* readonly */ +#define AuBrPerm_RR (1 << 2) /* natively readonly */ +#define AuBrPerm_Mask (AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR) + +#define AuBrAttr_COO_REG (1 << 3) /* copy-up on open */ +#define AuBrAttr_COO_ALL (1 << 4) +#define AuBrAttr_COO_Mask (AuBrAttr_COO_REG | AuBrAttr_COO_ALL) + +#define AuBrAttr_FHSM (1 << 5) /* file-based hsm */ +#define AuBrAttr_UNPIN (1 << 6) /* rename-able top dir of + branch. meaningless since + linux-3.18-rc1 */ + +/* ignore error in copying XATTR */ +#define AuBrAttr_ICEX_SEC (1 << 7) +#define AuBrAttr_ICEX_SYS (1 << 8) +#define AuBrAttr_ICEX_TR (1 << 9) +#define AuBrAttr_ICEX_USR (1 << 10) +#define AuBrAttr_ICEX_OTH (1 << 11) +#define AuBrAttr_ICEX (AuBrAttr_ICEX_SEC \ + | AuBrAttr_ICEX_SYS \ + | AuBrAttr_ICEX_TR \ + | AuBrAttr_ICEX_USR \ + | AuBrAttr_ICEX_OTH) + +#define AuBrRAttr_WH (1 << 12) /* whiteout-able */ +#define AuBrRAttr_Mask AuBrRAttr_WH + +#define AuBrWAttr_NoLinkWH (1 << 13) /* un-hardlinkable whiteouts */ +#define AuBrWAttr_MOO (1 << 14) /* move-up on open */ +#define AuBrWAttr_Mask (AuBrWAttr_NoLinkWH | AuBrWAttr_MOO) + +#define AuBrAttr_CMOO_Mask (AuBrAttr_COO_Mask | AuBrWAttr_MOO) + +/* #warning test userspace */ +#ifdef __KERNEL__ +#ifndef CONFIG_AUFS_FHSM +#undef AuBrAttr_FHSM +#define AuBrAttr_FHSM 0 +#endif +#ifndef CONFIG_AUFS_XATTR +#undef AuBrAttr_ICEX +#define AuBrAttr_ICEX 0 +#undef AuBrAttr_ICEX_SEC +#define AuBrAttr_ICEX_SEC 0 +#undef AuBrAttr_ICEX_SYS +#define AuBrAttr_ICEX_SYS 0 +#undef AuBrAttr_ICEX_TR +#define AuBrAttr_ICEX_TR 0 +#undef AuBrAttr_ICEX_USR +#define AuBrAttr_ICEX_USR 0 +#undef AuBrAttr_ICEX_OTH +#define AuBrAttr_ICEX_OTH 0 +#endif +#endif + +/* the longest combination */ +/* AUFS_BRATTR_ICEX and AUFS_BRATTR_ICEX_TR don't affect here */ +#define AuBrPermStrSz sizeof(AUFS_BRPERM_RW \ + "+" AUFS_BRATTR_COO_REG \ + "+" AUFS_BRATTR_FHSM \ + "+" AUFS_BRATTR_UNPIN \ + "+" AUFS_BRATTR_ICEX_SEC \ + "+" AUFS_BRATTR_ICEX_SYS \ + "+" AUFS_BRATTR_ICEX_USR \ + "+" AUFS_BRATTR_ICEX_OTH \ + "+" AUFS_BRWATTR_NLWH) + +typedef struct { + char a[AuBrPermStrSz]; +} au_br_perm_str_t; + +static inline int au_br_writable(int brperm) +{ + return brperm & AuBrPerm_RW; +} + +static inline int au_br_whable(int brperm) +{ + return brperm & (AuBrPerm_RW | AuBrRAttr_WH); +} + +static inline int au_br_wh_linkable(int brperm) +{ + return !(brperm & AuBrWAttr_NoLinkWH); +} + +static inline int au_br_cmoo(int brperm) +{ + return brperm & AuBrAttr_CMOO_Mask; +} + +static inline int au_br_fhsm(int brperm) +{ + return brperm & AuBrAttr_FHSM; +} + +/* ---------------------------------------------------------------------- */ + +/* ioctl */ +enum { + /* readdir in userspace */ + AuCtl_RDU, + AuCtl_RDU_INO, + + AuCtl_WBR_FD, /* pathconf wrapper */ + AuCtl_IBUSY, /* busy inode */ + AuCtl_MVDOWN, /* move-down */ + AuCtl_BR, /* info about branches */ + AuCtl_FHSM_FD /* connection for fhsm */ +}; + +/* borrowed from linux/include/linux/kernel.h */ +#ifndef ALIGN +#ifdef _GNU_SOURCE +#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) +#else +#define ALIGN(x, a) (((x) + (a) - 1) & ~((a) - 1)) +#endif +#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) +#endif + +/* borrowed from linux/include/linux/compiler-gcc3.h */ +#ifndef __aligned +#define __aligned(x) __attribute__((aligned(x))) +#endif + +#ifdef __KERNEL__ +#ifndef __packed +#define __packed __attribute__((packed)) +#endif +#endif + +struct au_rdu_cookie { + uint64_t h_pos; + int16_t bindex; + uint8_t flags; + uint8_t pad; + uint32_t generation; +} __aligned(8); + +struct au_rdu_ent { + uint64_t ino; + int16_t bindex; + uint8_t type; + uint8_t nlen; + uint8_t wh; + char name[]; +} __aligned(8); + +static inline int au_rdu_len(int nlen) +{ + /* include the terminating NULL */ + return ALIGN(sizeof(struct au_rdu_ent) + nlen + 1, + sizeof(uint64_t)); +} + +union au_rdu_ent_ul { + struct au_rdu_ent __user *e; + uint64_t ul; +}; + +enum { + AufsCtlRduV_SZ, + AufsCtlRduV_End +}; + +struct aufs_rdu { + /* input */ + union { + uint64_t sz; /* AuCtl_RDU */ + uint64_t nent; /* AuCtl_RDU_INO */ + }; + union au_rdu_ent_ul ent; + uint16_t verify[AufsCtlRduV_End]; + + /* input/output */ + uint32_t blk; + + /* output */ + union au_rdu_ent_ul tail; + /* number of entries which were added in a single call */ + uint64_t rent; + uint8_t full; + uint8_t shwh; + + struct au_rdu_cookie cookie; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +/* dirren. the branch is identified by the filename who contains this */ +struct au_drinfo { + uint64_t ino; + union { + uint8_t oldnamelen; + uint64_t _padding; + }; + uint8_t oldname[]; +} __aligned(8); + +struct au_drinfo_fdata { + uint32_t magic; + struct au_drinfo drinfo; +} __aligned(8); + +#define AUFS_DRINFO_MAGIC_V1 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x01) +/* future */ +#define AUFS_DRINFO_MAGIC_V2 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x02) + +/* ---------------------------------------------------------------------- */ + +struct aufs_wbr_fd { + uint32_t oflags; + int16_t brid; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +struct aufs_ibusy { + uint64_t ino, h_ino; + int16_t bindex; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +/* error code for move-down */ +/* the actual message strings are implemented in aufs-util.git */ +enum { + EAU_MVDOWN_OPAQUE = 1, + EAU_MVDOWN_WHITEOUT, + EAU_MVDOWN_UPPER, + EAU_MVDOWN_BOTTOM, + EAU_MVDOWN_NOUPPER, + EAU_MVDOWN_NOLOWERBR, + EAU_Last +}; + +/* flags for move-down */ +#define AUFS_MVDOWN_DMSG 1 +#define AUFS_MVDOWN_OWLOWER (1 << 1) /* overwrite lower */ +#define AUFS_MVDOWN_KUPPER (1 << 2) /* keep upper */ +#define AUFS_MVDOWN_ROLOWER (1 << 3) /* do even if lower is RO */ +#define AUFS_MVDOWN_ROLOWER_R (1 << 4) /* did on lower RO */ +#define AUFS_MVDOWN_ROUPPER (1 << 5) /* do even if upper is RO */ +#define AUFS_MVDOWN_ROUPPER_R (1 << 6) /* did on upper RO */ +#define AUFS_MVDOWN_BRID_UPPER (1 << 7) /* upper brid */ +#define AUFS_MVDOWN_BRID_LOWER (1 << 8) /* lower brid */ +#define AUFS_MVDOWN_FHSM_LOWER (1 << 9) /* find fhsm attr for lower */ +#define AUFS_MVDOWN_STFS (1 << 10) /* req. stfs */ +#define AUFS_MVDOWN_STFS_FAILED (1 << 11) /* output: stfs is unusable */ +#define AUFS_MVDOWN_BOTTOM (1 << 12) /* output: no more lowers */ + +/* index for move-down */ +enum { + AUFS_MVDOWN_UPPER, + AUFS_MVDOWN_LOWER, + AUFS_MVDOWN_NARRAY +}; + +/* + * additional info of move-down + * number of free blocks and inodes. + * subset of struct kstatfs, but smaller and always 64bit. + */ +struct aufs_stfs { + uint64_t f_blocks; + uint64_t f_bavail; + uint64_t f_files; + uint64_t f_ffree; +}; + +struct aufs_stbr { + int16_t brid; /* optional input */ + int16_t bindex; /* output */ + struct aufs_stfs stfs; /* output when AUFS_MVDOWN_STFS set */ +} __aligned(8); + +struct aufs_mvdown { + uint32_t flags; /* input/output */ + struct aufs_stbr stbr[AUFS_MVDOWN_NARRAY]; /* input/output */ + int8_t au_errno; /* output */ +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +union aufs_brinfo { + /* PATH_MAX may differ between kernel-space and user-space */ + char _spacer[4096]; + struct { + int16_t id; + int perm; + char path[]; + }; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +#define AuCtlType 'A' +#define AUFS_CTL_RDU _IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu) +#define AUFS_CTL_RDU_INO _IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu) +#define AUFS_CTL_WBR_FD _IOW(AuCtlType, AuCtl_WBR_FD, \ + struct aufs_wbr_fd) +#define AUFS_CTL_IBUSY _IOWR(AuCtlType, AuCtl_IBUSY, struct aufs_ibusy) +#define AUFS_CTL_MVDOWN _IOWR(AuCtlType, AuCtl_MVDOWN, \ + struct aufs_mvdown) +#define AUFS_CTL_BRINFO _IOW(AuCtlType, AuCtl_BR, union aufs_brinfo) +#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int) + +#endif /* __AUFS_TYPE_H__ */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a3fd55194e0b..7bffadcfd6eb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1416,8 +1416,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if the *skb* task belongs to the cgroup2. - * * 1, if the *skb* task does not belong to the cgroup2. + * * 0, if current task belongs to the cgroup2. + * * 1, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h index a5773899f4d9..22794eb8d1a3 100644 --- a/include/uapi/linux/msdos_fs.h +++ b/include/uapi/linux/msdos_fs.h @@ -48,6 +48,7 @@ #define CASE_LOWER_BASE 8 /* base is lower case */ #define CASE_LOWER_EXT 16 /* extension is lower case */ +#define FAT_NO_83NAME 32 /* no 8.3 short filename for this file */ #define DELETED_FLAG 0xe5 /* marks file as deleted when in name[0] */ #define IS_FREE(n) (!*(n) || *(n) == DELETED_FLAG) diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f9701410d3b5..57a222014cd2 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -76,6 +76,7 @@ #define PCI_CACHE_LINE_SIZE 0x0c /* 8 bits */ #define PCI_LATENCY_TIMER 0x0d /* 8 bits */ #define PCI_HEADER_TYPE 0x0e /* 8 bits */ +#define PCI_HEADER_TYPE_MASK 0x7f #define PCI_HEADER_TYPE_NORMAL 0 #define PCI_HEADER_TYPE_BRIDGE 1 #define PCI_HEADER_TYPE_CARDBUS 2 diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..dc33e3051819 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1155,7 +1155,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ /* 1 free */ -#define PERF_MEM_SNOOPX_SHIFT 37 +#define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ diff --git a/include/video/uvesafb.h b/include/video/uvesafb.h index 8d2a3bfc8dac..f6cbd0d3c8ed 100644 --- a/include/video/uvesafb.h +++ b/include/video/uvesafb.h @@ -89,7 +89,9 @@ struct vbe_mode_ib { #define UVESAFB_DEFAULT_MODE "640x480-16" -/* How long to wait for a reply from userspace [ms] */ +/* How long to wait for a reply from userspace [ms] + * This is the default value of module param task_timeout + */ #define UVESAFB_TIMEOUT 5000 /* Max number of concurrent tasks */ diff --git a/init/do_mounts.c b/init/do_mounts.c index 29d326b6c29d..882307e6dd90 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -458,7 +458,9 @@ retry: printk("DEBUG_BLOCK_EXT_DEVT is enabled, you need to specify " "explicit textual name for \"root=\" boot option.\n"); #endif - panic("VFS: Unable to mount root fs on %s", b); + printk(KERN_EMERG "VFS: Unable to mount root fs on %s\n", b); + printk(KERN_EMERG "User configuration error - no valid root filesystem found\n"); + panic("Invalid configuration from end user prevents continuing"); } if (!(flags & SB_RDONLY)) { flags |= SB_RDONLY; @@ -471,7 +473,9 @@ retry: for (p = fs_names; *p; p += strlen(p)+1) printk(" %s", p); printk("\n"); - panic("VFS: Unable to mount root fs on %s", b); + printk(KERN_EMERG "VFS: Unable to mount root fs on %s\n", b); + printk(KERN_EMERG "User configuration error - no valid root filesystem found\n"); + panic("Invalid configuration from end user prevents continuing"); out: put_page(page); } diff --git a/init/init_task.c b/init/init_task.c index 15089d15010a..7802f91109b4 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -113,6 +113,9 @@ struct task_struct init_task .thread = INIT_THREAD, .fs = &init_fs, .files = &init_files, +#ifdef CONFIG_IO_URING + .io_uring = NULL, +#endif .signal = &init_signals, .sighand = &init_sighand, .nsproxy = &init_nsproxy, diff --git a/init/main.c b/init/main.c index e214cdd18c28..bf27d2045ea3 100644 --- a/init/main.c +++ b/init/main.c @@ -1463,6 +1463,18 @@ static int __ref kernel_init(void *unused) void console_on_rootfs(void) { +#ifndef CONFIG_BLK_DEV_INITRD + /* + * Use /dev/console to infer if the rootfs is setup properly. + * In case of initrd or initramfs /dev/console might be instantiated + * later by /init so don't do this check for CONFIG_BLK_DEV_INITRD + */ + if (vfs_lstat((char __user *) "/dev/console", (struct kstat __user *) &console_stat) + || !S_ISCHR(console_stat.mode)) { + panic("/dev/console is missing or not a character device!\nPlease ensure your rootfs is properly configured\n"); + } +#endif + /* Open the /dev/console as stdin, this should never fail */ if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) pr_err("Warning: unable to open an initial console.\n"); @@ -1474,6 +1486,9 @@ void console_on_rootfs(void) static noinline void __init kernel_init_freeable(void) { +#ifndef CONFIG_BLK_DEV_INITRD + struct kstat console_stat; +#endif /* * Wait until kthreadd is all set-up. */ diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index b367430e611c..3d897de89061 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -17,6 +17,8 @@ int pcpu_freelist_init(struct pcpu_freelist *s) raw_spin_lock_init(&head->lock); head->first = NULL; } + raw_spin_lock_init(&s->extralist.lock); + s->extralist.first = NULL; return 0; } @@ -40,12 +42,50 @@ static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } +static inline bool pcpu_freelist_try_push_extra(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + if (!raw_spin_trylock(&s->extralist.lock)) + return false; + + pcpu_freelist_push_node(&s->extralist, node); + raw_spin_unlock(&s->extralist.lock); + return true; +} + +static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + int cpu, orig_cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + struct pcpu_freelist_head *head; + + head = per_cpu_ptr(s->freelist, cpu); + if (raw_spin_trylock(&head->lock)) { + pcpu_freelist_push_node(head, node); + raw_spin_unlock(&head->lock); + return; + } + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + + /* cannot lock any per cpu lock, try extralist */ + if (cpu == orig_cpu && + pcpu_freelist_try_push_extra(s, node)) + return; + } +} + void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { - struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - - ___pcpu_freelist_push(head, node); + if (in_nmi()) + ___pcpu_freelist_push_nmi(s, node); + else + ___pcpu_freelist_push(this_cpu_ptr(s->freelist), node); } void pcpu_freelist_push(struct pcpu_freelist *s, @@ -81,7 +121,7 @@ again: } } -struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) +static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; @@ -102,8 +142,59 @@ struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) if (cpu >= nr_cpu_ids) cpu = 0; if (cpu == orig_cpu) - return NULL; + break; + } + + /* per cpu lists are all empty, try extralist */ + raw_spin_lock(&s->extralist.lock); + node = s->extralist.first; + if (node) + s->extralist.first = node->next; + raw_spin_unlock(&s->extralist.lock); + return node; +} + +static struct pcpu_freelist_node * +___pcpu_freelist_pop_nmi(struct pcpu_freelist *s) +{ + struct pcpu_freelist_head *head; + struct pcpu_freelist_node *node; + int orig_cpu, cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + head = per_cpu_ptr(s->freelist, cpu); + if (raw_spin_trylock(&head->lock)) { + node = head->first; + if (node) { + head->first = node->next; + raw_spin_unlock(&head->lock); + return node; + } + raw_spin_unlock(&head->lock); + } + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + if (cpu == orig_cpu) + break; } + + /* cannot pop from per cpu lists, try extralist */ + if (!raw_spin_trylock(&s->extralist.lock)) + return NULL; + node = s->extralist.first; + if (node) + s->extralist.first = node->next; + raw_spin_unlock(&s->extralist.lock); + return node; +} + +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) +{ + if (in_nmi()) + return ___pcpu_freelist_pop_nmi(s); + return ___pcpu_freelist_pop(s); } struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index fbf8a8a28979..3c76553cfe57 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -13,6 +13,7 @@ struct pcpu_freelist_head { struct pcpu_freelist { struct pcpu_freelist_head __percpu *freelist; + struct pcpu_freelist_head extralist; }; struct pcpu_freelist_node { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 89b07db14676..12eb9e47d101 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1470,6 +1470,10 @@ static int check_subprogs(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; + if (code == (BPF_JMP | BPF_CALL) && + insn[i].imm == BPF_FUNC_tail_call && + insn[i].src_reg != BPF_PSEUDO_CALL) + subprog[cur_subprog].has_tail_call = true; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) @@ -2951,6 +2955,31 @@ static int check_max_stack_depth(struct bpf_verifier_env *env) int ret_prog[MAX_CALL_FRAMES]; process_func: + /* protect against potential stack overflow that might happen when + * bpf2bpf calls get combined with tailcalls. Limit the caller's stack + * depth for such case down to 256 so that the worst case scenario + * would result in 8k stack size (32 which is tailcall limit * 256 = + * 8k). + * + * To get the idea what might happen, see an example: + * func1 -> sub rsp, 128 + * subfunc1 -> sub rsp, 256 + * tailcall1 -> add rsp, 256 + * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320) + * subfunc2 -> sub rsp, 64 + * subfunc22 -> sub rsp, 128 + * tailcall2 -> add rsp, 128 + * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416) + * + * tailcall will unwind the current stack frame but it will not get rid + * of caller's stack as shown on the example above. + */ + if (idx && subprog[idx].has_tail_call && depth >= 256) { + verbose(env, + "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n", + depth); + return -EACCES; + } /* round up to 32-bytes, since this is granularity * of interpreter stack size */ @@ -10862,6 +10891,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } if (prog->expected_attach_type == BPF_MODIFY_RETURN) { + if (tgt_prog) { + verbose(env, "can't modify return codes of BPF programs\n"); + ret = -EINVAL; + goto out; + } ret = check_attach_modify_return(prog, addr); if (ret) verbose(env, "%s() is not modifiable\n", diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 683a799618ad..bc827bd547c8 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -706,12 +706,16 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) size_avail = sizeof(kdb_buffer) - len; goto kdb_print_out; } - if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) + if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) { /* * This was a interactive search (using '/' at more - * prompt) and it has completed. Clear the flag. + * prompt) and it has completed. Replace the \0 with + * its original value to ensure multi-line strings + * are handled properly, and return to normal mode. */ + *cphold = replaced_byte; kdb_grepping_flag = 0; + } /* * at this point the string is a full line and * should be printed, up to the null. diff --git a/kernel/events/core.c b/kernel/events/core.c index fd8cd00099da..38eeb297255e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5852,11 +5852,11 @@ static void perf_pmu_output_stop(struct perf_event *event); static void perf_mmap_close(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; - struct perf_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; int mmap_locked = rb->mmap_locked; unsigned long size = perf_data_size(rb); + bool detach_rest = false; if (event->pmu->event_unmapped) event->pmu->event_unmapped(event, vma->vm_mm); @@ -5887,7 +5887,8 @@ static void perf_mmap_close(struct vm_area_struct *vma) mutex_unlock(&event->mmap_mutex); } - atomic_dec(&rb->mmap_count); + if (atomic_dec_and_test(&rb->mmap_count)) + detach_rest = true; if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) goto out_put; @@ -5896,7 +5897,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) mutex_unlock(&event->mmap_mutex); /* If there's still other mmap()s of this buffer, we're done. */ - if (atomic_read(&rb->mmap_count)) + if (!detach_rest) goto out_put; /* diff --git a/kernel/fork.c b/kernel/fork.c index efc5493203ae..09f376d90551 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -95,6 +95,7 @@ #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> +#include <linux/io_uring.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> @@ -570,7 +571,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; - get_file(file); + vma_get_file(tmp); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); i_mmap_lock_write(mapping); @@ -745,6 +746,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); @@ -1830,6 +1832,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk) free_task(tsk); } +static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) +{ + /* Skip if kernel thread */ + if (!tsk->mm) + return; + + /* Skip if spawning a thread or using vfork */ + if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) + return; + + /* We need to synchronize with __set_oom_adj */ + mutex_lock(&oom_adj_mutex); + set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); + /* Update the values in case they were changed after copy_signal */ + tsk->signal->oom_score_adj = current->signal->oom_score_adj; + tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; + mutex_unlock(&oom_adj_mutex); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -2003,6 +2024,10 @@ static __latent_entropy struct task_struct *copy_process( p->vtime.state = VTIME_INACTIVE; #endif +#ifdef CONFIG_IO_URING + p->io_uring = NULL; +#endif + #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif @@ -2310,6 +2335,8 @@ static __latent_entropy struct task_struct *copy_process( trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); + copy_oom_score_adj(clone_flags, p); + return p; bad_fork_cancel_cgroup: diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index a611dedac7d6..935265368a51 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -169,7 +169,7 @@ static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS); -static inline struct lock_class *hlock_class(struct held_lock *hlock) +inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock) { unsigned int class_idx = hlock->class_idx; @@ -190,6 +190,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) */ return lock_classes + class_idx; } +EXPORT_SYMBOL_GPL(lockdep_hlock_class); +#define hlock_class(hlock) lockdep_hlock_class(hlock) #ifdef CONFIG_LOCK_STAT static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats); diff --git a/kernel/module.c b/kernel/module.c index 08c46084d8cc..991395d60f59 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -91,8 +91,9 @@ EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); /* Work queue for freeing init sections in success case */ -static struct work_struct init_free_wq; -static struct llist_head init_free_list; +static void do_free_init(struct work_struct *w); +static DECLARE_WORK(init_free_wq, do_free_init); +static LLIST_HEAD(init_free_list); #ifdef CONFIG_MODULES_TREE_LOOKUP @@ -3551,14 +3552,6 @@ static void do_free_init(struct work_struct *w) } } -static int __init modules_wq_init(void) -{ - INIT_WORK(&init_free_wq, do_free_init); - init_llist_head(&init_free_list); - return 0; -} -module_init(modules_wq_init); - /* * This is where the real work happens. * diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 02ec716a4927..0e60e10ed66a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -851,17 +851,6 @@ static int software_resume(void) /* Check if the device is there */ swsusp_resume_device = name_to_dev_t(resume_file); - - /* - * name_to_dev_t is ineffective to verify parition if resume_file is in - * integer format. (e.g. major:minor) - */ - if (isdigit(resume_file[0]) && resume_wait) { - int partno; - while (!get_gendisk(swsusp_resume_device, &partno)) - msleep(10); - } - if (!swsusp_resume_device) { /* * Some device discovery might still be in progress; we need diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index efb792e13fca..23ec68d8ff3a 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -2154,9 +2154,20 @@ static int __init rcu_torture_fwd_prog_init(void) return -ENOMEM; spin_lock_init(&rfp->rcu_fwd_lock); rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head; + rcu_fwds = rfp; return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task); } +static void rcu_torture_fwd_prog_cleanup(void) +{ + struct rcu_fwd *rfp; + + torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); + rfp = rcu_fwds; + rcu_fwds = NULL; + kfree(rfp); +} + /* Callback function for RCU barrier testing. */ static void rcu_torture_barrier_cbf(struct rcu_head *rcu) { @@ -2360,7 +2371,7 @@ rcu_torture_cleanup(void) show_rcu_gp_kthreads(); rcu_torture_barrier_cleanup(); - torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); + rcu_torture_fwd_prog_cleanup(); torture_stop_kthread(rcu_torture_stall, stall_task); torture_stop_kthread(rcu_torture_writer, writer_task); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1e9e500ff790..572a79b1a851 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1882,7 +1882,7 @@ static void rcu_gp_fqs_loop(void) break; /* If time for quiescent-state forcing, do it. */ if (!time_after(rcu_state.jiffies_force_qs, jiffies) || - (gf & RCU_GP_FLAG_FQS)) { + (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) { trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqsstart")); rcu_gp_fqs(first_gp_fqs); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f788cd61df21..1c68621743ac 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -39,7 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) +#ifdef CONFIG_SCHED_DEBUG /* * Debugging: various feature bits * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6b3b59cc51d6..f3496556b699 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1550,7 +1550,7 @@ struct task_numa_env { static unsigned long cpu_load(struct rq *rq); static unsigned long cpu_util(int cpu); -static inline long adjust_numa_imbalance(int imbalance, int src_nr_running); +static inline long adjust_numa_imbalance(int imbalance, int nr_running); static inline enum numa_type numa_classify(unsigned int imbalance_pct, @@ -1927,7 +1927,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, src_running = env->src_stats.nr_running - 1; dst_running = env->dst_stats.nr_running + 1; imbalance = max(0, dst_running - src_running); - imbalance = adjust_numa_imbalance(imbalance, src_running); + imbalance = adjust_numa_imbalance(imbalance, dst_running); /* Use idle CPU if there is no imbalance */ if (!imbalance) { @@ -6067,7 +6067,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; @@ -6075,7 +6075,8 @@ static int select_idle_smt(struct task_struct *p, int target) return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr) || + !cpumask_test_cpu(cpu, sched_domain_span(sd))) continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; @@ -6091,7 +6092,7 @@ static inline int select_idle_core(struct task_struct *p, struct sched_domain *s return -1; } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -6266,7 +6267,7 @@ symmetric: if ((unsigned)i < nr_cpumask_bits) return i; - i = select_idle_smt(p, target); + i = select_idle_smt(p, sd, target); if ((unsigned)i < nr_cpumask_bits) return i; @@ -6586,7 +6587,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - spare_cap = cpu_cap - util; + spare_cap = cpu_cap; + lsub_positive(&spare_cap, util); /* * Skip CPUs that cannot satisfy the capacity request. @@ -8943,7 +8945,7 @@ next_group: } } -static inline long adjust_numa_imbalance(int imbalance, int src_nr_running) +static inline long adjust_numa_imbalance(int imbalance, int nr_running) { unsigned int imbalance_min; @@ -8952,7 +8954,7 @@ static inline long adjust_numa_imbalance(int imbalance, int src_nr_running) * tasks that remain local when the source domain is almost idle. */ imbalance_min = 2; - if (src_nr_running <= imbalance_min) + if (nr_running <= imbalance_min) return 0; return imbalance; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c82857e2e288..0b1485ac19c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1600,7 +1600,7 @@ enum { #undef SCHED_FEAT -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) +#ifdef CONFIG_SCHED_DEBUG /* * To support run-time toggling of sched features, all the translation units @@ -1608,6 +1608,7 @@ enum { */ extern const_debug unsigned int sysctl_sched_features; +#ifdef CONFIG_JUMP_LABEL #define SCHED_FEAT(name, enabled) \ static __always_inline bool static_branch_##name(struct static_key *key) \ { \ @@ -1620,7 +1621,13 @@ static __always_inline bool static_branch_##name(struct static_key *key) \ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) -#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */ +#else /* !CONFIG_JUMP_LABEL */ + +#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) + +#endif /* CONFIG_JUMP_LABEL */ + +#else /* !SCHED_DEBUG */ /* * Each translation unit has its own copy of sysctl_sched_features to allow @@ -1636,7 +1643,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features = #define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) -#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */ +#endif /* SCHED_DEBUG */ extern struct static_key_false sched_numa_balancing; extern struct static_key_false sched_schedstats; diff --git a/kernel/task_work.c b/kernel/task_work.c index 613b2d634af8..1dd58908215d 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -144,3 +144,4 @@ void task_work_run(void) } while (work); } } +EXPORT_SYMBOL_GPL(task_work_run); diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index c6cca0d1d584..c8892156db34 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -132,7 +132,7 @@ static int synth_field_string_size(char *type) start += sizeof("char[") - 1; end = strchr(type, ']'); - if (!end || end < start) + if (!end || end < start || type + strlen(type) > end + 1) return -EINVAL; len = end - start; @@ -465,6 +465,7 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, struct synth_field *field; const char *prefix = NULL, *field_type = argv[0], *field_name, *array; int len, ret = 0; + ssize_t size; if (field_type[0] == ';') field_type++; @@ -501,8 +502,14 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, if (field_type[0] == ';') field_type++; len = strlen(field_type) + 1; - if (array) - len += strlen(array); + + if (array) { + int l = strlen(array); + + if (l && array[l - 1] == ';') + l--; + len += l; + } if (prefix) len += strlen(prefix); @@ -520,11 +527,12 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, field->type[len - 1] = '\0'; } - field->size = synth_field_size(field->type); - if (!field->size) { + size = synth_field_size(field->type); + if (size <= 0) { ret = -EINVAL; goto free; } + field->size = size; if (synth_field_is_string(field->type)) field->is_string = true; diff --git a/lib/Kconfig b/lib/Kconfig index df3f3da95990..776145864937 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -631,7 +631,12 @@ config UACCESS_MEMCPY config ARCH_HAS_UACCESS_FLUSHCACHE bool -config ARCH_HAS_UACCESS_MCSAFE +# arch has a concept of a recoverable synchronous exception due to a +# memory-read error like x86 machine-check or ARM data-abort, and +# implements copy_mc_to_{user,kernel} to abort and report +# 'bytes-transferred' if that exception fires when accessing the source +# buffer. +config ARCH_HAS_COPY_MC bool # Temporary. Goes away when all archs are cleaned up diff --git a/lib/crc32.c b/lib/crc32.c index 4a20455d1f61..bf60ef26a45c 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -331,7 +331,7 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, return crc; } -#if CRC_LE_BITS == 1 +#if CRC_BE_BITS == 1 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) { return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); diff --git a/lib/idr.c b/lib/idr.c index c2cf2c52bbde..4d2eef0259d2 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -470,6 +470,7 @@ alloc: goto retry; nospc: xas_unlock_irqrestore(&xas, flags); + kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index bf538c2bec77..aefe46990543 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -636,30 +636,30 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) } EXPORT_SYMBOL(_copy_to_iter); -#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE -static int copyout_mcsafe(void __user *to, const void *from, size_t n) +#ifdef CONFIG_ARCH_HAS_COPY_MC +static int copyout_mc(void __user *to, const void *from, size_t n) { if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); - n = copy_to_user_mcsafe((__force void *) to, from, n); + n = copy_mc_to_user((__force void *) to, from, n); } return n; } -static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, +static unsigned long copy_mc_to_page(struct page *page, size_t offset, const char *from, size_t len) { unsigned long ret; char *to; to = kmap_atomic(page); - ret = memcpy_mcsafe(to + offset, from, len); + ret = copy_mc_to_kernel(to + offset, from, len); kunmap_atomic(to); return ret; } -static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, +static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; @@ -677,7 +677,7 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, size_t chunk = min_t(size_t, n, PAGE_SIZE - off); unsigned long rem; - rem = memcpy_mcsafe_to_page(pipe->bufs[i_head & p_mask].page, + rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk - rem; @@ -694,18 +694,17 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, } /** - * _copy_to_iter_mcsafe - copy to user with source-read error exception handling + * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @iter: destination iterator * - * The pmem driver arranges for filesystem-dax to use this facility via - * dax_copy_to_iter() for protecting read/write to persistent memory. - * Unless / until an architecture can guarantee identical performance - * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a - * performance regression to switch more users to the mcsafe version. + * The pmem driver deploys this for the dax operation + * (dax_copy_to_iter()) for dax reads (bypass page-cache and the + * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes + * successfully copied. * - * Otherwise, the main differences between this and typical _copy_to_iter(). + * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine @@ -716,23 +715,22 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. * Compare to copy_to_iter() where only ITER_IOVEC attempts might return * a short copy. - * - * See MCSAFE_TEST for self-test. */ -size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) +size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; if (unlikely(iov_iter_is_pipe(i))) - return copy_pipe_to_iter_mcsafe(addr, bytes, i); + return copy_mc_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, - copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), + copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len, + v.iov_len), ({ - rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset, - (from += v.bv_len) - v.bv_len, v.bv_len); + rem = copy_mc_to_page(v.bv_page, v.bv_offset, + (from += v.bv_len) - v.bv_len, v.bv_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; @@ -740,8 +738,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) } }), ({ - rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, - v.iov_len); + rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len) + - v.iov_len, v.iov_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; @@ -752,8 +750,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) return bytes; } -EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe); -#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */ +EXPORT_SYMBOL_GPL(_copy_mc_to_iter); +#endif /* CONFIG_ARCH_HAS_COPY_MC */ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { diff --git a/mm/Makefile b/mm/Makefile index 6e9d46b2efc9..a432b5664d83 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -52,7 +52,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ mm_init.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - debug.o gup.o $(mmu-y) + prfile.o debug.o gup.o $(mmu-y) # Give 'page_alloc' its own module-parameter namespace page-alloc-y := page_alloc.o diff --git a/mm/filemap.c b/mm/filemap.c index 385759c4ce4b..9fc8f1fbd38e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -826,10 +826,10 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask, - void **shadowp) +noinline int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); @@ -2676,7 +2676,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); - file_update_time(vmf->vma->vm_file); + vma_file_update_time(vmf->vma); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 74300e337c3c..358403422104 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2449,7 +2449,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, ClearPageCompound(head); - split_page_owner(head, HPAGE_PMD_ORDER); + split_page_owner(head, HPAGE_PMD_NR); /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 13f559af1ab6..6795bdf66256 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5276,7 +5276,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); - if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent)) + if (!(mc.flags & MOVE_ANON)) return NULL; /* @@ -5295,6 +5295,9 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, return page; } + if (non_swap_entry(ent)) + return NULL; + /* * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. diff --git a/mm/mmap.c b/mm/mmap.c index dcdab2675a21..8b60be664ed6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -179,7 +179,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); mpol_put(vma_policy(vma)); vm_area_free(vma); return next; @@ -910,7 +910,7 @@ again: if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); - fput(file); + vma_fput(vma); } if (next->anon_vma) anon_vma_merge(vma, next); @@ -1831,8 +1831,8 @@ out: return addr; unmap_and_free_vma: + vma_fput(vma); vma->vm_file = NULL; - fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); @@ -2694,7 +2694,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, goto out_free_mpol; if (new->vm_file) - get_file(new->vm_file); + vma_get_file(new); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); @@ -2713,7 +2713,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); if (new->vm_file) - fput(new->vm_file); + vma_fput(new); unlink_anon_vmas(new); out_free_mpol: mpol_put(vma_policy(new)); @@ -2906,7 +2906,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; - struct file *file; + struct file *file, *prfile; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", current->comm, current->pid); @@ -2981,10 +2981,27 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, } } - file = get_file(vma->vm_file); + vma_get_file(vma); + file = vma->vm_file; + prfile = vma->vm_prfile; ret = do_mmap_pgoff(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); + if (!IS_ERR_VALUE(ret) && file && prfile) { + struct vm_area_struct *new_vma; + + new_vma = find_vma(mm, ret); + if (!new_vma->vm_prfile) + new_vma->vm_prfile = prfile; + if (new_vma != vma) + get_file(prfile); + } + /* + * two fput()s instead of vma_fput(vma), + * coz vma may not be available anymore. + */ fput(file); + if (prfile) + fput(prfile); out: mmap_write_unlock(mm); if (populate) @@ -3276,7 +3293,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) - get_file(new_vma->vm_file); + vma_get_file(new_vma); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); diff --git a/mm/nommu.c b/mm/nommu.c index f32a69095d50..26cd21666185 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -540,7 +540,7 @@ static void __put_nommu_region(struct vm_region *region) up_write(&nommu_region_sem); if (region->vm_file) - fput(region->vm_file); + vmr_fput(region); /* IO memory and memory shared directly out of the pagecache * from ramfs/tmpfs mustn't be released here */ @@ -672,7 +672,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); put_nommu_region(vma->vm_region); vm_area_free(vma); } @@ -1195,7 +1195,7 @@ unsigned long do_mmap(struct file *file, goto error_just_free; } } - fput(region->vm_file); + vmr_fput(region); kmem_cache_free(vm_region_jar, region); region = pregion; result = start; @@ -1272,10 +1272,10 @@ error_just_free: up_write(&nommu_region_sem); error: if (region->vm_file) - fput(region->vm_file); + vmr_fput(region); kmem_cache_free(vm_region_jar, region); if (vma->vm_file) - fput(vma->vm_file); + vma_fput(vma); vm_area_free(vma); return ret; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 6e94962893ee..67e5bb0900b3 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -64,6 +64,8 @@ int sysctl_oom_dump_tasks = 1; * and mark_oom_victim */ DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); static inline bool is_memcg_oom(struct oom_control *oc) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 43f6d91f5715..8cc774340d49 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3213,7 +3213,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); - split_page_owner(page, order); + split_page_owner(page, 1 << order); } EXPORT_SYMBOL_GPL(split_page); @@ -3487,7 +3487,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } diff --git a/mm/page_owner.c b/mm/page_owner.c index 360461509423..4ca3051a1035 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(struct page *page, int reason) page_owner->last_migrate_reason = reason; } -void __split_page_owner(struct page *page, unsigned int order) +void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = lookup_page_ext(page); @@ -213,7 +213,7 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - for (i = 0; i < (1 << order); i++) { + for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); diff --git a/mm/prfile.c b/mm/prfile.c new file mode 100644 index 000000000000..00d51187c325 --- /dev/null +++ b/mm/prfile.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Mainly for aufs which mmap(2) different file and wants to print different + * path in /proc/PID/maps. + * Call these functions via macros defined in linux/mm.h. + * + * See Documentation/filesystems/aufs/design/06mmap.txt + * + * Copyright (c) 2014-2020 Junjro R. Okajima + * Copyright (c) 2014 Ian Campbell + */ + +#include <linux/mm.h> +#include <linux/file.h> +#include <linux/fs.h> + +/* #define PRFILE_TRACE */ +static inline void prfile_trace(struct file *f, struct file *pr, + const char func[], int line, const char func2[]) +{ +#ifdef PRFILE_TRACE + if (pr) + pr_info("%s:%d: %s, %pD2\n", func, line, func2, f); +#endif +} + +void vma_do_file_update_time(struct vm_area_struct *vma, const char func[], + int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + file_update_time(f); + if (f && pr) + file_update_time(pr); +} + +struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[], + int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + return (f && pr) ? pr : f; +} + +void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + get_file(f); + if (f && pr) + get_file(pr); +} + +void vma_do_fput(struct vm_area_struct *vma, const char func[], int line) +{ + struct file *f = vma->vm_file, *pr = vma->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + fput(f); + if (f && pr) + fput(pr); +} + +#ifndef CONFIG_MMU +struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[], + int line) +{ + struct file *f = region->vm_file, *pr = region->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + return (f && pr) ? pr : f; +} + +void vmr_do_fput(struct vm_region *region, const char func[], int line) +{ + struct file *f = region->vm_file, *pr = region->vm_prfile; + + prfile_trace(f, pr, func, line, __func__); + fput(f); + if (f && pr) + fput(pr); +} +#endif /* !CONFIG_MMU */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 26707c5dc9fc..605294e4df68 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3336,7 +3336,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; - goto bad_swap_unlock_inode; + goto free_swap_address_space; } mutex_lock(&swapon_mutex); @@ -3361,6 +3361,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; +free_swap_address_space: + exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index fc28dc201b93..131d29e902a3 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3280,6 +3280,16 @@ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, } } +static void hci_suspend_clear_tasks(struct hci_dev *hdev) +{ + int i; + + for (i = 0; i < __SUSPEND_NUM_TASKS; i++) + clear_bit(i, hdev->suspend_tasks); + + wake_up(&hdev->suspend_wait_q); +} + static int hci_suspend_wait_event(struct hci_dev *hdev) { #define WAKE_COND \ @@ -3608,6 +3618,7 @@ void hci_unregister_dev(struct hci_dev *hdev) cancel_work_sync(&hdev->power_on); + hci_suspend_clear_tasks(hdev); unregister_pm_notifier(&hdev->suspend_notifier); cancel_work_sync(&hdev->suspend_prepare); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index c7fc28a465fd..fa66e27b7363 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1521,8 +1521,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) parent = bt_sk(sk)->parent; - sock_set_flag(sk, SOCK_ZAPPED); - switch (chan->state) { case BT_OPEN: case BT_BOUND: @@ -1549,8 +1547,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) break; } - release_sock(sk); + + /* Only zap after cleanup to avoid use after free race */ + sock_set_flag(sk, SOCK_ZAPPED); + } static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 12a4f4d93681..3fda71a8579d 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -21,7 +21,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 0cad62a4052b..307790562b49 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 27443bf229a3..7dfbcdfc30e5 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN * 2)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index a8dd956b5e8e..916fdf2464bc 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -580,6 +580,7 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); @@ -1487,6 +1488,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); diff --git a/net/core/filter.c b/net/core/filter.c index 0261531d4fda..3e4de9e461bd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4323,7 +4323,8 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val; + sk->sk_max_pacing_rate = (val == ~0U) ? + ~0UL : (unsigned int)val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); break; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6a32a1fd34f8..053472c48354 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -662,15 +662,16 @@ static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, { int ret; + /* strparser clones the skb before handing it to a upper layer, + * meaning we have the same data, but sk is NULL. We do want an + * sk pointer though when we run the BPF program. So we set it + * here and then NULL it to ensure we don't trigger a BUG_ON() + * in skb/sk operations later if kfree_skb is called with a + * valid skb->sk pointer and no destructor assigned. + */ skb->sk = psock->sk; bpf_compute_data_end_sk_skb(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - /* strparser clones the skb before handing it to a upper layer, - * meaning skb_orphan has been called. We NULL sk on the way out - * to ensure we don't trigger a BUG_ON() in skb/sk operations - * later and because we are not charging the memory of this skb - * to any socket yet. - */ skb->sk = NULL; return ret; } @@ -795,7 +796,6 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - skb_orphan(skb); tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); diff --git a/net/core/sock.c b/net/core/sock.c index 78f8736be9c5..25968369fe7f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -777,7 +777,6 @@ static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); - sock_reset_flag(sk, SOCK_TSTAMP_NEW); } } @@ -1007,8 +1006,6 @@ set_sndbuf: __sock_set_timestamps(sk, valbool, true, true); break; case SO_TIMESTAMPING_NEW: - sock_set_flag(sk, SOCK_TSTAMP_NEW); - /* fall through */ case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; @@ -1037,16 +1034,14 @@ set_sndbuf: } sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else { - if (optname == SO_TIMESTAMPING_NEW) - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - + else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); - } break; case SO_RCVLOWAT: @@ -1189,7 +1184,7 @@ set_sndbuf: case SO_MAX_PACING_RATE: { - unsigned long ulval = (val == ~0U) ? ~0UL : val; + unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 687971d83b4e..09ed488cb9ff 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -895,7 +895,14 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ - override = time_after(jiffies, + /* + * If n->updated is after jiffies, then the clock has wrapped and + * we are *well* past the locktime, so set the override flag + */ + if (time_after(n->updated, jiffies)) + override = 1; + else + override = time_after(jiffies, n->updated + NEIGH_VAR(n->parms, LOCKTIME)) || is_garp; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e30515f89802..70a505a713a5 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -239,7 +239,7 @@ static struct { /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * - * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec. + * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Note: called with BH disabled */ @@ -267,7 +267,10 @@ bool icmp_global_allow(void) } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { - credit--; + /* We want to use a credit of one in average, but need to randomize + * it for security reasons. + */ + credit = max_t(int, credit - prandom_u32_max(3), 0); rc = true; } WRITE_ONCE(icmp_global.credit, credit); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 4e31f23e4117..e70291748889 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -625,9 +625,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - /* Need space for new headers */ - if (skb_cow_head(skb, dev->needed_headroom - - (tunnel->hlen + sizeof(struct iphdr)))) + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; @@ -748,7 +746,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; - dev->needed_headroom = dev->needed_headroom + len; + if (dev->header_ops) + dev->hard_header_len += len; + else + dev->needed_headroom += len; + if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); @@ -944,6 +946,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -987,10 +990,14 @@ static int ipgre_tunnel_init(struct net_device *dev) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } return ip_tunnel_init(dev); diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index 7a83f881efa9..136030ad2e54 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -43,16 +43,31 @@ static void dump_arp_packet(struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int nhoff) { - const struct arphdr *ah; - struct arphdr _arph; const struct arppayload *ap; struct arppayload _arpp; + const struct arphdr *ah; + unsigned int logflags; + struct arphdr _arph; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { nf_log_buf_add(m, "TRUNCATED"); return; } + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + if (logflags & NF_LOG_MACDECODE) { + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + } + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 0c72156130b6..d07583fac8f8 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -284,8 +284,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", ntohs(eth_hdr(skb)->h_proto)); return; default: diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 134e92382275..355c4499fa1b 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -842,7 +842,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ - synchronize_rcu(); + synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 37f128889474..71a9b11b7126 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2764,10 +2764,12 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (IS_ERR(rt)) return rt; - if (flp4->flowi4_proto) + if (flp4->flowi4_proto) { + flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); + } return rt; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 06a8242aa698..6dd7f44497ec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -483,6 +483,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, return true; if (tcp_rmem_pressure(sk)) return true; + if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss) + return true; } if (sk->sk_prot->stream_memory_read) return sk->sk_prot->stream_memory_read(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 518f04355fbf..6c7e98216946 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4790,7 +4790,8 @@ void tcp_data_ready(struct sock *sk) int avail = tp->rcv_nxt - tp->copied_seq; if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && - !sock_flag(sk, SOCK_DONE)) + !sock_flag(sk, SOCK_DONE) && + tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss) return; sk->sk_data_ready(sk); @@ -5716,6 +5717,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; + } else { + tcp_update_wl(tp, TCP_SKB_CB(skb)->seq); } __tcp_ack_snd_check(sk, 0); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 3c32dcb5fd8e..c0a0d41b6c37 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2617,8 +2617,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { + loff_t p = 0; + ipv6_route_seq_setup_walk(iter, net); - return ipv6_route_seq_next(seq, NULL, pos); + return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index da64550a5707..8210ff34ed9b 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); return; default: break; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 1079a07e43e4..d74cfec68547 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -709,7 +709,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, u16 brate; sband = ieee80211_get_sband(sta->sdata); - if (sband) { + WARN_ON_ONCE(sband && !sband->bitrates); + if (sband && sband->bitrates) { brate = sband->bitrates[rate->idx].bitrate; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 05e966f1609e..b93916c382cd 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2122,6 +2122,10 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); sband = local->hw.wiphy->bands[band]; + + if (WARN_ON_ONCE(!sband->bitrates)) + break; + brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) shift = 2; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8f940be42f98..430a9213a7bf 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -296,6 +296,7 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->mp_capable = 0; mp_opt->mp_join = 0; mp_opt->add_addr = 0; + mp_opt->ahmac = 0; mp_opt->rm_addr = 0; mp_opt->dss = 0; @@ -517,7 +518,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, return ret; } - if (subflow->use_64bit_ack) { + if (READ_ONCE(msk->use_64bit_ack)) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; opts->ext_copy.data_ack = msk->ack_seq; opts->ext_copy.ack64 = 1; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c6eeaf3e8dcb..4675a7bbebb1 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -199,6 +199,7 @@ struct mptcp_sock { u32 token; unsigned long flags; bool can_ack; + bool use_64bit_ack; /* Set when we received a 64-bit DSN */ spinlock_t join_list_lock; struct work_struct work; struct list_head conn_list; @@ -285,7 +286,6 @@ struct mptcp_subflow_context { data_avail : 1, rx_eof : 1, data_fin_tx_enable : 1, - use_64bit_ack : 1, /* Set when we received a 64-bit DSN */ can_ack : 1; /* only after processing the remote a key */ u64 data_fin_tx_seq; u32 remote_nonce; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3838a0b3a21f..2e145b53b81f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -682,12 +682,11 @@ static enum mapping_status get_mapping_status(struct sock *ssk) if (!mpext->dsn64) { map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, mpext->data_seq); - subflow->use_64bit_ack = 0; pr_debug("expanded seq=%llu", subflow->map_seq); } else { map_seq = mpext->data_seq; - subflow->use_64bit_ack = 1; } + WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { /* Allow replacing only with an identical map */ diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 412656c34f20..beeafa42aad7 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2471,6 +2471,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; + } else if (!len) { + /* No more commands with len == 0 below */ + ret = -EINVAL; + goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2547,9 +2551,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); - break; - default: - ret = -EINVAL; } out_unlock: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b00866d777fe..d2e5a8f644b8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -609,6 +609,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset_ct(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; } return ret; } @@ -649,6 +651,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -669,6 +673,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1926fd56df56..848b137151c2 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -541,13 +541,20 @@ static bool tcp_in_window(const struct nf_conn *ct, swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; - /* - * We haven't seen traffic in the other direction yet - * but we have to tweak window tracking to pass III - * and IV until that happens. - */ - if (receiver->td_maxwin == 0) + if (receiver->td_maxwin == 0) { + /* We haven't seen traffic in the other + * direction yet but we have to tweak window + * tracking to pass III and IV until that + * happens. + */ receiver->td_end = receiver->td_maxend = sack; + } else if (sack == receiver->td_end + 1) { + /* Likely a reply to a keepalive. + * Needed for III. + */ + receiver->td_end++; + } + } } else if (((state->state == TCP_CONNTRACK_SYN_SENT && dir == IP_CT_DIR_ORIGINAL) diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 2b01a151eaa8..a579e59ee5c5 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -19,6 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) skb_push(skb, skb->mac_len); skb->dev = dev; + skb->tstamp = 0; dev_queue_xmit(skb); } diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index ae5628ddbe6d..fd7c5f0f5c25 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -171,6 +171,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, } EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) +{ + u16 vid; + + if (!skb_vlan_tag_present(skb)) + return; + + vid = skb_vlan_tag_get(skb); + nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); +} +EXPORT_SYMBOL_GPL(nf_log_dump_vlan); + /* bridge and netdev logging families share this code. */ void nf_log_l2packet(struct net *net, u_int8_t pf, __be16 protocol, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 05059f620d41..fe51a7df4f52 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -295,7 +295,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); @@ -310,7 +310,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); @@ -2917,7 +2917,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index c7cf1cde46de..ce2387bfb5dc 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -37,7 +37,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) num_actions++; @@ -61,7 +61,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 3087e23297db..b77985986b24 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -138,6 +138,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, return; skb->dev = dev; + skb->tstamp = 0; neigh_xmit(neigh_table, dev, addr, skb); out: regs->verdict.code = verdict; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e894254c17d4..8709f3d4e7c4 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1217,7 +1217,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aa69fc4ce39d..3715b1261c6f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -722,13 +722,6 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } -static int tcf_action_destroy_1(struct tc_action *a, int bind) -{ - struct tc_action *actions[] = { a, NULL }; - - return tcf_action_destroy(actions, bind); -} - static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -1000,13 +993,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err < 0) goto err_mod; - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && - !rcu_access_pointer(a->goto_chain)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); - return ERR_PTR(-EINVAL); - } - if (!name && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 0eb4722cf7cd..1558126af0d4 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -156,11 +156,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, __be16 target_dst = target.dst.u.udp.port; if (target_src != tuple->src.u.udp.port) - tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.udp.port) - tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e298ec3b3c9e..ca026e2bf8d2 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -408,6 +408,7 @@ static void __exit mpls_cleanup_module(void) module_init(mpls_init_module); module_exit(mpls_cleanup_module); +MODULE_SOFTDEP("post: mpls_gso"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MPLS manipulation actions"); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 23cf8469a2e7..e167f0ddfbcd 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -458,7 +458,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, - key_id, 0); + key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 4619cb3cb0a8..aa2448253dba 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -650,12 +650,12 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) block_cb->indr.binder_type, &block->flow_block, tcf_block_shared(block), &extack); + rtnl_lock(); down_write(&block->cb_lock); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); - up_write(&block->cb_lock); - rtnl_lock(); tcf_block_unbind(block, &bo); + up_write(&block->cb_lock); rtnl_unlock(); } @@ -3707,7 +3707,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->gate.num_entries = tcf_gate_num_entries(act); err = tcf_gate_get_entries(entry, act); if (err) - goto err_out; + goto err_out_locked; } else { err = -EOPNOTSUPP; goto err_out_locked; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 84f82771cdf5..0c345e43a09a 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma, /* default uniform distribution */ if (dist == NULL) - return ((rnd % (2 * sigma)) + mu) - sigma; + return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; + + /* capping dist_jitter to the range acceptable by tabledist() */ + q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); + q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | @@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); + /* capping jitter to the range acceptable by tabledist() */ + q->jitter = min_t(s64, abs(q->jitter), INT_MAX); + return ret; get_table_failure: diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f82a2e599917..49696f464794 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1595,7 +1595,7 @@ out: return rc; } -#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index df5b0a6ea848..398f1d952135 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -233,8 +233,6 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, default: flow->type = SMC_LLC_FLOW_NONE; } - if (qentry == lgr->delayed_event) - lgr->delayed_event = NULL; smc_llc_flow_qentry_set(flow, qentry); spin_unlock_bh(&lgr->llc_flow_lock); return true; @@ -1590,13 +1588,12 @@ static void smc_llc_event_work(struct work_struct *work) struct smc_llc_qentry *qentry; if (!lgr->llc_flow_lcl.type && lgr->delayed_event) { - if (smc_link_usable(lgr->delayed_event->link)) { - smc_llc_event_handler(lgr->delayed_event); - } else { - qentry = lgr->delayed_event; - lgr->delayed_event = NULL; + qentry = lgr->delayed_event; + lgr->delayed_event = NULL; + if (smc_link_usable(qentry->link)) + smc_llc_event_handler(qentry); + else kfree(qentry); - } } again: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index c28051f7d217..653c31769440 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1104,9 +1104,9 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct gssp_in_token *in_token) { struct kvec *argv = &rqstp->rq_arg.head[0]; - unsigned int page_base, length; - int pages, i, res; - size_t inlen; + unsigned int length, pgto_offs, pgfrom_offs; + int pages, i, res, pgto, pgfrom; + size_t inlen, to_offs, from_offs; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) @@ -1134,17 +1134,24 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, memcpy(page_address(in_token->pages[0]), argv->iov_base, length); inlen -= length; - i = 1; - page_base = rqstp->rq_arg.page_base; + to_offs = length; + from_offs = rqstp->rq_arg.page_base; while (inlen) { - length = min_t(unsigned int, inlen, PAGE_SIZE); - memcpy(page_address(in_token->pages[i]), - page_address(rqstp->rq_arg.pages[i]) + page_base, + pgto = to_offs >> PAGE_SHIFT; + pgfrom = from_offs >> PAGE_SHIFT; + pgto_offs = to_offs & ~PAGE_MASK; + pgfrom_offs = from_offs & ~PAGE_MASK; + + length = min_t(unsigned int, inlen, + min_t(unsigned int, PAGE_SIZE - pgto_offs, + PAGE_SIZE - pgfrom_offs)); + memcpy(page_address(in_token->pages[pgto]) + pgto_offs, + page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); + to_offs += length; + from_offs += length; inlen -= length; - page_base = 0; - i++; } return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 38e7c3c8c4a9..e4f410084c74 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -637,10 +637,11 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - pageoff, remaining); - memcpy(dst, page_address(*ppages), len); + memcpy(dst, page_address(*ppages) + pageoff, len); remaining -= len; dst += len; pageoff = 0; + ppages++; } } diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 383f87bc1061..f69fb54821e6 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -108,6 +108,8 @@ static void tipc_bcbase_select_primary(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int all_dests = tipc_link_bc_peers(bb->link); + int max_win = tipc_link_max_win(bb->link); + int min_win = tipc_link_min_win(bb->link); int i, mtu, prim; bb->primary_bearer = INVALID_BEARER_ID; @@ -121,8 +123,12 @@ static void tipc_bcbase_select_primary(struct net *net) continue; mtu = tipc_bearer_mtu(net, i); - if (mtu < tipc_link_mtu(bb->link)) + if (mtu < tipc_link_mtu(bb->link)) { tipc_link_set_mtu(bb->link, mtu); + tipc_link_set_queue_limits(bb->link, + min_win, + max_win); + } bb->bcast_support &= tipc_bearer_bcast_support(net, i); if (bb->dests[i] < all_dests) continue; @@ -585,7 +591,7 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win) if (max_win > TIPC_MAX_LINK_WIN) return -EINVAL; tipc_bcast_lock(net); - tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win); + tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win); tipc_bcast_unlock(net); return 0; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index e366ec9a7e4d..c5896730e393 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -139,10 +139,7 @@ static int bearer_name_validate(const char *name, u32 if_len; /* copy bearer name & ensure length is OK */ - name_copy[TIPC_MAX_BEARER_NAME - 1] = 0; - /* need above in case non-Posix strncpy() doesn't pad with nulls */ - strncpy(name_copy, name, TIPC_MAX_BEARER_NAME); - if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0) + if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0) return 0; /* ensure all component parts of bearer name are present */ diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 2776a41e0dec..0d6297f75df1 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -150,11 +150,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; + *buf = NULL; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; - *buf = NULL; TIPC_SKB_CB(head)->tail = NULL; if (skb_is_nonlinear(head)) { skb_walk_frags(head, tail) { diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 0cbad566f281..f19416371bb9 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -418,14 +418,14 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; - int copy, rc = 0; + bool more = false; bool done = false; + int copy, rc = 0; long timeo; if (flags & @@ -492,9 +492,8 @@ handle_error: if (!size) { last_record: tls_push_record_flags = flags; - if (more) { - tls_ctx->pending_open_record_frags = - !!record->num_frags; + if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) { + more = true; break; } @@ -526,6 +525,8 @@ last_record: } } while (!done); + tls_ctx->pending_open_record_frags = more; + if (orig_size - size > 0) rc = orig_size - size; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4d7b25506722..47ab86ee192a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2355,7 +2355,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, * case we'll continue with more data in the next round, * but break unconditionally so unsplit data stops here. */ - state->split_start++; + if (state->split) + state->split_start++; + else + state->split_start = 0; break; case 9: if (rdev->wiphy.extended_capabilities && @@ -4683,16 +4686,14 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs, if (err) return err; - if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] || - !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) - return -EINVAL; - - he_obss_pd->min_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); - he_obss_pd->max_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); + if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]) + he_obss_pd->min_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); + if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + he_obss_pd->max_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); - if (he_obss_pd->min_offset >= he_obss_pd->max_offset) + if (he_obss_pd->min_offset > he_obss_pd->max_offset) return -EINVAL; he_obss_pd->enable = true; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index c91e91362a0c..0151bb0b2fc7 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -921,7 +921,7 @@ static void rx_drop_all(void) } } -static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) +static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) { u32 idx; unsigned int i; @@ -934,14 +934,14 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; tx_desc->len = PKT_SIZE; } xsk_ring_prod__submit(&xsk->tx, batch_size); xsk->outstanding_tx += batch_size; - frame_nb += batch_size; - frame_nb %= NUM_FRAMES; + *frame_nb += batch_size; + *frame_nb %= NUM_FRAMES; complete_tx_only(xsk, batch_size); } @@ -997,7 +997,7 @@ static void tx_only_all(void) } for (i = 0; i < num_socks; i++) - tx_only(xsks[i], frame_nb[i], batch_size); + tx_only(xsks[i], &frame_nb[i], batch_size); pkt_cnt += batch_size; diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c index a11bf6c5b53b..cd3f16a6f5ca 100644 --- a/samples/mic/mpssd/mpssd.c +++ b/samples/mic/mpssd/mpssd.c @@ -403,9 +403,9 @@ mic_virtio_copy(struct mic_info *mic, int fd, static inline unsigned _vring_size(unsigned int num, unsigned long align) { - return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) + return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) + align - 1) & ~(align - 1)) - + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num; + + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4); } /* diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh index aa68ec95620d..32448bc198a5 100755..100644 --- a/scripts/kconfig/mconf-cfg.sh +++ b/scripts/kconfig/mconf-cfg.sh @@ -4,6 +4,14 @@ PKG="ncursesw" PKG2="ncurses" +if [ "$CROSS_CURSES_LIB" != "" ]; then + echo libs=\'$CROSS_CURSES_LIB\' + if [ x"$CROSS_CURSES_INC" != x ]; then + echo cflags=\'$CROSS_CURSES_INC\' + fi + exit 0 +fi + if [ -n "$(command -v pkg-config)" ]; then if pkg-config --exists $PKG; then echo cflags=\"$(pkg-config --cflags $PKG)\" diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 69341b36f271..40332eb85307 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1995,7 +1995,7 @@ static void read_symbols(const char *modname) char *license; char *namespace; struct module *mod; - struct elf_info info = { }; + struct elf_info info = { .hdr = NULL }; Elf_Sym *sym; if (!parse_elf(&info, modname)) @@ -2496,7 +2496,7 @@ static int dump_sym(struct symbol *sym) static void write_dump(const char *fname) { - struct buffer buf = { }; + struct buffer buf = { NULL, 0, 0 }; struct symbol *symbol; const char *namespace; int n; @@ -2550,7 +2550,7 @@ struct dump_list { int main(int argc, char **argv) { struct module *mod; - struct buffer buf = { }; + struct buffer buf = { NULL, 0, 0 }; char *missing_namespace_deps = NULL; char *dump_write = NULL, *files_source = NULL; int opt; diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 6df3c9f8b2da..8277144298a0 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -202,8 +202,10 @@ EOF done if [ "$ARCH" != "um" ]; then - deploy_kernel_headers debian/linux-headers - create_package linux-headers-$version debian/linux-headers + if is_enabled CONFIG_MODULES; then + deploy_kernel_headers debian/linux-headers + create_package linux-headers-$version debian/linux-headers + fi deploy_libc_headers debian/linux-libc-dev create_package linux-libc-dev debian/linux-libc-dev diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index df1adbfb8ead..9342517778bf 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -183,13 +183,6 @@ Description: Linux kernel, version $version This package contains the Linux kernel, modules and corresponding other files, version: $version. -Package: $kernel_headers_packagename -Architecture: $debarch -Description: Linux kernel headers for $version on $debarch - This package provides kernel header files for $version on $debarch - . - This is useful for people who need to build external modules - Package: linux-libc-dev Section: devel Provides: linux-kernel-headers @@ -200,6 +193,18 @@ Description: Linux support headers for userspace development Multi-Arch: same EOF +if is_enabled CONFIG_MODULES; then +cat <<EOF >> debian/control + +Package: $kernel_headers_packagename +Architecture: $debarch +Description: Linux kernel headers for $version on $debarch + This package provides kernel header files for $version on $debarch + . + This is useful for people who need to build external modules +EOF +fi + if is_enabled CONFIG_DEBUG_INFO; then cat <<EOF >> debian/control diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 20f2efd57b11..bb709eda96cd 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -45,7 +45,7 @@ scm_version() # Check for git and a git repo. if test -z "$(git rev-parse --show-cdup 2>/dev/null)" && - head=$(git rev-parse --verify --short HEAD 2>/dev/null); then + head=$(git rev-parse --verify HEAD 2>/dev/null); then # If we are at a tagged commit (like "v2.6.30-rc6"), we ignore # it, because this version is defined in the top level Makefile. @@ -59,11 +59,22 @@ scm_version() fi # If we are past a tagged commit (like # "v2.6.30-rc5-302-g72357d5"), we pretty print it. - if atag="$(git describe 2>/dev/null)"; then - echo "$atag" | awk -F- '{printf("-%05d-%s", $(NF-1),$(NF))}' - - # If we don't have a tag at all we print -g{commitish}. + # + # Ensure the abbreviated sha1 has exactly 12 + # hex characters, to make the output + # independent of git version, local + # core.abbrev settings and/or total number of + # objects in the current repository - passing + # --abbrev=12 ensures a minimum of 12, and the + # awk substr() then picks the 'g' and first 12 + # hex chars. + if atag="$(git describe --abbrev=12 2>/dev/null)"; then + echo "$atag" | awk -F- '{printf("-%05d-%s", $(NF-1),substr($(NF),0,13))}' + + # If we don't have a tag at all we print -g{commitish}, + # again using exactly 12 hex chars. else + head="$(echo $head | cut -c1-12)" printf '%s%s' -g $head fi fi diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 0d36259b690d..e4b47759ba1c 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -181,6 +181,12 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, break; case EVM_IMA_XATTR_DIGSIG: case EVM_XATTR_PORTABLE_DIGSIG: + /* accept xattr with non-empty signature field */ + if (xattr_len <= sizeof(struct signature_v2_hdr)) { + evm_status = INTEGRITY_FAIL; + goto out; + } + hdr = (struct signature_v2_hdr *)xattr_data; digest.hdr.algo = hdr->hash_algo; rc = evm_calc_hash(dentry, xattr_name, xattr_value, diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 011c3c76af86..21989fa0c107 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -829,6 +829,8 @@ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, /* now accumulate with current aggregate */ rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); + if (rc != 0) + return rc; } /* * Extend cumulative digest over TPM registers 8-9, which contain diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index c1583d98c5e5..0b8f17570f21 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -531,6 +531,16 @@ int ima_file_hash(struct file *file, char *buf, size_t buf_size) return -EOPNOTSUPP; mutex_lock(&iint->mutex); + + /* + * ima_file_hash can be called when ima_collect_measurement has still + * not been called, we might not always have a hash. + */ + if (!iint->ima_hash) { + mutex_unlock(&iint->mutex); + return -EOPNOTSUPP; + } + if (buf) { size_t copied_size; diff --git a/security/security.c b/security/security.c index 70a7ad357bc6..d55b72977544 100644 --- a/security/security.c +++ b/security/security.c @@ -1092,6 +1092,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry) return 0; return call_int_hook(path_rmdir, 0, dir, dentry); } +EXPORT_SYMBOL_GPL(security_path_rmdir); int security_path_unlink(const struct path *dir, struct dentry *dentry) { @@ -1108,6 +1109,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry, return 0; return call_int_hook(path_symlink, 0, dir, dentry, old_name); } +EXPORT_SYMBOL_GPL(security_path_symlink); int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) @@ -1116,6 +1118,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir, return 0; return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); } +EXPORT_SYMBOL_GPL(security_path_link); int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, @@ -1143,6 +1146,7 @@ int security_path_truncate(const struct path *path) return 0; return call_int_hook(path_truncate, 0, path); } +EXPORT_SYMBOL_GPL(security_path_truncate); int security_path_chmod(const struct path *path, umode_t mode) { @@ -1150,6 +1154,7 @@ int security_path_chmod(const struct path *path, umode_t mode) return 0; return call_int_hook(path_chmod, 0, path, mode); } +EXPORT_SYMBOL_GPL(security_path_chmod); int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { @@ -1157,6 +1162,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } +EXPORT_SYMBOL_GPL(security_path_chown); int security_path_chroot(const struct path *path) { @@ -1257,6 +1263,7 @@ int security_inode_permission(struct inode *inode, int mask) return 0; return call_int_hook(inode_permission, 0, inode, mask); } +EXPORT_SYMBOL_GPL(security_inode_permission); int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { @@ -1449,6 +1456,7 @@ int security_file_permission(struct file *file, int mask) return fsnotify_perm(file, mask); } +EXPORT_SYMBOL_GPL(security_file_permission); int security_file_alloc(struct file *file) { diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index c8b9c0b315d8..250a92b18726 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -174,9 +174,12 @@ odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (snd_BUG_ON(!dp)) return -ENXIO; - mutex_lock(®ister_mutex); + if (cmd != SNDCTL_SEQ_SYNC && + mutex_lock_interruptible(®ister_mutex)) + return -ERESTARTSYS; rc = snd_seq_oss_ioctl(dp, cmd, arg); - mutex_unlock(®ister_mutex); + if (cmd != SNDCTL_SEQ_SYNC) + mutex_unlock(®ister_mutex); return rc; } diff --git a/sound/firewire/bebob/bebob_hwdep.c b/sound/firewire/bebob/bebob_hwdep.c index 45b740f44c45..c362eb38ab90 100644 --- a/sound/firewire/bebob/bebob_hwdep.c +++ b/sound/firewire/bebob/bebob_hwdep.c @@ -36,12 +36,11 @@ hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, } memset(&event, 0, sizeof(event)); + count = min_t(long, count, sizeof(event.lock_status)); if (bebob->dev_lock_changed) { event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS; event.lock_status.status = (bebob->dev_lock_count > 0); bebob->dev_lock_changed = false; - - count = min_t(long, count, sizeof(event.lock_status)); } spin_unlock_irq(&bebob->lock); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4c23b169ac67..cc51ef98752a 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1003,12 +1003,14 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt) azx_init_pci(chip); hda_intel_init_chip(chip, true); - if (status && from_rt) { - list_for_each_codec(codec, &chip->bus) - if (!codec->relaxed_resume && - (status & (1 << codec->addr))) - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); + if (from_rt) { + list_for_each_codec(codec, &chip->bus) { + if (codec->relaxed_resume) + continue; + + if (codec->forced_resume || (status & (1 << codec->addr))) + pm_request_resume(hda_codec_dev(codec)); + } } /* power down again for link-controlled chips */ diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c index 02cc682caa55..588059428d8f 100644 --- a/sound/pci/hda/hda_jack.c +++ b/sound/pci/hda/hda_jack.c @@ -275,6 +275,23 @@ int snd_hda_jack_detect_state_mst(struct hda_codec *codec, } EXPORT_SYMBOL_GPL(snd_hda_jack_detect_state_mst); +static struct hda_jack_callback * +find_callback_from_list(struct hda_jack_tbl *jack, + hda_jack_callback_fn func) +{ + struct hda_jack_callback *cb; + + if (!func) + return NULL; + + for (cb = jack->callback; cb; cb = cb->next) { + if (cb->func == func) + return cb; + } + + return NULL; +} + /** * snd_hda_jack_detect_enable_mst - enable the jack-detection * @codec: the HDA codec @@ -297,7 +314,10 @@ snd_hda_jack_detect_enable_callback_mst(struct hda_codec *codec, hda_nid_t nid, jack = snd_hda_jack_tbl_new(codec, nid, dev_id); if (!jack) return ERR_PTR(-ENOMEM); - if (func) { + + callback = find_callback_from_list(jack, func); + + if (func && !callback) { callback = kzalloc(sizeof(*callback), GFP_KERNEL); if (!callback) return ERR_PTR(-ENOMEM); diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 6dfa864d3fe7..a49c322bdbe9 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1065,6 +1065,7 @@ enum { QUIRK_R3DI, QUIRK_R3D, QUIRK_AE5, + QUIRK_AE7, }; #ifdef CONFIG_PCI @@ -1184,6 +1185,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0051, "Sound Blaster AE-5", QUIRK_AE5), + SND_PCI_QUIRK(0x1102, 0x0081, "Sound Blaster AE-7", QUIRK_AE7), {} }; @@ -4675,6 +4677,15 @@ static int ca0132_alt_select_in(struct hda_codec *codec) ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00); tmp = FLOAT_THREE; break; + case QUIRK_AE7: + ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00); + tmp = FLOAT_THREE; + chipio_set_conn_rate(codec, MEM_CONNID_MICIN2, + SR_96_000); + chipio_set_conn_rate(codec, MEM_CONNID_MICOUT2, + SR_96_000); + dspio_set_uint_param(codec, 0x80, 0x01, FLOAT_ZERO); + break; default: tmp = FLOAT_ONE; break; @@ -4720,6 +4731,14 @@ static int ca0132_alt_select_in(struct hda_codec *codec) case QUIRK_AE5: ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00); break; + case QUIRK_AE7: + ca0113_mmio_command_set(codec, 0x30, 0x28, 0x3f); + chipio_set_conn_rate(codec, MEM_CONNID_MICIN2, + SR_96_000); + chipio_set_conn_rate(codec, MEM_CONNID_MICOUT2, + SR_96_000); + dspio_set_uint_param(codec, 0x80, 0x01, FLOAT_ZERO); + break; default: break; } @@ -4729,7 +4748,10 @@ static int ca0132_alt_select_in(struct hda_codec *codec) if (ca0132_quirk(spec) == QUIRK_R3DI) chipio_set_conn_rate(codec, 0x0F, SR_96_000); - tmp = FLOAT_ZERO; + if (ca0132_quirk(spec) == QUIRK_AE7) + tmp = FLOAT_THREE; + else + tmp = FLOAT_ZERO; dspio_set_uint_param(codec, 0x80, 0x00, tmp); switch (ca0132_quirk(spec)) { diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 419f012b9853..0d3e996beede 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1989,22 +1989,25 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo, int pinctl; int err = 0; + mutex_lock(&spec->pcm_lock); if (hinfo->nid) { pcm_idx = hinfo_to_pcm_index(codec, hinfo); - if (snd_BUG_ON(pcm_idx < 0)) - return -EINVAL; + if (snd_BUG_ON(pcm_idx < 0)) { + err = -EINVAL; + goto unlock; + } cvt_idx = cvt_nid_to_cvt_index(codec, hinfo->nid); - if (snd_BUG_ON(cvt_idx < 0)) - return -EINVAL; + if (snd_BUG_ON(cvt_idx < 0)) { + err = -EINVAL; + goto unlock; + } per_cvt = get_cvt(spec, cvt_idx); - snd_BUG_ON(!per_cvt->assigned); per_cvt->assigned = 0; hinfo->nid = 0; azx_stream(get_azx_dev(substream))->stripe = 0; - mutex_lock(&spec->pcm_lock); snd_hda_spdif_ctls_unassign(codec, pcm_idx); clear_bit(pcm_idx, &spec->pcm_in_use); pin_idx = hinfo_to_pin_index(codec, hinfo); @@ -2034,10 +2037,11 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo, per_pin->setup = false; per_pin->channels = 0; mutex_unlock(&per_pin->lock); - unlock: - mutex_unlock(&spec->pcm_lock); } +unlock: + mutex_unlock(&spec->pcm_lock); + return err; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 601683e05ccc..e9593abd4e23 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1142,6 +1142,7 @@ static int alc_alloc_spec(struct hda_codec *codec, hda_nid_t mixer_nid) codec->single_adc_amp = 1; /* FIXME: do we need this for all Realtek codec models? */ codec->spdif_status_reset = 1; + codec->forced_resume = 1; codec->patch_ops = alc_patch_ops; err = alc_codec_rename_from_preset(codec); @@ -1921,6 +1922,8 @@ enum { ALC1220_FIXUP_CLEVO_P950, ALC1220_FIXUP_CLEVO_PB51ED, ALC1220_FIXUP_CLEVO_PB51ED_PINS, + ALC887_FIXUP_ASUS_AUDIO, + ALC887_FIXUP_ASUS_HMIC, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -2133,6 +2136,31 @@ static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec, alc_fixup_headset_mode_no_hp_mic(codec, fix, action); } +static void alc887_asus_hp_automute_hook(struct hda_codec *codec, + struct hda_jack_callback *jack) +{ + struct alc_spec *spec = codec->spec; + unsigned int vref; + + snd_hda_gen_hp_automute(codec, jack); + + if (spec->gen.hp_jack_present) + vref = AC_PINCTL_VREF_80; + else + vref = AC_PINCTL_VREF_HIZ; + snd_hda_set_pin_ctl(codec, 0x19, PIN_HP | vref); +} + +static void alc887_fixup_asus_jack(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + if (action != HDA_FIXUP_ACT_PROBE) + return; + snd_hda_set_pin_ctl_cache(codec, 0x1b, PIN_HP); + spec->gen.hp_automute_hook = alc887_asus_hp_automute_hook; +} + static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { .type = HDA_FIXUP_PINS, @@ -2390,6 +2418,20 @@ static const struct hda_fixup alc882_fixups[] = { .chained = true, .chain_id = ALC1220_FIXUP_CLEVO_PB51ED, }, + [ALC887_FIXUP_ASUS_AUDIO] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x15, 0x02a14150 }, /* use as headset mic, without its own jack detect */ + { 0x19, 0x22219420 }, + {} + }, + }, + [ALC887_FIXUP_ASUS_HMIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc887_fixup_asus_jack, + .chained = true, + .chain_id = ALC887_FIXUP_ASUS_AUDIO, + }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2423,6 +2465,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x13c2, "Asus A7M", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x1043, 0x1873, "ASUS W90V", ALC882_FIXUP_ASUS_W90V), SND_PCI_QUIRK(0x1043, 0x1971, "Asus W2JC", ALC882_FIXUP_ASUS_W2JC), + SND_PCI_QUIRK(0x1043, 0x2390, "Asus D700SA", ALC887_FIXUP_ASUS_HMIC), SND_PCI_QUIRK(0x1043, 0x835f, "Asus Eee 1601", ALC888_FIXUP_EEE1601), SND_PCI_QUIRK(0x1043, 0x84bc, "ASUS ET2700", ALC887_FIXUP_ASUS_BASS), SND_PCI_QUIRK(0x1043, 0x8691, "ASUS ROG Ranger VIII", ALC882_FIXUP_GPIO3), @@ -6245,6 +6288,7 @@ enum { ALC269_FIXUP_LEMOTE_A190X, ALC256_FIXUP_INTEL_NUC8_RUGGED, ALC255_FIXUP_XIAOMI_HEADSET_MIC, + ALC274_FIXUP_HP_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -7624,6 +7668,14 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC289_FIXUP_ASUS_GA401 }, + [ALC274_FIXUP_HP_MIC] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 }, + { } + }, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7775,6 +7827,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), + SND_PCI_QUIRK(0x103c, 0x874e, "HP", ALC274_FIXUP_HP_MIC), + SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), @@ -8100,6 +8154,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"}, {.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"}, {.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"}, + {.id = ALC274_FIXUP_HP_MIC, .name = "alc274-hp-mic-detect"}, {} }; #define ALC225_STANDARD_PINS \ @@ -9634,6 +9689,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), + SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x1043, 0x1080, "Asus UX501VW", ALC668_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 986a6308818b..2a8484f37496 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -539,6 +539,7 @@ config SND_SOC_CQ0093VC config SND_SOC_CROS_EC_CODEC tristate "codec driver for ChromeOS EC" depends on CROS_EC + select CRYPTO select CRYPTO_LIB_SHA256 help If you say yes here you will get support for the diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c index cf071121c839..531bf3204381 100644 --- a/sound/soc/codecs/tas2770.c +++ b/sound/soc/codecs/tas2770.c @@ -16,7 +16,6 @@ #include <linux/i2c.h> #include <linux/gpio.h> #include <linux/gpio/consumer.h> -#include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/firmware.h> #include <linux/regmap.h> @@ -57,7 +56,12 @@ static int tas2770_set_bias_level(struct snd_soc_component *component, TAS2770_PWR_CTRL_MASK, TAS2770_PWR_CTRL_ACTIVE); break; - + case SND_SOC_BIAS_STANDBY: + case SND_SOC_BIAS_PREPARE: + snd_soc_component_update_bits(component, + TAS2770_PWR_CTRL, + TAS2770_PWR_CTRL_MASK, TAS2770_PWR_CTRL_MUTE); + break; case SND_SOC_BIAS_OFF: snd_soc_component_update_bits(component, TAS2770_PWR_CTRL, @@ -135,23 +139,18 @@ static int tas2770_dac_event(struct snd_soc_dapm_widget *w, TAS2770_PWR_CTRL, TAS2770_PWR_CTRL_MASK, TAS2770_PWR_CTRL_MUTE); - if (ret) - goto end; break; case SND_SOC_DAPM_PRE_PMD: ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL, TAS2770_PWR_CTRL_MASK, TAS2770_PWR_CTRL_SHUTDOWN); - if (ret) - goto end; break; default: dev_err(tas2770->dev, "Not supported evevt\n"); return -EINVAL; } -end: if (ret < 0) return ret; @@ -243,6 +242,9 @@ static int tas2770_set_bitwidth(struct tas2770_priv *tas2770, int bitwidth) return -EINVAL; } + if (ret < 0) + return ret; + tas2770->channel_size = bitwidth; ret = snd_soc_component_update_bits(component, @@ -251,16 +253,15 @@ static int tas2770_set_bitwidth(struct tas2770_priv *tas2770, int bitwidth) TAS2770_TDM_CFG_REG5_50_MASK, TAS2770_TDM_CFG_REG5_VSNS_ENABLE | tas2770->v_sense_slot); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG6, TAS2770_TDM_CFG_REG6_ISNS_MASK | TAS2770_TDM_CFG_REG6_50_MASK, TAS2770_TDM_CFG_REG6_ISNS_ENABLE | tas2770->i_sense_slot); - -end: if (ret < 0) return ret; @@ -278,36 +279,35 @@ static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate) TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_48KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, TAS2770_TDM_CFG_REG0_31_44_1_48KHZ); - if (ret) - goto end; break; case 44100: ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_44_1KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, TAS2770_TDM_CFG_REG0_31_44_1_48KHZ); - if (ret) - goto end; break; case 96000: ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_48KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, @@ -318,8 +318,9 @@ static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate) TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_44_1KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, @@ -330,22 +331,22 @@ static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate) TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_48KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, TAS2770_TDM_CFG_REG0_31_176_4_192KHZ); - if (ret) - goto end; break; case 17640: ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_SMP_MASK, TAS2770_TDM_CFG_REG0_SMP_44_1KHZ); - if (ret) - goto end; + if (ret < 0) + return ret; + ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0, TAS2770_TDM_CFG_REG0_31_MASK, @@ -355,7 +356,6 @@ static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate) ret = -EINVAL; } -end: if (ret < 0) return ret; @@ -574,6 +574,8 @@ static int tas2770_codec_probe(struct snd_soc_component *component) tas2770->component = component; + tas2770_reset(tas2770); + return 0; } @@ -700,29 +702,28 @@ static int tas2770_parse_dt(struct device *dev, struct tas2770_priv *tas2770) rc = fwnode_property_read_u32(dev->fwnode, "ti,asi-format", &tas2770->asi_format); if (rc) { - dev_err(tas2770->dev, "Looking up %s property failed %d\n", - "ti,asi-format", rc); - goto end; + dev_info(tas2770->dev, "Property %s is missing setting default slot\n", + "ti,asi-format"); + tas2770->asi_format = 0; } rc = fwnode_property_read_u32(dev->fwnode, "ti,imon-slot-no", &tas2770->i_sense_slot); if (rc) { - dev_err(tas2770->dev, "Looking up %s property failed %d\n", - "ti,imon-slot-no", rc); - goto end; + dev_info(tas2770->dev, "Property %s is missing setting default slot\n", + "ti,imon-slot-no"); + tas2770->i_sense_slot = 0; } rc = fwnode_property_read_u32(dev->fwnode, "ti,vmon-slot-no", &tas2770->v_sense_slot); if (rc) { - dev_err(tas2770->dev, "Looking up %s property failed %d\n", - "ti,vmon-slot-no", rc); - goto end; + dev_info(tas2770->dev, "Property %s is missing setting default slot\n", + "ti,vmon-slot-no"); + tas2770->v_sense_slot = 2; } -end: - return rc; + return 0; } static int tas2770_i2c_probe(struct i2c_client *client, @@ -770,8 +771,6 @@ static int tas2770_i2c_probe(struct i2c_client *client, tas2770->channel_size = 0; tas2770->slot_width = 0; - tas2770_reset(tas2770); - result = tas2770_register_codec(tas2770); if (result) dev_err(tas2770->dev, "Register codec failed.\n"); @@ -780,13 +779,6 @@ end: return result; } -static int tas2770_i2c_remove(struct i2c_client *client) -{ - pm_runtime_disable(&client->dev); - return 0; -} - - static const struct i2c_device_id tas2770_i2c_id[] = { { "tas2770", 0}, { } @@ -807,7 +799,6 @@ static struct i2c_driver tas2770_i2c_driver = { .of_match_table = of_match_ptr(tas2770_of_match), }, .probe = tas2770_i2c_probe, - .remove = tas2770_i2c_remove, .id_table = tas2770_i2c_id, }; diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c index 03fb50175d87..a6273ccb8401 100644 --- a/sound/soc/codecs/tlv320adcx140.c +++ b/sound/soc/codecs/tlv320adcx140.c @@ -154,7 +154,7 @@ static const struct regmap_config adcx140_i2c_regmap = { }; /* Digital Volume control. From -100 to 27 dB in 0.5 dB steps */ -static DECLARE_TLV_DB_SCALE(dig_vol_tlv, -10000, 50, 0); +static DECLARE_TLV_DB_SCALE(dig_vol_tlv, -10050, 50, 0); /* ADC gain. From 0 to 42 dB in 1 dB steps */ static DECLARE_TLV_DB_SCALE(adc_tlv, 0, 100, 0); diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index d087f3b20b1d..50b66cf9ea8f 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -665,7 +665,7 @@ static int aic32x4_set_processing_blocks(struct snd_soc_component *component, } static int aic32x4_setup_clocks(struct snd_soc_component *component, - unsigned int sample_rate) + unsigned int sample_rate, unsigned int channels) { u8 aosr; u16 dosr; @@ -753,7 +753,9 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component, dosr); clk_set_rate(clocks[5].clk, - sample_rate * 32); + sample_rate * 32 * + channels); + return 0; } } @@ -775,7 +777,8 @@ static int aic32x4_hw_params(struct snd_pcm_substream *substream, u8 iface1_reg = 0; u8 dacsetup_reg = 0; - aic32x4_setup_clocks(component, params_rate(params)); + aic32x4_setup_clocks(component, params_rate(params), + params_channels(params)); switch (params_width(params)) { case 16: diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 519ca2e69637..18f62fde9253 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -2043,6 +2043,7 @@ int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, { struct wm_coeff_ctl *ctl; struct snd_kcontrol *kcontrol; + char ctl_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; int ret; ctl = wm_adsp_get_ctl(dsp, name, type, alg); @@ -2053,8 +2054,25 @@ int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, return -EINVAL; ret = wm_coeff_write_ctrl(ctl, buf, len); + if (ret) + return ret; + + if (ctl->flags & WMFW_CTL_FLAG_SYS) + return 0; + + if (dsp->component->name_prefix) + snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s", + dsp->component->name_prefix, ctl->name); + else + snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", + ctl->name); + + kcontrol = snd_soc_card_get_kcontrol(dsp->component->card, ctl_name); + if (!kcontrol) { + adsp_err(dsp, "Can't find kcontrol %s\n", ctl_name); + return -EINVAL; + } - kcontrol = snd_soc_card_get_kcontrol(dsp->component->card, ctl->name); snd_ctl_notify(dsp->component->card->snd_card, SNDRV_CTL_EVENT_MASK_VALUE, &kcontrol->id); diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 7031869a023a..211e29a73a41 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -694,7 +694,7 @@ static int fsl_sai_dai_probe(struct snd_soc_dai *cpu_dai) return 0; } -static struct snd_soc_dai_driver fsl_sai_dai = { +static struct snd_soc_dai_driver fsl_sai_dai_template = { .probe = fsl_sai_dai_probe, .playback = { .stream_name = "CPU-Playback", @@ -966,12 +966,15 @@ static int fsl_sai_probe(struct platform_device *pdev) return ret; } + memcpy(&sai->cpu_dai_drv, &fsl_sai_dai_template, + sizeof(fsl_sai_dai_template)); + /* Sync Tx with Rx as default by following old DT binding */ sai->synchronous[RX] = true; sai->synchronous[TX] = false; - fsl_sai_dai.symmetric_rates = 1; - fsl_sai_dai.symmetric_channels = 1; - fsl_sai_dai.symmetric_samplebits = 1; + sai->cpu_dai_drv.symmetric_rates = 1; + sai->cpu_dai_drv.symmetric_channels = 1; + sai->cpu_dai_drv.symmetric_samplebits = 1; if (of_find_property(np, "fsl,sai-synchronous-rx", NULL) && of_find_property(np, "fsl,sai-asynchronous", NULL)) { @@ -988,9 +991,9 @@ static int fsl_sai_probe(struct platform_device *pdev) /* Discard all settings for asynchronous mode */ sai->synchronous[RX] = false; sai->synchronous[TX] = false; - fsl_sai_dai.symmetric_rates = 0; - fsl_sai_dai.symmetric_channels = 0; - fsl_sai_dai.symmetric_samplebits = 0; + sai->cpu_dai_drv.symmetric_rates = 0; + sai->cpu_dai_drv.symmetric_channels = 0; + sai->cpu_dai_drv.symmetric_samplebits = 0; } if (of_find_property(np, "fsl,sai-mclk-direction-output", NULL) && @@ -1019,7 +1022,7 @@ static int fsl_sai_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, - &fsl_sai_dai, 1); + &sai->cpu_dai_drv, 1); if (ret) goto err_pm_disable; diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h index 6aba7d28f5f3..677ecfc1ec68 100644 --- a/sound/soc/fsl/fsl_sai.h +++ b/sound/soc/fsl/fsl_sai.h @@ -180,6 +180,7 @@ struct fsl_sai { unsigned int bclk_ratio; const struct fsl_sai_soc_data *soc_data; + struct snd_soc_dai_driver cpu_dai_drv; struct snd_dmaengine_dai_dma_data dma_params_rx; struct snd_dmaengine_dai_dma_data dma_params_tx; }; diff --git a/sound/soc/fsl/imx-es8328.c b/sound/soc/fsl/imx-es8328.c index 15a27a2cd0ca..fad1eb6253d5 100644 --- a/sound/soc/fsl/imx-es8328.c +++ b/sound/soc/fsl/imx-es8328.c @@ -145,13 +145,13 @@ static int imx_es8328_probe(struct platform_device *pdev) data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) { ret = -ENOMEM; - goto fail; + goto put_device; } comp = devm_kzalloc(dev, 3 * sizeof(*comp), GFP_KERNEL); if (!comp) { ret = -ENOMEM; - goto fail; + goto put_device; } data->dev = dev; @@ -182,12 +182,12 @@ static int imx_es8328_probe(struct platform_device *pdev) ret = snd_soc_of_parse_card_name(&data->card, "model"); if (ret) { dev_err(dev, "Unable to parse card name\n"); - goto fail; + goto put_device; } ret = snd_soc_of_parse_audio_routing(&data->card, "audio-routing"); if (ret) { dev_err(dev, "Unable to parse routing: %d\n", ret); - goto fail; + goto put_device; } data->card.num_links = 1; data->card.owner = THIS_MODULE; @@ -196,10 +196,12 @@ static int imx_es8328_probe(struct platform_device *pdev) ret = snd_soc_register_card(&data->card); if (ret) { dev_err(dev, "Unable to register: %d\n", ret); - goto fail; + goto put_device; } platform_set_drvdata(pdev, data); +put_device: + put_device(&ssi_pdev->dev); fail: of_node_put(ssi_np); of_node_put(codec_np); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index 13a48b0c35ae..11233c3aeadf 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -118,6 +118,19 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = { .driver_data = (void *)(SOF_RT5682_MCLK_EN | SOF_RT5682_SSP_CODEC(0)), }, + { + .callback = sof_rt5682_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Volteer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Terrador"), + }, + .driver_data = (void *)(SOF_RT5682_MCLK_EN | + SOF_RT5682_SSP_CODEC(0) | + SOF_SPEAKER_AMP_PRESENT | + SOF_MAX98373_SPEAKER_AMP_PRESENT | + SOF_RT5682_SSP_AMP(2) | + SOF_RT5682_NUM_HDMIDEV(4)), + }, {} }; diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index e00a4af29c13..f25da84f175a 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -209,21 +209,6 @@ static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream, return 0; } -static int lpass_cpu_daiops_hw_free(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai); - int ret; - - ret = regmap_write(drvdata->lpaif_map, - LPAIF_I2SCTL_REG(drvdata->variant, dai->driver->id), - 0); - if (ret) - dev_err(dai->dev, "error writing to i2sctl reg: %d\n", ret); - - return ret; -} - static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -304,7 +289,6 @@ const struct snd_soc_dai_ops asoc_qcom_lpass_cpu_dai_ops = { .startup = lpass_cpu_daiops_startup, .shutdown = lpass_cpu_daiops_shutdown, .hw_params = lpass_cpu_daiops_hw_params, - .hw_free = lpass_cpu_daiops_hw_free, .prepare = lpass_cpu_daiops_prepare, .trigger = lpass_cpu_daiops_trigger, }; diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 34f7fd1bab1c..693839deebfe 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -61,7 +61,7 @@ static int lpass_platform_pcmops_open(struct snd_soc_component *component, int ret, dma_ch, dir = substream->stream; struct lpass_pcm_data *data; - data = devm_kzalloc(soc_runtime->dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -118,6 +118,7 @@ static int lpass_platform_pcmops_close(struct snd_soc_component *component, if (v->free_dma_channel) v->free_dma_channel(drvdata, data->dma_ch); + kfree(data); return 0; } diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 6eaa00c21011..a5460155b3f6 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -592,6 +592,17 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr, k->info = snd_soc_bytes_info_ext; k->tlv.c = snd_soc_bytes_tlv_callback; + /* + * When a topology-based implementation abuses the + * control interface and uses bytes_ext controls of + * more than 512 bytes, we need to disable the size + * checks, otherwise accesses to such controls will + * return an -EINVAL error and prevent the card from + * being configured. + */ + if (IS_ENABLED(CONFIG_SND_CTL_VALIDATION) && sbe->max > 512) + k->access |= SNDRV_CTL_ELEM_ACCESS_SKIP_CHECK; + ext_ops = tplg->bytes_ext_ops; num_ops = tplg->bytes_ext_ops_count; for (i = 0; i < num_ops; i++) { diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c index 186eea105bb1..009938d45ddd 100644 --- a/sound/soc/sof/control.c +++ b/sound/soc/sof/control.c @@ -298,6 +298,10 @@ int snd_sof_bytes_ext_put(struct snd_kcontrol *kcontrol, const struct snd_ctl_tlv __user *tlvd = (const struct snd_ctl_tlv __user *)binary_data; + /* make sure we have at least a header */ + if (size < sizeof(struct snd_ctl_tlv)) + return -EINVAL; + /* * The beginning of bytes data contains a header from where * the length (as bytes) is needed to know the correct copy @@ -306,6 +310,13 @@ int snd_sof_bytes_ext_put(struct snd_kcontrol *kcontrol, if (copy_from_user(&header, tlvd, sizeof(const struct snd_ctl_tlv))) return -EFAULT; + /* make sure TLV info is consistent */ + if (header.length + sizeof(struct snd_ctl_tlv) > size) { + dev_err_ratelimited(scomp->dev, "error: inconsistent TLV, data %d + header %zu > %d\n", + header.length, sizeof(struct snd_ctl_tlv), size); + return -EINVAL; + } + /* be->max is coming from topology */ if (header.length > be->max) { dev_err_ratelimited(scomp->dev, "error: Bytes data size %d exceeds max %d.\n", diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 63ca920c8e6e..7152e6d1cf67 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1179,7 +1179,13 @@ void hda_machine_select(struct snd_sof_dev *sdev) mach = snd_soc_acpi_find_machine(desc->machines); if (mach) { - sof_pdata->tplg_filename = mach->sof_tplg_filename; + /* + * If tplg file name is overridden, use it instead of + * the one set in mach table + */ + if (!sof_pdata->tplg_filename) + sof_pdata->tplg_filename = mach->sof_tplg_filename; + sof_pdata->machine = mach; if (mach->link_mask) { diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index aa3532ba1434..f3a8140773db 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -35,8 +35,28 @@ static int sof_pci_debug; module_param_named(sof_pci_debug, sof_pci_debug, int, 0444); MODULE_PARM_DESC(sof_pci_debug, "SOF PCI debug options (0x0 all off)"); +static const char *sof_override_tplg_name; + #define SOF_PCI_DISABLE_PM_RUNTIME BIT(0) +static int sof_tplg_cb(const struct dmi_system_id *id) +{ + sof_override_tplg_name = id->driver_data; + return 1; +} + +static const struct dmi_system_id sof_tplg_table[] = { + { + .callback = sof_tplg_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Volteer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Terrador"), + }, + .driver_data = "sof-tgl-rt5682-ssp0-max98373-ssp2.tplg", + }, + {} +}; + static const struct dmi_system_id community_key_platforms[] = { { .ident = "Up Squared", @@ -347,6 +367,10 @@ static int sof_pci_probe(struct pci_dev *pci, sof_pdata->tplg_filename_prefix = sof_pdata->desc->default_tplg_path; + dmi_check_system(sof_tplg_table); + if (sof_override_tplg_name) + sof_pdata->tplg_filename = sof_override_tplg_name; + #if IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE) /* set callback to enable runtime_pm */ sof_pdata->sof_probe_complete = sof_pci_probe_complete; diff --git a/sound/usb/format.c b/sound/usb/format.c index 1b28d01d1f4c..3bfead393aa3 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -406,6 +406,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4242): /* Line6 Helix Rack */ case USB_ID(0x0e41, 0x4244): /* Line6 Helix LT */ case USB_ID(0x0e41, 0x4246): /* Line6 HX-Stomp */ + case USB_ID(0x0e41, 0x4247): /* Line6 Pod Go */ case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h deleted file mode 100644 index 2ccd588fbad4..000000000000 --- a/tools/arch/x86/include/asm/mcsafe_test.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MCSAFE_TEST_H_ -#define _MCSAFE_TEST_H_ - -.macro MCSAFE_TEST_CTL -.endm - -.macro MCSAFE_TEST_SRC reg count target -.endm - -.macro MCSAFE_TEST_DST reg count target -.endm -#endif /* _MCSAFE_TEST_H_ */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 45f8e1b02241..0b5b8ae56bd9 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -4,7 +4,6 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -187,117 +186,3 @@ SYM_FUNC_START(memcpy_orig) SYM_FUNC_END(memcpy_orig) .popsection - -#ifndef CONFIG_UML - -MCSAFE_TEST_CTL - -/* - * __memcpy_mcsafe - memory copy with machine check exception handling - * Note that we only catch machine checks when reading the source addresses. - * Writes to target are posted and don't generate machine checks. - */ -SYM_FUNC_START(__memcpy_mcsafe) - cmpl $8, %edx - /* Less than 8 bytes? Go to byte copy loop */ - jb .L_no_whole_words - - /* Check for bad alignment of source */ - testl $7, %esi - /* Already aligned */ - jz .L_8byte_aligned - - /* Copy one byte at a time until source is 8-byte aligned */ - movl %esi, %ecx - andl $7, %ecx - subl $8, %ecx - negl %ecx - subl %ecx, %edx -.L_read_leading_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes - MCSAFE_TEST_DST %rdi 1 .E_leading_bytes -.L_write_leading_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_leading_bytes - -.L_8byte_aligned: - movl %edx, %ecx - andl $7, %edx - shrl $3, %ecx - jz .L_no_whole_words - -.L_read_words: - movq (%rsi), %r8 - MCSAFE_TEST_SRC %rsi 8 .E_read_words - MCSAFE_TEST_DST %rdi 8 .E_write_words -.L_write_words: - movq %r8, (%rdi) - addq $8, %rsi - addq $8, %rdi - decl %ecx - jnz .L_read_words - - /* Any trailing bytes? */ -.L_no_whole_words: - andl %edx, %edx - jz .L_done_memcpy_trap - - /* Copy trailing bytes */ - movl %edx, %ecx -.L_read_trailing_bytes: - movb (%rsi), %al - MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes - MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes -.L_write_trailing_bytes: - movb %al, (%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .L_read_trailing_bytes - - /* Copy successful. Return zero */ -.L_done_memcpy_trap: - xorl %eax, %eax -.L_done: - ret -SYM_FUNC_END(__memcpy_mcsafe) -EXPORT_SYMBOL_GPL(__memcpy_mcsafe) - - .section .fixup, "ax" - /* - * Return number of bytes not copied for any failure. Note that - * there is no "tail" handling since the source buffer is 8-byte - * aligned and poison is cacheline aligned. - */ -.E_read_words: - shll $3, %ecx -.E_leading_bytes: - addl %edx, %ecx -.E_trailing_bytes: - mov %ecx, %eax - jmp .L_done - - /* - * For write fault handling, given the destination is unaligned, - * we handle faults on multi-byte writes with a byte-by-byte - * copy up to the write-protected page. - */ -.E_write_words: - shll $3, %ecx - addl %edx, %ecx - movl %ecx, %edx - jmp mcsafe_handle_tail - - .previous - - _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) - _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) - _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) - _ASM_EXTABLE(.L_write_words, .E_write_words) - _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) -#endif diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..1c2832e9f77d 100644 --- a/tools/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk @@ -1,4 +1,4 @@ -#!/bin/awk -f +#!/usr/bin/awk -f # SPDX-License-Identifier: GPL-2.0 # gen-insn-attr-x86.awk: Instruction attribute table generator # Written by Masami Hiramatsu <mhiramat@redhat.com> diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index e7818b44b48e..6e5c907680b1 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -38,8 +38,6 @@ FEATURE_TESTS_BASIC := \ get_current_dir_name \ gettid \ glibc \ - gtk2 \ - gtk2-infobar \ libbfd \ libcap \ libelf \ @@ -81,6 +79,8 @@ FEATURE_TESTS_EXTRA := \ compile-32 \ compile-x32 \ cplus-demangle \ + gtk2 \ + gtk2-infobar \ hello \ libbabeltrace \ libbfd-liberty \ @@ -110,7 +110,6 @@ FEATURE_DISPLAY ?= \ dwarf \ dwarf_getlocations \ glibc \ - gtk2 \ libbfd \ libcap \ libelf \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 93b590d81209..85d341e25eae 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -89,7 +89,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma + $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd $(OUTPUT)test-hello.bin: $(BUILD) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 5479e543b194..d2623992ccd6 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -78,14 +78,6 @@ # include "test-libslang.c" #undef main -#define main main_test_gtk2 -# include "test-gtk2.c" -#undef main - -#define main main_test_gtk2_infobar -# include "test-gtk2-infobar.c" -#undef main - #define main main_test_libbfd # include "test-libbfd.c" #undef main @@ -205,8 +197,6 @@ int main(int argc, char *argv[]) main_test_libelf_getshdrstrndx(); main_test_libunwind(); main_test_libslang(); - main_test_gtk2(argc, argv); - main_test_gtk2_infobar(argc, argv); main_test_libbfd(); main_test_backtrace(); main_test_libnuma(); diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 9f9002734e19..6cf3ce891f5c 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -67,6 +67,7 @@ #define __always_inline inline #endif +#undef __user #define __user #define __rcu #define __read_mostly diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a3fd55194e0b..7bffadcfd6eb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1416,8 +1416,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if the *skb* task belongs to the cgroup2. - * * 1, if the *skb* task does not belong to the cgroup2. + * * 0, if current task belongs to the cgroup2. + * * 1, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 236c91aff48f..3e71c2f69afe 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3677,6 +3677,36 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) return 0; } +static int init_map_slots(struct bpf_map *map) +{ + const struct bpf_map *targ_map; + unsigned int i; + int fd, err; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_map = map->init_slots[i]; + fd = bpf_map__fd(targ_map); + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", + map->name, i, targ_map->name, + fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", + map->name, i, targ_map->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { @@ -3719,28 +3749,11 @@ bpf_object__create_maps(struct bpf_object *obj) } if (map->init_slots_sz) { - for (j = 0; j < map->init_slots_sz; j++) { - const struct bpf_map *targ_map; - int fd; - - if (!map->init_slots[j]) - continue; - - targ_map = map->init_slots[j]; - fd = bpf_map__fd(targ_map); - err = bpf_map_update_elem(map->fd, &j, &fd, 0); - if (err) { - err = -errno; - pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, j, targ_map->name, - fd, err); - goto err_out; - } - pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", - map->name, j, targ_map->name, fd); + err = init_map_slots(map); + if (err < 0) { + zclose(map->fd); + goto err_out; } - zfree(&map->init_slots); - map->init_slots_sz = 0; } if (map->pin_path && !map->pinned) { @@ -5253,7 +5266,7 @@ retry_load: free(log_buf); goto retry_load; } - ret = -errno; + ret = errno ? -errno : -LIBBPF_ERRNO__LOAD; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("load bpf program failed: %s\n", cp); pr_perm_msg(ret); diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 6a875a0f01bb..233592c5a52c 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -45,6 +45,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, if (!evsel->own_cpus || evlist->has_user_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evlist->cpus); + } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->cpus); } else if (evsel->cpus != evsel->own_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->own_cpus); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 773e6c7ee5f9..0ed92c3b1926 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -548,8 +548,9 @@ static const char *uaccess_safe_builtin[] = { "__ubsan_handle_shift_out_of_bounds", /* misc */ "csum_partial_copy_generic", - "__memcpy_mcsafe", - "mcsafe_handle_tail", + "copy_mc_fragile", + "copy_mc_fragile_handle_tail", + "copy_mc_enhanced_fast_string", "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */ NULL }; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 513633809c81..c64de16b9769 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -709,19 +709,23 @@ ifndef NO_SLANG endif endif ifndef NO_SLANG - # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h + # Some releases like Fedora have /usr/include/slang/slang.h instead of /usr/include/slang.h + SLANG_INC ?= -idirafter =/usr/include/slang + CFLAGS += $(SLANG_INC) CFLAGS += -DHAVE_SLANG_SUPPORT EXTLIBS += -lslang $(call detected,CONFIG_SLANG) endif endif -ifndef NO_GTK2 +ifdef GTK2 FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) + $(call feature_check,gtk2) ifneq ($(feature-gtk2), 1) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); NO_GTK2 := 1 else + $(call feature_check,gtk2-infobar) ifeq ($(feature-gtk2-infobar), 1) GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT endif @@ -744,6 +748,7 @@ else FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) ifneq ($(feature-libperl), 1) + msg := $(warning libperl not found, disables Perl scripting support. Please install libperl-dev or perl-devel); CFLAGS += -DNO_LIBPERL NO_LIBPERL := 1 msg := $(warning Missing perl devel files. Disabling perl scripting support, please install perl-ExtUtils-Embed/libperl-dev); diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 86dbb51bb272..4660d3898948 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -48,7 +48,7 @@ include ../scripts/utilities.mak # # Define NO_SLANG if you do not want TUI support. # -# Define NO_GTK2 if you do not want GTK+ GUI support. +# Define GTK2 if you want GTK+ GUI support. # # Define NO_DEMANGLE if you do not want C++ symbol demangling. # @@ -384,7 +384,7 @@ ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif -ifndef NO_GTK2 +ifdef GTK2 ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so GTK_IN := $(OUTPUT)gtk-in.o endif @@ -876,7 +876,7 @@ check: $(OUTPUT)common-cmds.h ### Installation rules -ifndef NO_GTK2 +ifdef GTK2 install-gtk: $(OUTPUT)libperf-gtk.so $(call QUIET_INSTALL, 'GTK UI') \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ @@ -963,7 +963,7 @@ install-bin: install-tools install-tests install-traceevent-plugins install: install-bin try-install-man install-python_ext: - $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' + $(PYTHON_WORD) util/setup.py --quiet install --prefix='$(DESTDIR_SQ)/usr' # 'make install-doc' should call 'make -C Documentation install' $(INSTALL_DOC_TARGETS): diff --git a/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk b/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk index 1a29f6379bde..6285ff7158a5 100644 --- a/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk +++ b/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk @@ -1,4 +1,4 @@ -#!/bin/awk -f +#!/usr/bin/awk -f # SPDX-License-Identifier: GPL-2.0-only # gen-insn-x86-dat.awk: script to convert data for the insn-x86 test # Copyright (c) 2015, Intel Corporation. diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 768e408757a0..5352303518e1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -11,7 +11,6 @@ perf-y += epoll-ctl.o perf-y += synthesize.o perf-y += kallsyms-parse.o -perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index 31b53cc7d5bc..33f3f3230ae1 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -14,6 +14,19 @@ #include <linux/futex.h> /** + * SYS_futex is expected from system C library, + * in glibc (/usr/include/bits/syscall.h defines it in terms of of NR_futex) + * some newer 32bit architectures e.g. RISCV32 is using 64bit time_t from + * get go unlike other 32bit architectures in glibc, therefore it wont have + * NR_futex defined but just NR_futex_time64 this aliases it to NR_futex + * so that SYS_futex is then defined for rv32 +*/ + +#if !defined(SYS_futex) && defined(SYS_futex_time64) +#define SYS_futex SYS_futex_time64 +#endif + +/** * futex() - SYS_futex syscall wrapper * @uaddr: address of first futex * @op: futex op code diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c deleted file mode 100644 index 4130734dde84..000000000000 --- a/tools/perf/bench/mem-memcpy-x86-64-lib.c +++ /dev/null @@ -1,24 +0,0 @@ -/* - * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy - * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' - * happy. - */ -#include <linux/types.h> - -unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); - -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++, from++) { - /* - * Call the assembly routine back directly since - * memcpy_mcsafe() may silently fallback to memcpy. - */ - unsigned long rem = __memcpy_mcsafe(to, from, 1); - - if (rem) - break; - } - return len; -} diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 5797253b9700..1aa2bad26fc7 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -24,6 +24,7 @@ #include <string.h> #include <unistd.h> #include <sys/mman.h> +#include <inttypes.h> #include <sys/time.h> #include <sys/resource.h> #include <sys/wait.h> @@ -1193,7 +1194,7 @@ static void *worker_thread(void *__tdata) /* Check whether our max runtime timed out: */ if (g->p.nr_secs) { timersub(&stop, &start0, &diff); - if ((u32)diff.tv_sec >= g->p.nr_secs) { + if ((u32)diff.tv_sec >= (long int)g->p.nr_secs) { g->stop_work = true; break; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 6e2502de755a..6494383687f8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1963,8 +1963,10 @@ static void setup_system_wide(int forks) struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { - if (!counter->core.system_wide) + if (!counter->core.system_wide && + strcmp(counter->name, "duration_time")) { return; + } } if (evsel_list->core.nr_entries) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4cbb64edc998..83e8cd663b4e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1762,7 +1762,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) if (table == NULL) return -ENOMEM; - memset(table + trace->sctbl->syscalls.max_id, 0, (id - trace->sctbl->syscalls.max_id) * sizeof(*sc)); + // Need to memset from offset 0 and +1 members if brand new + if (trace->syscalls.table == NULL) + memset(table, 0, (id + 1) * sizeof(*sc)); + else + memset(table + trace->sctbl->syscalls.max_id + 1, 0, (id - trace->sctbl->syscalls.max_id) * sizeof(*sc)); trace->syscalls.table = table; trace->sctbl->syscalls.max_id = id; diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 05cf2af9e2c2..d09ec2f03071 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -60,7 +60,6 @@ static void library_status(void) STATUS(HAVE_DWARF_SUPPORT, dwarf); STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); STATUS(HAVE_GLIBC_SUPPORT, glibc); - STATUS(HAVE_GTK2_SUPPORT, gtk2); #ifndef HAVE_SYSCALL_TABLE_SUPPORT STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); #endif diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 74014033df60..3031e2850000 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PERF_PERF_H +#include <stdbool.h> + #define _PERF_PERF_H #include <stdbool.h> diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 0b7096847991..9a50a7b6b56d 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -5,6 +5,10 @@ * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com> */ +#ifdef __mips__ +#include <sgidefs.h> +#endif + #include <Python.h> #include "../../../util/trace-event.h" diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index a9599ab8c471..77398608ca48 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -74,7 +74,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, return 0; snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir, - attr->type, attr->config, fd); + attr->type, (unsigned long long)attr->config, fd); file = fopen(path, "w+"); if (!file) { @@ -83,7 +83,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, } if (fprintf(file, "[event-%d-%llu-%d]\n", - attr->type, attr->config, fd) < 0) { + attr->type, (unsigned long long)attr->config, fd) < 0) { perror("test attr - failed to write event file"); fclose(file); return -1; @@ -99,10 +99,10 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, /* struct perf_event_attr */ WRITE_ASS(type, PRIu32); WRITE_ASS(size, PRIu32); - WRITE_ASS(config, "llu"); - WRITE_ASS(sample_period, "llu"); - WRITE_ASS(sample_type, "llu"); - WRITE_ASS(read_format, "llu"); + __WRITE_ASS(config, "llu", (unsigned long long)attr->config); + __WRITE_ASS(sample_period, "llu", (unsigned long long)attr->sample_period); + __WRITE_ASS(sample_type, "llu", (unsigned long long)attr->sample_type); + __WRITE_ASS(read_format, "llu", (unsigned long long)attr->read_format); WRITE_ASS(disabled, "d"); WRITE_ASS(inherit, "d"); WRITE_ASS(pinned, "d"); @@ -133,10 +133,10 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, WRITE_ASS(use_clockid, "d"); WRITE_ASS(wakeup_events, PRIu32); WRITE_ASS(bp_type, PRIu32); - WRITE_ASS(config1, "llu"); - WRITE_ASS(config2, "llu"); - WRITE_ASS(branch_sample_type, "llu"); - WRITE_ASS(sample_regs_user, "llu"); + __WRITE_ASS(config1, "llu", (unsigned long long)attr->config1); + __WRITE_ASS(config2, "llu", (unsigned long long)attr->config2); + __WRITE_ASS(branch_sample_type, "llu", (unsigned long long)attr->branch_sample_type); + __WRITE_ASS(sample_regs_user, "llu", (unsigned long long)attr->sample_regs_user); WRITE_ASS(sample_stack_user, PRIu32); fclose(file); diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index cc9fbcedb364..988f4bbd8ca6 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -124,7 +124,7 @@ static int __event(bool is_x, void *addr, int sig) fd = sys_perf_event_open(&pe, 0, -1, -1, perf_event_open_cloexec_flag()); if (fd < 0) { - pr_debug("failed opening event %llx\n", pe.config); + pr_debug("failed opening event %llx\n", (unsigned long long)pe.config); return TEST_FAIL; } diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index eb4dbbddf4ff..07e4f0457f87 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -96,7 +96,7 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may fd = sys_perf_event_open(&pe, 0, -1, -1, perf_event_open_cloexec_flag()); if (fd < 0) { - pr_debug("failed opening event %llx\n", pe.config); + pr_debug("failed opening event %llx\n", (unsigned long long)pe.config); return TEST_FAIL; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 9357b5f62c27..bc88175e377c 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1071,6 +1071,8 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt, if (queue->tid == -1 || pt->have_sched_switch) { ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu); + if (ptq->tid == -1) + ptq->pid = -1; thread__zput(ptq->thread); } @@ -2561,10 +2563,8 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event, tid = sample->tid; } - if (tid == -1) { - pr_err("context_switch event has no tid\n"); - return -EINVAL; - } + if (tid == -1) + intel_pt_log("context_switch event has no tid\n"); intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n", cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time, diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index 21c216c40a3b..420c690a3c54 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -21,6 +21,7 @@ #define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP +#include <errno.h> #include "unwind.h" #include "libunwind-x86.h" #include <../../../../arch/x86/include/uapi/asm/perf_regs.h> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 739516fdf6e3..da28e69a2a25 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -19,6 +19,10 @@ * */ +#ifdef __mips__ +#include <sgidefs.h> +#endif + #include <Python.h> #include <inttypes.h> diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index a8ee5c4d41eb..50a390d87db2 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -23,7 +23,8 @@ #include "nfit_test.h" #include "../watermark.h" -#include <asm/mcsafe_test.h> +#include <asm/copy_mc_test.h> +#include <asm/mce.h> /* * Generate an NFIT table to describe the following topology: @@ -3052,7 +3053,7 @@ static struct platform_driver nfit_test_driver = { .id_table = nfit_test_id, }; -static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE))); +static char copy_mc_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE))); enum INJECT { INJECT_NONE, @@ -3060,7 +3061,7 @@ enum INJECT { INJECT_DST, }; -static void mcsafe_test_init(char *dst, char *src, size_t size) +static void copy_mc_test_init(char *dst, char *src, size_t size) { size_t i; @@ -3069,7 +3070,7 @@ static void mcsafe_test_init(char *dst, char *src, size_t size) src[i] = (char) i; } -static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src, +static bool copy_mc_test_validate(unsigned char *dst, unsigned char *src, size_t size, unsigned long rem) { size_t i; @@ -3090,12 +3091,12 @@ static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src, return true; } -void mcsafe_test(void) +void copy_mc_test(void) { char *inject_desc[] = { "none", "source", "destination" }; enum INJECT inj; - if (IS_ENABLED(CONFIG_MCSAFE_TEST)) { + if (IS_ENABLED(CONFIG_COPY_MC_TEST)) { pr_info("%s: run...\n", __func__); } else { pr_info("%s: disabled, skip.\n", __func__); @@ -3113,31 +3114,31 @@ void mcsafe_test(void) switch (inj) { case INJECT_NONE: - mcsafe_inject_src(NULL); - mcsafe_inject_dst(NULL); - dst = &mcsafe_buf[2048]; - src = &mcsafe_buf[1024 - i]; + copy_mc_inject_src(NULL); + copy_mc_inject_dst(NULL); + dst = ©_mc_buf[2048]; + src = ©_mc_buf[1024 - i]; expect = 0; break; case INJECT_SRC: - mcsafe_inject_src(&mcsafe_buf[1024]); - mcsafe_inject_dst(NULL); - dst = &mcsafe_buf[2048]; - src = &mcsafe_buf[1024 - i]; + copy_mc_inject_src(©_mc_buf[1024]); + copy_mc_inject_dst(NULL); + dst = ©_mc_buf[2048]; + src = ©_mc_buf[1024 - i]; expect = 512 - i; break; case INJECT_DST: - mcsafe_inject_src(NULL); - mcsafe_inject_dst(&mcsafe_buf[2048]); - dst = &mcsafe_buf[2048 - i]; - src = &mcsafe_buf[1024]; + copy_mc_inject_src(NULL); + copy_mc_inject_dst(©_mc_buf[2048]); + dst = ©_mc_buf[2048 - i]; + src = ©_mc_buf[1024]; expect = 512 - i; break; } - mcsafe_test_init(dst, src, 512); - rem = __memcpy_mcsafe(dst, src, 512); - valid = mcsafe_test_validate(dst, src, 512, expect); + copy_mc_test_init(dst, src, 512); + rem = copy_mc_fragile(dst, src, 512); + valid = copy_mc_test_validate(dst, src, 512, expect); if (rem == expect && valid) continue; pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n", @@ -3149,8 +3150,8 @@ void mcsafe_test(void) } } - mcsafe_inject_src(NULL); - mcsafe_inject_dst(NULL); + copy_mc_inject_src(NULL); + copy_mc_inject_dst(NULL); } static __init int nfit_test_init(void) @@ -3161,7 +3162,7 @@ static __init int nfit_test_init(void) libnvdimm_test(); acpi_nfit_test(); device_dax_test(); - mcsafe_test(); + copy_mc_test(); dax_pmem_test(); dax_pmem_core_test(); #ifdef CONFIG_DEV_DAX_PMEM_COMPAT diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 8995092d541e..3b796dd5e577 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -523,8 +523,27 @@ static void *ida_random_fn(void *arg) return NULL; } +static void *ida_leak_fn(void *arg) +{ + struct ida *ida = arg; + time_t s = time(NULL); + int i, ret; + + rcu_register_thread(); + + do for (i = 0; i < 1000; i++) { + ret = ida_alloc_range(ida, 128, 128, GFP_KERNEL); + if (ret >= 0) + ida_free(ida, 128); + } while (time(NULL) < s + 2); + + rcu_unregister_thread(); + return NULL; +} + void ida_thread_tests(void) { + DEFINE_IDA(ida); pthread_t threads[20]; int i; @@ -536,6 +555,16 @@ void ida_thread_tests(void) while (i--) pthread_join(threads[i], NULL); + + for (i = 0; i < ARRAY_SIZE(threads); i++) + if (pthread_create(&threads[i], NULL, ida_leak_fn, &ida)) { + perror("creating ida thread"); + exit(1); + } + + while (i--) + pthread_join(threads[i], NULL); + assert(ida_is_empty(&ida)); } void ida_tests(void) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 944ad4721c83..da14eaac71d0 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -311,7 +311,6 @@ extern const struct bench bench_rename_kretprobe; extern const struct bench bench_rename_rawtp; extern const struct bench bench_rename_fentry; extern const struct bench bench_rename_fexit; -extern const struct bench bench_rename_fmodret; extern const struct bench bench_trig_base; extern const struct bench bench_trig_tp; extern const struct bench bench_trig_rawtp; @@ -332,7 +331,6 @@ static const struct bench *benchs[] = { &bench_rename_rawtp, &bench_rename_fentry, &bench_rename_fexit, - &bench_rename_fmodret, &bench_trig_base, &bench_trig_tp, &bench_trig_rawtp, @@ -462,4 +460,3 @@ int main(int argc, char **argv) return 0; } - diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index e74cff40f4fe..a967674098ad 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -106,12 +106,6 @@ static void setup_fexit() attach_bpf(ctx.skel->progs.prog5); } -static void setup_fmodret() -{ - setup_ctx(); - attach_bpf(ctx.skel->progs.prog6); -} - static void *consumer(void *input) { return NULL; @@ -182,14 +176,3 @@ const struct bench bench_rename_fexit = { .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, }; - -const struct bench bench_rename_fmodret = { - .name = "rename-fmodret", - .validate = validate, - .setup = setup_fmodret, - .producer_thread = producer, - .consumer_thread = consumer, - .measure = measure, - .report_progress = hits_drops_report_progress, - .report_final = hits_drops_report_final, -}; diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 47fa04adc147..21c2d265c3e8 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -265,7 +265,7 @@ void test_sk_assign(void) TEST("ipv6 udp port redir", AF_INET6, SOCK_DGRAM, false), TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true), }; - int server = -1; + __s64 server = -1; int server_map; int self_net; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 5f54c6aec7f0..b25c9c45c148 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -45,9 +45,9 @@ static int getsetsockopt(void) goto err; } - if (*(int *)big_buf != 0x08) { + if (*big_buf != 0x08) { log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08", - *(int *)big_buf); + (int)*big_buf); goto err; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index 2702df2b2343..9966685866fd 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -61,10 +61,9 @@ void test_test_overhead(void) const char *raw_tp_name = "raw_tp/task_rename"; const char *fentry_name = "fentry/__set_task_comm"; const char *fexit_name = "fexit/__set_task_comm"; - const char *fmodret_name = "fmod_ret/__set_task_comm"; const char *kprobe_func = "__set_task_comm"; struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog; - struct bpf_program *fentry_prog, *fexit_prog, *fmodret_prog; + struct bpf_program *fentry_prog, *fexit_prog; struct bpf_object *obj; struct bpf_link *link; int err, duration = 0; @@ -97,11 +96,6 @@ void test_test_overhead(void) if (CHECK(!fexit_prog, "find_probe", "prog '%s' not found\n", fexit_name)) goto cleanup; - fmodret_prog = bpf_object__find_program_by_title(obj, fmodret_name); - if (CHECK(!fmodret_prog, "find_probe", - "prog '%s' not found\n", fmodret_name)) - goto cleanup; - err = bpf_object__load(obj); if (CHECK(err, "obj_load", "err %d\n", err)) goto cleanup; @@ -148,12 +142,6 @@ void test_test_overhead(void) test_run("fexit"); bpf_link__destroy(link); - /* attach fmod_ret */ - link = bpf_program__attach_trace(fmodret_prog); - if (CHECK(IS_ERR(link), "attach fmod_ret", "err %ld\n", PTR_ERR(link))) - goto cleanup; - test_run("fmod_ret"); - bpf_link__destroy(link); cleanup: prctl(PR_SET_NAME, comm, 0L, 0L, 0L); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 42403d088abc..abb7344b531f 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -39,10 +39,4 @@ int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) return 0; } -SEC("fmod_ret/__set_task_comm") -int BPF_PROG(prog6, struct task_struct *tsk, const char *buf, bool exec) -{ - return !tsk; -} - char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c index 458b0d69133e..553a282d816a 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -18,11 +18,11 @@ #define MAX_ULONG_STR_LEN 7 #define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) +const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) { - volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; unsigned char i; - char name[64]; + char name[sizeof(tcp_mem_name)]; int ret; memset(name, 0, sizeof(name)); diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c index b2e6f9b0894d..2b64bc563a12 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -18,11 +18,11 @@ #define MAX_ULONG_STR_LEN 7 #define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) +const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx) { - volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; unsigned char i; - char name[64]; + char name[sizeof(tcp_mem_name)]; int ret; memset(name, 0, sizeof(name)); diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index 5611b564d3b1..f54b2293c490 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -19,12 +19,14 @@ SEC("tp/syscalls/sys_enter_nanosleep") int handle__tp(struct trace_event_raw_sys_enter *args) { struct __kernel_timespec *ts; + long tv_nsec; if (args->id != __NR_nanosleep) return 0; ts = (void *)args->args[0]; - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; tp_called = true; @@ -35,12 +37,14 @@ SEC("raw_tp/sys_enter") int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) { struct __kernel_timespec *ts; + long tv_nsec; if (id != __NR_nanosleep) return 0; ts = (void *)PT_REGS_PARM1_CORE(regs); - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; raw_tp_called = true; @@ -51,12 +55,14 @@ SEC("tp_btf/sys_enter") int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) { struct __kernel_timespec *ts; + long tv_nsec; if (id != __NR_nanosleep) return 0; ts = (void *)PT_REGS_PARM1_CORE(regs); - if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || + tv_nsec != MY_TV_NSEC) return 0; tp_btf_called = true; diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc index 7449a4b8f1f9..9098f1e7433f 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc @@ -25,12 +25,12 @@ echo 'wakeup_latency u64 lat pid_t pid' >> synthetic_events echo 'hist:keys=pid:ts1=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts1:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid) if next_comm=="ping"' > events/sched/sched_switch/trigger -echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events -echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger -echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger +echo 'waking_plus_wakeup_latency u64 lat; pid_t pid' >> synthetic_events +echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking_plus_wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger +echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking_plus_wakeup_latency/trigger ping $LOCALHOST -c 3 -if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then +if ! grep -q "pid:" events/synthetic/waking_plus_wakeup_latency/hist; then fail "Failed to create combined histogram" fi diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index 8383eb89d88a..bb7a1775307b 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -82,7 +82,7 @@ dmesg > "$DMESG" ($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true # Record and dump the results -dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true +dmesg | comm --nocheck-order -13 "$DMESG" - > "$LOG" || true cat "$LOG" # Check for expected output diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3b42c06b5985..c5e50ab2ced6 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -31,3 +31,4 @@ CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_NETEM=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_KALLSYMS=y +CONFIG_NET_FOU=m diff --git a/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh b/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh index a0b5f57d6bd3..0727e2012b68 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_asymmetric.sh @@ -215,10 +215,16 @@ switch_create() bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.vlan10-v.rp_filter 0 + sysctl_set net.ipv4.conf.vlan20-v.rp_filter 0 } switch_destroy() { + sysctl_restore net.ipv4.conf.all.rp_filter + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 20 bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 10 @@ -359,6 +365,10 @@ ns_switch_create() bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.vlan10-v.rp_filter 0 + sysctl_set net.ipv4.conf.vlan20-v.rp_filter 0 } export -f ns_switch_create diff --git a/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh b/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh index 1209031bc794..5d97fa347d75 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_symmetric.sh @@ -237,10 +237,16 @@ switch_create() bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.vlan10-v.rp_filter 0 + sysctl_set net.ipv4.conf.vlan20-v.rp_filter 0 } switch_destroy() { + sysctl_restore net.ipv4.conf.all.rp_filter + bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 20 bridge fdb del 00:00:5e:00:01:01 dev br1 self local vlan 10 @@ -402,6 +408,10 @@ ns_switch_create() bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 10 bridge fdb add 00:00:5e:00:01:01 dev br1 self local vlan 20 + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.vlan10-v.rp_filter 0 + sysctl_set net.ipv4.conf.vlan20-v.rp_filter 0 } export -f ns_switch_create diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index acf02e156d20..ed163e4ad434 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -421,9 +421,9 @@ do_transfer() duration=$(printf "(duration %05sms)" $duration) if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2 - echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2 + echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port" - echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2 + echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port" cat "$capout" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dd42c2f692d0..9cb0c6af326b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -167,9 +167,9 @@ do_transfer() if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then echo " client exit code $retc, server $rets" 1>&2 - echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2 + echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port" - echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2 + echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port" cat "$capout" diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index bdbf4b3125b6..28ea3753da20 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -521,6 +521,11 @@ kci_test_encap_fou() return $ksft_skip fi + if ! /sbin/modprobe -q -n fou; then + echo "SKIP: module fou is not found" + return $ksft_skip + fi + /sbin/modprobe -q fou ip -netns "$testns" fou add port 7777 ipproto 47 2>/dev/null if [ $? -ne 0 ];then echo "FAIL: can't add fou port 7777, skipping test" diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index ddaf140b8255..994b11af765c 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -12,4 +12,4 @@ memcpy_p7_t1 copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 -memcpy_mcsafe_64 +copy_mc_64 diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 0917983a1c78..3095b1f1c02b 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -12,7 +12,7 @@ ASFLAGS = $(CFLAGS) -Wa,-mpower4 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ copyuser_p7_t0 copyuser_p7_t1 \ memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \ - memcpy_p7_t0 memcpy_p7_t1 memcpy_mcsafe_64 \ + memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \ copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 EXTRA_SOURCES := validate.c ../harness.c stubs.S @@ -45,9 +45,9 @@ $(OUTPUT)/memcpy_p7_t%: memcpy_power7.S $(EXTRA_SOURCES) -D SELFTEST_CASE=$(subst memcpy_p7_t,,$(notdir $@)) \ -o $@ $^ -$(OUTPUT)/memcpy_mcsafe_64: memcpy_mcsafe_64.S $(EXTRA_SOURCES) +$(OUTPUT)/copy_mc_64: copy_mc_64.S $(EXTRA_SOURCES) $(CC) $(CPPFLAGS) $(CFLAGS) \ - -D COPY_LOOP=test_memcpy_mcsafe \ + -D COPY_LOOP=test_copy_mc_generic \ -o $@ $^ $(OUTPUT)/copyuser_64_exc_t%: copyuser_64.S exc_validate.c ../harness.c \ diff --git a/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S new file mode 100644 index 000000000000..88d46c471493 --- /dev/null +++ b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S @@ -0,0 +1,242 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) IBM Corporation, 2011 + * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com> + * Author - Balbir Singh <bsingharora@gmail.com> + */ +#include <asm/ppc_asm.h> +#include <asm/errno.h> +#include <asm/export.h> + + .macro err1 +100: + EX_TABLE(100b,.Ldo_err1) + .endm + + .macro err2 +200: + EX_TABLE(200b,.Ldo_err2) + .endm + + .macro err3 +300: EX_TABLE(300b,.Ldone) + .endm + +.Ldo_err2: + ld r22,STK_REG(R22)(r1) + ld r21,STK_REG(R21)(r1) + ld r20,STK_REG(R20)(r1) + ld r19,STK_REG(R19)(r1) + ld r18,STK_REG(R18)(r1) + ld r17,STK_REG(R17)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) + addi r1,r1,STACKFRAMESIZE +.Ldo_err1: + /* Do a byte by byte copy to get the exact remaining size */ + mtctr r7 +46: +err3; lbz r0,0(r4) + addi r4,r4,1 +err3; stb r0,0(r3) + addi r3,r3,1 + bdnz 46b + li r3,0 + blr + +.Ldone: + mfctr r3 + blr + + +_GLOBAL(copy_mc_generic) + mr r7,r5 + cmpldi r5,16 + blt .Lshort_copy + +.Lcopy: + /* Get the source 8B aligned */ + neg r6,r4 + mtocrf 0x01,r6 + clrldi r6,r6,(64-3) + + bf cr7*4+3,1f +err1; lbz r0,0(r4) + addi r4,r4,1 +err1; stb r0,0(r3) + addi r3,r3,1 + subi r7,r7,1 + +1: bf cr7*4+2,2f +err1; lhz r0,0(r4) + addi r4,r4,2 +err1; sth r0,0(r3) + addi r3,r3,2 + subi r7,r7,2 + +2: bf cr7*4+1,3f +err1; lwz r0,0(r4) + addi r4,r4,4 +err1; stw r0,0(r3) + addi r3,r3,4 + subi r7,r7,4 + +3: sub r5,r5,r6 + cmpldi r5,128 + + mflr r0 + stdu r1,-STACKFRAMESIZE(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) + std r0,STACKFRAMESIZE+16(r1) + + blt 5f + srdi r6,r5,7 + mtctr r6 + + /* Now do cacheline (128B) sized loads and stores. */ + .align 5 +4: +err2; ld r0,0(r4) +err2; ld r6,8(r4) +err2; ld r8,16(r4) +err2; ld r9,24(r4) +err2; ld r10,32(r4) +err2; ld r11,40(r4) +err2; ld r12,48(r4) +err2; ld r14,56(r4) +err2; ld r15,64(r4) +err2; ld r16,72(r4) +err2; ld r17,80(r4) +err2; ld r18,88(r4) +err2; ld r19,96(r4) +err2; ld r20,104(r4) +err2; ld r21,112(r4) +err2; ld r22,120(r4) + addi r4,r4,128 +err2; std r0,0(r3) +err2; std r6,8(r3) +err2; std r8,16(r3) +err2; std r9,24(r3) +err2; std r10,32(r3) +err2; std r11,40(r3) +err2; std r12,48(r3) +err2; std r14,56(r3) +err2; std r15,64(r3) +err2; std r16,72(r3) +err2; std r17,80(r3) +err2; std r18,88(r3) +err2; std r19,96(r3) +err2; std r20,104(r3) +err2; std r21,112(r3) +err2; std r22,120(r3) + addi r3,r3,128 + subi r7,r7,128 + bdnz 4b + + clrldi r5,r5,(64-7) + + /* Up to 127B to go */ +5: srdi r6,r5,4 + mtocrf 0x01,r6 + +6: bf cr7*4+1,7f +err2; ld r0,0(r4) +err2; ld r6,8(r4) +err2; ld r8,16(r4) +err2; ld r9,24(r4) +err2; ld r10,32(r4) +err2; ld r11,40(r4) +err2; ld r12,48(r4) +err2; ld r14,56(r4) + addi r4,r4,64 +err2; std r0,0(r3) +err2; std r6,8(r3) +err2; std r8,16(r3) +err2; std r9,24(r3) +err2; std r10,32(r3) +err2; std r11,40(r3) +err2; std r12,48(r3) +err2; std r14,56(r3) + addi r3,r3,64 + subi r7,r7,64 + +7: ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) + addi r1,r1,STACKFRAMESIZE + + /* Up to 63B to go */ + bf cr7*4+2,8f +err1; ld r0,0(r4) +err1; ld r6,8(r4) +err1; ld r8,16(r4) +err1; ld r9,24(r4) + addi r4,r4,32 +err1; std r0,0(r3) +err1; std r6,8(r3) +err1; std r8,16(r3) +err1; std r9,24(r3) + addi r3,r3,32 + subi r7,r7,32 + + /* Up to 31B to go */ +8: bf cr7*4+3,9f +err1; ld r0,0(r4) +err1; ld r6,8(r4) + addi r4,r4,16 +err1; std r0,0(r3) +err1; std r6,8(r3) + addi r3,r3,16 + subi r7,r7,16 + +9: clrldi r5,r5,(64-4) + + /* Up to 15B to go */ +.Lshort_copy: + mtocrf 0x01,r5 + bf cr7*4+0,12f +err1; lwz r0,0(r4) /* Less chance of a reject with word ops */ +err1; lwz r6,4(r4) + addi r4,r4,8 +err1; stw r0,0(r3) +err1; stw r6,4(r3) + addi r3,r3,8 + subi r7,r7,8 + +12: bf cr7*4+1,13f +err1; lwz r0,0(r4) + addi r4,r4,4 +err1; stw r0,0(r3) + addi r3,r3,4 + subi r7,r7,4 + +13: bf cr7*4+2,14f +err1; lhz r0,0(r4) + addi r4,r4,2 +err1; sth r0,0(r3) + addi r3,r3,2 + subi r7,r7,2 + +14: bf cr7*4+3,15f +err1; lbz r0,0(r4) +err1; stb r0,0(r3) + +15: li r3,0 + blr + +EXPORT_SYMBOL_GPL(copy_mc_generic); diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh index 8a8d0f456946..0d783e1065c8 100755 --- a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh +++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh @@ -1,17 +1,19 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0-only +KSELFTESTS_SKIP=4 + . ./eeh-functions.sh if ! eeh_supported ; then echo "EEH not supported on this system, skipping" - exit 0; + exit $KSELFTESTS_SKIP; fi if [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_check" ] && \ [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_break" ] ; then echo "debugfs EEH testing files are missing. Is debugfs mounted?" - exit 1; + exit $KSELFTESTS_SKIP; fi pre_lspci=`mktemp` @@ -84,4 +86,5 @@ echo "$failed devices failed to recover ($dev_count tested)" lspci | diff -u $pre_lspci - rm -f $pre_lspci -exit $failed +test "$failed" == 0 +exit $? diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk index e05182d3e47d..e05182d3e47d 100755..100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 3ba674b64fa9..69dd0d1aa30b 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -3,3 +3,4 @@ CONFIG_USERFAULTFD=y CONFIG_TEST_VMALLOC=m CONFIG_DEVICE_PRIVATE=y CONFIG_TEST_HMM=m +CONFIG_GUP_BENCHMARK=y diff --git a/usr/Makefile b/usr/Makefile index c12e6b15ce72..ed29c43088aa 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -55,7 +55,7 @@ cpio-data := $(obj)/initramfs_data.cpio hostprogs := gen_init_cpio # .initramfs_data.cpio.d is used to identify all files included -# in initramfs and to detect if any files are added/removed. +# in initramfs $(INITRAMFS_WRAPPER) and to detect if any files are added/removed. # Removed files are identified by directory timestamp being updated # The dependency list is generated by gen_initramfs.sh -l -include $(obj)/.initramfs_data.cpio.d |