diff options
1076 files changed, 62278 insertions, 3616 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/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 6aef7dbbde44..b97fde757bfe 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1563,7 +1563,8 @@ What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw KernelVersion: 4.3 Contact: linux-iio@vger.kernel.org Description: - Raw (unscaled no offset etc.) percentage reading of a substance. + Raw (unscaled no offset etc.) reading of a substance. Units + after application of scale and offset are percents. What: /sys/bus/iio/devices/iio:deviceX/in_resistance_raw What: /sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw diff --git a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt index c82794002595..89647d714387 100644 --- a/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt +++ b/Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.txt @@ -21,7 +21,7 @@ controller state. The mux controller state is described in Example: mux: mux-controller { - compatible = "mux-gpio"; + compatible = "gpio-mux"; #mux-control-cells = <0>; mux-gpios = <&pioA 0 GPIO_ACTIVE_HIGH>, diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt index 4438432bfe9b..ad76edccf881 100644 --- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt +++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt @@ -87,7 +87,7 @@ Example: ranges; /* APU<->RPU0 IPI mailbox controller */ - ipi_mailbox_rpu0: mailbox@ff90400 { + ipi_mailbox_rpu0: mailbox@ff990400 { reg = <0xff990400 0x20>, <0xff990420 0x20>, <0xff990080 0x20>, diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt index 8e5265e9f658..14d97c40b75c 100644 --- a/Documentation/devicetree/bindings/usb/dwc3.txt +++ b/Documentation/devicetree/bindings/usb/dwc3.txt @@ -73,6 +73,8 @@ Optional properties: from P0 to P1/P2/P3 without delay. - snps,dis-tx-ipgap-linecheck-quirk: when set, disable u2mac linestate check during HS transmit. + - snps,parkmode-disable-ss-quirk: when set, all SuperSpeed bus instances in + park mode are disabled. - snps,dis_metastability_quirk: when set, disable metastability workaround. CAUTION: use only if you are absolutely sure of it. - snps,is-utmi-l1-suspend: true when DWC3 asserts output signal diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README new file mode 100644 index 000000000000..6e6774fbf602 --- /dev/null +++ b/Documentation/filesystems/aufs/README @@ -0,0 +1,399 @@ + +Aufs5 -- advanced multi layered unification filesystem version 5.x +http://aufs.sf.net +Junjiro R. Okajima + + +0. Introduction +---------------------------------------- +In the early days, aufs was entirely re-designed and re-implemented +Unionfs Version 1.x series. Adding many original ideas, approaches, +improvements and implementations, it became totally different from +Unionfs while keeping the basic features. +Later, Unionfs Version 2.x series began taking some of the same +approaches to aufs1's. +Unionfs was being developed by Professor Erez Zadok at Stony Brook +University and his team. + +Aufs5 supports linux-v5.0 and later, If you want older kernel version +support, +- for linux-v4.x series, try aufs4-linux.git or aufs4-standalone.git +- for linux-v3.x series, try aufs3-linux.git or aufs3-standalone.git +- for linux-v2.6.16 and later, try aufs2-2.6.git, aufs2-standalone.git + or aufs1 from CVS on SourceForge. + +Note: it becomes clear that "Aufs was rejected. Let's give it up." + According to Christoph Hellwig, linux rejects all union-type + filesystems but UnionMount. +<http://marc.info/?l=linux-kernel&m=123938533724484&w=2> + +PS. Al Viro seems have a plan to merge aufs as well as overlayfs and + UnionMount, and he pointed out an issue around a directory mutex + lock and aufs addressed it. But it is still unsure whether aufs will + be merged (or any other union solution). +<http://marc.info/?l=linux-kernel&m=136312705029295&w=1> + + +1. Features +---------------------------------------- +- unite several directories into a single virtual filesystem. The member + directory is called as a branch. +- you can specify the permission flags to the branch, which are 'readonly', + 'readwrite' and 'whiteout-able.' +- by upper writable branch, internal copyup and whiteout, files/dirs on + readonly branch are modifiable logically. +- dynamic branch manipulation, add, del. +- etc... + +Also there are many enhancements in aufs, such as: +- test only the highest one for the directory permission (dirperm1) +- copyup on open (coo=) +- 'move' policy for copy-up between two writable branches, after + checking free space. +- xattr, acl +- readdir(3) in userspace. +- keep inode number by external inode number table +- keep the timestamps of file/dir in internal copyup operation +- seekable directory, supporting NFS readdir. +- whiteout is hardlinked in order to reduce the consumption of inodes + on branch +- do not copyup, nor create a whiteout when it is unnecessary +- revert a single systemcall when an error occurs in aufs +- remount interface instead of ioctl +- maintain /etc/mtab by an external command, /sbin/mount.aufs. +- loopback mounted filesystem as a branch +- kernel thread for removing the dir who has a plenty of whiteouts +- support copyup sparse file (a file which has a 'hole' in it) +- default permission flags for branches +- selectable permission flags for ro branch, whether whiteout can + exist or not +- export via NFS. +- support <sysfs>/fs/aufs and <debugfs>/aufs. +- support multiple writable branches, some policies to select one + among multiple writable branches. +- a new semantics for link(2) and rename(2) to support multiple + writable branches. +- no glibc changes are required. +- pseudo hardlink (hardlink over branches) +- allow a direct access manually to a file on branch, e.g. bypassing aufs. + including NFS or remote filesystem branch. +- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX. +- and more... + +Currently these features are dropped temporary from aufs5. +See design/08plan.txt in detail. +- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs + (robr) +- statistics of aufs thread (/sys/fs/aufs/stat) + +Features or just an idea in the future (see also design/*.txt), +- reorder the branch index without del/re-add. +- permanent xino files for NFSD +- an option for refreshing the opened files after add/del branches +- light version, without branch manipulation. (unnecessary?) +- copyup in userspace +- inotify in userspace +- readv/writev + + +2. Download +---------------------------------------- +There are three GIT trees for aufs5, aufs5-linux.git, +aufs5-standalone.git, and aufs-util.git. Note that there is no "5" in +"aufs-util.git." +While the aufs-util is always necessary, you need either of aufs5-linux +or aufs5-standalone. + +The aufs5-linux tree includes the whole linux mainline GIT tree, +git://git.kernel.org/.../torvalds/linux.git. +And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot +build aufs5 as an external kernel module. +Several extra patches are not included in this tree. Only +aufs5-standalone tree contains them. They are described in the later +section "Configuration and Compilation." + +On the other hand, the aufs5-standalone tree has only aufs source files +and necessary patches, and you can select CONFIG_AUFS_FS=m. +But you need to apply all aufs patches manually. + +You will find GIT branches whose name is in form of "aufs5.x" where "x" +represents the linux kernel version, "linux-5.x". For instance, +"aufs5.0" is for linux-5.0. For latest "linux-5.x-rcN", use +"aufs5.x-rcN" branch. + +o aufs5-linux tree +$ git clone --reference /your/linux/git/tree \ + git://github.com/sfjro/aufs5-linux.git aufs5-linux.git +- if you don't have linux GIT tree, then remove "--reference ..." +$ cd aufs5-linux.git +$ git checkout origin/aufs5.0 + +Or You may want to directly git-pull aufs into your linux GIT tree, and +leave the patch-work to GIT. +$ cd /your/linux/git/tree +$ git remote add aufs5 git://github.com/sfjro/aufs5-linux.git +$ git fetch aufs5 +$ git checkout -b my5.0 v5.0 +$ (add your local change...) +$ git pull aufs5 aufs5.0 +- now you have v5.0 + your_changes + aufs5.0 in you my5.0 branch. +- you may need to solve some conflicts between your_changes and + aufs5.0. in this case, git-rerere is recommended so that you can + solve the similar conflicts automatically when you upgrade to 5.1 or + later in the future. + +o aufs5-standalone tree +$ git clone git://github.com/sfjro/aufs5-standalone.git aufs5-standalone.git +$ cd aufs5-standalone.git +$ git checkout origin/aufs5.0 + +o aufs-util tree +$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git +- note that the public aufs-util.git is on SourceForge instead of + GitHUB. +$ cd aufs-util.git +$ git checkout origin/aufs5.0 + +Note: The 5.x-rcN branch is to be used with `rc' kernel versions ONLY. +The minor version number, 'x' in '5.x', of aufs may not always +follow the minor version number of the kernel. +Because changes in the kernel that cause the use of a new +minor version number do not always require changes to aufs-util. + +Since aufs-util has its own minor version number, you may not be +able to find a GIT branch in aufs-util for your kernel's +exact minor version number. +In this case, you should git-checkout the branch for the +nearest lower number. + +For (an unreleased) example: +If you are using "linux-5.10" and the "aufs5.10" branch +does not exist in aufs-util repository, then "aufs5.9", "aufs5.8" +or something numerically smaller is the branch for your kernel. + +Also you can view all branches by + $ git branch -a + + +3. Configuration and Compilation +---------------------------------------- +Make sure you have git-checkout'ed the correct branch. + +For aufs5-linux tree, +- enable CONFIG_AUFS_FS. +- set other aufs configurations if necessary. + +For aufs5-standalone tree, +There are several ways to build. + +1. +- apply ./aufs5-kbuild.patch to your kernel source files. +- apply ./aufs5-base.patch too. +- apply ./aufs5-mmap.patch too. +- apply ./aufs5-standalone.patch too, if you have a plan to set + CONFIG_AUFS_FS=m. otherwise you don't need ./aufs5-standalone.patch. +- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your + kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild. +- enable CONFIG_AUFS_FS, you can select either + =m or =y. +- and build your kernel as usual. +- install the built kernel. +- install the header files too by "make headers_install" to the + directory where you specify. By default, it is $PWD/usr. + "make help" shows a brief note for headers_install. +- and reboot your system. + +2. +- module only (CONFIG_AUFS_FS=m). +- apply ./aufs5-base.patch to your kernel source files. +- apply ./aufs5-mmap.patch too. +- apply ./aufs5-standalone.patch too. +- build your kernel, don't forget "make headers_install", and reboot. +- edit ./config.mk and set other aufs configurations if necessary. + Note: You should read $PWD/fs/aufs/Kconfig carefully which describes + every aufs configurations. +- build the module by simple "make". +- you can specify ${KDIR} make variable which points to your kernel + source tree. +- install the files + + run "make install" to install the aufs module, or copy the built + $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply). + + run "make install_headers" (instead of headers_install) to install + the modified aufs header file (you can specify DESTDIR which is + available in aufs standalone version's Makefile only), or copy + $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever + you like manually. By default, the target directory is $PWD/usr. +- no need to apply aufs5-kbuild.patch, nor copying source files to your + kernel source tree. + +Note: The header file aufs_type.h is necessary to build aufs-util + as well as "make headers_install" in the kernel source tree. + headers_install is subject to be forgotten, but it is essentially + necessary, not only for building aufs-util. + You may not meet problems without headers_install in some older + version though. + +And then, +- read README in aufs-util, build and install it +- note that your distribution may contain an obsoleted version of + aufs_type.h in /usr/include/linux or something. When you build aufs + utilities, make sure that your compiler refers the correct aufs header + file which is built by "make headers_install." +- if you want to use readdir(3) in userspace or pathconf(3) wrapper, + then run "make install_ulib" too. And refer to the aufs manual in + detail. + +There several other patches in aufs5-standalone.git. They are all +optional. When you meet some problems, they will help you. +- aufs5-loopback.patch + Supports a nested loopback mount in a branch-fs. This patch is + unnecessary until aufs produces a message like "you may want to try + another patch for loopback file". +- proc_mounts.patch + When there are many mountpoints and many mount(2)/umount(2) are + running, then /proc/mounts may not show the all mountpoints. This + patch makes /proc/mounts always show the full mountpoints list. + If you don't want to apply this patch and meet such problem, then you + need to increase the value of 'ProcMounts_Times' make-variable in + aufs-util.git as a second best solution. +- vfs-ino.patch + Modifies a system global kernel internal function get_next_ino() in + order to stop assigning 0 for an inode-number. Not directly related to + aufs, but recommended generally. +- tmpfs-idr.patch + Keeps the tmpfs inode number as the lowest value. Effective to reduce + the size of aufs XINO files for tmpfs branch. Also it prevents the + duplication of inode number, which is important for backup tools and + other utilities. When you find aufs XINO files for tmpfs branch + growing too much, try this patch. +- lockdep-debug.patch + Because aufs is not only an ordinary filesystem (callee of VFS), but + also a caller of VFS functions for branch filesystems, subclassing of + the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging + feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will + need to apply this debug patch to expand several constant values. + If don't know what LOCKDEP is, then you don't have apply this patch. + + +4. Usage +---------------------------------------- +At first, make sure aufs-util are installed, and please read the aufs +manual, aufs.5 in aufs-util.git tree. +$ man -l aufs.5 + +And then, +$ mkdir /tmp/rw /tmp/aufs +# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs + +Here is another example. The result is equivalent. +# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs + Or +# mount -t aufs -o br:/tmp/rw none /tmp/aufs +# mount -o remount,append:${HOME} /tmp/aufs + +Then, you can see whole tree of your home dir through /tmp/aufs. If +you modify a file under /tmp/aufs, the one on your home directory is +not affected, instead the same named file will be newly created under +/tmp/rw. And all of your modification to a file will be applied to +the one under /tmp/rw. This is called the file based Copy on Write +(COW) method. +Aufs mount options are described in aufs.5. +If you run chroot or something and make your aufs as a root directory, +then you need to customize the shutdown script. See the aufs manual in +detail. + +Additionally, there are some sample usages of aufs which are a +diskless system with network booting, and LiveCD over NFS. +See sample dir in CVS tree on SourceForge. + + +5. Contact +---------------------------------------- +When you have any problems or strange behaviour in aufs, please let me +know with: +- /proc/mounts (instead of the output of mount(8)) +- /sys/module/aufs/* +- /sys/fs/aufs/* (if you have them) +- /debug/aufs/* (if you have them) +- linux kernel version + if your kernel is not plain, for example modified by distributor, + the url where i can download its source is necessary too. +- aufs version which was printed at loading the module or booting the + system, instead of the date you downloaded. +- configuration (define/undefine CONFIG_AUFS_xxx) +- kernel configuration or /proc/config.gz (if you have it) +- behaviour which you think to be incorrect +- actual operation, reproducible one is better +- mailto: aufs-users at lists.sourceforge.net + +Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches, +and Feature Requests) on SourceForge. Please join and write to +aufs-users ML. + + +6. Acknowledgements +---------------------------------------- +Thanks to everyone who have tried and are using aufs, whoever +have reported a bug or any feedback. + +Especially donators: +Tomas Matejicek(slax.org) made a donation (much more than once). + Since Apr 2010, Tomas M (the author of Slax and Linux Live + scripts) is making "doubling" donations. + Unfortunately I cannot list all of the donators, but I really + appreciate. + It ends Aug 2010, but the ordinary donation URL is still available. + <http://sourceforge.net/donate/index.php?group_id=167503> +Dai Itasaka made a donation (2007/8). +Chuck Smith made a donation (2008/4, 10 and 12). +Henk Schoneveld made a donation (2008/9). +Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). +Francois Dupoux made a donation (2008/11). +Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public + aufs2 GIT tree (2009/2). +William Grant made a donation (2009/3). +Patrick Lane made a donation (2009/4). +The Mail Archive (mail-archive.com) made donations (2009/5). +Nippy Networks (Ed Wildgoose) made a donation (2009/7). +New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). +Pavel Pronskiy made a donation (2011/2). +Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy + Networks (Ed Wildgoose) made a donation for hardware (2011/3). +Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and +11). +Sam Liddicott made a donation (2011/9). +Era Scarecrow made a donation (2013/4). +Bor Ratajc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +POIRETTE Marc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +lauri kasvandik made a donation (2013/5). +"pemasu from Finland" made a donation (2013/7). +The Parted Magic Project made a donation (2013/9 and 11). +Pavel Barta made a donation (2013/10). +Nikolay Pertsev made a donation (2014/5). +James B made a donation (2014/7 and 2015/7). +Stefano Di Biase made a donation (2014/8). +Daniel Epellei made a donation (2015/1). +OmegaPhil made a donation (2016/1, 2018/4). +Tomasz Szewczyk made a donation (2016/4). +James Burry made a donation (2016/12). +Carsten Rose made a donation (2018/9). +Porteus Kiosk made a donation (2018/10). + +Thank you very much. +Donations are always, including future donations, very important and +helpful for me to keep on developing aufs. + + +7. +---------------------------------------- +If you are an experienced user, no explanation is needed. Aufs is +just a linux filesystem. + + +Enjoy! + +# Local variables: ; +# mode: text; +# End: ; diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt new file mode 100644 index 000000000000..609bf0e9b93a --- /dev/null +++ b/Documentation/filesystems/aufs/design/01intro.txt @@ -0,0 +1,171 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Introduction +---------------------------------------- + +aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s] +1. abbrev. for "advanced multi-layered unification filesystem". +2. abbrev. for "another unionfs". +3. abbrev. for "auf das" in German which means "on the" in English. + Ex. "Butter aufs Brot"(G) means "butter onto bread"(E). + But "Filesystem aufs Filesystem" is hard to understand. +4. abbrev. for "African Urban Fashion Show". + +AUFS is a filesystem with features: +- multi layered stackable unification filesystem, the member directory + is called as a branch. +- branch permission and attribute, 'readonly', 'real-readonly', + 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their + combination. +- internal "file copy-on-write". +- logical deletion, whiteout. +- dynamic branch manipulation, adding, deleting and changing permission. +- allow bypassing aufs, user's direct branch access. +- external inode number translation table and bitmap which maintains the + persistent aufs inode number. +- seekable directory, including NFS readdir. +- file mapping, mmap and sharing pages. +- pseudo-link, hardlink over branches. +- loopback mounted filesystem as a branch. +- several policies to select one among multiple writable branches. +- revert a single systemcall when an error occurs in aufs. +- and more... + + +Multi Layered Stackable Unification Filesystem +---------------------------------------------------------------------- +Most people already knows what it is. +It is a filesystem which unifies several directories and provides a +merged single directory. When users access a file, the access will be +passed/re-directed/converted (sorry, I am not sure which English word is +correct) to the real file on the member filesystem. The member +filesystem is called 'lower filesystem' or 'branch' and has a mode +'readonly' and 'readwrite.' And the deletion for a file on the lower +readonly branch is handled by creating 'whiteout' on the upper writable +branch. + +On LKML, there have been discussions about UnionMount (Jan Blunck, +Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took +different approaches to implement the merged-view. +The former tries putting it into VFS, and the latter implements as a +separate filesystem. +(If I misunderstand about these implementations, please let me know and +I shall correct it. Because it is a long time ago when I read their +source files last time). + +UnionMount's approach will be able to small, but may be hard to share +branches between several UnionMount since the whiteout in it is +implemented in the inode on branch filesystem and always +shared. According to Bharata's post, readdir does not seems to be +finished yet. +There are several missing features known in this implementations such as +- for users, the inode number may change silently. eg. copy-up. +- link(2) may break by copy-up. +- read(2) may get an obsoleted filedata (fstat(2) too). +- fcntl(F_SETLK) may be broken by copy-up. +- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after + open(O_RDWR). + +In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was +merged into mainline. This is another implementation of UnionMount as a +separated filesystem. All the limitations and known problems which +UnionMount are equally inherited to "overlay" filesystem. + +Unionfs has a longer history. When I started implementing a stackable +filesystem (Aug 2005), it already existed. It has virtual super_block, +inode, dentry and file objects and they have an array pointing lower +same kind objects. After contributing many patches for Unionfs, I +re-started my project AUFS (Jun 2006). + +In AUFS, the structure of filesystem resembles to Unionfs, but I +implemented my own ideas, approaches and enhancements and it became +totally different one. + +Comparing DM snapshot and fs based implementation +- the number of bytes to be copied between devices is much smaller. +- the type of filesystem must be one and only. +- the fs must be writable, no readonly fs, even for the lower original + device. so the compression fs will not be usable. but if we use + loopback mount, we may address this issue. + for instance, + mount /cdrom/squashfs.img /sq + losetup /sq/ext2.img + losetup /somewhere/cow + dmsetup "snapshot /dev/loop0 /dev/loop1 ..." +- it will be difficult (or needs more operations) to extract the + difference between the original device and COW. +- DM snapshot-merge may help a lot when users try merging. in the + fs-layer union, users will use rsync(1). + +You may want to read my old paper "Filesystems in LiveCD" +(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf). + + +Several characters/aspects/persona of aufs +---------------------------------------------------------------------- + +Aufs has several characters, aspects or persona. +1. a filesystem, callee of VFS helper +2. sub-VFS, caller of VFS helper for branches +3. a virtual filesystem which maintains persistent inode number +4. reader/writer of files on branches such like an application + +1. Callee of VFS Helper +As an ordinary linux filesystem, aufs is a callee of VFS. For instance, +unlink(2) from an application reaches sys_unlink() kernel function and +then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it +calls filesystem specific unlink operation. Actually aufs implements the +unlink operation but it behaves like a redirector. + +2. Caller of VFS Helper for Branches +aufs_unlink() passes the unlink request to the branch filesystem as if +it were called from VFS. So the called unlink operation of the branch +filesystem acts as usual. As a caller of VFS helper, aufs should handle +every necessary pre/post operation for the branch filesystem. +- acquire the lock for the parent dir on a branch +- lookup in a branch +- revalidate dentry on a branch +- mnt_want_write() for a branch +- vfs_unlink() for a branch +- mnt_drop_write() for a branch +- release the lock on a branch + +3. Persistent Inode Number +One of the most important issue for a filesystem is to maintain inode +numbers. This is particularly important to support exporting a +filesystem via NFS. Aufs is a virtual filesystem which doesn't have a +backend block device for its own. But some storage is necessary to +keep and maintain the inode numbers. It may be a large space and may not +suit to keep in memory. Aufs rents some space from its first writable +branch filesystem (by default) and creates file(s) on it. These files +are created by aufs internally and removed soon (currently) keeping +opened. +Note: Because these files are removed, they are totally gone after + unmounting aufs. It means the inode numbers are not persistent + across unmount or reboot. I have a plan to make them really + persistent which will be important for aufs on NFS server. + +4. Read/Write Files Internally (copy-on-write) +Because a branch can be readonly, when you write a file on it, aufs will +"copy-up" it to the upper writable branch internally. And then write the +originally requested thing to the file. Generally kernel doesn't +open/read/write file actively. In aufs, even a single write may cause a +internal "file copy". This behaviour is very similar to cp(1) command. + +Some people may think it is better to pass such work to user space +helper, instead of doing in kernel space. Actually I am still thinking +about it. But currently I have implemented it in kernel space. diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt new file mode 100644 index 000000000000..2467788c7f10 --- /dev/null +++ b/Documentation/filesystems/aufs/design/02struct.txt @@ -0,0 +1,258 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Basic Aufs Internal Structure + +Superblock/Inode/Dentry/File Objects +---------------------------------------------------------------------- +As like an ordinary filesystem, aufs has its own +superblock/inode/dentry/file objects. All these objects have a +dynamically allocated array and store the same kind of pointers to the +lower filesystem, branch. +For example, when you build a union with one readwrite branch and one +readonly, mounted /au, /rw and /ro respectively. +- /au = /rw + /ro +- /ro/fileA exists but /rw/fileA + +Aufs lookup operation finds /ro/fileA and gets dentry for that. These +pointers are stored in a aufs dentry. The array in aufs dentry will be, +- [0] = NULL (because /rw/fileA doesn't exist) +- [1] = /ro/fileA + +This style of an array is essentially same to the aufs +superblock/inode/dentry/file objects. + +Because aufs supports manipulating branches, ie. add/delete/change +branches dynamically, these objects has its own generation. When +branches are changed, the generation in aufs superblock is +incremented. And a generation in other object are compared when it is +accessed. When a generation in other objects are obsoleted, aufs +refreshes the internal array. + + +Superblock +---------------------------------------------------------------------- +Additionally aufs superblock has some data for policies to select one +among multiple writable branches, XIB files, pseudo-links and kobject. +See below in detail. +About the policies which supports copy-down a directory, see +wbr_policy.txt too. + + +Branch and XINO(External Inode Number Translation Table) +---------------------------------------------------------------------- +Every branch has its own xino (external inode number translation table) +file. The xino file is created and unlinked by aufs internally. When two +members of a union exist on the same filesystem, they share the single +xino file. +The struct of a xino file is simple, just a sequence of aufs inode +numbers which is indexed by the lower inode number. +In the above sample, assume the inode number of /ro/fileA is i111 and +aufs assigns the inode number i999 for fileA. Then aufs writes 999 as +4(8) bytes at 111 * 4(8) bytes offset in the xino file. + +When the inode numbers are not contiguous, the xino file will be sparse +which has a hole in it and doesn't consume as much disk space as it +might appear. If your branch filesystem consumes disk space for such +holes, then you should specify 'xino=' option at mounting aufs. + +Aufs has a mount option to free the disk blocks for such holes in XINO +files on tmpfs or ramdisk. But it is not so effective actually. If you +meet a problem of disk shortage due to XINO files, then you should try +"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git. +The patch localizes the assignment inumbers per tmpfs-mount and avoid +the holes in XINO files. + +Also a writable branch has three kinds of "whiteout bases". All these +are existed when the branch is joined to aufs, and their names are +whiteout-ed doubly, so that users will never see their names in aufs +hierarchy. +1. a regular file which will be hardlinked to all whiteouts. +2. a directory to store a pseudo-link. +3. a directory to store an "orphan"-ed file temporary. + +1. Whiteout Base + When you remove a file on a readonly branch, aufs handles it as a + logical deletion and creates a whiteout on the upper writable branch + as a hardlink of this file in order not to consume inode on the + writable branch. +2. Pseudo-link Dir + See below, Pseudo-link. +3. Step-Parent Dir + When "fileC" exists on the lower readonly branch only and it is + opened and removed with its parent dir, and then user writes + something into it, then aufs copies-up fileC to this + directory. Because there is no other dir to store fileC. After + creating a file under this dir, the file is unlinked. + +Because aufs supports manipulating branches, ie. add/delete/change +dynamically, a branch has its own id. When the branch order changes, +aufs finds the new index by searching the branch id. + + +Pseudo-link +---------------------------------------------------------------------- +Assume "fileA" exists on the lower readonly branch only and it is +hardlinked to "fileB" on the branch. When you write something to fileA, +aufs copies-up it to the upper writable branch. Additionally aufs +creates a hardlink under the Pseudo-link Directory of the writable +branch. The inode of a pseudo-link is kept in aufs super_block as a +simple list. If fileB is read after unlinking fileA, aufs returns +filedata from the pseudo-link instead of the lower readonly +branch. Because the pseudo-link is based upon the inode, to keep the +inode number by xino (see above) is essentially necessary. + +All the hardlinks under the Pseudo-link Directory of the writable branch +should be restored in a proper location later. Aufs provides a utility +to do this. The userspace helpers executed at remounting and unmounting +aufs by default. +During this utility is running, it puts aufs into the pseudo-link +maintenance mode. In this mode, only the process which began the +maintenance mode (and its child processes) is allowed to operate in +aufs. Some other processes which are not related to the pseudo-link will +be allowed to run too, but the rest have to return an error or wait +until the maintenance mode ends. If a process already acquires an inode +mutex (in VFS), it has to return an error. + + +XIB(external inode number bitmap) +---------------------------------------------------------------------- +Addition to the xino file per a branch, aufs has an external inode number +bitmap in a superblock object. It is also an internal file such like a +xino file. +It is a simple bitmap to mark whether the aufs inode number is in-use or +not. +To reduce the file I/O, aufs prepares a single memory page to cache xib. + +As well as XINO files, aufs has a feature to truncate/refresh XIB to +reduce the number of consumed disk blocks for these files. + + +Virtual or Vertical Dir, and Readdir in Userspace +---------------------------------------------------------------------- +In order to support multiple layers (branches), aufs readdir operation +constructs a virtual dir block on memory. For readdir, aufs calls +vfs_readdir() internally for each dir on branches, merges their entries +with eliminating the whiteout-ed ones, and sets it to file (dir) +object. So the file object has its entry list until it is closed. The +entry list will be updated when the file position is zero and becomes +obsoleted. This decision is made in aufs automatically. + +The dynamically allocated memory block for the name of entries has a +unit of 512 bytes (by default) and stores the names contiguously (no +padding). Another block for each entry is handled by kmem_cache too. +During building dir blocks, aufs creates hash list and judging whether +the entry is whiteouted by its upper branch or already listed. +The merged result is cached in the corresponding inode object and +maintained by a customizable life-time option. + +Some people may call it can be a security hole or invite DoS attack +since the opened and once readdir-ed dir (file object) holds its entry +list and becomes a pressure for system memory. But I'd say it is similar +to files under /proc or /sys. The virtual files in them also holds a +memory page (generally) while they are opened. When an idea to reduce +memory for them is introduced, it will be applied to aufs too. +For those who really hate this situation, I've developed readdir(3) +library which operates this merging in userspace. You just need to set +LD_PRELOAD environment variable, and aufs will not consume no memory in +kernel space for readdir(3). + + +Workqueue +---------------------------------------------------------------------- +Aufs sometimes requires privilege access to a branch. For instance, +in copy-up/down operation. When a user process is going to make changes +to a file which exists in the lower readonly branch only, and the mode +of one of ancestor directories may not be writable by a user +process. Here aufs copy-up the file with its ancestors and they may +require privilege to set its owner/group/mode/etc. +This is a typical case of a application character of aufs (see +Introduction). + +Aufs uses workqueue synchronously for this case. It creates its own +workqueue. The workqueue is a kernel thread and has privilege. Aufs +passes the request to call mkdir or write (for example), and wait for +its completion. This approach solves a problem of a signal handler +simply. +If aufs didn't adopt the workqueue and changed the privilege of the +process, then the process may receive the unexpected SIGXFSZ or other +signals. + +Also aufs uses the system global workqueue ("events" kernel thread) too +for asynchronous tasks, such like handling inotify/fsnotify, re-creating a +whiteout base and etc. This is unrelated to a privilege. +Most of aufs operation tries acquiring a rw_semaphore for aufs +superblock at the beginning, at the same time waits for the completion +of all queued asynchronous tasks. + + +Whiteout +---------------------------------------------------------------------- +The whiteout in aufs is very similar to Unionfs's. That is represented +by its filename. UnionMount takes an approach of a file mode, but I am +afraid several utilities (find(1) or something) will have to support it. + +Basically the whiteout represents "logical deletion" which stops aufs to +lookup further, but also it represents "dir is opaque" which also stop +further lookup. + +In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively. +In order to make several functions in a single systemcall to be +revertible, aufs adopts an approach to rename a directory to a temporary +unique whiteouted name. +For example, in rename(2) dir where the target dir already existed, aufs +renames the target dir to a temporary unique whiteouted name before the +actual rename on a branch, and then handles other actions (make it opaque, +update the attributes, etc). If an error happens in these actions, aufs +simply renames the whiteouted name back and returns an error. If all are +succeeded, aufs registers a function to remove the whiteouted unique +temporary name completely and asynchronously to the system global +workqueue. + + +Copy-up +---------------------------------------------------------------------- +It is a well-known feature or concept. +When user modifies a file on a readonly branch, aufs operate "copy-up" +internally and makes change to the new file on the upper writable branch. +When the trigger systemcall does not update the timestamps of the parent +dir, aufs reverts it after copy-up. + + +Move-down (aufs3.9 and later) +---------------------------------------------------------------------- +"Copy-up" is one of the essential feature in aufs. It copies a file from +the lower readonly branch to the upper writable branch when a user +changes something about the file. +"Move-down" is an opposite action of copy-up. Basically this action is +ran manually instead of automatically and internally. +For desgin and implementation, aufs has to consider these issues. +- whiteout for the file may exist on the lower branch. +- ancestor directories may not exist on the lower branch. +- diropq for the ancestor directories may exist on the upper branch. +- free space on the lower branch will reduce. +- another access to the file may happen during moving-down, including + UDBA (see "Revalidate Dentry and UDBA"). +- the file should not be hard-linked nor pseudo-linked. they should be + handled by auplink utility later. + +Sometimes users want to move-down a file from the upper writable branch +to the lower readonly or writable branch. For instance, +- the free space of the upper writable branch is going to run out. +- create a new intermediate branch between the upper and lower branch. +- etc. + +For this purpose, use "aumvdown" command in aufs-util.git. diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt new file mode 100644 index 000000000000..9f16ac1e0173 --- /dev/null +++ b/Documentation/filesystems/aufs/design/03atomic_open.txt @@ -0,0 +1,85 @@ + +# Copyright (C) 2015-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Support for a branch who has its ->atomic_open() +---------------------------------------------------------------------- +The filesystems who implement its ->atomic_open() are not majority. For +example NFSv4 does, and aufs should call NFSv4 ->atomic_open, +particularly for open(O_CREAT|O_EXCL, 0400) case. Other than +->atomic_open(), NFSv4 returns an error for this open(2). While I am not +sure whether all filesystems who have ->atomic_open() behave like this, +but NFSv4 surely returns the error. + +In order to support ->atomic_open() for aufs, there are a few +approaches. + +A. Introduce aufs_atomic_open() + - calls one of VFS:do_last(), lookup_open() or atomic_open() for + branch fs. +B. Introduce aufs_atomic_open() calling create, open and chmod. this is + an aufs user Pip Cet's approach + - calls aufs_create(), VFS finish_open() and notify_change(). + - pass fake-mode to finish_open(), and then correct the mode by + notify_change(). +C. Extend aufs_open() to call branch fs's ->atomic_open() + - no aufs_atomic_open(). + - aufs_lookup() registers the TID to an aufs internal object. + - aufs_create() does nothing when the matching TID is registered, but + registers the mode. + - aufs_open() calls branch fs's ->atomic_open() when the matching + TID is registered. +D. Extend aufs_open() to re-try branch fs's ->open() with superuser's + credential + - no aufs_atomic_open(). + - aufs_create() registers the TID to an internal object. this info + represents "this process created this file just now." + - when aufs gets EACCES from branch fs's ->open(), then confirm the + registered TID and re-try open() with superuser's credential. + +Pros and cons for each approach. + +A. + - straightforward but highly depends upon VFS internal. + - the atomic behavaiour is kept. + - some of parameters such as nameidata are hard to reproduce for + branch fs. + - large overhead. +B. + - easy to implement. + - the atomic behavaiour is lost. +C. + - the atomic behavaiour is kept. + - dirty and tricky. + - VFS checks whether the file is created correctly after calling + ->create(), which means this approach doesn't work. +D. + - easy to implement. + - the atomic behavaiour is lost. + - to open a file with superuser's credential and give it to a user + process is a bad idea, since the file object keeps the credential + in it. It may affect LSM or something. This approach doesn't work + either. + +The approach A is ideal, but it hard to implement. So here is a +variation of A, which is to be implemented. + +A-1. Introduce aufs_atomic_open() + - calls branch fs ->atomic_open() if exists. otherwise calls + vfs_create() and finish_open(). + - the demerit is that the several checks after branch fs + ->atomic_open() are lost. in the ordinary case, the checks are + done by VFS:do_last(), lookup_open() and atomic_open(). some can + be implemented in aufs, but not all I am afraid. diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt new file mode 100644 index 000000000000..08b443d94dfa --- /dev/null +++ b/Documentation/filesystems/aufs/design/03lookup.txt @@ -0,0 +1,113 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Lookup in a Branch +---------------------------------------------------------------------- +Since aufs has a character of sub-VFS (see Introduction), it operates +lookup for branches as VFS does. It may be a heavy work. But almost all +lookup operation in aufs is the simplest case, ie. lookup only an entry +directly connected to its parent. Digging down the directory hierarchy +is unnecessary. VFS has a function lookup_one_len() for that use, and +aufs calls it. + +When a branch is a remote filesystem, aufs basically relies upon its +->d_revalidate(), also aufs forces the hardest revalidate tests for +them. +For d_revalidate, aufs implements three levels of revalidate tests. See +"Revalidate Dentry and UDBA" in detail. + + +Test Only the Highest One for the Directory Permission (dirperm1 option) +---------------------------------------------------------------------- +Let's try case study. +- aufs has two branches, upper readwrite and lower readonly. + /au = /rw + /ro +- "dirA" exists under /ro, but /rw. and its mode is 0700. +- user invoked "chmod a+rx /au/dirA" +- the internal copy-up is activated and "/rw/dirA" is created and its + permission bits are set to world readable. +- then "/au/dirA" becomes world readable? + +In this case, /ro/dirA is still 0700 since it exists in readonly branch, +or it may be a natively readonly filesystem. If aufs respects the lower +branch, it should not respond readdir request from other users. But user +allowed it by chmod. Should really aufs rejects showing the entries +under /ro/dirA? + +To be honest, I don't have a good solution for this case. So aufs +implements 'dirperm1' and 'nodirperm1' mount options, and leave it to +users. +When dirperm1 is specified, aufs checks only the highest one for the +directory permission, and shows the entries. Otherwise, as usual, checks +every dir existing on all branches and rejects the request. + +As a side effect, dirperm1 option improves the performance of aufs +because the number of permission check is reduced when the number of +branch is many. + + +Revalidate Dentry and UDBA (User's Direct Branch Access) +---------------------------------------------------------------------- +Generally VFS helpers re-validate a dentry as a part of lookup. +0. digging down the directory hierarchy. +1. lock the parent dir by its i_mutex. +2. lookup the final (child) entry. +3. revalidate it. +4. call the actual operation (create, unlink, etc.) +5. unlock the parent dir + +If the filesystem implements its ->d_revalidate() (step 3), then it is +called. Actually aufs implements it and checks the dentry on a branch is +still valid. +But it is not enough. Because aufs has to release the lock for the +parent dir on a branch at the end of ->lookup() (step 2) and +->d_revalidate() (step 3) while the i_mutex of the aufs dir is still +held by VFS. +If the file on a branch is changed directly, eg. bypassing aufs, after +aufs released the lock, then the subsequent operation may cause +something unpleasant result. + +This situation is a result of VFS architecture, ->lookup() and +->d_revalidate() is separated. But I never say it is wrong. It is a good +design from VFS's point of view. It is just not suitable for sub-VFS +character in aufs. + +Aufs supports such case by three level of revalidation which is +selectable by user. +1. Simple Revalidate + Addition to the native flow in VFS's, confirm the child-parent + relationship on the branch just after locking the parent dir on the + branch in the "actual operation" (step 4). When this validation + fails, aufs returns EBUSY. ->d_revalidate() (step 3) in aufs still + checks the validation of the dentry on branches. +2. Monitor Changes Internally by Inotify/Fsnotify + Addition to above, in the "actual operation" (step 4) aufs re-lookup + the dentry on the branch, and returns EBUSY if it finds different + dentry. + Additionally, aufs sets the inotify/fsnotify watch for every dir on branches + during it is in cache. When the event is notified, aufs registers a + function to kernel 'events' thread by schedule_work(). And the + function sets some special status to the cached aufs dentry and inode + private data. If they are not cached, then aufs has nothing to + do. When the same file is accessed through aufs (step 0-3) later, + aufs will detect the status and refresh all necessary data. + In this mode, aufs has to ignore the event which is fired by aufs + itself. +3. No Extra Validation + This is the simplest test and doesn't add any additional revalidation + test, and skip the revalidation in step 4. It is useful and improves + aufs performance when system surely hide the aufs branches from user, + by over-mounting something (or another method). diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt new file mode 100644 index 000000000000..3ab3682a42b4 --- /dev/null +++ b/Documentation/filesystems/aufs/design/04branch.txt @@ -0,0 +1,74 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Branch Manipulation + +Since aufs supports dynamic branch manipulation, ie. add/remove a branch +and changing its permission/attribute, there are a lot of works to do. + + +Add a Branch +---------------------------------------------------------------------- +o Confirm the adding dir exists outside of aufs, including loopback + mount, and its various attributes. +o Initialize the xino file and whiteout bases if necessary. + See struct.txt. + +o Check the owner/group/mode of the directory + When the owner/group/mode of the adding directory differs from the + existing branch, aufs issues a warning because it may impose a + security risk. + For example, when a upper writable branch has a world writable empty + top directory, a malicious user can create any files on the writable + branch directly, like copy-up and modify manually. If something like + /etc/{passwd,shadow} exists on the lower readonly branch but the upper + writable branch, and the writable branch is world-writable, then a + malicious guy may create /etc/passwd on the writable branch directly + and the infected file will be valid in aufs. + I am afraid it can be a security issue, but aufs can do nothing except + producing a warning. + + +Delete a Branch +---------------------------------------------------------------------- +o Confirm the deleting branch is not busy + To be general, there is one merit to adopt "remount" interface to + manipulate branches. It is to discard caches. At deleting a branch, + aufs checks the still cached (and connected) dentries and inodes. If + there are any, then they are all in-use. An inode without its + corresponding dentry can be alive alone (for example, inotify/fsnotify case). + + For the cached one, aufs checks whether the same named entry exists on + other branches. + If the cached one is a directory, because aufs provides a merged view + to users, as long as one dir is left on any branch aufs can show the + dir to users. In this case, the branch can be removed from aufs. + Otherwise aufs rejects deleting the branch. + + If any file on the deleting branch is opened by aufs, then aufs + rejects deleting. + + +Modify the Permission of a Branch +---------------------------------------------------------------------- +o Re-initialize or remove the xino file and whiteout bases if necessary. + See struct.txt. + +o rw --> ro: Confirm the modifying branch is not busy + Aufs rejects the request if any of these conditions are true. + - a file on the branch is mmap-ed. + - a regular file on the branch is opened for write and there is no + same named entry on the upper branch. diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt new file mode 100644 index 000000000000..1f9b86bc6a3e --- /dev/null +++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt @@ -0,0 +1,64 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Policies to Select One among Multiple Writable Branches +---------------------------------------------------------------------- +When the number of writable branch is more than one, aufs has to decide +the target branch for file creation or copy-up. By default, the highest +writable branch which has the parent (or ancestor) dir of the target +file is chosen (top-down-parent policy). +By user's request, aufs implements some other policies to select the +writable branch, for file creation several policies, round-robin, +most-free-space, and other policies. For copy-up, top-down-parent, +bottom-up-parent, bottom-up and others. + +As expected, the round-robin policy selects the branch in circular. When +you have two writable branches and creates 10 new files, 5 files will be +created for each branch. mkdir(2) systemcall is an exception. When you +create 10 new directories, all will be created on the same branch. +And the most-free-space policy selects the one which has most free +space among the writable branches. The amount of free space will be +checked by aufs internally, and users can specify its time interval. + +The policies for copy-up is more simple, +top-down-parent is equivalent to the same named on in create policy, +bottom-up-parent selects the writable branch where the parent dir +exists and the nearest upper one from the copyup-source, +bottom-up selects the nearest upper writable branch from the +copyup-source, regardless the existence of the parent dir. + +There are some rules or exceptions to apply these policies. +- If there is a readonly branch above the policy-selected branch and + the parent dir is marked as opaque (a variation of whiteout), or the + target (creating) file is whiteout-ed on the upper readonly branch, + then the result of the policy is ignored and the target file will be + created on the nearest upper writable branch than the readonly branch. +- If there is a writable branch above the policy-selected branch and + the parent dir is marked as opaque or the target file is whiteouted + on the branch, then the result of the policy is ignored and the target + file will be created on the highest one among the upper writable + branches who has diropq or whiteout. In case of whiteout, aufs removes + it as usual. +- link(2) and rename(2) systemcalls are exceptions in every policy. + They try selecting the branch where the source exists as possible + since copyup a large file will take long time. If it can't be, + ie. the branch where the source exists is readonly, then they will + follow the copyup policy. +- There is an exception for rename(2) when the target exists. + If the rename target exists, aufs compares the index of the branches + where the source and the target exists and selects the higher + one. If the selected branch is readonly, then aufs follows the + copyup policy. diff --git a/Documentation/filesystems/aufs/design/06dirren.dot b/Documentation/filesystems/aufs/design/06dirren.dot new file mode 100644 index 000000000000..2d62bb6dd55f --- /dev/null +++ b/Documentation/filesystems/aufs/design/06dirren.dot @@ -0,0 +1,31 @@ + +// to view this graph, run dot(1) command in GRAPHVIZ. + +digraph G { +node [shape=box]; +whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"]; + +node [shape=oval]; + +aufs_rename -> whinfo [label="store/remove"]; + +node [shape=oval]; +inode_list [label="h_inum list in branch\ncache"]; + +node [shape=box]; +whinode [label="h_inum list file"]; + +node [shape=oval]; +brmgmt [label="br_add/del/mod/umount"]; + +brmgmt -> inode_list [label="create/remove"]; +brmgmt -> whinode [label="load/store"]; + +inode_list -> whinode [style=dashed,dir=both]; + +aufs_rename -> inode_list [label="add/del"]; + +aufs_lookup -> inode_list [label="search"]; + +aufs_lookup -> whinfo [label="load/remove"]; +} diff --git a/Documentation/filesystems/aufs/design/06dirren.txt b/Documentation/filesystems/aufs/design/06dirren.txt new file mode 100644 index 000000000000..3b80f8659b3e --- /dev/null +++ b/Documentation/filesystems/aufs/design/06dirren.txt @@ -0,0 +1,102 @@ + +# Copyright (C) 2017-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Special handling for renaming a directory (DIRREN) +---------------------------------------------------------------------- +First, let's assume we have a simple usecase. + +- /u = /rw + /ro +- /rw/dirA exists +- /ro/dirA and /ro/dirA/file exist too +- there is no dirB on both branches +- a user issues rename("dirA", "dirB") + +Now, what should aufs behave against this rename(2)? +There are a few possible cases. + +A. returns EROFS. + since dirA exists on a readonly branch which cannot be renamed. +B. returns EXDEV. + it is possible to copy-up dirA (only the dir itself), but the child + entries ("file" in this case) should not be. it must be a bad + approach to copy-up recursively. +C. returns a success. + even the branch /ro is readonly, aufs tries renaming it. Obviously it + is a violation of aufs' policy. +D. construct an extra information which indicates that /ro/dirA should + be handled as the name of dirB. + overlayfs has a similar feature called REDIRECT. + +Until now, aufs implements the case B only which returns EXDEV, and +expects the userspace application behaves like mv(1) which tries +issueing rename(2) recursively. + +A new aufs feature called DIRREN is introduced which implements the case +D. There are several "extra information" added. + +1. detailed info per renamed directory + path: /rw/dirB/$AUFS_WH_DR_INFO_PFX.<lower branch-id> +2. the inode-number list of directories on a branch + path: /rw/dirB/$AUFS_WH_DR_BRHINO + +The filename of "detailed info per directory" represents the lower +branch, and its format is +- a type of the branch id + one of these. + + uuid (not implemented yet) + + fsid + + dev +- the inode-number of the branch root dir + +And it contains these info in a single regular file. +- magic number +- branch's inode-number of the logically renamed dir +- the name of the before-renamed dir + +The "detailed info per directory" file is created in aufs rename(2), and +loaded in any lookup. +The info is considered in lookup for the matching case only. Here +"matching" means that the root of branch (in the info filename) is same +to the current looking-up branch. After looking-up the before-renamed +name, the inode-number is compared. And the matched dentry is used. + +The "inode-number list of directories" is a regular file which contains +simply the inode-numbers on the branch. The file is created or updated +in removing the branch, and loaded in adding the branch. Its lifetime is +equal to the branch. +The list is refered in lookup, and when the current target inode is +found in the list, the aufs tries loading the "detailed info per +directory" and get the changed and valid name of the dir. + +Theoretically these "extra informaiton" may be able to be put into XATTR +in the dir inode. But aufs doesn't choose this way because +1. XATTR may not be supported by the branch (or its configuration) +2. XATTR may have its size limit. +3. XATTR may be less easy to convert than a regular file, when the + format of the info is changed in the future. +At the same time, I agree that the regular file approach is much slower +than XATTR approach. So, in the future, aufs may take the XATTR or other +better approach. + +This DIRREN feature is enabled by aufs configuration, and is activated +by a new mount option. + +For the more complicated case, there is a work with UDBA option, which +is to dected the direct access to the branches (by-passing aufs) and to +maintain the cashes in aufs. Since a single cached aufs dentry may +contains two names, before- and after-rename, the name comparision in +UDBA handler may not work correctly. In this case, the behaviour will be +equivalen to udba=reval case. diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt new file mode 100644 index 000000000000..8b498d0af812 --- /dev/null +++ b/Documentation/filesystems/aufs/design/06fhsm.txt @@ -0,0 +1,120 @@ + +# Copyright (C) 2011-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + + +File-based Hierarchical Storage Management (FHSM) +---------------------------------------------------------------------- +Hierarchical Storage Management (or HSM) is a well-known feature in the +storage world. Aufs provides this feature as file-based with multiple +writable branches, based upon the principle of "Colder, the Lower". +Here the word "colder" means that the less used files, and "lower" means +that the position in the order of the stacked branches vertically. +These multiple writable branches are prioritized, ie. the topmost one +should be the fastest drive and be used heavily. + +o Characters in aufs FHSM story +- aufs itself and a new branch attribute. +- a new ioctl interface to move-down and to establish a connection with + the daemon ("move-down" is a converse of "copy-up"). +- userspace tool and daemon. + +The userspace daemon establishes a connection with aufs and waits for +the notification. The notified information is very similar to struct +statfs containing the number of consumed blocks and inodes. +When the consumed blocks/inodes of a branch exceeds the user-specified +upper watermark, the daemon activates its move-down process until the +consumed blocks/inodes reaches the user-specified lower watermark. + +The actual move-down is done by aufs based upon the request from +user-space since we need to maintain the inode number and the internal +pointer arrays in aufs. + +Currently aufs FHSM handles the regular files only. Additionally they +must not be hard-linked nor pseudo-linked. + + +o Cowork of aufs and the user-space daemon + During the userspace daemon established the connection, aufs sends a + small notification to it whenever aufs writes something into the + writable branch. But it may cost high since aufs issues statfs(2) + internally. So user can specify a new option to cache the + info. Actually the notification is controlled by these factors. + + the specified cache time. + + classified as "force" by aufs internally. + Until the specified time expires, aufs doesn't send the info + except the forced cases. When aufs decide forcing, the info is always + notified to userspace. + For example, the number of free inodes is generally large enough and + the shortage of it happens rarely. So aufs doesn't force the + notification when creating a new file, directory and others. This is + the typical case which aufs doesn't force. + When aufs writes the actual filedata and the files consumes any of new + blocks, the aufs forces notifying. + + +o Interfaces in aufs +- New branch attribute. + + fhsm + Specifies that the branch is managed by FHSM feature. In other word, + participant in the FHSM. + When nofhsm is set to the branch, it will not be the source/target + branch of the move-down operation. This attribute is set + independently from coo and moo attributes, and if you want full + FHSM, you should specify them as well. +- New mount option. + + fhsm_sec + Specifies a second to suppress many less important info to be + notified. +- New ioctl. + + AUFS_CTL_FHSM_FD + create a new file descriptor which userspace can read the notification + (a subset of struct statfs) from aufs. +- Module parameter 'brs' + It has to be set to 1. Otherwise the new mount option 'fhsm' will not + be set. +- mount helpers /sbin/mount.aufs and /sbin/umount.aufs + When there are two or more branches with fhsm attributes, + /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs + terminates it. As a result of remounting and branch-manipulation, the + number of branches with fhsm attribute can be one. In this case, + /sbin/mount.aufs will terminate the user-space daemon. + + +Finally the operation is done as these steps in kernel-space. +- make sure that, + + no one else is using the file. + + the file is not hard-linked. + + the file is not pseudo-linked. + + the file is a regular file. + + the parent dir is not opaqued. +- find the target writable branch. +- make sure the file is not whiteout-ed by the upper (than the target) + branch. +- make the parent dir on the target branch. +- mutex lock the inode on the branch. +- unlink the whiteout on the target branch (if exists). +- lookup and create the whiteout-ed temporary name on the target branch. +- copy the file as the whiteout-ed temporary name on the target branch. +- rename the whiteout-ed temporary name to the original name. +- unlink the file on the source branch. +- maintain the internal pointer array and the external inode number + table (XINO). +- maintain the timestamps and other attributes of the parent dir and the + file. + +And of course, in every step, an error may happen. So the operation +should restore the original file state after an error happens. diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt new file mode 100644 index 000000000000..cdd84ea777fc --- /dev/null +++ b/Documentation/filesystems/aufs/design/06mmap.txt @@ -0,0 +1,72 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +mmap(2) -- File Memory Mapping +---------------------------------------------------------------------- +In aufs, the file-mapped pages are handled by a branch fs directly, no +interaction with aufs. It means aufs_mmap() calls the branch fs's +->mmap(). +This approach is simple and good, but there is one problem. +Under /proc, several entries show the mmapped files by its path (with +device and inode number), and the printed path will be the path on the +branch fs's instead of virtual aufs's. +This is not a problem in most cases, but some utilities lsof(1) (and its +user) may expect the path on aufs. + +To address this issue, aufs adds a new member called vm_prfile in struct +vm_area_struct (and struct vm_region). The original vm_file points to +the file on the branch fs in order to handle everything correctly as +usual. The new vm_prfile points to a virtual file in aufs, and the +show-functions in procfs refers to vm_prfile if it is set. +Also we need to maintain several other places where touching vm_file +such like +- fork()/clone() copies vma and the reference count of vm_file is + incremented. +- merging vma maintains the ref count too. + +This is not a good approach. It just fakes the printed path. But it +leaves all behaviour around f_mapping unchanged. This is surely an +advantage. +Actually aufs had adopted another complicated approach which calls +generic_file_mmap() and handles struct vm_operations_struct. In this +approach, aufs met a hard problem and I could not solve it without +switching the approach. + +There may be one more another approach which is +- bind-mount the branch-root onto the aufs-root internally +- grab the new vfsmount (ie. struct mount) +- lazy-umount the branch-root internally +- in open(2) the aufs-file, open the branch-file with the hidden + vfsmount (instead of the original branch's vfsmount) +- ideally this "bind-mount and lazy-umount" should be done atomically, + but it may be possible from userspace by the mount helper. + +Adding the internal hidden vfsmount and using it in opening a file, the +file path under /proc will be printed correctly. This approach looks +smarter, but is not possible I am afraid. +- aufs-root may be bind-mount later. when it happens, another hidden + vfsmount will be required. +- it is hard to get the chance to bind-mount and lazy-umount + + in kernel-space, FS can have vfsmount in open(2) via + file->f_path, and aufs can know its vfsmount. But several locks are + already acquired, and if aufs tries to bind-mount and lazy-umount + here, then it may cause a deadlock. + + in user-space, bind-mount doesn't invoke the mount helper. +- since /proc shows dev and ino, aufs has to give vma these info. it + means a new member vm_prinode will be necessary. this is essentially + equivalent to vm_prfile described above. + +I have to give up this "looks-smater" approach. diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt new file mode 100644 index 000000000000..edd7553f3289 --- /dev/null +++ b/Documentation/filesystems/aufs/design/06xattr.txt @@ -0,0 +1,96 @@ + +# Copyright (C) 2014-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + + +Listing XATTR/EA and getting the value +---------------------------------------------------------------------- +For the inode standard attributes (owner, group, timestamps, etc.), aufs +shows the values from the topmost existing file. This behaviour is good +for the non-dir entries since the bahaviour exactly matches the shown +information. But for the directories, aufs considers all the same named +entries on the lower branches. Which means, if one of the lower entry +rejects readdir call, then aufs returns an error even if the topmost +entry allows it. This behaviour is necessary to respect the branch fs's +security, but can make users confused since the user-visible standard +attributes don't match the behaviour. +To address this issue, aufs has a mount option called dirperm1 which +checks the permission for the topmost entry only, and ignores the lower +entry's permission. + +A similar issue can happen around XATTR. +getxattr(2) and listxattr(2) families behave as if dirperm1 option is +always set. Otherwise these very unpleasant situation would happen. +- listxattr(2) may return the duplicated entries. +- users may not be able to remove or reset the XATTR forever, + + +XATTR/EA support in the internal (copy,move)-(up,down) +---------------------------------------------------------------------- +Generally the extended attributes of inode are categorized as these. +- "security" for LSM and capability. +- "system" for posix ACL, 'acl' mount option is required for the branch + fs generally. +- "trusted" for userspace, CAP_SYS_ADMIN is required. +- "user" for userspace, 'user_xattr' mount option is required for the + branch fs generally. + +Moreover there are some other categories. Aufs handles these rather +unpopular categories as the ordinary ones, ie. there is no special +condition nor exception. + +In copy-up, the support for XATTR on the dst branch may differ from the +src branch. In this case, the copy-up operation will get an error and +the original user operation which triggered the copy-up will fail. It +can happen that even all copy-up will fail. +When both of src and dst branches support XATTR and if an error occurs +during copying XATTR, then the copy-up should fail obviously. That is a +good reason and aufs should return an error to userspace. But when only +the src branch support that XATTR, aufs should not return an error. +For example, the src branch supports ACL but the dst branch doesn't +because the dst branch may natively un-support it or temporary +un-support it due to "noacl" mount option. Of course, the dst branch fs +may NOT return an error even if the XATTR is not supported. It is +totally up to the branch fs. + +Anyway when the aufs internal copy-up gets an error from the dst branch +fs, then aufs tries removing the just copied entry and returns the error +to the userspace. The worst case of this situation will be all copy-up +will fail. + +For the copy-up operation, there two basic approaches. +- copy the specified XATTR only (by category above), and return the + error unconditionally if it happens. +- copy all XATTR, and ignore the error on the specified category only. + +In order to support XATTR and to implement the correct behaviour, aufs +chooses the latter approach and introduces some new branch attributes, +"icexsec", "icexsys", "icextr", "icexusr", and "icexoth". +They correspond to the XATTR namespaces (see above). Additionally, to be +convenient, "icex" is also provided which means all "icex*" attributes +are set (here the word "icex" stands for "ignore copy-error on XATTR"). + +The meaning of these attributes is to ignore the error from setting +XATTR on that branch. +Note that aufs tries copying all XATTR unconditionally, and ignores the +error from the dst branch according to the specified attributes. + +Some XATTR may have its default value. The default value may come from +the parent dir or the environment. If the default value is set at the +file creating-time, it will be overwritten by copy-up. +Some contradiction may happen I am afraid. +Do we need another attribute to stop copying XATTR? I am unsure. For +now, aufs implements the branch attributes to ignore the error. diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt new file mode 100644 index 000000000000..9b983f3dd78a --- /dev/null +++ b/Documentation/filesystems/aufs/design/07export.txt @@ -0,0 +1,58 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Export Aufs via NFS +---------------------------------------------------------------------- +Here is an approach. +- like xino/xib, add a new file 'xigen' which stores aufs inode + generation. +- iget_locked(): initialize aufs inode generation for a new inode, and + store it in xigen file. +- destroy_inode(): increment aufs inode generation and store it in xigen + file. it is necessary even if it is not unlinked, because any data of + inode may be changed by UDBA. +- encode_fh(): for a root dir, simply return FILEID_ROOT. otherwise + build file handle by + + branch id (4 bytes) + + superblock generation (4 bytes) + + inode number (4 or 8 bytes) + + parent dir inode number (4 or 8 bytes) + + inode generation (4 bytes)) + + return value of exportfs_encode_fh() for the parent on a branch (4 + bytes) + + file handle for a branch (by exportfs_encode_fh()) +- fh_to_dentry(): + + find the index of a branch from its id in handle, and check it is + still exist in aufs. + + 1st level: get the inode number from handle and search it in cache. + + 2nd level: if not found in cache, get the parent inode number from + the handle and search it in cache. and then open the found parent + dir, find the matching inode number by vfs_readdir() and get its + name, and call lookup_one_len() for the target dentry. + + 3rd level: if the parent dir is not cached, call + exportfs_decode_fh() for a branch and get the parent on a branch, + build a pathname of it, convert it a pathname in aufs, call + path_lookup(). now aufs gets a parent dir dentry, then handle it as + the 2nd level. + + to open the dir, aufs needs struct vfsmount. aufs keeps vfsmount + for every branch, but not itself. to get this, (currently) aufs + searches in current->nsproxy->mnt_ns list. it may not be a good + idea, but I didn't get other approach. + + test the generation of the gotten inode. +- every inode operation: they may get EBUSY due to UDBA. in this case, + convert it into ESTALE for NFSD. +- readdir(): call lockdep_on/off() because filldir in NFSD calls + lookup_one_len(), vfs_getattr(), encode_fh() and others. diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt new file mode 100644 index 000000000000..647a86a65db7 --- /dev/null +++ b/Documentation/filesystems/aufs/design/08shwh.txt @@ -0,0 +1,52 @@ + +# Copyright (C) 2005-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Show Whiteout Mode (shwh) +---------------------------------------------------------------------- +Generally aufs hides the name of whiteouts. But in some cases, to show +them is very useful for users. For instance, creating a new middle layer +(branch) by merging existing layers. + +(borrowing aufs1 HOW-TO from a user, Michael Towers) +When you have three branches, +- Bottom: 'system', squashfs (underlying base system), read-only +- Middle: 'mods', squashfs, read-only +- Top: 'overlay', ram (tmpfs), read-write + +The top layer is loaded at boot time and saved at shutdown, to preserve +the changes made to the system during the session. +When larger changes have been made, or smaller changes have accumulated, +the size of the saved top layer data grows. At this point, it would be +nice to be able to merge the two overlay branches ('mods' and 'overlay') +and rewrite the 'mods' squashfs, clearing the top layer and thus +restoring save and load speed. + +This merging is simplified by the use of another aufs mount, of just the +two overlay branches using the 'shwh' option. +# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \ + aufs /livesys/merge_union + +A merged view of these two branches is then available at +/livesys/merge_union, and the new feature is that the whiteouts are +visible! +Note that in 'shwh' mode the aufs mount must be 'ro', which will disable +writing to all branches. Also the default mode for all branches is 'ro'. +It is now possible to save the combined contents of the two overlay +branches to a new squashfs, e.g.: +# mksquashfs /livesys/merge_union /path/to/newmods.squash + +This new squashfs archive can be stored on the boot device and the +initramfs will use it to replace the old one at the next boot. diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt new file mode 100644 index 000000000000..13e8583f2b91 --- /dev/null +++ b/Documentation/filesystems/aufs/design/10dynop.txt @@ -0,0 +1,47 @@ + +# Copyright (C) 2010-2019 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +Dynamically customizable FS operations +---------------------------------------------------------------------- +Generally FS operations (struct inode_operations, struct +address_space_operations, struct file_operations, etc.) are defined as +"static const", but it never means that FS have only one set of +operation. Some FS have multiple sets of them. For instance, ext2 has +three sets, one for XIP, for NOBH, and for normal. +Since aufs overrides and redirects these operations, sometimes aufs has +to change its behaviour according to the branch FS type. More importantly +VFS acts differently if a function (member in the struct) is set or +not. It means aufs should have several sets of operations and select one +among them according to the branch FS definition. + +In order to solve this problem and not to affect the behaviour of VFS, +aufs defines these operations dynamically. For instance, aufs defines +dummy direct_IO function for struct address_space_operations, but it may +not be set to the address_space_operations actually. When the branch FS +doesn't have it, aufs doesn't set it to its address_space_operations +while the function definition itself is still alive. So the behaviour +itself will not change, and it will return an error when direct_IO is +not set. + +The lifetime of these dynamically generated operation object is +maintained by aufs branch object. When the branch is removed from aufs, +the reference counter of the object is decremented. When it reaches +zero, the dynamically generated operation object will be freed. + +This approach is designed to support AIO (io_submit), Direct I/O and +XIP (DAX) mainly. +Currently this approach is applied to address_space_operations for +regular files only. diff --git a/MAINTAINERS b/MAINTAINERS index 78c72062884a..f5e7745c6d4b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2769,6 +2769,19 @@ F: include/linux/audit.h F: include/uapi/linux/audit.h F: kernel/audit* +AUFS (advanced multi layered unification filesystem) FILESYSTEM +M: "J. R. Okajima" <hooanon05g@gmail.com> +L: aufs-users@lists.sourceforge.net (members only) +L: linux-unionfs@vger.kernel.org +W: http://aufs.sourceforge.net +T: git://github.com/sfjro/aufs4-linux.git +S: Supported +F: Documentation/filesystems/aufs/ +F: Documentation/ABI/testing/debugfs-aufs +F: Documentation/ABI/testing/sysfs-aufs +F: fs/aufs/ +F: include/uapi/linux/aufs_type.h + AUXILIARY DISPLAY DRIVERS M: Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com> S: Maintained @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 2 -SUBLEVEL = 52 +SUBLEVEL = 60 EXTRAVERSION = NAME = Bobtail Squid @@ -490,7 +490,7 @@ export MODVERDIR := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_ve # 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 @@ -522,7 +522,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) -CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) +CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif ifneq ($(GCC_TOOLCHAIN),) diff --git a/arch/arm/Makefile b/arch/arm/Makefile index f7c9252117d3..d81ebbbbd7ad 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -64,7 +64,7 @@ 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 @@ -341,6 +341,9 @@ 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/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index 04bee4ff9dcb..53017a1e5ab0 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -1578,8 +1578,9 @@ reg-names = "rev"; ti,hwmods = "d_can0"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>; - clock-names = "fck"; + clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>, + <&dcan0_fck>; + clock-names = "fck", "osc"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0xcc000 0x2000>; @@ -1587,6 +1588,8 @@ dcan0: can@0 { compatible = "ti,am4372-d_can", "ti,am3352-d_can"; reg = <0x0 0x2000>; + clocks = <&dcan0_fck>; + clock-names = "fck"; syscon-raminit = <&scm_conf 0x644 0>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; @@ -1599,8 +1602,9 @@ reg-names = "rev"; ti,hwmods = "d_can1"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>; - clock-names = "fck"; + clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>, + <&dcan1_fck>; + clock-names = "fck", "osc"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0xd0000 0x2000>; @@ -1608,6 +1612,8 @@ dcan1: can@0 { compatible = "ti,am4372-d_can", "ti,am3352-d_can"; reg = <0x0 0x2000>; + clocks = <&dcan1_fck>; + clock-name = "fck"; syscon-raminit = <&scm_conf 0x644 1>; interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 3f4bb44d85f0..669da3a33d82 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -339,7 +339,8 @@ comphy: phy@18300 { compatible = "marvell,armada-380-comphy"; - reg = <0x18300 0x100>; + reg-names = "comphy", "conf"; + reg = <0x18300 0x100>, <0x18460 4>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi index c23ba229fd05..8c33510c9519 100644 --- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi @@ -105,19 +105,16 @@ sound-digital { compatible = "simple-audio-card"; simple-audio-card,name = "tda1997x-audio"; + simple-audio-card,format = "i2s"; + simple-audio-card,bitclock-master = <&sound_codec>; + simple-audio-card,frame-master = <&sound_codec>; - simple-audio-card,dai-link@0 { - format = "i2s"; - - cpu { - sound-dai = <&ssi2>; - }; + sound_cpu: simple-audio-card,cpu { + sound-dai = <&ssi1>; + }; - codec { - bitclock-master; - frame-master; - sound-dai = <&hdmi_receiver>; - }; + sound_codec: simple-audio-card,codec { + sound-dai = <&hdmi_receiver>; }; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi index 7814f1ef0804..fde56f98398d 100644 --- a/arch/arm/boot/dts/imx6qdl-icore.dtsi +++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi @@ -384,7 +384,7 @@ pinctrl_usbotg: usbotggrp { fsl,pins = < - MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059 + MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059 >; }; @@ -396,6 +396,7 @@ MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070 MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070 MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070 + MX6QDL_PAD_GPIO_1__GPIO1_IO01 0x1b0b0 >; }; diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 315044ccd65f..e4719566133c 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -99,7 +99,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy0>; fsl,magic-packet; status = "okay"; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index f6972deb5e39..865528b134d8 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -213,7 +213,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy2>; status = "okay"; }; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 7f2ddb78da5f..4227da71cc62 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -105,6 +105,14 @@ linux,code = <SW_FRONT_PROXIMITY>; linux,can-disable; }; + + machine_cover { + label = "Machine Cover"; + gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ + linux,input-type = <EV_SW>; + linux,code = <SW_MACHINE_COVER>; + linux,can-disable; + }; }; isp1707: isp1707 { @@ -814,10 +822,6 @@ pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; bus-width = <4>; - /* For debugging, it is often good idea to remove this GPIO. - It means you can remove back cover (to reboot by removing - battery) and still use the MMC card. */ - cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ }; /* most boards use vaux3, only some old versions use vmmc2 instead */ diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts index f51601af89a2..68da21cbdd8f 100644 --- a/arch/arm/boot/dts/r8a7793-gose.dts +++ b/arch/arm/boot/dts/r8a7793-gose.dts @@ -339,7 +339,7 @@ reg = <0x20>; remote = <&vin1>; - port { + ports { #address-cells = <1>; #size-cells = <0>; @@ -399,7 +399,7 @@ interrupts = <2 IRQ_TYPE_LEVEL_LOW>; default-input = <0>; - port { + ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi index ec1966480f2f..9a14b5fe3b57 100644 --- a/arch/arm/boot/dts/socfpga.dtsi +++ b/arch/arm/boot/dts/socfpga.dtsi @@ -709,7 +709,7 @@ }; }; - L2: l2-cache@fffef000 { + L2: cache-controller@fffef000 { compatible = "arm,pl310-cache"; reg = <0xfffef000 0x1000>; interrupts = <0 38 0x04>; diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi index ae24599d5829..6378e6461bf7 100644 --- a/arch/arm/boot/dts/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/socfpga_arria10.dtsi @@ -633,7 +633,7 @@ reg = <0xffcfb100 0x80>; }; - L2: l2-cache@fffff000 { + L2: cache-controller@fffff000 { compatible = "arm,pl310-cache"; reg = <0xfffff000 0x1000>; interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index ef6ec526f394..d777ec70a6f0 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -198,7 +198,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi index 510568a19e9d..c0775e391df8 100644 --- a/arch/arm/boot/dts/sun5i.dtsi +++ b/arch/arm/boot/dts/sun5i.dtsi @@ -117,7 +117,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 794c915f504b..259b9e1555b6 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -180,7 +180,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi index 53edd1faee99..3635b251e250 100644 --- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi +++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus-v1.2.dtsi @@ -16,16 +16,28 @@ regulator-type = "voltage"; regulator-boot-on; regulator-always-on; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1300000>; + regulator-min-microvolt = <1108475>; + regulator-max-microvolt = <1308475>; regulator-ramp-delay = <50>; /* 4ms */ gpios = <&r_pio 0 1 GPIO_ACTIVE_HIGH>; /* PL1 */ gpios-states = <0x1>; - states = <1100000 0x0 - 1300000 0x1>; + states = <1108475 0x0 + 1308475 0x1>; }; }; &cpu0 { cpu-supply = <®_vdd_cpux>; }; + +&cpu1 { + cpu-supply = <®_vdd_cpux>; +}; + +&cpu2 { + cpu-supply = <®_vdd_cpux>; +}; + +&cpu3 { + cpu-supply = <®_vdd_cpux>; +}; 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/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index af8b8e15f589..35cec1c78485 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -677,6 +677,12 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } +static int watchpoint_fault_on_uaccess(struct pt_regs *regs, + struct arch_hw_breakpoint *info) +{ + return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER; +} + static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { @@ -736,16 +742,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, } pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + + /* + * If we triggered a user watchpoint from a uaccess routine, + * then handle the stepping ourselves since userspace really + * can't help us with this. + */ + if (watchpoint_fault_on_uaccess(regs, info)) + goto step; + perf_bp_event(wp, regs); /* - * If no overflow handler is present, insert a temporary - * mismatch breakpoint so we can single-step over the - * watchpoint trigger. + * Defer stepping to the overflow handler if one is installed. + * Otherwise, insert a temporary mismatch breakpoint so that + * we can single-step over the watchpoint trigger. */ - if (is_default_overflow_handler(wp)) - enable_single_step(wp, instruction_pointer(regs)); + if (!is_default_overflow_handler(wp)) + goto unlock; +step: + enable_single_step(wp, instruction_pointer(regs)); unlock: rcu_read_unlock(); } diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index 71778bb0475b..a082f6e4f0f4 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -22,6 +22,19 @@ * A simple function epilogue looks like this: * ldm sp, {fp, sp, pc} * + * When compiled with clang, pc and sp are not pushed. A simple function + * prologue looks like this when built with clang: + * + * stmdb {..., fp, lr} + * add fp, sp, #x + * sub sp, sp, #y + * + * A simple function epilogue looks like this when built with clang: + * + * sub sp, fp, #x + * ldm {..., fp, pc} + * + * * Note that with framepointer enabled, even the leaf functions have the same * prologue and epilogue, therefore we can ignore the LR value in this case. */ @@ -34,6 +47,16 @@ int notrace unwind_frame(struct stackframe *frame) low = frame->sp; high = ALIGN(low, THREAD_SIZE); +#ifdef CONFIG_CC_IS_CLANG + /* check current frame pointer is within bounds */ + if (fp < low + 4 || fp > high - 4) + return -EINVAL; + + frame->sp = frame->fp; + frame->fp = *(unsigned long *)(fp); + frame->pc = frame->lr; + frame->lr = *(unsigned long *)(fp + 4); +#else /* check current frame pointer is within bounds */ if (fp < low + 12 || fp > high - 4) return -EINVAL; @@ -42,6 +65,7 @@ int notrace unwind_frame(struct stackframe *frame) frame->fp = *(unsigned long *)(fp - 12); frame->sp = *(unsigned long *)(fp - 8); frame->pc = *(unsigned long *)(fp - 4); +#endif return 0; } diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 6550a6231f6b..21591fff6b0e 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -591,13 +591,13 @@ static void __init at91_pm_sram_init(void) sram_pool = gen_pool_get(&pdev->dev, NULL); if (!sram_pool) { pr_warn("%s: sram pool unavailable!\n", __func__); - return; + goto out_put_device; } sram_base = gen_pool_alloc(sram_pool, at91_pm_suspend_in_sram_sz); if (!sram_base) { pr_warn("%s: unable to alloc sram!\n", __func__); - return; + goto out_put_device; } sram_pbase = gen_pool_virt_to_phys(sram_pool, sram_base); @@ -605,12 +605,17 @@ static void __init at91_pm_sram_init(void) at91_pm_suspend_in_sram_sz, false); if (!at91_suspend_sram_fn) { pr_warn("SRAM: Could not map\n"); - return; + goto out_put_device; } /* Copy the pm suspend handler to SRAM */ at91_suspend_sram_fn = fncpy(at91_suspend_sram_fn, &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); + return; + +out_put_device: + put_device(&pdev->dev); + return; } static bool __init at91_is_pm_mode_active(int pm_mode) diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S index ed57c879d4e1..2591cba61937 100644 --- a/arch/arm/mach-at91/pm_suspend.S +++ b/arch/arm/mach-at91/pm_suspend.S @@ -268,6 +268,10 @@ ENDPROC(at91_backup_mode) orr tmp1, tmp1, #AT91_PMC_KEY str tmp1, [pmc, #AT91_CKGR_MOR] + /* Quirk for SAM9X60's PMC */ + nop + nop + wait_mckrdy /* Enable the crystal oscillator */ diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c index 9a681b421ae1..cd861c57d5ad 100644 --- a/arch/arm/mach-exynos/mcpm-exynos.c +++ b/arch/arm/mach-exynos/mcpm-exynos.c @@ -26,6 +26,7 @@ #define EXYNOS5420_USE_L2_COMMON_UP_STATE BIT(30) static void __iomem *ns_sram_base_addr __ro_after_init; +static bool secure_firmware __ro_after_init; /* * The common v7_exit_coherency_flush API could not be used because of the @@ -58,15 +59,16 @@ static void __iomem *ns_sram_base_addr __ro_after_init; static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster) { unsigned int cpunr = cpu + (cluster * EXYNOS5420_CPUS_PER_CLUSTER); + bool state; pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster); if (cpu >= EXYNOS5420_CPUS_PER_CLUSTER || cluster >= EXYNOS5420_NR_CLUSTERS) return -EINVAL; - if (!exynos_cpu_power_state(cpunr)) { - exynos_cpu_power_up(cpunr); - + state = exynos_cpu_power_state(cpunr); + exynos_cpu_power_up(cpunr); + if (!state && secure_firmware) { /* * This assumes the cluster number of the big cores(Cortex A15) * is 0 and the Little cores(Cortex A7) is 1. @@ -258,6 +260,8 @@ static int __init exynos_mcpm_init(void) return -ENOMEM; } + secure_firmware = exynos_secure_firmware_available(); + /* * To increase the stability of KFC reset we need to program * the PMU SPARE3 register diff --git a/arch/arm/mach-socfpga/pm.c b/arch/arm/mach-socfpga/pm.c index 6ed887cf8dc9..365c0428b21b 100644 --- a/arch/arm/mach-socfpga/pm.c +++ b/arch/arm/mach-socfpga/pm.c @@ -49,14 +49,14 @@ static int socfpga_setup_ocram_self_refresh(void) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, socfpga_sdram_self_refresh_sz); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -67,7 +67,7 @@ static int socfpga_setup_ocram_self_refresh(void) if (!suspend_ocram_base) { pr_warn("%s: __arm_ioremap_exec failed!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } /* Copy the code that puts DDR in self refresh to ocram */ @@ -81,6 +81,8 @@ static int socfpga_setup_ocram_self_refresh(void) if (!socfpga_sdram_self_refresh_in_ocram) ret = -EFAULT; +put_device: + put_device(&pdev->dev); put_node: of_node_put(np); diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index e76155d5840b..864d01e53a92 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -452,8 +452,16 @@ 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); @@ -476,8 +484,9 @@ 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/boot/dts/amlogic/meson-g12a.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi index 4a47344dc252..85b3ba605a23 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12a.dtsi @@ -605,6 +605,7 @@ dr_mode = "host"; snps,dis_u2_susphy_quirk; snps,quirk-frame-length-adjustment; + snps,parkmode-disable-ss-quirk; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts index 82b1c4851147..e034bbff8e66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts @@ -9,7 +9,7 @@ #include <dt-bindings/input/input.h> -#include "meson-gxl-s905x.dtsi" +#include "meson-gxl-s805x.dtsi" / { compatible = "libretech,aml-s805x-ac", "amlogic,s805x", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts index 70433e023fda..9abfc2512b69 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts @@ -9,7 +9,7 @@ #include <dt-bindings/input/input.h> -#include "meson-gxl-s905x.dtsi" +#include "meson-gxl-s805x.dtsi" / { compatible = "amlogic,p241", "amlogic,s805x", "amlogic,meson-gxl"; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi new file mode 100644 index 000000000000..f9d705648426 --- /dev/null +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (c) 2020 BayLibre SAS + * Author: Neil Armstrong <narmstrong@baylibre.com> + */ + +#include "meson-gxl-s905x.dtsi" + +/ { + compatible = "amlogic,s805x", "amlogic,meson-gxl"; +}; + +/* The S805X Package doesn't seem to handle the 744MHz OPP correctly */ +&mali { + assigned-clocks = <&clkc CLKID_MALI_0_SEL>, + <&clkc CLKID_MALI_0>, + <&clkc CLKID_MALI>; /* Glitch free mux */ + assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>, + <0>, /* Do Nothing */ + <&clkc CLKID_MALI_0>; + assigned-clock-rates = <0>, /* Do Nothing */ + <666666666>, + <0>; /* Do Nothing */ +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 3093ae421b17..f66a545aab51 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -291,6 +291,11 @@ }; }; +&hwrng { + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; +}; + &i2c_A { clocks = <&clkc CLKID_I2C>; }; diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 00dd89b92b42..d991eae5202f 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -152,6 +152,7 @@ regulator-min-microvolt = <700000>; regulator-max-microvolt = <1150000>; regulator-enable-ramp-delay = <125>; + regulator-always-on; }; ldo8_reg: LDO8 { diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts index e035cf195b19..8c4bfbaf3a80 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts +++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts @@ -530,6 +530,17 @@ status = "ok"; compatible = "adi,adv7533"; reg = <0x39>; + adi,dsi-lanes = <4>; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + }; + port@1 { + reg = <1>; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index c14205cd6bf5..3e47150c05ec 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -516,7 +516,7 @@ reg = <0x39>; interrupt-parent = <&gpio1>; interrupts = <1 2>; - pd-gpio = <&gpio0 4 0>; + pd-gpios = <&gpio0 4 0>; adi,dsi-lanes = <4>; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi index 242aaea68804..1235830ffd0b 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi @@ -508,7 +508,7 @@ pins = "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; cdc_pdm_lines_sus: pdm_lines_off { @@ -537,7 +537,7 @@ pins = "gpio113", "gpio114", "gpio115", "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -565,7 +565,7 @@ pinconf { pins = "gpio110"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -591,7 +591,7 @@ pinconf { pins = "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_mclk_tlmm_lines_sus: mclk_lines_off { @@ -619,7 +619,7 @@ pins = "gpio112", "gpio117", "gpio118", "gpio119"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_sec_tlmm_lines_sus: tlmm_lines_off { diff --git a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts index 54515eaf0310..b9088a4e0a4a 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts +++ b/arch/arm64/boot/dts/renesas/r8a7795-h3ulcb.dts @@ -2,7 +2,7 @@ /* * Device Tree Source for the H3ULCB (R-Car Starter Kit Premier) board * - * Copyright (C) 2016 Renesas Electronics Corp. + * Copyright (C) 2016-2017 Renesas Electronics Corp. * Copyright (C) 2016 Cogent Embedded, Inc. */ @@ -34,6 +34,33 @@ device_type = "memory"; reg = <0x7 0x00000000 0x0 0x40000000>; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* device specific region for Lossy Decompression */ + lossy_decompress: linux,lossy_decompress@54000000 { + no-map; + reg = <0x00000000 0x54000000 0x0 0x03000000>; + }; + + /* global autoconfigured region for contiguous allocations */ + linux,cma@57000000 { + compatible = "shared-dma-pool"; + reusable; + reg = <0x00000000 0x57000000 0x0 0x19000000>; + linux,cma-default; + }; + + /* device specific region for contiguous allocations */ + mmp_reserved: linux,multimedia@70000000 { + compatible = "shared-dma-pool"; + reusable; + reg = <0x00000000 0x70000000 0x0 0x10000000>; + }; + }; }; &du { diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi index 7a09576b3112..e8d431028fc7 100644 --- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi @@ -38,6 +38,37 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; }; + + wlan_en: regulator-wlan_en { + compatible = "regulator-fixed"; + regulator-name = "wlan-en-regulator"; + + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + + gpio = <&gpio_exp_74 4 GPIO_ACTIVE_HIGH>; + startup-delay-us = <70000>; + enable-active-high; + }; + + mpcie_3v3: regulator-mpcie_3v3 { + compatible = "regulator-fixed"; + regulator-name = "mPCIe 3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio_exp_77 14 GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + mpcie_1v8: regulator-mpcie_1v8 { + compatible = "regulator-fixed"; + regulator-name = "mPCIe 1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + gpio = <&gpio_exp_77 15 GPIO_ACTIVE_HIGH>; + startup-delay-us = <200000>; + enable-active-high; + }; }; &can0 { @@ -88,6 +119,13 @@ line-name = "Audio_Out_OFF"; }; + sd-wifi-mux { + gpio-hog; + gpios = <5 GPIO_ACTIVE_HIGH>; + output-low; /* Connect WL1837 */ + line-name = "SD WiFi mux"; + }; + hub_pwen { gpio-hog; gpios = <6 GPIO_ACTIVE_HIGH>; @@ -186,6 +224,15 @@ }; }; +&gpio5 { + gpio_exp_77_int { + gpio-hog; + gpios = <9 0>; + input; + line-name = "gpio-exp-77-int"; + }; +}; + &i2c4 { gpio_exp_76: gpio@76 { compatible = "ti,tca9539"; @@ -205,6 +252,31 @@ interrupt-controller; interrupt-parent = <&gpio5>; interrupts = <9 IRQ_TYPE_EDGE_FALLING>; + + mpcie_wake { + gpio-hog; + gpios = <0 GPIO_ACTIVE_HIGH>; + output-low; + line-name = "mPCIe WAKE#"; + }; + mpcie_wdisable { + gpio-hog; + gpios = <1 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "mPCIe W_DISABLE"; + }; + mpcie_clreq { + gpio-hog; + gpios = <2 GPIO_ACTIVE_HIGH>; + input; + line-name = "mPCIe CLKREQ#"; + }; + mpcie_ovc { + gpio-hog; + gpios = <3 GPIO_ACTIVE_HIGH>; + input; + line-name = "mPCIe OVC"; + }; }; i2cswitch4: i2c-switch@71 { @@ -231,6 +303,9 @@ &pciec1 { status = "okay"; + + pcie3v3-supply = <&mpcie_3v3>; + pcie1v8-supply = <&mpcie_1v8>; }; &pfc { @@ -254,6 +329,12 @@ function = "scif1"; }; + sdhi3_pins: sdhi3 { + groups = "sdhi3_data4", "sdhi3_ctrl"; + function = "sdhi3"; + power-source = <3300>; + }; + usb0_pins: usb0 { groups = "usb0"; function = "usb0"; @@ -273,6 +354,30 @@ status = "okay"; }; +&sdhi3 { + pinctrl-0 = <&sdhi3_pins>; + pinctrl-names = "default"; + + vmmc-supply = <&wlan_en>; + vqmmc-supply = <&wlan_en>; + bus-width = <4>; + no-1-8-v; + non-removable; + cap-power-off-card; + keep-power-in-suspend; + max-frequency = <26000000>; + status = "okay"; + + #address-cells = <1>; + #size-cells = <0>; + wlcore: wlcore@2 { + compatible = "ti,wl1837"; + reg = <2>; + interrupt-parent = <&gpio1>; + interrupts = <25 IRQ_TYPE_EDGE_FALLING>; + }; +}; + &usb2_phy0 { pinctrl-0 = <&usb0_pins>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi index e17311e09082..216aafd90e7f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi @@ -156,7 +156,7 @@ pinctrl-0 = <&rgmii_pins>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_HIGH>; + snps,reset-gpio = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>; tx_delay = <0x10>; rx_delay = <0x10>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 62ea288a1a70..45b86933c6ea 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -101,7 +101,7 @@ vcc5v0_host: vcc5v0-host-regulator { compatible = "regulator-fixed"; - gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>; enable-active-low; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_host_en>; @@ -157,7 +157,7 @@ phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>; + snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; tx_delay = <0x10>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index 41fa080d9364..334cbf04e6bc 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -226,6 +226,19 @@ dma-coherent; }; + sdhci1: sdhci@4fa0000 { + compatible = "ti,am654-sdhci-5.1"; + reg = <0x0 0x4fa0000 0x0 0x260>, <0x0 0x4fb0000 0x0 0x134>; + power-domains = <&k3_pds 48>; + clocks = <&k3_clks 48 0>, <&k3_clks 48 1>; + clock-names = "clk_ahb", "clk_xin"; + interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>; + ti,otap-del-sel = <0x2>; + ti,trm-icp = <0x8>; + no-1-8-v; + dma-coherent; + }; + scm_conf: scm_conf@100000 { compatible = "syscon", "simple-mfd"; reg = <0 0x00100000 0 0x1c000>; diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi index 6f7d2b316ded..a409622da769 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi @@ -87,4 +87,45 @@ compatible = "ti,am654-adc", "ti,am3359-adc"; }; }; + + fss: fss@47000000 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + ospi0: spi@47040000 { + compatible = "ti,am654-ospi", "cdns,qspi-nor"; + reg = <0x0 0x47040000 0x0 0x100>, + <0x5 0x00000000 0x1 0x0000000>; + interrupts = <GIC_SPI 552 IRQ_TYPE_LEVEL_HIGH>; + cdns,fifo-depth = <256>; + cdns,fifo-width = <4>; + cdns,trigger-address = <0x50000000>; + cdns,delay-elem-ps = <80>; + clocks = <&k3_clks 55 5>; + assigned-clocks = <&k3_clks 55 5>; + assigned-clock-parents = <&k3_clks 55 7>; + assigned-clock-rates = <166666666>; + power-domains = <&k3_pds 55>; + #address-cells = <1>; + #size-cells = <0>; + dma-coherent; + }; + + ospi1: spi@47050000 { + compatible = "ti,am654-ospi", "cdns,qspi-nor"; + reg = <0x0 0x47050000 0x0 0x100>, + <0x7 0x00000000 0x1 0x00000000>; + interrupts = <GIC_SPI 553 IRQ_TYPE_LEVEL_HIGH>; + cdns,fifo-depth = <256>; + cdns,fifo-width = <4>; + cdns,trigger-address = <0x58000000>; + clocks = <&k3_clks 55 16>; + power-domains = <&k3_pds 55>; + #address-cells = <1>; + #size-cells = <0>; + dma-coherent; + }; + }; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65.dtsi b/arch/arm64/boot/dts/ti/k3-am65.dtsi index 50f4be2047a9..e49e52c7e8f5 100644 --- a/arch/arm64/boot/dts/ti/k3-am65.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65.dtsi @@ -74,7 +74,10 @@ <0x00 0x42040000 0x00 0x42040000 0x00 0x03ac2400>, <0x00 0x45100000 0x00 0x45100000 0x00 0x00c24000>, <0x00 0x46000000 0x00 0x46000000 0x00 0x00200000>, - <0x00 0x47000000 0x00 0x47000000 0x00 0x00068400>; + <0x00 0x47000000 0x00 0x47000000 0x00 0x00068400>, + <0x00 0x50000000 0x00 0x50000000 0x00 0x8000000>, + <0x05 0x00000000 0x05 0x00000000 0x01 0x0000000>, + <0x07 0x00000000 0x07 0x00000000 0x01 0x0000000>; cbass_mcu: interconnect@28380000 { compatible = "simple-bus"; @@ -85,7 +88,10 @@ <0x00 0x42040000 0x00 0x42040000 0x00 0x03ac2400>, /* WKUP */ <0x00 0x45100000 0x00 0x45100000 0x00 0x00c24000>, /* MMRs, remaining NAVSS */ <0x00 0x46000000 0x00 0x46000000 0x00 0x00200000>, /* CPSW */ - <0x00 0x47000000 0x00 0x47000000 0x00 0x00068400>; /* OSPI space 1 */ + <0x00 0x47000000 0x00 0x47000000 0x00 0x00068400>, /* OSPI space 1 */ + <0x00 0x50000000 0x00 0x50000000 0x00 0x8000000>, /* FSS OSPI0 data region 1 */ + <0x05 0x00000000 0x05 0x00000000 0x01 0x0000000>, /* FSS OSPI0 data region 3*/ + <0x07 0x00000000 0x07 0x00000000 0x01 0x0000000>; /* FSS OSPI1 data region 3*/ cbass_wakeup: interconnect@42040000 { compatible = "simple-bus"; diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts index cf1aa276a1ea..db60fc29a424 100644 --- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts +++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts @@ -42,6 +42,22 @@ AM65X_WKUP_IOPAD(0x00e4, PIN_INPUT, 0) /* (AD6) WKUP_I2C0_SDA */ >; }; + + mcu_fss0_ospi0_pins_default: mcu-fss0-ospi0-pins_default { + pinctrl-single,pins = < + AM65X_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* (V1) MCU_OSPI0_CLK */ + AM65X_WKUP_IOPAD(0x0008, PIN_INPUT, 0) /* (U2) MCU_OSPI0_DQS */ + AM65X_WKUP_IOPAD(0x000c, PIN_INPUT, 0) /* (U4) MCU_OSPI0_D0 */ + AM65X_WKUP_IOPAD(0x0010, PIN_INPUT, 0) /* (U5) MCU_OSPI0_D1 */ + AM65X_WKUP_IOPAD(0x0014, PIN_INPUT, 0) /* (T2) MCU_OSPI0_D2 */ + AM65X_WKUP_IOPAD(0x0018, PIN_INPUT, 0) /* (T3) MCU_OSPI0_D3 */ + AM65X_WKUP_IOPAD(0x001c, PIN_INPUT, 0) /* (T4) MCU_OSPI0_D4 */ + AM65X_WKUP_IOPAD(0x0020, PIN_INPUT, 0) /* (T5) MCU_OSPI0_D5 */ + AM65X_WKUP_IOPAD(0x0024, PIN_INPUT, 0) /* (R2) MCU_OSPI0_D6 */ + AM65X_WKUP_IOPAD(0x0028, PIN_INPUT, 0) /* (R3) MCU_OSPI0_D7 */ + AM65X_WKUP_IOPAD(0x002c, PIN_OUTPUT, 0) /* (R4) MCU_OSPI0_CSn0 */ + >; + }; }; &main_pmx0 { @@ -87,6 +103,19 @@ >; }; + main_mmc1_pins_default: main_mmc1_pins_default { + pinctrl-single,pins = < + AM65X_IOPAD(0x02d4, PIN_INPUT_PULLDOWN, 0) /* (C27) MMC1_CLK */ + AM65X_IOPAD(0x02d8, PIN_INPUT_PULLUP, 0) /* (C28) MMC1_CMD */ + AM65X_IOPAD(0x02d0, PIN_INPUT_PULLUP, 0) /* (D28) MMC1_DAT0 */ + AM65X_IOPAD(0x02cc, PIN_INPUT_PULLUP, 0) /* (E27) MMC1_DAT1 */ + AM65X_IOPAD(0x02c8, PIN_INPUT_PULLUP, 0) /* (D26) MMC1_DAT2 */ + AM65X_IOPAD(0x02c4, PIN_INPUT_PULLUP, 0) /* (D27) MMC1_DAT3 */ + AM65X_IOPAD(0x02dc, PIN_INPUT_PULLUP, 0) /* (B24) MMC1_SDCD */ + AM65X_IOPAD(0x02e0, PIN_INPUT, 0) /* (C24) MMC1_SDWP */ + >; + }; + usb1_pins_default: usb1_pins_default { pinctrl-single,pins = < AM65X_IOPAD(0x02c0, PIN_OUTPUT, 0) /* (AC8) USB1_DRVVBUS */ @@ -195,6 +224,12 @@ ti,driver-strength-ohm = <50>; }; +&sdhci1 { + pinctrl-names = "default"; + pinctrl-0 = <&main_mmc1_pins_default>; + ti,driver-strength-ohm = <50>; +}; + &dwc3_1 { status = "okay"; }; @@ -228,3 +263,25 @@ ti,adc-channels = <0 1 2 3 4 5 6 7>; }; }; + +&ospi0 { + pinctrl-names = "default"; + pinctrl-0 = <&mcu_fss0_ospi0_pins_default>; + + flash@0{ + compatible = "jedec,spi-nor"; + reg = <0x0>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <8>; + spi-max-frequency = <50000000>; + spi-dqs; + cdns,tshsl-ns = <60>; + cdns,tsd2d-ns = <60>; + cdns,tchsh-ns = <60>; + cdns,tslch-ns = <60>; + cdns,read-delay = <2>; + cdns,phy-mode; + #address-cells = <1>; + #size-cells = <1>; + }; +}; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 97624ee1aaa3..aa9ad4097361 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -71,13 +71,13 @@ static inline void apply_alternatives_module(void *start, size_t length) { } ALTINSTR_ENTRY(feature,cb) \ ".popsection\n" \ " .if " __stringify(cb) " == 0\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".else\n\t" \ "663:\n\t" \ "664:\n\t" \ @@ -107,9 +107,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection +664: .previous .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .endif @@ -150,7 +150,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -169,9 +169,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -182,7 +182,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_endif 664: .if .Lasm_alt_mode==0 - .popsection + .previous .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index d064a50deb5f..5665a3fc14be 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -19,16 +19,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index d8ec5bb881c2..6c289542cee5 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -111,6 +111,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5ab5200b2bdc..d48667b04c41 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -14,6 +14,19 @@ #define MCOUNT_ADDR ((unsigned long)_mcount) #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +/* + * Currently, gcc tends to save the link register after the local variables + * on the stack. This causes the max stack tracer to report the function + * frame sizes for the wrong functions. By defining + * ARCH_FTRACE_SHIFT_STACK_TRACER, it will tell the stack tracer to expect + * to find the return address on the stack after the local variables have + * been set up. + * + * Note, this may change in the future, and we will need to deal with that + * if it were to happen. + */ +#define ARCH_FTRACE_SHIFT_STACK_TRACER 1 + #ifndef __ASSEMBLY__ #include <linux/compat.h> diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index d328540cb85e..a7ac50fb5abc 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -3,7 +3,6 @@ #define __ASM_POINTER_AUTH_H #include <linux/bitops.h> -#include <linux/random.h> #include <asm/cpufeature.h> #include <asm/memory.h> @@ -30,6 +29,13 @@ struct ptrauth_keys { struct ptrauth_key apga; }; +/* + * Only include random.h once ptrauth_keys_* structures are defined + * to avoid yet another circular include hell (random.h * ends up + * including asm/smp.h, which requires ptrauth_keys_kernel). + */ +#include <linux/random.h> + static inline void ptrauth_keys_init(struct ptrauth_keys *keys) { if (system_supports_address_auth()) { diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 65299a2dcf9c..cfc0672013f6 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -34,6 +34,10 @@ static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->regs[0]; + + if (is_compat_thread(task_thread_info(task))) + error = sign_extend64(error, 31); + return IS_ERR_VALUE(error) ? error : 0; } @@ -47,7 +51,13 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - regs->regs[0] = (long) error ? error : val; + if (error) + val = error; + + if (is_compat_thread(task_thread_info(task))) + val = lower_32_bits(val); + + regs->regs[0] = val; } #define SYSCALL_MAX_ARGS 6 diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 2372e97db29c..90441da764ab 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -100,6 +100,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index d1757ef1b1e7..73039949b5ce 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature) */ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { - unsigned long replptr; - - if (kernel_text_address(pc)) - return true; - - replptr = (unsigned long)ALT_REPL_PTR(alt); - if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return false; - - /* - * Branching into *another* alternate sequence is doomed, and - * we're not even trying to fix it up. - */ - BUG(); + unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); + return !(pc >= replptr && pc <= (replptr + alt->alt_len)); } #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index f8719bd30850..d64a3c1e1b6b 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ -static void set_regs_spsr_ss(struct pt_regs *regs) +static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } -NOKPROBE_SYMBOL(set_regs_spsr_ss); +NOKPROBE_SYMBOL(set_user_regs_spsr_ss); -static void clear_regs_spsr_ss(struct pt_regs *regs) +static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } -NOKPROBE_SYMBOL(clear_regs_spsr_ss); +NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); + +#define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) +#define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) static DEFINE_SPINLOCK(debug_hook_lock); static LIST_HEAD(user_step_hook); @@ -207,16 +210,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_step_hook : &kernel_step_hook; - rcu_read_lock(); - + /* + * Since single-step exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - rcu_read_unlock(); - return retval; } NOKPROBE_SYMBOL(call_step_hook); @@ -305,14 +308,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; - rcu_read_lock(); + /* + * Since brk exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~hook->mask) == hook->imm) fn = hook->fn; } - rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } @@ -391,17 +396,26 @@ void user_rewind_single_step(struct task_struct *task) * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) + set_user_regs_spsr_ss(regs); + else + clear_user_regs_spsr_ss(regs); +} + /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 96e90e270042..1439cff99a28 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -154,7 +154,7 @@ armv8pmu_events_sysfs_show(struct device *dev, pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - return sprintf(page, "event=0x%03llx\n", pmu_attr->id); + return sprintf(page, "event=0x%04llx\n", pmu_attr->id); } #define ARMV8_EVENT_ATTR_RESOLVE(m) #m @@ -303,10 +303,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj, test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) return attr->mode; - pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; - if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && - test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap)) - return attr->mode; + if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) { + u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; + + if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS && + test_bit(id, cpu_pmu->pmceid_ext_bitmap)) + return attr->mode; + } return 0; } diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 666b225aeb3a..7c6ae5cf0365 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->pc; + return regs->regs[idx]; } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9b4edc23a442..49bc065cf3f0 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1819,12 +1819,23 @@ static void tracehook_report_syscall(struct pt_regs *regs, saved_reg = regs->regs[regno]; regs->regs[regno] = dir; - if (dir == PTRACE_SYSCALL_EXIT) + if (dir == PTRACE_SYSCALL_ENTER) { + if (tracehook_report_syscall_entry(regs)) + forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else if (!test_thread_flag(TIF_SINGLESTEP)) { tracehook_report_syscall_exit(regs, 0); - else if (tracehook_report_syscall_entry(regs)) - forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else { + regs->regs[regno] = saved_reg; - regs->regs[regno] = saved_reg; + /* + * Signal a pseudo-step exception since we are stepping but + * tracer modifications to the registers may have rewound the + * state machine. + */ + tracehook_report_syscall_exit(regs, 1); + } } int syscall_trace_enter(struct pt_regs *regs) @@ -1847,12 +1858,14 @@ int syscall_trace_enter(struct pt_regs *regs) void syscall_trace_exit(struct pt_regs *regs) { + unsigned long flags = READ_ONCE(current_thread_info()->flags); + audit_syscall_exit(regs); - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, regs_return_value(regs)); - if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); @@ -1930,8 +1943,8 @@ static int valid_native_regs(struct user_pt_regs *regs) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) - regs->pstate &= ~DBG_SPSR_SS; + /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ + user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index dd2cdc0d5be2..ddb757b2c3e5 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -782,7 +782,6 @@ static void setup_restart_syscall(struct pt_regs *regs) */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - struct task_struct *tsk = current; sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; @@ -806,14 +805,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) */ ret |= !valid_user_regs(®s->user_regs, current); - /* - * Fast forward the stepping logic so we step into the signal - * handler. - */ - if (!ret) - user_fastforward_single_step(tsk); - - signal_setup_done(ret, ksig, 0); + /* Step into the signal handler if we are stepping */ + signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..1457a0ba83db 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, ret = do_ni_syscall(regs, scno); } + if (is_compat_task()) + ret = lower_32_bits(ret); + regs->regs[0] = ret; } @@ -121,7 +124,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags)) { + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { /* * We're off to userspace, where interrupts are * always enabled after we restore the flags from diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 6ef635c35ff3..61d63657ab59 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -172,9 +172,6 @@ SECTIONS *(.altinstructions) __alt_instructions_end = .; } - .altinstr_replacement : { - *(.altinstr_replacement) - } . = ALIGN(PAGE_SIZE); __inittext_end = .; diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index 3c5def10d486..caa260f877f2 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -139,7 +139,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); - memblock_add(memory_start, memory_end - memory_start); + memblock_add(_rambase, memory_end - _rambase); + memblock_reserve(_rambase, memory_start - _rambase); /* Keep a copy of command line */ *cmdline_p = &command_line[0]; diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c index 9bfa17015768..c432bfafe63e 100644 --- a/arch/m68k/mac/iop.c +++ b/arch/m68k/mac/iop.c @@ -183,7 +183,7 @@ static __inline__ void iop_writeb(volatile struct mac_iop *iop, __u16 addr, __u8 static __inline__ void iop_stop(volatile struct mac_iop *iop) { - iop->status_ctrl &= ~IOP_RUN; + iop->status_ctrl = IOP_AUTOINC; } static __inline__ void iop_start(volatile struct mac_iop *iop) @@ -191,14 +191,9 @@ static __inline__ void iop_start(volatile struct mac_iop *iop) iop->status_ctrl = IOP_RUN | IOP_AUTOINC; } -static __inline__ void iop_bypass(volatile struct mac_iop *iop) -{ - iop->status_ctrl |= IOP_BYPASS; -} - static __inline__ void iop_interrupt(volatile struct mac_iop *iop) { - iop->status_ctrl |= IOP_IRQ; + iop->status_ctrl = IOP_IRQ | IOP_RUN | IOP_AUTOINC; } static int iop_alive(volatile struct mac_iop *iop) @@ -244,7 +239,6 @@ void __init iop_preinit(void) } else { iop_base[IOP_NUM_SCC] = (struct mac_iop *) SCC_IOP_BASE_QUADRA; } - iop_base[IOP_NUM_SCC]->status_ctrl = 0x87; iop_scc_present = 1; } else { iop_base[IOP_NUM_SCC] = NULL; @@ -256,7 +250,7 @@ void __init iop_preinit(void) } else { iop_base[IOP_NUM_ISM] = (struct mac_iop *) ISM_IOP_BASE_QUADRA; } - iop_base[IOP_NUM_ISM]->status_ctrl = 0; + iop_stop(iop_base[IOP_NUM_ISM]); iop_ism_present = 1; } else { iop_base[IOP_NUM_ISM] = NULL; @@ -416,7 +410,8 @@ static void iop_handle_send(uint iop_num, uint chan) msg->status = IOP_MSGSTATUS_UNUSED; msg = msg->next; iop_send_queue[iop_num][chan] = msg; - if (msg) iop_do_send(msg); + if (msg && iop_readb(iop, IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) + iop_do_send(msg); } /* @@ -490,16 +485,12 @@ int iop_send_message(uint iop_num, uint chan, void *privdata, if (!(q = iop_send_queue[iop_num][chan])) { iop_send_queue[iop_num][chan] = msg; + iop_do_send(msg); } else { while (q->next) q = q->next; q->next = msg; } - if (iop_readb(iop_base[iop_num], - IOP_ADDR_SEND_STATE + chan) == IOP_MSG_IDLE) { - iop_do_send(msg); - } - return 0; } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 6cb1e41d58d0..70a5f55ea664 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -164,7 +164,7 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index 1f730ded5224..5ab29c18aacd 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -517,6 +517,7 @@ static int __init dwc3_octeon_device_init(void) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res == NULL) { + put_device(&pdev->dev); dev_err(&pdev->dev, "No memory resources\n"); return -ENXIO; } @@ -528,8 +529,10 @@ static int __init dwc3_octeon_device_init(void) * know the difference. */ base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(base)) + if (IS_ERR(base)) { + put_device(&pdev->dev); return PTR_ERR(base); + } mutex_lock(&dwc3_octeon_clocks_mutex); dwc3_octeon_clocks_start(&pdev->dev, (u64)base); diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c index cd3e1f82e1a5..08ad6371fbe0 100644 --- a/arch/mips/kernel/topology.c +++ b/arch/mips/kernel/topology.c @@ -20,7 +20,7 @@ static int __init topology_init(void) for_each_present_cpu(i) { struct cpu *c = &per_cpu(cpu_devices, i); - c->hotpluggable = 1; + c->hotpluggable = !!i; ret = register_cpu(c, i); if (ret) printk(KERN_WARNING "topology_init: register_cpu %d " diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 7c8282399bf1..f6ab5825c03c 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); @@ -558,7 +560,6 @@ 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/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c index 43f140a28bc7..54d38809e22c 100644 --- a/arch/openrisc/kernel/stacktrace.c +++ b/arch/openrisc/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <asm/processor.h> @@ -68,12 +69,25 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { unsigned long *sp = NULL; + if (!try_get_task_stack(tsk)) + return; + if (tsk == current) sp = (unsigned long *) &sp; - else - sp = (unsigned long *) KSTK_ESP(tsk); + else { + unsigned long ksp; + + /* Locate stack from kernel context */ + ksp = task_thread_info(tsk)->ksp; + ksp += STACK_FRAME_OVERHEAD; /* redzone */ + ksp += sizeof(struct pt_regs); + + sp = (unsigned long *) ksp; + } unwind_stack(trace, sp, save_stack_address_nosched); + + put_task_stack(tsk); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 118953d41763..6dd4171c9530 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -212,6 +212,8 @@ atomic64_set(atomic64_t *v, s64 i) _atomic_spin_unlock_irqrestore(v, flags); } +#define atomic64_set_release(v, i) atomic64_set((v), (i)) + static __inline__ s64 atomic64_read(const atomic64_t *v) { diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h index dbaaca84f27f..640d46edf32e 100644 --- a/arch/parisc/include/asm/barrier.h +++ b/arch/parisc/include/asm/barrier.h @@ -26,6 +26,67 @@ #define __smp_rmb() mb() #define __smp_wmb() mb() +#define __smp_store_release(p, v) \ +do { \ + typeof(p) __p = (p); \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(*p)) (v) }; \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("stb,ma %0,0(%1)" \ + : : "r"(*(__u8 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("sth,ma %0,0(%1)" \ + : : "r"(*(__u16 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("stw,ma %0,0(%1)" \ + : : "r"(*(__u32 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("std,ma %0,0(%1)" \ + : : "r"(*(__u64 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + } \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u; \ + typeof(p) __p = (p); \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("ldb,ma 0(%1),%0" \ + : "=r"(*(__u8 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("ldh,ma 0(%1),%0" \ + : "=r"(*(__u16 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("ldw,ma 0(%1),%0" \ + : "=r"(*(__u32 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("ldd,ma 0(%1),%0" \ + : "=r"(*(__u64 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + } \ + __u.__val; \ +}) #include <asm-generic/barrier.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index ab5c215cf46c..068958575871 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void); extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_); extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_); +extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_); /* don't worry...optimizer will get rid of most of this */ static inline unsigned long @@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size) #endif case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int)old, (unsigned int)new_); + case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_); } __cmpxchg_called_with_bad_pointer(); return old; diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 197d2247e4db..16aec9ba2580 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -37,12 +37,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *x) volatile unsigned int *a; a = __ldcw_align(x); -#ifdef CONFIG_SMP - (void) __ldcw(a); -#else - mb(); -#endif - *a = 1; + /* Release with ordered store. */ + __asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory"); } static inline int arch_spin_trylock(arch_spinlock_t *x) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 89c801c2b5d1..d4acd0fce6f9 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -454,7 +454,6 @@ nop LDREG 0(\ptp),\pte bb,<,n \pte,_PAGE_PRESENT_BIT,3f - LDCW 0(\tmp),\tmp1 b \fault stw \spc,0(\tmp) 99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) @@ -464,23 +463,26 @@ 3: .endm - /* Release pa_tlb_lock lock without reloading lock address. */ - .macro tlb_unlock0 spc,tmp,tmp1 + /* Release pa_tlb_lock lock without reloading lock address. + Note that the values in the register spc are limited to + NR_SPACE_IDS (262144). Thus, the stw instruction always + stores a nonzero value even when register spc is 64 bits. + We use an ordered store to ensure all prior accesses are + performed prior to releasing the lock. */ + .macro tlb_unlock0 spc,tmp #ifdef CONFIG_SMP 98: or,COND(=) %r0,\spc,%r0 - LDCW 0(\tmp),\tmp1 - or,COND(=) %r0,\spc,%r0 - stw \spc,0(\tmp) + stw,ma \spc,0(\tmp) 99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) #endif .endm /* Release pa_tlb_lock lock. */ - .macro tlb_unlock1 spc,tmp,tmp1 + .macro tlb_unlock1 spc,tmp #ifdef CONFIG_SMP 98: load_pa_tlb_lock \tmp 99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) - tlb_unlock0 \spc,\tmp,\tmp1 + tlb_unlock0 \spc,\tmp #endif .endm @@ -1163,7 +1165,7 @@ dtlb_miss_20w: idtlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1189,7 +1191,7 @@ nadtlb_miss_20w: idtlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1223,7 +1225,7 @@ dtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1256,7 +1258,7 @@ nadtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1285,7 +1287,7 @@ dtlb_miss_20: idtlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1313,7 +1315,7 @@ nadtlb_miss_20: idtlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1420,7 +1422,7 @@ itlb_miss_20w: iitlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1444,7 +1446,7 @@ naitlb_miss_20w: iitlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1478,7 +1480,7 @@ itlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1502,7 +1504,7 @@ naitlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1532,7 +1534,7 @@ itlb_miss_20: iitlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1552,7 +1554,7 @@ naitlb_miss_20: iitlbt pte,prot - tlb_unlock1 spc,t0,t1 + tlb_unlock1 spc,t0 rfir nop @@ -1582,7 +1584,7 @@ dbit_trap_20w: idtlbt pte,prot - tlb_unlock0 spc,t0,t1 + tlb_unlock0 spc,t0 rfir nop #else @@ -1608,7 +1610,7 @@ dbit_trap_11: mtsp t1, %sr1 /* Restore sr1 */ - tlb_unlock0 spc,t0,t1 + tlb_unlock0 spc,t0 rfir nop @@ -1628,7 +1630,7 @@ dbit_trap_20: idtlbt pte,prot - tlb_unlock0 spc,t0,t1 + tlb_unlock0 spc,t0 rfir nop #endif diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 97ac707c6bff..a37814cb66c7 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -640,11 +640,7 @@ cas_action: sub,<> %r28, %r25, %r0 2: stw %r24, 0(%r26) /* Free lock */ -#ifdef CONFIG_SMP -98: LDCW 0(%sr2,%r20), %r1 /* Barrier */ -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ stw %r0, 4(%sr2,%r20) @@ -658,11 +654,7 @@ cas_action: 3: /* Error occurred on load or store */ /* Free lock */ -#ifdef CONFIG_SMP -98: LDCW 0(%sr2,%r20), %r1 /* Barrier */ -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) #endif @@ -863,11 +855,7 @@ cas2_action: cas2_end: /* Free lock */ -#ifdef CONFIG_SMP -98: LDCW 0(%sr2,%r20), %r1 /* Barrier */ -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) /* Enable interrupts */ ssm PSW_SM_I, %r0 /* Return to userspace, set no error */ @@ -877,11 +865,7 @@ cas2_end: 22: /* Error occurred on load or store */ /* Free lock */ -#ifdef CONFIG_SMP -98: LDCW 0(%sr2,%r20), %r1 /* Barrier */ -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 1(%r0),%r28 b lws_exit diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c index 70ffbcf889b8..2e4d1f05a926 100644 --- a/arch/parisc/lib/bitops.c +++ b/arch/parisc/lib/bitops.c @@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign _atomic_spin_unlock_irqrestore(ptr, flags); return (unsigned long)prev; } + +u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new) +{ + unsigned long flags; + u8 prev; + + _atomic_spin_lock_irqsave(ptr, flags); + if ((prev = *ptr) == old) + *ptr = new; + _atomic_spin_unlock_irqrestore(ptr, flags); + return prev; +} diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 8a887d012df3..a120561f8433 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -293,6 +293,9 @@ 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 +421,7 @@ endif archclean: $(Q)$(MAKE) $(clean)=$(boot) -archprepare: checkbin +archprepare: checkbin arch/powerpc/lib/crtsavres.o archheaders: $(Q)$(MAKE) $(build)=arch/powerpc/kernel/syscalls all diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 73d1f3562978..a6fd5d43a9ba 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -122,7 +122,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c -src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c +src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index b0491b8c0199..afef4fcdea98 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -129,7 +129,7 @@ int serial_console_init(void) dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC_MPC52XX +#ifdef CONFIG_PPC_MPC52xx else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index b68eeff77806..6db06f58deed 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -27,9 +27,11 @@ #ifdef CONFIG_KASAN void kasan_early_init(void); +void kasan_mmu_init(void); void kasan_init(void); #else static inline void kasan_init(void) { } +static inline void kasan_mmu_init(void) { } #endif #endif /* __ASSEMBLY */ diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 7426d7a90e1e..7aba3c7ea25c 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -12,6 +12,8 @@ #ifdef CONFIG_PPC_PERF_CTRS #include <asm/perf_event_server.h> +#else +static inline bool is_sier_available(void) { return false; } #endif #ifdef CONFIG_FSL_EMB_PERF_EVENT diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 3c1887351c71..bd227e0eab07 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -368,8 +368,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); -extern int rtas_online_cpus_mask(cpumask_var_t cpus); -extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(u64 handle); struct rtc_time; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1a5c05e9e8c4..447b7d935f4c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -3,7 +3,9 @@ # Makefile for the linux kernel. # -CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' +CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' $(call cc-disable-warning, attribute-alias) +CFLAGS_ptrace.o += $(call cc-disable-warning, array-bounds) +CFLAGS_syscalls.o += $(call cc-disable-warning, attribute-alias) ifdef CONFIG_PPC64 CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 65cd96c3b1d6..5e468938a661 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -841,97 +841,6 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } -enum rtas_cpu_state { - DOWN, - UP, -}; - -#ifndef CONFIG_SMP -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - if (!cpumask_empty(cpus)) { - cpumask_clear(cpus); - return -EINVAL; - } else - return 0; -} -#else -/* On return cpumask will be altered to indicate CPUs changed. - * CPUs with states changed will be set in the mask, - * CPUs with status unchanged will be unset in the mask. */ -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - int cpu; - int cpuret = 0; - int ret = 0; - - if (cpumask_empty(cpus)) - return 0; - - for_each_cpu(cpu, cpus) { - struct device *dev = get_cpu_device(cpu); - - switch (state) { - case DOWN: - cpuret = device_offline(dev); - break; - case UP: - cpuret = device_online(dev); - break; - } - if (cpuret < 0) { - pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", - __func__, - ((state == UP) ? "up" : "down"), - cpu, cpuret); - if (!ret) - ret = cpuret; - if (state == UP) { - /* clear bits for unchanged cpus, return */ - cpumask_shift_right(cpus, cpus, cpu); - cpumask_shift_left(cpus, cpus, cpu); - break; - } else { - /* clear bit for unchanged cpu, continue */ - cpumask_clear_cpu(cpu, cpus); - } - } - } - - return ret; -} -#endif - -int rtas_online_cpus_mask(cpumask_var_t cpus) -{ - int ret; - - ret = rtas_cpu_state_change_mask(UP, cpus); - - if (ret) { - cpumask_var_t tmp_mask; - - if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL)) - return ret; - - /* Use tmp_mask to preserve cpus mask from first failure */ - cpumask_copy(tmp_mask, cpus); - rtas_offline_cpus_mask(tmp_mask); - free_cpumask_var(tmp_mask); - } - - return ret; -} -EXPORT_SYMBOL(rtas_online_cpus_mask); - -int rtas_offline_cpus_mask(cpumask_var_t cpus) -{ - return rtas_cpu_state_change_mask(DOWN, cpus); -} -EXPORT_SYMBOL(rtas_offline_cpus_mask); - int rtas_ibm_suspend_me(u64 handle) { long state; @@ -939,8 +848,6 @@ int rtas_ibm_suspend_me(u64 handle) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); - cpumask_var_t offline_mask; - int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -961,9 +868,6 @@ int rtas_ibm_suspend_me(u64 handle) return -EIO; } - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); @@ -972,24 +876,8 @@ int rtas_ibm_suspend_me(u64 handle) lock_device_hotplug(); - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); - cpuret = rtas_online_cpus_mask(offline_mask); - if (cpuret) { - pr_err("%s: Could not bring present CPUs online.\n", __func__); - atomic_set(&data.error, cpuret); - goto out; - } - cpu_hotplug_disable(); - /* Check if we raced with a CPU-Offline Operation */ - if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { - pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); - atomic_set(&data.error, -EAGAIN); - goto out_hotplug_enable; - } - /* Call function on all CPUs. One of us will make the * rtas call */ @@ -1001,18 +889,11 @@ int rtas_ibm_suspend_me(u64 handle) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); -out_hotplug_enable: - cpu_hotplug_enable(); - /* Take down CPUs not online prior to suspend */ - cpuret = rtas_offline_cpus_mask(offline_mask); - if (cpuret) - pr_warn("%s: Could not restore CPUs to offline state.\n", - __func__); + cpu_hotplug_enable(); -out: unlock_device_hotplug(); - free_cpumask_var(offline_mask); + return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index d60598113a9f..36849b693d86 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -704,7 +704,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; 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/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index ae7fca40e5b3..432fd9fa8c3f 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -83,13 +83,17 @@ static int pkey_initialize(void) scan_pkey_feature(); /* - * Let's assume 32 pkeys on P8 bare metal, if its not defined by device - * tree. We make this exception since skiboot forgot to expose this - * property on power8. + * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device + * tree. We make this exception since some version of skiboot forgot to + * expose this property on power8/9. */ - if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) && - cpu_has_feature(CPU_FTRS_POWER8)) - pkeys_total = 32; + if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR)) { + unsigned long pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E || + PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9) + pkeys_total = 32; + } /* * Adjust the upper limit, based on the number of bits supported by @@ -367,12 +371,14 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) return true; pkey_shift = pkeyshift(pkey); - if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) - return true; + if (execute) + return !(read_iamr() & (IAMR_EX_BIT << pkey_shift)); + + amr = read_amr(); + if (write) + return !(amr & (AMR_WR_BIT << pkey_shift)); - amr = read_amr(); /* Delay reading amr until absolutely needed */ - return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) || - (write && !(amr & (AMR_WR_BIT << pkey_shift)))); + return !(amr & (AMR_RD_BIT << pkey_shift)); } bool arch_pte_access_permitted(u64 pte, bool write, bool execute) diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 716204aee3da..80f1c834613e 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -547,6 +547,7 @@ 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/fault.c b/arch/powerpc/mm/fault.c index f71c0987eaa9..74b3a03a578e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -262,6 +262,9 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, return false; } +// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE +#define SIGFRAME_MAX_SIZE (4096 + 128) + static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma, unsigned int flags, bool *must_retry) @@ -269,7 +272,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, /* * N.B. The POWER/Open ABI allows programs to access up to * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB + * The kernel signal delivery code writes a bit over 4KB * below the stack pointer (r1) before decrementing it. * The exec code can write slightly over 640kB to the stack * before setting the user r1. Thus we allow the stack to @@ -294,7 +297,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * between the last mapped region and the stack will * expand the stack rather than segfaulting. */ - if (address + 2048 >= uregs->gpr[1]) + if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1]) return false; if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 68f7446193d1..b04896a88d79 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -175,6 +175,8 @@ void __init MMU_init(void) btext_unmap(); #endif + kasan_mmu_init(); + setup_kup(); /* Shortly after that, the entire linear mapping will be available */ diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index b01d4b72eccf..1cfe57b51d7e 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -129,7 +129,7 @@ static void __init kasan_remap_early_shadow_ro(void) flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END); } -static void __init kasan_mmu_init(void) +void __init kasan_mmu_init(void) { int ret; struct memblock_region *reg; @@ -156,8 +156,6 @@ static void __init kasan_mmu_init(void) void __init kasan_init(void) { - kasan_mmu_init(); - kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 65aaa971dc99..c5de633e8436 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -27,7 +27,7 @@ static bool rtas_hp_event; unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 0a24a5a185f0..f789693f61f4 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - stream_id = simple_strtoul(buf, NULL, 16); do { @@ -150,32 +146,16 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, - cpu_online_mask); - rc = rtas_online_cpus_mask(offline_mask); - if (rc) { - pr_err("%s: Could not bring present CPUs online.\n", - __func__); - goto out; - } - stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); - - /* Take down CPUs not online prior to suspend */ - if (!rtas_offline_cpus_mask(offline_mask)) - pr_warn("%s: Could not restore CPUs to offline " - "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; -out: - free_cpumask_var(offline_mask); + return rc; } diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 3f1737f301cc..d0e24aaa2aa0 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -58,8 +58,16 @@ do { \ * The AQ/RL pair provides a RCpc critical section, but there's not really any * way we can take advantage of that here because the ordering is only enforced * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. */ -#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) +#define smp_mb__after_spinlock() RISCV_FENCE(iorw,iorw) #include <asm-generic/barrier.h> diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 905372d7eeb8..3df9a82bdbfd 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -12,7 +12,11 @@ #include <linux/const.h> /* thread information allocation */ +#ifdef CONFIG_64BIT +#define THREAD_SIZE_ORDER (2) +#else #define THREAD_SIZE_ORDER (1) +#endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #ifndef __ASSEMBLY__ diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c9dc1109ba6a..67d7fb8924ff 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -120,9 +120,9 @@ void __init setup_bootmem(void) } BUG_ON(mem_size == 0); - set_max_mapnr(PFN_DOWN(mem_size)); max_pfn = PFN_DOWN(memblock_end_of_DRAM()); max_low_pfn = max_pfn; + set_max_mapnr(max_low_pfn); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bc2bde4db8ae..f41053055c6f 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2485,23 +2485,36 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4], } EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + + split_huge_pmd(vma, pmd, addr); + return 0; +} + +static const struct mm_walk_ops thp_split_walk_ops = { + .pmd_entry = thp_split_walk_pmd_entry, +}; + static inline void thp_split_mm(struct mm_struct *mm) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE struct vm_area_struct *vma; - unsigned long addr; for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { - for (addr = vma->vm_start; - addr < vma->vm_end; - addr += PAGE_SIZE) - follow_page(vma, addr, FOLL_SPLIT); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; + walk_page_vma(vma, &thp_split_walk_ops, NULL); } mm->def_flags |= VM_NOHUGEPAGE; -#endif } +#else +static inline void thp_split_mm(struct mm_struct *mm) +{ +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Remove all empty zero pages from the mapping for lazy refaulting diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c index 16b4d8b0bb85..2c44b94f82fb 100644 --- a/arch/sh/boards/mach-landisk/setup.c +++ b/arch/sh/boards/mach-landisk/setup.c @@ -82,6 +82,9 @@ device_initcall(landisk_devices_setup); static void __init landisk_setup(char **cmdline_p) { + /* I/O port identity mapping */ + __set_io_port_base(0); + /* LED ON */ __raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED); diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index b56f908b1395..c267035421f1 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -14,6 +14,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address); extern void pmd_free(struct mm_struct *mm, pmd_t *pmd); +#define __pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, (pmdp)) #endif static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, @@ -70,15 +71,6 @@ do { \ tlb_remove_page((tlb), (pte)); \ } while (0) -#if CONFIG_PGTABLE_LEVELS > 2 -#define __pmd_free_tlb(tlb, pmdp, addr) \ -do { \ - struct page *page = virt_to_page(pmdp); \ - pgtable_pmd_page_dtor(page); \ - tlb_remove_page((tlb), page); \ -} while (0); -#endif - static inline void check_pgt_cache(void) { quicklist_trim(QUICK_PT, NULL, 25, 16); diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index d31f66e82ce5..4a8ec9e40cc2 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -199,7 +199,7 @@ syscall_trace_entry: mov.l @(OFF_R7,r15), r7 ! arg3 mov.l @(OFF_R3,r15), r3 ! syscall_nr ! - mov.l 2f, r10 ! Number of syscalls + mov.l 6f, r10 ! Number of syscalls cmp/hs r10, r3 bf syscall_call mov #-ENOSYS, r0 @@ -353,7 +353,7 @@ ENTRY(system_call) tst r9, r8 bf syscall_trace_entry ! - mov.l 2f, r8 ! Number of syscalls + mov.l 6f, r8 ! Number of syscalls cmp/hs r8, r3 bt syscall_badsys ! @@ -392,7 +392,7 @@ syscall_exit: #if !defined(CONFIG_CPU_SH2) 1: .long TRA #endif -2: .long NR_syscalls +6: .long NR_syscalls 3: .long sys_call_table 7: .long do_syscall_trace_enter 8: .long do_syscall_trace_leave 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/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6b84afdd7538..b246f18c5857 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -38,6 +38,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign +KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 76e1edf5bf12..34c6aff410d9 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/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 5f6a5af9c489..77043a82da51 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -127,10 +127,6 @@ ddq_add_8: /* generate a unique variable for ddq_add_x */ -.macro setddq n - var_ddq_add = ddq_add_\n -.endm - /* generate a unique variable for xmm register */ .macro setxdata n var_xdata = %xmm\n @@ -140,9 +136,7 @@ ddq_add_8: .macro club name, id .altmacro - .if \name == DDQ_DATA - setddq %\id - .elseif \name == XDATA + .if \name == XDATA setxdata %\id .endif .noaltmacro @@ -165,9 +159,8 @@ ddq_add_8: .set i, 1 .rept (by - 1) - club DDQ_DATA, i club XDATA, i - vpaddq var_ddq_add(%rip), xcounter, var_xdata + vpaddq (ddq_add_1 + 16 * (i - 1))(%rip), xcounter, var_xdata vptest ddq_low_msk(%rip), var_xdata jnz 1f vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata @@ -180,8 +173,7 @@ ddq_add_8: vmovdqa 1*16(p_keys), xkeyA vpxor xkey0, xdata0, xdata0 - club DDQ_DATA, by - vpaddq var_ddq_add(%rip), xcounter, xcounter + vpaddq (ddq_add_1 + 16 * (by - 1))(%rip), xcounter, xcounter vptest ddq_low_msk(%rip), xcounter jnz 1f vpaddq ddq_high_add_1(%rip), xcounter, xcounter diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index e40bdf024ba7..9afeb58c910e 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -266,7 +266,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff PSHUFB_XMM %xmm2, %xmm0 movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv - PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7 movdqu HashKey(%arg2), %xmm13 CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ @@ -978,7 +978,7 @@ _initial_blocks_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_enc TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 @@ -1186,7 +1186,7 @@ aes_loop_par_enc_done\@: * arg1, %arg3, %arg4 are used as pointers only, not modified * %r11 is the data offset value */ -.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \ +.macro GHASH_4_ENCRYPT_4_PARALLEL_dec TMP1 TMP2 TMP3 TMP4 TMP5 \ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM1, \XMM5 diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 390edb763826..e5530e74b738 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -63,7 +63,7 @@ * enough to patch inline, increasing performance. */ -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT # define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF #else # define preempt_stop(clobbers) @@ -1104,7 +1104,7 @@ restore_all: INTERRUPT_RETURN restore_all_kernel: -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT DISABLE_INTERRUPTS(CLBR_ANY) cmpl $0, PER_CPU_VAR(__preempt_count) jnz .Lno_preempt @@ -1393,7 +1393,7 @@ ENTRY(xen_hypervisor_callback) TRACE_IRQS_OFF mov %esp, %eax call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPTION +#ifndef CONFIG_PREEMPT call xen_maybe_preempt_hcall #endif jmp ret_from_intr diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 499008b3f285..b83feb7d9464 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -665,7 +665,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) /* Returning to kernel space */ retint_kernel: -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ btl $9, EFLAGS(%rsp) /* were interrupts off? */ @@ -1116,7 +1116,7 @@ ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ call xen_evtchn_do_upcall LEAVE_IRQ_STACK -#ifndef CONFIG_PREEMPTION +#ifndef CONFIG_PREEMPT call xen_maybe_preempt_hcall #endif jmp error_exit diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 2713490611a3..cb3464525b37 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -34,7 +34,7 @@ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 #endif -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index d6d1fdc09f9e..cfdca8b42c70 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -47,7 +47,7 @@ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit #endif -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule THUNK ___preempt_schedule_notrace, preempt_schedule_notrace EXPORT_SYMBOL(___preempt_schedule) @@ -56,7 +56,7 @@ #if defined(CONFIG_TRACE_IRQFLAGS) \ || defined(CONFIG_DEBUG_LOCK_ALLOC) \ - || defined(CONFIG_PREEMPTION) + || defined(CONFIG_PREEMPT) .L_restore: popq %r11 popq %r10 diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 44c48e34d799..00eac7f1529b 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -619,6 +619,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 3d4cb83a8828..99a7fa9ab0a3 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -102,7 +102,7 @@ static __always_inline bool should_resched(int preempt_offset) return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() \ asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..259d17d08983 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -557,6 +555,16 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->hwirq = virq + i; irqd_set_single_target(irqd); /* + * Prevent that any of these interrupts is invoked in + * non interrupt context via e.g. generic_handle_irq() + * as that can corrupt the affinity move state. + */ + irqd_set_handle_enforce_irqctx(irqd); + + /* Don't invoke affinity setter on deactivated interrupts */ + irqd_set_affinity_on_activate(irqd); + + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is * required for check_timer() to work correctly as it might @@ -769,20 +777,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 7c8958dee103..6c9b91b773ef 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -328,6 +328,7 @@ static const struct file_operations mce_chrdev_ops = { .write = mce_chrdev_write, .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 5d108f70f315..799b74b1582c 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -511,7 +511,7 @@ static void do_inject(void) */ if (inj_type == DFR_INT_INJ) { i_mce.status |= MCI_STATUS_DEFERRED; - i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + i_mce.status &= ~MCI_STATUS_UC; } /* diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 3c648476d4fb..88569536d529 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/fpu/core.c b/arch/x86/kernel/fpu/core.c index 649fbc3fcf9f..8ba0e53dec75 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -113,6 +113,12 @@ static void __kernel_fpu_begin(void) } } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } static void __kernel_fpu_end(void) diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 519649ddf100..fe522691ac71 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -207,7 +207,7 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG + printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 636426345e65..27159a40dc93 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -580,7 +580,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, if (setup_detour_execution(p, regs, reenter)) return; -#if !defined(CONFIG_PREEMPTION) +#if !defined(CONFIG_PREEMPT) if (p->ainsn.boostable && !p->post_handler) { /* Boost up -- we can execute copied instructions directly */ if (!reenter) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 250e4c4ac6d9..d02874cddda3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -326,7 +326,7 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 2d6898c2cb64..6d83b4b857e6 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index aa0f39dc8129..187a86e0e753 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -431,8 +431,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -653,6 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index b3f6a15b9593..96d8025ea1b0 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -362,6 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d2c1cb127791..9483b9da8864 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2087,7 +2087,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || + if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index f031c0e19356..515cdee90df7 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -209,7 +209,7 @@ sqrt_stage_2_finish: #ifdef PARANOID /* It should be possible to get here only if the arg is ffff....ffff */ - cmp $0xffffffff,FPU_fsqrt_arg_1 + cmpl $0xffffffff,FPU_fsqrt_arg_1 jnz sqrt_stage_2_error #endif /* PARANOID */ 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/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h index f092cc3f4e66..956d4d47c6cd 100644 --- a/arch/xtensa/include/asm/thread_info.h +++ b/arch/xtensa/include/asm/thread_info.h @@ -55,6 +55,10 @@ struct thread_info { mm_segment_t addr_limit; /* thread address space */ unsigned long cpenable; +#if XCHAL_HAVE_EXCLUSIVE + /* result of the most recent exclusive store */ + unsigned long atomctl8; +#endif /* Allocate storage for extra user states and coprocessor states. */ #if XTENSA_HAVE_COPROCESSORS diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c index 33a257b33723..dc5c83cad9be 100644 --- a/arch/xtensa/kernel/asm-offsets.c +++ b/arch/xtensa/kernel/asm-offsets.c @@ -93,6 +93,9 @@ int main(void) DEFINE(THREAD_RA, offsetof (struct task_struct, thread.ra)); DEFINE(THREAD_SP, offsetof (struct task_struct, thread.sp)); DEFINE(THREAD_CPENABLE, offsetof (struct thread_info, cpenable)); +#if XCHAL_HAVE_EXCLUSIVE + DEFINE(THREAD_ATOMCTL8, offsetof (struct thread_info, atomctl8)); +#endif #if XTENSA_HAVE_COPROCESSORS DEFINE(THREAD_XTREGS_CP0, offsetof(struct thread_info, xtregs_cp.cp0)); DEFINE(THREAD_XTREGS_CP1, offsetof(struct thread_info, xtregs_cp.cp1)); diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index e54af8b7e0f8..f9c7a02acc29 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -374,6 +374,11 @@ common_exception: s32i a2, a1, PT_LCOUNT #endif +#if XCHAL_HAVE_EXCLUSIVE + /* Clear exclusive access monitor set by interrupted code */ + clrex +#endif + /* It is now save to restore the EXC_TABLE_FIXUP variable. */ rsr a2, exccause @@ -1989,6 +1994,12 @@ ENTRY(_switch_to) s32i a3, a4, THREAD_CPENABLE #endif +#if XCHAL_HAVE_EXCLUSIVE + l32i a3, a5, THREAD_ATOMCTL8 + getex a3 + s32i a3, a4, THREAD_ATOMCTL8 +#endif + /* Flush register file. */ spill_registers_kernel diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c index 9bae79f70301..86c9ba963155 100644 --- a/arch/xtensa/kernel/perf_event.c +++ b/arch/xtensa/kernel/perf_event.c @@ -401,7 +401,7 @@ static struct pmu xtensa_pmu = { .read = xtensa_pmu_read, }; -static int xtensa_pmu_setup(int cpu) +static int xtensa_pmu_setup(unsigned int cpu) { unsigned i; diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 0634bfb82a0b..5ea7f39e5d62 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -723,7 +723,8 @@ c_start(struct seq_file *f, loff_t *pos) static void * c_next(struct seq_file *f, void *v, loff_t *pos) { - return NULL; + ++*pos; + return c_start(f, pos); } static void diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 4092555828b1..24cf6972eace 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -87,13 +87,13 @@ void __xtensa_libgcc_window_spill(void) } EXPORT_SYMBOL(__xtensa_libgcc_window_spill); -unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v) { BUG(); } EXPORT_SYMBOL(__sync_fetch_and_and_4); -unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v) { BUG(); } diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 52c2ab6c9d14..a1b4821bc103 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -256,7 +256,7 @@ static void bfqg_put(struct bfq_group *bfqg) kfree(bfqg); } -void bfqg_and_blkg_get(struct bfq_group *bfqg) +static void bfqg_and_blkg_get(struct bfq_group *bfqg) { /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */ bfqg_get(bfqg); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 5e5e922b23bc..54d2e5cc9b52 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -949,7 +949,6 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg); struct bfq_group *bfqq_group(struct bfq_queue *bfqq); struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node); -void bfqg_and_blkg_get(struct bfq_group *bfqg); void bfqg_and_blkg_put(struct bfq_group *bfqg); #ifdef CONFIG_BFQ_GROUP_IOSCHED diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 3be22faa4c01..c9ba225081ce 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -536,9 +536,7 @@ static void bfq_get_entity(struct bfq_entity *entity) bfqq->ref++; bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d", bfqq, bfqq->ref); - } else - bfqg_and_blkg_get(container_of(entity, struct bfq_group, - entity)); + } } /** @@ -652,14 +650,8 @@ static void bfq_forget_entity(struct bfq_service_tree *st, entity->on_st = false; st->wsum -= entity->weight; - if (is_in_service) - return; - - if (bfqq) + if (bfqq && !is_in_service) bfq_put_queue(bfqq); - else - bfqg_and_blkg_put(container_of(entity, struct bfq_group, - entity)); } /** diff --git a/block/bio.c b/block/bio.c index 7eea97790851..22280cfba22f 100644 --- a/block/bio.c +++ b/block/bio.c @@ -835,8 +835,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page, struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; if (page_is_mergeable(bv, page, len, off, same_page)) { - if (bio->bi_iter.bi_size > UINT_MAX - len) + if (bio->bi_iter.bi_size > UINT_MAX - len) { + *same_page = false; return false; + } bv->bv_len += len; bio->bi_iter.bi_size += len; return true; diff --git a/block/blk-lib.c b/block/blk-lib.c index 5f2c429d4378..bdcfe4fbeac7 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, op = REQ_OP_DISCARD; } + /* In case the discard granularity isn't set by buggy device driver */ + if (WARN_ON_ONCE(!q->limits.discard_granularity)) { + char dev_name[BDEVNAME_SIZE]; + + bdevname(bdev, dev_name); + pr_err_ratelimited("%s: Error: discard_granularity is 0.\n", dev_name); + return -EOPNOTSUPP; + } + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; diff --git a/block/blk-merge.c b/block/blk-merge.c index 17713d7d98d5..4140c9594b92 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -144,17 +144,20 @@ static inline unsigned get_max_io_size(struct request_queue *q, return sectors; } -static unsigned get_max_segment_size(struct request_queue *q, - unsigned offset) +static inline unsigned get_max_segment_size(struct request_queue *q, + struct page *start_page, + unsigned long offset) { unsigned long mask = queue_segment_boundary(q); - /* default segment boundary mask means no boundary limit */ - if (mask == BLK_SEG_BOUNDARY_MASK) - return queue_max_segment_size(q); + offset = mask & (page_to_phys(start_page) + offset); - return min_t(unsigned long, mask - (mask & offset) + 1, - queue_max_segment_size(q)); + /* + * overflow may be triggered in case of zero page physical address + * on 32bit arch, use queue's max segment size when that happens. + */ + return min_not_zero(mask - offset + 1, + (unsigned long)queue_max_segment_size(q)); } /* @@ -173,7 +176,8 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv, * current bvec has to be splitted as multiple segments. */ while (len && new_nsegs + *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_offset + total_len); + seg_size = get_max_segment_size(q, bv->bv_page, + bv->bv_offset + total_len); seg_size = min(seg_size, len); new_nsegs++; @@ -375,7 +379,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(q, offset), nbytes); + unsigned len = min(get_max_segment_size(q, bvec->bv_page, + offset), nbytes); struct page *page = bvec->bv_page; /* diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3afe327f816f..082faacb9993 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -125,6 +125,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(REGISTERED), QUEUE_FLAG_NAME(SCSI_PASSTHROUGH), QUEUE_FLAG_NAME(QUIESCED), + QUEUE_FLAG_NAME(PCI_P2PDMA), }; #undef QUEUE_FLAG_NAME diff --git a/crypto/af_alg.c b/crypto/af_alg.c index a3b9df99af6d..1d4b0157ee5d 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/net.h> #include <linux/rwsem.h> +#include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/security.h> @@ -635,6 +636,7 @@ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, if (!ctx->used) ctx->merge = 0; + ctx->init = ctx->more; } EXPORT_SYMBOL_GPL(af_alg_pull_tsgl); @@ -734,9 +736,10 @@ EXPORT_SYMBOL_GPL(af_alg_wmem_wakeup); * * @sk socket of connection to user space * @flags If MSG_DONTWAIT is set, then only report if function would sleep + * @min Set to minimum request size if partial requests are allowed. * @return 0 when writable memory is available, < 0 upon error */ -int af_alg_wait_for_data(struct sock *sk, unsigned flags) +int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct alg_sock *ask = alg_sk(sk); @@ -754,7 +757,9 @@ int af_alg_wait_for_data(struct sock *sk, unsigned flags) if (signal_pending(current)) break; timeout = MAX_SCHEDULE_TIMEOUT; - if (sk_wait_event(sk, &timeout, (ctx->used || !ctx->more), + if (sk_wait_event(sk, &timeout, + ctx->init && (!ctx->more || + (min && ctx->used >= min)), &wait)) { err = 0; break; @@ -843,10 +848,17 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, } lock_sock(sk); - if (!ctx->more && ctx->used) { - err = -EINVAL; - goto unlock; + if (ctx->init && !ctx->more) { + if (ctx->used) { + err = -EINVAL; + goto unlock; + } + + pr_info_once( + "%s sent an empty control message without MSG_MORE.\n", + current->comm); } + ctx->init = true; if (init) { ctx->enc = enc; diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 0ae000a61c7f..43c6aa784858 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -106,8 +106,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t usedpages = 0; /* [in] RX bufs to be used from user */ size_t processed = 0; /* [in] TX bufs to be consumed */ - if (!ctx->used) { - err = af_alg_wait_for_data(sk, flags); + if (!ctx->init || ctx->more) { + err = af_alg_wait_for_data(sk, flags, 0); if (err) return err; } @@ -558,12 +558,6 @@ static int aead_accept_parent_nokey(void *private, struct sock *sk) INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; - ctx->used = 0; - atomic_set(&ctx->rcvused, 0); - ctx->more = 0; - ctx->merge = 0; - ctx->enc = 0; - ctx->aead_assoclen = 0; crypto_init_wait(&ctx->wait); ask->private = ctx; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index ec5567c87a6d..81c4022285a7 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -61,8 +61,8 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, int err = 0; size_t len = 0; - if (!ctx->used) { - err = af_alg_wait_for_data(sk, flags); + if (!ctx->init || (ctx->more && ctx->used < bs)) { + err = af_alg_wait_for_data(sk, flags, bs); if (err) return err; } @@ -333,6 +333,7 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk) ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; + memset(ctx, 0, len); ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(tfm), GFP_KERNEL); @@ -340,16 +341,10 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk) sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_skcipher_ivsize(tfm)); INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; - ctx->used = 0; - atomic_set(&ctx->rcvused, 0); - ctx->more = 0; - ctx->merge = 0; - ctx->enc = 0; crypto_init_wait(&ctx->wait); ask->private = ctx; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index d7f43d4ea925..e5fae4e838c0 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -119,6 +119,7 @@ static int software_key_query(const struct kernel_pkey_params *params, if (IS_ERR(tfm)) return PTR_ERR(tfm); + ret = -ENOMEM; key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, GFP_KERNEL); if (!key) diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 728d752f7adc..85f799c9c25c 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -473,10 +473,6 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) (u8)access_byte_width; } } - /* An additional reference for the container */ - - acpi_ut_add_reference(obj_desc->field.region_obj); - ACPI_DEBUG_PRINT((ACPI_DB_BFIELD, "RegionField: BitOff %X, Off %X, Gran %X, Region %p\n", obj_desc->field.start_field_bit_offset, diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c index c365faf4e6cd..4c0d4e434196 100644 --- a/drivers/acpi/acpica/utdelete.c +++ b/drivers/acpi/acpica/utdelete.c @@ -568,11 +568,6 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action) next_object = object->buffer_field.buffer_obj; break; - case ACPI_TYPE_LOCAL_REGION_FIELD: - - next_object = object->field.region_obj; - break; - case ACPI_TYPE_LOCAL_BANK_FIELD: next_object = object->bank_field.bank_obj; @@ -613,6 +608,7 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action) } break; + case ACPI_TYPE_LOCAL_REGION_FIELD: case ACPI_TYPE_REGION: default: diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index e63fd7bfd3a5..5bcb4c01ec5f 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -336,6 +336,25 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"), }, }, + { + .callback = video_detect_force_native, + .ident = "Acer Aspire 5738z", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"), + DMI_MATCH(DMI_BOARD_NAME, "JV50"), + }, + }, + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=207835 */ + .callback = video_detect_force_native, + .ident = "Acer TravelMate 5735Z", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 5735Z"), + DMI_MATCH(DMI_BOARD_NAME, "BA51_MV"), + }, + }, /* * Desktops which falsely report a backlight and which our heuristics diff --git a/drivers/android/binder.c b/drivers/android/binder.c index ae649044112b..4fe23f28514e 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3002,6 +3002,12 @@ static void binder_transaction(struct binder_proc *proc, goto err_dead_binder; } e->to_node = target_node->debug_id; + if (WARN_ON(proc == target_proc)) { + return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; + goto err_invalid_target_handle; + } if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) { return_error = BR_FAILED_REPLY; @@ -3655,10 +3661,17 @@ static int binder_thread_write(struct binder_proc *proc, struct binder_node *ctx_mgr_node; mutex_lock(&context->context_mgr_node_lock); ctx_mgr_node = context->binder_context_mgr_node; - if (ctx_mgr_node) + if (ctx_mgr_node) { + if (ctx_mgr_node->proc == proc) { + binder_user_error("%d:%d context manager tried to acquire desc 0\n", + proc->pid, thread->pid); + mutex_unlock(&context->context_mgr_node_lock); + return -EINVAL; + } ret = binder_inc_ref_for_node( proc, ctx_mgr_node, strong, NULL, &rdata); + } mutex_unlock(&context->context_mgr_node_lock); } if (ret) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index bb0a732cd98a..f8953fcbcc0e 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -948,7 +948,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_user_end(alloc, index); } up_read(&mm->mmap_sem); - mmput(mm); + mmput_async(mm); trace_binder_unmap_kernel_start(alloc, index); diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index d9fd70280482..7f814da3c2d0 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -433,9 +433,15 @@ static int atmtcp_remove_persistent(int itf) return -EMEDIUMTYPE; } dev_data = PRIV(dev); - if (!dev_data->persist) return 0; + if (!dev_data->persist) { + atm_dev_put(dev); + return 0; + } dev_data->persist = 0; - if (PRIV(dev)->vcc) return 0; + if (PRIV(dev)->vcc) { + atm_dev_put(dev); + return 0; + } kfree(dev_data); atm_dev_put(dev); atm_dev_deregister(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 98c1d471a8eb..432a6f52cadb 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -819,7 +819,9 @@ static int __device_attach(struct device *dev, bool allow_async) int ret = 0; device_lock(dev); - if (dev->driver) { + if (dev->p->dead) { + goto out_unlock; + } else if (dev->driver) { if (device_is_bound(dev)) { ret = 1; goto out_unlock; diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5b2b6a05a4f3..50f9e89c3f4e 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -1053,6 +1053,9 @@ static void *wakeup_sources_stats_seq_next(struct seq_file *m, break; } + if (!next_ws) + print_wakeup_source_stats(m, &deleted_ws); + return next_ws; } diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index e5e1b3a01b1a..bfb357e273fb 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -227,6 +227,9 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from, if (*ppos < 0 || !count) return -EINVAL; + if (count > (PAGE_SIZE << (MAX_ORDER - 1))) + count = PAGE_SIZE << (MAX_ORDER - 1); + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -371,6 +374,9 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file, if (*ppos < 0 || !count) return -EINVAL; + if (count > (PAGE_SIZE << (MAX_ORDER - 1))) + count = PAGE_SIZE << (MAX_ORDER - 1); + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -457,29 +463,31 @@ static ssize_t regmap_cache_only_write_file(struct file *file, { struct regmap *map = container_of(file->private_data, struct regmap, cache_only); - ssize_t result; - bool was_enabled, require_sync = false; + bool new_val, require_sync = false; int err; - map->lock(map->lock_arg); + err = kstrtobool_from_user(user_buf, count, &new_val); + /* Ignore malforned data like debugfs_write_file_bool() */ + if (err) + return count; - was_enabled = map->cache_only; + err = debugfs_file_get(file->f_path.dentry); + if (err) + return err; - result = debugfs_write_file_bool(file, user_buf, count, ppos); - if (result < 0) { - map->unlock(map->lock_arg); - return result; - } + map->lock(map->lock_arg); - if (map->cache_only && !was_enabled) { + if (new_val && !map->cache_only) { dev_warn(map->dev, "debugfs cache_only=Y forced\n"); add_taint(TAINT_USER, LOCKDEP_STILL_OK); - } else if (!map->cache_only && was_enabled) { + } else if (!new_val && map->cache_only) { dev_warn(map->dev, "debugfs cache_only=N forced: syncing cache\n"); require_sync = true; } + map->cache_only = new_val; map->unlock(map->lock_arg); + debugfs_file_put(file->f_path.dentry); if (require_sync) { err = regcache_sync(map); @@ -487,7 +495,7 @@ static ssize_t regmap_cache_only_write_file(struct file *file, dev_err(map->dev, "Failed to sync cache %d\n", err); } - return result; + return count; } static const struct file_operations regmap_cache_only_fops = { @@ -502,28 +510,32 @@ static ssize_t regmap_cache_bypass_write_file(struct file *file, { struct regmap *map = container_of(file->private_data, struct regmap, cache_bypass); - ssize_t result; - bool was_enabled; + bool new_val; + int err; - map->lock(map->lock_arg); + err = kstrtobool_from_user(user_buf, count, &new_val); + /* Ignore malforned data like debugfs_write_file_bool() */ + if (err) + return count; - was_enabled = map->cache_bypass; + err = debugfs_file_get(file->f_path.dentry); + if (err) + return err; - result = debugfs_write_file_bool(file, user_buf, count, ppos); - if (result < 0) - goto out; + map->lock(map->lock_arg); - if (map->cache_bypass && !was_enabled) { + if (new_val && !map->cache_bypass) { dev_warn(map->dev, "debugfs cache_bypass=Y forced\n"); add_taint(TAINT_USER, LOCKDEP_STILL_OK); - } else if (!map->cache_bypass && was_enabled) { + } else if (!new_val && map->cache_bypass) { dev_warn(map->dev, "debugfs cache_bypass=N forced\n"); } + map->cache_bypass = new_val; -out: map->unlock(map->lock_arg); + debugfs_file_put(file->f_path.dentry); - return result; + return count; } static const struct file_operations regmap_cache_bypass_fops = { diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 320d23de02c2..927ebde1607b 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1363,7 +1363,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data) /* If the user didn't specify a name match any */ if (data) - return (*r)->name == data; + return !strcmp((*r)->name, data); else return 1; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 62ef4a2e0983..a1522cd580de 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -757,6 +757,24 @@ 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, @@ -871,6 +889,7 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; + u32 granularity, max_discard_sectors; /* * If the backing device is a block device, mirror its zeroing @@ -883,11 +902,10 @@ static void loop_config_discard(struct loop_device *lo) struct request_queue *backingq; backingq = bdev_get_queue(inode->i_bdev); - blk_queue_max_discard_sectors(q, - backingq->limits.max_write_zeroes_sectors); - blk_queue_max_write_zeroes_sectors(q, - backingq->limits.max_write_zeroes_sectors); + max_discard_sectors = backingq->limits.max_write_zeroes_sectors; + granularity = backingq->limits.discard_granularity ?: + queue_physical_block_size(backingq); /* * We use punch hole to reclaim the free space used by the @@ -896,23 +914,26 @@ static void loop_config_discard(struct loop_device *lo) * useful information. */ } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { - q->limits.discard_granularity = 0; - q->limits.discard_alignment = 0; - blk_queue_max_discard_sectors(q, 0); - blk_queue_max_write_zeroes_sectors(q, 0); + max_discard_sectors = 0; + granularity = 0; } else { - q->limits.discard_granularity = inode->i_sb->s_blocksize; - q->limits.discard_alignment = 0; - - blk_queue_max_discard_sectors(q, UINT_MAX >> 9); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); + max_discard_sectors = UINT_MAX >> 9; + granularity = inode->i_sb->s_blocksize; } - if (q->limits.max_write_zeroes_sectors) + if (max_discard_sectors) { + q->limits.discard_granularity = granularity; + blk_queue_max_discard_sectors(q, max_discard_sectors); + blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - else + } else { + q->limits.discard_granularity = 0; + blk_queue_max_discard_sectors(q, 0); + blk_queue_max_write_zeroes_sectors(q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); + } + q->limits.discard_alignment = 0; } static void loop_unprepare_queue(struct loop_device *lo) @@ -2333,6 +2354,8 @@ static void __exit loop_exit(void) range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; + mutex_lock(&loop_ctl_mutex); + idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); idr_destroy(&loop_index_idr); @@ -2340,6 +2363,8 @@ static void __exit loop_exit(void) unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); + + mutex_unlock(&loop_ctl_mutex); } module_init(loop_init); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 8c79e65267a3..fa49b2a0dba2 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4305,6 +4305,9 @@ static ssize_t rbd_config_info_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + return sprintf(buf, "%s\n", rbd_dev->config_info); } @@ -4416,6 +4419,9 @@ static ssize_t rbd_image_refresh(struct device *dev, struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); int ret; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = rbd_dev_refresh(rbd_dev); if (ret) return ret; @@ -6012,6 +6018,9 @@ static ssize_t do_rbd_add(struct bus_type *bus, struct rbd_client *rbdc; int rc; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!try_module_get(THIS_MODULE)) return -ENODEV; @@ -6167,6 +6176,9 @@ static ssize_t do_rbd_remove(struct bus_type *bus, bool force = false; int ret; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + dev_id = -1; opt_buf[0] = '\0'; sscanf(buf, "%d %5s", &dev_id, opt_buf); diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 0f3a020703ab..4c7978cb1786 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -328,7 +328,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8897 = { static const struct btmrvl_sdio_device btmrvl_sdio_sd8977 = { .helper = NULL, - .firmware = "mrvl/sd8977_uapsta.bin", + .firmware = "mrvl/sdsd8977_combo_v2.bin", .reg = &btmrvl_reg_8977, .support_pscan_win_report = true, .sd_blksz_fw_dl = 256, @@ -346,7 +346,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8987 = { static const struct btmrvl_sdio_device btmrvl_sdio_sd8997 = { .helper = NULL, - .firmware = "mrvl/sd8997_uapsta.bin", + .firmware = "mrvl/sdsd8997_combo_v4.bin", .reg = &btmrvl_reg_8997, .support_pscan_win_report = true, .sd_blksz_fw_dl = 256, @@ -1831,6 +1831,6 @@ MODULE_FIRMWARE("mrvl/sd8787_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8797_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8887_uapsta.bin"); MODULE_FIRMWARE("mrvl/sd8897_uapsta.bin"); -MODULE_FIRMWARE("mrvl/sd8977_uapsta.bin"); +MODULE_FIRMWARE("mrvl/sdsd8977_combo_v2.bin"); MODULE_FIRMWARE("mrvl/sd8987_uapsta.bin"); -MODULE_FIRMWARE("mrvl/sd8997_uapsta.bin"); +MODULE_FIRMWARE("mrvl/sdsd8997_combo_v4.bin"); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 813338288453..b7de7cb8cca9 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -684,7 +684,7 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) const u8 *fw_ptr; size_t fw_size; int err, dlen; - u8 flag; + u8 flag, param; err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { @@ -692,6 +692,20 @@ static int mtk_setup_firmware(struct hci_dev *hdev, const char *fwname) return err; } + /* Power on data RAM the firmware relies on. */ + param = 1; + wmt_params.op = MTK_WMT_FUNC_CTRL; + wmt_params.flag = 3; + wmt_params.dlen = sizeof(param); + wmt_params.data = ¶m; + wmt_params.status = NULL; + + err = mtk_hci_wmt_sync(hdev, &wmt_params); + if (err < 0) { + bt_dev_err(hdev, "Failed to power on data RAM (%d)", err); + return err; + } + fw_ptr = fw->data; fw_size = fw->size; diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index dacf297baf59..5df0651b6cd5 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -790,7 +790,7 @@ static int h5_serdev_probe(struct serdev_device *serdev) if (!h5) return -ENOMEM; - set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags); + set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.hdev_flags); h5->hu = &h5->serdev_hu; h5->serdev_hu.serdev = serdev; diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 4652896d4990..ad2f26cb2622 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -357,7 +357,8 @@ void hci_uart_unregister_device(struct hci_uart *hu) struct hci_dev *hdev = hu->hdev; clear_bit(HCI_UART_PROTO_READY, &hu->flags); - hci_unregister_dev(hdev); + if (test_bit(HCI_UART_REGISTERED, &hu->flags)) + hci_unregister_dev(hdev); hci_free_dev(hdev); cancel_work_sync(&hu->write_work); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 8fb90245f7b6..801c39ca46a5 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1109,6 +1109,10 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("smartreflex", 0, -1, 0x24, -1, 0x00000000, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), + SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff, + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), + SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -1, 0x50700101, 0xffffffff, + SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("smartreflex", 0, -1, 0x38, -1, 0x00000000, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("timer", 0, 0, 0x10, 0x14, 0x00000015, 0xffffffff, @@ -1181,8 +1185,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("timer32k", 0, 0, 0x4, -1, 0x00000060, 0xffffffff, 0), SYSC_QUIRK("usbhstll", 0, 0, 0x10, 0x14, 0x00000004, 0xffffffff, 0), SYSC_QUIRK("usbhstll", 0, 0, 0x10, 0x14, 0x00000008, 0xffffffff, 0), - SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff, 0), - SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -1, 0x50700101, 0xffffffff, 0), SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050, 0xffffffff, 0), SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0, 0), diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index b161bdf60000..0941d38b2d32 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -304,8 +304,10 @@ static int intel_gtt_setup_scratch_page(void) if (intel_private.needs_dmar) { dma_addr = pci_map_page(intel_private.pcidev, page, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) + if (pci_dma_mapping_error(intel_private.pcidev, dma_addr)) { + __free_page(page); return -EINVAL; + } intel_private.scratch_page_dma = dma_addr; } else diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index b12ac1ae107b..61f9acc5d741 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -389,13 +389,8 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev, chip->cdev.owner = THIS_MODULE; chip->cdevs.owner = THIS_MODULE; - chip->work_space.context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!chip->work_space.context_buf) { - rc = -ENOMEM; - goto out; - } - chip->work_space.session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!chip->work_space.session_buf) { + rc = tpm2_init_space(&chip->work_space, TPM2_SPACE_BUFFER_SIZE); + if (rc) { rc = -ENOMEM; goto out; } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 218cb496222a..37f010421a36 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -177,6 +177,9 @@ struct tpm_header { #define TPM_TAG_RQU_COMMAND 193 +/* TPM2 specific constants. */ +#define TPM2_SPACE_BUFFER_SIZE 16384 /* 16 kB */ + struct stclear_flags_t { __be16 tag; u8 deactivated; @@ -456,7 +459,7 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type); unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm2_probe(struct tpm_chip *chip); int tpm2_find_cc(struct tpm_chip *chip, u32 cc); -int tpm2_init_space(struct tpm_space *space); +int tpm2_init_space(struct tpm_space *space, unsigned int buf_size); void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space); void tpm2_flush_space(struct tpm_chip *chip); int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd, diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 982d341d8837..784b8b3cb903 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -38,18 +38,21 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space) } } -int tpm2_init_space(struct tpm_space *space) +int tpm2_init_space(struct tpm_space *space, unsigned int buf_size) { - space->context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + space->context_buf = kzalloc(buf_size, GFP_KERNEL); if (!space->context_buf) return -ENOMEM; - space->session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + space->session_buf = kzalloc(buf_size, GFP_KERNEL); if (space->session_buf == NULL) { kfree(space->context_buf); + /* Prevent caller getting a dangling pointer. */ + space->context_buf = NULL; return -ENOMEM; } + space->buf_size = buf_size; return 0; } @@ -311,8 +314,10 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd, sizeof(space->context_tbl)); memcpy(&chip->work_space.session_tbl, &space->session_tbl, sizeof(space->session_tbl)); - memcpy(chip->work_space.context_buf, space->context_buf, PAGE_SIZE); - memcpy(chip->work_space.session_buf, space->session_buf, PAGE_SIZE); + memcpy(chip->work_space.context_buf, space->context_buf, + space->buf_size); + memcpy(chip->work_space.session_buf, space->session_buf, + space->buf_size); rc = tpm2_load_space(chip); if (rc) { @@ -492,7 +497,7 @@ static int tpm2_save_space(struct tpm_chip *chip) continue; rc = tpm2_save_context(chip, space->context_tbl[i], - space->context_buf, PAGE_SIZE, + space->context_buf, space->buf_size, &offset); if (rc == -ENOENT) { space->context_tbl[i] = 0; @@ -509,9 +514,8 @@ static int tpm2_save_space(struct tpm_chip *chip) continue; rc = tpm2_save_context(chip, space->session_tbl[i], - space->session_buf, PAGE_SIZE, + space->session_buf, space->buf_size, &offset); - if (rc == -ENOENT) { /* handle error saving session, just forget it */ space->session_tbl[i] = 0; @@ -557,8 +561,10 @@ int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space, sizeof(space->context_tbl)); memcpy(&space->session_tbl, &chip->work_space.session_tbl, sizeof(space->session_tbl)); - memcpy(space->context_buf, chip->work_space.context_buf, PAGE_SIZE); - memcpy(space->session_buf, chip->work_space.session_buf, PAGE_SIZE); + memcpy(space->context_buf, chip->work_space.context_buf, + space->buf_size); + memcpy(space->session_buf, chip->work_space.session_buf, + space->buf_size); return 0; out: diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 7e202796782d..e79655a05a76 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1008,7 +1008,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, return 0; out_err: - if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL)) + if (chip->ops->clk_enable != NULL) chip->ops->clk_enable(chip, false); tpm_tis_remove(chip); diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index 7a0a7051a06f..eef0fb06ea83 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -21,7 +21,7 @@ static int tpmrm_open(struct inode *inode, struct file *file) if (priv == NULL) return -ENOMEM; - rc = tpm2_init_space(&priv->space); + rc = tpm2_init_space(&priv->space, TPM2_SPACE_BUFFER_SIZE); if (rc) { kfree(priv); return -ENOMEM; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 3259426f01dc..9ebce2c12c43 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2118,6 +2118,7 @@ static struct virtio_device_id id_table[] = { { VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID }, { 0 }, }; +MODULE_DEVICE_TABLE(virtio, id_table); static unsigned int features[] = { VIRTIO_CONSOLE_F_SIZE, @@ -2130,6 +2131,7 @@ static struct virtio_device_id rproc_serial_id_table[] = { #endif { 0 }, }; +MODULE_DEVICE_TABLE(virtio, rproc_serial_id_table); static unsigned int rproc_serial_features[] = { }; @@ -2282,6 +2284,5 @@ static void __exit fini(void) module_init(init); module_exit(fini); -MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio console driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/actions/owl-s500.c b/drivers/clk/actions/owl-s500.c index e2007ac4d235..0eb83a0b70bc 100644 --- a/drivers/clk/actions/owl-s500.c +++ b/drivers/clk/actions/owl-s500.c @@ -183,7 +183,7 @@ static OWL_GATE(timer_clk, "timer_clk", "hosc", CMU_DEVCLKEN1, 27, 0, 0); static OWL_GATE(hdmi_clk, "hdmi_clk", "hosc", CMU_DEVCLKEN1, 3, 0, 0); /* divider clocks */ -static OWL_DIVIDER(h_clk, "h_clk", "ahbprevdiv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0); +static OWL_DIVIDER(h_clk, "h_clk", "ahbprediv_clk", CMU_BUSCLK1, 12, 2, NULL, 0, 0); static OWL_DIVIDER(rmii_ref_clk, "rmii_ref_clk", "ethernet_pll_clk", CMU_ETHERNETPLL, 1, 1, rmii_ref_div_table, 0, 0); /* factor clocks */ diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c index a2287c770d5c..06a47bbcf565 100644 --- a/drivers/clk/clk-scmi.c +++ b/drivers/clk/clk-scmi.c @@ -103,6 +103,8 @@ static const struct clk_ops scmi_clk_ops = { static int scmi_clk_ops_init(struct device *dev, struct scmi_clk *sclk) { int ret; + unsigned long min_rate, max_rate; + struct clk_init_data init = { .flags = CLK_GET_RATE_NOCACHE, .num_parents = 0, @@ -112,9 +114,23 @@ static int scmi_clk_ops_init(struct device *dev, struct scmi_clk *sclk) sclk->hw.init = &init; ret = devm_clk_hw_register(dev, &sclk->hw); - if (!ret) - clk_hw_set_rate_range(&sclk->hw, sclk->info->range.min_rate, - sclk->info->range.max_rate); + if (ret) + return ret; + + if (sclk->info->rate_discrete) { + int num_rates = sclk->info->list.num_rates; + + if (num_rates <= 0) + return -EINVAL; + + min_rate = sclk->info->list.rates[0]; + max_rate = sclk->info->list.rates[num_rates - 1]; + } else { + min_rate = sclk->info->range.min_rate; + max_rate = sclk->info->range.max_rate; + } + + clk_hw_set_rate_range(&sclk->hw, min_rate, max_rate); return ret; } diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index c3fd632af119..3ed9e623e32b 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -147,12 +147,22 @@ static inline bool has_state_changed(struct clk_rpmh *c, u32 state) != (c->aggr_state & BIT(state)); } +static int clk_rpmh_send(struct clk_rpmh *c, enum rpmh_state state, + struct tcs_cmd *cmd, bool wait) +{ + if (wait) + return rpmh_write(c->dev, state, cmd, 1); + + return rpmh_write_async(c->dev, state, cmd, 1); +} + static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c) { struct tcs_cmd cmd = { 0 }; u32 cmd_state, on_val; enum rpmh_state state = RPMH_SLEEP_STATE; int ret; + bool wait; cmd.addr = c->res_addr; cmd_state = c->aggr_state; @@ -163,7 +173,8 @@ static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c) if (cmd_state & BIT(state)) cmd.data = on_val; - ret = rpmh_write_async(c->dev, state, &cmd, 1); + wait = cmd_state && state == RPMH_ACTIVE_ONLY_STATE; + ret = clk_rpmh_send(c, state, &cmd, wait); if (ret) { dev_err(c->dev, "set %s state of %s failed: (%d)\n", !state ? "sleep" : @@ -271,7 +282,7 @@ static int clk_rpmh_bcm_send_cmd(struct clk_rpmh *c, bool enable) cmd.addr = c->res_addr; cmd.data = BCM_TCS_CMD(enable, cmd_state); - ret = rpmh_write_async(c->dev, RPMH_ACTIVE_ONLY_STATE, &cmd, 1); + ret = clk_rpmh_send(c, RPMH_ACTIVE_ONLY_STATE, &cmd, enable); if (ret) { dev_err(c->dev, "set active state of %s failed: (%d)\n", c->res_name, ret); diff --git a/drivers/clk/qcom/gcc-sdm660.c b/drivers/clk/qcom/gcc-sdm660.c index 8827db23066f..e111bfcd3230 100644 --- a/drivers/clk/qcom/gcc-sdm660.c +++ b/drivers/clk/qcom/gcc-sdm660.c @@ -1715,6 +1715,9 @@ static struct clk_branch gcc_mss_cfg_ahb_clk = { static struct clk_branch gcc_mss_mnoc_bimc_axi_clk = { .halt_reg = 0x8a004, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x8a004, + .hwcg_bit = 1, .clkr = { .enable_reg = 0x8a004, .enable_mask = BIT(0), diff --git a/drivers/clk/sirf/clk-atlas6.c b/drivers/clk/sirf/clk-atlas6.c index c84d5bab7ac2..b95483bb6a5e 100644 --- a/drivers/clk/sirf/clk-atlas6.c +++ b/drivers/clk/sirf/clk-atlas6.c @@ -135,7 +135,7 @@ static void __init atlas6_clk_init(struct device_node *np) for (i = pll1; i < maxclk; i++) { atlas6_clks[i] = clk_register(NULL, atlas6_clk_hw_array[i]); - BUG_ON(!atlas6_clks[i]); + BUG_ON(IS_ERR(atlas6_clks[i])); } clk_register_clkdev(atlas6_clks[cpu], NULL, "cpu"); clk_register_clkdev(atlas6_clks[io], NULL, "io"); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index f8129edc145e..bac07ebcb29c 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -29,6 +29,7 @@ config ARM_ARMADA_37XX_CPUFREQ config ARM_ARMADA_8K_CPUFREQ tristate "Armada 8K CPUFreq driver" depends on ARCH_MVEBU && CPUFREQ_DT + select ARMADA_AP_CPU_CLK help This enables the CPUFreq driver support for Marvell Armada8k SOCs. diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index 0df16eb1eb3c..c5f98cafc25c 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -458,6 +458,7 @@ static int __init armada37xx_cpufreq_driver_init(void) /* Now that everything is setup, enable the DVFS at hardware level */ armada37xx_cpufreq_enable_dvfs(nb_pm_base); + memset(&pdata, 0, sizeof(pdata)); pdata.suspend = armada37xx_cpufreq_suspend; pdata.resume = armada37xx_cpufreq_resume; diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 1de2349f1be6..4bdd761a8ca9 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -469,11 +469,9 @@ if CRYPTO_DEV_UX500 endif # if CRYPTO_DEV_UX500 config CRYPTO_DEV_ATMEL_AUTHENC - tristate "Support for Atmel IPSEC/SSL hw accelerator" + bool "Support for Atmel IPSEC/SSL hw accelerator" depends on ARCH_AT91 || COMPILE_TEST - select CRYPTO_AUTHENC - select CRYPTO_DEV_ATMEL_AES - select CRYPTO_DEV_ATMEL_SHA + depends on CRYPTO_DEV_ATMEL_AES help Some Atmel processors can combine the AES and SHA hw accelerators to enhance support of IPSEC/SSL. @@ -486,6 +484,8 @@ config CRYPTO_DEV_ATMEL_AES select CRYPTO_AES select CRYPTO_AEAD select CRYPTO_BLKCIPHER + select CRYPTO_AUTHENC if CRYPTO_DEV_ATMEL_AUTHENC + select CRYPTO_DEV_ATMEL_SHA if CRYPTO_DEV_ATMEL_AUTHENC help Some Atmel processors have AES hw accelerator. Select this if you want to use the Atmel module for diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c index e9f4704494fb..10fd8f314c1c 100644 --- a/drivers/crypto/cavium/cpt/cptvf_algs.c +++ b/drivers/crypto/cavium/cpt/cptvf_algs.c @@ -201,6 +201,7 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc) int status; memset(req_info, 0, sizeof(struct cpt_request_info)); + req_info->may_sleep = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) != 0; memset(fctx, 0, sizeof(struct fc_context)); create_input_list(req, enc, enc_iv_len); create_output_list(req, enc_iv_len); diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c index 7a24019356b5..e343249c8d05 100644 --- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c +++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c @@ -133,7 +133,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf, /* Setup gather (input) components */ g_sz_bytes = ((req->incnt + 3) / 4) * sizeof(struct sglist_component); - info->gather_components = kzalloc(g_sz_bytes, GFP_KERNEL); + info->gather_components = kzalloc(g_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (!info->gather_components) { ret = -ENOMEM; goto scatter_gather_clean; @@ -150,7 +150,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf, /* Setup scatter (output) components */ s_sz_bytes = ((req->outcnt + 3) / 4) * sizeof(struct sglist_component); - info->scatter_components = kzalloc(s_sz_bytes, GFP_KERNEL); + info->scatter_components = kzalloc(s_sz_bytes, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (!info->scatter_components) { ret = -ENOMEM; goto scatter_gather_clean; @@ -167,7 +167,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf, /* Create and initialize DPTR */ info->dlen = g_sz_bytes + s_sz_bytes + SG_LIST_HDR_SIZE; - info->in_buffer = kzalloc(info->dlen, GFP_KERNEL); + info->in_buffer = kzalloc(info->dlen, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (!info->in_buffer) { ret = -ENOMEM; goto scatter_gather_clean; @@ -195,7 +195,7 @@ static inline int setup_sgio_list(struct cpt_vf *cptvf, } /* Create and initialize RPTR */ - info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, GFP_KERNEL); + info->out_buffer = kzalloc(COMPLETION_CODE_SIZE, req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (!info->out_buffer) { ret = -ENOMEM; goto scatter_gather_clean; @@ -421,7 +421,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req) struct cpt_vq_command vq_cmd; union cpt_inst_s cptinst; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!info)) { dev_err(&pdev->dev, "Unable to allocate memory for info_buffer\n"); return -ENOMEM; @@ -443,7 +443,7 @@ int process_request(struct cpt_vf *cptvf, struct cpt_request_info *req) * Get buffer for union cpt_res_s response * structure and its physical address */ - info->completion_addr = kzalloc(sizeof(union cpt_res_s), GFP_KERNEL); + info->completion_addr = kzalloc(sizeof(union cpt_res_s), req->may_sleep ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!info->completion_addr)) { dev_err(&pdev->dev, "Unable to allocate memory for completion_addr\n"); ret = -ENOMEM; diff --git a/drivers/crypto/cavium/cpt/request_manager.h b/drivers/crypto/cavium/cpt/request_manager.h index 3514b082eca7..1e8dd9ebcc17 100644 --- a/drivers/crypto/cavium/cpt/request_manager.h +++ b/drivers/crypto/cavium/cpt/request_manager.h @@ -62,6 +62,8 @@ struct cpt_request_info { union ctrl_info ctrl; /* User control information */ struct cptvf_request req; /* Request Information (Core specific) */ + bool may_sleep; + struct buf_ptr in[MAX_BUF_CNT]; struct buf_ptr out[MAX_BUF_CNT]; diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h index 5e624920fd99..ee9d2ca5e651 100644 --- a/drivers/crypto/ccp/ccp-dev.h +++ b/drivers/crypto/ccp/ccp-dev.h @@ -468,6 +468,7 @@ struct ccp_sg_workarea { unsigned int sg_used; struct scatterlist *dma_sg; + struct scatterlist *dma_sg_head; struct device *dma_dev; unsigned int dma_count; enum dma_data_direction dma_dir; diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index e12506c93a52..95d06cfb7421 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -64,7 +64,7 @@ static u32 ccp_gen_jobid(struct ccp_device *ccp) static void ccp_sg_free(struct ccp_sg_workarea *wa) { if (wa->dma_count) - dma_unmap_sg(wa->dma_dev, wa->dma_sg, wa->nents, wa->dma_dir); + dma_unmap_sg(wa->dma_dev, wa->dma_sg_head, wa->nents, wa->dma_dir); wa->dma_count = 0; } @@ -93,6 +93,7 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev, return 0; wa->dma_sg = sg; + wa->dma_sg_head = sg; wa->dma_dev = dev; wa->dma_dir = dma_dir; wa->dma_count = dma_map_sg(dev, sg, wa->nents, dma_dir); @@ -105,14 +106,28 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev, static void ccp_update_sg_workarea(struct ccp_sg_workarea *wa, unsigned int len) { unsigned int nbytes = min_t(u64, len, wa->bytes_left); + unsigned int sg_combined_len = 0; if (!wa->sg) return; wa->sg_used += nbytes; wa->bytes_left -= nbytes; - if (wa->sg_used == wa->sg->length) { - wa->sg = sg_next(wa->sg); + if (wa->sg_used == sg_dma_len(wa->dma_sg)) { + /* Advance to the next DMA scatterlist entry */ + wa->dma_sg = sg_next(wa->dma_sg); + + /* In the case that the DMA mapped scatterlist has entries + * that have been merged, the non-DMA mapped scatterlist + * must be advanced multiple times for each merged entry. + * This ensures that the current non-DMA mapped entry + * corresponds to the current DMA mapped entry. + */ + do { + sg_combined_len += wa->sg->length; + wa->sg = sg_next(wa->sg); + } while (wa->sg_used > sg_combined_len); + wa->sg_used = 0; } } @@ -301,7 +316,7 @@ static unsigned int ccp_queue_buf(struct ccp_data *data, unsigned int from) /* Update the structures and generate the count */ buf_count = 0; while (sg_wa->bytes_left && (buf_count < dm_wa->length)) { - nbytes = min(sg_wa->sg->length - sg_wa->sg_used, + nbytes = min(sg_dma_len(sg_wa->dma_sg) - sg_wa->sg_used, dm_wa->length - buf_count); nbytes = min_t(u64, sg_wa->bytes_left, nbytes); @@ -333,11 +348,11 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst, * and destination. The resulting len values will always be <= UINT_MAX * because the dma length is an unsigned int. */ - sg_src_len = sg_dma_len(src->sg_wa.sg) - src->sg_wa.sg_used; + sg_src_len = sg_dma_len(src->sg_wa.dma_sg) - src->sg_wa.sg_used; sg_src_len = min_t(u64, src->sg_wa.bytes_left, sg_src_len); if (dst) { - sg_dst_len = sg_dma_len(dst->sg_wa.sg) - dst->sg_wa.sg_used; + sg_dst_len = sg_dma_len(dst->sg_wa.dma_sg) - dst->sg_wa.sg_used; sg_dst_len = min_t(u64, src->sg_wa.bytes_left, sg_dst_len); op_len = min(sg_src_len, sg_dst_len); } else { @@ -367,7 +382,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst, /* Enough data in the sg element, but we need to * adjust for any previously copied data */ - op->src.u.dma.address = sg_dma_address(src->sg_wa.sg); + op->src.u.dma.address = sg_dma_address(src->sg_wa.dma_sg); op->src.u.dma.offset = src->sg_wa.sg_used; op->src.u.dma.length = op_len & ~(block_size - 1); @@ -388,7 +403,7 @@ static void ccp_prepare_data(struct ccp_data *src, struct ccp_data *dst, /* Enough room in the sg element, but we need to * adjust for any previously used area */ - op->dst.u.dma.address = sg_dma_address(dst->sg_wa.sg); + op->dst.u.dma.address = sg_dma_address(dst->sg_wa.dma_sg); op->dst.u.dma.offset = dst->sg_wa.sg_used; op->dst.u.dma.length = op->src.u.dma.length; } @@ -2040,7 +2055,7 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q, dst.sg_wa.sg_used = 0; for (i = 1; i <= src.sg_wa.dma_count; i++) { if (!dst.sg_wa.sg || - (dst.sg_wa.sg->length < src.sg_wa.sg->length)) { + (sg_dma_len(dst.sg_wa.sg) < sg_dma_len(src.sg_wa.sg))) { ret = -EINVAL; goto e_dst; } @@ -2066,8 +2081,8 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q, goto e_dst; } - dst.sg_wa.sg_used += src.sg_wa.sg->length; - if (dst.sg_wa.sg_used == dst.sg_wa.sg->length) { + dst.sg_wa.sg_used += sg_dma_len(src.sg_wa.sg); + if (dst.sg_wa.sg_used == sg_dma_len(dst.sg_wa.sg)) { dst.sg_wa.sg = sg_next(dst.sg_wa.sg); dst.sg_wa.sg_used = 0; } diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c index 67ac87d25aea..5604e188d2d4 100644 --- a/drivers/crypto/ccree/cc_cipher.c +++ b/drivers/crypto/ccree/cc_cipher.c @@ -167,7 +167,6 @@ static int cc_cipher_init(struct crypto_tfm *tfm) skcipher_alg.base); struct device *dev = drvdata_to_dev(cc_alg->drvdata); unsigned int max_key_buf_size = cc_alg->skcipher_alg.max_keysize; - int rc = 0; dev_dbg(dev, "Initializing context @%p for %s\n", ctx_p, crypto_tfm_alg_name(tfm)); @@ -179,10 +178,19 @@ static int cc_cipher_init(struct crypto_tfm *tfm) ctx_p->flow_mode = cc_alg->flow_mode; ctx_p->drvdata = cc_alg->drvdata; + if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) { + /* Alloc hash tfm for essiv */ + ctx_p->shash_tfm = crypto_alloc_shash("sha256-generic", 0, 0); + if (IS_ERR(ctx_p->shash_tfm)) { + dev_err(dev, "Error allocating hash tfm for ESSIV.\n"); + return PTR_ERR(ctx_p->shash_tfm); + } + } + /* Allocate key buffer, cache line aligned */ ctx_p->user.key = kmalloc(max_key_buf_size, GFP_KERNEL); if (!ctx_p->user.key) - return -ENOMEM; + goto free_shash; dev_dbg(dev, "Allocated key buffer in context. key=@%p\n", ctx_p->user.key); @@ -194,21 +202,19 @@ static int cc_cipher_init(struct crypto_tfm *tfm) if (dma_mapping_error(dev, ctx_p->user.key_dma_addr)) { dev_err(dev, "Mapping Key %u B at va=%pK for DMA failed\n", max_key_buf_size, ctx_p->user.key); - return -ENOMEM; + goto free_key; } dev_dbg(dev, "Mapped key %u B at va=%pK to dma=%pad\n", max_key_buf_size, ctx_p->user.key, &ctx_p->user.key_dma_addr); - if (ctx_p->cipher_mode == DRV_CIPHER_ESSIV) { - /* Alloc hash tfm for essiv */ - ctx_p->shash_tfm = crypto_alloc_shash("sha256-generic", 0, 0); - if (IS_ERR(ctx_p->shash_tfm)) { - dev_err(dev, "Error allocating hash tfm for ESSIV.\n"); - return PTR_ERR(ctx_p->shash_tfm); - } - } + return 0; - return rc; +free_key: + kfree(ctx_p->user.key); +free_shash: + crypto_free_shash(ctx_p->shash_tfm); + + return -ENOMEM; } static void cc_cipher_exit(struct crypto_tfm *tfm) diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c index 8c789b8671fc..9a98efc95333 100644 --- a/drivers/crypto/hisilicon/sec/sec_algs.c +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -157,7 +157,8 @@ static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl, dma_addr_t *psec_sgl, struct scatterlist *sgl, int count, - struct sec_dev_info *info) + struct sec_dev_info *info, + gfp_t gfp) { struct sec_hw_sgl *sgl_current = NULL; struct sec_hw_sgl *sgl_next; @@ -172,7 +173,7 @@ static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl, sge_index = i % SEC_MAX_SGE_NUM; if (sge_index == 0) { sgl_next = dma_pool_zalloc(info->hw_sgl_pool, - GFP_KERNEL, &sgl_next_dma); + gfp, &sgl_next_dma); if (!sgl_next) { ret = -ENOMEM; goto err_free_hw_sgls; @@ -555,14 +556,14 @@ void sec_alg_callback(struct sec_bd_info *resp, void *shadow) } static int sec_alg_alloc_and_calc_split_sizes(int length, size_t **split_sizes, - int *steps) + int *steps, gfp_t gfp) { size_t *sizes; int i; /* Split into suitable sized blocks */ *steps = roundup(length, SEC_REQ_LIMIT) / SEC_REQ_LIMIT; - sizes = kcalloc(*steps, sizeof(*sizes), GFP_KERNEL); + sizes = kcalloc(*steps, sizeof(*sizes), gfp); if (!sizes) return -ENOMEM; @@ -578,7 +579,7 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes, int steps, struct scatterlist ***splits, int **splits_nents, int sgl_len_in, - struct device *dev) + struct device *dev, gfp_t gfp) { int ret, count; @@ -586,12 +587,12 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes, if (!count) return -EINVAL; - *splits = kcalloc(steps, sizeof(struct scatterlist *), GFP_KERNEL); + *splits = kcalloc(steps, sizeof(struct scatterlist *), gfp); if (!*splits) { ret = -ENOMEM; goto err_unmap_sg; } - *splits_nents = kcalloc(steps, sizeof(int), GFP_KERNEL); + *splits_nents = kcalloc(steps, sizeof(int), gfp); if (!*splits_nents) { ret = -ENOMEM; goto err_free_splits; @@ -599,7 +600,7 @@ static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes, /* output the scatter list before and after this */ ret = sg_split(sgl, count, 0, steps, split_sizes, - *splits, *splits_nents, GFP_KERNEL); + *splits, *splits_nents, gfp); if (ret) { ret = -ENOMEM; goto err_free_splits_nents; @@ -640,13 +641,13 @@ static struct sec_request_el int el_size, bool different_dest, struct scatterlist *sgl_in, int n_ents_in, struct scatterlist *sgl_out, int n_ents_out, - struct sec_dev_info *info) + struct sec_dev_info *info, gfp_t gfp) { struct sec_request_el *el; struct sec_bd_info *req; int ret; - el = kzalloc(sizeof(*el), GFP_KERNEL); + el = kzalloc(sizeof(*el), gfp); if (!el) return ERR_PTR(-ENOMEM); el->el_length = el_size; @@ -678,7 +679,7 @@ static struct sec_request_el el->sgl_in = sgl_in; ret = sec_alloc_and_fill_hw_sgl(&el->in, &el->dma_in, el->sgl_in, - n_ents_in, info); + n_ents_in, info, gfp); if (ret) goto err_free_el; @@ -689,7 +690,7 @@ static struct sec_request_el el->sgl_out = sgl_out; ret = sec_alloc_and_fill_hw_sgl(&el->out, &el->dma_out, el->sgl_out, - n_ents_out, info); + n_ents_out, info, gfp); if (ret) goto err_free_hw_sgl_in; @@ -730,6 +731,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, int *splits_out_nents = NULL; struct sec_request_el *el, *temp; bool split = skreq->src != skreq->dst; + gfp_t gfp = skreq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC; mutex_init(&sec_req->lock); sec_req->req_base = &skreq->base; @@ -738,13 +740,13 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, sec_req->len_in = sg_nents(skreq->src); ret = sec_alg_alloc_and_calc_split_sizes(skreq->cryptlen, &split_sizes, - &steps); + &steps, gfp); if (ret) return ret; sec_req->num_elements = steps; ret = sec_map_and_split_sg(skreq->src, split_sizes, steps, &splits_in, &splits_in_nents, sec_req->len_in, - info->dev); + info->dev, gfp); if (ret) goto err_free_split_sizes; @@ -752,7 +754,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, sec_req->len_out = sg_nents(skreq->dst); ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps, &splits_out, &splits_out_nents, - sec_req->len_out, info->dev); + sec_req->len_out, info->dev, gfp); if (ret) goto err_unmap_in_sg; } @@ -785,7 +787,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, splits_in[i], splits_in_nents[i], split ? splits_out[i] : NULL, split ? splits_out_nents[i] : 0, - info); + info, gfp); if (IS_ERR(el)) { ret = PTR_ERR(el); goto err_free_elements; diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c index 6bd8f6a2a24f..aeb03081415c 100644 --- a/drivers/crypto/qat/qat_common/qat_uclo.c +++ b/drivers/crypto/qat/qat_common/qat_uclo.c @@ -332,13 +332,18 @@ static int qat_uclo_create_batch_init_list(struct icp_qat_fw_loader_handle } return 0; out_err: + /* Do not free the list head unless we allocated it. */ + tail_old = tail_old->next; + if (flag) { + kfree(*init_tab_base); + *init_tab_base = NULL; + } + while (tail_old) { mem_init = tail_old->next; kfree(tail_old); tail_old = mem_init; } - if (flag) - kfree(*init_tab_base); return -ENOMEM; } diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 21cb2a58dbd2..a1b56f52db2f 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -118,16 +118,11 @@ static void dwc_initialize(struct dw_dma_chan *dwc) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); - if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags)) - return; - dw->initialize_chan(dwc); /* Enable interrupts */ channel_set_bit(dw, MASK.XFER, dwc->mask); channel_set_bit(dw, MASK.ERROR, dwc->mask); - - set_bit(DW_DMA_IS_INITIALIZED, &dwc->flags); } /*----------------------------------------------------------------------*/ @@ -954,8 +949,6 @@ static void dwc_issue_pending(struct dma_chan *chan) void do_dw_dma_off(struct dw_dma *dw) { - unsigned int i; - dma_writel(dw, CFG, 0); channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask); @@ -966,9 +959,6 @@ void do_dw_dma_off(struct dw_dma *dw) while (dma_readl(dw, CFG) & DW_CFG_DMA_EN) cpu_relax(); - - for (i = 0; i < dw->dma.chancnt; i++) - clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags); } void do_dw_dma_on(struct dw_dma *dw) @@ -1032,8 +1022,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan) /* Clear custom channel configuration */ memset(&dwc->dws, 0, sizeof(struct dw_dma_slave)); - clear_bit(DW_DMA_IS_INITIALIZED, &dwc->flags); - /* Disable interrupts */ channel_clear_bit(dw, MASK.XFER, dwc->mask); channel_clear_bit(dw, MASK.BLOCK, dwc->mask); diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 680b2a00a953..c459c8eb96aa 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -320,26 +320,28 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, /* * TCD parameters are stored in struct fsl_edma_hw_tcd in little * endian format. However, we need to load the TCD registers in - * big- or little-endian obeying the eDMA engine model endian. + * big- or little-endian obeying the eDMA engine model endian, + * and this is performed from specific edma_write functions */ edma_writew(edma, 0, ®s->tcd[ch].csr); - edma_writel(edma, le32_to_cpu(tcd->saddr), ®s->tcd[ch].saddr); - edma_writel(edma, le32_to_cpu(tcd->daddr), ®s->tcd[ch].daddr); - edma_writew(edma, le16_to_cpu(tcd->attr), ®s->tcd[ch].attr); - edma_writew(edma, le16_to_cpu(tcd->soff), ®s->tcd[ch].soff); + edma_writel(edma, (s32)tcd->saddr, ®s->tcd[ch].saddr); + edma_writel(edma, (s32)tcd->daddr, ®s->tcd[ch].daddr); - edma_writel(edma, le32_to_cpu(tcd->nbytes), ®s->tcd[ch].nbytes); - edma_writel(edma, le32_to_cpu(tcd->slast), ®s->tcd[ch].slast); + edma_writew(edma, (s16)tcd->attr, ®s->tcd[ch].attr); + edma_writew(edma, tcd->soff, ®s->tcd[ch].soff); - edma_writew(edma, le16_to_cpu(tcd->citer), ®s->tcd[ch].citer); - edma_writew(edma, le16_to_cpu(tcd->biter), ®s->tcd[ch].biter); - edma_writew(edma, le16_to_cpu(tcd->doff), ®s->tcd[ch].doff); + edma_writel(edma, (s32)tcd->nbytes, ®s->tcd[ch].nbytes); + edma_writel(edma, (s32)tcd->slast, ®s->tcd[ch].slast); - edma_writel(edma, le32_to_cpu(tcd->dlast_sga), + edma_writew(edma, (s16)tcd->citer, ®s->tcd[ch].citer); + edma_writew(edma, (s16)tcd->biter, ®s->tcd[ch].biter); + edma_writew(edma, (s16)tcd->doff, ®s->tcd[ch].doff); + + edma_writel(edma, (s32)tcd->dlast_sga, ®s->tcd[ch].dlast_sga); - edma_writew(edma, le16_to_cpu(tcd->csr), ®s->tcd[ch].csr); + edma_writew(edma, (s16)tcd->csr, ®s->tcd[ch].csr); } static inline diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index c53f76eeb4d3..b434c6b9fd54 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -32,7 +32,7 @@ #define EDMA_TCD_ATTR_DSIZE_16BIT BIT(0) #define EDMA_TCD_ATTR_DSIZE_32BIT BIT(1) #define EDMA_TCD_ATTR_DSIZE_64BIT (BIT(0) | BIT(1)) -#define EDMA_TCD_ATTR_DSIZE_32BYTE (BIT(3) | BIT(0)) +#define EDMA_TCD_ATTR_DSIZE_32BYTE (BIT(2) | BIT(0)) #define EDMA_TCD_ATTR_SSIZE_8BIT 0 #define EDMA_TCD_ATTR_SSIZE_16BIT (EDMA_TCD_ATTR_DSIZE_16BIT << 8) #define EDMA_TCD_ATTR_SSIZE_32BIT (EDMA_TCD_ATTR_DSIZE_32BIT << 8) diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c index 0ddad3adb761..8f03930e4691 100644 --- a/drivers/dma/fsl-edma.c +++ b/drivers/dma/fsl-edma.c @@ -38,6 +38,13 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id) fsl_chan = &fsl_edma->chans[ch]; spin_lock(&fsl_chan->vchan.lock); + + if (!fsl_chan->edesc) { + /* terminate_all called before */ + spin_unlock(&fsl_chan->vchan.lock); + continue; + } + if (!fsl_chan->edesc->iscyclic) { list_del(&fsl_chan->edesc->vdesc.node); vchan_cookie_complete(&fsl_chan->edesc->vdesc); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 18c011e57592..8e2a4d1f0be5 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -26,6 +26,18 @@ #include "../dmaengine.h" +int completion_timeout = 200; +module_param(completion_timeout, int, 0644); +MODULE_PARM_DESC(completion_timeout, + "set ioat completion timeout [msec] (default 200 [msec])"); +int idle_timeout = 2000; +module_param(idle_timeout, int, 0644); +MODULE_PARM_DESC(idle_timeout, + "set ioat idel timeout [msec] (default 2000 [msec])"); + +#define IDLE_TIMEOUT msecs_to_jiffies(idle_timeout) +#define COMPLETION_TIMEOUT msecs_to_jiffies(completion_timeout) + static char *chanerr_str[] = { "DMA Transfer Source Address Error", "DMA Transfer Destination Address Error", diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index b8e8e0b9693c..4ac9134962f3 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -99,8 +99,6 @@ struct ioatdma_chan { #define IOAT_RUN 5 #define IOAT_CHAN_ACTIVE 6 struct timer_list timer; - #define COMPLETION_TIMEOUT msecs_to_jiffies(100) - #define IDLE_TIMEOUT msecs_to_jiffies(2000) #define RESET_DELAY msecs_to_jiffies(100) struct ioatdma_device *ioat_dma; dma_addr_t completion_dma; diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c index 7de54b2fafdb..6e3d4ab34321 100644 --- a/drivers/dma/mcf-edma.c +++ b/drivers/dma/mcf-edma.c @@ -35,6 +35,13 @@ static irqreturn_t mcf_edma_tx_handler(int irq, void *dev_id) mcf_chan = &mcf_edma->chans[ch]; spin_lock(&mcf_chan->vchan.lock); + + if (!mcf_chan->edesc) { + /* terminate_all called before */ + spin_unlock(&mcf_chan->vchan.lock); + continue; + } + if (!mcf_chan->edesc->iscyclic) { list_del(&mcf_chan->edesc->vdesc.node); vchan_cookie_complete(&mcf_chan->edesc->vdesc); diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 5f30a22c8723..4373116b579c 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -666,6 +666,7 @@ static int tegra_adma_alloc_chan_resources(struct dma_chan *dc) ret = pm_runtime_get_sync(tdc2dev(tdc)); if (ret < 0) { + pm_runtime_put_noidle(tdc2dev(tdc)); free_irq(tdc->irq, tdc); return ret; } @@ -877,8 +878,10 @@ static int tegra_adma_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); goto rpm_disable; + } ret = tegra_adma_init(tdma); if (ret) diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index 0e7ea3591b78..5e7593753799 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -275,6 +275,7 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev) /* Error exit stack */ err_kobj_reg: + kobject_put(&edac_dev->kobj); module_put(edac_dev->owner); err_out: diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index 72c9eb9fdffb..53042af7262e 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -386,7 +386,7 @@ static int edac_pci_main_kobj_setup(void) /* Error unwind statck */ kobject_init_and_add_fail: - kfree(edac_pci_top_main_kobj); + kobject_put(edac_pci_top_main_kobj); kzalloc_fail: module_put(THIS_MODULE); diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c index 87f737e01473..041f8152272b 100644 --- a/drivers/firmware/arm_scmi/scmi_pm_domain.c +++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c @@ -85,7 +85,10 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) for (i = 0; i < num_domains; i++, scmi_pd++) { u32 state; - domains[i] = &scmi_pd->genpd; + if (handle->power_ops->state_get(handle, i, &state)) { + dev_warn(dev, "failed to get state for domain %d\n", i); + continue; + } scmi_pd->domain = i; scmi_pd->handle = handle; @@ -94,13 +97,10 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) scmi_pd->genpd.power_off = scmi_pd_power_off; scmi_pd->genpd.power_on = scmi_pd_power_on; - if (handle->power_ops->state_get(handle, i, &state)) { - dev_warn(dev, "failed to get state for domain %d\n", i); - continue; - } - pm_genpd_init(&scmi_pd->genpd, NULL, state == SCMI_POWER_STATE_GENERIC_OFF); + + domains[i] = &scmi_pd->genpd; } scmi_pd_data->domains = domains; diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c index f3659443f8c2..d89c0dd5159a 100644 --- a/drivers/firmware/psci/psci_checker.c +++ b/drivers/firmware/psci/psci_checker.c @@ -157,8 +157,10 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups) cpu_groups = kcalloc(nb_available_cpus, sizeof(cpu_groups), GFP_KERNEL); - if (!cpu_groups) + if (!cpu_groups) { + free_cpumask_var(tmp); return -ENOMEM; + } cpumask_copy(tmp, cpu_online_mask); @@ -167,6 +169,7 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups) topology_core_cpumask(cpumask_any(tmp)); if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) { + free_cpumask_var(tmp); free_cpu_groups(num_groups, &cpu_groups); return -ENOMEM; } diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 039e0f91dba8..6945c3c96637 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -605,8 +605,10 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) /* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */ err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype, fw_cfg_sel_ko, "%d", entry->select); - if (err) - goto err_register; + if (err) { + kobject_put(&entry->kobj); + return err; + } /* add raw binary content access */ err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw); @@ -622,7 +624,6 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) err_add_raw: kobject_del(&entry->kobj); -err_register: kfree(entry); return err; } diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c index 02baa6a227c0..fc048f9a99b1 100644 --- a/drivers/fpga/dfl-afu-main.c +++ b/drivers/fpga/dfl-afu-main.c @@ -79,7 +79,8 @@ static int port_disable(struct platform_device *pdev) * on this port and minimum soft reset pulse width has elapsed. * Driver polls port_soft_reset_ack to determine if reset done by HW. */ - if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST, + if (readq_poll_timeout(base + PORT_HDR_CTRL, v, + v & PORT_CTRL_SFTRST_ACK, RST_POLL_INVL, RST_POLL_TIMEOUT)) { dev_err(&pdev->dev, "timeout, fail to reset device\n"); return -ETIMEDOUT; diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index c07fad975049..6e192581495b 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -64,6 +64,7 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset) ret = pm_runtime_get_sync(chip->parent); if (ret < 0) { dev_err(chip->parent, "Failed to resume: %d\n", ret); + pm_runtime_put_autosuspend(chip->parent); return ret; } @@ -72,12 +73,15 @@ static int arizona_gpio_get(struct gpio_chip *chip, unsigned offset) if (ret < 0) { dev_err(chip->parent, "Failed to drop cache: %d\n", ret); + pm_runtime_put_autosuspend(chip->parent); return ret; } ret = regmap_read(arizona->regmap, reg, &val); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(chip->parent); return ret; + } pm_runtime_mark_last_busy(chip->parent); pm_runtime_put_autosuspend(chip->parent); @@ -106,6 +110,7 @@ static int arizona_gpio_direction_out(struct gpio_chip *chip, ret = pm_runtime_get_sync(chip->parent); if (ret < 0) { dev_err(chip->parent, "Failed to resume: %d\n", ret); + pm_runtime_put(chip->parent); return ret; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 4dee2326b29c..04ef5a264f7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -402,7 +402,9 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, ring->fence_drv.gpu_addr = adev->uvd.inst[ring->me].gpu_addr + index; } amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq)); - amdgpu_irq_get(adev, irq_src, irq_type); + + if (irq_src) + amdgpu_irq_get(adev, irq_src, irq_type); ring->fence_drv.irq_src = irq_src; ring->fence_drv.irq_type = irq_type; @@ -514,8 +516,9 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) /* no need to trigger GPU reset as we are unloading */ amdgpu_fence_driver_force_completion(ring); } - amdgpu_irq_put(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_put(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); drm_sched_fini(&ring->sched); del_timer_sync(&ring->fence_drv.fallback_timer); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) @@ -551,8 +554,9 @@ void amdgpu_fence_driver_suspend(struct amdgpu_device *adev) } /* disable the interrupt */ - amdgpu_irq_put(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_put(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); } } @@ -578,8 +582,9 @@ void amdgpu_fence_driver_resume(struct amdgpu_device *adev) continue; /* enable the interrupt */ - amdgpu_irq_get(adev, ring->fence_drv.irq_src, - ring->fence_drv.irq_type); + if (ring->fence_drv.irq_src) + amdgpu_irq_get(adev, ring->fence_drv.irq_src, + ring->fence_drv.irq_type); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index b3c9ab4e4a55..fe42c6b5849d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -653,9 +653,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info = {}; + struct drm_amdgpu_info_device dev_info; uint64_t vm_size; + memset(&dev_info, 0, sizeof(dev_info)); dev_info.device_id = dev->pdev->device; dev_info.chip_rev = adev->rev_id; dev_info.external_rev = adev->external_rev_id; 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 ab7ce802c164..1557bd9f0b80 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -777,9 +777,14 @@ static int dm_late_init(void *handle) struct dmcu_iram_parameters params; unsigned int linear_lut[16]; int i; - struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu; + struct dmcu *dmcu = NULL; bool ret; + if (!adev->dm.fw_dmcu) + return detect_mst_link_for_all_connectors(adev->ddev); + + dmcu = adev->dm.dc->res_pool->dmcu; + for (i = 0; i < 16; i++) linear_lut[i] = 0xFFFF * i / 15; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index 37893145e712..b7ab878f3932 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -500,6 +500,8 @@ bool dm_pp_get_static_clocks( &pp_clk_info); else if (adev->smu.funcs) ret = smu_get_current_clocks(&adev->smu, &pp_clk_info); + else + return false; if (ret) return false; diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 4749574d5fd5..50e5ab5a0be1 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -166,7 +166,8 @@ static int smu_v11_0_init_microcode(struct smu_context *smu) chip_name = "vega20"; break; default: - BUG(); + dev_err(adev->dev, "Unsupported ASIC type %d\n", adev->asic_type); + return -EINVAL; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c index 7627792cda93..4de562758436 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c @@ -2724,7 +2724,10 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr) { - return ci_is_smc_ram_running(hwmgr); + return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, + CGS_IND_REG__SMC, FEATURE_STATUS, + VOLTAGE_CONTROLLER_ON)) + ? true : false; } static int ci_smu_init(struct pp_hwmgr *hwmgr) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c index 1e69300f6175..d33ae5ba8fbf 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c @@ -642,9 +642,6 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, /* sclk is bigger than max sclk in the dependence table */ *voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), - (dep_table->entries[i - 1].vddc - - (uint16_t)VDDC_VDDCI_DELTA)); if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control) *voltage |= (data->vbios_boot_state.vddci_bootup_value * @@ -652,8 +649,13 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, else if (dep_table->entries[i - 1].vddci) *voltage |= (dep_table->entries[i - 1].vddci * VOLTAGE_SCALE) << VDDC_SHIFT; - else + else { + vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), + (dep_table->entries[i - 1].vddc - + (uint16_t)VDDC_VDDCI_DELTA)); + *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; + } if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) *mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE; diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index 062e88e238dd..2631e76bac7c 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -928,7 +928,7 @@ int malidp_de_planes_init(struct drm_device *drm) const struct malidp_hw_regmap *map = &malidp->dev->hw->map; struct malidp_plane *plane = NULL; enum drm_plane_type plane_type; - unsigned long crtcs = 1 << drm->mode_config.num_crtc; + unsigned long crtcs = BIT(drm->mode_config.num_crtc); unsigned long flags = DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 37e515221ad8..6f42db56c20c 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -190,6 +190,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.fb_base = bochs->fb_base; bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; + bochs->dev->mode_config.fbdev_use_iomem = true; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index bd3165ee5354..04431dbac4a4 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -177,7 +177,7 @@ static void sii8620_read_buf(struct sii8620 *ctx, u16 addr, u8 *buf, int len) static u8 sii8620_readb(struct sii8620 *ctx, u16 addr) { - u8 ret; + u8 ret = 0; sii8620_read_buf(ctx, addr, &ret, 1); return ret; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index f72ee137e5f1..638fd14e0858 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -607,6 +607,12 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, buf[i]); } + /* Clear old status bits before start so we don't get confused */ + regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG, + AUX_IRQ_STATUS_NAT_I2C_FAIL | + AUX_IRQ_STATUS_AUX_RPLY_TOUT | + AUX_IRQ_STATUS_AUX_SHORT); + regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND); ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val, diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index f8468eae0503..b531649e4ee2 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -354,13 +354,13 @@ static ssize_t connector_write(struct file *file, const char __user *ubuf, buf[len] = '\0'; - if (!strcmp(buf, "on")) + if (sysfs_streq(buf, "on")) connector->force = DRM_FORCE_ON; - else if (!strcmp(buf, "digital")) + else if (sysfs_streq(buf, "digital")) connector->force = DRM_FORCE_ON_DIGITAL; - else if (!strcmp(buf, "off")) + else if (sysfs_streq(buf, "off")) connector->force = DRM_FORCE_OFF; - else if (!strcmp(buf, "unspecified")) + else if (sysfs_streq(buf, "unspecified")) connector->force = DRM_FORCE_UNSPECIFIED; else return -EINVAL; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index d4cc602a9bd5..aa6e6d88f30b 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3241,11 +3241,11 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, { int ret; - port = drm_dp_mst_topology_get_port_validated(mgr, port); - if (!port) + if (slots < 0) return false; - if (slots < 0) + port = drm_dp_mst_topology_get_port_validated(mgr, port); + if (!port) return false; if (port->vcpi.vcpi > 0) { @@ -3261,6 +3261,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, if (ret) { DRM_DEBUG_KMS("failed to init vcpi slots=%d max=63 ret=%d\n", DIV_ROUND_UP(pbn, mgr->pbn_div), ret); + drm_dp_mst_topology_put_port(port); goto out; } DRM_DEBUG_KMS("initing vcpi for pbn=%d slots=%d\n", diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index d0d945f739d7..1124be028ff5 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -775,7 +775,11 @@ static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper, unsigned int y; for (y = clip->y1; y < clip->y2; y++) { - memcpy(dst, src, len); + if (!fb_helper->dev->mode_config.fbdev_use_iomem) + memcpy(dst, src, len); + else + memcpy_toio((void __iomem *)dst, src, len); + src += fb->pitches[0]; dst += fb->pitches[0]; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 50de138c89e0..dbab035203ee 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -703,6 +703,8 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, if (!objs) return -ENOMEM; + *objs_out = objs; + handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL); if (!handles) { ret = -ENOMEM; @@ -716,8 +718,6 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, } ret = objects_lookup(filp, handles, count, objs); - *objs_out = objs; - out: kvfree(handles); return ret; @@ -865,9 +865,6 @@ err: * @file_priv: drm file-private structure * * Open an object using the global name, returning a handle and the size. - * - * This handle (of course) holds a reference to the object, so the object - * will not go away until the handle is deleted. */ int drm_gem_open_ioctl(struct drm_device *dev, void *data, @@ -892,14 +889,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data, /* drm_gem_handle_create_tail unlocks dev->object_name_lock. */ ret = drm_gem_handle_create_tail(file_priv, obj, &handle); - drm_gem_object_put_unlocked(obj); if (ret) - return ret; + goto err; args->handle = handle; args->size = obj->size; - return 0; +err: + drm_gem_object_put_unlocked(obj); + return ret; } /** diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 80b75501f5c6..7ed8e510565e 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -1034,11 +1034,11 @@ EXPORT_SYMBOL(mipi_dsi_dcs_set_pixel_format); */ int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline) { - u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8, - scanline & 0xff }; + u8 payload[2] = { scanline >> 8, scanline & 0xff }; ssize_t err; - err = mipi_dsi_generic_write(dsi, payload, sizeof(payload)); + err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_SCANLINE, payload, + sizeof(payload)); if (err < 0) return err; diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index d00ea384dcbf..58f5dc2f6dd5 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -121,6 +121,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Asus T103HAF */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* GPD MicroPC (generic strings, also match on bios date) */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"), diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 5418a1a87b2c..517d87175fed 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -694,7 +694,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) ret = pm_runtime_get_sync(gpu->dev); if (ret < 0) { dev_err(gpu->dev, "Failed to enable GPU power domain\n"); - return ret; + goto pm_put; } etnaviv_hw_identify(gpu); @@ -808,6 +808,7 @@ destroy_iommu: gpu->mmu = NULL; fail: pm_runtime_mark_last_busy(gpu->dev); +pm_put: pm_runtime_put_autosuspend(gpu->dev); return ret; @@ -848,7 +849,7 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) ret = pm_runtime_get_sync(gpu->dev); if (ret < 0) - return ret; + goto pm_put; dma_lo = gpu_read(gpu, VIVS_FE_DMA_LOW); dma_hi = gpu_read(gpu, VIVS_FE_DMA_HIGH); @@ -971,6 +972,7 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) ret = 0; pm_runtime_mark_last_busy(gpu->dev); +pm_put: pm_runtime_put_autosuspend(gpu->dev); return ret; @@ -984,7 +986,7 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu) dev_err(gpu->dev, "recover hung GPU!\n"); if (pm_runtime_get_sync(gpu->dev) < 0) - return; + goto pm_put; mutex_lock(&gpu->lock); @@ -1002,6 +1004,7 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu) mutex_unlock(&gpu->lock); pm_runtime_mark_last_busy(gpu->dev); +pm_put: pm_runtime_put_autosuspend(gpu->dev); } @@ -1274,8 +1277,10 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) if (!submit->runtime_resumed) { ret = pm_runtime_get_sync(gpu->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(gpu->dev); return NULL; + } submit->runtime_resumed = true; } @@ -1292,6 +1297,7 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) ret = event_alloc(gpu, nr_events, event); if (ret) { DRM_ERROR("no free events\n"); + pm_runtime_put_noidle(gpu->dev); return NULL; } @@ -1453,7 +1459,7 @@ static int etnaviv_gpu_clk_enable(struct etnaviv_gpu *gpu) if (gpu->clk_bus) { ret = clk_prepare_enable(gpu->clk_bus); if (ret) - return ret; + goto disable_clk_reg; } if (gpu->clk_core) { @@ -1476,6 +1482,9 @@ disable_clk_core: disable_clk_bus: if (gpu->clk_bus) clk_disable_unprepare(gpu->clk_bus); +disable_clk_reg: + if (gpu->clk_reg) + clk_disable_unprepare(gpu->clk_reg); return ret; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 1098a4c8f526..38f7e9dc9485 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -59,7 +59,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; - int ret; + int ret = 0; if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) { DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n", @@ -90,7 +90,7 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, if (ret) clear_dma_max_seg_size(subdrv_dev); - return 0; + return ret; } /* diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 8363cb40daed..08e5e45eaf0e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -266,8 +266,10 @@ static void mic_pre_enable(struct drm_bridge *bridge) goto unlock; ret = pm_runtime_get_sync(mic->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(mic->dev); goto unlock; + } mic_set_path(mic, 1); diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 25f78196b964..689b07bc91c4 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -3103,8 +3103,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL); - MMIO_D(GAMT_CHKN_BIT_REG, D_KBL); - MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL); + MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL); + MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS); return 0; } diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 06393cd1067d..fb86fb6c67e7 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -210,9 +210,8 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master, if (!pdev->dev.of_node) return -ENODEV; - hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); - if (!hdmi) - return -ENOMEM; + hdmi = dev_get_drvdata(dev); + memset(hdmi, 0, sizeof(*hdmi)); match = of_match_node(dw_hdmi_imx_dt_ids, pdev->dev.of_node); plat_data = match->data; @@ -237,8 +236,6 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master, drm_encoder_init(drm, encoder, &dw_hdmi_imx_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); - platform_set_drvdata(pdev, hdmi); - hdmi->hdmi = dw_hdmi_bind(pdev, encoder, plat_data); /* @@ -268,6 +265,14 @@ static const struct component_ops dw_hdmi_imx_ops = { static int dw_hdmi_imx_probe(struct platform_device *pdev) { + struct imx_hdmi *hdmi; + + hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); + if (!hdmi) + return -ENOMEM; + + platform_set_drvdata(pdev, hdmi); + return component_add(&pdev->dev, &dw_hdmi_imx_ops); } diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 3e8bece620df..97b78e384183 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -280,9 +280,10 @@ static void imx_drm_unbind(struct device *dev) drm_kms_helper_poll_fini(drm); + component_unbind_all(drm->dev, drm); + drm_mode_config_cleanup(drm); - component_unbind_all(drm->dev, drm); dev_set_drvdata(dev, NULL); drm_dev_put(drm); diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 383733302280..c92a5149ae4e 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -303,18 +303,19 @@ static void imx_ldb_encoder_disable(struct drm_encoder *encoder) { struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); struct imx_ldb *ldb = imx_ldb_ch->ldb; + int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; int mux, ret; drm_panel_disable(imx_ldb_ch->panel); - if (imx_ldb_ch == &ldb->channel[0]) + if (imx_ldb_ch == &ldb->channel[0] || dual) ldb->ldb_ctrl &= ~LDB_CH0_MODE_EN_MASK; - else if (imx_ldb_ch == &ldb->channel[1]) + if (imx_ldb_ch == &ldb->channel[1] || dual) ldb->ldb_ctrl &= ~LDB_CH1_MODE_EN_MASK; regmap_write(ldb->regmap, IOMUXC_GPR2, ldb->ldb_ctrl); - if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) { + if (dual) { clk_disable_unprepare(ldb->clk[0]); clk_disable_unprepare(ldb->clk[1]); } @@ -593,9 +594,8 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) int ret; int i; - imx_ldb = devm_kzalloc(dev, sizeof(*imx_ldb), GFP_KERNEL); - if (!imx_ldb) - return -ENOMEM; + imx_ldb = dev_get_drvdata(dev); + memset(imx_ldb, 0, sizeof(*imx_ldb)); imx_ldb->regmap = syscon_regmap_lookup_by_phandle(np, "gpr"); if (IS_ERR(imx_ldb->regmap)) { @@ -703,8 +703,6 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) } } - dev_set_drvdata(dev, imx_ldb); - return 0; free_child: @@ -736,6 +734,14 @@ static const struct component_ops imx_ldb_ops = { static int imx_ldb_probe(struct platform_device *pdev) { + struct imx_ldb *imx_ldb; + + imx_ldb = devm_kzalloc(&pdev->dev, sizeof(*imx_ldb), GFP_KERNEL); + if (!imx_ldb) + return -ENOMEM; + + platform_set_drvdata(pdev, imx_ldb); + return component_add(&pdev->dev, &imx_ldb_ops); } diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index e725af8a0025..527e2659d99c 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -490,6 +490,13 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve) return 0; } +static void imx_tve_disable_regulator(void *data) +{ + struct imx_tve *tve = data; + + regulator_disable(tve->dac_reg); +} + static bool imx_tve_readable_reg(struct device *dev, unsigned int reg) { return (reg % 4 == 0) && (reg <= 0xdc); @@ -542,9 +549,8 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) int irq; int ret; - tve = devm_kzalloc(dev, sizeof(*tve), GFP_KERNEL); - if (!tve) - return -ENOMEM; + tve = dev_get_drvdata(dev); + memset(tve, 0, sizeof(*tve)); tve->dev = dev; spin_lock_init(&tve->lock); @@ -614,6 +620,9 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) ret = regulator_enable(tve->dac_reg); if (ret) return ret; + ret = devm_add_action_or_reset(dev, imx_tve_disable_regulator, tve); + if (ret) + return ret; } tve->clk = devm_clk_get(dev, "tve"); @@ -655,27 +664,23 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) if (ret) return ret; - dev_set_drvdata(dev, tve); - return 0; } -static void imx_tve_unbind(struct device *dev, struct device *master, - void *data) -{ - struct imx_tve *tve = dev_get_drvdata(dev); - - if (!IS_ERR(tve->dac_reg)) - regulator_disable(tve->dac_reg); -} - static const struct component_ops imx_tve_ops = { .bind = imx_tve_bind, - .unbind = imx_tve_unbind, }; static int imx_tve_probe(struct platform_device *pdev) { + struct imx_tve *tve; + + tve = devm_kzalloc(&pdev->dev, sizeof(*tve), GFP_KERNEL); + if (!tve) + return -ENOMEM; + + platform_set_drvdata(pdev, tve); + return component_add(&pdev->dev, &imx_tve_ops); } diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index c436a28d50e4..f3df21880140 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -434,21 +434,13 @@ static int ipu_drm_bind(struct device *dev, struct device *master, void *data) struct ipu_client_platformdata *pdata = dev->platform_data; struct drm_device *drm = data; struct ipu_crtc *ipu_crtc; - int ret; - ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL); - if (!ipu_crtc) - return -ENOMEM; + ipu_crtc = dev_get_drvdata(dev); + memset(ipu_crtc, 0, sizeof(*ipu_crtc)); ipu_crtc->dev = dev; - ret = ipu_crtc_init(ipu_crtc, pdata, drm); - if (ret) - return ret; - - dev_set_drvdata(dev, ipu_crtc); - - return 0; + return ipu_crtc_init(ipu_crtc, pdata, drm); } static void ipu_drm_unbind(struct device *dev, struct device *master, @@ -470,6 +462,7 @@ static const struct component_ops ipu_crtc_ops = { static int ipu_drm_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct ipu_crtc *ipu_crtc; int ret; if (!dev->platform_data) @@ -479,6 +472,12 @@ static int ipu_drm_probe(struct platform_device *pdev) if (ret) return ret; + ipu_crtc = devm_kzalloc(dev, sizeof(*ipu_crtc), GFP_KERNEL); + if (!ipu_crtc) + return -ENOMEM; + + dev_set_drvdata(dev, ipu_crtc); + return component_add(dev, &ipu_crtc_ops); } diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 1a76de1e8e7b..487ba3b176d3 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -205,9 +205,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) u32 bus_format = 0; const char *fmt; - imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL); - if (!imxpd) - return -ENOMEM; + imxpd = dev_get_drvdata(dev); + memset(imxpd, 0, sizeof(*imxpd)); edidp = of_get_property(np, "edid", &imxpd->edid_len); if (edidp) @@ -237,8 +236,6 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) if (ret) return ret; - dev_set_drvdata(dev, imxpd); - return 0; } @@ -260,6 +257,14 @@ static const struct component_ops imx_pd_ops = { static int imx_pd_probe(struct platform_device *pdev) { + struct imx_parallel_display *imxpd; + + imxpd = devm_kzalloc(&pdev->dev, sizeof(*imxpd), GFP_KERNEL); + if (!imxpd) + return -ENOMEM; + + platform_set_drvdata(pdev, imxpd); + return component_add(&pdev->dev, &imx_pd_ops); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 8026e4035e17..862ec6a96406 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -713,10 +713,19 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) /* Turn on the resources */ pm_runtime_get_sync(gmu->dev); + /* + * "enable" the GX power domain which won't actually do anything but it + * will make sure that the refcounting is correct in case we need to + * bring down the GX after a GMU failure + */ + if (!IS_ERR_OR_NULL(gmu->gxpd)) + pm_runtime_get_sync(gmu->gxpd); + /* Use a known rate to bring up the GMU */ clk_set_rate(gmu->core_clk, 200000000); ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks); if (ret) { + pm_runtime_put(gmu->gxpd); pm_runtime_put(gmu->dev); return ret; } @@ -752,19 +761,12 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) /* Set the GPU to the highest power frequency */ __a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1); - /* - * "enable" the GX power domain which won't actually do anything but it - * will make sure that the refcounting is correct in case we need to - * bring down the GX after a GMU failure - */ - if (!IS_ERR_OR_NULL(gmu->gxpd)) - pm_runtime_get(gmu->gxpd); - out: /* On failure, shut down the GMU to leave it in a good state */ if (ret) { disable_irq(gmu->gmu_irq); a6xx_rpmh_stop(gmu); + pm_runtime_put(gmu->gxpd); pm_runtime_put(gmu->dev); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index ccc298711bae..b97a541079ec 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -397,7 +397,7 @@ static void dpu_crtc_frame_event_cb(void *data, u32 event) spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags); if (!fevent) { - DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event); + DRM_ERROR_RATELIMITED("crtc%d event %d overflow\n", crtc->base.id, event); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index e26d2f3363ee..8fcfee5e6e85 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2221,7 +2221,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, dpu_enc = to_dpu_encoder_virt(enc); - mutex_init(&dpu_enc->enc_lock); ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info); if (ret) goto fail; @@ -2236,7 +2235,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, 0); - mutex_init(&dpu_enc->rc_lock); INIT_DELAYED_WORK(&dpu_enc->delayed_off_work, dpu_encoder_off_work); dpu_enc->idle_timeout = IDLE_TIMEOUT; @@ -2281,6 +2279,8 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, spin_lock_init(&dpu_enc->enc_spinlock); dpu_enc->enabled = false; + mutex_init(&dpu_enc->enc_lock); + mutex_init(&dpu_enc->rc_lock); return &dpu_enc->base; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 49a019939ccd..bba6291b58a2 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -937,10 +937,8 @@ int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, static int msm_gem_new_impl(struct drm_device *dev, uint32_t size, uint32_t flags, struct reservation_object *resv, - struct drm_gem_object **obj, - bool struct_mutex_locked) + struct drm_gem_object **obj) { - struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; switch (flags & MSM_BO_CACHE_MASK) { @@ -969,15 +967,6 @@ static int msm_gem_new_impl(struct drm_device *dev, INIT_LIST_HEAD(&msm_obj->submit_entry); INIT_LIST_HEAD(&msm_obj->vmas); - if (struct_mutex_locked) { - WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - list_add_tail(&msm_obj->mm_list, &priv->inactive_list); - } else { - mutex_lock(&dev->struct_mutex); - list_add_tail(&msm_obj->mm_list, &priv->inactive_list); - mutex_unlock(&dev->struct_mutex); - } - *obj = &msm_obj->base; return 0; @@ -987,6 +976,7 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, uint32_t size, uint32_t flags, bool struct_mutex_locked) { struct msm_drm_private *priv = dev->dev_private; + struct msm_gem_object *msm_obj; struct drm_gem_object *obj = NULL; bool use_vram = false; int ret; @@ -1007,14 +997,15 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, if (size == 0) return ERR_PTR(-EINVAL); - ret = msm_gem_new_impl(dev, size, flags, NULL, &obj, struct_mutex_locked); + ret = msm_gem_new_impl(dev, size, flags, NULL, &obj); if (ret) goto fail; + msm_obj = to_msm_bo(obj); + if (use_vram) { struct msm_gem_vma *vma; struct page **pages; - struct msm_gem_object *msm_obj = to_msm_bo(obj); mutex_lock(&msm_obj->lock); @@ -1049,6 +1040,15 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER); } + if (struct_mutex_locked) { + WARN_ON(!mutex_is_locked(&dev->struct_mutex)); + list_add_tail(&msm_obj->mm_list, &priv->inactive_list); + } else { + mutex_lock(&dev->struct_mutex); + list_add_tail(&msm_obj->mm_list, &priv->inactive_list); + mutex_unlock(&dev->struct_mutex); + } + return obj; fail: @@ -1071,6 +1071,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, struct drm_gem_object *msm_gem_import(struct drm_device *dev, struct dma_buf *dmabuf, struct sg_table *sgt) { + struct msm_drm_private *priv = dev->dev_private; struct msm_gem_object *msm_obj; struct drm_gem_object *obj; uint32_t size; @@ -1084,7 +1085,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, size = PAGE_ALIGN(dmabuf->size); - ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj, false); + ret = msm_gem_new_impl(dev, size, MSM_BO_WC, dmabuf->resv, &obj); if (ret) goto fail; @@ -1109,6 +1110,11 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, } mutex_unlock(&msm_obj->lock); + + mutex_lock(&dev->struct_mutex); + list_add_tail(&msm_obj->mm_list, &priv->inactive_list); + mutex_unlock(&dev->struct_mutex); + return obj; fail: diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index c70e00e22c4c..5ae5a465d28a 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -69,8 +69,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, queue->flags = flags; if (priv->gpu) { - if (prio >= priv->gpu->nr_rings) + if (prio >= priv->gpu->nr_rings) { + kfree(queue); return -EINVAL; + } queue->prio = prio; } diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 4497f07935cd..ec639d055595 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -83,18 +83,20 @@ nv50_head_atomic_check_dither(struct nv50_head_atom *armh, { u32 mode = 0x00; - if (asyc->dither.mode == DITHERING_MODE_AUTO) { - if (asyh->base.depth > asyh->or.bpc * 3) - mode = DITHERING_MODE_DYNAMIC2X2; - } else { - mode = asyc->dither.mode; - } + if (asyc->dither.mode) { + if (asyc->dither.mode == DITHERING_MODE_AUTO) { + if (asyh->base.depth > asyh->or.bpc * 3) + mode = DITHERING_MODE_DYNAMIC2X2; + } else { + mode = asyc->dither.mode; + } - if (asyc->dither.depth == DITHERING_DEPTH_AUTO) { - if (asyh->or.bpc >= 8) - mode |= DITHERING_DEPTH_8BPC; - } else { - mode |= asyc->dither.depth; + if (asyc->dither.depth == DITHERING_DEPTH_AUTO) { + if (asyh->or.bpc >= 8) + mode |= DITHERING_DEPTH_8BPC; + } else { + mode |= asyc->dither.depth; + } } asyh->dither.enable = mode; diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 7dfbbbc1beea..5c314f135dd1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -54,8 +54,10 @@ nouveau_debugfs_strap_peek(struct seq_file *m, void *data) int ret; ret = pm_runtime_get_sync(drm->dev->dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(drm->dev->dev); return ret; + } seq_printf(m, "0x%08x\n", nvif_rd32(&drm->client.device.object, 0x101000)); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index e6b2cd082544..425fe54da1f5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1050,8 +1050,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) /* need to bring up power immediately if opening device */ ret = pm_runtime_get_sync(dev->dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(dev->dev); return ret; + } get_task_comm(tmpname, current); snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid)); @@ -1133,8 +1135,10 @@ nouveau_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) long ret; ret = pm_runtime_get_sync(dev->dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(dev->dev); return ret; + } switch (_IOC_NR(cmd) - DRM_COMMAND_BASE) { case DRM_NOUVEAU_NVIF: diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 73cc3217068a..d323b7e99def 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -315,7 +315,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, struct nouveau_framebuffer *fb; struct nouveau_channel *chan; struct nouveau_bo *nvbo; - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {}; int ret; mode_cmd.width = sizes->surface_width; @@ -592,6 +592,7 @@ fini: drm_fb_helper_fini(&fbcon->helper); free: kfree(fbcon); + drm->fbcon = NULL; return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index b4bda716564d..0f96beec66ac 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -45,8 +45,10 @@ nouveau_gem_object_del(struct drm_gem_object *gem) int ret; ret = pm_runtime_get_sync(dev); - if (WARN_ON(ret < 0 && ret != -EACCES)) + if (WARN_ON(ret < 0 && ret != -EACCES)) { + pm_runtime_put_autosuspend(dev); return; + } if (gem->import_attach) drm_prime_gem_destroy(gem, nvbo->bo.sg); diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index 8ebdc74cc0ad..326948b65542 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -96,12 +96,9 @@ nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo, uint32_t page_flags) else nvbe->ttm.ttm.func = &nv50_sgdma_backend; - if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags)) - /* - * A failing ttm_dma_tt_init() will call ttm_tt_destroy() - * and thus our nouveau_sgdma_destroy() hook, so we don't need - * to free nvbe here. - */ + if (ttm_dma_tt_init(&nvbe->ttm, bo, page_flags)) { + kfree(nvbe); return NULL; + } return &nvbe->ttm.ttm; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c index c8ab1b5741a3..db7769cb33eb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c @@ -118,10 +118,10 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry, if (retries) udelay(400); - /* transaction request, wait up to 1ms for it to complete */ + /* transaction request, wait up to 2ms for it to complete */ nvkm_wr32(device, 0x00e4e4 + base, 0x00010000 | ctrl); - timeout = 1000; + timeout = 2000; do { ctrl = nvkm_rd32(device, 0x00e4e4 + base); udelay(1); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c index 7ef60895f43a..edb6148cbca0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c @@ -118,10 +118,10 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry, if (retries) udelay(400); - /* transaction request, wait up to 1ms for it to complete */ + /* transaction request, wait up to 2ms for it to complete */ nvkm_wr32(device, 0x00d954 + base, 0x00010000 | ctrl); - timeout = 1000; + timeout = 2000; do { ctrl = nvkm_rd32(device, 0x00d954 + base); udelay(1); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 70844fab052f..3a7410057c92 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1663,7 +1663,7 @@ static const struct drm_display_mode lg_lb070wv8_mode = { static const struct panel_desc lg_lb070wv8 = { .modes = &lg_lb070wv8_mode, .num_modes = 1, - .bpc = 16, + .bpc = 8, .size = { .width = 151, .height = 91, diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index b1ff1de6fa7c..0f9d7945ae09 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -4364,7 +4364,7 @@ static int ci_set_mc_special_registers(struct radeon_device *rdev, table->mc_reg_table_entry[k].mc_data[j] |= 0x100; } j++; - if (j > SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE) + if (j >= SMU7_DISCRETE_MC_REGISTER_ARRAY_SIZE) return -EINVAL; if (!pi->mem_gddr5) { diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 68743c78b486..b1efbef8107f 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -626,8 +626,10 @@ radeon_crtc_set_config(struct drm_mode_set *set, dev = set->crtc->dev; ret = pm_runtime_get_sync(dev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(dev->dev); return ret; + } ret = drm_crtc_helper_set_config(set, ctx); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index c7f208d1be08..ab1bc6fcfd0b 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -170,12 +170,7 @@ int radeon_no_wb; int radeon_modeset = -1; int radeon_dynclks = -1; int radeon_r4xx_atom = 0; -#ifdef __powerpc__ -/* Default to PCI on PowerPC (fdo #95017) */ int radeon_agpmode = -1; -#else -int radeon_agpmode = 0; -#endif int radeon_vram_limit = 0; int radeon_gart_size = -1; /* auto */ int radeon_benchmarking = 0; @@ -542,8 +537,10 @@ long radeon_drm_ioctl(struct file *filp, long ret; dev = file_priv->minor->dev; ret = pm_runtime_get_sync(dev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(dev->dev); return ret; + } ret = drm_ioctl(filp, cmd, arg); diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 250e8495970e..44901fba0dbf 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -633,8 +633,10 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) file_priv->driver_priv = NULL; r = pm_runtime_get_sync(dev->dev); - if (r < 0) + if (r < 0) { + pm_runtime_put_autosuspend(dev->dev); return r; + } /* new gpu have virtual address space support */ if (rdev->family >= CHIP_CAYMAN) { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 7774824bf04c..9ecd0a604c19 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -1501,6 +1501,8 @@ const struct of_device_id sun4i_tcon_of_table[] = { { .compatible = "allwinner,sun6i-a31-tcon", .data = &sun6i_a31_quirks }, { .compatible = "allwinner,sun6i-a31s-tcon", .data = &sun6i_a31s_quirks }, { .compatible = "allwinner,sun7i-a20-tcon", .data = &sun7i_a20_quirks }, + { .compatible = "allwinner,sun7i-a20-tcon0", .data = &sun7i_a20_quirks }, + { .compatible = "allwinner,sun7i-a20-tcon1", .data = &sun7i_a20_quirks }, { .compatible = "allwinner,sun8i-a23-tcon", .data = &sun8i_a33_quirks }, { .compatible = "allwinner,sun8i-a33-tcon", .data = &sun8i_a33_quirks }, { .compatible = "allwinner,sun8i-a83t-tcon-lcd", .data = &sun8i_a83t_lcd_quirks }, diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c index 22b100d2e174..199fc2ecbb19 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c @@ -140,12 +140,16 @@ static int panel_connector_get_modes(struct drm_connector *connector) int i; for (i = 0; i < timings->num_timings; i++) { - struct drm_display_mode *mode = drm_mode_create(dev); + struct drm_display_mode *mode; struct videomode vm; if (videomode_from_timings(timings, &vm, i)) break; + mode = drm_mode_create(dev); + if (!mode) + break; + drm_display_mode_from_videomode(&vm, mode); mode->type = DRM_MODE_TYPE_DRIVER; diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c index eea15c07c554..379b3bf31b1d 100644 --- a/drivers/gpu/drm/tinydrm/mipi-dbi.c +++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c @@ -820,7 +820,7 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *mipi, int dc, } } - tr.len = chunk; + tr.len = chunk * 2; len -= chunk; tinydrm_dbg_spi_message(spi, &m); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index e3a0691582ff..68cfa25674e5 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -241,7 +241,6 @@ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, ttm_tt_init_fields(ttm, bo, page_flags); if (ttm_tt_alloc_page_directory(ttm)) { - ttm_tt_destroy(ttm); pr_err("Failed allocating page table\n"); return -ENOMEM; } @@ -265,7 +264,6 @@ int ttm_dma_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo, INIT_LIST_HEAD(&ttm_dma->pages_list); if (ttm_dma_tt_alloc_page_directory(ttm_dma)) { - ttm_tt_destroy(ttm); pr_err("Failed allocating page table\n"); return -ENOMEM; } @@ -287,7 +285,6 @@ int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo, else ret = ttm_dma_tt_alloc_page_directory(ttm_dma); if (ret) { - ttm_tt_destroy(ttm); pr_err("Failed allocating page table\n"); return -ENOMEM; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index b97bc8e5944b..e9f7c67a5499 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2657,7 +2657,7 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv, ++i; } - if (i != unit) { + if (&con->head == &dev_priv->dev->mode_config.connector_list) { DRM_ERROR("Could not find initial display unit.\n"); ret = -EINVAL; goto out_unlock; @@ -2681,13 +2681,13 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv, break; } - if (mode->type & DRM_MODE_TYPE_PREFERRED) - *p_mode = mode; - else { + if (&mode->head == &con->modes) { WARN_ONCE(true, "Could not find initial preferred mode.\n"); *p_mode = list_first_entry(&con->modes, struct drm_display_mode, head); + } else { + *p_mode = mode; } out_unlock: diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index 25e6343bcf21..9fa16361ee2a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -79,7 +79,7 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv) struct vmw_legacy_display_unit *entry; struct drm_framebuffer *fb = NULL; struct drm_crtc *crtc = NULL; - int i = 0; + int i; /* If there is no display topology the host just assumes * that the guest will set the same layout as the host. @@ -90,12 +90,11 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv) crtc = &entry->base.crtc; w = max(w, crtc->x + crtc->mode.hdisplay); h = max(h, crtc->y + crtc->mode.vdisplay); - i++; } if (crtc == NULL) return 0; - fb = entry->base.crtc.primary->state->fb; + fb = crtc->primary->state->fb; return vmw_kms_write_svga(dev_priv, w, h, fb->pitches[0], fb->format->cpp[0] * 8, diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c index 070b30f72947..277696029f3e 100644 --- a/drivers/gpu/host1x/debug.c +++ b/drivers/gpu/host1x/debug.c @@ -16,6 +16,8 @@ #include "debug.h" #include "channel.h" +static DEFINE_MUTEX(debug_lock); + unsigned int host1x_debug_trace_cmdbuf; static pid_t host1x_debug_force_timeout_pid; @@ -52,12 +54,14 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo) struct output *o = data; mutex_lock(&ch->cdma.lock); + mutex_lock(&debug_lock); if (show_fifo) host1x_hw_show_channel_fifo(m, ch, o); host1x_hw_show_channel_cdma(m, ch, o); + mutex_unlock(&debug_lock); mutex_unlock(&ch->cdma.lock); return 0; diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c index e744f3527ce1..9d3b965b128e 100644 --- a/drivers/gpu/ipu-v3/ipu-image-convert.c +++ b/drivers/gpu/ipu-v3/ipu-image-convert.c @@ -137,6 +137,17 @@ struct ipu_image_convert_ctx; struct ipu_image_convert_chan; struct ipu_image_convert_priv; +enum eof_irq_mask { + EOF_IRQ_IN = BIT(0), + EOF_IRQ_ROT_IN = BIT(1), + EOF_IRQ_OUT = BIT(2), + EOF_IRQ_ROT_OUT = BIT(3), +}; + +#define EOF_IRQ_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT) +#define EOF_IRQ_ROT_COMPLETE (EOF_IRQ_IN | EOF_IRQ_OUT | \ + EOF_IRQ_ROT_IN | EOF_IRQ_ROT_OUT) + struct ipu_image_convert_ctx { struct ipu_image_convert_chan *chan; @@ -172,6 +183,9 @@ struct ipu_image_convert_ctx { /* where to place converted tile in dest image */ unsigned int out_tile_map[MAX_TILES]; + /* mask of completed EOF irqs at every tile conversion */ + enum eof_irq_mask eof_mask; + struct list_head list; }; @@ -188,6 +202,8 @@ struct ipu_image_convert_chan { struct ipuv3_channel *rotation_out_chan; /* the IPU end-of-frame irqs */ + int in_eof_irq; + int rot_in_eof_irq; int out_eof_irq; int rot_out_eof_irq; @@ -1361,6 +1377,9 @@ static int convert_start(struct ipu_image_convert_run *run, unsigned int tile) init_idmac_channel(ctx, chan->in_chan, s_image, IPU_ROTATE_NONE, false, tile); + /* clear EOF irq mask */ + ctx->eof_mask = 0; + if (ipu_rot_mode_is_irt(ctx->rot_mode)) { /* init the IC PP-->MEM IDMAC channel */ init_idmac_channel(ctx, chan->out_chan, d_image, @@ -1559,7 +1578,7 @@ static bool ic_settings_changed(struct ipu_image_convert_ctx *ctx) } /* hold irqlock when calling */ -static irqreturn_t do_irq(struct ipu_image_convert_run *run) +static irqreturn_t do_tile_complete(struct ipu_image_convert_run *run) { struct ipu_image_convert_ctx *ctx = run->ctx; struct ipu_image_convert_chan *chan = ctx->chan; @@ -1644,6 +1663,7 @@ static irqreturn_t do_irq(struct ipu_image_convert_run *run) ctx->cur_buf_num ^= 1; } + ctx->eof_mask = 0; /* clear EOF irq mask for next tile */ ctx->next_tile++; return IRQ_HANDLED; done: @@ -1653,13 +1673,15 @@ done: return IRQ_WAKE_THREAD; } -static irqreturn_t norotate_irq(int irq, void *data) +static irqreturn_t eof_irq(int irq, void *data) { struct ipu_image_convert_chan *chan = data; + struct ipu_image_convert_priv *priv = chan->priv; struct ipu_image_convert_ctx *ctx; struct ipu_image_convert_run *run; + irqreturn_t ret = IRQ_HANDLED; + bool tile_complete = false; unsigned long flags; - irqreturn_t ret; spin_lock_irqsave(&chan->irqlock, flags); @@ -1672,46 +1694,33 @@ static irqreturn_t norotate_irq(int irq, void *data) ctx = run->ctx; - if (ipu_rot_mode_is_irt(ctx->rot_mode)) { - /* this is a rotation operation, just ignore */ - spin_unlock_irqrestore(&chan->irqlock, flags); - return IRQ_HANDLED; - } - - ret = do_irq(run); -out: - spin_unlock_irqrestore(&chan->irqlock, flags); - return ret; -} - -static irqreturn_t rotate_irq(int irq, void *data) -{ - struct ipu_image_convert_chan *chan = data; - struct ipu_image_convert_priv *priv = chan->priv; - struct ipu_image_convert_ctx *ctx; - struct ipu_image_convert_run *run; - unsigned long flags; - irqreturn_t ret; - - spin_lock_irqsave(&chan->irqlock, flags); - - /* get current run and its context */ - run = chan->current_run; - if (!run) { + if (irq == chan->in_eof_irq) { + ctx->eof_mask |= EOF_IRQ_IN; + } else if (irq == chan->out_eof_irq) { + ctx->eof_mask |= EOF_IRQ_OUT; + } else if (irq == chan->rot_in_eof_irq || + irq == chan->rot_out_eof_irq) { + if (!ipu_rot_mode_is_irt(ctx->rot_mode)) { + /* this was NOT a rotation op, shouldn't happen */ + dev_err(priv->ipu->dev, + "Unexpected rotation interrupt\n"); + goto out; + } + ctx->eof_mask |= (irq == chan->rot_in_eof_irq) ? + EOF_IRQ_ROT_IN : EOF_IRQ_ROT_OUT; + } else { + dev_err(priv->ipu->dev, "Received unknown irq %d\n", irq); ret = IRQ_NONE; goto out; } - ctx = run->ctx; - - if (!ipu_rot_mode_is_irt(ctx->rot_mode)) { - /* this was NOT a rotation operation, shouldn't happen */ - dev_err(priv->ipu->dev, "Unexpected rotation interrupt\n"); - spin_unlock_irqrestore(&chan->irqlock, flags); - return IRQ_HANDLED; - } + if (ipu_rot_mode_is_irt(ctx->rot_mode)) + tile_complete = (ctx->eof_mask == EOF_IRQ_ROT_COMPLETE); + else + tile_complete = (ctx->eof_mask == EOF_IRQ_COMPLETE); - ret = do_irq(run); + if (tile_complete) + ret = do_tile_complete(run); out: spin_unlock_irqrestore(&chan->irqlock, flags); return ret; @@ -1745,6 +1754,10 @@ static void force_abort(struct ipu_image_convert_ctx *ctx) static void release_ipu_resources(struct ipu_image_convert_chan *chan) { + if (chan->in_eof_irq >= 0) + free_irq(chan->in_eof_irq, chan); + if (chan->rot_in_eof_irq >= 0) + free_irq(chan->rot_in_eof_irq, chan); if (chan->out_eof_irq >= 0) free_irq(chan->out_eof_irq, chan); if (chan->rot_out_eof_irq >= 0) @@ -1763,7 +1776,27 @@ static void release_ipu_resources(struct ipu_image_convert_chan *chan) chan->in_chan = chan->out_chan = chan->rotation_in_chan = chan->rotation_out_chan = NULL; - chan->out_eof_irq = chan->rot_out_eof_irq = -1; + chan->in_eof_irq = -1; + chan->rot_in_eof_irq = -1; + chan->out_eof_irq = -1; + chan->rot_out_eof_irq = -1; +} + +static int get_eof_irq(struct ipu_image_convert_chan *chan, + struct ipuv3_channel *channel) +{ + struct ipu_image_convert_priv *priv = chan->priv; + int ret, irq; + + irq = ipu_idmac_channel_irq(priv->ipu, channel, IPU_IRQ_EOF); + + ret = request_threaded_irq(irq, eof_irq, do_bh, 0, "ipu-ic", chan); + if (ret < 0) { + dev_err(priv->ipu->dev, "could not acquire irq %d\n", irq); + return ret; + } + + return irq; } static int get_ipu_resources(struct ipu_image_convert_chan *chan) @@ -1799,31 +1832,33 @@ static int get_ipu_resources(struct ipu_image_convert_chan *chan) } /* acquire the EOF interrupts */ - chan->out_eof_irq = ipu_idmac_channel_irq(priv->ipu, - chan->out_chan, - IPU_IRQ_EOF); + ret = get_eof_irq(chan, chan->in_chan); + if (ret < 0) { + chan->in_eof_irq = -1; + goto err; + } + chan->in_eof_irq = ret; - ret = request_threaded_irq(chan->out_eof_irq, norotate_irq, do_bh, - 0, "ipu-ic", chan); + ret = get_eof_irq(chan, chan->rotation_in_chan); if (ret < 0) { - dev_err(priv->ipu->dev, "could not acquire irq %d\n", - chan->out_eof_irq); - chan->out_eof_irq = -1; + chan->rot_in_eof_irq = -1; goto err; } + chan->rot_in_eof_irq = ret; - chan->rot_out_eof_irq = ipu_idmac_channel_irq(priv->ipu, - chan->rotation_out_chan, - IPU_IRQ_EOF); + ret = get_eof_irq(chan, chan->out_chan); + if (ret < 0) { + chan->out_eof_irq = -1; + goto err; + } + chan->out_eof_irq = ret; - ret = request_threaded_irq(chan->rot_out_eof_irq, rotate_irq, do_bh, - 0, "ipu-ic", chan); + ret = get_eof_irq(chan, chan->rotation_out_chan); if (ret < 0) { - dev_err(priv->ipu->dev, "could not acquire irq %d\n", - chan->rot_out_eof_irq); chan->rot_out_eof_irq = -1; goto err; } + chan->rot_out_eof_irq = ret; return 0; err: @@ -2389,6 +2424,8 @@ int ipu_image_convert_init(struct ipu_soc *ipu, struct device *dev) chan->ic_task = i; chan->priv = priv; chan->dma_ch = &image_convert_dma_chan[i]; + chan->in_eof_irq = -1; + chan->rot_in_eof_irq = -1; chan->out_eof_irq = -1; chan->rot_out_eof_irq = -1; diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index b2ad319a74b9..d33f5abc8f64 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -25,6 +25,7 @@ #define U1_MOUSE_REPORT_ID 0x01 /* Mouse data ReportID */ #define U1_ABSOLUTE_REPORT_ID 0x03 /* Absolute data ReportID */ +#define U1_ABSOLUTE_REPORT_ID_SECD 0x02 /* FW-PTP Absolute data ReportID */ #define U1_FEATURE_REPORT_ID 0x05 /* Feature ReportID */ #define U1_SP_ABSOLUTE_REPORT_ID 0x06 /* Feature ReportID */ @@ -368,6 +369,7 @@ static int u1_raw_event(struct alps_dev *hdata, u8 *data, int size) case U1_FEATURE_REPORT_ID: break; case U1_ABSOLUTE_REPORT_ID: + case U1_ABSOLUTE_REPORT_ID_SECD: for (i = 0; i < hdata->max_fingers; i++) { u8 *contact = &data[i * 5]; diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index d732d1d10caf..6909c045fece 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -54,6 +54,7 @@ MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option (\"Alt\") and Command (\"Flag\") struct apple_sc { unsigned long quirks; unsigned int fn_on; + unsigned int fn_found; DECLARE_BITMAP(pressed_numlock, KEY_CNT); }; @@ -339,12 +340,15 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { + struct apple_sc *asc = hid_get_drvdata(hdev); + if (usage->hid == (HID_UP_CUSTOM | 0x0003) || usage->hid == (HID_UP_MSVENDOR | 0x0003) || usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); + asc->fn_found = true; apple_setup_input(hi->input); return 1; } @@ -371,6 +375,19 @@ static int apple_input_mapped(struct hid_device *hdev, struct hid_input *hi, return 0; } +static int apple_input_configured(struct hid_device *hdev, + struct hid_input *hidinput) +{ + struct apple_sc *asc = hid_get_drvdata(hdev); + + if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) { + hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n"); + asc->quirks = 0; + } + + return 0; +} + static int apple_probe(struct hid_device *hdev, const struct hid_device_id *id) { @@ -585,6 +602,7 @@ static struct hid_driver apple_driver = { .event = apple_event, .input_mapping = apple_input_mapping, .input_mapped = apple_input_mapped, + .input_configured = apple_input_configured, }; module_hid_driver(apple_driver); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 4a74614c22c1..e253e3a7a169 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -619,6 +619,7 @@ #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081 0xa081 #define USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2 0xa0c2 #define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096 0xa096 +#define USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A293 0xa293 #define USB_VENDOR_ID_IMATION 0x0718 #define USB_DEVICE_ID_DISC_STAKKA 0xd000 @@ -992,6 +993,8 @@ #define USB_DEVICE_ID_ROCCAT_RYOS_MK_PRO 0x3232 #define USB_DEVICE_ID_ROCCAT_SAVU 0x2d5a +#define USB_VENDOR_ID_SAI 0x17dd + #define USB_VENDOR_ID_SAITEK 0x06a3 #define USB_DEVICE_ID_SAITEK_RUMBLEPAD 0xff17 #define USB_DEVICE_ID_SAITEK_PS1000 0x0621 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index dea9cc65bf80..e8641ce677e4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -350,13 +350,13 @@ static int hidinput_query_battery_capacity(struct hid_device *dev) u8 *buf; int ret; - buf = kmalloc(2, GFP_KERNEL); + buf = kmalloc(4, GFP_KERNEL); if (!buf) return -ENOMEM; - ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2, + ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 4, dev->battery_report_type, HID_REQ_GET_REPORT); - if (ret != 2) { + if (ret < 2) { kfree(buf); return -ENODATA; } diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index f97913974983..e994403f7650 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -2964,7 +2964,7 @@ static int hi_res_scroll_enable(struct hidpp_device *hidpp) multiplier = 1; hidpp->vertical_wheel_counter.wheel_multiplier = multiplier; - hid_info(hidpp->hid_dev, "multiplier = %d\n", multiplier); + hid_dbg(hidpp->hid_dev, "wheel multiplier = %d\n", multiplier); return 0; } diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 34138667f8af..abd86903875f 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -535,6 +535,12 @@ static int magicmouse_setup_input(struct input_dev *input, struct hid_device *hd __set_bit(MSC_RAW, input->mscbit); } + /* + * hid-input may mark device as using autorepeat, but neither + * the trackpad, nor the mouse actually want it. + */ + __clear_bit(EV_REP, input->evbit); + return 0; } diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 76a4539b1224..affcd54c08e0 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -87,6 +87,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A293), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, @@ -399,9 +400,6 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2) }, #endif -#if IS_ENABLED(CONFIG_HID_ITE) - { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, -#endif #if IS_ENABLED(CONFIG_HID_ICADE) { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ION, USB_DEVICE_ID_ICADE) }, #endif @@ -841,6 +839,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PETZL, USB_DEVICE_ID_PETZL_HEADLAMP) }, { HID_USB_DEVICE(USB_VENDOR_ID_PHILIPS, USB_DEVICE_ID_PHILIPS_IEEE802154_DONGLE) }, { HID_USB_DEVICE(USB_VENDOR_ID_POWERCOM, USB_DEVICE_ID_POWERCOM_UPS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAI, USB_DEVICE_ID_CYPRESS_HIDCOM) }, #if IS_ENABLED(CONFIG_MOUSE_SYNAPTICS_USB) { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP) }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_INT_TP) }, diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index 6286204d4c56..a3b151b29bd7 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -526,7 +526,8 @@ static int steam_register(struct steam_device *steam) steam_battery_register(steam); mutex_lock(&steam_devices_lock); - list_add(&steam->list, &steam_devices); + if (list_empty(&steam->list)) + list_add(&steam->list, &steam_devices); mutex_unlock(&steam_devices_lock); } @@ -552,7 +553,7 @@ static void steam_unregister(struct steam_device *steam) hid_info(steam->hdev, "Steam Controller '%s' disconnected", steam->serial_no); mutex_lock(&steam_devices_lock); - list_del(&steam->list); + list_del_init(&steam->list); mutex_unlock(&steam_devices_lock); steam->serial_no[0] = 0; } @@ -738,6 +739,7 @@ static int steam_probe(struct hid_device *hdev, mutex_init(&steam->mutex); steam->quirks = id->driver_data; INIT_WORK(&steam->work_connect, steam_work_connect_cb); + INIT_LIST_HEAD(&steam->list); steam->client_hdev = steam_create_client_hid(hdev); if (IS_ERR(steam->client_hdev)) { diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index ec142bc8c1da..35f3bfc3e6f5 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -374,6 +374,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + .ident = "Mediacom FlexBook edge 13", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook_edge13-M-FBE13"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Odys Winbook 13", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AXDIA International GmbH"), diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 93907dc3f02f..a8fca0279013 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -1227,6 +1227,8 @@ channel_message_table[CHANNELMSG_COUNT] = { { CHANNELMSG_19, 0, NULL }, { CHANNELMSG_20, 0, NULL }, { CHANNELMSG_TL_CONNECT_REQUEST, 0, NULL }, + { CHANNELMSG_22, 0, NULL }, + { CHANNELMSG_TL_CONNECT_RESULT, 0, NULL }, }; /* @@ -1238,25 +1240,16 @@ void vmbus_onmessage(void *context) { struct hv_message *msg = context; struct vmbus_channel_message_header *hdr; - int size; hdr = (struct vmbus_channel_message_header *)msg->u.payload; - size = msg->header.payload_size; trace_vmbus_on_message(hdr); - if (hdr->msgtype >= CHANNELMSG_COUNT) { - pr_err("Received invalid channel message type %d size %d\n", - hdr->msgtype, size); - print_hex_dump_bytes("", DUMP_PREFIX_NONE, - (unsigned char *)msg->u.payload, size); - return; - } - - if (channel_message_table[hdr->msgtype].message_handler) - channel_message_table[hdr->msgtype].message_handler(hdr); - else - pr_err("Unhandled channel message type %d\n", hdr->msgtype); + /* + * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go + * out of bound and the message_handler pointer can not be NULL. + */ + channel_message_table[hdr->msgtype].message_handler(hdr); } /* diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 18c5197bc191..8342028bc005 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1019,6 +1019,10 @@ void vmbus_on_msg_dpc(unsigned long data) } entry = &channel_message_table[hdr->msgtype]; + + if (!entry->message_handler) + goto msg_handled; + if (entry->handler_type == VMHT_BLOCKING) { ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx == NULL) diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index 40c489be62ea..40f3139f1e02 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -851,6 +851,8 @@ static int aspeed_create_fan(struct device *dev, ret = of_property_read_u32(child, "reg", &pwm_port); if (ret) return ret; + if (pwm_port >= ARRAY_SIZE(pwm_port_params)) + return -EINVAL; aspeed_create_pwm_port(priv, (u8)pwm_port); ret = of_property_count_u8_elems(child, "cooling-levels"); diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c index 491a570e8e50..924c02c1631d 100644 --- a/drivers/hwmon/emc2103.c +++ b/drivers/hwmon/emc2103.c @@ -443,7 +443,7 @@ static ssize_t pwm1_enable_store(struct device *dev, } result = read_u8_from_i2c(client, REG_FAN_CONF1, &conf_reg); - if (result) { + if (result < 0) { count = result; goto err; } diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index d42bc0883a32..c6b7d6f72520 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -782,13 +782,13 @@ static const char *const nct6798_temp_label[] = { "Agent1 Dimm1", "BYTE_TEMP0", "BYTE_TEMP1", - "", - "", + "PECI Agent 0 Calibration", /* undocumented */ + "PECI Agent 1 Calibration", /* undocumented */ "", "Virtual_TEMP" }; -#define NCT6798_TEMP_MASK 0x8fff0ffe +#define NCT6798_TEMP_MASK 0xbfff0ffe #define NCT6798_VIRT_TEMP_MASK 0x80000c00 /* NCT6102D/NCT6106D specific data */ diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c index 82052b6611c9..8104d8ad6086 100644 --- a/drivers/hwmon/pmbus/adm1275.c +++ b/drivers/hwmon/pmbus/adm1275.c @@ -355,6 +355,7 @@ MODULE_DEVICE_TABLE(i2c, adm1275_id); static int adm1275_probe(struct i2c_client *client, const struct i2c_device_id *id) { + s32 (*config_read_fn)(const struct i2c_client *client, u8 reg); u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1]; int config, device_config; int ret; @@ -400,11 +401,16 @@ static int adm1275_probe(struct i2c_client *client, "Device mismatch: Configured %s, detected %s\n", id->name, mid->name); - config = i2c_smbus_read_byte_data(client, ADM1275_PMON_CONFIG); + if (mid->driver_data == adm1272 || mid->driver_data == adm1278 || + mid->driver_data == adm1293 || mid->driver_data == adm1294) + config_read_fn = i2c_smbus_read_word_data; + else + config_read_fn = i2c_smbus_read_byte_data; + config = config_read_fn(client, ADM1275_PMON_CONFIG); if (config < 0) return config; - device_config = i2c_smbus_read_byte_data(client, ADM1275_DEVICE_CONFIG); + device_config = config_read_fn(client, ADM1275_DEVICE_CONFIG); if (device_config < 0) return device_config; diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c index a80183a488c5..8c70f6250241 100644 --- a/drivers/hwmon/scmi-hwmon.c +++ b/drivers/hwmon/scmi-hwmon.c @@ -99,7 +99,7 @@ static enum hwmon_sensor_types scmi_types[] = { [ENERGY] = hwmon_energy, }; -static u32 hwmon_attributes[] = { +static u32 hwmon_attributes[hwmon_max] = { [hwmon_chip] = HWMON_C_REGISTER_TZ, [hwmon_temp] = HWMON_T_INPUT | HWMON_T_LABEL, [hwmon_in] = HWMON_I_INPUT | HWMON_I_LABEL, diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 64b12fe2660f..e43e9ef0617c 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -635,15 +635,14 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata) spin_lock_irqsave(&drvdata->spinlock, flags); - /* There is no point in reading a TMC in HW FIFO mode */ - mode = readl_relaxed(drvdata->base + TMC_MODE); - if (mode != TMC_MODE_CIRCULAR_BUFFER) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); - return -EINVAL; - } - /* Re-enable the TMC if need be */ if (drvdata->mode == CS_MODE_SYSFS) { + /* There is no point in reading a TMC in HW FIFO mode */ + mode = readl_relaxed(drvdata->base + TMC_MODE); + if (mode != TMC_MODE_CIRCULAR_BUFFER) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EINVAL; + } /* * The trace run will continue with the same allocated trace * buffer. As such zero-out the buffer so that we don't end diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 52f000d37bac..9ea1d8f54465 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -1030,15 +1030,30 @@ int intel_th_set_output(struct intel_th_device *thdev, { struct intel_th_device *hub = to_intel_th_hub(thdev); struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver); + int ret; /* In host mode, this is up to the external debugger, do nothing. */ if (hub->host_mode) return 0; - if (!hubdrv->set_output) - return -ENOTSUPP; + /* + * hub is instantiated together with the source device that + * calls here, so guaranteed to be present. + */ + hubdrv = to_intel_th_driver(hub->dev.driver); + if (!hubdrv || !try_module_get(hubdrv->driver.owner)) + return -EINVAL; + + if (!hubdrv->set_output) { + ret = -ENOTSUPP; + goto out; + } + + ret = hubdrv->set_output(hub, master); - return hubdrv->set_output(hub, master); +out: + module_put(hubdrv->driver.owner); + return ret; } EXPORT_SYMBOL_GPL(intel_th_set_output); diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 86aa6a46bcba..0d26484d6795 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -230,11 +230,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Tiger Lake PCH-H */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x43a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Jasper Lake PCH */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, { + /* Jasper Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4e29), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { /* Elkhart Lake CPU */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4529), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -244,6 +254,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Emmitsburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1bcc), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c index 3a1f4e650378..a1529f571491 100644 --- a/drivers/hwtracing/intel_th/sth.c +++ b/drivers/hwtracing/intel_th/sth.c @@ -161,9 +161,7 @@ static int sth_stm_link(struct stm_data *stm_data, unsigned int master, { struct sth_device *sth = container_of(stm_data, struct sth_device, stm); - intel_th_set_output(to_intel_th_device(sth->dev), master); - - return 0; + return intel_th_set_output(to_intel_th_device(sth->dev), master); } static int intel_th_sw_init(struct sth_device *sth) diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 9d71ce15db05..a51d3b795770 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -377,10 +377,8 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if ((id->recv_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) + if (id->recv_count > CDNS_I2C_FIFO_DEPTH) ctrl_reg |= CDNS_I2C_CR_HOLD; - else - ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); @@ -437,11 +435,8 @@ static void cdns_i2c_msend(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) + if (id->send_count > CDNS_I2C_FIFO_DEPTH) ctrl_reg |= CDNS_I2C_CR_HOLD; - else - ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; - cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); /* Clear the interrupts in interrupt status register. */ diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index bb810dee8fb5..73f139690e4e 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -180,6 +180,7 @@ static const struct pci_device_id pch_pcidev_id[] = { { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7831_I2C), 1, }, {0,} }; +MODULE_DEVICE_TABLE(pci, pch_pcidev_id); static irqreturn_t pch_i2c_handler(int irq, void *pData); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 715ddc5d0eac..509fd583de89 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -367,7 +367,6 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, geni_se_select_mode(se, GENI_SE_FIFO); writel_relaxed(len, se->base + SE_I2C_RX_TRANS_LEN); - geni_se_setup_m_cmd(se, I2C_READ, m_param); if (dma_buf && geni_se_rx_dma_prep(se, dma_buf, len, &rx_dma)) { geni_se_select_mode(se, GENI_SE_FIFO); @@ -375,6 +374,8 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, dma_buf = NULL; } + geni_se_setup_m_cmd(se, I2C_READ, m_param); + time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); if (!time_left) geni_i2c_abort_xfer(gi2c); @@ -408,7 +409,6 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, geni_se_select_mode(se, GENI_SE_FIFO); writel_relaxed(len, se->base + SE_I2C_TX_TRANS_LEN); - geni_se_setup_m_cmd(se, I2C_WRITE, m_param); if (dma_buf && geni_se_tx_dma_prep(se, dma_buf, len, &tx_dma)) { geni_se_select_mode(se, GENI_SE_FIFO); @@ -416,6 +416,8 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, dma_buf = NULL; } + geni_se_setup_m_cmd(se, I2C_WRITE, m_param); + if (!dma_buf) /* Get FIFO IRQ */ writel_relaxed(1, se->base + SE_GENI_TX_WATERMARK_REG); diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 531c01100b56..0b90aa0318df 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -580,13 +580,14 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) rcar_i2c_write(priv, ICSIER, SDR | SSR | SAR); } - rcar_i2c_write(priv, ICSSR, ~SAR & 0xff); + /* Clear SSR, too, because of old STOPs to other clients than us */ + rcar_i2c_write(priv, ICSSR, ~(SAR | SSR) & 0xff); } /* master sent stop */ if (ssr_filtered & SSR) { i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value); - rcar_i2c_write(priv, ICSIER, SAR | SSR); + rcar_i2c_write(priv, ICSIER, SAR); rcar_i2c_write(priv, ICSSR, ~SSR & 0xff); } @@ -850,7 +851,7 @@ static int rcar_reg_slave(struct i2c_client *slave) priv->slave = slave; rcar_i2c_write(priv, ICSAR, slave->addr); rcar_i2c_write(priv, ICSSR, 0); - rcar_i2c_write(priv, ICSIER, SAR | SSR); + rcar_i2c_write(priv, ICSIER, SAR); rcar_i2c_write(priv, ICSCR, SIE | SDBS); return 0; @@ -862,11 +863,14 @@ static int rcar_unreg_slave(struct i2c_client *slave) WARN_ON(!priv->slave); - /* disable irqs and ensure none is running before clearing ptr */ + /* ensure no irq is running before clearing ptr */ + disable_irq(priv->irq); rcar_i2c_write(priv, ICSIER, 0); - rcar_i2c_write(priv, ICSCR, 0); + rcar_i2c_write(priv, ICSSR, 0); + enable_irq(priv->irq); + rcar_i2c_write(priv, ICSCR, SDBS); + rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ - synchronize_irq(priv->irq); priv->slave = NULL; pm_runtime_put(rcar_i2c_priv_to_dev(priv)); @@ -971,6 +975,8 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ + if (priv->devtype == I2C_RCAR_GEN3) { priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); if (!IS_ERR(priv->rstc)) { diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c index 5427f047faf0..1589179d5eb9 100644 --- a/drivers/i2c/i2c-core-slave.c +++ b/drivers/i2c/i2c-core-slave.c @@ -18,10 +18,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb) { int ret; - if (!client || !slave_cb) { - WARN(1, "insufficient data\n"); + if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n")) return -EINVAL; - } if (!(client->flags & I2C_CLIENT_SLAVE)) dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n", @@ -60,6 +58,9 @@ int i2c_slave_unregister(struct i2c_client *client) { int ret; + if (IS_ERR_OR_NULL(client)) + return -EINVAL; + if (!client->adapter->algo->unreg_slave) { dev_err(&client->dev, "%s: not supported by adapter\n", __func__); return -EOPNOTSUPP; diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index 00e100fc845a..813bca7cfc3e 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -1685,10 +1685,13 @@ static int mma8452_probe(struct i2c_client *client, ret = mma8452_set_freefall_mode(data, false); if (ret < 0) - goto buffer_cleanup; + goto unregister_device; return 0; +unregister_device: + iio_device_unregister(indio_dev); + buffer_cleanup: iio_triggered_buffer_cleanup(indio_dev); diff --git a/drivers/iio/adc/ad7780.c b/drivers/iio/adc/ad7780.c index 217a5a5c3c6d..7e741294de7b 100644 --- a/drivers/iio/adc/ad7780.c +++ b/drivers/iio/adc/ad7780.c @@ -309,7 +309,7 @@ static int ad7780_probe(struct spi_device *spi) ret = ad7780_init_gpios(&spi->dev, st); if (ret) - goto error_cleanup_buffer_and_trigger; + return ret; st->reg = devm_regulator_get(&spi->dev, "avdd"); if (IS_ERR(st->reg)) diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 2d897e64c6a9..424922cad1e3 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -416,7 +416,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev, s64 tmp = *val * (3767897513LL / 25LL); *val = div_s64_rem(tmp, 1000000000LL, val2); - ret = IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_MICRO; } else { int mult; @@ -447,7 +447,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev, ret = IIO_VAL_INT; break; default: - ret = -EINVAL; + return -EINVAL; } unlock: diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index dc22dc363a99..a3507624b30f 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -23,6 +23,8 @@ #include <linux/iio/triggered_buffer.h> #include <linux/iio/trigger_consumer.h> +#include <asm/unaligned.h> + #include "afe440x.h" #define AFE4403_DRIVER_NAME "afe4403" @@ -63,6 +65,7 @@ static const struct reg_field afe4403_reg_fields[] = { * @regulator: Pointer to the regulator for the IC * @trig: IIO trigger for this device * @irq: ADC_RDY line interrupt number + * @buffer: Used to construct data layout to push into IIO buffer. */ struct afe4403_data { struct device *dev; @@ -72,6 +75,8 @@ struct afe4403_data { struct regulator *regulator; struct iio_trigger *trig; int irq; + /* Ensure suitable alignment for timestamp */ + s32 buffer[8] __aligned(8); }; enum afe4403_chan_id { @@ -220,13 +225,11 @@ static int afe4403_read(struct afe4403_data *afe, unsigned int reg, u32 *val) if (ret) return ret; - ret = spi_write_then_read(afe->spi, ®, 1, rx, 3); + ret = spi_write_then_read(afe->spi, ®, 1, rx, sizeof(rx)); if (ret) return ret; - *val = (rx[0] << 16) | - (rx[1] << 8) | - (rx[2]); + *val = get_unaligned_be24(&rx[0]); /* Disable reading from the device */ tx[3] = AFE440X_CONTROL0_WRITE; @@ -309,7 +312,6 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private) struct iio_dev *indio_dev = pf->indio_dev; struct afe4403_data *afe = iio_priv(indio_dev); int ret, bit, i = 0; - s32 buffer[8]; u8 tx[4] = {AFE440X_CONTROL0, 0x0, 0x0, AFE440X_CONTROL0_READ}; u8 rx[3]; @@ -322,13 +324,11 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private) indio_dev->masklength) { ret = spi_write_then_read(afe->spi, &afe4403_channel_values[bit], 1, - rx, 3); + rx, sizeof(rx)); if (ret) goto err; - buffer[i++] = (rx[0] << 16) | - (rx[1] << 8) | - (rx[2]); + afe->buffer[i++] = get_unaligned_be24(&rx[0]); } /* Disable reading from the device */ @@ -337,7 +337,8 @@ static irqreturn_t afe4403_trigger_handler(int irq, void *private) if (ret) goto err; - iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp); + iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer, + pf->timestamp); err: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c index e728bbb21ca8..cebb1fd4d0b1 100644 --- a/drivers/iio/health/afe4404.c +++ b/drivers/iio/health/afe4404.c @@ -83,6 +83,7 @@ static const struct reg_field afe4404_reg_fields[] = { * @regulator: Pointer to the regulator for the IC * @trig: IIO trigger for this device * @irq: ADC_RDY line interrupt number + * @buffer: Used to construct a scan to push to the iio buffer. */ struct afe4404_data { struct device *dev; @@ -91,6 +92,7 @@ struct afe4404_data { struct regulator *regulator; struct iio_trigger *trig; int irq; + s32 buffer[10] __aligned(8); }; enum afe4404_chan_id { @@ -328,17 +330,17 @@ static irqreturn_t afe4404_trigger_handler(int irq, void *private) struct iio_dev *indio_dev = pf->indio_dev; struct afe4404_data *afe = iio_priv(indio_dev); int ret, bit, i = 0; - s32 buffer[10]; for_each_set_bit(bit, indio_dev->active_scan_mask, indio_dev->masklength) { ret = regmap_read(afe->regmap, afe4404_channel_values[bit], - &buffer[i++]); + &afe->buffer[i++]); if (ret) goto err; } - iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp); + iio_push_to_buffers_with_timestamp(indio_dev, afe->buffer, + pf->timestamp); err: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index ff6666ac5d68..0fcaa2c0b2f4 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -38,6 +38,11 @@ struct hdc100x_data { /* integration time of the sensor */ int adc_int_us[2]; + /* Ensure natural alignment of timestamp */ + struct { + __be16 channels[2]; + s64 ts __aligned(8); + } scan; }; /* integration time in us */ @@ -319,7 +324,6 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p) struct i2c_client *client = data->client; int delay = data->adc_int_us[0] + data->adc_int_us[1]; int ret; - s16 buf[8]; /* 2x s16 + padding + 8 byte timestamp */ /* dual read starts at temp register */ mutex_lock(&data->lock); @@ -330,13 +334,13 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p) } usleep_range(delay, delay + 1000); - ret = i2c_master_recv(client, (u8 *)buf, 4); + ret = i2c_master_recv(client, (u8 *)data->scan.channels, 4); if (ret < 0) { dev_err(&client->dev, "cannot read sensor data\n"); goto err; } - iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_push_to_buffers_with_timestamp(indio_dev, &data->scan, iio_get_time_ns(indio_dev)); err: mutex_unlock(&data->lock); diff --git a/drivers/iio/humidity/hts221.h b/drivers/iio/humidity/hts221.h index 7d6771f7cf47..b2eb5abeaccd 100644 --- a/drivers/iio/humidity/hts221.h +++ b/drivers/iio/humidity/hts221.h @@ -14,8 +14,6 @@ #include <linux/iio/iio.h> -#define HTS221_DATA_SIZE 2 - enum hts221_sensor_type { HTS221_SENSOR_H, HTS221_SENSOR_T, @@ -39,6 +37,11 @@ struct hts221_hw { bool enabled; u8 odr; + /* Ensure natural alignment of timestamp */ + struct { + __le16 channels[2]; + s64 ts __aligned(8); + } scan; }; extern const struct dev_pm_ops hts221_pm_ops; diff --git a/drivers/iio/humidity/hts221_buffer.c b/drivers/iio/humidity/hts221_buffer.c index 81d50a861c22..49dcd36d8838 100644 --- a/drivers/iio/humidity/hts221_buffer.c +++ b/drivers/iio/humidity/hts221_buffer.c @@ -162,7 +162,6 @@ static const struct iio_buffer_setup_ops hts221_buffer_ops = { static irqreturn_t hts221_buffer_handler_thread(int irq, void *p) { - u8 buffer[ALIGN(2 * HTS221_DATA_SIZE, sizeof(s64)) + sizeof(s64)]; struct iio_poll_func *pf = p; struct iio_dev *iio_dev = pf->indio_dev; struct hts221_hw *hw = iio_priv(iio_dev); @@ -172,18 +171,20 @@ static irqreturn_t hts221_buffer_handler_thread(int irq, void *p) /* humidity data */ ch = &iio_dev->channels[HTS221_SENSOR_H]; err = regmap_bulk_read(hw->regmap, ch->address, - buffer, HTS221_DATA_SIZE); + &hw->scan.channels[0], + sizeof(hw->scan.channels[0])); if (err < 0) goto out; /* temperature data */ ch = &iio_dev->channels[HTS221_SENSOR_T]; err = regmap_bulk_read(hw->regmap, ch->address, - buffer + HTS221_DATA_SIZE, HTS221_DATA_SIZE); + &hw->scan.channels[1], + sizeof(hw->scan.channels[1])); if (err < 0) goto out; - iio_push_to_buffers_with_timestamp(iio_dev, buffer, + iio_push_to_buffers_with_timestamp(iio_dev, &hw->scan, iio_get_time_ns(iio_dev)); out: diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 245b5844028d..393bafc91331 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -130,6 +130,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_PM2P5] = "pm2p5", [IIO_MOD_PM4] = "pm4", [IIO_MOD_PM10] = "pm10", + [IIO_MOD_ETHANOL] = "ethanol", + [IIO_MOD_H2] = "h2", }; /* relies on pairs of these shared then separate */ diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c index d32996702110..87c15a63c1a4 100644 --- a/drivers/iio/magnetometer/ak8974.c +++ b/drivers/iio/magnetometer/ak8974.c @@ -185,6 +185,11 @@ struct ak8974 { bool drdy_irq; struct completion drdy_complete; bool drdy_active_low; + /* Ensure timestamp is naturally aligned */ + struct { + __le16 channels[3]; + s64 ts __aligned(8); + } scan; }; static const char ak8974_reg_avdd[] = "avdd"; @@ -581,7 +586,6 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev) { struct ak8974 *ak8974 = iio_priv(indio_dev); int ret; - __le16 hw_values[8]; /* Three axes + 64bit padding */ pm_runtime_get_sync(&ak8974->i2c->dev); mutex_lock(&ak8974->lock); @@ -591,13 +595,13 @@ static void ak8974_fill_buffer(struct iio_dev *indio_dev) dev_err(&ak8974->i2c->dev, "error triggering measure\n"); goto out_unlock; } - ret = ak8974_getresult(ak8974, hw_values); + ret = ak8974_getresult(ak8974, ak8974->scan.channels); if (ret) { dev_err(&ak8974->i2c->dev, "error getting measures\n"); goto out_unlock; } - iio_push_to_buffers_with_timestamp(indio_dev, hw_values, + iio_push_to_buffers_with_timestamp(indio_dev, &ak8974->scan, iio_get_time_ns(indio_dev)); out_unlock: @@ -764,19 +768,21 @@ static int ak8974_probe(struct i2c_client *i2c, ak8974->map = devm_regmap_init_i2c(i2c, &ak8974_regmap_config); if (IS_ERR(ak8974->map)) { dev_err(&i2c->dev, "failed to allocate register map\n"); + pm_runtime_put_noidle(&i2c->dev); + pm_runtime_disable(&i2c->dev); return PTR_ERR(ak8974->map); } ret = ak8974_set_power(ak8974, AK8974_PWR_ON); if (ret) { dev_err(&i2c->dev, "could not power on\n"); - goto power_off; + goto disable_pm; } ret = ak8974_detect(ak8974); if (ret) { dev_err(&i2c->dev, "neither AK8974 nor AMI30x found\n"); - goto power_off; + goto disable_pm; } ret = ak8974_selftest(ak8974); @@ -786,14 +792,9 @@ static int ak8974_probe(struct i2c_client *i2c, ret = ak8974_reset(ak8974); if (ret) { dev_err(&i2c->dev, "AK8974 reset failed\n"); - goto power_off; + goto disable_pm; } - pm_runtime_set_autosuspend_delay(&i2c->dev, - AK8974_AUTOSUSPEND_DELAY); - pm_runtime_use_autosuspend(&i2c->dev); - pm_runtime_put(&i2c->dev); - indio_dev->dev.parent = &i2c->dev; indio_dev->channels = ak8974_channels; indio_dev->num_channels = ARRAY_SIZE(ak8974_channels); @@ -846,6 +847,11 @@ no_irq: goto cleanup_buffer; } + pm_runtime_set_autosuspend_delay(&i2c->dev, + AK8974_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(&i2c->dev); + pm_runtime_put(&i2c->dev); + return 0; cleanup_buffer: @@ -854,7 +860,6 @@ disable_pm: pm_runtime_put_noidle(&i2c->dev); pm_runtime_disable(&i2c->dev); ak8974_set_power(ak8974, AK8974_PWR_OFF); -power_off: regulator_bulk_disable(ARRAY_SIZE(ak8974->regs), ak8974->regs); return ret; diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c index 2f598ad91621..f5db9fa086f3 100644 --- a/drivers/iio/pressure/ms5611_core.c +++ b/drivers/iio/pressure/ms5611_core.c @@ -212,16 +212,21 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct ms5611_state *st = iio_priv(indio_dev); - s32 buf[4]; /* s32 (pressure) + s32 (temp) + 2 * s32 (timestamp) */ + /* Ensure buffer elements are naturally aligned */ + struct { + s32 channels[2]; + s64 ts __aligned(8); + } scan; int ret; mutex_lock(&st->lock); - ret = ms5611_read_temp_and_pressure(indio_dev, &buf[1], &buf[0]); + ret = ms5611_read_temp_and_pressure(indio_dev, &scan.channels[1], + &scan.channels[0]); mutex_unlock(&st->lock); if (ret < 0) goto err; - iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_push_to_buffers_with_timestamp(indio_dev, &scan, iio_get_time_ns(indio_dev)); err: diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index 9d0d07930236..7f2e5a8942a4 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -664,8 +664,10 @@ static int zpa2326_resume(const struct iio_dev *indio_dev) int err; err = pm_runtime_get_sync(indio_dev->dev.parent); - if (err < 0) + if (err < 0) { + pm_runtime_put(indio_dev->dev.parent); return err; + } if (err > 0) { /* diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 7823c6738ab6..80a1e20a95ae 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1315,6 +1315,10 @@ out: return ret; } +static void prevent_dealloc_device(struct ib_device *ib_dev) +{ +} + /** * ib_register_device - Register an IB device with IB core * @device:Device to register @@ -1380,11 +1384,11 @@ int ib_register_device(struct ib_device *device, const char *name) * possibility for a parallel unregistration along with this * error flow. Since we have a refcount here we know any * parallel flow is stopped in disable_device and will see the - * NULL pointers, causing the responsibility to + * special dealloc_driver pointer, causing the responsibility to * ib_dealloc_device() to revert back to this thread. */ dealloc_fn = device->ops.dealloc_driver; - device->ops.dealloc_driver = NULL; + device->ops.dealloc_driver = prevent_dealloc_device; ib_device_put(device); __ib_unregister_device(device); device->ops.dealloc_driver = dealloc_fn; @@ -1432,7 +1436,8 @@ static void __ib_unregister_device(struct ib_device *ib_dev) * Drivers using the new flow may not call ib_dealloc_device except * in error unwind prior to registration success. */ - if (ib_dev->ops.dealloc_driver) { + if (ib_dev->ops.dealloc_driver && + ib_dev->ops.dealloc_driver != prevent_dealloc_device) { WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1); ib_dealloc_device(ib_dev); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index e01bb641e5ae..6273d2430736 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -760,6 +760,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs) mr->uobject = uobj; atomic_inc(&pd->usecnt); mr->res.type = RDMA_RESTRACK_MR; + mr->iova = cmd.hca_va; rdma_restrack_uadd(&mr->res); uobj->object = mr; @@ -850,6 +851,9 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) atomic_dec(&old_pd->usecnt); } + if (cmd.flags & IB_MR_REREG_TRANS) + mr->iova = cmd.hca_va; + memset(&resp, 0, sizeof(resp)); resp.lkey = mr->lkey; resp.rkey = mr->rkey; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index bca9877033a7..41caf36575df 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1641,7 +1641,7 @@ static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr, if (!(rdma_protocol_ib(qp->device, attr->alt_ah_attr.port_num) && rdma_protocol_ib(qp->device, port))) { - ret = EINVAL; + ret = -EINVAL; goto out; } } diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 69b287d025f7..7af958b3318e 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -398,7 +398,6 @@ static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag) mmid = stag >> 8; mhp->ibmr.rkey = mhp->ibmr.lkey = stag; mhp->ibmr.length = mhp->attr.len; - mhp->ibmr.iova = mhp->attr.va_fbo; mhp->ibmr.page_size = 1U << (mhp->attr.page_size + 12); pr_debug("mmid 0x%x mhp %p\n", mmid, mhp); return xa_insert_irq(&mhp->rhp->mrs, mmid, mhp, GFP_KERNEL); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 7d64e70e54c6..4aa439a7ce61 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -780,7 +780,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->ip_gids = true; props->gid_tbl_len = mdev->dev->caps.gid_table_len[port]; props->max_msg_sz = mdev->dev->caps.max_msg_sz; - props->pkey_tbl_len = 1; + if (mdev->dev->caps.pkey_table_len[port]) + props->pkey_tbl_len = 1; props->max_mtu = IB_MTU_4096; props->max_vl_num = 2; props->state = IB_PORT_DOWN; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 355205a28544..6fd661076ade 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -440,7 +440,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key; mr->ibmr.length = length; - mr->ibmr.iova = virt_addr; mr->ibmr.page_size = 1U << shift; return &mr->ibmr; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 0b9cc00525b9..b19e580939ac 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1468,6 +1468,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u16 uid = to_mpd(pd)->uid; u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {}; + if (!qp->sq.wqe_cnt && !qp->rq.wqe_cnt) + return -EINVAL; if (qp->sq.wqe_cnt) { err = create_raw_packet_qp_tis(dev, qp, sq, tdn, pd); if (err) diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index b0d0687c7a68..2e8fa8767fd7 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -83,11 +83,11 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn) struct mlx5_srq_table *table = &dev->srq_table; struct mlx5_core_srq *srq; - xa_lock(&table->array); + xa_lock_irq(&table->array); srq = xa_load(&table->array, srqn); if (srq) atomic_inc(&srq->common.refcount); - xa_unlock(&table->array); + xa_unlock_irq(&table->array); return srq; } diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 8a9b0ee7dbc5..bbf72944b720 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -347,10 +347,10 @@ struct qedr_srq_hwq_info { u32 wqe_prod; u32 sge_prod; u32 wr_prod_cnt; - u32 wr_cons_cnt; + atomic_t wr_cons_cnt; u32 num_elems; - u32 *virt_prod_pair_addr; + struct rdma_srq_producers *virt_prod_pair_addr; dma_addr_t phy_prod_pair_addr; }; diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 2b1ec2d43e74..9d3204410ead 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -3497,7 +3497,7 @@ static u32 qedr_srq_elem_left(struct qedr_srq_hwq_info *hw_srq) * count and consumer count and subtract it from max * work request supported so that we get elements left. */ - used = hw_srq->wr_prod_cnt - hw_srq->wr_cons_cnt; + used = hw_srq->wr_prod_cnt - (u32)atomic_read(&hw_srq->wr_cons_cnt); return hw_srq->max_wr - used; } @@ -3512,7 +3512,6 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, unsigned long flags; int status = 0; u32 num_sge; - u32 offset; spin_lock_irqsave(&srq->lock, flags); @@ -3525,7 +3524,8 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, if (!qedr_srq_elem_left(hw_srq) || wr->num_sge > srq->hw_srq.max_sges) { DP_ERR(dev, "Can't post WR (%d,%d) || (%d > %d)\n", - hw_srq->wr_prod_cnt, hw_srq->wr_cons_cnt, + hw_srq->wr_prod_cnt, + atomic_read(&hw_srq->wr_cons_cnt), wr->num_sge, srq->hw_srq.max_sges); status = -ENOMEM; *bad_wr = wr; @@ -3559,22 +3559,20 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, hw_srq->sge_prod++; } - /* Flush WQE and SGE information before + /* Update WQE and SGE information before * updating producer. */ - wmb(); + dma_wmb(); /* SRQ producer is 8 bytes. Need to update SGE producer index * in first 4 bytes and need to update WQE producer in * next 4 bytes. */ - *srq->hw_srq.virt_prod_pair_addr = hw_srq->sge_prod; - offset = offsetof(struct rdma_srq_producers, wqe_prod); - *((u8 *)srq->hw_srq.virt_prod_pair_addr + offset) = - hw_srq->wqe_prod; + srq->hw_srq.virt_prod_pair_addr->sge_prod = hw_srq->sge_prod; + /* Make sure sge producer is updated first */ + dma_wmb(); + srq->hw_srq.virt_prod_pair_addr->wqe_prod = hw_srq->wqe_prod; - /* Flush producer after updating it. */ - wmb(); wr = wr->next; } @@ -3993,7 +3991,7 @@ static int process_resp_one_srq(struct qedr_dev *dev, struct qedr_qp *qp, } else { __process_resp_one(dev, qp, cq, wc, resp, wr_id); } - srq->hw_srq.wr_cons_cnt++; + atomic_inc(&srq->hw_srq.wr_cons_cnt); return 1; } diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 831ad578a7b2..46e111c218fd 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -330,10 +330,14 @@ err1: static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb) { + struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); const struct ib_gid_attr *gid_attr; union ib_gid dgid; union ib_gid *pdgid; + if (pkt->mask & RXE_LOOPBACK_MASK) + return 0; + if (skb->protocol == htons(ETH_P_IP)) { ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, (struct in6_addr *)&dgid); @@ -366,7 +370,7 @@ void rxe_rcv(struct sk_buff *skb) if (unlikely(skb->len < pkt->offset + RXE_BTH_BYTES)) goto drop; - if (unlikely(rxe_match_dgid(rxe, skb) < 0)) { + if (rxe_match_dgid(rxe, skb) < 0) { pr_warn_ratelimited("failed matching dgid\n"); goto drop; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 8c3e2a18cfe4..75a41f99a23a 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -679,6 +679,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, unsigned int mask; unsigned int length = 0; int i; + struct ib_send_wr *next; while (wr) { mask = wr_opcode_mask(wr->opcode, qp); @@ -695,6 +696,8 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, break; } + next = wr->next; + length = 0; for (i = 0; i < wr->num_sge; i++) length += wr->sg_list[i].length; @@ -705,7 +708,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, *bad_wr = wr; break; } - wr = wr->next; + wr = next; } rxe_run_task(&qp->req.task, 1); diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 0e5f27caf2b2..50a355738609 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -515,7 +515,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev); int ipoib_ib_dev_open_default(struct net_device *dev); int ipoib_ib_dev_open(struct net_device *dev); -int ipoib_ib_dev_stop(struct net_device *dev); +void ipoib_ib_dev_stop(struct net_device *dev); void ipoib_ib_dev_up(struct net_device *dev); void ipoib_ib_dev_down(struct net_device *dev); int ipoib_ib_dev_stop_default(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index aec931973fd8..7b598b66f235 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -669,13 +669,12 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, return rc; } -static void __ipoib_reap_ah(struct net_device *dev) +static void ipoib_reap_dead_ahs(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; unsigned long flags; - netif_tx_lock_bh(dev); + netif_tx_lock_bh(priv->dev); spin_lock_irqsave(&priv->lock, flags); list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list) @@ -686,37 +685,37 @@ static void __ipoib_reap_ah(struct net_device *dev) } spin_unlock_irqrestore(&priv->lock, flags); - netif_tx_unlock_bh(dev); + netif_tx_unlock_bh(priv->dev); } void ipoib_reap_ah(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, ah_reap_task.work); - struct net_device *dev = priv->dev; - __ipoib_reap_ah(dev); + ipoib_reap_dead_ahs(priv); if (!test_bit(IPOIB_STOP_REAPER, &priv->flags)) queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); } -static void ipoib_flush_ah(struct net_device *dev) +static void ipoib_start_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - cancel_delayed_work(&priv->ah_reap_task); - flush_workqueue(priv->wq); - ipoib_reap_ah(&priv->ah_reap_task.work); + clear_bit(IPOIB_STOP_REAPER, &priv->flags); + queue_delayed_work(priv->wq, &priv->ah_reap_task, + round_jiffies_relative(HZ)); } -static void ipoib_stop_ah(struct net_device *dev) +static void ipoib_stop_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - set_bit(IPOIB_STOP_REAPER, &priv->flags); - ipoib_flush_ah(dev); + cancel_delayed_work(&priv->ah_reap_task); + /* + * After ipoib_stop_ah_reaper() we always go through + * ipoib_reap_dead_ahs() which ensures the work is really stopped and + * does a final flush out of the dead_ah's list + */ } static int recvs_pending(struct net_device *dev) @@ -845,18 +844,6 @@ timeout: return 0; } -int ipoib_ib_dev_stop(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - priv->rn_ops->ndo_stop(dev); - - clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_flush_ah(dev); - - return 0; -} - int ipoib_ib_dev_open_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -900,10 +887,7 @@ int ipoib_ib_dev_open(struct net_device *dev) return -1; } - clear_bit(IPOIB_STOP_REAPER, &priv->flags); - queue_delayed_work(priv->wq, &priv->ah_reap_task, - round_jiffies_relative(HZ)); - + ipoib_start_ah_reaper(priv); if (priv->rn_ops->ndo_open(dev)) { pr_warn("%s: Failed to open dev\n", dev->name); goto dev_stop; @@ -914,13 +898,20 @@ int ipoib_ib_dev_open(struct net_device *dev) return 0; dev_stop: - set_bit(IPOIB_STOP_REAPER, &priv->flags); - cancel_delayed_work(&priv->ah_reap_task); - set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_ib_dev_stop(dev); + ipoib_stop_ah_reaper(priv); return -1; } +void ipoib_ib_dev_stop(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + priv->rn_ops->ndo_stop(dev); + + clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + ipoib_stop_ah_reaper(priv); +} + void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -1231,7 +1222,7 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_mcast_dev_flush(dev); if (oper_up) set_bit(IPOIB_FLAG_OPER_UP, &priv->flags); - ipoib_flush_ah(dev); + ipoib_reap_dead_ahs(priv); } if (level >= IPOIB_FLUSH_NORMAL) @@ -1306,7 +1297,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) * the neighbor garbage collection is stopped and reaped. * That should all be done now, so make a final ah flush. */ - ipoib_stop_ah(dev); + ipoib_reap_dead_ahs(priv); clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 4fd095fd63b6..044bcacad6e4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1979,6 +1979,8 @@ static void ipoib_ndo_uninit(struct net_device *dev) /* no more works over the priv->wq */ if (priv->wq) { + /* See ipoib_mcast_carrier_on_task() */ + WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); flush_workqueue(priv->wq); destroy_workqueue(priv->wq); priv->wq = NULL; diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index e78c20d7df41..6b3b5d5ad721 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -914,6 +914,8 @@ static void elan_report_absolute(struct elan_tp_data *data, u8 *packet) u8 hover_info = packet[ETP_HOVER_INFO_OFFSET]; bool contact_valid, hover_event; + pm_wakeup_event(&data->client->dev, 0); + hover_event = hover_info & 0x40; for (i = 0; i < ETP_MAX_FINGERS; i++) { contact_valid = tp_info & (1U << (3 + i)); @@ -936,6 +938,8 @@ static void elan_report_trackpoint(struct elan_tp_data *data, u8 *report) u8 *packet = &report[ETP_REPORT_ID_OFFSET + 1]; int x, y; + pm_wakeup_event(&data->client->dev, 0); + if (!data->tp_input) { dev_warn_once(&data->client->dev, "received a trackpoint report while no trackpoint device has been created. Please report upstream.\n"); @@ -960,7 +964,6 @@ static void elan_report_trackpoint(struct elan_tp_data *data, u8 *report) static irqreturn_t elan_isr(int irq, void *dev_id) { struct elan_tp_data *data = dev_id; - struct device *dev = &data->client->dev; int error; u8 report[ETP_MAX_REPORT_LEN]; @@ -978,8 +981,6 @@ static irqreturn_t elan_isr(int irq, void *dev_id) if (error) goto out; - pm_wakeup_event(dev, 0); - switch (report[ETP_REPORT_ID_OFFSET]) { case ETP_REPORT_ID: elan_report_absolute(data, report); @@ -988,7 +989,7 @@ static irqreturn_t elan_isr(int irq, void *dev_id) elan_report_trackpoint(data, report); break; default: - dev_err(dev, "invalid report id data (%x)\n", + dev_err(&data->client->dev, "invalid report id data (%x)\n", report[ETP_REPORT_ID_OFFSET]); } @@ -1376,8 +1377,15 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN062B", 0 }, { "ELAN062C", 0 }, { "ELAN062D", 0 }, + { "ELAN062E", 0 }, /* Lenovo V340 Whiskey Lake U */ + { "ELAN062F", 0 }, /* Lenovo V340 Comet Lake U */ { "ELAN0631", 0 }, { "ELAN0632", 0 }, + { "ELAN0633", 0 }, /* Lenovo S145 */ + { "ELAN0634", 0 }, /* Lenovo V340 Ice lake */ + { "ELAN0635", 0 }, /* Lenovo V1415-IIL */ + { "ELAN0636", 0 }, /* Lenovo V1415-Dali */ + { "ELAN0637", 0 }, /* Lenovo V1415-IGLR */ { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c index e99d9bf1a267..e78c4c7eda34 100644 --- a/drivers/input/mouse/sentelic.c +++ b/drivers/input/mouse/sentelic.c @@ -441,7 +441,7 @@ static ssize_t fsp_attr_set_setreg(struct psmouse *psmouse, void *data, fsp_reg_write_enable(psmouse, false); - return count; + return retval; } PSMOUSE_DEFINE_WO_ATTR(setreg, S_IWUSR, NULL, fsp_attr_set_setreg); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 944564137a36..9e7ff6fdad78 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -179,6 +179,7 @@ static const char * const smbus_pnp_ids[] = { "LEN0093", /* T480 */ "LEN0096", /* X280 */ "LEN0097", /* X280 -> ALPS trackpoint */ + "LEN0099", /* X1 Extreme 1st */ "LEN009b", /* T580 */ "LEN200f", /* T450s */ "LEN2044", /* L470 */ diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 7e048b557462..858a26302198 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -426,6 +426,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Lenovo XiaoXin Air 12 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "80UN"), + }, + }, + { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 1360"), diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index b99ace9b9a0e..ab18cc298d76 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -153,6 +153,22 @@ static const struct dmi_system_id rotated_screen[] = { {} }; +/* + * Those tablets have their x coordinate inverted + */ +static const struct dmi_system_id inverted_x_screen[] = { +#if defined(CONFIG_DMI) && defined(CONFIG_X86) + { + .ident = "Cube I15-TC", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Cube"), + DMI_MATCH(DMI_PRODUCT_NAME, "I15-TC") + }, + }, +#endif + {} +}; + /** * goodix_i2c_read - read data from a register of the i2c slave device. * @@ -739,6 +755,12 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) "Applying '180 degrees rotated screen' quirk\n"); } + if (dmi_check_system(inverted_x_screen)) { + ts->prop.invert_x = true; + dev_dbg(&ts->client->dev, + "Applying 'inverted x screen' quirk\n"); + } + error = input_mt_init_slots(ts->input_dev, ts->max_touch_num, INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); if (error) { diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index fca908ba4841..fb28fd2d6f1c 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -54,6 +54,7 @@ enum mms_type { TYPE_MMS114 = 114, TYPE_MMS152 = 152, + TYPE_MMS345L = 345, }; struct mms114_data { @@ -250,6 +251,15 @@ static int mms114_get_version(struct mms114_data *data) int error; switch (data->type) { + case TYPE_MMS345L: + error = __mms114_read_reg(data, MMS152_FW_REV, 3, buf); + if (error) + return error; + + dev_info(dev, "TSP FW Rev: bootloader 0x%x / core 0x%x / config 0x%x\n", + buf[0], buf[1], buf[2]); + break; + case TYPE_MMS152: error = __mms114_read_reg(data, MMS152_FW_REV, 3, buf); if (error) @@ -287,8 +297,8 @@ static int mms114_setup_regs(struct mms114_data *data) if (error < 0) return error; - /* MMS152 has no configuration or power on registers */ - if (data->type == TYPE_MMS152) + /* Only MMS114 has configuration and power on registers */ + if (data->type != TYPE_MMS114) return 0; error = mms114_set_active(data, true); @@ -598,6 +608,9 @@ static const struct of_device_id mms114_dt_match[] = { }, { .compatible = "melfas,mms152", .data = (void *)TYPE_MMS152, + }, { + .compatible = "melfas,mms345l", + .data = (void *)TYPE_MMS345L, }, { } }; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 83664db5221d..c255fc8c7f8a 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -204,7 +204,7 @@ config INTEL_IOMMU_DEBUGFS config INTEL_IOMMU_SVM bool "Support for Shared Virtual Memory with Intel IOMMU" - depends on INTEL_IOMMU && X86 + depends on INTEL_IOMMU && X86_64 select PCI_PASID select MMU_NOTIFIER help diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index ff31bddba60a..02e8156b6a75 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -98,8 +98,11 @@ static ssize_t debug_read_regs(struct file *file, char __user *userbuf, mutex_lock(&iommu_debug_lock); bytes = omap_iommu_dump_ctx(obj, p, count); + if (bytes < 0) + goto err; bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes); +err: mutex_unlock(&iommu_debug_lock); kfree(buf); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index eeea66daa389..0e8c08ce2cd6 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2581,6 +2581,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, msi_alloc_info_t *info = args; struct its_device *its_dev = info->scratchpad[0].ptr; struct its_node *its = its_dev->its; + struct irq_data *irqd; irq_hw_number_t hwirq; int err; int i; @@ -2600,7 +2601,9 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, &its_irq_chip, its_dev); - irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i))); + irqd = irq_get_irq_data(virq + i); + irqd_set_single_target(irqd); + irqd_set_affinity_on_activate(irqd); pr_debug("ID:%d pID:%d vID:%d\n", (int)(hwirq + i - its_dev->event_map.lpi_base), (int)(hwirq + i), virq + i); diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c index 73eae5966a40..6ff98b87e5c0 100644 --- a/drivers/irqchip/irq-mtk-sysirq.c +++ b/drivers/irqchip/irq-mtk-sysirq.c @@ -15,7 +15,7 @@ #include <linux/spinlock.h> struct mtk_sysirq_chip_data { - spinlock_t lock; + raw_spinlock_t lock; u32 nr_intpol_bases; void __iomem **intpol_bases; u32 *intpol_words; @@ -37,7 +37,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type) reg_index = chip_data->which_word[hwirq]; offset = hwirq & 0x1f; - spin_lock_irqsave(&chip_data->lock, flags); + raw_spin_lock_irqsave(&chip_data->lock, flags); value = readl_relaxed(base + reg_index * 4); if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_EDGE_FALLING) { if (type == IRQ_TYPE_LEVEL_LOW) @@ -53,7 +53,7 @@ static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type) data = data->parent_data; ret = data->chip->irq_set_type(data, type); - spin_unlock_irqrestore(&chip_data->lock, flags); + raw_spin_unlock_irqrestore(&chip_data->lock, flags); return ret; } @@ -212,7 +212,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node, ret = -ENOMEM; goto out_free_which_word; } - spin_lock_init(&chip_data->lock); + raw_spin_lock_init(&chip_data->lock); return 0; diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index fa7488863bd0..0a35499c4672 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -571,7 +571,7 @@ static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); inta->base = devm_ioremap_resource(dev, res); if (IS_ERR(inta->base)) - return -ENODEV; + return PTR_ERR(inta->base); domain = irq_domain_add_linear(dev_of_node(dev), ti_sci_get_num_resources(inta->vint), diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 4793e77808e2..930158dcfb6e 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -171,6 +171,7 @@ void led_classdev_suspend(struct led_classdev *led_cdev) { led_cdev->flags |= LED_SUSPENDED; led_set_brightness_nopm(led_cdev, 0); + flush_work(&led_cdev->set_brightness_work); } EXPORT_SYMBOL_GPL(led_classdev_suspend); diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c index b3044c9a8120..465c3755cf2e 100644 --- a/drivers/leds/leds-88pm860x.c +++ b/drivers/leds/leds-88pm860x.c @@ -203,21 +203,33 @@ static int pm860x_led_probe(struct platform_device *pdev) data->cdev.brightness_set_blocking = pm860x_led_set; mutex_init(&data->lock); - ret = devm_led_classdev_register(chip->dev, &data->cdev); + ret = led_classdev_register(chip->dev, &data->cdev); if (ret < 0) { dev_err(&pdev->dev, "Failed to register LED: %d\n", ret); return ret; } pm860x_led_set(&data->cdev, 0); + + platform_set_drvdata(pdev, data); + return 0; } +static int pm860x_led_remove(struct platform_device *pdev) +{ + struct pm860x_led *data = platform_get_drvdata(pdev); + + led_classdev_unregister(&data->cdev); + + return 0; +} static struct platform_driver pm860x_led_driver = { .driver = { .name = "88pm860x-led", }, .probe = pm860x_led_probe, + .remove = pm860x_led_remove, }; module_platform_driver(pm860x_led_driver); diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c index ed1b303f699f..2b5fb00438a2 100644 --- a/drivers/leds/leds-da903x.c +++ b/drivers/leds/leds-da903x.c @@ -110,12 +110,23 @@ static int da903x_led_probe(struct platform_device *pdev) led->flags = pdata->flags; led->master = pdev->dev.parent; - ret = devm_led_classdev_register(led->master, &led->cdev); + ret = led_classdev_register(led->master, &led->cdev); if (ret) { dev_err(&pdev->dev, "failed to register LED %d\n", id); return ret; } + platform_set_drvdata(pdev, led); + + return 0; +} + +static int da903x_led_remove(struct platform_device *pdev) +{ + struct da903x_led *led = platform_get_drvdata(pdev); + + led_classdev_unregister(&led->cdev); + return 0; } @@ -124,6 +135,7 @@ static struct platform_driver da903x_led_driver = { .name = "da903x-led", }, .probe = da903x_led_probe, + .remove = da903x_led_remove, }; module_platform_driver(da903x_led_driver); diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c index 9504ad405aef..b3edee703193 100644 --- a/drivers/leds/leds-lm3533.c +++ b/drivers/leds/leds-lm3533.c @@ -694,7 +694,7 @@ static int lm3533_led_probe(struct platform_device *pdev) platform_set_drvdata(pdev, led); - ret = devm_led_classdev_register(pdev->dev.parent, &led->cdev); + ret = led_classdev_register(pdev->dev.parent, &led->cdev); if (ret) { dev_err(&pdev->dev, "failed to register LED %d\n", pdev->id); return ret; @@ -704,13 +704,18 @@ static int lm3533_led_probe(struct platform_device *pdev) ret = lm3533_led_setup(led, pdata); if (ret) - return ret; + goto err_deregister; ret = lm3533_ctrlbank_enable(&led->cb); if (ret) - return ret; + goto err_deregister; return 0; + +err_deregister: + led_classdev_unregister(&led->cdev); + + return ret; } static int lm3533_led_remove(struct platform_device *pdev) @@ -720,6 +725,7 @@ static int lm3533_led_remove(struct platform_device *pdev) dev_dbg(&pdev->dev, "%s\n", __func__); lm3533_ctrlbank_disable(&led->cb); + led_classdev_unregister(&led->cdev); return 0; } diff --git a/drivers/leds/leds-lm355x.c b/drivers/leds/leds-lm355x.c index a5abb499574b..129f475aebf2 100644 --- a/drivers/leds/leds-lm355x.c +++ b/drivers/leds/leds-lm355x.c @@ -165,18 +165,19 @@ static int lm355x_chip_init(struct lm355x_chip_data *chip) /* input and output pins configuration */ switch (chip->type) { case CHIP_LM3554: - reg_val = pdata->pin_tx2 | pdata->ntc_pin; + reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin; ret = regmap_update_bits(chip->regmap, 0xE0, 0x28, reg_val); if (ret < 0) goto out; - reg_val = pdata->pass_mode; + reg_val = (u32)pdata->pass_mode; ret = regmap_update_bits(chip->regmap, 0xA0, 0x04, reg_val); if (ret < 0) goto out; break; case CHIP_LM3556: - reg_val = pdata->pin_tx2 | pdata->ntc_pin | pdata->pass_mode; + reg_val = (u32)pdata->pin_tx2 | (u32)pdata->ntc_pin | + (u32)pdata->pass_mode; ret = regmap_update_bits(chip->regmap, 0x0A, 0xC4, reg_val); if (ret < 0) goto out; diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c index 082df7f1dd90..67f4235cb28a 100644 --- a/drivers/leds/leds-wm831x-status.c +++ b/drivers/leds/leds-wm831x-status.c @@ -269,12 +269,23 @@ static int wm831x_status_probe(struct platform_device *pdev) drvdata->cdev.blink_set = wm831x_status_blink_set; drvdata->cdev.groups = wm831x_status_groups; - ret = devm_led_classdev_register(wm831x->dev, &drvdata->cdev); + ret = led_classdev_register(wm831x->dev, &drvdata->cdev); if (ret < 0) { dev_err(&pdev->dev, "Failed to register LED: %d\n", ret); return ret; } + platform_set_drvdata(pdev, drvdata); + + return 0; +} + +static int wm831x_status_remove(struct platform_device *pdev) +{ + struct wm831x_status *drvdata = platform_get_drvdata(pdev); + + led_classdev_unregister(&drvdata->cdev); + return 0; } @@ -283,6 +294,7 @@ static struct platform_driver wm831x_status_driver = { .name = "wm831x-status", }, .probe = wm831x_status_probe, + .remove = wm831x_status_remove, }; module_platform_driver(wm831x_status_driver); diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c index ac824d7b2dcf..6aa903529570 100644 --- a/drivers/macintosh/via-macii.c +++ b/drivers/macintosh/via-macii.c @@ -270,15 +270,12 @@ static int macii_autopoll(int devs) unsigned long flags; int err = 0; + local_irq_save(flags); + /* bit 1 == device 1, and so on. */ autopoll_devs = devs & 0xFFFE; - if (!autopoll_devs) - return 0; - - local_irq_save(flags); - - if (current_req == NULL) { + if (autopoll_devs && !current_req) { /* Send a Talk Reg 0. The controller will repeatedly transmit * this as long as it is idle. */ diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index eb918b2dc805..2e396954b39d 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -264,7 +264,7 @@ struct bcache_device { #define BCACHE_DEV_UNLINK_DONE 2 #define BCACHE_DEV_WB_RUNNING 3 #define BCACHE_DEV_RATE_DW_RUNNING 4 - unsigned int nr_stripes; + int nr_stripes; unsigned int stripe_size; atomic_t *stripe_sectors_dirty; unsigned long *full_dirty_stripes; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 268f1b685084..ec48cf86cab6 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -321,7 +321,7 @@ int bch_btree_keys_alloc(struct btree_keys *b, b->page_order = page_order; - t->data = (void *) __get_free_pages(gfp, b->page_order); + t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order); if (!t->data) goto err; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index b6a50e5e818e..b60cb7a99b18 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -836,7 +836,7 @@ int bch_btree_cache_alloc(struct cache_set *c) mutex_init(&c->verify_lock); c->verify_ondisk = (void *) - __get_free_pages(GFP_KERNEL, ilog2(bucket_pages(c))); + __get_free_pages(GFP_KERNEL|__GFP_COMP, ilog2(bucket_pages(c))); c->verify_data = mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL); diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 33556acdcf9c..e145c2b1e2c9 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -865,8 +865,8 @@ int bch_journal_alloc(struct cache_set *c) j->w[1].c = c; if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) || - !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) || - !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS))) + !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS)) || + !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP, JSET_BITS))) return -ENOMEM; return 0; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 5b7cfb1d3968..5248bca5e2ed 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1703,7 +1703,7 @@ void bch_cache_set_unregister(struct cache_set *c) } #define alloc_bucket_pages(gfp, c) \ - ((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c)))) + ((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c)))) struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) { @@ -2023,7 +2023,14 @@ found: sysfs_create_link(&c->kobj, &ca->kobj, buf)) goto err; - if (ca->sb.seq > c->sb.seq) { + /* + * A special case is both ca->sb.seq and c->sb.seq are 0, + * such condition happens on a new created cache device whose + * super block is never flushed yet. In this case c->sb.version + * and other members should be updated too, otherwise we will + * have a mistaken super block version in cache set. + */ + if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) { c->sb.version = ca->sb.version; memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16); c->sb.flags = ca->sb.flags; diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index e9ffcea1ca50..58bedd51e11b 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -516,15 +516,19 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode, uint64_t offset, int nr_sectors) { struct bcache_device *d = c->devices[inode]; - unsigned int stripe_offset, stripe, sectors_dirty; + unsigned int stripe_offset, sectors_dirty; + int stripe; if (!d) return; + stripe = offset_to_stripe(d, offset); + if (stripe < 0) + return; + if (UUID_FLASH_ONLY(&c->uuids[inode])) atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors); - stripe = offset_to_stripe(d, offset); stripe_offset = offset & (d->stripe_size - 1); while (nr_sectors) { @@ -564,12 +568,12 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k) static void refill_full_stripes(struct cached_dev *dc) { struct keybuf *buf = &dc->writeback_keys; - unsigned int start_stripe, stripe, next_stripe; + unsigned int start_stripe, next_stripe; + int stripe; bool wrapped = false; stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned)); - - if (stripe >= dc->disk.nr_stripes) + if (stripe < 0) stripe = 0; start_stripe = stripe; diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 4e4c6810dc3c..c4ff76037227 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -33,10 +33,22 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d) return ret; } -static inline unsigned int offset_to_stripe(struct bcache_device *d, +static inline int offset_to_stripe(struct bcache_device *d, uint64_t offset) { do_div(offset, d->stripe_size); + + /* d->nr_stripes is in range [1, INT_MAX] */ + if (unlikely(offset >= d->nr_stripes)) { + pr_err("Invalid stripe %llu (>= nr_stripes %d).\n", + offset, d->nr_stripes); + return -EINVAL; + } + + /* + * Here offset is definitly smaller than INT_MAX, + * return it as int will never overflow. + */ return offset; } @@ -44,7 +56,10 @@ static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc, uint64_t offset, unsigned int nr_sectors) { - unsigned int stripe = offset_to_stripe(&dc->disk, offset); + int stripe = offset_to_stripe(&dc->disk, offset); + + if (stripe < 0) + return false; while (1) { if (atomic_read(dc->disk.stripe_sectors_dirty + stripe)) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index b41ecb451c78..99784f16cb56 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -70,9 +70,6 @@ void dm_start_queue(struct request_queue *q) void dm_stop_queue(struct request_queue *q) { - if (blk_mq_queue_stopped(q)) - return; - blk_mq_quiesce_queue(q); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fecefe9a7302..9e7765ea73a9 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1440,9 +1440,6 @@ static int __send_empty_flush(struct clone_info *ci) BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); - - bio_disassociate_blkg(ci->bio); - return 0; } @@ -1630,6 +1627,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else if (bio_op(bio) == REQ_OP_ZONE_RESET) { ci.bio = bio; @@ -1704,6 +1702,7 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map, ci.bio = &flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); + bio_uninit(ci.bio); /* dec_pending submits any data associated with flush */ } else { struct dm_target_io *tio; diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 813a99ffa86f..d50737ec4039 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1139,6 +1139,7 @@ static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsiz bitmap = get_bitmap_from_slot(mddev, i); if (IS_ERR(bitmap)) { pr_err("can't get bitmap from slot %d\n", i); + bitmap = NULL; goto out; } counts = &bitmap->counts; @@ -1518,6 +1519,7 @@ static void unlock_all_bitmaps(struct mddev *mddev) } } kfree(cinfo->other_bitmap_lockres); + cinfo->other_bitmap_lockres = NULL; } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9313dc8e3389..d0af52da65af 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3598,6 +3598,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s, * is missing/faulty, then we need to read everything we can. */ if (sh->raid_conf->level != 6 && + sh->raid_conf->rmw_level != PARITY_DISABLE_RMW && sh->sector < sh->raid_conf->mddev->recovery_cp) /* reconstruct-write isn't being forced */ return 0; @@ -4834,7 +4835,7 @@ static void handle_stripe(struct stripe_head *sh) * or to load a block that is being partially written. */ if (s.to_read || s.non_overwrite - || (conf->level == 6 && s.to_write && s.failed) + || (s.to_write && s.failed) || (s.syncing && (s.uptodate + s.compute < disks)) || s.replacing || s.expanding) diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c index 97144734eb05..3f1ca40b9b98 100644 --- a/drivers/media/firewire/firedtv-fw.c +++ b/drivers/media/firewire/firedtv-fw.c @@ -272,6 +272,8 @@ 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; 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/media-request.c b/drivers/media/media-request.c index e3fca436c75b..c0782fd96c59 100644 --- a/drivers/media/media-request.c +++ b/drivers/media/media-request.c @@ -296,9 +296,18 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd) if (WARN_ON(!mdev->ops->req_alloc ^ !mdev->ops->req_free)) return -ENOMEM; + if (mdev->ops->req_alloc) + req = mdev->ops->req_alloc(mdev); + else + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + fd = get_unused_fd_flags(O_CLOEXEC); - if (fd < 0) - return fd; + if (fd < 0) { + ret = fd; + goto err_free_req; + } filp = anon_inode_getfile("request", &request_fops, NULL, O_CLOEXEC); if (IS_ERR(filp)) { @@ -306,15 +315,6 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd) goto err_put_fd; } - if (mdev->ops->req_alloc) - req = mdev->ops->req_alloc(mdev); - else - req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) { - ret = -ENOMEM; - goto err_fput; - } - filp->private_data = req; req->mdev = mdev; req->state = MEDIA_REQUEST_STATE_IDLE; @@ -336,12 +336,15 @@ int media_request_alloc(struct media_device *mdev, int *alloc_fd) return 0; -err_fput: - fput(filp); - err_put_fd: put_unused_fd(fd); +err_free_req: + if (mdev->ops->req_free) + mdev->ops->req_free(req); + else + kfree(req); + return ret; } diff --git a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c index 068df9888dbf..e49ca6e726e1 100644 --- a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c +++ b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c @@ -276,11 +276,7 @@ static int cros_ec_cec_probe(struct platform_device *pdev) if (ret) return ret; - ret = device_init_wakeup(&pdev->dev, 1); - if (ret) { - dev_err(&pdev->dev, "failed to initialize wakeup\n"); - return ret; - } + device_init_wakeup(&pdev->dev, 1); cros_ec_cec->adap = cec_allocate_adapter(&cros_ec_cec_ops, cros_ec_cec, DRV_NAME, CEC_CAP_DEFAULTS, 1); diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index 594e4807e45b..0ed62d11389a 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1266,6 +1266,9 @@ static int fimc_md_get_pinctrl(struct fimc_md *fmd) 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/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c index 97d660606d98..b8c2b8bba826 100644 --- a/drivers/media/platform/omap3isp/isppreview.c +++ b/drivers/media/platform/omap3isp/isppreview.c @@ -2287,7 +2287,7 @@ static int preview_init_entities(struct isp_prev_device *prev) me->ops = &preview_media_ops; ret = media_entity_pads_init(me, PREV_PADS_NUM, pads); if (ret < 0) - return ret; + goto error_handler_free; preview_init_formats(sd, NULL); @@ -2320,6 +2320,8 @@ error_video_out: omap3isp_video_cleanup(&prev->video_in); error_video_in: media_entity_cleanup(&prev->subdev.entity); +error_handler_free: + v4l2_ctrl_handler_free(&prev->ctrls); return ret; } diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c index 4be6dcf292ff..aaa96f256356 100644 --- a/drivers/media/platform/rockchip/rga/rga-hw.c +++ b/drivers/media/platform/rockchip/rga/rga-hw.c @@ -200,22 +200,25 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx) dst_info.data.format = ctx->out.fmt->hw_format; dst_info.data.swap = ctx->out.fmt->color_swap; - if (ctx->in.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) { - if (ctx->out.fmt->hw_format < RGA_COLOR_FMT_YUV422SP) { - switch (ctx->in.colorspace) { - case V4L2_COLORSPACE_REC709: - src_info.data.csc_mode = - RGA_SRC_CSC_MODE_BT709_R0; - break; - default: - src_info.data.csc_mode = - RGA_SRC_CSC_MODE_BT601_R0; - break; - } + /* + * CSC mode must only be set when the colorspace families differ between + * input and output. It must remain unset (zeroed) if both are the same. + */ + + if (RGA_COLOR_FMT_IS_YUV(ctx->in.fmt->hw_format) && + RGA_COLOR_FMT_IS_RGB(ctx->out.fmt->hw_format)) { + switch (ctx->in.colorspace) { + case V4L2_COLORSPACE_REC709: + src_info.data.csc_mode = RGA_SRC_CSC_MODE_BT709_R0; + break; + default: + src_info.data.csc_mode = RGA_SRC_CSC_MODE_BT601_R0; + break; } } - if (ctx->out.fmt->hw_format >= RGA_COLOR_FMT_YUV422SP) { + if (RGA_COLOR_FMT_IS_RGB(ctx->in.fmt->hw_format) && + RGA_COLOR_FMT_IS_YUV(ctx->out.fmt->hw_format)) { switch (ctx->out.colorspace) { case V4L2_COLORSPACE_REC709: dst_info.data.csc_mode = RGA_SRC_CSC_MODE_BT709_R0; diff --git a/drivers/media/platform/rockchip/rga/rga-hw.h b/drivers/media/platform/rockchip/rga/rga-hw.h index 96cb0314dfa7..e8917e5630a4 100644 --- a/drivers/media/platform/rockchip/rga/rga-hw.h +++ b/drivers/media/platform/rockchip/rga/rga-hw.h @@ -95,6 +95,11 @@ #define RGA_COLOR_FMT_CP_8BPP 15 #define RGA_COLOR_FMT_MASK 15 +#define RGA_COLOR_FMT_IS_YUV(fmt) \ + (((fmt) >= RGA_COLOR_FMT_YUV422SP) && ((fmt) < RGA_COLOR_FMT_CP_1BPP)) +#define RGA_COLOR_FMT_IS_RGB(fmt) \ + ((fmt) < RGA_COLOR_FMT_YUV422SP) + #define RGA_COLOR_NONE_SWAP 0 #define RGA_COLOR_RB_SWAP 1 #define RGA_COLOR_ALPHA_SWAP 2 diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c index d7b43037e500..e07b135613eb 100644 --- a/drivers/media/platform/vsp1/vsp1_dl.c +++ b/drivers/media/platform/vsp1/vsp1_dl.c @@ -431,6 +431,8 @@ vsp1_dl_cmd_pool_create(struct vsp1_device *vsp1, enum vsp1_extcmd_type type, if (!pool) return NULL; + pool->vsp1 = vsp1; + spin_lock_init(&pool->lock); INIT_LIST_HEAD(&pool->free); diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index 4a31907a4525..3ff872c205ee 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -1430,6 +1430,15 @@ err_irq: arizona_irq_exit(arizona); err_pm: pm_runtime_disable(arizona->dev); + + switch (arizona->pdata.clk32k_src) { + case ARIZONA_32KZ_MCLK1: + case ARIZONA_32KZ_MCLK2: + arizona_clk32k_disable(arizona); + break; + default: + break; + } err_reset: arizona_enable_reset(arizona); regulator_disable(arizona->dcvdd); @@ -1452,6 +1461,15 @@ int arizona_dev_exit(struct arizona *arizona) regulator_disable(arizona->dcvdd); regulator_put(arizona->dcvdd); + switch (arizona->pdata.clk32k_src) { + case ARIZONA_32KZ_MCLK1: + case ARIZONA_32KZ_MCLK2: + arizona_clk32k_disable(arizona); + break; + default: + break; + } + mfd_remove_devices(arizona->dev); arizona_free_irq(arizona, ARIZONA_IRQ_UNDERCLOCKED, arizona); arizona_free_irq(arizona, ARIZONA_IRQ_OVERCLOCKED, arizona); diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c index 4faa8d2e5d04..707f4287ab4a 100644 --- a/drivers/mfd/dln2.c +++ b/drivers/mfd/dln2.c @@ -287,7 +287,11 @@ static void dln2_rx(struct urb *urb) len = urb->actual_length - sizeof(struct dln2_header); if (handle == DLN2_HANDLE_EVENT) { + unsigned long flags; + + spin_lock_irqsave(&dln2->event_cb_lock, flags); dln2_run_event_callbacks(dln2, id, echo, data, len); + spin_unlock_irqrestore(&dln2->event_cb_lock, flags); } else { /* URB will be re-submitted in _dln2_transfer (free_rx_slot) */ if (dln2_transfer_complete(dln2, urb, handle, echo)) diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c index ab4144ea1f11..d6cd5537126c 100644 --- a/drivers/misc/atmel-ssc.c +++ b/drivers/misc/atmel-ssc.c @@ -10,7 +10,7 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/io.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/atmel-ssc.h> #include <linux/slab.h> #include <linux/module.h> @@ -20,7 +20,7 @@ #include "../../sound/soc/atmel/atmel_ssc_dai.h" /* Serialize access to ssc_list and user count */ -static DEFINE_SPINLOCK(user_lock); +static DEFINE_MUTEX(user_lock); static LIST_HEAD(ssc_list); struct ssc_device *ssc_request(unsigned int ssc_num) @@ -28,7 +28,7 @@ struct ssc_device *ssc_request(unsigned int ssc_num) int ssc_valid = 0; struct ssc_device *ssc; - spin_lock(&user_lock); + mutex_lock(&user_lock); list_for_each_entry(ssc, &ssc_list, list) { if (ssc->pdev->dev.of_node) { if (of_alias_get_id(ssc->pdev->dev.of_node, "ssc") @@ -44,18 +44,18 @@ struct ssc_device *ssc_request(unsigned int ssc_num) } if (!ssc_valid) { - spin_unlock(&user_lock); + mutex_unlock(&user_lock); pr_err("ssc: ssc%d platform device is missing\n", ssc_num); return ERR_PTR(-ENODEV); } if (ssc->user) { - spin_unlock(&user_lock); + mutex_unlock(&user_lock); dev_dbg(&ssc->pdev->dev, "module busy\n"); return ERR_PTR(-EBUSY); } ssc->user++; - spin_unlock(&user_lock); + mutex_unlock(&user_lock); clk_prepare(ssc->clk); @@ -67,14 +67,14 @@ void ssc_free(struct ssc_device *ssc) { bool disable_clk = true; - spin_lock(&user_lock); + mutex_lock(&user_lock); if (ssc->user) ssc->user--; else { disable_clk = false; dev_dbg(&ssc->pdev->dev, "device already free\n"); } - spin_unlock(&user_lock); + mutex_unlock(&user_lock); if (disable_clk) clk_unprepare(ssc->clk); @@ -237,9 +237,9 @@ static int ssc_probe(struct platform_device *pdev) return -ENXIO; } - spin_lock(&user_lock); + mutex_lock(&user_lock); list_add_tail(&ssc->list, &ssc_list); - spin_unlock(&user_lock); + mutex_unlock(&user_lock); platform_set_drvdata(pdev, ssc); @@ -258,9 +258,9 @@ static int ssc_remove(struct platform_device *pdev) ssc_sound_dai_remove(ssc); - spin_lock(&user_lock); + mutex_lock(&user_lock); list_del(&ssc->list); - spin_unlock(&user_lock); + mutex_unlock(&user_lock); return 0; } diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c index f0263d1a1fdf..d97a243ad30c 100644 --- a/drivers/misc/cxl/sysfs.c +++ b/drivers/misc/cxl/sysfs.c @@ -624,7 +624,7 @@ static struct afu_config_record *cxl_sysfs_afu_new_cr(struct cxl_afu *afu, int c rc = kobject_init_and_add(&cr->kobj, &afu_config_record_type, &afu->dev.kobj, "cr%i", cr->cr); if (rc) - goto err; + goto err1; rc = sysfs_create_bin_file(&cr->kobj, &cr->config_attr); if (rc) diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 53bb394ccba6..cef97a7eb8b6 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -745,9 +745,8 @@ static int mei_cl_device_remove(struct device *dev) mei_cl_bus_module_put(cldev); module_put(THIS_MODULE); - dev->driver = NULL; - return ret; + return ret; } static ssize_t name_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 5a4eddef8067..18a7afb2a5b2 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -458,6 +458,10 @@ static int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms, bool expired = false; bool busy = false; + /* We have an unspecified cmd timeout, use the fallback value. */ + if (!timeout_ms) + timeout_ms = MMC_OPS_TIMEOUT_MS; + /* * In cases when not allowed to poll by using CMD13 or because we aren't * capable of polling by using ->card_busy(), then rely on waiting the @@ -530,21 +534,16 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value, mmc_retune_hold(host); - if (!timeout_ms) { - pr_warn("%s: unspecified timeout for CMD6 - use generic\n", - mmc_hostname(host)); - timeout_ms = card->ext_csd.generic_cmd6_time; - } - /* - * If the max_busy_timeout of the host is specified, make sure it's - * enough to fit the used timeout_ms. In case it's not, let's instruct - * the host to avoid HW busy detection, by converting to a R1 response - * instead of a R1B. Note, some hosts requires R1B, which also means - * they are on their own when it comes to deal with the busy timeout. + * If the cmd timeout and the max_busy_timeout of the host are both + * specified, let's validate them. A failure means we need to prevent + * the host from doing hw busy detection, which is done by converting + * to a R1 response instead of a R1B. Note, some hosts requires R1B, + * which also means they are on their own when it comes to deal with the + * busy timeout. */ - if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout && - (timeout_ms > host->max_busy_timeout)) + if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && timeout_ms && + host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) use_r1b_resp = false; cmd.opcode = MMC_SWITCH; @@ -555,6 +554,10 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value, cmd.flags = MMC_CMD_AC; if (use_r1b_resp) { cmd.flags |= MMC_RSP_SPI_R1B | MMC_RSP_R1B; + /* + * A busy_timeout of zero means the host can decide to use + * whatever value it finds suitable. + */ cmd.busy_timeout = timeout_ms; } else { cmd.flags |= MMC_RSP_SPI_R1 | MMC_RSP_R1; diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index b8554bf38f72..da59512e9411 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -168,6 +168,8 @@ static struct variant_data variant_ux500 = { .cmdreg_srsp = MCI_CPSM_RESPONSE, .datalength_bits = 24, .datactrl_blocksz = 11, + .datactrl_any_blocksz = true, + .dma_power_of_2 = true, .datactrl_mask_sdio = MCI_DPSM_ST_SDIOEN, .st_sdio = true, .st_clkdiv = true, @@ -201,6 +203,8 @@ static struct variant_data variant_ux500v2 = { .datactrl_mask_ddrmode = MCI_DPSM_ST_DDRMODE, .datalength_bits = 24, .datactrl_blocksz = 11, + .datactrl_any_blocksz = true, + .dma_power_of_2 = true, .datactrl_mask_sdio = MCI_DPSM_ST_SDIOEN, .st_sdio = true, .st_clkdiv = true, @@ -260,6 +264,7 @@ static struct variant_data variant_stm32_sdmmc = { .datacnt_useless = true, .datalength_bits = 25, .datactrl_blocksz = 14, + .datactrl_any_blocksz = true, .stm32_idmabsize_mask = GENMASK(12, 5), .init = sdmmc_variant_init, }; @@ -279,6 +284,7 @@ static struct variant_data variant_qcom = { .data_cmd_enable = MCI_CPSM_QCOM_DATCMD, .datalength_bits = 24, .datactrl_blocksz = 11, + .datactrl_any_blocksz = true, .pwrreg_powerup = MCI_PWR_UP, .f_max = 208000000, .explicit_mclk_control = true, @@ -447,10 +453,11 @@ void mmci_dma_setup(struct mmci_host *host) static int mmci_validate_data(struct mmci_host *host, struct mmc_data *data) { + struct variant_data *variant = host->variant; + if (!data) return 0; - - if (!is_power_of_2(data->blksz)) { + if (!is_power_of_2(data->blksz) && !variant->datactrl_any_blocksz) { dev_err(mmc_dev(host->mmc), "unsupported block size (%d bytes)\n", data->blksz); return -EINVAL; @@ -515,7 +522,9 @@ int mmci_dma_start(struct mmci_host *host, unsigned int datactrl) "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n", data->sg_len, data->blksz, data->blocks, data->flags); - host->ops->dma_start(host, &datactrl); + ret = host->ops->dma_start(host, &datactrl); + if (ret) + return ret; /* Trigger the DMA transfer */ mmci_write_datactrlreg(host, datactrl); @@ -822,6 +831,18 @@ static int _mmci_dmae_prep_data(struct mmci_host *host, struct mmc_data *data, if (data->blksz * data->blocks <= variant->fifosize) return -EINVAL; + /* + * This is necessary to get SDIO working on the Ux500. We do not yet + * know if this is a bug in: + * - The Ux500 DMA controller (DMA40) + * - The MMCI DMA interface on the Ux500 + * some power of two blocks (such as 64 bytes) are sent regularly + * during SDIO traffic and those work fine so for these we enable DMA + * transfers. + */ + if (host->variant->dma_power_of_2 && !is_power_of_2(data->blksz)) + return -EINVAL; + device = chan->device; nr_sg = dma_map_sg(device->dev, data->sg, data->sg_len, mmc_get_dma_dir(data)); @@ -872,9 +893,14 @@ int mmci_dmae_prep_data(struct mmci_host *host, int mmci_dmae_start(struct mmci_host *host, unsigned int *datactrl) { struct mmci_dmae_priv *dmae = host->dma_priv; + int ret; host->dma_in_progress = true; - dmaengine_submit(dmae->desc_current); + ret = dma_submit_error(dmaengine_submit(dmae->desc_current)); + if (ret < 0) { + host->dma_in_progress = false; + return ret; + } dma_async_issue_pending(dmae->cur); *datactrl |= MCI_DPSM_DMAENABLE; diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h index 833236ecb31e..89ab73343cf3 100644 --- a/drivers/mmc/host/mmci.h +++ b/drivers/mmc/host/mmci.h @@ -278,7 +278,11 @@ struct mmci_host; * @stm32_clkdiv: true if using a STM32-specific clock divider algorithm * @datactrl_mask_ddrmode: ddr mode mask in datactrl register. * @datactrl_mask_sdio: SDIO enable mask in datactrl register - * @datactrl_blksz: block size in power of two + * @datactrl_blocksz: block size in power of two + * @datactrl_any_blocksz: true if block any block sizes are accepted by + * hardware, such as with some SDIO traffic that send + * odd packets. + * @dma_power_of_2: DMA only works with blocks that are a power of 2. * @datactrl_first: true if data must be setup before send command * @datacnt_useless: true if you could not use datacnt register to read * remaining data @@ -323,6 +327,8 @@ struct variant_data { unsigned int datactrl_mask_ddrmode; unsigned int datactrl_mask_sdio; unsigned int datactrl_blocksz; + u8 datactrl_any_blocksz:1; + u8 dma_power_of_2:1; u8 datactrl_first:1; u8 datacnt_useless:1; u8 st_sdio:1; diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c index 751fe91c7571..63eb203bba61 100644 --- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c @@ -229,15 +229,12 @@ static void renesas_sdhi_internal_dmac_issue_tasklet_fn(unsigned long arg) DTRAN_CTRL_DM_START); } -static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg) +static bool renesas_sdhi_internal_dmac_complete(struct tmio_mmc_host *host) { - struct tmio_mmc_host *host = (struct tmio_mmc_host *)arg; enum dma_data_direction dir; - spin_lock_irq(&host->lock); - if (!host->data) - goto out; + return false; if (host->data->flags & MMC_DATA_READ) dir = DMA_FROM_DEVICE; @@ -250,6 +247,17 @@ static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg) if (dir == DMA_FROM_DEVICE) clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags); + return true; +} + +static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg) +{ + struct tmio_mmc_host *host = (struct tmio_mmc_host *)arg; + + spin_lock_irq(&host->lock); + if (!renesas_sdhi_internal_dmac_complete(host)) + goto out; + tmio_mmc_do_data_irq(host); out: spin_unlock_irq(&host->lock); diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index 44139fceac24..58d2fdd6155f 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -11,6 +11,7 @@ #include <linux/mmc/host.h> #include <linux/mmc/mmc.h> #include <linux/of.h> +#include <linux/of_device.h> #include "sdhci-pltfm.h" @@ -193,52 +194,6 @@ static u32 sdhci_cdns_get_emmc_mode(struct sdhci_cdns_priv *priv) return FIELD_GET(SDHCI_CDNS_HRS06_MODE, tmp); } -static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host, - unsigned int timing) -{ - struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host); - u32 mode; - - switch (timing) { - case MMC_TIMING_MMC_HS: - mode = SDHCI_CDNS_HRS06_MODE_MMC_SDR; - break; - case MMC_TIMING_MMC_DDR52: - mode = SDHCI_CDNS_HRS06_MODE_MMC_DDR; - break; - case MMC_TIMING_MMC_HS200: - mode = SDHCI_CDNS_HRS06_MODE_MMC_HS200; - break; - case MMC_TIMING_MMC_HS400: - if (priv->enhanced_strobe) - mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400ES; - else - mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400; - break; - default: - mode = SDHCI_CDNS_HRS06_MODE_SD; - break; - } - - sdhci_cdns_set_emmc_mode(priv, mode); - - /* For SD, fall back to the default handler */ - if (mode == SDHCI_CDNS_HRS06_MODE_SD) - sdhci_set_uhs_signaling(host, timing); -} - -static const struct sdhci_ops sdhci_cdns_ops = { - .set_clock = sdhci_set_clock, - .get_timeout_clock = sdhci_cdns_get_timeout_clock, - .set_bus_width = sdhci_set_bus_width, - .reset = sdhci_reset, - .set_uhs_signaling = sdhci_cdns_set_uhs_signaling, -}; - -static const struct sdhci_pltfm_data sdhci_cdns_pltfm_data = { - .ops = &sdhci_cdns_ops, -}; - static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val) { struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host); @@ -272,23 +227,24 @@ static int sdhci_cdns_set_tune_val(struct sdhci_host *host, unsigned int val) return 0; } -static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode) +/* + * In SD mode, software must not use the hardware tuning and instead perform + * an almost identical procedure to eMMC. + */ +static int sdhci_cdns_execute_tuning(struct sdhci_host *host, u32 opcode) { - struct sdhci_host *host = mmc_priv(mmc); int cur_streak = 0; int max_streak = 0; int end_of_streak = 0; int i; /* - * This handler only implements the eMMC tuning that is specific to - * this controller. Fall back to the standard method for SD timing. + * Do not execute tuning for UHS_SDR50 or UHS_DDR50. + * The delay is set by probe, based on the DT properties. */ - if (host->timing != MMC_TIMING_MMC_HS200) - return sdhci_execute_tuning(mmc, opcode); - - if (WARN_ON(opcode != MMC_SEND_TUNING_BLOCK_HS200)) - return -EINVAL; + if (host->timing != MMC_TIMING_MMC_HS200 && + host->timing != MMC_TIMING_UHS_SDR104) + return 0; for (i = 0; i < SDHCI_CDNS_MAX_TUNING_LOOP; i++) { if (sdhci_cdns_set_tune_val(host, i) || @@ -311,6 +267,58 @@ static int sdhci_cdns_execute_tuning(struct mmc_host *mmc, u32 opcode) return sdhci_cdns_set_tune_val(host, end_of_streak - max_streak / 2); } +static void sdhci_cdns_set_uhs_signaling(struct sdhci_host *host, + unsigned int timing) +{ + struct sdhci_cdns_priv *priv = sdhci_cdns_priv(host); + u32 mode; + + switch (timing) { + case MMC_TIMING_MMC_HS: + mode = SDHCI_CDNS_HRS06_MODE_MMC_SDR; + break; + case MMC_TIMING_MMC_DDR52: + mode = SDHCI_CDNS_HRS06_MODE_MMC_DDR; + break; + case MMC_TIMING_MMC_HS200: + mode = SDHCI_CDNS_HRS06_MODE_MMC_HS200; + break; + case MMC_TIMING_MMC_HS400: + if (priv->enhanced_strobe) + mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400ES; + else + mode = SDHCI_CDNS_HRS06_MODE_MMC_HS400; + break; + default: + mode = SDHCI_CDNS_HRS06_MODE_SD; + break; + } + + sdhci_cdns_set_emmc_mode(priv, mode); + + /* For SD, fall back to the default handler */ + if (mode == SDHCI_CDNS_HRS06_MODE_SD) + sdhci_set_uhs_signaling(host, timing); +} + +static const struct sdhci_ops sdhci_cdns_ops = { + .set_clock = sdhci_set_clock, + .get_timeout_clock = sdhci_cdns_get_timeout_clock, + .set_bus_width = sdhci_set_bus_width, + .reset = sdhci_reset, + .platform_execute_tuning = sdhci_cdns_execute_tuning, + .set_uhs_signaling = sdhci_cdns_set_uhs_signaling, +}; + +static const struct sdhci_pltfm_data sdhci_cdns_uniphier_pltfm_data = { + .ops = &sdhci_cdns_ops, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, +}; + +static const struct sdhci_pltfm_data sdhci_cdns_pltfm_data = { + .ops = &sdhci_cdns_ops, +}; + static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc, struct mmc_ios *ios) { @@ -334,6 +342,7 @@ static void sdhci_cdns_hs400_enhanced_strobe(struct mmc_host *mmc, static int sdhci_cdns_probe(struct platform_device *pdev) { struct sdhci_host *host; + const struct sdhci_pltfm_data *data; struct sdhci_pltfm_host *pltfm_host; struct sdhci_cdns_priv *priv; struct clk *clk; @@ -350,9 +359,13 @@ static int sdhci_cdns_probe(struct platform_device *pdev) if (ret) return ret; + data = of_device_get_match_data(dev); + if (!data) + data = &sdhci_cdns_pltfm_data; + nr_phy_params = sdhci_cdns_phy_param_count(dev->of_node); priv_size = sizeof(*priv) + sizeof(priv->phy_params[0]) * nr_phy_params; - host = sdhci_pltfm_init(pdev, &sdhci_cdns_pltfm_data, priv_size); + host = sdhci_pltfm_init(pdev, data, priv_size); if (IS_ERR(host)) { ret = PTR_ERR(host); goto disable_clk; @@ -366,7 +379,6 @@ static int sdhci_cdns_probe(struct platform_device *pdev) priv->hrs_addr = host->ioaddr; priv->enhanced_strobe = false; host->ioaddr += SDHCI_CDNS_SRS_BASE; - host->mmc_host_ops.execute_tuning = sdhci_cdns_execute_tuning; host->mmc_host_ops.hs400_enhanced_strobe = sdhci_cdns_hs400_enhanced_strobe; sdhci_enable_v4_mode(host); @@ -430,7 +442,10 @@ static const struct dev_pm_ops sdhci_cdns_pm_ops = { }; static const struct of_device_id sdhci_cdns_match[] = { - { .compatible = "socionext,uniphier-sd4hc" }, + { + .compatible = "socionext,uniphier-sd4hc", + .data = &sdhci_cdns_uniphier_pltfm_data, + }, { .compatible = "cdns,sd4hc" }, { /* sentinel */ } }; diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c index 19944b0049db..7b3c9e6dab65 100644 --- a/drivers/mmc/host/sdhci-pci-o2micro.c +++ b/drivers/mmc/host/sdhci-pci-o2micro.c @@ -441,6 +441,12 @@ int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot) slot->host->mmc_host_ops.get_cd = sdhci_o2_get_cd; } + if (chip->pdev->device == PCI_DEVICE_ID_O2_SEABIRD1) { + slot->host->mmc_host_ops.get_cd = sdhci_o2_get_cd; + host->mmc->caps2 |= MMC_CAP2_NO_SDIO; + host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN; + } + host->mmc_host_ops.execute_tuning = sdhci_o2_execute_tuning; if (chip->pdev->device != PCI_DEVICE_ID_O2_FUJIN2) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 89ff43b43de9..5a8d97a8f1e1 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -152,7 +152,7 @@ static void sdhci_set_card_detection(struct sdhci_host *host, bool enable) u32 present; if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) || - !mmc_card_is_removable(host->mmc)) + !mmc_card_is_removable(host->mmc) || mmc_can_gpio_cd(host->mmc)) return; if (enable) { diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 975aed94f06c..48832f9b215c 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -354,9 +354,6 @@ static int mtdchar_writeoob(struct file *file, struct mtd_info *mtd, uint32_t retlen; int ret = 0; - if (!(file->f_mode & FMODE_WRITE)) - return -EPERM; - if (length > 4096) return -EINVAL; @@ -641,6 +638,48 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg) pr_debug("MTD_ioctl\n"); + /* + * Check the file mode to require "dangerous" commands to have write + * permissions. + */ + switch (cmd) { + /* "safe" commands */ + case MEMGETREGIONCOUNT: + case MEMGETREGIONINFO: + case MEMGETINFO: + case MEMREADOOB: + case MEMREADOOB64: + case MEMLOCK: + case MEMUNLOCK: + case MEMISLOCKED: + case MEMGETOOBSEL: + case MEMGETBADBLOCK: + case MEMSETBADBLOCK: + case OTPSELECT: + case OTPGETREGIONCOUNT: + case OTPGETREGIONINFO: + case OTPLOCK: + case ECCGETLAYOUT: + case ECCGETSTATS: + case MTDFILEMODE: + case BLKPG: + case BLKRRPART: + break; + + /* "dangerous" commands */ + case MEMERASE: + case MEMERASE64: + case MEMWRITEOOB: + case MEMWRITEOOB64: + case MEMWRITE: + if (!(file->f_mode & FMODE_WRITE)) + return -EPERM; + break; + + default: + return -ENOTTY; + } + switch (cmd) { case MEMGETREGIONCOUNT: if (copy_to_user(argp, &(mtd->numeraseregions), sizeof(int))) @@ -688,9 +727,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg) { struct erase_info *erase; - if(!(file->f_mode & FMODE_WRITE)) - return -EPERM; - erase=kzalloc(sizeof(struct erase_info),GFP_KERNEL); if (!erase) ret = -ENOMEM; @@ -983,9 +1019,6 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg) ret = 0; break; } - - default: - ret = -ENOTTY; } return ret; @@ -1029,6 +1062,11 @@ static long mtdchar_compat_ioctl(struct file *file, unsigned int cmd, struct mtd_oob_buf32 buf; struct mtd_oob_buf32 __user *buf_user = argp; + if (!(file->f_mode & FMODE_WRITE)) { + ret = -EPERM; + break; + } + if (copy_from_user(&buf, argp, sizeof(buf))) ret = -EFAULT; else diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index f71bab29c475..9d0a532efcf2 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -483,8 +483,9 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl) } else { ctrl->cs_offsets = brcmnand_cs_offsets; - /* v5.0 and earlier has a different CS0 offset layout */ - if (ctrl->nand_version <= 0x0500) + /* v3.3-5.0 have a different CS0 offset layout */ + if (ctrl->nand_version >= 0x0303 && + ctrl->nand_version <= 0x0500) ctrl->cs0_offsets = brcmnand_cs_offsets_cs0; } @@ -1665,25 +1666,31 @@ static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip, static int brcmstb_nand_verify_erased_page(struct mtd_info *mtd, struct nand_chip *chip, void *buf, u64 addr) { - int i, sas; - void *oob = chip->oob_poi; + struct mtd_oob_region ecc; + int i; int bitflips = 0; int page = addr >> chip->page_shift; int ret; + void *ecc_bytes; + void *ecc_chunk; if (!buf) buf = nand_get_data_buf(chip); - sas = mtd->oobsize / chip->ecc.steps; - /* read without ecc for verification */ ret = chip->ecc.read_page_raw(chip, buf, true, page); if (ret) return ret; - for (i = 0; i < chip->ecc.steps; i++, oob += sas) { - ret = nand_check_erased_ecc_chunk(buf, chip->ecc.size, - oob, sas, NULL, 0, + for (i = 0; i < chip->ecc.steps; i++) { + ecc_chunk = buf + chip->ecc.size * i; + + mtd_ooblayout_ecc(mtd, i, &ecc); + ecc_bytes = chip->oob_poi + ecc.offset; + + ret = nand_check_erased_ecc_chunk(ecc_chunk, chip->ecc.size, + ecc_bytes, ecc.length, + NULL, 0, chip->ecc.strength); if (ret < 0) return ret; diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c index 1054cc070747..20b0ee174dc6 100644 --- a/drivers/mtd/nand/raw/fsl_upm.c +++ b/drivers/mtd/nand/raw/fsl_upm.c @@ -62,7 +62,6 @@ static int fun_chip_ready(struct nand_chip *chip) static void fun_wait_rnb(struct fsl_upm_nand *fun) { if (fun->rnb_gpio[fun->mchip_number] >= 0) { - struct mtd_info *mtd = nand_to_mtd(&fun->chip); int cnt = 1000000; while (--cnt && !fun_chip_ready(&fun->chip)) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index fc49e13d81ec..ee4afa17d8a3 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -707,7 +707,7 @@ static int marvell_nfc_wait_op(struct nand_chip *chip, unsigned int timeout_ms) * In case the interrupt was not served in the required time frame, * check if the ISR was not served or if something went actually wrong. */ - if (ret && !pending) { + if (!ret && !pending) { dev_err(nfc->dev, "Timeout waiting for RB signal\n"); return -ETIMEDOUT; } @@ -2664,7 +2664,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, ret = mtd_device_register(mtd, NULL, 0); if (ret) { dev_err(dev, "failed to register mtd device: %d\n", ret); - nand_release(chip); + nand_cleanup(chip); return ret; } @@ -2673,6 +2673,16 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, return 0; } +static void marvell_nand_chips_cleanup(struct marvell_nfc *nfc) +{ + struct marvell_nand_chip *entry, *temp; + + list_for_each_entry_safe(entry, temp, &nfc->chips, node) { + nand_release(&entry->chip); + list_del(&entry->node); + } +} + static int marvell_nand_chips_init(struct device *dev, struct marvell_nfc *nfc) { struct device_node *np = dev->of_node; @@ -2707,21 +2717,16 @@ static int marvell_nand_chips_init(struct device *dev, struct marvell_nfc *nfc) ret = marvell_nand_chip_init(dev, nfc, nand_np); if (ret) { of_node_put(nand_np); - return ret; + goto cleanup_chips; } } return 0; -} -static void marvell_nand_chips_cleanup(struct marvell_nfc *nfc) -{ - struct marvell_nand_chip *entry, *temp; +cleanup_chips: + marvell_nand_chips_cleanup(nfc); - list_for_each_entry_safe(entry, temp, &nfc->chips, node) { - nand_release(&entry->chip); - list_del(&entry->node); - } + return ret; } static int marvell_nfc_init_dma(struct marvell_nfc *nfc) diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c index f64b06a71dfa..f12b7a7844c9 100644 --- a/drivers/mtd/nand/raw/nand_timings.c +++ b/drivers/mtd/nand/raw/nand_timings.c @@ -314,10 +314,9 @@ int onfi_fill_data_interface(struct nand_chip *chip, /* microseconds -> picoseconds */ timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX; timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX; - timings->tR_max = 1000000ULL * 200000000ULL; - /* nanoseconds -> picoseconds */ - timings->tCCS_min = 1000UL * 500000; + timings->tR_max = 200000000; + timings->tCCS_min = 500000; } return 0; diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c index 30c51f772de6..504c4504300c 100644 --- a/drivers/mtd/nand/raw/oxnas_nand.c +++ b/drivers/mtd/nand/raw/oxnas_nand.c @@ -32,6 +32,7 @@ struct oxnas_nand_ctrl { void __iomem *io_base; struct clk *clk; struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS]; + unsigned int nchips; }; static uint8_t oxnas_nand_read_byte(struct nand_chip *chip) @@ -79,9 +80,9 @@ static int oxnas_nand_probe(struct platform_device *pdev) struct nand_chip *chip; struct mtd_info *mtd; struct resource *res; - int nchips = 0; int count = 0; int err = 0; + int i; /* Allocate memory for the device structure (and zero it) */ oxnas = devm_kzalloc(&pdev->dev, sizeof(*oxnas), @@ -116,7 +117,7 @@ static int oxnas_nand_probe(struct platform_device *pdev) GFP_KERNEL); if (!chip) { err = -ENOMEM; - goto err_clk_unprepare; + goto err_release_child; } chip->controller = &oxnas->base; @@ -137,20 +138,20 @@ static int oxnas_nand_probe(struct platform_device *pdev) /* Scan to find existence of the device */ err = nand_scan(chip, 1); if (err) - goto err_clk_unprepare; + goto err_release_child; err = mtd_device_register(mtd, NULL, 0); if (err) { nand_release(chip); - goto err_clk_unprepare; + goto err_release_child; } - oxnas->chips[nchips] = chip; - ++nchips; + oxnas->chips[oxnas->nchips] = chip; + ++oxnas->nchips; } /* Exit if no chips found */ - if (!nchips) { + if (!oxnas->nchips) { err = -ENODEV; goto err_clk_unprepare; } @@ -159,6 +160,15 @@ static int oxnas_nand_probe(struct platform_device *pdev) return 0; +err_release_child: + of_node_put(nand_np); + + for (i = 0; i < oxnas->nchips; i++) { + chip = oxnas->chips[i]; + WARN_ON(mtd_device_unregister(nand_to_mtd(chip))); + nand_cleanup(chip); + } + err_clk_unprepare: clk_disable_unprepare(oxnas->clk); return err; @@ -167,9 +177,13 @@ err_clk_unprepare: static int oxnas_nand_remove(struct platform_device *pdev) { struct oxnas_nand_ctrl *oxnas = platform_get_drvdata(pdev); + struct nand_chip *chip; + int i; - if (oxnas->chips[0]) - nand_release(oxnas->chips[0]); + for (i = 0; i < oxnas->nchips; i++) { + chip = oxnas->chips[i]; + nand_release(chip); + } clk_disable_unprepare(oxnas->clk); diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 7bb9a7e8e1e7..c1c53b02b35f 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -459,11 +459,13 @@ struct qcom_nand_host { * among different NAND controllers. * @ecc_modes - ecc mode for NAND * @is_bam - whether NAND controller is using BAM + * @is_qpic - whether NAND CTRL is part of qpic IP * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset */ struct qcom_nandc_props { u32 ecc_modes; bool is_bam; + bool is_qpic; u32 dev_cmd_reg_start; }; @@ -2751,7 +2753,8 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc) u32 nand_ctrl; /* kill onenand */ - nandc_write(nandc, SFLASHC_BURST_CFG, 0); + if (!nandc->props->is_qpic) + nandc_write(nandc, SFLASHC_BURST_CFG, 0); nandc_write(nandc, dev_cmd_reg_addr(nandc, NAND_DEV_CMD_VLD), NAND_DEV_CMD_VLD_VAL); @@ -3007,12 +3010,14 @@ static const struct qcom_nandc_props ipq806x_nandc_props = { static const struct qcom_nandc_props ipq4019_nandc_props = { .ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT), .is_bam = true, + .is_qpic = true, .dev_cmd_reg_start = 0x0, }; static const struct qcom_nandc_props ipq8074_nandc_props = { .ecc_modes = (ECC_BCH_4BIT | ECC_BCH_8BIT), .is_bam = true, + .is_qpic = true, .dev_cmd_reg_start = 0x7000, }; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 23024742040a..350d960a3839 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4885,15 +4885,19 @@ int bond_create(struct net *net, const char *name) bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); + if (res < 0) { + free_netdev(bond_dev); + rtnl_unlock(); + + return res; + } netif_carrier_off(bond_dev); bond_work_init_all(bond); rtnl_unlock(); - if (res < 0) - free_netdev(bond_dev); - return res; + return 0; } static int __net_init bond_net_init(struct net *net) diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index b24cce48ae35..c3dfbd26b62b 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -447,11 +447,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, return err; err = register_netdevice(bond_dev); - - netif_carrier_off(bond_dev); if (!err) { struct bonding *bond = netdev_priv(bond_dev); + netif_carrier_off(bond_dev); bond_work_init_all(bond); } diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 13e66297b65f..f788b826e4aa 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -15,6 +15,7 @@ #include <linux/can/led.h> #include <linux/can/dev.h> #include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/can/platform/rcar_can.h> #include <linux/of.h> @@ -864,7 +865,9 @@ static int __maybe_unused rcar_can_suspend(struct device *dev) writew(ctlr, &priv->regs->ctlr); priv->can.state = CAN_STATE_SLEEPING; - clk_disable(priv->clk); + if(__clk_is_enabled(priv->clk)) + clk_disable(priv->clk); + return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 8ec5678085b0..40dbe94bf9eb 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1009,23 +1009,6 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port, PORT_MIRROR_SNIFFER, false); } -static void ksz9477_phy_setup(struct ksz_device *dev, int port, - struct phy_device *phy) -{ - /* Only apply to port with PHY. */ - if (port >= dev->phy_port_cnt) - return; - - /* The MAC actually cannot run in 1000 half-duplex mode. */ - phy_remove_link_mode(phy, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - - /* PHY does not support gigabit. */ - if (!(dev->features & GBIT_SUPPORT)) - phy_remove_link_mode(phy, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT); -} - static bool ksz9477_get_gbit(struct ksz_device *dev, u8 data) { bool gbit; @@ -1567,7 +1550,6 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { .get_port_addr = ksz9477_get_port_addr, .cfg_port_member = ksz9477_cfg_port_member, .flush_dyn_mac_table = ksz9477_flush_dyn_mac_table, - .phy_setup = ksz9477_phy_setup, .port_setup = ksz9477_port_setup, .r_mib_cnt = ksz9477_r_mib_cnt, .r_mib_pkt = ksz9477_r_mib_pkt, @@ -1581,7 +1563,29 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { int ksz9477_switch_register(struct ksz_device *dev) { - return ksz_switch_register(dev, &ksz9477_dev_ops); + int ret, i; + struct phy_device *phydev; + + ret = ksz_switch_register(dev, &ksz9477_dev_ops); + if (ret) + return ret; + + for (i = 0; i < dev->phy_port_cnt; ++i) { + if (!dsa_is_user_port(dev->ds, i)) + continue; + + phydev = dsa_to_port(dev->ds, i)->slave->phydev; + + /* The MAC actually cannot run in 1000 half-duplex mode. */ + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + + /* PHY does not support gigabit. */ + if (!(dev->features & GBIT_SUPPORT)) + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + } + return ret; } EXPORT_SYMBOL(ksz9477_switch_register); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index db91b213eae1..158644e592d2 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -373,7 +373,6 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) /* setup slave port */ dev->dev_ops->port_setup(dev, port, false); - dev->dev_ops->phy_setup(dev, port, phy); /* port_stp_state_set() will be called after to enable the port so * there is no need to do anything. diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h index b52e5ca17ab4..ef3156df7d58 100644 --- a/drivers/net/dsa/microchip/ksz_priv.h +++ b/drivers/net/dsa/microchip/ksz_priv.h @@ -136,8 +136,6 @@ struct ksz_dev_ops { u32 (*get_port_addr)(int port, int offset); void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); - void (*phy_setup)(struct ksz_device *dev, int port, - struct phy_device *phy); void (*port_cleanup)(struct ksz_device *dev, int port); void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 2e8b1ab2c6f7..d8b2d1310029 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2844,7 +2844,6 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_egress_floods = mv88e6352_port_set_egress_floods, .port_set_ether_type = mv88e6351_port_set_ether_type, - .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting, .port_pause_limit = mv88e6097_port_pause_limit, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index ac88caca5ad4..1368816abaed 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -43,18 +43,26 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, int ret; int i; + dev_dbg(smi->dev, + "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", + vid, member, untag); + /* Update the 4K table */ ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); if (ret) return ret; - vlan4k.member = member; - vlan4k.untag = untag; + vlan4k.member |= member; + vlan4k.untag |= untag; vlan4k.fid = fid; ret = smi->ops->set_vlan_4k(smi, &vlan4k); if (ret) return ret; + dev_dbg(smi->dev, + "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; @@ -65,11 +73,16 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, if (vid == vlanmc.vid) { /* update the MC entry */ - vlanmc.member = member; - vlanmc.untag = untag; + vlanmc.member |= member; + vlanmc.untag |= untag; vlanmc.fid = fid; ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + + dev_dbg(smi->dev, + "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", + vid, vlanmc.member, vlanmc.untag); + break; } } @@ -384,7 +397,7 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) dev_err(smi->dev, "port is DSA or CPU port\n"); - for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { int pvid_val = 0; dev_info(smi->dev, "add VLAN %04x\n", vid); @@ -407,13 +420,13 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port, if (ret < 0) return; } - } - ret = rtl8366_set_vlan(smi, port, member, untag, 0); - if (ret) - dev_err(smi->dev, - "failed to set up VLAN %04x", - vid); + ret = rtl8366_set_vlan(smi, vid, member, untag, 0); + if (ret) + dev_err(smi->dev, + "failed to set up VLAN %04x", + vid); + } } EXPORT_SYMBOL_GPL(rtl8366_vlan_add); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 0f140a9fe404..9cf8add34e6c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -776,7 +776,7 @@ static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self, int err = 0; if (count > (HW_ATL_A0_MAC_MAX - HW_ATL_A0_MAC_MIN)) { - err = EBADRQC; + err = -EBADRQC; goto err_exit; } for (self->aq_nic_cfg->mc_list_count = 0U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index bf6673aab7a4..06838a38a246 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -1581,7 +1581,7 @@ void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location, for (i = 0; i < 4; ++i) aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_SRCA_ADR(location + i), - ipv6_src[i]); + ipv6_src[3 - i]); } void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location, @@ -1592,7 +1592,7 @@ void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location, for (i = 0; i < 4; ++i) aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location + i), - ipv6_dest[i]); + ipv6_dest[3 - i]); } u32 hw_atl_sem_ram_get(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 436e98980012..6fec1da7c409 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -2546,7 +2546,7 @@ */ /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */ -#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053B0 + (location) * 0x4) +#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053D0 + (location) * 0x4) /* Bitmask for bitfield l3_da0[1F:0] */ #define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu /* Inverted bitmask for bitfield l3_da0[1F:0] */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 214cd635bfdd..3503699ef205 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1630,8 +1630,11 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (epause->tx_pause) link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX; - if (netif_running(dev)) + if (netif_running(dev)) { + mutex_lock(&bp->link_lock); rc = bnxt_hwrm_set_pause(bp); + mutex_unlock(&bp->link_lock); + } return rc; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 0ec4ea47f966..aef87ba68aec 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3697,7 +3697,7 @@ static int at91ether_open(struct net_device *dev) ret = at91ether_start(dev); if (ret) - return ret; + goto pm_exit; /* Enable MAC interrupts */ macb_writel(lp, IER, MACB_BIT(RCOMP) | @@ -3714,6 +3714,10 @@ static int at91ether_open(struct net_device *dev) netif_start_queue(dev); return 0; + +pm_exit: + pm_runtime_put_sync(&lp->pdev->dev); + return ret; } /* Close the interface */ diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 43d11c38b38a..4cddd628d41b 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1167,7 +1167,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct) oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) & CN23XX_PCIE_SRIOV_FDL_MASK); } else { - ret = EINVAL; + ret = -EINVAL; /* Under some virtual environments, extended PCI regs are * inaccessible, in which case the above read will have failed. diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 40a44dcb3d9b..5c45c0c6dd23 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2047,11 +2047,11 @@ static void nicvf_set_rx_mode_task(struct work_struct *work_arg) /* Save message data locally to prevent them from * being overwritten by next ndo_set_rx_mode call(). */ - spin_lock(&nic->rx_mode_wq_lock); + spin_lock_bh(&nic->rx_mode_wq_lock); mode = vf_work->mode; mc = vf_work->mc; vf_work->mc = NULL; - spin_unlock(&nic->rx_mode_wq_lock); + spin_unlock_bh(&nic->rx_mode_wq_lock); __nicvf_set_rx_mode_task(mode, mc, nic); } @@ -2185,6 +2185,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) nic->max_queues *= 2; nic->ptp_clock = ptp_clock; + /* Initialize mutex that serializes usage of VF's mailbox */ + mutex_init(&nic->rx_mode_mtx); + /* MAP VF's configuration registers */ nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); if (!nic->reg_base) { @@ -2261,7 +2264,6 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); spin_lock_init(&nic->rx_mode_wq_lock); - mutex_init(&nic->rx_mode_mtx); err = register_netdev(netdev); if (err) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 506170fe3a8b..049f1bbe27ab 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2441,6 +2441,7 @@ static inline int uld_send(struct adapter *adap, struct sk_buff *skb, txq_info = adap->sge.uld_txq_info[tx_uld_type]; if (unlikely(!txq_info)) { WARN_ON(true); + kfree_skb(skb); return NET_XMIT_DROP; } diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index bd385c1927f2..d39f6ed0c235 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2448,6 +2448,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); + clk_disable_unprepare(port->pclk); return PTR_ERR(port->reset); } reset_control_reset(port->reset); @@ -2503,8 +2504,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); - if (ret) + if (ret) { + clk_disable_unprepare(port->pclk); return ret; + } ret = register_netdev(netdev); if (!ret) { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ecf9cc1ffafa..1315cc42c88f 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2802,7 +2802,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) } /* Do this here, so we can be verbose early */ - SET_NETDEV_DEV(net_dev, dev->parent); + SET_NETDEV_DEV(net_dev, dev); dev_set_drvdata(dev, net_dev); priv = netdev_priv(net_dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 3f16661cfc47..c977c58dd3df 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1947,7 +1947,7 @@ close: free: fsl_mc_object_free(dpcon); - return NULL; + return ERR_PTR(err); } static void free_dpcon(struct dpaa2_eth_priv *priv, @@ -1971,8 +1971,8 @@ alloc_channel(struct dpaa2_eth_priv *priv) return NULL; channel->dpcon = setup_dpcon(priv); - if (IS_ERR_OR_NULL(channel->dpcon)) { - err = PTR_ERR_OR_ZERO(channel->dpcon); + if (IS_ERR(channel->dpcon)) { + err = PTR_ERR(channel->dpcon); goto err_setup; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 78287c517095..32c1e9533b14 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -880,6 +880,7 @@ static int enetc_pf_probe(struct pci_dev *pdev, return 0; err_reg_netdev: + enetc_mdio_remove(pf); enetc_of_put_phy(priv); enetc_free_msix(priv); err_alloc_msix: diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 21d8023535ae..eba7e54ecf85 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -1396,8 +1396,7 @@ static void enable_time_stamp(struct fman *fman) { struct fman_fpm_regs __iomem *fpm_rg = fman->fpm_regs; u16 fm_clk_freq = fman->state->fm_clk_freq; - u32 tmp, intgr, ts_freq; - u64 frac; + u32 tmp, intgr, ts_freq, frac; ts_freq = (u32)(1 << fman->state->count1_micro_bit); /* configure timestamp so that bit 8 will count 1 microsecond diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 1ca543ac8f2c..d2de9ea80c43 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1205,7 +1205,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) list_for_each(pos, &dtsec->multicast_addr_hash->lsts[bucket]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; @@ -1218,7 +1218,7 @@ int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) list_for_each(pos, &dtsec->unicast_addr_hash->lsts[bucket]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/freescale/fman/fman_mac.h b/drivers/net/ethernet/freescale/fman/fman_mac.h index dd6d0526f6c1..19f327efdaff 100644 --- a/drivers/net/ethernet/freescale/fman/fman_mac.h +++ b/drivers/net/ethernet/freescale/fman/fman_mac.h @@ -252,7 +252,7 @@ static inline struct eth_hash_t *alloc_hash_table(u16 size) struct eth_hash_t *hash; /* Allocate address hash table */ - hash = kmalloc_array(size, sizeof(struct eth_hash_t *), GFP_KERNEL); + hash = kmalloc(sizeof(*hash), GFP_KERNEL); if (!hash) return NULL; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index e1901874c19f..9088b4f4b4b8 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -856,7 +856,6 @@ int memac_set_tx_pause_frames(struct fman_mac *memac, u8 priority, tmp = ioread32be(®s->command_config); tmp &= ~CMD_CFG_PFC_MODE; - priority = 0; iowrite32be(tmp, ®s->command_config); @@ -986,7 +985,7 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) list_for_each(pos, &memac->multicast_addr_hash->lsts[hash]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index ee82ee1384eb..47f6fee1f396 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1756,6 +1756,7 @@ static int fman_port_probe(struct platform_device *of_dev) struct fman_port *port; struct fman *fman; struct device_node *fm_node, *port_node; + struct platform_device *fm_pdev; struct resource res; struct resource *dev_res; u32 val; @@ -1780,8 +1781,14 @@ static int fman_port_probe(struct platform_device *of_dev) goto return_err; } - fman = dev_get_drvdata(&of_find_device_by_node(fm_node)->dev); + fm_pdev = of_find_device_by_node(fm_node); of_node_put(fm_node); + if (!fm_pdev) { + err = -EINVAL; + goto return_err; + } + + fman = dev_get_drvdata(&fm_pdev->dev); if (!fman) { err = -EINVAL; goto return_err; diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index f75b9c11b2d2..ac5a281e0ec3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -630,7 +630,7 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) list_for_each(pos, &tgec->multicast_addr_hash->lsts[hash]) { hash_entry = ETH_HASH_ENTRY_OBJ(pos); - if (hash_entry->addr == addr) { + if (hash_entry && hash_entry->addr == addr) { list_del_init(&hash_entry->node); kfree(hash_entry); break; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 0178de087fc0..537caba74107 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -77,6 +77,7 @@ ((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num) enum hns_desc_type { + DESC_TYPE_UNKNOWN, DESC_TYPE_SKB, DESC_TYPE_PAGE, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 6cf51b828c6e..5132431fe372 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1263,6 +1263,10 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) unsigned int i; for (i = 0; i < ring->desc_num; i++) { + struct hns3_desc *desc = &ring->desc[ring->next_to_use]; + + memset(desc, 0, sizeof(*desc)); + /* check if this is where we started */ if (ring->next_to_use == next_to_use_orig) break; @@ -1270,6 +1274,9 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) /* rollback one */ ring_ptr_move_bw(ring, next_to_use); + if (!ring->desc_cb[ring->next_to_use].dma) + continue; + /* unmap the descriptor dma address */ if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB) dma_unmap_single(dev, @@ -1284,6 +1291,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) ring->desc_cb[ring->next_to_use].length = 0; ring->desc_cb[ring->next_to_use].dma = 0; + ring->desc_cb[ring->next_to_use].type = DESC_TYPE_UNKNOWN; } } @@ -3941,8 +3949,8 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) return; if (linkup) { - netif_carrier_on(netdev); netif_tx_wake_all_queues(netdev); + netif_carrier_on(netdev); if (netif_msg_link(handle)) netdev_info(netdev, "link up\n"); } else { diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e16ebdeb38da..44fb5d25efd0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3063,7 +3063,7 @@ req_rx_irq_failed: req_tx_irq_failed: for (j = 0; j < i; j++) { free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - irq_dispose_mapping(adapter->rx_scrq[j]->irq); + irq_dispose_mapping(adapter->tx_scrq[j]->irq); } release_sub_crqs(adapter, 1); return rc; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a7e52e33c90a..879ade3adefc 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6205,9 +6205,18 @@ static void igb_reset_task(struct work_struct *work) struct igb_adapter *adapter; adapter = container_of(work, struct igb_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igb_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igb_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index e332e82fc066..d82aa27e947d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -43,7 +43,7 @@ struct qmem { void *base; dma_addr_t iova; int alloc_sz; - u8 entry_sz; + u16 entry_sz; u8 align; u32 qsize; }; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 7e88446ac97a..0b88fb96503f 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -203,7 +203,7 @@ io_error: static inline u16 gm_phy_read(struct sky2_hw *hw, unsigned port, u16 reg) { - u16 v; + u16 v = 0; __gm_phy_read(hw, port, reg, &v); return v; } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index b4ed7b65b108..260229138208 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4312,12 +4312,14 @@ end: static void mlx4_shutdown(struct pci_dev *pdev) { struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); mutex_unlock(&persist->interface_state_mutex); + mlx4_pci_disable_device(dev); } static const struct pci_error_handlers mlx4_err_handler = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5f33074d4094..392d14031362 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -438,7 +438,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -483,7 +483,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -2889,6 +2889,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; } +static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, + enum mlx5_port_status state) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int vport_admin_state; + + mlx5_set_port_admin_status(mdev, state); + + if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == SRIOV_OFFLOADS) + return; + + if (state == MLX5_PORT_UP) + vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO; + else + vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN; + + mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state); +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -2921,7 +2940,7 @@ int mlx5e_open(struct net_device *netdev) mutex_lock(&priv->state_lock); err = mlx5e_open_locked(netdev); if (!err) - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); if (mlx5_vxlan_allowed(priv->mdev->vxlan)) @@ -2958,7 +2977,7 @@ int mlx5e_close(struct net_device *netdev) return -ENODEV; mutex_lock(&priv->state_lock); - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN); err = mlx5e_close_locked(netdev); mutex_unlock(&priv->state_lock); @@ -4898,7 +4917,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) /* Marking the link as currently not needed by the Driver */ if (!netif_running(netdev)) - mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN); mlx5e_set_netdev_mtu_boundaries(priv); mlx5e_set_dev_port_mtu(priv); @@ -5071,6 +5090,8 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + cancel_work_sync(&priv->update_stats_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 23f843dd92dc..e6515fcb548b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1692,6 +1692,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work, mlx5e_tc_reoffload_flows_work); + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 76ffde866979..3fcc53a6b2dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1957,6 +1957,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT; + int other_vport = 1; int err = 0; if (!ESW_ALLOWED(esw)) @@ -1964,15 +1966,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, if (IS_ERR(evport)) return PTR_ERR(evport); + if (vport == MLX5_VPORT_UPLINK) { + opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK; + other_vport = 0; + vport = 0; + } mutex_lock(&esw->state_lock); - err = mlx5_modify_vport_admin_state(esw->dev, - MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, 1, link_state); + err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state); if (err) { - mlx5_core_warn(esw->dev, - "Failed to set vport %d link state, err = %d", - vport, err); + mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d", + vport, opmod, err); goto unlock; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d043d6f9797d..5df1759b2b9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -498,6 +498,8 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} static inline int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; } static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {} static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; } +static inline +int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } #define FDB_MAX_CHAIN 1 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 7ec97307c214..53f43c576d56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -778,18 +778,15 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root = find_root(&prio->node); struct mlx5_flow_table *iter; - int i = 0; int err; fs_for_each_ft(iter, prio) { - i++; err = root->cmds->modify_flow_table(root, iter, ft); if (err) { - mlx5_core_warn(dev, "Failed to modify flow table %d\n", - iter->id); + mlx5_core_err(dev, + "Failed to modify flow table id %d, type %d, err %d\n", + iter->id, iter->type, err); /* The driver is out of sync with the FW */ - if (i > 1) - WARN_ON(true); return err; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 0059b290e095..d08155d67bcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -371,10 +371,31 @@ static int mlx5_ptp_enable(struct ptp_clock_info *ptp, return 0; } +enum { + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN = BIT(0), + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT = BIT(1), +}; + static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, enum ptp_pin_function func, unsigned int chan) { - return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + switch (func) { + case PTP_PF_NONE: + return 0; + case PTP_PF_EXTTS: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN); + case PTP_PF_PEROUT: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT); + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; } static const struct ptp_clock_info mlx5_ptp_clock_info = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 09eb0b56a50f..758bcd299aff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -593,7 +593,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener, mlxsw_core); if (err) - return err; + goto err_trap_register; err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core); if (err) @@ -605,6 +605,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) err_emad_trap_set: mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener, mlxsw_core); +err_trap_register: destroy_workqueue(mlxsw_core->emad_wq); return err; } @@ -1476,7 +1477,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core, err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans, bulk_list, cb, cb_priv, tid); if (err) { - kfree(trans); + kfree_rcu(trans, rcu); return err; } return 0; @@ -1701,11 +1702,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, break; } } - rcu_read_unlock(); - if (!found) + if (!found) { + rcu_read_unlock(); goto drop; + } rxl->func(skb, local_port, rxl_item->priv); + rcu_read_unlock(); return; drop: diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 96f7a9818294..5245ffb0a806 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1318,19 +1318,21 @@ static int nixge_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT); err = nixge_of_get_resources(pdev); if (err) - return err; + goto free_netdev; __nixge_hw_set_mac_address(ndev); priv->tx_irq = platform_get_irq_byname(pdev, "tx"); if (priv->tx_irq < 0) { netdev_err(ndev, "could not find 'tx' irq"); - return priv->tx_irq; + err = priv->tx_irq; + goto free_netdev; } priv->rx_irq = platform_get_irq_byname(pdev, "rx"); if (priv->rx_irq < 0) { netdev_err(ndev, "could not find 'rx' irq"); - return priv->rx_irq; + err = priv->rx_irq; + goto free_netdev; } priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index d8c95101809f..ea27220d6b14 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2073,8 +2073,8 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn, num_srqs = min_t(u32, QED_RDMA_MAX_SRQS, p_params->num_srqs); if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) { - DP_NOTICE(p_hwfn, - "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n"); + DP_VERBOSE(p_hwfn, QED_MSG_SP, + "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n"); p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 70fef2df165f..ede2d1cc4c8a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -2151,7 +2151,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) } /* Log and clear previous pglue_b errors if such exist */ - qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt); + qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt, true); /* Enable the PF's internal FID_enable in the PXP */ rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt, diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 70a771cd8788..7f871d2b1217 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -256,9 +256,10 @@ out: #define PGLUE_ATTENTION_ZLR_VALID (1 << 25) #define PGLUE_ATTENTION_ILT_VALID (1 << 23) -int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt) +int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool hw_init) { + char msg[256]; u32 tmp; tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2); @@ -272,22 +273,23 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, details = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS); - DP_NOTICE(p_hwfn, - "Illegal write by chip to [%08x:%08x] blocked.\n" - "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n" - "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n", - addr_hi, addr_lo, details, - (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID), - (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID), - GET_FIELD(details, - PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0, - tmp, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0); + snprintf(msg, sizeof(msg), + "Illegal write by chip to [%08x:%08x] blocked.\n" + "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n" + "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]", + addr_hi, addr_lo, details, + (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID), + (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID), + !!GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VF_VALID), + tmp, + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR), + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME), + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN)); + + if (hw_init) + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg); + else + DP_NOTICE(p_hwfn, "%s\n", msg); } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2); @@ -320,8 +322,14 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL); - if (tmp & PGLUE_ATTENTION_ICPL_VALID) - DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp); + if (tmp & PGLUE_ATTENTION_ICPL_VALID) { + snprintf(msg, sizeof(msg), "ICPL error - %08x", tmp); + + if (hw_init) + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg); + else + DP_NOTICE(p_hwfn, "%s\n", msg); + } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS); if (tmp & PGLUE_ATTENTION_ZLR_VALID) { @@ -360,7 +368,7 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn) { - return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt); + return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt, false); } #define QED_DORQ_ATTENTION_REASON_MASK (0xfffff) @@ -1172,7 +1180,8 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn) index, attn_bits, attn_acks, asserted_bits, deasserted_bits, p_sb_attn_sw->known_attn); } else if (asserted_bits == 0x100) { - DP_INFO(p_hwfn, "MFW indication via attention\n"); + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, + "MFW indication via attention\n"); } else { DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "MFW indication [deassertion]\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index d473b522afc5..ba5cfebf2d0d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -431,7 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, #define QED_MAPPING_MEMORY_SIZE(dev) (NUM_OF_SBS(dev)) -int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt); +int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool hw_init); #endif diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 59c2349b59df..b02536fb21fb 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -485,13 +485,24 @@ static int emac_clks_phase1_init(struct platform_device *pdev, ret = clk_prepare_enable(adpt->clk[EMAC_CLK_CFG_AHB]); if (ret) - return ret; + goto disable_clk_axi; ret = clk_set_rate(adpt->clk[EMAC_CLK_HIGH_SPEED], 19200000); if (ret) - return ret; + goto disable_clk_cfg_ahb; + + ret = clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]); + if (ret) + goto disable_clk_cfg_ahb; - return clk_prepare_enable(adpt->clk[EMAC_CLK_HIGH_SPEED]); + return 0; + +disable_clk_cfg_ahb: + clk_disable_unprepare(adpt->clk[EMAC_CLK_CFG_AHB]); +disable_clk_axi: + clk_disable_unprepare(adpt->clk[EMAC_CLK_AXI]); + + return ret; } /* Enable clocks; needs emac_clks_phase1_init to be called before */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 393644833cd5..972074776651 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1450,6 +1450,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) struct ravb_private *priv = container_of(work, struct ravb_private, work); struct net_device *ndev = priv->ndev; + int error; netif_tx_stop_all_queues(ndev); @@ -1458,15 +1459,36 @@ static void ravb_tx_timeout_work(struct work_struct *work) ravb_ptp_stop(ndev); /* Wait for DMA stopping */ - ravb_stop_dma(ndev); + if (ravb_stop_dma(ndev)) { + /* If ravb_stop_dma() fails, the hardware is still operating + * for TX and/or RX. So, this should not call the following + * functions because ravb_dmac_init() is possible to fail too. + * Also, this should not retry ravb_stop_dma() again and again + * here because it's possible to wait forever. So, this just + * re-enables the TX and RX and skip the following + * re-initialization procedure. + */ + ravb_rcv_snd_enable(ndev); + goto out; + } ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); /* Device init */ - ravb_dmac_init(ndev); + error = ravb_dmac_init(ndev); + if (error) { + /* If ravb_dmac_init() fails, descriptors are freed. So, this + * should return here to avoid re-enabling the TX and RX in + * ravb_emac_init(). + */ + netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n", + __func__, error); + return; + } ravb_emac_init(ndev); +out: /* Initialise PTP Clock driver */ if (priv->chip_id == RCAR_GEN2) ravb_ptp_init(ndev, priv->pdev); diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 601e76ad99a0..24182dd3d38c 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2275,7 +2275,7 @@ static int smc_drv_probe(struct platform_device *pdev) ret = try_toggle_control_gpio(&pdev->dev, &lp->power_gpio, "power", 0, 0, 100); if (ret) - return ret; + goto out_free_netdev; /* * Optional reset GPIO configured? Minimum 100 ns reset needed @@ -2284,7 +2284,7 @@ static int smc_drv_probe(struct platform_device *pdev) ret = try_toggle_control_gpio(&pdev->dev, &lp->reset_gpio, "reset", 0, 0, 100); if (ret) - return ret; + goto out_free_netdev; /* * Need to wait for optional EEPROM to load, max 750 us according diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index f4924a435fcd..6a102885fcfd 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1191,7 +1191,7 @@ static int ave_init(struct net_device *ndev) ret = regmap_update_bits(priv->regmap, SG_ETPINMODE, priv->pinmode_mask, priv->pinmode_val); if (ret) - return ret; + goto out_reset_assert; ave_global_reset(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index bc0e2fe71682..db3264d374f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -350,6 +350,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) plat_dat->has_gmac = true; plat_dat->bsp_priv = gmac; plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed; + plat_dat->multicast_filter_bins = 0; err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (err) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 81af0f3f5cf9..054e79a36b5a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -166,6 +166,9 @@ static void dwmac1000_set_filter(struct mac_device_info *hw, value = GMAC_FRAME_FILTER_PR; } else if (dev->flags & IFF_ALLMULTI) { value = GMAC_FRAME_FILTER_PM; /* pass all multi */ + } else if (!netdev_mc_empty(dev) && (mcbitslog2 == 0)) { + /* Fall back to all multicast if we've no filter */ + value = GMAC_FRAME_FILTER_PM; } else if (!netdev_mc_empty(dev)) { struct netdev_hw_addr *ha; diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 5b196ebfed49..d75892169737 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -283,8 +283,8 @@ spider_net_free_chain(struct spider_net_card *card, descr = descr->next; } while (descr != chain->ring); - dma_free_coherent(&card->pdev->dev, chain->num_desc, - chain->hwring, chain->dma_addr); + dma_free_coherent(&card->pdev->dev, chain->num_desc * sizeof(struct spider_net_hw_descr), + chain->hwring, chain->dma_addr); } /** diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 7b9350dbebdd..dd6393394bab 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1244,7 +1244,7 @@ static int rr_open(struct net_device *dev) rrpriv->info = NULL; } if (rrpriv->rx_ctrl) { - pci_free_consistent(pdev, sizeof(struct ring_ctrl), + pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl), rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); rrpriv->rx_ctrl = NULL; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 15447151ddc4..b61d895b6a63 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -531,12 +531,13 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) u32 hash; struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT]; - /* if VF is present and up then redirect packets - * already called with rcu_read_lock_bh + /* If VF is present and up then redirect packets to it. + * Skip the VF if it is marked down or has no carrier. + * If netpoll is in uses, then VF can not be used either. */ vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev); if (vf_netdev && netif_running(vf_netdev) && - !netpoll_tx_running(net)) + netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net)) return netvsc_vf_xmit(net, vf_netdev, skb); /* We will atmost need two pages to describe the rndis diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index c9392d70e639..3cbdda5e06e5 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1269,7 +1269,7 @@ static int adf7242_probe(struct spi_device *spi) WQ_MEM_RECLAIM); if (unlikely(!lp->wqueue)) { ret = -ENOMEM; - goto err_hw_init; + goto err_alloc_wq; } ret = adf7242_hw_init(lp); @@ -1301,6 +1301,8 @@ static int adf7242_probe(struct spi_device *spi) return ret; err_hw_init: + destroy_workqueue(lp->wqueue); +err_alloc_wq: mutex_destroy(&lp->bmux); ieee802154_free_hw(lp->hw); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 533a182eefca..2a197cd22628 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -314,7 +314,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) rtnl_lock(); err = nsim_bpf_init(ns); if (err) - goto err_free_netdev; + goto err_rtnl_unlock; nsim_ipsec_init(ns); @@ -328,8 +328,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) err_ipsec_teardown: nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); +err_rtnl_unlock: rtnl_unlock(); -err_free_netdev: free_netdev(dev); return ERR_PTR(err); } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index cc786eea4a02..1205affd5caa 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1332,6 +1332,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V1; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: @@ -1339,6 +1340,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: @@ -1346,6 +1348,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: @@ -1353,6 +1356,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; default: return -ERANGE; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 4882f43b83d0..2ea37519c56b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -615,7 +615,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, if (c45_ids) dev->c45_ids = *c45_ids; dev->irq = bus->irq[addr]; + dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr); + device_initialize(&mdiodev->dev); dev->state = PHY_DOWN; @@ -649,10 +651,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, ret = phy_request_driver_module(dev, phy_id); } - if (!ret) { - device_initialize(&mdiodev->dev); - } else { - kfree(dev); + if (ret) { + put_device(&mdiodev->dev); dev = ERR_PTR(ret); } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index e9c187946cca..f64e9fcd5c4b 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -9,6 +9,12 @@ #include "sfp.h" +struct sfp_quirk { + const char *vendor; + const char *part; + void (*modes)(const struct sfp_eeprom_id *id, unsigned long *modes); +}; + /** * struct sfp_bus - internal representation of a sfp bus */ @@ -21,6 +27,7 @@ struct sfp_bus { const struct sfp_socket_ops *socket_ops; struct device *sfp_dev; struct sfp *sfp; + const struct sfp_quirk *sfp_quirk; const struct sfp_upstream_ops *upstream_ops; void *upstream; @@ -31,6 +38,71 @@ struct sfp_bus { bool started; }; +static void sfp_quirk_2500basex(const struct sfp_eeprom_id *id, + unsigned long *modes) +{ + phylink_set(modes, 2500baseX_Full); +} + +static const struct sfp_quirk sfp_quirks[] = { + { + // Alcatel Lucent G-010S-P can operate at 2500base-X, but + // incorrectly report 2500MBd NRZ in their EEPROM + .vendor = "ALCATELLUCENT", + .part = "G010SP", + .modes = sfp_quirk_2500basex, + }, { + // Alcatel Lucent G-010S-A can operate at 2500base-X, but + // report 3.2GBd NRZ in their EEPROM + .vendor = "ALCATELLUCENT", + .part = "3FE46541AA", + .modes = sfp_quirk_2500basex, + }, { + // Huawei MA5671A can operate at 2500base-X, but report 1.2GBd + // NRZ in their EEPROM + .vendor = "HUAWEI", + .part = "MA5671A", + .modes = sfp_quirk_2500basex, + }, +}; + +static size_t sfp_strlen(const char *str, size_t maxlen) +{ + size_t size, i; + + /* Trailing characters should be filled with space chars */ + for (i = 0, size = 0; i < maxlen; i++) + if (str[i] != ' ') + size = i + 1; + + return size; +} + +static bool sfp_match(const char *qs, const char *str, size_t len) +{ + if (!qs) + return true; + if (strlen(qs) != len) + return false; + return !strncmp(qs, str, len); +} + +static const struct sfp_quirk *sfp_lookup_quirk(const struct sfp_eeprom_id *id) +{ + const struct sfp_quirk *q; + unsigned int i; + size_t vs, ps; + + vs = sfp_strlen(id->base.vendor_name, ARRAY_SIZE(id->base.vendor_name)); + ps = sfp_strlen(id->base.vendor_pn, ARRAY_SIZE(id->base.vendor_pn)); + + for (i = 0, q = sfp_quirks; i < ARRAY_SIZE(sfp_quirks); i++, q++) + if (sfp_match(q->vendor, id->base.vendor_name, vs) && + sfp_match(q->part, id->base.vendor_pn, ps)) + return q; + + return NULL; +} /** * sfp_parse_port() - Parse the EEPROM base ID, setting the port type * @bus: a pointer to the &struct sfp_bus structure for the sfp module @@ -234,6 +306,9 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, phylink_set(modes, 1000baseX_Full); } + if (bus->sfp_quirk) + bus->sfp_quirk->modes(id, modes); + bitmap_or(support, support, modes, __ETHTOOL_LINK_MODE_MASK_NBITS); phylink_set(support, Autoneg); @@ -557,6 +632,8 @@ int sfp_module_insert(struct sfp_bus *bus, const struct sfp_eeprom_id *id) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); int ret = 0; + bus->sfp_quirk = sfp_lookup_quirk(id); + if (ops && ops->module_insert) ret = ops->module_insert(bus->upstream, id); @@ -570,6 +647,8 @@ void sfp_module_remove(struct sfp_bus *bus) if (ops && ops->module_remove) ops->module_remove(bus->upstream); + + bus->sfp_quirk = NULL; } EXPORT_SYMBOL_GPL(sfp_module_remove); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index a505b2ab88b8..cab6ae76156b 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1389,8 +1389,9 @@ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old) unsigned long flags; if (old) - hso_dbg(0x16, "Termios called with: cflags new[%d] - old[%d]\n", - tty->termios.c_cflag, old->c_cflag); + hso_dbg(0x16, "Termios called with: cflags new[%u] - old[%u]\n", + (unsigned int)tty->termios.c_cflag, + (unsigned int)old->c_cflag); /* the actual setup */ spin_lock_irqsave(&serial->serial_lock, flags); @@ -2259,12 +2260,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, minor = get_free_serial_index(); if (minor < 0) - goto exit; + goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, tty_drv, minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); + if (IS_ERR(serial->parent->dev)) + goto exit2; /* fill in specific data for later use */ serial->minor = minor; @@ -2309,6 +2312,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, return 0; exit: hso_serial_tty_unregister(serial); +exit2: hso_serial_common_free(serial); return -1; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 2f3ec2f985b9..c78cd0f5b922 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -377,10 +377,6 @@ struct lan78xx_net { struct tasklet_struct bh; struct delayed_work wq; - struct usb_host_endpoint *ep_blkin; - struct usb_host_endpoint *ep_blkout; - struct usb_host_endpoint *ep_intr; - int msg_enable; struct urb *urb_intr; @@ -2872,78 +2868,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) return NETDEV_TX_OK; } -static int -lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf) -{ - int tmp; - struct usb_host_interface *alt = NULL; - struct usb_host_endpoint *in = NULL, *out = NULL; - struct usb_host_endpoint *status = NULL; - - for (tmp = 0; tmp < intf->num_altsetting; tmp++) { - unsigned ep; - - in = NULL; - out = NULL; - status = NULL; - alt = intf->altsetting + tmp; - - for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) { - struct usb_host_endpoint *e; - int intr = 0; - - e = alt->endpoint + ep; - switch (e->desc.bmAttributes) { - case USB_ENDPOINT_XFER_INT: - if (!usb_endpoint_dir_in(&e->desc)) - continue; - intr = 1; - /* FALLTHROUGH */ - case USB_ENDPOINT_XFER_BULK: - break; - default: - continue; - } - if (usb_endpoint_dir_in(&e->desc)) { - if (!intr && !in) - in = e; - else if (intr && !status) - status = e; - } else { - if (!out) - out = e; - } - } - if (in && out) - break; - } - if (!alt || !in || !out) - return -EINVAL; - - dev->pipe_in = usb_rcvbulkpipe(dev->udev, - in->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->pipe_out = usb_sndbulkpipe(dev->udev, - out->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->ep_intr = status; - - return 0; -} - static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = NULL; int ret; int i; - ret = lan78xx_get_endpoints(dev, intf); - if (ret) { - netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", - ret); - return ret; - } - dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); pdata = (struct lan78xx_priv *)(dev->data[0]); @@ -3715,6 +3645,7 @@ static void lan78xx_stat_monitor(struct timer_list *t) static int lan78xx_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr; struct lan78xx_net *dev; struct net_device *netdev; struct usb_device *udev; @@ -3763,6 +3694,34 @@ static int lan78xx_probe(struct usb_interface *intf, mutex_init(&dev->stats.access_lock); + if (intf->cur_altsetting->desc.bNumEndpoints < 3) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); + ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in); + if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); + ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out); + if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) { + ret = -ENODEV; + goto out2; + } + + ep_intr = &intf->cur_altsetting->endpoint[2]; + if (!usb_endpoint_is_int_in(&ep_intr->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_intr = usb_rcvintpipe(dev->udev, + usb_endpoint_num(&ep_intr->desc)); + ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; @@ -3774,18 +3733,7 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->max_mtu = MAX_SINGLE_PACKET_SIZE; netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER); - dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0; - dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1; - dev->ep_intr = (intf->cur_altsetting)->endpoint + 2; - - dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); - dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); - - dev->pipe_intr = usb_rcvintpipe(dev->udev, - dev->ep_intr->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - period = dev->ep_intr->desc.bInterval; - + period = ep_intr->desc.bInterval; maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0); buf = kmalloc(maxp, GFP_KERNEL); if (buf) { @@ -3798,6 +3746,7 @@ static int lan78xx_probe(struct usb_interface *intf, usb_fill_int_urb(dev->urb_intr, dev->udev, dev->pipe_intr, buf, maxp, intr_complete, dev, period); + dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; } } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 7d2ca9174b8b..9348a2fa60e4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1369,6 +1369,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f6c3030e282f..54e7d7a8ea01 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1213,6 +1213,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; + rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; @@ -1225,12 +1226,15 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip: *idx += 1; } } + rcu_read_unlock(); } out: return err; @@ -2532,7 +2536,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = &rt->dst; skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM); - tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb); + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); @@ -2572,7 +2576,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM); - tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb); + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), @@ -2847,8 +2851,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ - if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f, true, true); + if (is_zero_ether_addr(f->eth_addr) && + f->vni == vxlan->cfg.vni) + continue; + vxlan_fdb_destroy(vxlan, f, true, true); } } spin_unlock_bh(&vxlan->hash_lock); diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index bf78073ee7fd..e2a83f4cd3bb 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -62,8 +62,10 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb) { unsigned char *ptr; - if (skb_cow(skb, 1)) + if (skb_cow(skb, 1)) { + kfree_skb(skb); return NET_RX_DROP; + } skb_push(skb, 1); skb_reset_network_header(skb); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 0f1217b506ad..996eb9c55b39 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -128,10 +128,12 @@ static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) { unsigned char *ptr; - skb_push(skb, 1); - - if (skb_cow(skb, 1)) + if (skb_cow(skb, 1)) { + kfree_skb(skb); return NET_RX_DROP; + } + + skb_push(skb, 1); ptr = skb->data; *ptr = X25_IFACE_DATA; @@ -155,6 +157,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, if (!netif_running(dev)) goto drop; + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) + goto drop; + switch (skb->data[0]) { case X25_IFACE_DATA: break; @@ -303,7 +311,7 @@ static void lapbeth_setup(struct net_device *dev) dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; - dev->hard_header_len = 3; + dev->hard_header_len = 0; dev->mtu = 1000; dev->addr_len = 0; } @@ -324,6 +332,15 @@ static int lapbeth_new_device(struct net_device *dev) if (!ndev) goto out; + /* When transmitting data: + * first this driver removes a pseudo header of 1 byte, + * then the lapb module prepends an LAPB header of at most 3 bytes, + * then this driver prepends a length field of 2 bytes, + * then the underlying Ethernet device prepends its own header. + */ + ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + + dev->needed_headroom; + lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index d78bc838d631..24923471360e 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl) netif_wake_queue(sl->dev); } -/* Send one completely decapsulated IP datagram to the IP layer. */ +/* Send an LAPB frame to the LAPB module to process. */ static void x25_asy_bump(struct x25_asy *sl) { @@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl) count = sl->rcount; dev->stats.rx_bytes += count; - skb = dev_alloc_skb(count+1); + skb = dev_alloc_skb(count); if (skb == NULL) { netdev_warn(sl->dev, "memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } - skb_push(skb, 1); /* LAPB internal control */ skb_put_data(skb, sl->rbuff, count); skb->protocol = x25_type_trans(skb, sl->dev); err = lapb_data_received(skb->dev, skb); @@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl) kfree_skb(skb); printk(KERN_DEBUG "x25_asy: data received err - %d\n", err); } else { - netif_rx(skb); dev->stats.rx_packets++; } } @@ -356,12 +354,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb, */ /* - * Called when I frame data arrives. We did the work above - throw it - * at the net layer. + * Called when I frame data arrive. We add a pseudo header for upper + * layers and pass it to upper layers. */ static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb) { + if (skb_cow(skb, 1)) { + kfree_skb(skb); + return NET_RX_DROP; + } + skb_push(skb, 1); + skb->data[0] = X25_IFACE_DATA; + + skb->protocol = x25_type_trans(skb, dev); + return netif_rx(skb); } @@ -657,7 +664,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s) switch (s) { case X25_END: if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && - sl->rcount > 2) + sl->rcount >= 2) x25_asy_bump(sl); clear_bit(SLF_ESCAPE, &sl->flags); sl->rcount = 0; diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c index e726acaf9e36..50ab8a300cf4 100644 --- a/drivers/net/wireless/ath/ath10k/htt_tx.c +++ b/drivers/net/wireless/ath/ath10k/htt_tx.c @@ -1513,7 +1513,9 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt, err_unmap_msdu: dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); err_free_msdu_id: + spin_lock_bh(&htt->tx_lock); ath10k_htt_tx_free_msdu_id(htt, msdu_id); + spin_unlock_bh(&htt->tx_lock); err: return res; } @@ -1720,7 +1722,9 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt, err_unmap_msdu: dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE); err_free_msdu_id: + spin_lock_bh(&htt->tx_lock); ath10k_htt_tx_free_msdu_id(htt, msdu_id); + spin_unlock_bh(&htt->tx_lock); err: return res; } diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c index b242085c3c16..ea0c22fa2378 100644 --- a/drivers/net/wireless/ath/ath10k/hw.c +++ b/drivers/net/wireless/ath/ath10k/hw.c @@ -1145,6 +1145,7 @@ static bool ath10k_qca99x0_rx_desc_msdu_limit_error(struct htt_rx_desc *rxd) const struct ath10k_hw_ops qca99x0_ops = { .rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes, .rx_desc_get_msdu_limit_error = ath10k_qca99x0_rx_desc_msdu_limit_error, + .is_rssi_enable = ath10k_htt_tx_rssi_enable, }; const struct ath10k_hw_ops qca6174_ops = { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index 39ac1bbb6cc0..7ca7afdd598e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -30,7 +30,7 @@ #define BRCMF_ARP_OL_PEER_AUTO_REPLY 0x00000008 #define BRCMF_BSS_INFO_VERSION 109 /* curr ver of brcmf_bss_info_le struct */ -#define BRCMF_BSS_RSSI_ON_CHANNEL 0x0002 +#define BRCMF_BSS_RSSI_ON_CHANNEL 0x0004 #define BRCMF_STA_BRCM 0x00000001 /* Running a Broadcom driver */ #define BRCMF_STA_WME 0x00000002 /* WMM association */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c index c22c49ae552e..834ddb34502d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c @@ -654,6 +654,7 @@ static inline int brcmf_fws_hanger_poppkt(struct brcmf_fws_hanger *h, static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q, int ifidx) { + struct brcmf_fws_hanger_item *hi; bool (*matchfn)(struct sk_buff *, void *) = NULL; struct sk_buff *skb; int prec; @@ -665,6 +666,9 @@ static void brcmf_fws_psq_flush(struct brcmf_fws_info *fws, struct pktq *q, skb = brcmu_pktq_pdeq_match(q, prec, matchfn, &ifidx); while (skb) { hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT); + hi = &fws->hanger.items[hslot]; + WARN_ON(skb != hi->pkt); + hi->state = BRCMF_FWS_HANGER_ITEM_STATE_FREE; brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb, true); brcmu_pkt_buf_free_skb(skb); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ea8df8f6a790..868560c10544 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -3696,7 +3696,11 @@ static void brcmf_sdio_bus_watchdog(struct brcmf_sdio *bus) if (bus->idlecount > bus->idletime) { brcmf_dbg(SDIO, "idle\n"); sdio_claim_host(bus->sdiodev->func1); - brcmf_sdio_wd_timer(bus, false); +#ifdef DEBUG + if (!BRCMF_FWCON_ON() || + bus->console_interval == 0) +#endif + brcmf_sdio_wd_timer(bus, false); bus->idlecount = 0; brcmf_sdio_bus_sleep(bus, true, false); sdio_release_host(bus->sdiodev->func1); diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c index 4f0bdf152938..ba005a13b923 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.c +++ b/drivers/net/wireless/intel/iwlegacy/common.c @@ -4286,8 +4286,8 @@ il_apm_init(struct il_priv *il) * power savings, even without L1. */ if (il->cfg->set_l0s) { - pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl); - if (lctl & PCI_EXP_LNKCTL_ASPM_L1) { + ret = pcie_capability_read_word(il->pci_dev, PCI_EXP_LNKCTL, &lctl); + if (!ret && (lctl & PCI_EXP_LNKCTL_ASPM_L1)) { /* L1-ASPM enabled; disable(!) L0S */ il_set_bit(il, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index bd6a571b3e28..e5b7f7e4cad4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1197,261 +1197,6 @@ static u8 rs_get_tid(struct ieee80211_hdr *hdr) return tid; } -void iwl_mvm_rs_init_wk(struct work_struct *wk) -{ - struct iwl_mvm_sta *mvmsta = container_of(wk, struct iwl_mvm_sta, - rs_init_wk); - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); - struct ieee80211_sta *sta; - - rcu_read_lock(); - - sta = rcu_dereference(mvmvif->mvm->fw_id_to_mac_id[mvmsta->sta_id]); - if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { - rcu_read_unlock(); - return; - } - - iwl_mvm_rs_rate_init(mvmvif->mvm, sta, mvmvif->phy_ctxt->channel->band, - true); - - rcu_read_unlock(); -} - -void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - int tid, struct ieee80211_tx_info *info, bool ndp) -{ - int legacy_success; - int retries; - int i; - struct iwl_lq_cmd *table; - u32 lq_hwrate; - struct rs_rate lq_rate, tx_resp_rate; - struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; - u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; - u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; - u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); - u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; - - /* Treat uninitialized rate scaling data same as non-existing. */ - if (!lq_sta) { - IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); - return; - } else if (!lq_sta->pers.drv) { - IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); - return; - } - - /* This packet was aggregated but doesn't carry status info */ - if ((info->flags & IEEE80211_TX_CTL_AMPDU) && - !(info->flags & IEEE80211_TX_STAT_AMPDU)) - return; - - if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, - &tx_resp_rate)) { - WARN_ON_ONCE(1); - return; - } - -#ifdef CONFIG_MAC80211_DEBUGFS - /* Disable last tx check if we are debugging with fixed rate but - * update tx stats */ - if (lq_sta->pers.dbg_fixed_rate) { - int index = tx_resp_rate.index; - enum rs_column column; - int attempts, success; - - column = rs_get_column_from_rate(&tx_resp_rate); - if (WARN_ONCE(column == RS_COLUMN_INVALID, - "Can't map rate 0x%x to column", - tx_resp_hwrate)) - return; - - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - attempts = info->status.ampdu_len; - success = info->status.ampdu_ack_len; - } else { - attempts = info->status.rates[0].count; - success = !!(info->flags & IEEE80211_TX_STAT_ACK); - } - - lq_sta->pers.tx_stats[column][index].total += attempts; - lq_sta->pers.tx_stats[column][index].success += success; - - IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", - tx_resp_hwrate, success, attempts); - return; - } -#endif - - if (time_after(jiffies, - (unsigned long)(lq_sta->last_tx + - (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { - IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); - schedule_work(&mvmsta->rs_init_wk); - return; - } - lq_sta->last_tx = jiffies; - - /* Ignore this Tx frame response if its initial rate doesn't match - * that of latest Link Quality command. There may be stragglers - * from a previous Link Quality command, but we're no longer interested - * in those; they're either from the "active" mode while we're trying - * to check "search" mode, or a prior "search" mode after we've moved - * to a new "search" mode (which might become the new "active" mode). - */ - table = &lq_sta->lq; - lq_hwrate = le32_to_cpu(table->rs_table[0]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* Here we actually compare this rate to the latest LQ command */ - if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { - IWL_DEBUG_RATE(mvm, - "tx resp color 0x%x does not match 0x%x\n", - lq_color, LQ_FLAG_COLOR_GET(table->flags)); - - /* - * Since rates mis-match, the last LQ command may have failed. - * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with - * ... driver. - */ - lq_sta->missed_rate_counter++; - if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { - lq_sta->missed_rate_counter = 0; - IWL_DEBUG_RATE(mvm, - "Too many rates mismatch. Send sync LQ. rs_state %d\n", - lq_sta->rs_state); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); - } - /* Regardless, ignore this status info for outdated rate */ - return; - } else - /* Rate did match, so reset the missed_rate_counter */ - lq_sta->missed_rate_counter = 0; - - if (!lq_sta->search_better_tbl) { - curr_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - } else { - curr_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - } - - if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { - IWL_DEBUG_RATE(mvm, - "Neither active nor search matches tx rate\n"); - tmp_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); - tmp_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); - rs_dump_rate(mvm, &lq_rate, "ACTUAL"); - - /* - * no matching table found, let's by-pass the data collection - * and continue to perform rate scale to find the rate table - */ - rs_stay_in_table(lq_sta, true); - goto done; - } - - /* - * Updating the frame history depends on whether packets were - * aggregated. - * - * For aggregation, all packets were transmitted at the same rate, the - * first index into rate scale table. - */ - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len, - reduced_txp); - - /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat - * it as a single frame loss as we don't want the success ratio - * to dip too quickly because a BA wasn't received. - * For TPC, there's no need for this optimisation since we want - * to recover very quickly from a bad power reduction and, - * therefore we'd like the success ratio to get an immediate hit - * when failing to get a BA, so we'd switch back to a lower or - * zero power reduction. When FW transmits agg with a rate - * different from the initial rate, it will not use reduced txp - * and will send BA notification twice (one empty with reduced - * txp equal to the value from LQ and one with reduced txp 0). - * We need to update counters for each txp level accordingly. - */ - if (info->status.ampdu_ack_len == 0) - info->status.ampdu_len = 1; - - rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, - tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len); - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += info->status.ampdu_ack_len; - lq_sta->total_failed += (info->status.ampdu_len - - info->status.ampdu_ack_len); - } - } else { - /* For legacy, update frame history with for each Tx retry. */ - retries = info->status.rates[0].count - 1; - /* HW doesn't send more than 15 retries */ - retries = min(retries, 15); - - /* The last transmission may have been successful */ - legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); - /* Collect data for each rate used during failed TX attempts */ - for (i = 0; i <= retries; ++i) { - lq_hwrate = le32_to_cpu(table->rs_table[i]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, - &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* - * Only collect stats if retried rate is in the same RS - * table as active/search. - */ - if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) - tmp_tbl = curr_tbl; - else if (rs_rate_column_match(&lq_rate, - &other_tbl->rate)) - tmp_tbl = other_tbl; - else - continue; - - rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success, - reduced_txp); - rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success); - } - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += legacy_success; - lq_sta->total_failed += retries + (1 - legacy_success); - } - } - /* The last TX rate is cached in lq_sta; it's set in if/else above */ - lq_sta->last_rate_n_flags = lq_hwrate; - IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); -done: - /* See if there's a better rate or modulation mode to try. */ - if (sta->supp_rates[info->band]) - rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); -} - /* * mac80211 sends us Tx status */ @@ -1473,15 +1218,8 @@ static void rs_drv_mac80211_tx_status(void *mvm_r, info->flags & IEEE80211_TX_CTL_NO_ACK) return; - /* If it's locked we are in middle of init flow - * just wait for next tx status to update the lq_sta data - */ - if (!mutex_trylock(&mvmsta->lq_sta.rs_drv.mutex)) - return; - iwl_mvm_rs_tx_status(mvm, sta, rs_get_tid(hdr), info, ieee80211_is_qos_nullfunc(hdr->frame_control)); - mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); } /* @@ -1614,6 +1352,18 @@ static void rs_set_expected_tpt_table(struct iwl_lq_sta *lq_sta, tbl->expected_tpt = rs_get_expected_tpt_table(lq_sta, column, rate->bw); } +/* rs uses two tables, one is active and the second is for searching better + * configuration. This function, according to the index of the currently + * active table returns the search table, which is located at the + * index complementary to 1 according to the active table (active = 1, + * search = 0 or active = 0, search = 1). + * Since lq_info is an arary of size 2, make sure index cannot be out of bounds. + */ +static inline u8 rs_search_tbl(u8 active_tbl) +{ + return (active_tbl ^ 1) & 1; +} + static s32 rs_get_best_rate(struct iwl_mvm *mvm, struct iwl_lq_sta *lq_sta, struct iwl_scale_tbl_info *tbl, /* "search" */ @@ -1961,9 +1711,9 @@ static int rs_switch_to_column(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum rs_column col_id) { - struct iwl_scale_tbl_info *tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); + struct iwl_scale_tbl_info *tbl = &lq_sta->lq_info[lq_sta->active_tbl]; struct iwl_scale_tbl_info *search_tbl = - &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; struct rs_rate *rate = &search_tbl->rate; const struct rs_tx_column *column = &rs_tx_columns[col_id]; const struct rs_tx_column *curr_column = &rs_tx_columns[tbl->column]; @@ -2371,7 +2121,7 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -2595,7 +2345,7 @@ lq_update: /* If new "search" mode was selected, set up in uCode table */ if (lq_sta->search_better_tbl) { /* Access the "search" table, clear its history. */ - tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; rs_rate_scale_clear_tbl_windows(mvm, tbl); /* Use new "search" start rate */ @@ -2938,7 +2688,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -3220,6 +2970,8 @@ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct ieee80211_supported_band *sband; unsigned long supp; /* must be unsigned long for for_each_set_bit */ + lockdep_assert_held(&mvmsta->lq_sta.rs_drv.pers.lock); + /* clear all non-persistent lq data */ memset(lq_sta, 0, offsetof(typeof(*lq_sta), pers)); @@ -3312,6 +3064,258 @@ static void rs_drv_rate_update(void *mvm_r, iwl_mvm_rs_rate_init(mvm, sta, sband->band, true); } +static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, + bool ndp) +{ + int legacy_success; + int retries; + int i; + struct iwl_lq_cmd *table; + u32 lq_hwrate; + struct rs_rate lq_rate, tx_resp_rate; + struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; + u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; + u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; + u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); + u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; + + /* Treat uninitialized rate scaling data same as non-existing. */ + if (!lq_sta) { + IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); + return; + } else if (!lq_sta->pers.drv) { + IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); + return; + } + + /* This packet was aggregated but doesn't carry status info */ + if ((info->flags & IEEE80211_TX_CTL_AMPDU) && + !(info->flags & IEEE80211_TX_STAT_AMPDU)) + return; + + if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, + &tx_resp_rate)) { + WARN_ON_ONCE(1); + return; + } + +#ifdef CONFIG_MAC80211_DEBUGFS + /* Disable last tx check if we are debugging with fixed rate but + * update tx stats + */ + if (lq_sta->pers.dbg_fixed_rate) { + int index = tx_resp_rate.index; + enum rs_column column; + int attempts, success; + + column = rs_get_column_from_rate(&tx_resp_rate); + if (WARN_ONCE(column == RS_COLUMN_INVALID, + "Can't map rate 0x%x to column", + tx_resp_hwrate)) + return; + + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + attempts = info->status.ampdu_len; + success = info->status.ampdu_ack_len; + } else { + attempts = info->status.rates[0].count; + success = !!(info->flags & IEEE80211_TX_STAT_ACK); + } + + lq_sta->pers.tx_stats[column][index].total += attempts; + lq_sta->pers.tx_stats[column][index].success += success; + + IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", + tx_resp_hwrate, success, attempts); + return; + } +#endif + + if (time_after(jiffies, + (unsigned long)(lq_sta->last_tx + + (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { + IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); + /* reach here only in case of driver RS, call directly + * the unlocked version + */ + rs_drv_rate_init(mvm, sta, info->band); + return; + } + lq_sta->last_tx = jiffies; + + /* Ignore this Tx frame response if its initial rate doesn't match + * that of latest Link Quality command. There may be stragglers + * from a previous Link Quality command, but we're no longer interested + * in those; they're either from the "active" mode while we're trying + * to check "search" mode, or a prior "search" mode after we've moved + * to a new "search" mode (which might become the new "active" mode). + */ + table = &lq_sta->lq; + lq_hwrate = le32_to_cpu(table->rs_table[0]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Here we actually compare this rate to the latest LQ command */ + if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { + IWL_DEBUG_RATE(mvm, + "tx resp color 0x%x does not match 0x%x\n", + lq_color, LQ_FLAG_COLOR_GET(table->flags)); + + /* Since rates mis-match, the last LQ command may have failed. + * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with + * ... driver. + */ + lq_sta->missed_rate_counter++; + if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { + lq_sta->missed_rate_counter = 0; + IWL_DEBUG_RATE(mvm, + "Too many rates mismatch. Send sync LQ. rs_state %d\n", + lq_sta->rs_state); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); + } + /* Regardless, ignore this status info for outdated rate */ + return; + } + + /* Rate did match, so reset the missed_rate_counter */ + lq_sta->missed_rate_counter = 0; + + if (!lq_sta->search_better_tbl) { + curr_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + other_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + } else { + curr_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + other_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + } + + if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { + IWL_DEBUG_RATE(mvm, + "Neither active nor search matches tx rate\n"); + tmp_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); + tmp_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); + rs_dump_rate(mvm, &lq_rate, "ACTUAL"); + + /* no matching table found, let's by-pass the data collection + * and continue to perform rate scale to find the rate table + */ + rs_stay_in_table(lq_sta, true); + goto done; + } + + /* Updating the frame history depends on whether packets were + * aggregated. + * + * For aggregation, all packets were transmitted at the same rate, the + * first index into rate scale table. + */ + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len, + reduced_txp); + + /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat + * it as a single frame loss as we don't want the success ratio + * to dip too quickly because a BA wasn't received. + * For TPC, there's no need for this optimisation since we want + * to recover very quickly from a bad power reduction and, + * therefore we'd like the success ratio to get an immediate hit + * when failing to get a BA, so we'd switch back to a lower or + * zero power reduction. When FW transmits agg with a rate + * different from the initial rate, it will not use reduced txp + * and will send BA notification twice (one empty with reduced + * txp equal to the value from LQ and one with reduced txp 0). + * We need to update counters for each txp level accordingly. + */ + if (info->status.ampdu_ack_len == 0) + info->status.ampdu_len = 1; + + rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, + tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len); + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += info->status.ampdu_ack_len; + lq_sta->total_failed += (info->status.ampdu_len - + info->status.ampdu_ack_len); + } + } else { + /* For legacy, update frame history with for each Tx retry. */ + retries = info->status.rates[0].count - 1; + /* HW doesn't send more than 15 retries */ + retries = min(retries, 15); + + /* The last transmission may have been successful */ + legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); + /* Collect data for each rate used during failed TX attempts */ + for (i = 0; i <= retries; ++i) { + lq_hwrate = le32_to_cpu(table->rs_table[i]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, + &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Only collect stats if retried rate is in the same RS + * table as active/search. + */ + if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) + tmp_tbl = curr_tbl; + else if (rs_rate_column_match(&lq_rate, + &other_tbl->rate)) + tmp_tbl = other_tbl; + else + continue; + + rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success, + reduced_txp); + rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success); + } + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += legacy_success; + lq_sta->total_failed += retries + (1 - legacy_success); + } + } + /* The last TX rate is cached in lq_sta; it's set in if/else above */ + lq_sta->last_rate_n_flags = lq_hwrate; + IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); +done: + /* See if there's a better rate or modulation mode to try. */ + if (sta->supp_rates[info->band]) + rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); +} + +void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, bool ndp) +{ + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + /* If it's locked we are in middle of init flow + * just wait for next tx status to update the lq_sta data + */ + if (!spin_trylock(&mvmsta->lq_sta.rs_drv.pers.lock)) + return; + + __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); +} + #ifdef CONFIG_MAC80211_DEBUGFS static void rs_build_rates_table_from_fixed(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq_cmd, @@ -4171,9 +4175,9 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, } else { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - mutex_lock(&mvmsta->lq_sta.rs_drv.mutex); + spin_lock(&mvmsta->lq_sta.rs_drv.pers.lock); rs_drv_rate_init(mvm, sta, band); - mutex_unlock(&mvmsta->lq_sta.rs_drv.mutex); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index 086f47e2a4f0..428642e66658 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -376,9 +376,6 @@ struct iwl_lq_sta { /* tx power reduce for this sta */ int tpc_reduce; - /* avoid races of reinit and update table from rx_tx */ - struct mutex mutex; - /* persistent fields - initialized only once - keep last! */ struct lq_sta_pers { #ifdef CONFIG_MAC80211_DEBUGFS @@ -393,6 +390,7 @@ struct iwl_lq_sta { s8 last_rssi; struct rs_rate_stats tx_stats[RS_COLUMN_COUNT][IWL_RATE_COUNT]; struct iwl_mvm *drv; + spinlock_t lock; /* for races in reinit/update table */ } pers; }; @@ -443,8 +441,6 @@ struct iwl_mvm_sta; int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, bool enable); -void iwl_mvm_rs_init_wk(struct work_struct *wk); - #ifdef CONFIG_IWLWIFI_DEBUGFS void iwl_mvm_reset_frame_stats(struct iwl_mvm *mvm); #endif diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 214d710e2baf..a2e03190e7e2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1690,9 +1690,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, if (iwl_mvm_has_tlc_offload(mvm)) iwl_mvm_rs_add_sta(mvm, mvm_sta); else - mutex_init(&mvm_sta->lq_sta.rs_drv.mutex); - - INIT_WORK(&mvm_sta->rs_init_wk, iwl_mvm_rs_init_wk); + spin_lock_init(&mvm_sta->lq_sta.rs_drv.pers.lock); iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant); @@ -1855,8 +1853,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, if (ret) return ret; - cancel_work_sync(&mvm_sta->rs_init_wk); - /* flush its queues here since we are freeing mvm_sta */ ret = iwl_mvm_flush_sta(mvm, mvm_sta, false, 0); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 223e1a2c8efb..d744ca656f2f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -421,7 +421,6 @@ struct iwl_mvm_sta { struct iwl_lq_sta_rs_fw rs_fw; struct iwl_lq_sta rs_drv; } lq_sta; - struct work_struct rs_init_wk; struct ieee80211_vif *vif; struct iwl_mvm_key_pn __rcu *ptk_pn[4]; struct iwl_mvm_rxq_dup_data *dup_data; diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h index f672bdf52cc1..2d9ec225aead 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.h +++ b/drivers/net/wireless/marvell/mwifiex/sdio.h @@ -36,9 +36,9 @@ #define SD8897_DEFAULT_FW_NAME "mrvl/sd8897_uapsta.bin" #define SD8887_DEFAULT_FW_NAME "mrvl/sd8887_uapsta.bin" #define SD8801_DEFAULT_FW_NAME "mrvl/sd8801_uapsta.bin" -#define SD8977_DEFAULT_FW_NAME "mrvl/sd8977_uapsta.bin" +#define SD8977_DEFAULT_FW_NAME "mrvl/sdsd8977_combo_v2.bin" #define SD8987_DEFAULT_FW_NAME "mrvl/sd8987_uapsta.bin" -#define SD8997_DEFAULT_FW_NAME "mrvl/sd8997_uapsta.bin" +#define SD8997_DEFAULT_FW_NAME "mrvl/sdsd8997_combo_v4.bin" #define BLOCK_MODE 1 #define BYTE_MODE 0 diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 24b33e20e7a9..ec34a429a97f 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -581,6 +581,11 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv, { struct host_cmd_ds_802_11_key_material *key = &resp->params.key_material; + int len; + + len = le16_to_cpu(key->key_param_set.key_len); + if (len > sizeof(key->key_param_set.key)) + return -EINVAL; if (le16_to_cpu(key->action) == HostCmd_ACT_GEN_SET) { if ((le16_to_cpu(key->key_param_set.key_info) & KEY_MCAST)) { @@ -594,9 +599,8 @@ static int mwifiex_ret_802_11_key_material_v1(struct mwifiex_private *priv, memset(priv->aes_key.key_param_set.key, 0, sizeof(key->key_param_set.key)); - priv->aes_key.key_param_set.key_len = key->key_param_set.key_len; - memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key, - le16_to_cpu(priv->aes_key.key_param_set.key_len)); + priv->aes_key.key_param_set.key_len = cpu_to_le16(len); + memcpy(priv->aes_key.key_param_set.key, key->key_param_set.key, len); return 0; } @@ -611,9 +615,14 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, struct host_cmd_ds_command *resp) { struct host_cmd_ds_802_11_key_material_v2 *key_v2; - __le16 len; + int len; key_v2 = &resp->params.key_material_v2; + + len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len); + if (len > WLAN_KEY_LEN_CCMP) + return -EINVAL; + if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) { if ((le16_to_cpu(key_v2->key_param_set.key_info) & KEY_MCAST)) { mwifiex_dbg(priv->adapter, INFO, "info: key: GTK is set\n"); @@ -629,10 +638,9 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0, WLAN_KEY_LEN_CCMP); priv->aes_key_v2.key_param_set.key_params.aes.key_len = - key_v2->key_param_set.key_params.aes.key_len; - len = priv->aes_key_v2.key_param_set.key_params.aes.key_len; + cpu_to_le16(len); memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key, - key_v2->key_param_set.key_params.aes.key, le16_to_cpu(len)); + key_v2->key_param_set.key_params.aes.key, len); return 0; } diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index 2dd5c091b02c..04f6f0bed7fe 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -209,7 +209,7 @@ void rtw_fw_send_ra_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) SET_RA_INFO_INIT_RA_LVL(h2c_pkt, si->init_ra_lv); SET_RA_INFO_SGI_EN(h2c_pkt, si->sgi_enable); SET_RA_INFO_BW_MODE(h2c_pkt, si->bw_mode); - SET_RA_INFO_LDPC(h2c_pkt, si->ldpc_en); + SET_RA_INFO_LDPC(h2c_pkt, !!si->ldpc_en); SET_RA_INFO_NO_UPDATE(h2c_pkt, no_update); SET_RA_INFO_VHT_EN(h2c_pkt, si->vht_enable); SET_RA_INFO_DIS_PT(h2c_pkt, disable_pt); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 3f2ab0ed9f43..d72b346d7307 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -505,8 +505,6 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) stbc_en = VHT_STBC_EN; if (sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC) ldpc_en = VHT_LDPC_EN; - if (sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80) - is_support_sgi = true; } else if (sta->ht_cap.ht_supported) { ra_mask |= (sta->ht_cap.mcs.rx_mask[1] << 20) | (sta->ht_cap.mcs.rx_mask[0] << 12); @@ -514,9 +512,6 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) stbc_en = HT_STBC_EN; if (sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING) ldpc_en = HT_LDPC_EN; - if (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20 || - sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40) - is_support_sgi = true; } if (efuse->hw_cap.nss == 1) @@ -558,12 +553,18 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) switch (sta->bandwidth) { case IEEE80211_STA_RX_BW_80: bw_mode = RTW_CHANNEL_WIDTH_80; + is_support_sgi = sta->vht_cap.vht_supported && + (sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80); break; case IEEE80211_STA_RX_BW_40: bw_mode = RTW_CHANNEL_WIDTH_40; + is_support_sgi = sta->ht_cap.ht_supported && + (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40); break; default: bw_mode = RTW_CHANNEL_WIDTH_20; + is_support_sgi = sta->ht_cap.ht_supported && + (sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20); break; } diff --git a/drivers/net/wireless/ti/wl1251/event.c b/drivers/net/wireless/ti/wl1251/event.c index 850864dbafa1..e6d426edab56 100644 --- a/drivers/net/wireless/ti/wl1251/event.c +++ b/drivers/net/wireless/ti/wl1251/event.c @@ -70,7 +70,7 @@ static int wl1251_event_ps_report(struct wl1251 *wl, break; } - return 0; + return ret; } static void wl1251_event_mbox_dump(struct event_mailbox *mbox) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 7370e06a0e4b..a2c59b2ba6cc 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -63,6 +63,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644); MODULE_PARM_DESC(max_queues, "Maximum number of queues per virtual interface"); +#define XENNET_TIMEOUT (5 * HZ) + static const struct ethtool_ops xennet_ethtool_ops; struct netfront_cb { @@ -1334,12 +1336,15 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); - xenbus_switch_state(dev, XenbusStateInitialising); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) != - XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != - XenbusStateUnknown); + do { + xenbus_switch_state(dev, XenbusStateInitialising); + err = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown, XENNET_TIMEOUT); + } while (!err); + return netdev; exit: @@ -2139,28 +2144,43 @@ static const struct attribute_group xennet_dev_group = { }; #endif /* CONFIG_SYSFS */ -static int xennet_remove(struct xenbus_device *dev) +static void xennet_bus_close(struct xenbus_device *dev) { - struct netfront_info *info = dev_get_drvdata(&dev->dev); - - dev_dbg(&dev->dev, "%s\n", dev->nodename); + int ret; - if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { + if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + return; + do { xenbus_switch_state(dev, XenbusStateClosing); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosing || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown); + ret = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosing || + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); + } while (!ret); + + if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + return; + do { xenbus_switch_state(dev, XenbusStateClosed); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosed || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown); - } + ret = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); + } while (!ret); +} + +static int xennet_remove(struct xenbus_device *dev) +{ + struct netfront_info *info = dev_get_drvdata(&dev->dev); + xennet_bus_close(dev); xennet_disconnect_backend(info); if (info->netdev->reg_state == NETREG_REGISTERED) diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 91d4d5b28a7d..ba6c486d6465 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -198,6 +198,7 @@ int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb, case S3FWRN5_MODE_FW: return s3fwrn5_fw_recv_frame(ndev, skb); default: + kfree_skb(skb); return -ENODEV; } } diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index a570f2263a42..bb1851133f28 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -461,14 +461,19 @@ void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) else dev_dbg(&nvdimm->dev, "overwrite completed\n"); - if (nvdimm->sec.overwrite_state) - sysfs_notify_dirent(nvdimm->sec.overwrite_state); + /* + * Mark the overwrite work done and update dimm security flags, + * then send a sysfs event notification to wake up userspace + * poll threads to picked up the changed state. + */ nvdimm->sec.overwrite_tmo = 0; clear_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags); clear_bit(NDD_WORK_PENDING, &nvdimm->flags); - put_device(&nvdimm->dev); nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER); nvdimm->sec.ext_state = nvdimm_security_state(nvdimm, NVDIMM_MASTER); + if (nvdimm->sec.overwrite_state) + sysfs_notify_dirent(nvdimm->sec.overwrite_state); + put_device(&nvdimm->dev); } void nvdimm_security_overwrite_query(struct work_struct *work) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 0a93a480c4f2..ec3c0f2ba405 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -167,14 +167,19 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) mutex_unlock(&ctrl->scan_lock); } +static bool nvme_path_is_disabled(struct nvme_ns *ns) +{ + return ns->ctrl->state != NVME_CTRL_LIVE || + test_bit(NVME_NS_ANA_PENDING, &ns->flags); +} + static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) { int found_distance = INT_MAX, fallback_distance = INT_MAX, distance; struct nvme_ns *found = NULL, *fallback = NULL, *ns; list_for_each_entry_rcu(ns, &head->list, siblings) { - if (ns->ctrl->state != NVME_CTRL_LIVE || - test_bit(NVME_NS_ANA_PENDING, &ns->flags)) + if (nvme_path_is_disabled(ns)) continue; if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) @@ -228,8 +233,7 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, for (ns = nvme_next_ns(head, old); ns != old; ns = nvme_next_ns(head, ns)) { - if (ns->ctrl->state != NVME_CTRL_LIVE || - test_bit(NVME_NS_ANA_PENDING, &ns->flags)) + if (nvme_path_is_disabled(ns)) continue; if (ns->ana_state == NVME_ANA_OPTIMIZED) { @@ -240,6 +244,17 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, fallback = ns; } + /* + * The loop above skips the current path for round-robin semantics. + * Fall back to the current path if either: + * - no other optimized path found and current is optimized, + * - no other usable path found and current is usable. + */ + if (!nvme_path_is_disabled(old) && + (old->ana_state == NVME_ANA_OPTIMIZED || + (!fallback && old->ana_state == NVME_ANA_NONOPTIMIZED))) + return old; + if (!fallback) return NULL; found = fallback; @@ -260,10 +275,13 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) struct nvme_ns *ns; ns = srcu_dereference(head->current_path[node], &head->srcu); - if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns) - ns = nvme_round_robin_path(head, node, ns); - if (unlikely(!ns || !nvme_path_is_optimized(ns))) - ns = __nvme_find_path(head, node); + if (unlikely(!ns)) + return __nvme_find_path(head, node); + + if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR) + return nvme_round_robin_path(head, node, ns); + if (unlikely(!nvme_path_is_optimized(ns))) + return __nvme_find_path(head, node); return ns; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a27cc8df10af..727fec79b6cf 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2970,6 +2970,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index bf29524cf347..ad17c79fd1e2 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -142,14 +142,6 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); static const struct blk_mq_ops nvme_rdma_mq_ops; static const struct blk_mq_ops nvme_rdma_admin_mq_ops; -/* XXX: really should move to a generic header sooner or later.. */ -static inline void put_unaligned_le24(u32 val, u8 *p) -{ - *p++ = val; - *p++ = val >> 8; - *p++ = val >> 16; -} - static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue) { return queue - queue->ctrl->queues; @@ -883,15 +875,20 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) ret = PTR_ERR(ctrl->ctrl.connect_q); goto out_free_tag_set; } - } else { - blk_mq_update_nr_hw_queues(&ctrl->tag_set, - ctrl->ctrl.queue_count - 1); } ret = nvme_rdma_start_io_queues(ctrl); if (ret) goto out_cleanup_connect_q; + if (!new) { + nvme_start_queues(&ctrl->ctrl); + nvme_wait_freeze(&ctrl->ctrl); + blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset, + ctrl->ctrl.queue_count - 1); + nvme_unfreeze(&ctrl->ctrl); + } + return 0; out_cleanup_connect_q: @@ -921,6 +918,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { if (ctrl->ctrl.queue_count > 1) { + nvme_start_freeze(&ctrl->ctrl); nvme_stop_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); if (ctrl->ctrl.tagset) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 4bf01f2cd3f3..8651b6cfd3ee 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1304,6 +1304,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, goto err_sock; } + /* Set 10 seconds timeout for icresp recvmsg */ + queue->sock->sk->sk_rcvtimeo = 10 * HZ; + queue->sock->sk->sk_allocation = GFP_ATOMIC; if (!qid) n = 0; @@ -1656,15 +1659,20 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) ret = PTR_ERR(ctrl->connect_q); goto out_free_tag_set; } - } else { - blk_mq_update_nr_hw_queues(ctrl->tagset, - ctrl->queue_count - 1); } ret = nvme_tcp_start_io_queues(ctrl); if (ret) goto out_cleanup_connect_q; + if (!new) { + nvme_start_queues(ctrl); + nvme_wait_freeze(ctrl); + blk_mq_update_nr_hw_queues(ctrl->tagset, + ctrl->queue_count - 1); + nvme_unfreeze(ctrl); + } + return 0; out_cleanup_connect_q: @@ -1763,6 +1771,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, { if (ctrl->queue_count <= 1) return; + nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); if (ctrl->tagset) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 36d906a7f70d..dc193526d4da 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -143,12 +143,6 @@ static int num_pages(int len) return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT); } -/* XXX: really should move to a generic header sooner or later.. */ -static inline u32 get_unaligned_le24(const u8 *p) -{ - return (u32)p[0] | (u32)p[1] << 8 | (u32)p[2] << 16; -} - static inline bool nvmet_rdma_need_data_in(struct nvmet_rdma_rsp *rsp) { return nvme_is_write(rsp->req.cmd) && diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 296668caf7e5..c18541db7c20 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -1277,7 +1277,7 @@ sba_ioc_init_pluto(struct parisc_device *sba, struct ioc *ioc, int ioc_num) ** (one that doesn't overlap memory or LMMIO space) in the ** IBASE and IMASK registers. */ - ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE); + ioc->ibase = READ_REG(ioc->ioc_hpa + IOC_IBASE) & ~0x1fffffULL; iova_space_size = ~(READ_REG(ioc->ioc_hpa + IOC_IMASK) & 0xFFFFFFFFUL) + 1; if ((ioc->ibase < 0xfed00000UL) && ((ioc->ibase + iova_space_size) > 0xfee00000UL)) { diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 2fccb5762c76..0914ddeae17f 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -204,17 +204,13 @@ EXPORT_SYMBOL(pci_bus_set_ops); static DECLARE_WAIT_QUEUE_HEAD(pci_cfg_wait); static noinline void pci_wait_cfg(struct pci_dev *dev) + __must_hold(&pci_lock) { - DECLARE_WAITQUEUE(wait, current); - - __add_wait_queue(&pci_cfg_wait, &wait); do { - set_current_state(TASK_UNINTERRUPTIBLE); raw_spin_unlock_irq(&pci_lock); - schedule(); + wait_event(pci_cfg_wait, !dev->block_cfg_access); raw_spin_lock_irq(&pci_lock); } while (dev->block_cfg_access); - __remove_wait_queue(&pci_cfg_wait, &wait); } /* Returns 0 on success, negative values indicate error. */ diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 495059d923f7..ff1170dd172d 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -322,12 +322,8 @@ void pci_bus_add_device(struct pci_dev *dev) dev->match_driver = true; retval = device_attach(&dev->dev); - if (retval < 0 && retval != -EPROBE_DEFER) { + if (retval < 0 && retval != -EPROBE_DEFER) pci_warn(dev, "device attach failed (%d)\n", retval); - pci_proc_detach_device(dev); - pci_remove_sysfs_dev_files(dev); - return; - } pci_dev_assign_added(dev, true); } diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index fbf7a006d854..a16994e59776 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -45,7 +45,13 @@ #define PCIE_CAP_CPL_TIMEOUT_DISABLE 0x10 #define PCIE20_PARF_PHY_CTRL 0x40 +#define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK GENMASK(20, 16) +#define PHY_CTRL_PHY_TX0_TERM_OFFSET(x) ((x) << 16) + #define PCIE20_PARF_PHY_REFCLK 0x4C +#define PHY_REFCLK_SSP_EN BIT(16) +#define PHY_REFCLK_USE_PAD BIT(12) + #define PCIE20_PARF_DBI_BASE_ADDR 0x168 #define PCIE20_PARF_SLV_ADDR_SPACE_SIZE 0x16C #define PCIE20_PARF_MHI_CLOCK_RESET_CTRL 0x174 @@ -76,6 +82,18 @@ #define DBI_RO_WR_EN 1 #define PERST_DELAY_US 1000 +/* PARF registers */ +#define PCIE20_PARF_PCS_DEEMPH 0x34 +#define PCS_DEEMPH_TX_DEEMPH_GEN1(x) ((x) << 16) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x) ((x) << 8) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x) ((x) << 0) + +#define PCIE20_PARF_PCS_SWING 0x38 +#define PCS_SWING_TX_SWING_FULL(x) ((x) << 8) +#define PCS_SWING_TX_SWING_LOW(x) ((x) << 0) + +#define PCIE20_PARF_CONFIG_BITS 0x50 +#define PHY_RX0_EQ(x) ((x) << 24) #define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE 0x358 #define SLV_ADDR_SPACE_SZ 0x10000000 @@ -275,6 +293,7 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; + struct device_node *node = dev->of_node; u32 val; int ret; @@ -319,9 +338,29 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) val &= ~BIT(0); writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34), + pcie->parf + PCIE20_PARF_PCS_DEEMPH); + writel(PCS_SWING_TX_SWING_FULL(120) | + PCS_SWING_TX_SWING_LOW(120), + pcie->parf + PCIE20_PARF_PCS_SWING); + writel(PHY_RX0_EQ(4), pcie->parf + PCIE20_PARF_CONFIG_BITS); + } + + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + /* set TX termination offset */ + val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); + val &= ~PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK; + val |= PHY_CTRL_PHY_TX0_TERM_OFFSET(7); + writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + } + /* enable external reference clock */ val = readl(pcie->parf + PCIE20_PARF_PHY_REFCLK); - val |= BIT(16); + val &= ~PHY_REFCLK_USE_PAD; + val |= PHY_REFCLK_SSP_EN; writel(val, pcie->parf + PCIE20_PARF_PHY_REFCLK); ret = reset_control_deassert(res->phy_reset); diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c index 97e251090b4f..0dfc778f40a7 100644 --- a/drivers/pci/controller/pcie-cadence-host.c +++ b/drivers/pci/controller/pcie-cadence-host.c @@ -102,6 +102,7 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) { struct cdns_pcie *pcie = &rc->pcie; u32 value, ctrl; + u32 id; /* * Set the root complex BAR configuration register: @@ -121,8 +122,12 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); /* Set root port configuration space */ - if (rc->vendor_id != 0xffff) - cdns_pcie_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id); + if (rc->vendor_id != 0xffff) { + id = CDNS_PCIE_LM_ID_VENDOR(rc->vendor_id) | + CDNS_PCIE_LM_ID_SUBSYS(rc->vendor_id); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + if (rc->device_id != 0xffff) cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index 04114352d0e7..8be0e8d880e4 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -14,6 +14,7 @@ #include <linux/bitops.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/regulator/consumer.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> @@ -154,6 +155,8 @@ struct rcar_pcie { struct list_head resources; int root_bus_nr; struct clk *bus_clk; + struct regulator *pcie3v3; /* 3.3V power supply */ + struct regulator *pcie1v8; /* 1.8V power supply */ struct rcar_msi msi; }; @@ -1126,6 +1129,36 @@ static const struct of_device_id rcar_pcie_of_match[] = { {}, }; +static int rcar_pcie_set_vpcie(struct rcar_pcie *pcie) +{ + struct device *dev = pcie->dev; + int err; + + if (!IS_ERR(pcie->pcie3v3)) { + err = regulator_enable(pcie->pcie3v3); + if (err) { + dev_err(dev, "fail to enable vpcie3v3 regulator\n"); + goto err_out; + } + } + + if (!IS_ERR(pcie->pcie1v8)) { + err = regulator_enable(pcie->pcie1v8); + if (err) { + dev_err(dev, "fail to enable vpcie1v8 regulator\n"); + goto err_disable_3v3; + } + } + + return 0; + +err_disable_3v3: + if (!IS_ERR(pcie->pcie3v3)) + regulator_disable(pcie->pcie3v3); +err_out: + return err; +} + static int rcar_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1144,6 +1177,31 @@ static int rcar_pcie_probe(struct platform_device *pdev) pcie->dev = dev; platform_set_drvdata(pdev, pcie); + pcie->pcie3v3 = devm_regulator_get_optional(dev, "pcie3v3"); + if (IS_ERR(pcie->pcie3v3)) { + if (PTR_ERR(pcie->pcie3v3) == -EPROBE_DEFER) { + pci_free_host_bridge(bridge); + return -EPROBE_DEFER; + } + dev_info(dev, "no pcie3v3 regulator found\n"); + } + + pcie->pcie1v8 = devm_regulator_get_optional(dev, "pcie1v8"); + if (IS_ERR(pcie->pcie1v8)) { + if (PTR_ERR(pcie->pcie1v8) == -EPROBE_DEFER) { + pci_free_host_bridge(bridge); + return -EPROBE_DEFER; + } + dev_info(dev, "no pcie1v8 regulator found\n"); + } + + err = rcar_pcie_set_vpcie(pcie); + if (err) { + dev_err(dev, "failed to set pcie regulators\n"); + pci_free_host_bridge(bridge); + return err; + } + err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, NULL); if (err) goto err_free_bridge; @@ -1229,6 +1287,12 @@ err_pm_disable: pci_free_resource_list(&pcie->resources); err_free_bridge: + if(!IS_ERR(pcie->pcie3v3)) + if (regulator_is_enabled(pcie->pcie3v3)) + regulator_disable(pcie->pcie3v3); + if(!IS_ERR(pcie->pcie1v8)) + if (regulator_is_enabled(pcie->pcie1v8)) + regulator_disable(pcie->pcie1v8); pci_free_host_bridge(bridge); return err; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index b3869951c0eb..6e60b4b1bf53 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -122,13 +122,21 @@ static struct acpiphp_context *acpiphp_grab_context(struct acpi_device *adev) struct acpiphp_context *context; acpi_lock_hp_context(); + context = acpiphp_get_context(adev); - if (!context || context->func.parent->is_going_away) { - acpi_unlock_hp_context(); - return NULL; + if (!context) + goto unlock; + + if (context->func.parent->is_going_away) { + acpiphp_put_context(context); + context = NULL; + goto unlock; } + get_bridge(context->func.parent); acpiphp_put_context(context); + +unlock: acpi_unlock_hp_context(); return context; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 11cba24e263c..4edfa4f5f65e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -796,7 +796,9 @@ static inline bool platform_pci_need_resume(struct pci_dev *dev) static inline bool platform_pci_bridge_d3(struct pci_dev *dev) { - return pci_platform_pm ? pci_platform_pm->bridge_d3(dev) : false; + if (pci_platform_pm && pci_platform_pm->bridge_d3) + return pci_platform_pm->bridge_d3(dev); + return false; } /** diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 72c705843347..676863722695 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1156,6 +1156,7 @@ static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp) cnt += sprintf(buffer + cnt, "[%s] ", policy_str[i]); else cnt += sprintf(buffer + cnt, "%s ", policy_str[i]); + cnt += sprintf(buffer + cnt, "\n"); return cnt; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f767375ed4a2..2984ff2e1ea6 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4353,6 +4353,8 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags) if (ACPI_FAILURE(status)) return -ENODEV; + acpi_put_table(header); + /* Filter out flags not applicable to multifunction */ acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC | PCI_ACS_DT); @@ -5116,7 +5118,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); */ static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - if (pdev->device == 0x7340 && pdev->revision != 0xc5) + if ((pdev->device == 0x7312 && pdev->revision != 0x00) || + (pdev->device == 0x7340 && pdev->revision != 0xc5)) return; pci_info(pdev, "disabling ATS\n"); @@ -5127,6 +5130,8 @@ static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); /* AMD Iceland dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); +/* AMD Navi10 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c index 8f8606b9bc9e..aca4570f78a8 100644 --- a/drivers/perf/arm-cci.c +++ b/drivers/perf/arm-cci.c @@ -1720,6 +1720,7 @@ static struct platform_driver cci_pmu_driver = { .driver = { .name = DRIVER_NAME, .of_match_table = arm_cci_pmu_matches, + .suppress_bind_attrs = true, }, .probe = cci_pmu_probe, .remove = cci_pmu_remove, diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c index 6fc0273b6129..336948b41bd1 100644 --- a/drivers/perf/arm-ccn.c +++ b/drivers/perf/arm-ccn.c @@ -1545,6 +1545,7 @@ static struct platform_driver arm_ccn_driver = { .driver = { .name = "arm-ccn", .of_match_table = arm_ccn_match, + .suppress_bind_attrs = true, }, .probe = arm_ccn_probe, .remove = arm_ccn_remove, diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c index 70968c8c09d7..4594e2ed13d5 100644 --- a/drivers/perf/arm_dsu_pmu.c +++ b/drivers/perf/arm_dsu_pmu.c @@ -759,6 +759,7 @@ static struct platform_driver dsu_pmu_driver = { .driver = { .name = DRVNAME, .of_match_table = of_match_ptr(dsu_pmu_of_match), + .suppress_bind_attrs = true, }, .probe = dsu_pmu_device_probe, .remove = dsu_pmu_device_remove, diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 10f335b64931..add1480bce73 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -715,6 +715,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) platform_set_drvdata(pdev, smmu_pmu); smmu_pmu->pmu = (struct pmu) { + .module = THIS_MODULE, .task_ctx_nr = perf_invalid_context, .pmu_enable = smmu_pmu_enable, .pmu_disable = smmu_pmu_disable, @@ -833,6 +834,7 @@ static void smmu_pmu_shutdown(struct platform_device *pdev) static struct platform_driver smmu_pmu_driver = { .driver = { .name = "arm-smmu-v3-pmcg", + .suppress_bind_attrs = true, }, .probe = smmu_pmu_probe, .remove = smmu_pmu_remove, diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 49b490925255..a6e0cccce3ba 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -1220,6 +1220,7 @@ static struct platform_driver arm_spe_pmu_driver = { .driver = { .name = DRVNAME, .of_match_table = of_match_ptr(arm_spe_pmu_of_match), + .suppress_bind_attrs = true, }, .probe = arm_spe_pmu_device_dt_probe, .remove = arm_spe_pmu_device_remove, diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index 6ad0823bcf23..9fc278620c28 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -383,6 +383,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev) ddrc_pmu->sccl_id, ddrc_pmu->index_id); ddrc_pmu->pmu = (struct pmu) { .name = name, + .module = THIS_MODULE, .task_ctx_nr = perf_invalid_context, .event_init = hisi_uncore_pmu_event_init, .pmu_enable = hisi_uncore_pmu_enable, @@ -421,6 +422,7 @@ static struct platform_driver hisi_ddrc_pmu_driver = { .driver = { .name = "hisi_ddrc_pmu", .acpi_match_table = ACPI_PTR(hisi_ddrc_pmu_acpi_match), + .suppress_bind_attrs = true, }, .probe = hisi_ddrc_pmu_probe, .remove = hisi_ddrc_pmu_remove, diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index cbc65451b248..2c2513de57d6 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -394,6 +394,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev) hha_pmu->sccl_id, hha_pmu->index_id); hha_pmu->pmu = (struct pmu) { .name = name, + .module = THIS_MODULE, .task_ctx_nr = perf_invalid_context, .event_init = hisi_uncore_pmu_event_init, .pmu_enable = hisi_uncore_pmu_enable, @@ -432,6 +433,7 @@ static struct platform_driver hisi_hha_pmu_driver = { .driver = { .name = "hisi_hha_pmu", .acpi_match_table = ACPI_PTR(hisi_hha_pmu_acpi_match), + .suppress_bind_attrs = true, }, .probe = hisi_hha_pmu_probe, .remove = hisi_hha_pmu_remove, diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 3bf9c820dc74..0991fc96ecc1 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -384,6 +384,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev) l3c_pmu->sccl_id, l3c_pmu->index_id); l3c_pmu->pmu = (struct pmu) { .name = name, + .module = THIS_MODULE, .task_ctx_nr = perf_invalid_context, .event_init = hisi_uncore_pmu_event_init, .pmu_enable = hisi_uncore_pmu_enable, @@ -422,6 +423,7 @@ static struct platform_driver hisi_l3c_pmu_driver = { .driver = { .name = "hisi_l3c_pmu", .acpi_match_table = ACPI_PTR(hisi_l3c_pmu_acpi_match), + .suppress_bind_attrs = true, }, .probe = hisi_l3c_pmu_probe, .remove = hisi_l3c_pmu_remove, diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index d06182fe14b8..3f7c02da5781 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -1032,6 +1032,7 @@ static struct platform_driver l2_cache_pmu_driver = { .driver = { .name = "qcom-l2cache-pmu", .acpi_match_table = ACPI_PTR(l2_cache_pmu_acpi_match), + .suppress_bind_attrs = true, }, .probe = l2_cache_pmu_probe, .remove = l2_cache_pmu_remove, diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c index 15b8c10c2b2b..fc4704cd7a27 100644 --- a/drivers/perf/qcom_l3_pmu.c +++ b/drivers/perf/qcom_l3_pmu.c @@ -814,6 +814,7 @@ static struct platform_driver qcom_l3_cache_pmu_driver = { .driver = { .name = "qcom-l3cache-pmu", .acpi_match_table = ACPI_PTR(qcom_l3_cache_pmu_acpi_match), + .suppress_bind_attrs = true, }, .probe = qcom_l3_cache_pmu_probe, }; diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c index 43d76c85da56..9e1c3c7eeba9 100644 --- a/drivers/perf/thunderx2_pmu.c +++ b/drivers/perf/thunderx2_pmu.c @@ -816,6 +816,7 @@ static struct platform_driver tx2_uncore_driver = { .driver = { .name = "tx2-uncore-pmu", .acpi_match_table = ACPI_PTR(tx2_uncore_acpi_match), + .suppress_bind_attrs = true, }, .probe = tx2_uncore_probe, .remove = tx2_uncore_remove, diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c index 3259e2ebeb39..30cb581db6d4 100644 --- a/drivers/perf/xgene_pmu.c +++ b/drivers/perf/xgene_pmu.c @@ -1983,6 +1983,7 @@ static struct platform_driver xgene_pmu_driver = { .name = "xgene-pmu", .of_match_table = xgene_pmu_of_match, .acpi_match_table = ACPI_PTR(xgene_pmu_acpi_match), + .suppress_bind_attrs = true, }, }; diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index 856927382248..e5842e48a5e0 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -545,13 +545,14 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work) struct sun4i_usb_phy_data *data = container_of(work, struct sun4i_usb_phy_data, detect.work); struct phy *phy0 = data->phys[0].phy; - struct sun4i_usb_phy *phy = phy_get_drvdata(phy0); + struct sun4i_usb_phy *phy; bool force_session_end, id_notify = false, vbus_notify = false; int id_det, vbus_det; - if (phy0 == NULL) + if (!phy0) return; + phy = phy_get_drvdata(phy0); id_det = sun4i_usb_phy0_get_id_det(data); vbus_det = sun4i_usb_phy0_get_vbus_det(data); diff --git a/drivers/phy/marvell/phy-armada38x-comphy.c b/drivers/phy/marvell/phy-armada38x-comphy.c index 3e00bc679d4e..10169b2a5968 100644 --- a/drivers/phy/marvell/phy-armada38x-comphy.c +++ b/drivers/phy/marvell/phy-armada38x-comphy.c @@ -41,6 +41,7 @@ struct a38x_comphy_lane { struct a38x_comphy { void __iomem *base; + void __iomem *conf; struct device *dev; struct a38x_comphy_lane lane[MAX_A38X_COMPHY]; }; @@ -54,6 +55,21 @@ static const u8 gbe_mux[MAX_A38X_COMPHY][MAX_A38X_PORTS] = { { 0, 0, 3 }, }; +static void a38x_set_conf(struct a38x_comphy_lane *lane, bool enable) +{ + struct a38x_comphy *priv = lane->priv; + u32 conf; + + if (priv->conf) { + conf = readl_relaxed(priv->conf); + if (enable) + conf |= BIT(lane->port); + else + conf &= ~BIT(lane->port); + writel(conf, priv->conf); + } +} + static void a38x_comphy_set_reg(struct a38x_comphy_lane *lane, unsigned int offset, u32 mask, u32 value) { @@ -97,6 +113,7 @@ static int a38x_comphy_set_mode(struct phy *phy, enum phy_mode mode, int sub) { struct a38x_comphy_lane *lane = phy_get_drvdata(phy); unsigned int gen; + int ret; if (mode != PHY_MODE_ETHERNET) return -EINVAL; @@ -115,13 +132,20 @@ static int a38x_comphy_set_mode(struct phy *phy, enum phy_mode mode, int sub) return -EINVAL; } + a38x_set_conf(lane, false); + a38x_comphy_set_speed(lane, gen, gen); - return a38x_comphy_poll(lane, COMPHY_STAT1, - COMPHY_STAT1_PLL_RDY_TX | - COMPHY_STAT1_PLL_RDY_RX, - COMPHY_STAT1_PLL_RDY_TX | - COMPHY_STAT1_PLL_RDY_RX); + ret = a38x_comphy_poll(lane, COMPHY_STAT1, + COMPHY_STAT1_PLL_RDY_TX | + COMPHY_STAT1_PLL_RDY_RX, + COMPHY_STAT1_PLL_RDY_TX | + COMPHY_STAT1_PLL_RDY_RX); + + if (ret == 0) + a38x_set_conf(lane, true); + + return ret; } static const struct phy_ops a38x_comphy_ops = { @@ -174,14 +198,21 @@ static int a38x_comphy_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&pdev->dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); priv->dev = &pdev->dev; priv->base = base; + /* Optional */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "conf"); + if (res) { + priv->conf = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->conf)) + return PTR_ERR(priv->conf); + } + for_each_available_child_of_node(pdev->dev.of_node, child) { struct phy *phy; int ret; diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index bfb22f868857..5087b7c44d55 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -111,6 +111,7 @@ struct rcar_gen3_chan { struct work_struct work; struct mutex lock; /* protects rphys[...].powered */ enum usb_dr_mode dr_mode; + int irq; bool extcon_host; bool is_otg_channel; bool uses_otg_pins; @@ -389,12 +390,38 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch) rcar_gen3_device_recognition(ch); } +static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch) +{ + struct rcar_gen3_chan *ch = _ch; + void __iomem *usb2_base = ch->base; + u32 status = readl(usb2_base + USB2_OBINTSTA); + irqreturn_t ret = IRQ_NONE; + + if (status & USB2_OBINT_BITS) { + dev_vdbg(ch->dev, "%s: %08x\n", __func__, status); + writel(USB2_OBINT_BITS, usb2_base + USB2_OBINTSTA); + rcar_gen3_device_recognition(ch); + ret = IRQ_HANDLED; + } + + return ret; +} + static int rcar_gen3_phy_usb2_init(struct phy *p) { struct rcar_gen3_phy *rphy = phy_get_drvdata(p); struct rcar_gen3_chan *channel = rphy->ch; void __iomem *usb2_base = channel->base; u32 val; + int ret; + + if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) { + INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); + ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq, + IRQF_SHARED, dev_name(channel->dev), channel); + if (ret < 0) + dev_err(channel->dev, "No irq handler (%d)\n", channel->irq); + } /* Initialize USB2 part */ val = readl(usb2_base + USB2_INT_ENABLE); @@ -433,6 +460,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p) val &= ~USB2_INT_ENABLE_UCOM_INTEN; writel(val, usb2_base + USB2_INT_ENABLE); + if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel)) + free_irq(channel->irq, channel); + return 0; } @@ -503,23 +533,6 @@ static const struct phy_ops rz_g1c_phy_usb2_ops = { .owner = THIS_MODULE, }; -static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch) -{ - struct rcar_gen3_chan *ch = _ch; - void __iomem *usb2_base = ch->base; - u32 status = readl(usb2_base + USB2_OBINTSTA); - irqreturn_t ret = IRQ_NONE; - - if (status & USB2_OBINT_BITS) { - dev_vdbg(ch->dev, "%s: %08x\n", __func__, status); - writel(USB2_OBINT_BITS, usb2_base + USB2_OBINTSTA); - rcar_gen3_device_recognition(ch); - ret = IRQ_HANDLED; - } - - return ret; -} - static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = { { .compatible = "renesas,usb2-phy-r8a77470", @@ -598,7 +611,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) struct phy_provider *provider; struct resource *res; const struct phy_ops *phy_usb2_ops; - int irq, ret = 0, i; + int ret = 0, i; if (!dev->of_node) { dev_err(dev, "This driver needs device tree\n"); @@ -614,16 +627,8 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) if (IS_ERR(channel->base)) return PTR_ERR(channel->base); - /* call request_irq for OTG */ - irq = platform_get_irq_optional(pdev, 0); - if (irq >= 0) { - INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); - irq = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq, - IRQF_SHARED, dev_name(dev), channel); - if (irq < 0) - dev_err(dev, "No irq handler (%d)\n", irq); - } - + /* get irq number here and request_irq for OTG in phy_init */ + channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { int ret; diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c index 646259bee909..f07edd80d2f3 100644 --- a/drivers/phy/samsung/phy-exynos5-usbdrd.c +++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c @@ -714,7 +714,9 @@ static int exynos5_usbdrd_phy_calibrate(struct phy *phy) struct phy_usb_instance *inst = phy_get_drvdata(phy); struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst); - return exynos5420_usbdrd_phy_calibrate(phy_drd); + if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) + return exynos5420_usbdrd_phy_calibrate(phy_drd); + return 0; } static const struct phy_ops exynos5_usbdrd_phy_ops = { diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 3e5760f1a715..d4a192df5fab 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -252,7 +252,7 @@ static const struct amd_pingroup kerncz_groups[] = { { .name = "uart0", .pins = uart0_pins, - .npins = 9, + .npins = 5, }, { .name = "uart1", diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index c8ef3b91a730..0e95c247def6 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -873,9 +873,9 @@ static void ingenic_gpio_irq_ack(struct irq_data *irqd) */ high = ingenic_gpio_get_value(jzgc, irq); if (high) - irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_FALLING); + irq_set_type(jzgc, irq, IRQ_TYPE_LEVEL_LOW); else - irq_set_type(jzgc, irq, IRQ_TYPE_EDGE_RISING); + irq_set_type(jzgc, irq, IRQ_TYPE_LEVEL_HIGH); } if (jzgc->jzpc->version >= ID_JZ4770) @@ -911,7 +911,7 @@ static int ingenic_gpio_irq_set_type(struct irq_data *irqd, unsigned int type) */ bool high = ingenic_gpio_get_value(jzgc, irqd->hwirq); - type = high ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING; + type = high ? IRQ_TYPE_LEVEL_LOW : IRQ_TYPE_LEVEL_HIGH; } irq_set_type(jzgc, irqd->hwirq, type); diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 1e0614daee9b..a9d511982780 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -916,7 +916,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np, /* If pinconf isn't supported, don't parse properties in below. */ if (!PCS_HAS_PINCONF) - return 0; + return -ENOTSUPP; /* cacluate how much properties are supported in current node */ for (i = 0; i < ARRAY_SIZE(prop2); i++) { @@ -928,7 +928,7 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np, nconfs++; } if (!nconfs) - return 0; + return -ENOTSUPP; func->conf = devm_kcalloc(pcs->dev, nconfs, sizeof(struct pcs_conf_vals), @@ -1056,9 +1056,12 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs, if (PCS_HAS_PINCONF && function) { res = pcs_parse_pinconf(pcs, np, function, map); - if (res) + if (res == 0) + *num_maps = 2; + else if (res == -ENOTSUPP) + *num_maps = 1; + else goto free_pingroups; - *num_maps = 2; } else { *num_maps = 1; } diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 76f77b06b63f..fec5a1e544e4 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -110,6 +110,16 @@ static struct quirk_entry quirk_asus_forceals = { .wmi_force_als_set = true, }; +static struct quirk_entry quirk_asus_ga401i = { + .wmi_backlight_power = true, + .wmi_backlight_set_devstate = true, +}; + +static struct quirk_entry quirk_asus_ga502i = { + .wmi_backlight_power = true, + .wmi_backlight_set_devstate = true, +}; + static int dmi_matched(const struct dmi_system_id *dmi) { pr_info("Identified laptop model '%s'\n", dmi->ident); @@ -402,6 +412,78 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_forceals, }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA401IH", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA401IH"), + }, + .driver_data = &quirk_asus_ga401i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA401II", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA401II"), + }, + .driver_data = &quirk_asus_ga401i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA401IU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA401IU"), + }, + .driver_data = &quirk_asus_ga401i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA401IV", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA401IV"), + }, + .driver_data = &quirk_asus_ga401i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA401IVC", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA401IVC"), + }, + .driver_data = &quirk_asus_ga401i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA502II", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA502II"), + }, + .driver_data = &quirk_asus_ga502i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA502IU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA502IU"), + }, + .driver_data = &quirk_asus_ga502i, + }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. GA502IV", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA502IV"), + }, + .driver_data = &quirk_asus_ga502i, + }, {}, }; diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 844e562eb4f7..820268cd0c8d 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -554,7 +554,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv) return AE_OK; if (acpi_match_device_ids(dev, ids) == 0) - if (acpi_create_platform_device(dev, NULL)) + if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL))) dev_info(&dev->dev, "intel-hid: created platform device\n"); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index d122f33d43ac..c7c8b432c163 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -272,7 +272,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv) return AE_OK; if (acpi_match_device_ids(dev, ids) == 0) - if (acpi_create_platform_device(dev, NULL)) + if (!IS_ERR_OR_NULL(acpi_create_platform_device(dev, NULL))) dev_info(&dev->dev, "intel-vbtn: created platform device\n"); diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 22f4b92c5da4..a719acac6031 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1307,7 +1307,7 @@ 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; } @@ -1361,7 +1361,7 @@ 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/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c index 5ca047b3f58f..23e7d6447ae9 100644 --- a/drivers/power/supply/88pm860x_battery.c +++ b/drivers/power/supply/88pm860x_battery.c @@ -433,7 +433,7 @@ static void pm860x_init_battery(struct pm860x_battery_info *info) int ret; int data; int bat_remove; - int soc; + int soc = 0; /* measure enable on GPADC1 */ data = MEAS1_GP1; @@ -496,7 +496,9 @@ static void pm860x_init_battery(struct pm860x_battery_info *info) } mutex_unlock(&info->lock); - calc_soc(info, OCV_MODE_ACTIVE, &soc); + ret = calc_soc(info, OCV_MODE_ACTIVE, &soc); + if (ret < 0) + goto out; data = pm860x_reg_read(info->i2c, PM8607_POWER_UP_LOG); bat_remove = data & BAT_WU_LOG; diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c index 31b01035d0ab..8cfba3614e60 100644 --- a/drivers/pwm/pwm-bcm-iproc.c +++ b/drivers/pwm/pwm-bcm-iproc.c @@ -85,8 +85,6 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm, u64 tmp, multi, rate; u32 value, prescale; - rate = clk_get_rate(ip->clk); - value = readl(ip->base + IPROC_PWM_CTRL_OFFSET); if (value & BIT(IPROC_PWM_CTRL_EN_SHIFT(pwm->hwpwm))) @@ -99,6 +97,13 @@ static void iproc_pwmc_get_state(struct pwm_chip *chip, struct pwm_device *pwm, else state->polarity = PWM_POLARITY_INVERSED; + rate = clk_get_rate(ip->clk); + if (rate == 0) { + state->period = 0; + state->duty_cycle = 0; + return; + } + value = readl(ip->base + IPROC_PWM_PRESCALE_OFFSET); prescale = value >> IPROC_PWM_PRESCALE_SHIFT(pwm->hwpwm); prescale &= IPROC_PWM_PRESCALE_MAX; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 25924af15449..cb5f33b97082 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -4880,7 +4880,10 @@ static int regulator_init_coupling(struct regulator_dev *rdev) if (!of_check_coupling_data(rdev)) return -EPERM; + mutex_lock(®ulator_list_mutex); rdev->coupling_desc.coupler = regulator_find_coupler(rdev); + mutex_unlock(®ulator_list_mutex); + if (IS_ERR(rdev->coupling_desc.coupler)) { err = PTR_ERR(rdev->coupling_desc.coupler); rdev_err(rdev, "failed to get coupler: %d\n", err); @@ -4926,7 +4929,6 @@ regulator_register(const struct regulator_desc *regulator_desc, struct regulator_dev *rdev; bool dangling_cfg_gpiod = false; bool dangling_of_gpiod = false; - bool reg_device_fail = false; struct device *dev; int ret, i; @@ -4976,6 +4978,7 @@ regulator_register(const struct regulator_desc *regulator_desc, ret = -ENOMEM; goto rinse; } + device_initialize(&rdev->dev); /* * Duplicate the config so the driver could override it after @@ -4983,13 +4986,23 @@ regulator_register(const struct regulator_desc *regulator_desc, */ config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL); if (config == NULL) { - kfree(rdev); ret = -ENOMEM; - goto rinse; + goto clean; } init_data = regulator_of_get_init_data(dev, regulator_desc, config, &rdev->dev.of_node); + + /* + * Sometimes not all resources are probed already so we need to take + * that into account. This happens most the time if the ena_gpiod comes + * from a gpio extender or something else. + */ + if (PTR_ERR(init_data) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto clean; + } + /* * We need to keep track of any GPIO descriptor coming from the * device tree until we have handled it over to the core. If the @@ -5046,6 +5059,7 @@ regulator_register(const struct regulator_desc *regulator_desc, rdev->dev.parent = dev; dev_set_name(&rdev->dev, "regulator.%lu", (unsigned long) atomic_inc_return(®ulator_no)); + dev_set_drvdata(&rdev->dev, rdev); /* set regulator constraints */ if (init_data) @@ -5068,9 +5082,7 @@ regulator_register(const struct regulator_desc *regulator_desc, if (ret < 0) goto wash; - mutex_lock(®ulator_list_mutex); ret = regulator_init_coupling(rdev); - mutex_unlock(®ulator_list_mutex); if (ret < 0) goto wash; @@ -5096,12 +5108,9 @@ regulator_register(const struct regulator_desc *regulator_desc, !rdev->desc->fixed_uV) rdev->is_switch = true; - dev_set_drvdata(&rdev->dev, rdev); - ret = device_register(&rdev->dev); - if (ret != 0) { - reg_device_fail = true; + ret = device_add(&rdev->dev); + if (ret != 0) goto unset_supplies; - } rdev_init_debugfs(rdev); @@ -5123,18 +5132,14 @@ unset_supplies: mutex_unlock(®ulator_list_mutex); wash: kfree(rdev->coupling_desc.coupled_rdevs); - kfree(rdev->constraints); mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); - if (reg_device_fail) - put_device(&rdev->dev); - else - kfree(rdev); kfree(config); + put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 921afd116f43..d0c2aecd2734 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -443,11 +443,20 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev, goto error; } - if (desc->of_parse_cb && desc->of_parse_cb(child, desc, config)) { - dev_err(dev, - "driver callback failed to parse DT for regulator %pOFn\n", - child); - goto error; + if (desc->of_parse_cb) { + int ret; + + ret = desc->of_parse_cb(child, desc, config); + if (ret) { + if (ret == -EPROBE_DEFER) { + of_node_put(child); + return ERR_PTR(-EPROBE_DEFER); + } + dev_err(dev, + "driver callback failed to parse DT for regulator %pOFn\n", + child); + goto error; + } } *node = child; diff --git a/drivers/remoteproc/qcom_q6v5.c b/drivers/remoteproc/qcom_q6v5.c index 0d33e3079f0d..ef61cb709acd 100644 --- a/drivers/remoteproc/qcom_q6v5.c +++ b/drivers/remoteproc/qcom_q6v5.c @@ -151,6 +151,8 @@ int qcom_q6v5_request_stop(struct qcom_q6v5 *q6v5) { int ret; + q6v5->running = false; + qcom_smem_state_update_bits(q6v5->state, BIT(q6v5->stop_bit), BIT(q6v5->stop_bit)); diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c index 99c7efb1f398..abdef10eadec 100644 --- a/drivers/remoteproc/qcom_q6v5_mss.c +++ b/drivers/remoteproc/qcom_q6v5_mss.c @@ -381,6 +381,12 @@ static int q6v5_load(struct rproc *rproc, const struct firmware *fw) { struct q6v5 *qproc = rproc->priv; + /* MBA is restricted to a maximum size of 1M */ + if (fw->size > qproc->mba_size || fw->size > SZ_1M) { + dev_err(qproc->dev, "MBA firmware load failed\n"); + return -EINVAL; + } + memcpy(qproc->mba_region, fw->data, fw->size); return 0; @@ -1028,15 +1034,14 @@ static int q6v5_mpss_load(struct q6v5 *qproc) } else if (phdr->p_filesz) { /* Replace "xxx.xxx" with "xxx.bxx" */ sprintf(fw_name + fw_name_len - 3, "b%02d", i); - ret = request_firmware(&seg_fw, fw_name, qproc->dev); + ret = request_firmware_into_buf(&seg_fw, fw_name, qproc->dev, + ptr, phdr->p_filesz); if (ret) { dev_err(qproc->dev, "failed to load %s\n", fw_name); iounmap(ptr); goto release_firmware; } - memcpy(ptr, seg_fw->data, seg_fw->size); - release_firmware(seg_fw); } diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index e1fe02477ea8..b60f88907269 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -319,7 +319,7 @@ dasd_diag_check_device(struct dasd_device *device) struct dasd_diag_characteristics *rdc_data; struct vtoc_cms_label *label; struct dasd_block *block; - struct dasd_diag_bio bio; + struct dasd_diag_bio *bio; unsigned int sb, bsize; blocknum_t end_block; int rc; @@ -395,29 +395,36 @@ dasd_diag_check_device(struct dasd_device *device) rc = -ENOMEM; goto out; } + bio = kzalloc(sizeof(*bio), GFP_KERNEL); + if (bio == NULL) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "No memory to allocate initialization bio"); + rc = -ENOMEM; + goto out_label; + } rc = 0; end_block = 0; /* try all sizes - needed for ECKD devices */ for (bsize = 512; bsize <= PAGE_SIZE; bsize <<= 1) { mdsk_init_io(device, bsize, 0, &end_block); - memset(&bio, 0, sizeof (struct dasd_diag_bio)); - bio.type = MDSK_READ_REQ; - bio.block_number = private->pt_block + 1; - bio.buffer = label; + memset(bio, 0, sizeof(*bio)); + bio->type = MDSK_READ_REQ; + bio->block_number = private->pt_block + 1; + bio->buffer = label; memset(&private->iob, 0, sizeof (struct dasd_diag_rw_io)); private->iob.dev_nr = rdc_data->dev_nr; private->iob.key = 0; private->iob.flags = 0; /* do synchronous io */ private->iob.block_count = 1; private->iob.interrupt_params = 0; - private->iob.bio_list = &bio; + private->iob.bio_list = bio; private->iob.flaga = DASD_DIAG_FLAGA_DEFAULT; rc = dia250(&private->iob, RW_BIO); if (rc == 3) { pr_warn("%s: A 64-bit DIAG call failed\n", dev_name(&device->cdev->dev)); rc = -EOPNOTSUPP; - goto out_label; + goto out_bio; } mdsk_term_io(device); if (rc == 0) @@ -427,7 +434,7 @@ dasd_diag_check_device(struct dasd_device *device) pr_warn("%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n", dev_name(&device->cdev->dev), rc); rc = -EIO; - goto out_label; + goto out_bio; } /* check for label block */ if (memcmp(label->label_id, DASD_DIAG_CMS1, @@ -457,6 +464,8 @@ dasd_diag_check_device(struct dasd_device *device) (rc == 4) ? ", read-only device" : ""); rc = 0; } +out_bio: + kfree(bio); out_label: free_page((long) label); out: diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 19cfeac0e182..2e51675e8d45 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1255,6 +1255,10 @@ static void qeth_bridge_state_change(struct qeth_card *card, int extrasize; QETH_CARD_TEXT(card, 2, "brstchng"); + if (qports->num_entries == 0) { + QETH_CARD_TEXT(card, 2, "BPempty"); + return; + } if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) { QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length); return; diff --git a/drivers/scsi/arm/cumana_2.c b/drivers/scsi/arm/cumana_2.c index a1f3e9ee4e63..14e1d001253c 100644 --- a/drivers/scsi/arm/cumana_2.c +++ b/drivers/scsi/arm/cumana_2.c @@ -450,7 +450,7 @@ static int cumanascsi2_probe(struct expansion_card *ec, if (info->info.scsi.dma != NO_DMA) free_dma(info->info.scsi.dma); - free_irq(ec->irq, host); + free_irq(ec->irq, info); out_release: fas216_release(host); diff --git a/drivers/scsi/arm/eesox.c b/drivers/scsi/arm/eesox.c index 134f040d58e2..f441ec8eb93d 100644 --- a/drivers/scsi/arm/eesox.c +++ b/drivers/scsi/arm/eesox.c @@ -571,7 +571,7 @@ static int eesoxscsi_probe(struct expansion_card *ec, const struct ecard_id *id) if (info->info.scsi.dma != NO_DMA) free_dma(info->info.scsi.dma); - free_irq(ec->irq, host); + free_irq(ec->irq, info); out_remove: fas216_remove(host); diff --git a/drivers/scsi/arm/powertec.c b/drivers/scsi/arm/powertec.c index c795537a671c..2dc0df005cb3 100644 --- a/drivers/scsi/arm/powertec.c +++ b/drivers/scsi/arm/powertec.c @@ -378,7 +378,7 @@ static int powertecscsi_probe(struct expansion_card *ec, if (info->info.scsi.dma != NO_DMA) free_dma(info->info.scsi.dma); - free_irq(ec->irq, host); + free_irq(ec->irq, info); out_release: fas216_release(host); diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index d74bfd264495..8a93dfa79297 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1723,7 +1723,7 @@ lpfc_nvmet_destroy_targetport(struct lpfc_hba *phba) } tgtp->tport_unreg_cmp = &tport_unreg_cmp; nvmet_fc_unregister_targetport(phba->targetport); - if (!wait_for_completion_timeout(tgtp->tport_unreg_cmp, + if (!wait_for_completion_timeout(&tport_unreg_cmp, msecs_to_jiffies(LPFC_NVMET_WAIT_TMO))) lpfc_printf_log(phba, KERN_ERR, LOG_NVME, "6179 Unreg targetport %p timeout " diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c index 74fb50644678..4dd50db90677 100644 --- a/drivers/scsi/mesh.c +++ b/drivers/scsi/mesh.c @@ -1045,6 +1045,8 @@ static void handle_error(struct mesh_state *ms) while ((in_8(&mr->bus_status1) & BS1_RST) != 0) udelay(1); printk("done\n"); + if (ms->dma_started) + halt_dma(ms); handle_reset(ms); /* request_q is empty, no point in mesh_start() */ return; @@ -1357,7 +1359,8 @@ static void halt_dma(struct mesh_state *ms) ms->conn_tgt, ms->data_ptr, scsi_bufflen(cmd), ms->tgts[ms->conn_tgt].data_goes_out); } - scsi_dma_unmap(cmd); + if (cmd) + scsi_dma_unmap(cmd); ms->dma_started = 0; } @@ -1712,6 +1715,9 @@ static int mesh_host_reset(struct scsi_cmnd *cmd) spin_lock_irqsave(ms->host->host_lock, flags); + if (ms->dma_started) + halt_dma(ms); + /* Reset the controller & dbdma channel */ out_le32(&md->control, (RUN|PAUSE|FLUSH|WAKE) << 16); /* stop dma */ out_8(&mr->exception, 0xff); /* clear all exception bits */ diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index c20b4b70a3c8..10f8e1791a5a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -2893,19 +2893,18 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr, if (!ioc->is_warpdrive) { ioc_err(ioc, "%s: BRM attribute is only for warpdrive\n", __func__); - goto out; + return 0; } /* pci_access_mutex lock acquired by sysfs show path */ mutex_lock(&ioc->pci_access_mutex); - if (ioc->pci_error_recovery || ioc->remove_host) { - mutex_unlock(&ioc->pci_access_mutex); - return 0; - } + if (ioc->pci_error_recovery || ioc->remove_host) + goto out; /* allocate upto GPIOVal 36 entries */ sz = offsetof(Mpi2IOUnitPage3_t, GPIOVal) + (sizeof(u16) * 36); io_unit_pg3 = kzalloc(sz, GFP_KERNEL); if (!io_unit_pg3) { + rc = -ENOMEM; ioc_err(ioc, "%s: failed allocating memory for iounit_pg3: (%d) bytes\n", __func__, sz); goto out; @@ -2915,6 +2914,7 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr, 0) { ioc_err(ioc, "%s: failed reading iounit_pg3\n", __func__); + rc = -EINVAL; goto out; } @@ -2922,12 +2922,14 @@ _ctl_BRM_status_show(struct device *cdev, struct device_attribute *attr, if (ioc_status != MPI2_IOCSTATUS_SUCCESS) { ioc_err(ioc, "%s: iounit_pg3 failed with ioc_status(0x%04x)\n", __func__, ioc_status); + rc = -EINVAL; goto out; } if (io_unit_pg3->GPIOCount < 25) { ioc_err(ioc, "%s: iounit_pg3->GPIOCount less than 25 entries, detected (%d) entries\n", __func__, io_unit_pg3->GPIOCount); + rc = -EINVAL; goto out; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 32965ec76965..44181a2cbf18 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5296,6 +5296,12 @@ static int __init scsi_debug_init(void) pr_err("submit_queues must be 1 or more\n"); return -EINVAL; } + + if ((sdebug_max_queue > SDEBUG_CANQUEUE) || (sdebug_max_queue < 1)) { + pr_err("max_queue must be in range [1, %d]\n", SDEBUG_CANQUEUE); + return -EINVAL; + } + sdebug_q_arr = kcalloc(submit_queues, sizeof(struct sdebug_queue), GFP_KERNEL); if (sdebug_q_arr == NULL) diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index a08ff3bd6310..d16d8b6aaccc 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -239,6 +239,7 @@ static struct { {"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, + {"FUJITSU", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36}, {"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN}, {"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */ diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 42f0550d6b11..6f41e4b5a2b8 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -63,6 +63,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = { {"LSI", "INF-01-00", "rdac", }, {"ENGENIO", "INF-01-00", "rdac", }, {"LENOVO", "DE_Series", "rdac", }, + {"FUJITSU", "ETERNUS_AHB", "rdac", }, {NULL, NULL, NULL }, }; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 74f79e622a57..65646497295f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -554,6 +554,15 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) scsi_del_cmd_from_list(cmd); } +static void scsi_run_queue_async(struct scsi_device *sdev) +{ + if (scsi_target(sdev)->single_lun || + !list_empty(&sdev->host->starved_list)) + kblockd_schedule_work(&sdev->requeue_work); + else + blk_mq_run_hw_queues(sdev->request_queue, true); +} + /* Returns false when no more bytes to process, true if there are more */ static bool scsi_end_request(struct request *req, blk_status_t error, unsigned int bytes) @@ -598,11 +607,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, __blk_mq_end_request(req, error); - if (scsi_target(sdev)->single_lun || - !list_empty(&sdev->host->starved_list)) - kblockd_schedule_work(&sdev->requeue_work); - else - blk_mq_run_hw_queues(q, true); + scsi_run_queue_async(sdev); percpu_ref_put(&q->q_usage_counter); return false; @@ -1712,6 +1717,7 @@ out_put_budget: */ if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); + scsi_run_queue_async(sdev); break; } return ret; diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c index f8661062ef95..f3d5b1bbd5aa 100644 --- a/drivers/scsi/scsi_transport_spi.c +++ b/drivers/scsi/scsi_transport_spi.c @@ -339,7 +339,7 @@ store_spi_transport_##field(struct device *dev, \ struct spi_transport_attrs *tp \ = (struct spi_transport_attrs *)&starget->starget_data; \ \ - if (i->f->set_##field) \ + if (!i->f->set_##field) \ return -EINVAL; \ val = simple_strtoul(buf, NULL, 0); \ if (val > tp->max_##field) \ diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index b2f07d2043eb..bdfbe64b4641 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -288,6 +288,7 @@ EXPORT_SYMBOL_GPL(slim_register_controller); /* slim_remove_device: Remove the effect of slim_add_device() */ static void slim_remove_device(struct slim_device *sbdev) { + of_node_put(sbdev->dev.of_node); device_unregister(&sbdev->dev); } diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index e278fc11fe5c..8924fcd9f5f5 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -148,7 +148,7 @@ int rpmh_rsc_invalidate(struct rsc_drv *drv) static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv, const struct tcs_request *msg) { - int type, ret; + int type; struct tcs_group *tcs; switch (msg->state) { @@ -169,19 +169,10 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv, * If we are making an active request on a RSC that does not have a * dedicated TCS for active state use, then re-purpose a wake TCS to * send active votes. - * NOTE: The driver must be aware that this RSC does not have a - * dedicated AMC, and therefore would invalidate the sleep and wake - * TCSes before making an active state request. */ tcs = get_tcs_of_type(drv, type); - if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) { + if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) tcs = get_tcs_of_type(drv, WAKE_TCS); - if (tcs->num_tcs) { - ret = rpmh_rsc_invalidate(drv); - if (ret) - return ERR_PTR(ret); - } - } return tcs; } @@ -201,6 +192,42 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv, return NULL; } +static void __tcs_set_trigger(struct rsc_drv *drv, int tcs_id, bool trigger) +{ + u32 enable; + + /* + * HW req: Clear the DRV_CONTROL and enable TCS again + * While clearing ensure that the AMC mode trigger is cleared + * and then the mode enable is cleared. + */ + enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0); + enable &= ~TCS_AMC_MODE_TRIGGER; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + enable &= ~TCS_AMC_MODE_ENABLE; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + + if (trigger) { + /* Enable the AMC mode on the TCS and then trigger the TCS */ + enable = TCS_AMC_MODE_ENABLE; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + enable |= TCS_AMC_MODE_TRIGGER; + write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); + } +} + +static void enable_tcs_irq(struct rsc_drv *drv, int tcs_id, bool enable) +{ + u32 data; + + data = read_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, 0); + if (enable) + data |= BIT(tcs_id); + else + data &= ~BIT(tcs_id); + write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, data); +} + /** * tcs_tx_done: TX Done interrupt handler */ @@ -237,6 +264,14 @@ static irqreturn_t tcs_tx_done(int irq, void *p) } trace_rpmh_tx_done(drv, i, req, err); + + /* + * If wake tcs was re-purposed for sending active + * votes, clear AMC trigger & enable modes and + * disable interrupt for this TCS + */ + if (!drv->tcs[ACTIVE_TCS].num_tcs) + __tcs_set_trigger(drv, i, false); skip: /* Reclaim the TCS */ write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0); @@ -244,6 +279,13 @@ skip: write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i)); spin_lock(&drv->lock); clear_bit(i, drv->tcs_in_use); + /* + * Disable interrupt for WAKE TCS to avoid being + * spammed with interrupts coming when the solver + * sends its wake votes. + */ + if (!drv->tcs[ACTIVE_TCS].num_tcs) + enable_tcs_irq(drv, i, false); spin_unlock(&drv->lock); if (req) rpmh_tx_done(req, err); @@ -285,28 +327,6 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id, write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable); } -static void __tcs_trigger(struct rsc_drv *drv, int tcs_id) -{ - u32 enable; - - /* - * HW req: Clear the DRV_CONTROL and enable TCS again - * While clearing ensure that the AMC mode trigger is cleared - * and then the mode enable is cleared. - */ - enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0); - enable &= ~TCS_AMC_MODE_TRIGGER; - write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); - enable &= ~TCS_AMC_MODE_ENABLE; - write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); - - /* Enable the AMC mode on the TCS and then trigger the TCS */ - enable = TCS_AMC_MODE_ENABLE; - write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); - enable |= TCS_AMC_MODE_TRIGGER; - write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable); -} - static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs, const struct tcs_request *msg) { @@ -377,10 +397,20 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) tcs->req[tcs_id - tcs->offset] = msg; set_bit(tcs_id, drv->tcs_in_use); + if (msg->state == RPMH_ACTIVE_ONLY_STATE && tcs->type != ACTIVE_TCS) { + /* + * Clear previously programmed WAKE commands in selected + * repurposed TCS to avoid triggering them. tcs->slots will be + * cleaned from rpmh_flush() by invoking rpmh_rsc_invalidate() + */ + write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0); + write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0); + enable_tcs_irq(drv, tcs_id, true); + } spin_unlock(&drv->lock); __tcs_buffer_write(drv, tcs_id, 0, msg); - __tcs_trigger(drv, tcs_id); + __tcs_set_trigger(drv, tcs_id, true); done_write: spin_unlock_irqrestore(&tcs->lock, flags); @@ -685,6 +715,7 @@ static struct platform_driver rpmh_driver = { .driver = { .name = "rpmh", .of_match_table = rpmh_drv_match, + .suppress_bind_attrs = true, }, }; diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index 035091fd44b8..13e1b450f296 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -119,6 +119,7 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, { struct cache_req *req; unsigned long flags; + u32 old_sleep_val, old_wake_val; spin_lock_irqsave(&ctrlr->cache_lock, flags); req = __find_req(ctrlr, cmd->addr); @@ -133,26 +134,27 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, req->addr = cmd->addr; req->sleep_val = req->wake_val = UINT_MAX; - INIT_LIST_HEAD(&req->list); list_add_tail(&req->list, &ctrlr->cache); existing: + old_sleep_val = req->sleep_val; + old_wake_val = req->wake_val; + switch (state) { case RPMH_ACTIVE_ONLY_STATE: - if (req->sleep_val != UINT_MAX) - req->wake_val = cmd->data; - break; case RPMH_WAKE_ONLY_STATE: req->wake_val = cmd->data; break; case RPMH_SLEEP_STATE: req->sleep_val = cmd->data; break; - default: - break; } - ctrlr->dirty = true; + ctrlr->dirty |= (req->sleep_val != old_sleep_val || + req->wake_val != old_wake_val) && + req->sleep_val != UINT_MAX && + req->wake_val != UINT_MAX; + unlock: spin_unlock_irqrestore(&ctrlr->cache_lock, flags); @@ -287,6 +289,7 @@ static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req) spin_lock_irqsave(&ctrlr->cache_lock, flags); list_add_tail(&req->list, &ctrlr->batch_cache); + ctrlr->dirty = true; spin_unlock_irqrestore(&ctrlr->cache_lock, flags); } @@ -314,18 +317,6 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr) return ret; } -static void invalidate_batch(struct rpmh_ctrlr *ctrlr) -{ - struct batch_cache_req *req, *tmp; - unsigned long flags; - - spin_lock_irqsave(&ctrlr->cache_lock, flags); - list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list) - kfree(req); - INIT_LIST_HEAD(&ctrlr->batch_cache); - spin_unlock_irqrestore(&ctrlr->cache_lock, flags); -} - /** * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the * batch to finish. @@ -465,6 +456,13 @@ int rpmh_flush(const struct device *dev) return 0; } + /* Invalidate the TCSes first to avoid stale data */ + do { + ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr)); + } while (ret == -EAGAIN); + if (ret) + return ret; + /* First flush the cached batch requests */ ret = flush_batch(ctrlr); if (ret) @@ -496,25 +494,25 @@ int rpmh_flush(const struct device *dev) EXPORT_SYMBOL(rpmh_flush); /** - * rpmh_invalidate: Invalidate all sleep and active sets - * sets. + * rpmh_invalidate: Invalidate sleep and wake sets in batch_cache * * @dev: The device making the request * - * Invalidate the sleep and active values in the TCS blocks. + * Invalidate the sleep and wake values in batch_cache. */ int rpmh_invalidate(const struct device *dev) { struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev); - int ret; + struct batch_cache_req *req, *tmp; + unsigned long flags; - invalidate_batch(ctrlr); + spin_lock_irqsave(&ctrlr->cache_lock, flags); + list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list) + kfree(req); + INIT_LIST_HEAD(&ctrlr->batch_cache); ctrlr->dirty = true; + spin_unlock_irqrestore(&ctrlr->cache_lock, flags); - do { - ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr)); - } while (ret == -EAGAIN); - - return ret; + return 0; } EXPORT_SYMBOL(rpmh_invalidate); diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index f83f3b4ed6b1..412a64b29b09 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -701,8 +701,9 @@ static int intel_create_dai(struct sdw_cdns *cdns, /* TODO: Read supported rates/formats from hardware */ for (i = off; i < (off + num); i++) { - dais[i].name = kasprintf(GFP_KERNEL, "SDW%d Pin%d", - cdns->instance, i); + dais[i].name = devm_kasprintf(cdns->dev, GFP_KERNEL, + "SDW%d Pin%d", + cdns->instance, i); if (!dais[i].name) return -ENOMEM; diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c index 8f01858c0ae6..365008d304f5 100644 --- a/drivers/spi/spi-lantiq-ssc.c +++ b/drivers/spi/spi-lantiq-ssc.c @@ -184,6 +184,7 @@ struct lantiq_ssc_spi { unsigned int tx_fifo_size; unsigned int rx_fifo_size; unsigned int base_cs; + unsigned int fdx_tx_level; }; static u32 lantiq_ssc_readl(const struct lantiq_ssc_spi *spi, u32 reg) @@ -481,6 +482,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi) u32 data; unsigned int tx_free = tx_fifo_free(spi); + spi->fdx_tx_level = 0; while (spi->tx_todo && tx_free) { switch (spi->bits_per_word) { case 2 ... 8: @@ -509,6 +511,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi) lantiq_ssc_writel(spi, data, LTQ_SPI_TB); tx_free--; + spi->fdx_tx_level++; } } @@ -520,6 +523,13 @@ static void rx_fifo_read_full_duplex(struct lantiq_ssc_spi *spi) u32 data; unsigned int rx_fill = rx_fifo_level(spi); + /* + * Wait until all expected data to be shifted in. + * Otherwise, rx overrun may occur. + */ + while (rx_fill != spi->fdx_tx_level) + rx_fill = rx_fifo_level(spi); + while (rx_fill) { data = lantiq_ssc_readl(spi, LTQ_SPI_RB); @@ -913,7 +923,7 @@ static int lantiq_ssc_probe(struct platform_device *pdev) master->bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 8) | SPI_BPW_MASK(16) | SPI_BPW_MASK(32); - spi->wq = alloc_ordered_workqueue(dev_name(dev), 0); + spi->wq = alloc_ordered_workqueue(dev_name(dev), WQ_MEM_RECLAIM); if (!spi->wq) { err = -ENOMEM; goto err_clk_put; diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 10041eab36a2..ea737f69a870 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -33,7 +33,6 @@ #define SPI_CFG0_SCK_LOW_OFFSET 8 #define SPI_CFG0_CS_HOLD_OFFSET 16 #define SPI_CFG0_CS_SETUP_OFFSET 24 -#define SPI_ADJUST_CFG0_SCK_LOW_OFFSET 16 #define SPI_ADJUST_CFG0_CS_HOLD_OFFSET 0 #define SPI_ADJUST_CFG0_CS_SETUP_OFFSET 16 @@ -45,6 +44,8 @@ #define SPI_CFG1_CS_IDLE_MASK 0xff #define SPI_CFG1_PACKET_LOOP_MASK 0xff00 #define SPI_CFG1_PACKET_LENGTH_MASK 0x3ff0000 +#define SPI_CFG2_SCK_HIGH_OFFSET 0 +#define SPI_CFG2_SCK_LOW_OFFSET 16 #define SPI_CMD_ACT BIT(0) #define SPI_CMD_RESUME BIT(1) @@ -263,7 +264,7 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable) static void mtk_spi_prepare_transfer(struct spi_master *master, struct spi_transfer *xfer) { - u32 spi_clk_hz, div, sck_time, cs_time, reg_val = 0; + u32 spi_clk_hz, div, sck_time, cs_time, reg_val; struct mtk_spi *mdata = spi_master_get_devdata(master); spi_clk_hz = clk_get_rate(mdata->spi_clk); @@ -276,18 +277,18 @@ static void mtk_spi_prepare_transfer(struct spi_master *master, cs_time = sck_time * 2; if (mdata->dev_comp->enhance_timing) { + reg_val = (((sck_time - 1) & 0xffff) + << SPI_CFG2_SCK_HIGH_OFFSET); reg_val |= (((sck_time - 1) & 0xffff) - << SPI_CFG0_SCK_HIGH_OFFSET); - reg_val |= (((sck_time - 1) & 0xffff) - << SPI_ADJUST_CFG0_SCK_LOW_OFFSET); + << SPI_CFG2_SCK_LOW_OFFSET); writel(reg_val, mdata->base + SPI_CFG2_REG); - reg_val |= (((cs_time - 1) & 0xffff) + reg_val = (((cs_time - 1) & 0xffff) << SPI_ADJUST_CFG0_CS_HOLD_OFFSET); reg_val |= (((cs_time - 1) & 0xffff) << SPI_ADJUST_CFG0_CS_SETUP_OFFSET); writel(reg_val, mdata->base + SPI_CFG0_REG); } else { - reg_val |= (((sck_time - 1) & 0xff) + reg_val = (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_HIGH_OFFSET); reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_LOW_OFFSET); reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET); diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 2cc6d9951b52..008b64f4e031 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -286,7 +286,7 @@ static void rockchip_spi_pio_writer(struct rockchip_spi *rs) static void rockchip_spi_pio_reader(struct rockchip_spi *rs) { u32 words = readl_relaxed(rs->regs + ROCKCHIP_SPI_RXFLR); - u32 rx_left = rs->rx_left - words; + u32 rx_left = (rs->rx_left > words) ? rs->rx_left - words : 0; /* the hardware doesn't allow us to change fifo threshold * level while spi is enabled, so instead make sure to leave diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c index f1fc2bde6ef3..e41976010dc4 100644 --- a/drivers/spi/spi-sprd-adi.c +++ b/drivers/spi/spi-sprd-adi.c @@ -358,9 +358,9 @@ static int sprd_adi_restart_handler(struct notifier_block *this, sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOCK, WDG_UNLOCK_KEY); /* Load the watchdog timeout value, 50ms is always enough. */ + sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0); sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_LOW, WDG_LOAD_VAL & WDG_LOAD_MASK); - sprd_adi_write(sadi, sadi->slave_pbase + REG_WDG_LOAD_HIGH, 0); /* Start the watchdog to reset system */ sprd_adi_read(sadi, sadi->slave_pbase + REG_WDG_CTRL, &val); diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c index ee2bdaf5b856..2d361af9140e 100644 --- a/drivers/spi/spi-sun6i.c +++ b/drivers/spi/spi-sun6i.c @@ -198,7 +198,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master, struct spi_transfer *tfr) { struct sun6i_spi *sspi = spi_master_get_devdata(master); - unsigned int mclk_rate, div, timeout; + unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout; unsigned int start, end, tx_time; unsigned int trig_level; unsigned int tx_len = 0; @@ -287,14 +287,12 @@ static int sun6i_spi_transfer_one(struct spi_master *master, * First try CDR2, and if we can't reach the expected * frequency, fall back to CDR1. */ - div = mclk_rate / (2 * tfr->speed_hz); - if (div <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) { - if (div > 0) - div--; - - reg = SUN6I_CLK_CTL_CDR2(div) | SUN6I_CLK_CTL_DRS; + div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz); + div_cdr2 = DIV_ROUND_UP(div_cdr1, 2); + if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) { + reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS; } else { - div = ilog2(mclk_rate) - ilog2(tfr->speed_hz); + div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1)); reg = SUN6I_CLK_CTL_CDR1(div); } diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 4c13eb715a2b..c62576ce2a88 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -223,6 +223,11 @@ static int spidev_message(struct spidev_data *spidev, for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers; n; n--, k_tmp++, u_tmp++) { + /* Ensure that also following allocations from rx_buf/tx_buf will meet + * DMA alignment requirements. + */ + unsigned int len_aligned = ALIGN(u_tmp->len, ARCH_KMALLOC_MINALIGN); + k_tmp->len = u_tmp->len; total += k_tmp->len; @@ -238,17 +243,17 @@ static int spidev_message(struct spidev_data *spidev, if (u_tmp->rx_buf) { /* this transfer needs space in RX bounce buffer */ - rx_total += k_tmp->len; + rx_total += len_aligned; if (rx_total > bufsiz) { status = -EMSGSIZE; goto done; } k_tmp->rx_buf = rx_buf; - rx_buf += k_tmp->len; + rx_buf += len_aligned; } if (u_tmp->tx_buf) { /* this transfer needs space in TX bounce buffer */ - tx_total += k_tmp->len; + tx_total += len_aligned; if (tx_total > bufsiz) { status = -EMSGSIZE; goto done; @@ -258,7 +263,7 @@ static int spidev_message(struct spidev_data *spidev, (uintptr_t) u_tmp->tx_buf, u_tmp->len)) goto done; - tx_buf += k_tmp->len; + tx_buf += len_aligned; } k_tmp->cs_change = !!u_tmp->cs_change; @@ -290,16 +295,16 @@ static int spidev_message(struct spidev_data *spidev, goto done; /* copy any rx data out of bounce buffer */ - rx_buf = spidev->rx_buffer; - for (n = n_xfers, u_tmp = u_xfers; n; n--, u_tmp++) { + for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers; + n; + n--, k_tmp++, u_tmp++) { if (u_tmp->rx_buf) { if (copy_to_user((u8 __user *) - (uintptr_t) u_tmp->rx_buf, rx_buf, + (uintptr_t) u_tmp->rx_buf, k_tmp->rx_buf, u_tmp->len)) { status = -EFAULT; goto done; } - rx_buf += u_tmp->len; } } status = total; diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index c6695354b123..19b0cc5ea33f 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -95,6 +95,15 @@ static DEFINE_MUTEX(ashmem_mutex); static struct kmem_cache *ashmem_area_cachep __read_mostly; static struct kmem_cache *ashmem_range_cachep __read_mostly; +/* + * A separate lockdep class for the backing shmem inodes to resolve the lockdep + * warning about the race between kswapd taking fs_reclaim before inode_lock + * and write syscall taking inode_lock and then fs_reclaim. + * Note that such race is impossible because ashmem does not support write + * syscalls operating on the backing shmem. + */ +static struct lock_class_key backing_shmem_inode_class; + static inline unsigned long range_size(struct ashmem_range *range) { return range->pgend - range->pgstart + 1; @@ -396,6 +405,7 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) if (!asma->file) { char *name = ASHMEM_NAME_DEF; struct file *vmfile; + struct inode *inode; if (asma->name[ASHMEM_NAME_PREFIX_LEN] != '\0') name = asma->name; @@ -407,6 +417,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) goto out; } vmfile->f_mode |= FMODE_LSEEK; + inode = file_inode(vmfile); + lockdep_set_class(&inode->i_rwsem, &backing_shmem_inode_class); asma->file = vmfile; /* * override mmap operation of the vmfile so that it can't be diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c index 560649be9d13..e035c9f757a1 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1032.c +++ b/drivers/staging/comedi/drivers/addi_apci_1032.c @@ -106,14 +106,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1032_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -136,8 +144,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA | @@ -154,8 +162,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c index 45ad4ba92f94..816dd25b9d0e 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1500.c +++ b/drivers/staging/comedi/drivers/addi_apci_1500.c @@ -452,13 +452,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, struct apci1500_private *devpriv = dev->private; unsigned int trig = data[1]; unsigned int shift = data[3]; - unsigned int hi_mask = data[4] << shift; - unsigned int lo_mask = data[5] << shift; - unsigned int chan_mask = hi_mask | lo_mask; - unsigned int old_mask = (1 << shift) - 1; - unsigned int pm = devpriv->pm[trig] & old_mask; - unsigned int pt = devpriv->pt[trig] & old_mask; - unsigned int pp = devpriv->pp[trig] & old_mask; + unsigned int hi_mask; + unsigned int lo_mask; + unsigned int chan_mask; + unsigned int old_mask; + unsigned int pm; + unsigned int pt; + unsigned int pp; + unsigned int invalid_chan; if (trig > 1) { dev_dbg(dev->class_dev, @@ -466,11 +467,28 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, return -EINVAL; } - if (chan_mask > 0xffff) { + if (shift <= 16) { + hi_mask = data[4] << shift; + lo_mask = data[5] << shift; + old_mask = (1U << shift) - 1; + invalid_chan = (data[4] | data[5]) >> (16 - shift); + } else { + hi_mask = 0; + lo_mask = 0; + old_mask = 0xffff; + invalid_chan = data[4] | data[5]; + } + chan_mask = hi_mask | lo_mask; + + if (invalid_chan) { dev_dbg(dev->class_dev, "invalid digital trigger channel\n"); return -EINVAL; } + pm = devpriv->pm[trig] & old_mask; + pt = devpriv->pt[trig] & old_mask; + pp = devpriv->pp[trig] & old_mask; + switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: /* clear trigger configuration */ diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c index 10501fe6bb25..1268ba34be5f 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1564.c +++ b/drivers/staging/comedi/drivers/addi_apci_1564.c @@ -331,14 +331,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1564_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -362,8 +370,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA | @@ -380,8 +388,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c index 4d1eccb5041d..4518c2680b7c 100644 --- a/drivers/staging/comedi/drivers/ni_6527.c +++ b/drivers/staging/comedi/drivers/ni_6527.c @@ -332,7 +332,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev, case COMEDI_DIGITAL_TRIG_ENABLE_EDGES: /* check shift amount */ shift = data[3]; - if (shift >= s->n_chan) { + if (shift >= 32) { mask = 0; rising = 0; falling = 0; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index 20f513fbaa85..47c99ed6d2d6 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -263,6 +263,9 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) pko_command.s.n2 = 1; /* Don't pollute L2 with the outgoing packet */ pko_command.s.segs = 1; pko_command.s.total_bytes = skb->len; +#if GCC_VERSION >= 80000 + barrier(); +#endif pko_command.s.size0 = CVMX_FAU_OP_SIZE_32; pko_command.s.subone0 = 1; diff --git a/drivers/staging/rtl8188eu/core/rtw_mlme.c b/drivers/staging/rtl8188eu/core/rtw_mlme.c index 9a4aad5ec365..24c0ec1674b1 100644 --- a/drivers/staging/rtl8188eu/core/rtw_mlme.c +++ b/drivers/staging/rtl8188eu/core/rtw_mlme.c @@ -1740,9 +1740,11 @@ int rtw_restruct_sec_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_ if ((ndisauthmode == Ndis802_11AuthModeWPA) || (ndisauthmode == Ndis802_11AuthModeWPAPSK)) authmode = _WPA_IE_ID_; - if ((ndisauthmode == Ndis802_11AuthModeWPA2) || + else if ((ndisauthmode == Ndis802_11AuthModeWPA2) || (ndisauthmode == Ndis802_11AuthModeWPA2PSK)) authmode = _WPA2_IE_ID_; + else + authmode = 0x0; if (check_fwstate(pmlmepriv, WIFI_UNDER_WPS)) { memcpy(out_ie+ielength, psecuritypriv->wps_ie, psecuritypriv->wps_ie_len); diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c index 309f06439a23..001157e7fa57 100644 --- a/drivers/staging/rtl8192u/r8192U_core.c +++ b/drivers/staging/rtl8192u/r8192U_core.c @@ -2447,7 +2447,7 @@ static int rtl8192_read_eeprom_info(struct net_device *dev) ret = eprom_read(dev, (EEPROM_TX_PW_INDEX_CCK >> 1)); if (ret < 0) return ret; - priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff) >> 8; + priv->EEPROMTxPowerLevelCCK = ((u16)ret & 0xff00) >> 8; } else priv->EEPROMTxPowerLevelCCK = 0x10; RT_TRACE(COMP_EPROM, "CCK Tx Power Levl: 0x%02x\n", priv->EEPROMTxPowerLevelCCK); diff --git a/drivers/staging/rtl8712/hal_init.c b/drivers/staging/rtl8712/hal_init.c index 401f0e442bcf..fd220c284c01 100644 --- a/drivers/staging/rtl8712/hal_init.c +++ b/drivers/staging/rtl8712/hal_init.c @@ -33,7 +33,6 @@ static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context) { struct _adapter *padapter = context; - complete(&padapter->rtl8712_fw_ready); if (!firmware) { struct usb_device *udev = padapter->dvobjpriv.pusbdev; struct usb_interface *pusb_intf = padapter->pusb_intf; @@ -41,11 +40,13 @@ static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context) dev_err(&udev->dev, "r8712u: Firmware request failed\n"); usb_put_dev(udev); usb_set_intfdata(pusb_intf, NULL); + complete(&padapter->rtl8712_fw_ready); return; } padapter->fw = firmware; /* firmware available - start netdev */ register_netdev(padapter->pnetdev); + complete(&padapter->rtl8712_fw_ready); } static const char firmware_file[] = "rtlwifi/rtl8712u.bin"; diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index d6fd4b9a9105..7c4678859ebd 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -595,13 +595,17 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf) if (pnetdev) { struct _adapter *padapter = netdev_priv(pnetdev); - usb_set_intfdata(pusb_intf, NULL); - release_firmware(padapter->fw); /* never exit with a firmware callback pending */ wait_for_completion(&padapter->rtl8712_fw_ready); + pnetdev = usb_get_intfdata(pusb_intf); + usb_set_intfdata(pusb_intf, NULL); + if (!pnetdev) + goto firmware_load_fail; + release_firmware(padapter->fw); if (drvpriv.drv_registered) padapter->surprise_removed = true; - unregister_netdev(pnetdev); /* will call netdev_close() */ + if (pnetdev->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(pnetdev); /* will call netdev_close() */ flush_scheduled_work(); udelay(1); /* Stop driver mlme relation timer */ @@ -614,6 +618,7 @@ static void r871xu_dev_remove(struct usb_interface *pusb_intf) */ usb_put_dev(udev); } +firmware_load_fail: /* If we didn't unplug usb dongle and remove/insert module, driver * fails on sitesurvey for the first time when device is up. * Reset usb port for sitesurvey fail issue. diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 6f6388c96bf6..4cf59696ac6f 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -3545,6 +3545,7 @@ failed_platform_init: static int vchiq_remove(struct platform_device *pdev) { + platform_device_unregister(bcm2835_audio); platform_device_unregister(bcm2835_camera); vchiq_debugfs_deinit(); device_destroy(vchiq_class, vchiq_devid); diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c index 91aaff02a59e..a93370af5426 100644 --- a/drivers/staging/wlan-ng/hfa384x_usb.c +++ b/drivers/staging/wlan-ng/hfa384x_usb.c @@ -532,13 +532,8 @@ static void hfa384x_usb_defer(struct work_struct *data) */ void hfa384x_create(struct hfa384x *hw, struct usb_device *usb) { - memset(hw, 0, sizeof(*hw)); hw->usb = usb; - /* set up the endpoints */ - hw->endp_in = usb_rcvbulkpipe(usb, 1); - hw->endp_out = usb_sndbulkpipe(usb, 2); - /* Set up the waitq */ init_waitqueue_head(&hw->cmdq); diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index d8d86761b790..9eee72aff723 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -61,11 +61,16 @@ static int prism2sta_probe_usb(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *dev; - + struct usb_endpoint_descriptor *bulk_in, *bulk_out; + struct usb_host_interface *iface_desc = interface->cur_altsetting; struct wlandevice *wlandev = NULL; struct hfa384x *hw = NULL; int result = 0; + result = usb_find_common_endpoints(iface_desc, &bulk_in, &bulk_out, NULL, NULL); + if (result) + goto failed; + dev = interface_to_usbdev(interface); wlandev = create_wlan(); if (!wlandev) { @@ -82,6 +87,8 @@ static int prism2sta_probe_usb(struct usb_interface *interface, } /* Initialize the hw data */ + hw->endp_in = usb_rcvbulkpipe(dev, bulk_in->bEndpointAddress); + hw->endp_out = usb_sndbulkpipe(dev, bulk_out->bEndpointAddress); hfa384x_create(hw, dev); hw->wlandev = wlandev; diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 4c5db59a619b..a4baa5d21ecd 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -264,11 +264,11 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, int i; struct freq_table *freq_table = cpufreq_cdev->freq_table; - for (i = 1; i <= cpufreq_cdev->max_level; i++) - if (power > freq_table[i].power) + for (i = 0; i < cpufreq_cdev->max_level; i++) + if (power >= freq_table[i].power) break; - return freq_table[i - 1].frequency; + return freq_table[i].frequency; } /** diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index bb6754a5342c..85511c1160b7 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -656,7 +656,7 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data) { struct device_node *np; - int ret; + int ret = 0; data->policy = cpufreq_cpu_get(0); if (!data->policy) { @@ -671,11 +671,12 @@ static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data) if (IS_ERR(data->cdev)) { ret = PTR_ERR(data->cdev); cpufreq_cpu_put(data->policy); - return ret; } } - return 0; + of_node_put(np); + + return ret; } static void imx_thermal_unregister_legacy_cooling(struct imx_thermal_data *data) diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c index f5749d4418ae..ff94d7f95216 100644 --- a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c @@ -74,7 +74,7 @@ static void int3403_notify(acpi_handle handle, THERMAL_TRIP_CHANGED); break; default: - dev_err(&priv->pdev->dev, "Unsupported event [0x%x]\n", event); + dev_dbg(&priv->pdev->dev, "Unsupported event [0x%x]\n", event); break; } } diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index 85776db4bf34..2ce4b19f312a 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -169,7 +169,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id, data = ti_bandgap_get_sensor_data(bgp, id); - if (!IS_ERR_OR_NULL(data)) + if (IS_ERR_OR_NULL(data)) data = ti_thermal_build_data(bgp, id); if (!data) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index a8aa64c30fea..0c4451f7c4b9 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -523,6 +523,7 @@ static void __init serial8250_isa_init_ports(void) */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; + serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ @@ -546,7 +547,6 @@ static void __init serial8250_isa_init_ports(void) port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; - serial8250_set_defaults(up); port->irqflags |= irqflag; if (serial8250_isa_config != NULL) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 6f730c357bee..4c183889f65e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -227,7 +227,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p) * devices will export them as GPIOs, so we pre-configure them safely * as inputs. */ - u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00; + + u8 dir = 0x00; + + if ((pcidev->vendor == PCI_VENDOR_ID_EXAR) && + (pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) { + // Configure GPIO as inputs for Commtech adapters + dir = 0xff; + } else { + // Configure GPIO as outputs for SeaLevel adapters + dir = 0x00; + } writeb(0x00, p + UART_EXAR_MPIOINT_7_0); writeb(0x00, p + UART_EXAR_MPIOLVL_7_0); diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index 4c188f4079b3..63810eefa44b 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1703,21 +1703,21 @@ static int mxs_auart_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { ret = irq; - goto out_disable_clks; + goto out_iounmap; } s->port.irq = irq; ret = devm_request_irq(&pdev->dev, irq, mxs_auart_irq_handle, 0, dev_name(&pdev->dev), s); if (ret) - goto out_disable_clks; + goto out_iounmap; platform_set_drvdata(pdev, s); ret = mxs_auart_init_gpios(s, &pdev->dev); if (ret) { dev_err(&pdev->dev, "Failed to initialize GPIOs.\n"); - goto out_disable_clks; + goto out_iounmap; } /* @@ -1725,7 +1725,7 @@ static int mxs_auart_probe(struct platform_device *pdev) */ ret = mxs_auart_request_gpio_irq(s); if (ret) - goto out_disable_clks; + goto out_iounmap; auart_port[s->port.line] = s; @@ -1751,6 +1751,9 @@ out_free_qpio_irq: mxs_auart_free_gpio_irq(s); auart_port[pdev->id] = NULL; +out_iounmap: + iounmap(s->port.membase); + out_disable_clks: if (is_asm9260_auart(s)) { clk_disable_unprepare(s->clk); @@ -1766,6 +1769,7 @@ static int mxs_auart_remove(struct platform_device *pdev) uart_remove_one_port(&auart_driver, &s->port); auart_port[pdev->id] = NULL; mxs_auart_free_gpio_irq(s); + iounmap(s->port.membase); if (is_asm9260_auart(s)) { clk_disable_unprepare(s->clk); clk_disable_unprepare(s->clk_ahb); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 95202c1c9a10..ec3b59f9bcb3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1092,10 +1092,19 @@ static const struct tty_port_operations vc_port_ops = { .destruct = vc_port_destruct, }; +/* + * Change # of rows and columns (0 means unchanged/the size of fg_console) + * [this is to be used together with some user program + * like resize that changes the hardware videomode] + */ +#define VC_MAXCOL (32767) +#define VC_MAXROW (32767) + int vc_allocate(unsigned int currcons) /* return 0 on success */ { struct vt_notifier_param param; struct vc_data *vc; + int err; WARN_CONSOLE_UNLOCKED(); @@ -1125,6 +1134,11 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ if (!*vc->vc_uni_pagedir_loc) con_set_default_unimap(vc); + err = -EINVAL; + if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW || + vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size) + goto err_free; + err = -ENOMEM; vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL); if (!vc->vc_screenbuf) goto err_free; @@ -1143,7 +1157,7 @@ err_free: visual_deinit(vc); kfree(vc); vc_cons[currcons].d = NULL; - return -ENOMEM; + return err; } static inline int resize_screen(struct vc_data *vc, int width, int height, @@ -1158,14 +1172,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, return err; } -/* - * Change # of rows and columns (0 means unchanged/the size of fg_console) - * [this is to be used together with some user program - * like resize that changes the hardware videomode] - */ -#define VC_RESIZE_MAXCOL (32767) -#define VC_RESIZE_MAXROW (32767) - /** * vc_do_resize - resizing method for the tty * @tty: tty being resized @@ -1201,7 +1207,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, user = vc->vc_resize_user; vc->vc_resize_user = 0; - if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW) + if (cols > VC_MAXCOL || lines > VC_MAXROW) return -EINVAL; new_cols = (cols ? cols : vc->vc_cols); @@ -1212,7 +1218,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (new_cols == vc->vc_cols && new_rows == vc->vc_rows) return 0; - if (new_screen_size > KMALLOC_MAX_SIZE) + if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size) return -EINVAL; newscreen = kzalloc(new_screen_size, GFP_USER); if (!newscreen) @@ -3396,6 +3402,7 @@ static int __init con_init(void) INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); tty_port_init(&vc->port); visual_init(vc, currcons, 1); + /* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); vc_init(vc, vc->vc_rows, vc->vc_cols, currcons || !vc->vc_sw->con_save_screen); diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c index 3d9fab21a21e..6dea4fc1fc59 100644 --- a/drivers/uio/uio_pdrv_genirq.c +++ b/drivers/uio/uio_pdrv_genirq.c @@ -146,7 +146,7 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev) if (!uioinfo->irq) { ret = platform_get_irq_optional(pdev, 0); uioinfo->irq = ret; - if (ret == -ENXIO && pdev->dev.of_node) + if (ret == -ENXIO) uioinfo->irq = UIO_IRQ_NONE; else if (ret < 0) { dev_err(&pdev->dev, "failed to get IRQ\n"); diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c index 633c52de3bb3..9865750bc31e 100644 --- a/drivers/usb/c67x00/c67x00-sched.c +++ b/drivers/usb/c67x00/c67x00-sched.c @@ -486,7 +486,7 @@ c67x00_giveback_urb(struct c67x00_hcd *c67x00, struct urb *urb, int status) c67x00_release_urb(c67x00, urb); usb_hcd_unlink_urb_from_ep(c67x00_hcd_to_hcd(c67x00), urb); spin_unlock(&c67x00->lock); - usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, urbp->status); + usb_hcd_giveback_urb(c67x00_hcd_to_hcd(c67x00), urb, status); spin_lock(&c67x00->lock); } diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 27749ace2d93..fb2e7a611eb4 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1188,6 +1188,29 @@ static void ci_controller_suspend(struct ci_hdrc *ci) enable_irq(ci->irq); } +/* + * Handle the wakeup interrupt triggered by extcon connector + * We need to call ci_irq again for extcon since the first + * interrupt (wakeup int) only let the controller be out of + * low power mode, but not handle any interrupts. + */ +static void ci_extcon_wakeup_int(struct ci_hdrc *ci) +{ + struct ci_hdrc_cable *cable_id, *cable_vbus; + u32 otgsc = hw_read_otgsc(ci, ~0); + + cable_id = &ci->platdata->id_extcon; + cable_vbus = &ci->platdata->vbus_extcon; + + if (!IS_ERR(cable_id->edev) && ci->is_otg && + (otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS)) + ci_irq(ci->irq, ci); + + if (!IS_ERR(cable_vbus->edev) && ci->is_otg && + (otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS)) + ci_irq(ci->irq, ci); +} + static int ci_controller_resume(struct device *dev) { struct ci_hdrc *ci = dev_get_drvdata(dev); @@ -1220,6 +1243,7 @@ static int ci_controller_resume(struct device *dev) enable_irq(ci->irq); if (ci_otg_is_fsm_mode(ci)) ci_otg_fsm_wakeup_by_srp(ci); + ci_extcon_wakeup_int(ci); } return 0; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index c68217b7dace..a0c5569300cf 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -298,10 +298,10 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, goto skip_to_next_endpoint_or_interface_descriptor; } - /* Ignore blacklisted endpoints */ - if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) { - if (usb_endpoint_is_blacklisted(udev, ifp, d)) { - dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n", + /* Ignore some endpoints */ + if (udev->quirks & USB_QUIRK_ENDPOINT_IGNORE) { + if (usb_endpoint_is_ignored(udev, ifp, d)) { + dev_warn(ddev, "config %d interface %d altsetting %d has an ignored endpoint with address 0x%X, skipping\n", cfgno, inum, asnum, d->bEndpointAddress); goto skip_to_next_endpoint_or_interface_descriptor; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index e0b77674869c..1dae4d88fd69 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -25,17 +25,23 @@ static unsigned int quirk_count; static char quirks_param[128]; -static int quirks_param_set(const char *val, const struct kernel_param *kp) +static int quirks_param_set(const char *value, const struct kernel_param *kp) { - char *p, *field; + char *val, *p, *field; u16 vid, pid; u32 flags; size_t i; int err; + val = kstrdup(value, GFP_KERNEL); + if (!val) + return -ENOMEM; + err = param_set_copystring(val, kp); - if (err) + if (err) { + kfree(val); return err; + } mutex_lock(&quirk_mutex); @@ -60,10 +66,11 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp) if (!quirk_list) { quirk_count = 0; mutex_unlock(&quirk_mutex); + kfree(val); return -ENOMEM; } - for (i = 0, p = (char *)val; p && *p;) { + for (i = 0, p = val; p && *p;) { /* Each entry consists of VID:PID:flags */ field = strsep(&p, ":"); if (!field) @@ -144,6 +151,7 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp) unlock: mutex_unlock(&quirk_mutex); + kfree(val); return 0; } @@ -360,7 +368,11 @@ static const struct usb_device_id usb_quirk_list[] = { /* Sound Devices USBPre2 */ { USB_DEVICE(0x0926, 0x0202), .driver_info = - USB_QUIRK_ENDPOINT_BLACKLIST }, + USB_QUIRK_ENDPOINT_IGNORE }, + + /* Sound Devices MixPre-D */ + { USB_DEVICE(0x0926, 0x0208), .driver_info = + USB_QUIRK_ENDPOINT_IGNORE }, /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = @@ -494,24 +506,25 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { }; /* - * Entries for blacklisted endpoints that should be ignored when parsing - * configuration descriptors. + * Entries for endpoints that should be ignored when parsing configuration + * descriptors. * - * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST. + * Matched for devices with USB_QUIRK_ENDPOINT_IGNORE. */ -static const struct usb_device_id usb_endpoint_blacklist[] = { +static const struct usb_device_id usb_endpoint_ignore[] = { { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, + { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 }, { } }; -bool usb_endpoint_is_blacklisted(struct usb_device *udev, - struct usb_host_interface *intf, - struct usb_endpoint_descriptor *epd) +bool usb_endpoint_is_ignored(struct usb_device *udev, + struct usb_host_interface *intf, + struct usb_endpoint_descriptor *epd) { const struct usb_device_id *id; unsigned int address; - for (id = usb_endpoint_blacklist; id->match_flags; ++id) { + for (id = usb_endpoint_ignore; id->match_flags; ++id) { if (!usb_match_device(udev, id)) continue; diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index d376c725e51f..642a37653ac7 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -37,7 +37,7 @@ extern void usb_authorize_interface(struct usb_interface *); extern void usb_detect_quirks(struct usb_device *udev); extern void usb_detect_interface_quirks(struct usb_device *udev); extern void usb_release_quirk_list(void); -extern bool usb_endpoint_is_blacklisted(struct usb_device *udev, +extern bool usb_endpoint_is_ignored(struct usb_device *udev, struct usb_host_interface *intf, struct usb_endpoint_descriptor *epd); extern int usb_remove_device(struct usb_device *udev); diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index f1acfdee4ac3..05a6fb4c2273 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -337,7 +337,8 @@ static void dwc2_driver_shutdown(struct platform_device *dev) { struct dwc2_hsotg *hsotg = platform_get_drvdata(dev); - disable_irq(hsotg->irq); + dwc2_disable_global_interrupts(hsotg); + synchronize_irq(hsotg->irq); } /** @@ -503,6 +504,7 @@ static int dwc2_driver_probe(struct platform_device *dev) if (hsotg->gadget_enabled) { retval = usb_add_gadget_udc(hsotg->dev, &hsotg->gadget); if (retval) { + hsotg->gadget.udc = NULL; dwc2_hsotg_remove(hsotg); goto error; } @@ -511,7 +513,8 @@ static int dwc2_driver_probe(struct platform_device *dev) return 0; error: - dwc2_lowlevel_hw_disable(hsotg); + if (hsotg->dr_mode != USB_DR_MODE_PERIPHERAL) + dwc2_lowlevel_hw_disable(hsotg); return retval; } diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 389ec4c689c4..de8e5e971f70 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -36,6 +36,8 @@ #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e #define PCI_DEVICE_ID_INTEL_CNPV 0xa3b0 #define PCI_DEVICE_ID_INTEL_ICLLP 0x34ee +#define PCI_DEVICE_ID_INTEL_TGPH 0x43ee +#define PCI_DEVICE_ID_INTEL_JSP 0x4dee #define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511" #define PCI_INTEL_BXT_FUNC_PMU_PWR 4 @@ -350,6 +352,12 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICLLP), (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGPH), + (kernel_ulong_t) &dwc3_pci_intel_properties, }, + + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP), + (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB), (kernel_ulong_t) &dwc3_pci_amd_properties, }, { } /* Terminating Entry */ diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index f2bc8d037067..492f0d70510f 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -216,6 +216,7 @@ #include <linux/freezer.h> #include <linux/module.h> #include <linux/uaccess.h> +#include <asm/unaligned.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> diff --git a/drivers/usb/gadget/function/f_uac1_legacy.c b/drivers/usb/gadget/function/f_uac1_legacy.c index 6677ae932de0..06ee6e901808 100644 --- a/drivers/usb/gadget/function/f_uac1_legacy.c +++ b/drivers/usb/gadget/function/f_uac1_legacy.c @@ -336,7 +336,9 @@ static int f_audio_out_ep_complete(struct usb_ep *ep, struct usb_request *req) /* Copy buffer is full, add it to the play_queue */ if (audio_buf_size - copy_buf->actual < req->actual) { + spin_lock_irq(&audio->lock); list_add_tail(©_buf->list, &audio->play_queue); + spin_unlock_irq(&audio->lock); schedule_work(&audio->playback_work); copy_buf = f_audio_buffer_alloc(audio_buf_size); if (IS_ERR(copy_buf)) diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index db2d4980cb35..3633df6d7610 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -215,10 +215,7 @@ static struct uac2_ac_header_descriptor ac_hdr_desc = { .bDescriptorSubtype = UAC_MS_HEADER, .bcdADC = cpu_to_le16(0x200), .bCategory = UAC2_FUNCTION_IO_BOX, - .wTotalLength = cpu_to_le16(sizeof in_clk_src_desc - + sizeof out_clk_src_desc + sizeof usb_out_it_desc - + sizeof io_in_it_desc + sizeof usb_in_ot_desc - + sizeof io_out_ot_desc), + /* .wTotalLength = DYNAMIC */ .bmControls = 0, }; @@ -501,7 +498,7 @@ static void setup_descriptor(struct f_uac2_opts *opts) as_in_hdr_desc.bTerminalLink = usb_in_ot_desc.bTerminalID; iad_desc.bInterfaceCount = 1; - ac_hdr_desc.wTotalLength = 0; + ac_hdr_desc.wTotalLength = cpu_to_le16(sizeof(ac_hdr_desc)); if (EPIN_EN(opts)) { u16 len = le16_to_cpu(ac_hdr_desc.wTotalLength); diff --git a/drivers/usb/gadget/function/storage_common.h b/drivers/usb/gadget/function/storage_common.h index e5e3a2553aaa..bdeb1e233fc9 100644 --- a/drivers/usb/gadget/function/storage_common.h +++ b/drivers/usb/gadget/function/storage_common.h @@ -172,11 +172,6 @@ enum data_direction { DATA_DIR_NONE }; -static inline u32 get_unaligned_be24(u8 *buf) -{ - return 0xffffff & (u32) get_unaligned_be32(buf - 1); -} - static inline struct fsg_lun *fsg_lun_from_dev(struct device *dev) { return container_of(dev, struct fsg_lun, dev); diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 18372025c452..2d969b7185d4 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -869,7 +869,7 @@ static int usba_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req) u32 status; DBG(DBG_GADGET | DBG_QUEUE, "ep_dequeue: %s, req %p\n", - ep->ep.name, req); + ep->ep.name, _req); spin_lock_irqsave(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c index ccbd1d34eb2a..b157a7abd39f 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_core.c +++ b/drivers/usb/gadget/udc/bdc/bdc_core.c @@ -282,6 +282,7 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit) * in that case reinit is passed as 1 */ if (reinit) { + int i; /* Enable interrupts */ temp = bdc_readl(bdc->regs, BDC_BDCSC); temp |= BDC_GIE; @@ -291,6 +292,9 @@ static void bdc_mem_init(struct bdc *bdc, bool reinit) /* Initialize SRR to 0 */ memset(bdc->srr.sr_bds, 0, NUM_SR_ENTRIES * sizeof(struct bdc_bd)); + /* clear ep flags to avoid post disconnect stops/deconfigs */ + for (i = 1; i < bdc->num_eps; ++i) + bdc->bdc_ep_array[i]->flags = 0; } else { /* One time initiaization only */ /* Enable status report function pointers */ @@ -603,9 +607,14 @@ static int bdc_remove(struct platform_device *pdev) static int bdc_suspend(struct device *dev) { struct bdc *bdc = dev_get_drvdata(dev); + int ret; - clk_disable_unprepare(bdc->clk); - return 0; + /* Halt the controller */ + ret = bdc_stop(bdc); + if (!ret) + clk_disable_unprepare(bdc->clk); + + return ret; } static int bdc_resume(struct device *dev) diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c index d49c6dc1082d..9ddc0b4e92c9 100644 --- a/drivers/usb/gadget/udc/bdc/bdc_ep.c +++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c @@ -615,7 +615,6 @@ int bdc_ep_enable(struct bdc_ep *ep) } bdc_dbg_bd_list(bdc, ep); /* only for ep0: config ep is called for ep0 from connect event */ - ep->flags |= BDC_EP_ENABLED; if (ep->ep_num == 1) return ret; @@ -759,10 +758,13 @@ static int ep_dequeue(struct bdc_ep *ep, struct bdc_req *req) __func__, ep->name, start_bdi, end_bdi); dev_dbg(bdc->dev, "ep_dequeue ep=%p ep->desc=%p\n", ep, (void *)ep->usb_ep.desc); - /* Stop the ep to see where the HW is ? */ - ret = bdc_stop_ep(bdc, ep->ep_num); - /* if there is an issue with stopping ep, then no need to go further */ - if (ret) + /* if still connected, stop the ep to see where the HW is ? */ + if (!(bdc_readl(bdc->regs, BDC_USPC) & BDC_PST_MASK)) { + ret = bdc_stop_ep(bdc, ep->ep_num); + /* if there is an issue, then no need to go further */ + if (ret) + return 0; + } else return 0; /* @@ -1911,7 +1913,9 @@ static int bdc_gadget_ep_disable(struct usb_ep *_ep) __func__, ep->name, ep->flags); if (!(ep->flags & BDC_EP_ENABLED)) { - dev_warn(bdc->dev, "%s is already disabled\n", ep->name); + if (bdc->gadget.speed != USB_SPEED_UNKNOWN) + dev_warn(bdc->dev, "%s is already disabled\n", + ep->name); return 0; } spin_lock_irqsave(&bdc->lock, flags); diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index e50108f9a374..e0b2fb33ed0d 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1980,9 +1980,12 @@ static int gr_ep_init(struct gr_udc *dev, int num, int is_in, u32 maxplimit) if (num == 0) { _req = gr_alloc_request(&ep->ep, GFP_ATOMIC); + if (!_req) + return -ENOMEM; + buf = devm_kzalloc(dev->dev, PAGE_SIZE, GFP_DMA | GFP_ATOMIC); - if (!_req || !buf) { - /* possible _req freed by gr_probe via gr_remove */ + if (!buf) { + gr_free_request(&ep->ep, _req); return -ENOMEM; } diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index b6bbe2e448ba..19de7392e17f 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -3778,8 +3778,10 @@ static int net2280_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; done: - if (dev) + if (dev) { net2280_remove(pdev); + kfree(dev); + } return retval; } diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c index cbc45941a699..8a45362155c5 100644 --- a/drivers/usb/host/ehci-platform.c +++ b/drivers/usb/host/ehci-platform.c @@ -457,10 +457,6 @@ static int ehci_platform_resume(struct device *dev) ehci_resume(hcd, priv->reset_on_resume); - pm_runtime_disable(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - if (priv->quirk_poll) quirk_poll_init(priv); diff --git a/drivers/usb/host/ohci-platform.c b/drivers/usb/host/ohci-platform.c index f40112c5920d..65a1c3fdc88c 100644 --- a/drivers/usb/host/ohci-platform.c +++ b/drivers/usb/host/ohci-platform.c @@ -301,11 +301,6 @@ static int ohci_platform_resume(struct device *dev) } ohci_resume(hcd, false); - - pm_runtime_disable(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - return 0; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index ad05c27b3a7b..31f4090a2286 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -634,6 +634,9 @@ 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. */ @@ -647,9 +650,16 @@ 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-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index fea555570ad4..45c54d56ecbd 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -557,6 +557,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep, if (is_fs_or_ls(speed) && !has_tt) return false; + /* skip endpoint with zero maxpkt */ + if (usb_endpoint_maxp(&ep->desc) == 0) + return false; + return true; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 2f67353d3cac..ec24b6ae22d6 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -55,7 +55,10 @@ #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba #define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb #define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc +#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 +#define PCI_DEVICE_ID_ASMEDIA_1142_XHCI 0x1242 +#define PCI_DEVICE_ID_ASMEDIA_2142_XHCI 0x2142 static const char hcd_name[] = "xhci_hcd"; @@ -245,11 +248,15 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_BROKEN_STREAMS; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && - pdev->device == 0x1042) + pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) xhci->quirks |= XHCI_BROKEN_STREAMS; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && - pdev->device == 0x1142) + pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + (pdev->device == PCI_DEVICE_ID_ASMEDIA_1142_XHCI || + pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI)) + xhci->quirks |= XHCI_NO_64BIT_SUPPORT; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 64fb384695d0..19c5eee20eb4 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -415,15 +415,7 @@ static int __maybe_unused xhci_plat_resume(struct device *dev) if (ret) return ret; - ret = xhci_resume(xhci, 0); - if (ret) - return ret; - - pm_runtime_disable(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - - return 0; + return xhci_resume(xhci, 0); } static int __maybe_unused xhci_plat_runtime_suspend(struct device *dev) diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c index f8bd1d57e795..98b6b17fca64 100644 --- a/drivers/usb/mtu3/mtu3_core.c +++ b/drivers/usb/mtu3/mtu3_core.c @@ -130,8 +130,12 @@ static void mtu3_device_disable(struct mtu3 *mtu) mtu3_setbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_DIS | SSUSB_U2_PORT_PDN); - if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) + if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) { mtu3_clrbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_OTG_SEL); + if (mtu->is_u3_ip) + mtu3_clrbits(ibase, SSUSB_U3_CTRL(0), + SSUSB_U3_PORT_DUAL_MODE); + } mtu3_setbits(ibase, U3D_SSUSB_IP_PW_CTRL2, SSUSB_IP_DEV_PDN); } diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index dcdd541b3291..390bc4b25045 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -81,6 +81,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x4348, 0x5523) }, + { USB_DEVICE(0x1a86, 0x7522) }, { USB_DEVICE(0x1a86, 0x7523) }, { USB_DEVICE(0x1a86, 0x5523) }, { }, diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f5143eedbc48..a90801ef0055 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -272,6 +272,8 @@ static struct usb_serial_driver cp210x_device = { .break_ctl = cp210x_break_ctl, .set_termios = cp210x_set_termios, .tx_empty = cp210x_tx_empty, + .throttle = usb_serial_generic_throttle, + .unthrottle = usb_serial_generic_unthrottle, .tiocmget = cp210x_tiocmget, .tiocmset = cp210x_tiocmset, .attach = cp210x_attach, @@ -915,6 +917,7 @@ static void cp210x_get_termios_port(struct usb_serial_port *port, u32 baud; u16 bits; u32 ctl_hs; + u32 flow_repl; cp210x_read_u32_reg(port, CP210X_GET_BAUDRATE, &baud); @@ -1015,6 +1018,22 @@ static void cp210x_get_termios_port(struct usb_serial_port *port, ctl_hs = le32_to_cpu(flow_ctl.ulControlHandshake); if (ctl_hs & CP210X_SERIAL_CTS_HANDSHAKE) { dev_dbg(dev, "%s - flow control = CRTSCTS\n", __func__); + /* + * When the port is closed, the CP210x hardware disables + * auto-RTS and RTS is deasserted but it leaves auto-CTS when + * in hardware flow control mode. When re-opening the port, if + * auto-CTS is enabled on the cp210x, then auto-RTS must be + * re-enabled in the driver. + */ + flow_repl = le32_to_cpu(flow_ctl.ulFlowReplace); + flow_repl &= ~CP210X_SERIAL_RTS_MASK; + flow_repl |= CP210X_SERIAL_RTS_SHIFT(CP210X_SERIAL_RTS_FLOW_CTL); + flow_ctl.ulFlowReplace = cpu_to_le32(flow_repl); + cp210x_write_reg_block(port, + CP210X_SET_FLOW, + &flow_ctl, + sizeof(flow_ctl)); + cflag |= CRTSCTS; } else { dev_dbg(dev, "%s - flow control = NONE\n", __func__); diff --git a/drivers/usb/serial/cypress_m8.c b/drivers/usb/serial/cypress_m8.c index 72d3ae1ebc64..77681229486e 100644 --- a/drivers/usb/serial/cypress_m8.c +++ b/drivers/usb/serial/cypress_m8.c @@ -59,6 +59,7 @@ static const struct usb_device_id id_table_earthmate[] = { static const struct usb_device_id id_table_cyphidcomrs232[] = { { USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) }, + { USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) }, { USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) }, { USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) }, { } /* Terminating entry */ @@ -73,6 +74,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB) }, { USB_DEVICE(VENDOR_ID_DELORME, PRODUCT_ID_EARTHMATEUSB_LT20) }, { USB_DEVICE(VENDOR_ID_CYPRESS, PRODUCT_ID_CYPHIDCOM) }, + { USB_DEVICE(VENDOR_ID_SAI, PRODUCT_ID_CYPHIDCOM) }, { USB_DEVICE(VENDOR_ID_POWERCOM, PRODUCT_ID_UPS) }, { USB_DEVICE(VENDOR_ID_FRWD, PRODUCT_ID_CYPHIDCOM_FRWD) }, { USB_DEVICE(VENDOR_ID_DAZZLE, PRODUCT_ID_CA42) }, diff --git a/drivers/usb/serial/cypress_m8.h b/drivers/usb/serial/cypress_m8.h index 35e223751c0e..16b7410ad057 100644 --- a/drivers/usb/serial/cypress_m8.h +++ b/drivers/usb/serial/cypress_m8.h @@ -25,6 +25,9 @@ #define VENDOR_ID_CYPRESS 0x04b4 #define PRODUCT_ID_CYPHIDCOM 0x5500 +/* Simply Automated HID->COM UPB PIM (using Cypress PID 0x5500) */ +#define VENDOR_ID_SAI 0x17dd + /* FRWD Dongle - a GPS sports watch */ #define VENDOR_ID_FRWD 0x6737 #define PRODUCT_ID_CYPHIDCOM_FRWD 0x0001 diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 0346b046cca2..13aaf0687367 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -2437,12 +2437,11 @@ static int ftdi_prepare_write_buffer(struct usb_serial_port *port, #define FTDI_RS_ERR_MASK (FTDI_RS_BI | FTDI_RS_PE | FTDI_RS_FE | FTDI_RS_OE) static int ftdi_process_packet(struct usb_serial_port *port, - struct ftdi_private *priv, char *packet, int len) + struct ftdi_private *priv, unsigned char *buf, int len) { + unsigned char status; int i; - char status; char flag; - char *ch; if (len < 2) { dev_dbg(&port->dev, "malformed packet\n"); @@ -2452,7 +2451,7 @@ static int ftdi_process_packet(struct usb_serial_port *port, /* Compare new line status to the old one, signal if different/ N.B. packet may be processed more than once, but differences are only processed once. */ - status = packet[0] & FTDI_STATUS_B0_MASK; + status = buf[0] & FTDI_STATUS_B0_MASK; if (status != priv->prev_status) { char diff_status = status ^ priv->prev_status; @@ -2478,13 +2477,12 @@ static int ftdi_process_packet(struct usb_serial_port *port, } /* save if the transmitter is empty or not */ - if (packet[1] & FTDI_RS_TEMT) + if (buf[1] & FTDI_RS_TEMT) priv->transmit_empty = 1; else priv->transmit_empty = 0; - len -= 2; - if (!len) + if (len == 2) return 0; /* status only */ /* @@ -2492,40 +2490,41 @@ static int ftdi_process_packet(struct usb_serial_port *port, * data payload to avoid over-reporting. */ flag = TTY_NORMAL; - if (packet[1] & FTDI_RS_ERR_MASK) { + if (buf[1] & FTDI_RS_ERR_MASK) { /* Break takes precedence over parity, which takes precedence * over framing errors */ - if (packet[1] & FTDI_RS_BI) { + if (buf[1] & FTDI_RS_BI) { flag = TTY_BREAK; port->icount.brk++; usb_serial_handle_break(port); - } else if (packet[1] & FTDI_RS_PE) { + } else if (buf[1] & FTDI_RS_PE) { flag = TTY_PARITY; port->icount.parity++; - } else if (packet[1] & FTDI_RS_FE) { + } else if (buf[1] & FTDI_RS_FE) { flag = TTY_FRAME; port->icount.frame++; } /* Overrun is special, not associated with a char */ - if (packet[1] & FTDI_RS_OE) { + if (buf[1] & FTDI_RS_OE) { port->icount.overrun++; tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } } - port->icount.rx += len; - ch = packet + 2; + port->icount.rx += len - 2; if (port->port.console && port->sysrq) { - for (i = 0; i < len; i++, ch++) { - if (!usb_serial_handle_sysrq_char(port, *ch)) - tty_insert_flip_char(&port->port, *ch, flag); + for (i = 2; i < len; i++) { + if (usb_serial_handle_sysrq_char(port, buf[i])) + continue; + tty_insert_flip_char(&port->port, buf[i], flag); } } else { - tty_insert_flip_string_fixed_flag(&port->port, ch, flag, len); + tty_insert_flip_string_fixed_flag(&port->port, buf + 2, flag, + len - 2); } - return len; + return len - 2; } static void ftdi_process_read_urb(struct urb *urb) diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c index d5bff69b1769..ffbb2a8901b2 100644 --- a/drivers/usb/serial/iuu_phoenix.c +++ b/drivers/usb/serial/iuu_phoenix.c @@ -353,10 +353,11 @@ static void iuu_led_activity_on(struct urb *urb) struct usb_serial_port *port = urb->context; int result; char *buf_ptr = port->write_urb->transfer_buffer; - *buf_ptr++ = IUU_SET_LED; + if (xmas) { - get_random_bytes(buf_ptr, 6); - *(buf_ptr+7) = 1; + buf_ptr[0] = IUU_SET_LED; + get_random_bytes(buf_ptr + 1, 6); + buf_ptr[7] = 1; } else { iuu_rgbf_fill_buffer(buf_ptr, 255, 255, 0, 0, 0, 0, 255); } @@ -374,13 +375,14 @@ static void iuu_led_activity_off(struct urb *urb) struct usb_serial_port *port = urb->context; int result; char *buf_ptr = port->write_urb->transfer_buffer; + if (xmas) { iuu_rxcmd(urb); return; - } else { - *buf_ptr++ = IUU_SET_LED; - iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255); } + + iuu_rgbf_fill_buffer(buf_ptr, 0, 0, 255, 255, 0, 0, 255); + usb_fill_bulk_urb(port->write_urb, port->serial->dev, usb_sndbulkpipe(port->serial->dev, port->bulk_out_endpointAddress), @@ -697,14 +699,16 @@ static int iuu_uart_write(struct tty_struct *tty, struct usb_serial_port *port, struct iuu_private *priv = usb_get_serial_port_data(port); unsigned long flags; - if (count > 256) - return -ENOMEM; - spin_lock_irqsave(&priv->lock, flags); + count = min(count, 256 - priv->writelen); + if (count == 0) + goto out; + /* fill the buffer */ memcpy(priv->writebuf + priv->writelen, buf, count); priv->writelen += count; +out: spin_unlock_irqrestore(&priv->lock, flags); return count; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 254a8bbeea67..9b7cee98ea60 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -245,6 +245,7 @@ static void option_instat_callback(struct urb *urb); /* These Quectel products use Quectel's vendor ID */ #define QUECTEL_PRODUCT_EC21 0x0121 #define QUECTEL_PRODUCT_EC25 0x0125 +#define QUECTEL_PRODUCT_EG95 0x0195 #define QUECTEL_PRODUCT_BG96 0x0296 #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM12 0x0512 @@ -1097,6 +1098,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) }, { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25), .driver_info = RSVD(4) }, + { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95), + .driver_info = RSVD(4) }, { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), @@ -2028,6 +2031,9 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ .driver_info = RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ + { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ + { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index d147feae83e6..0f60363c1bbc 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -155,6 +155,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9062)}, /* Sierra Wireless EM7305 QDL */ {DEVICE_SWI(0x1199, 0x9063)}, /* Sierra Wireless EM7305 */ {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index f6c3681fa2e9..88275842219e 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2328,7 +2328,7 @@ UNUSUAL_DEV( 0x357d, 0x7788, 0x0114, 0x0114, "JMicron", "USB to ATA/ATAPI Bridge", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_BROKEN_FUA ), + US_FL_BROKEN_FUA | US_FL_IGNORE_UAS ), /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */ UNUSUAL_DEV( 0x4102, 0x1020, 0x0100, 0x0100, diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 987b4d311fde..de7ac0cd6c5c 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -31,12 +31,14 @@ struct vfio_pci_ioeventfd { struct list_head next; + struct vfio_pci_device *vdev; struct virqfd *virqfd; void __iomem *addr; uint64_t data; loff_t pos; int bar; int count; + bool test_mem; }; struct vfio_pci_irq_ctx { diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 83f81d24df78..eaa1975ebae2 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -37,17 +37,70 @@ #define vfio_ioread8 ioread8 #define vfio_iowrite8 iowrite8 +#define VFIO_IOWRITE(size) \ +static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + vfio_iowrite##size(val, io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOWRITE(8) +VFIO_IOWRITE(16) +VFIO_IOWRITE(32) +#ifdef iowrite64 +VFIO_IOWRITE(64) +#endif + +#define VFIO_IOREAD(size) \ +static int vfio_pci_ioread##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + *val = vfio_ioread##size(io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOREAD(8) +VFIO_IOREAD(16) +VFIO_IOREAD(32) + /* * Read or write from an __iomem region (MMIO or I/O port) with an excluded * range which is inaccessible. The excluded range drops writes and fills * reads with -1. This is intended for handling MSI-X vector tables and * leftover space for ROM BARs. */ -static ssize_t do_io_rw(void __iomem *io, char __user *buf, +static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, size_t x_end, bool iswrite) { ssize_t done = 0; + int ret; while (count) { size_t fillable, filled; @@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 4)) return -EFAULT; - vfio_iowrite32(val, io + off); + ret = vfio_pci_iowrite32(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread32(io + off); + ret = vfio_pci_ioread32(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 4)) return -EFAULT; @@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 2)) return -EFAULT; - vfio_iowrite16(val, io + off); + ret = vfio_pci_iowrite16(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread16(io + off); + ret = vfio_pci_ioread16(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 2)) return -EFAULT; @@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 1)) return -EFAULT; - vfio_iowrite8(val, io + off); + ret = vfio_pci_iowrite8(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread8(io + off); + ret = vfio_pci_ioread8(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 1)) return -EFAULT; @@ -178,14 +249,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, count = min(count, (size_t)(end - pos)); - if (res->flags & IORESOURCE_MEM) { - down_read(&vdev->memory_lock); - if (!__vfio_pci_memory_enabled(vdev)) { - up_read(&vdev->memory_lock); - return -EIO; - } - } - if (bar == PCI_ROM_RESOURCE) { /* * The ROM can fill less space than the BAR, so we start the @@ -213,7 +276,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, x_end = vdev->msix_offset + vdev->msix_size; } - done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite); + done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); if (done >= 0) *ppos += done; @@ -221,9 +285,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, if (bar == PCI_ROM_RESOURCE) pci_unmap_rom(pdev, io); out: - if (res->flags & IORESOURCE_MEM) - up_read(&vdev->memory_lock); - return done; } @@ -278,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, return ret; } - done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite); + /* + * VGA MMIO is a legacy, non-BAR resource that hopefully allows + * probing, so we don't currently worry about access in relation + * to the memory enable bit in the command register. + */ + done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); vga_put(vdev->pdev, rsrc); @@ -296,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) switch (ioeventfd->count) { case 1: - vfio_iowrite8(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_iowrite16(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_iowrite32(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_iowrite64(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #endif } @@ -378,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, goto out_unlock; } + ioeventfd->vdev = vdev; ioeventfd->addr = vdev->barmap[bar] + pos; ioeventfd->data = data; ioeventfd->pos = pos; ioeventfd->bar = bar; ioeventfd->count = count; + ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, NULL, NULL, &ioeventfd->virqfd, fd); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 88ce114790d7..f63f84a25725 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1215,7 +1215,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - switch (v_req.type) { + switch (vhost32_to_cpu(vq, v_req.type)) { case VIRTIO_SCSI_T_TMF: vc.req = &v_req.tmf; vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req); diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 00dddf6e08b0..2d2ee17052e8 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -32,6 +32,8 @@ #include <linux/linux_logo.h> #include <linux/font.h> +#define NEWPORT_LEN 0x10000 + #define FONT_DATA ((unsigned char *)font_vga_8x16.data) /* borrowed from fbcon.c */ @@ -43,6 +45,7 @@ static unsigned char *font_data[MAX_NR_CONSOLES]; static struct newport_regs *npregs; +static unsigned long newport_addr; static int logo_active; static int topscan; @@ -702,7 +705,6 @@ const struct consw newport_con = { static int newport_probe(struct gio_device *dev, const struct gio_device_id *id) { - unsigned long newport_addr; int err; if (!dev->resource.start) @@ -712,7 +714,7 @@ static int newport_probe(struct gio_device *dev, return -EBUSY; /* we only support one Newport as console */ newport_addr = dev->resource.start + 0xF0000; - if (!request_mem_region(newport_addr, 0x10000, "Newport")) + if (!request_mem_region(newport_addr, NEWPORT_LEN, "Newport")) return -ENODEV; npregs = (struct newport_regs *)/* ioremap cannot fail */ @@ -720,6 +722,11 @@ static int newport_probe(struct gio_device *dev, console_lock(); err = do_take_over_console(&newport_con, 0, MAX_NR_CONSOLES - 1, 1); console_unlock(); + + if (err) { + iounmap((void *)npregs); + release_mem_region(newport_addr, NEWPORT_LEN); + } return err; } @@ -727,6 +734,7 @@ static void newport_remove(struct gio_device *dev) { give_up_console(&newport_con); iounmap((void *)npregs); + release_mem_region(newport_addr, NEWPORT_LEN); } static struct gio_device_id newport_ids[] = { diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index bfaa9ec4bc1f..e079b910feb2 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -251,6 +251,10 @@ static void vgacon_scrollback_update(struct vc_data *c, int t, int count) p = (void *) (c->vc_origin + t * c->vc_size_row); while (count--) { + if ((vgacon_scrollback_cur->tail + c->vc_size_row) > + vgacon_scrollback_cur->size) + vgacon_scrollback_cur->tail = 0; + scr_memcpyw(vgacon_scrollback_cur->data + vgacon_scrollback_cur->tail, p, c->vc_size_row); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index ca935c09a261..35ebeeccde4d 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = info->var.xoffset + rs; region.dy = 0; region.width = rw; @@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset + bs; region.width = rs; diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index dfa9a8aa4509..78f3a5621478 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset; region.height = rw; @@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset + bs; region.dy = 0; region.height = info->var.yres_virtual; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index ce08251bfd38..fd098ff17574 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset + rs; region.height = rw; @@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset; region.height = info->var.yres; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 1936afc78fec..e165a3fad29a 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dy = 0; region.dx = info->var.xoffset; region.width = rw; @@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dy = info->var.yoffset; region.dx = info->var.xoffset; region.height = bh; diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c index 5d3a444083f7..2018e1ca33eb 100644 --- a/drivers/video/fbdev/neofb.c +++ b/drivers/video/fbdev/neofb.c @@ -1820,6 +1820,7 @@ static int neo_scan_monitor(struct fb_info *info) #else printk(KERN_ERR "neofb: Only 640x480, 800x600/480 and 1024x768 panels are currently supported\n"); + kfree(info->monspecs.modedb); return -1; #endif default: diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c index 7252d22dd117..bfc5c4c5a26a 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c @@ -833,7 +833,7 @@ static const struct dss_features omap34xx_dss_feats = { }; static const struct dss_features omap3630_dss_feats = { - .fck_div_max = 32, + .fck_div_max = 31, .dss_fck_multiplier = 1, .parent_clk_name = "dpll4_ck", .dpi_select_source = &dss_dpi_select_source_omap2_omap3, diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index d59c8a59f582..90dee3e6f8bc 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2446,8 +2446,8 @@ static int pxafb_remove(struct platform_device *dev) free_pages_exact(fbi->video_mem, fbi->video_mem_size); - dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff, - fbi->dma_buff_phys); + dma_free_coherent(&dev->dev, fbi->dma_buff_size, fbi->dma_buff, + fbi->dma_buff_phys); return 0; } diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index 47b78f0138c3..cb608b76cc40 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -2158,6 +2158,8 @@ static int savage_init_fb_info(struct fb_info *info, struct pci_dev *dev, info->flags |= FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_IMAGEBLIT; + else + kfree(info->pixmap.addr); } #endif return err; diff --git a/drivers/video/fbdev/sm712fb.c b/drivers/video/fbdev/sm712fb.c index f1dcc6766d1e..1781ca697f66 100644 --- a/drivers/video/fbdev/sm712fb.c +++ b/drivers/video/fbdev/sm712fb.c @@ -1429,6 +1429,8 @@ static int smtc_map_smem(struct smtcfb_info *sfb, static void smtc_unmap_smem(struct smtcfb_info *sfb) { if (sfb && sfb->fb->screen_base) { + if (sfb->chip_id == 0x720) + sfb->fb->screen_base -= 0x00200000; iounmap(sfb->fb->screen_base); sfb->fb->screen_base = NULL; } diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index 439565cae7ab..27c92315e01c 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 = 1; /* 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/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c index 2307b0329aec..95bfdb8ac8a2 100644 --- a/drivers/virt/vboxguest/vboxguest_core.c +++ b/drivers/virt/vboxguest/vboxguest_core.c @@ -1443,7 +1443,7 @@ static int vbg_ioctl_change_guest_capabilities(struct vbg_dev *gdev, or_mask = caps->u.in.or_mask; not_mask = caps->u.in.not_mask; - if ((or_mask | not_mask) & ~VMMDEV_EVENT_VALID_EVENT_MASK) + if ((or_mask | not_mask) & ~VMMDEV_GUEST_CAPABILITIES_MASK) return -EINVAL; ret = vbg_set_session_capabilities(gdev, session, or_mask, not_mask, @@ -1519,7 +1519,8 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data) /* For VMMDEV_REQUEST hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT */ if (req_no_size == VBG_IOCTL_VMMDEV_REQUEST(0) || - req == VBG_IOCTL_VMMDEV_REQUEST_BIG) + req == VBG_IOCTL_VMMDEV_REQUEST_BIG || + req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT) return vbg_ioctl_vmmrequest(gdev, session, data); if (hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT) @@ -1557,6 +1558,7 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data) case VBG_IOCTL_HGCM_CALL(0): return vbg_ioctl_hgcm_call(gdev, session, f32bit, data); case VBG_IOCTL_LOG(0): + case VBG_IOCTL_LOG_ALT(0): return vbg_ioctl_log(data); } diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h index 4188c12b839f..77c3a9c8255d 100644 --- a/drivers/virt/vboxguest/vboxguest_core.h +++ b/drivers/virt/vboxguest/vboxguest_core.h @@ -15,6 +15,21 @@ #include <linux/vboxguest.h> #include "vmmdev.h" +/* + * The mainline kernel version (this version) of the vboxguest module + * contained a bug where it defined VBGL_IOCTL_VMMDEV_REQUEST_BIG and + * VBGL_IOCTL_LOG using _IOC(_IOC_READ | _IOC_WRITE, 'V', ...) instead + * of _IO(V, ...) as the out of tree VirtualBox upstream version does. + * + * These _ALT definitions keep compatibility with the wrong defines the + * mainline kernel version used for a while. + * Note the VirtualBox userspace bits have always been built against + * VirtualBox upstream's headers, so this is likely not necessary. But + * we must never break our ABI so we keep these around to be 100% sure. + */ +#define VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT _IOC(_IOC_READ | _IOC_WRITE, 'V', 3, 0) +#define VBG_IOCTL_LOG_ALT(s) _IOC(_IOC_READ | _IOC_WRITE, 'V', 9, s) + struct vbg_session; /** VBox guest memory balloon. */ diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c index 6e8c0f1c1056..32c2c52f7e84 100644 --- a/drivers/virt/vboxguest/vboxguest_linux.c +++ b/drivers/virt/vboxguest/vboxguest_linux.c @@ -131,7 +131,8 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req, * the need for a bounce-buffer and another copy later on. */ is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) || - req == VBG_IOCTL_VMMDEV_REQUEST_BIG; + req == VBG_IOCTL_VMMDEV_REQUEST_BIG || + req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT; if (is_vmmdev_req) buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT, diff --git a/drivers/virt/vboxguest/vmmdev.h b/drivers/virt/vboxguest/vmmdev.h index 6337b8d75d96..21f408120e3f 100644 --- a/drivers/virt/vboxguest/vmmdev.h +++ b/drivers/virt/vboxguest/vmmdev.h @@ -206,6 +206,8 @@ VMMDEV_ASSERT_SIZE(vmmdev_mask, 24 + 8); * not. */ #define VMMDEV_GUEST_SUPPORTS_GRAPHICS BIT(2) +/* The mask of valid capabilities, for sanity checking. */ +#define VMMDEV_GUEST_CAPABILITIES_MASK 0x00000007U /** struct vmmdev_hypervisorinfo - Hypervisor info structure. */ struct vmmdev_hypervisorinfo { diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index f9aed4e41700..d3e0c2182111 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -528,10 +528,14 @@ static int init_vqs(struct virtio_balloon *vb) static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, - &vb->config_read_bitmap)) + &vb->config_read_bitmap)) { virtio_cread(vb->vdev, struct virtio_balloon_config, free_page_report_cmd_id, &vb->cmd_id_received_cache); + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache); + } return vb->cmd_id_received_cache; } diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index ff5cf1b48a4d..491ba2d973ac 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -677,9 +677,9 @@ static int __init watchdog_init(int sioaddr) * into the module have been registered yet. */ watchdog.sioaddr = sioaddr; - watchdog.ident.options = WDIOC_SETTIMEOUT - | WDIOF_MAGICCLOSE - | WDIOF_KEEPALIVEPING; + watchdog.ident.options = WDIOF_MAGICCLOSE + | WDIOF_KEEPALIVEPING + | WDIOF_CARDRESET; snprintf(watchdog.ident.identity, sizeof(watchdog.ident.identity), "%s watchdog", @@ -693,6 +693,13 @@ static int __init watchdog_init(int sioaddr) wdt_conf = superio_inb(sioaddr, F71808FG_REG_WDT_CONF); watchdog.caused_reboot = wdt_conf & BIT(F71808FG_FLAG_WDTMOUT_STS); + /* + * We don't want WDTMOUT_STS to stick around till regular reboot. + * Write 1 to the bit to clear it to zero. + */ + superio_outb(sioaddr, F71808FG_REG_WDT_CONF, + wdt_conf | BIT(F71808FG_FLAG_WDTMOUT_STS)); + superio_exit(sioaddr); err = watchdog_set_timeout(timeout); diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 4e0b308eadee..00bba772afbc 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -947,6 +947,15 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) if (IS_ERR_OR_NULL(watchdog_kworker)) return -ENODEV; + device_initialize(&wd_data->dev); + wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id); + wd_data->dev.class = &watchdog_class; + wd_data->dev.parent = wdd->parent; + wd_data->dev.groups = wdd->groups; + wd_data->dev.release = watchdog_core_data_release; + dev_set_drvdata(&wd_data->dev, wdd); + dev_set_name(&wd_data->dev, "watchdog%d", wdd->id); + kthread_init_work(&wd_data->work, watchdog_ping_work); hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); wd_data->timer.function = watchdog_timer_expired; @@ -967,15 +976,6 @@ static int watchdog_cdev_register(struct watchdog_device *wdd) } } - device_initialize(&wd_data->dev); - wd_data->dev.devt = MKDEV(MAJOR(watchdog_devt), wdd->id); - wd_data->dev.class = &watchdog_class; - wd_data->dev.parent = wdd->parent; - wd_data->dev.groups = wdd->groups; - wd_data->dev.release = watchdog_core_data_release; - dev_set_drvdata(&wd_data->dev, wdd); - dev_set_name(&wd_data->dev, "watchdog%d", wdd->id); - /* Fill in the data structures */ cdev_init(&wd_data->cdev, &watchdog_fops); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index b5c8b70380bd..dcc255226e21 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -578,11 +578,13 @@ static int add_ballooned_pages(int nr_pages) if (xen_hotplug_unpopulated) { st = reserve_additional_memory(); if (st != BP_ECANCELED) { + int rc; + mutex_unlock(&balloon_mutex); - wait_event(balloon_wq, + rc = wait_event_interruptible(balloon_wq, !list_empty(&ballooned_pages)); mutex_lock(&balloon_mutex); - return 0; + return rc ? -ENOMEM : 0; } } @@ -641,6 +643,12 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) out_undo: mutex_unlock(&balloon_mutex); free_xenballooned_pages(pgno, pages); + /* + * NB: free_xenballooned_pages will only subtract pgno pages, but since + * target_unpopulated is incremented with nr_pages at the start we need + * to remove the remaining ones also, or accounting will be screwed. + */ + balloon_stats.target_unpopulated -= nr_pages - pgno; return ret; } EXPORT_SYMBOL(alloc_xenballooned_pages); diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 2c4f324f8626..da799929087d 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -641,6 +641,14 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, goto fail_detach; } + /* Check that we have zero offset. */ + if (sgt->sgl->offset) { + ret = ERR_PTR(-EINVAL); + pr_debug("DMA buffer has %d bytes offset, user-space expects 0\n", + sgt->sgl->offset); + goto fail_unmap; + } + /* Check number of pages that imported buffer has. */ if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) { ret = ERR_PTR(-EINVAL); diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 15a99f9c7253..39def020a074 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -500,10 +500,9 @@ void v9fs_session_close(struct v9fs_session_info *v9ses) } #ifdef CONFIG_9P_FSCACHE - if (v9ses->fscache) { + if (v9ses->fscache) v9fs_cache_session_put_cookie(v9ses); - kfree(v9ses->cachetag); - } + kfree(v9ses->cachetag); #endif kfree(v9ses->uname); kfree(v9ses->aname); diff --git a/fs/Kconfig b/fs/Kconfig index bfb1c6095c7a..c2d166973d71 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -246,6 +246,7 @@ 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" @@ -261,6 +262,7 @@ source "fs/romfs/Kconfig" source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" +source "fs/aufs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Makefile b/fs/Makefile index c9aea23aba56..99d54d031b24 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -130,3 +130,5 @@ obj-$(CONFIG_F2FS_FS) += f2fs/ obj-$(CONFIG_CEPH_FS) += ceph/ obj-$(CONFIG_PSTORE) += pstore/ obj-$(CONFIG_EFIVAR_FS) += efivarfs/ +obj-$(CONFIG_YAFFS_FS) += yaffs2/ +obj-$(CONFIG_AUFS_FS) += aufs/ diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 02e976ca5732..51ee3dd79700 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -92,8 +92,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; alist->preferred = index; have_result = true; diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index e3aa013c2177..081b7e5b13f5 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -92,8 +92,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; alist->preferred = index; have_result = true; diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig new file mode 100644 index 000000000000..9f436425716a --- /dev/null +++ b/fs/aufs/Kconfig @@ -0,0 +1,199 @@ +# SPDX-License-Identifier: GPL-2.0 +config AUFS_FS + tristate "Aufs (Advanced multi layered unification filesystem) support" + help + Aufs is a stackable unification filesystem such as Unionfs, + which unifies several directories and provides a merged single + directory. + In the early days, aufs was entirely re-designed and + re-implemented Unionfs Version 1.x series. Introducing many + original ideas, approaches and improvements, it becomes totally + different from Unionfs while keeping the basic features. + +if AUFS_FS +choice + prompt "Maximum number of branches" + default AUFS_BRANCH_MAX_127 + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_127 + bool "127" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_511 + bool "511" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_1023 + bool "1023" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_32767 + bool "32767" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +endchoice + +config AUFS_SBILIST + bool + depends on AUFS_MAGIC_SYSRQ || PROC_FS + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq or /proc, enabled automatically. + +config AUFS_HNOTIFY + bool "Detect direct branch access (bypassing aufs)" + help + If you want to modify files on branches directly, eg. bypassing aufs, + and want aufs to detect the changes of them fully, then enable this + option and use 'udba=notify' mount option. + Currently there is only one available configuration, "fsnotify". + It will have a negative impact to the performance. + See detail in aufs.5. + +choice + prompt "method" if AUFS_HNOTIFY + default AUFS_HFSNOTIFY +config AUFS_HFSNOTIFY + bool "fsnotify" + select FSNOTIFY +endchoice + +config AUFS_EXPORT + bool "NFS-exportable aufs" + depends on EXPORTFS + help + If you want to export your mounted aufs via NFS, then enable this + option. There are several requirements for this configuration. + See detail in aufs.5. + +config AUFS_INO_T_64 + bool + depends on AUFS_EXPORT + depends on 64BIT && !(ALPHA || S390) + default y + help + Automatic configuration for internal use. + /* typedef unsigned long/int __kernel_ino_t */ + /* alpha and s390x are int */ + +config AUFS_XATTR + bool "support for XATTR/EA (including Security Labels)" + help + If your branch fs supports XATTR/EA and you want to make them + available in aufs too, then enable this opsion and specify the + branch attributes for EA. + See detail in aufs.5. + +config AUFS_FHSM + bool "File-based Hierarchical Storage Management" + help + Hierarchical Storage Management (or HSM) is a well-known feature + in the storage world. Aufs provides this feature as file-based. + with multiple branches. + These multiple branches are prioritized, ie. the topmost one + should be the fastest drive and be used heavily. + +config AUFS_RDU + bool "Readdir in userspace" + help + Aufs has two methods to provide a merged view for a directory, + by a user-space library and by kernel-space natively. The latter + is always enabled but sometimes large and slow. + If you enable this option, install the library in aufs2-util + package, and set some environment variables for your readdir(3), + then the work will be handled in user-space which generally + shows better performance in most cases. + See detail in aufs.5. + +config AUFS_DIRREN + bool "Workaround for rename(2)-ing a directory" + help + By default, aufs returns EXDEV error in renameing a dir who has + his child on the lower branch, since it is a bad idea to issue + rename(2) internally for every lower branch. But user may not + accept this behaviour. So here is a workaround to allow such + rename(2) and store some extra infromation on the writable + branch. Obviously this costs high (and I don't like it). + To use this feature, you need to enable this configuration AND + to specify the mount option `dirren.' + See details in aufs.5 and the design documents. + +config AUFS_SHWH + bool "Show whiteouts" + help + If you want to make the whiteouts in aufs visible, then enable + this option and specify 'shwh' mount option. Although it may + sounds like philosophy or something, but in technically it + simply shows the name of whiteout with keeping its behaviour. + +config AUFS_BR_RAMFS + bool "Ramfs (initramfs/rootfs) as an aufs branch" + help + If you want to use ramfs as an aufs branch fs, then enable this + option. Generally tmpfs is recommended. + Aufs prohibited them to be a branch fs by default, because + initramfs becomes unusable after switch_root or something + generally. If you sets initramfs as an aufs branch and boot your + system by switch_root, you will meet a problem easily since the + files in initramfs may be inaccessible. + Unless you are going to use ramfs as an aufs branch fs without + switch_root or something, leave it N. + +config AUFS_BR_FUSE + bool "Fuse fs as an aufs branch" + depends on FUSE_FS + select AUFS_POLL + help + If you want to use fuse-based userspace filesystem as an aufs + branch fs, then enable this option. + It implements the internal poll(2) operation which is + implemented by fuse only (curretnly). + +config AUFS_POLL + bool + help + Automatic configuration for internal use. + +config AUFS_BR_HFSPLUS + bool "Hfsplus as an aufs branch" + depends on HFSPLUS_FS + default y + help + If you want to use hfsplus fs as an aufs branch fs, then enable + this option. This option introduces a small overhead at + copying-up a file on hfsplus. + +config AUFS_BDEV_LOOP + bool + depends on BLK_DEV_LOOP + default y + help + Automatic configuration for internal use. + Convert =[ym] into =y. + +config AUFS_DEBUG + bool "Debug aufs" + help + Enable this to compile aufs internal debug code. + It will have a negative impact to the performance. + +config AUFS_MAGIC_SYSRQ + bool + depends on AUFS_DEBUG && MAGIC_SYSRQ + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq, enabled automatically. +endif diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile new file mode 100644 index 000000000000..2c819a64935e --- /dev/null +++ b/fs/aufs/Makefile @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: GPL-2.0 + +include ${src}/magic.mk +ifeq (${CONFIG_AUFS_FS},m) +include ${src}/conf.mk +endif +-include ${src}/priv_def.mk + +# cf. include/linux/kernel.h +# enable pr_debug +ccflags-y += -DDEBUG +# sparse requires the full pathname +ifdef M +ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h +else +ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h +endif + +obj-$(CONFIG_AUFS_FS) += aufs.o +aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ + wkq.o vfsub.o dcsub.o \ + cpup.o whout.o wbr_policy.o \ + dinfo.o dentry.o \ + dynop.o \ + finfo.o file.o f_op.o \ + dir.o vdir.o \ + iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ + mvdown.o ioctl.o + +# all are boolean +aufs-$(CONFIG_PROC_FS) += procfs.o plink.o +aufs-$(CONFIG_SYSFS) += sysfs.o +aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o +aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o +aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o +aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o +aufs-$(CONFIG_AUFS_EXPORT) += export.o +aufs-$(CONFIG_AUFS_XATTR) += xattr.o +aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o +aufs-$(CONFIG_AUFS_DIRREN) += dirren.o +aufs-$(CONFIG_AUFS_FHSM) += fhsm.o +aufs-$(CONFIG_AUFS_POLL) += poll.o +aufs-$(CONFIG_AUFS_RDU) += rdu.o +aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o +aufs-$(CONFIG_AUFS_DEBUG) += debug.o +aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h new file mode 100644 index 000000000000..a62a85211b88 --- /dev/null +++ b/fs/aufs/aufs.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * all header files + */ + +#ifndef __AUFS_H__ +#define __AUFS_H__ + +#ifdef __KERNEL__ + +#define AuStub(type, name, body, ...) \ + static inline type name(__VA_ARGS__) { body; } + +#define AuStubVoid(name, ...) \ + AuStub(void, name, , __VA_ARGS__) +#define AuStubInt0(name, ...) \ + AuStub(int, name, return 0, __VA_ARGS__) + +#include "debug.h" + +#include "branch.h" +#include "cpup.h" +#include "dcsub.h" +#include "dbgaufs.h" +#include "dentry.h" +#include "dir.h" +#include "dirren.h" +#include "dynop.h" +#include "file.h" +#include "fstype.h" +#include "hbl.h" +#include "inode.h" +#include "lcnt.h" +#include "loop.h" +#include "module.h" +#include "opts.h" +#include "rwsem.h" +#include "super.h" +#include "sysaufs.h" +#include "vfsub.h" +#include "whout.h" +#include "wkq.h" + +#endif /* __KERNEL__ */ +#endif /* __AUFS_H__ */ diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c new file mode 100644 index 000000000000..fb388a049940 --- /dev/null +++ b/fs/aufs/branch.c @@ -0,0 +1,1423 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * branch management + */ + +#include <linux/compat.h> +#include <linux/statfs.h> +#include "aufs.h" + +/* + * free a single branch + */ +static void au_br_do_free(struct au_branch *br) +{ + int i; + struct au_wbr *wbr; + struct au_dykey **key; + + au_hnotify_fin_br(br); + /* always, regardless the mount option */ + au_dr_hino_free(&br->br_dirren); + au_xino_put(br); + + AuLCntZero(au_lcnt_read(&br->br_nfiles, /*do_rev*/0)); + au_lcnt_fin(&br->br_nfiles, /*do_sync*/0); + AuLCntZero(au_lcnt_read(&br->br_count, /*do_rev*/0)); + au_lcnt_fin(&br->br_count, /*do_sync*/0); + + wbr = br->br_wbr; + if (wbr) { + for (i = 0; i < AuBrWh_Last; i++) + dput(wbr->wbr_wh[i]); + AuDebugOn(atomic_read(&wbr->wbr_wh_running)); + AuRwDestroy(&wbr->wbr_wh_rwsem); + } + + if (br->br_fhsm) { + au_br_fhsm_fin(br->br_fhsm); + au_kfree_try_rcu(br->br_fhsm); + } + + key = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++, key++) + if (*key) + au_dy_put(*key); + else + break; + + /* recursive lock, s_umount of branch's */ + /* synchronize_rcu(); */ /* why? */ + lockdep_off(); + path_put(&br->br_path); + lockdep_on(); + au_kfree_rcu(wbr); + au_lcnt_wait_for_fin(&br->br_nfiles); + au_lcnt_wait_for_fin(&br->br_count); + /* I don't know why, but percpu_refcount requires this */ + /* synchronize_rcu(); */ + au_kfree_rcu(br); +} + +/* + * frees all branches + */ +void au_br_free(struct au_sbinfo *sbinfo) +{ + aufs_bindex_t bmax; + struct au_branch **br; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + bmax = sbinfo->si_bbot + 1; + br = sbinfo->si_branch; + while (bmax--) + au_br_do_free(*br++); +} + +/* + * find the index of a branch which is specified by @br_id. + */ +int au_br_index(struct super_block *sb, aufs_bindex_t br_id) +{ + aufs_bindex_t bindex, bbot; + + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) + if (au_sbr_id(sb, bindex) == br_id) + return bindex; + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * add a branch + */ + +static int test_overlap(struct super_block *sb, struct dentry *h_adding, + struct dentry *h_root) +{ + if (unlikely(h_adding == h_root + || au_test_loopback_overlap(sb, h_adding))) + return 1; + if (h_adding->d_sb != h_root->d_sb) + return 0; + return au_test_subdir(h_adding, h_root) + || au_test_subdir(h_root, h_adding); +} + +/* + * returns a newly allocated branch. @new_nbranch is a number of branches + * after adding a branch. + */ +static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch, + int perm) +{ + struct au_branch *add_branch; + struct dentry *root; + struct inode *inode; + int err; + + err = -ENOMEM; + add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS); + if (unlikely(!add_branch)) + goto out; + add_branch->br_xino = au_xino_alloc(/*nfile*/1); + if (unlikely(!add_branch->br_xino)) + goto out_br; + err = au_hnotify_init_br(add_branch, perm); + if (unlikely(err)) + goto out_xino; + + if (au_br_writable(perm)) { + /* may be freed separately at changing the branch permission */ + add_branch->br_wbr = kzalloc(sizeof(*add_branch->br_wbr), + GFP_NOFS); + if (unlikely(!add_branch->br_wbr)) + goto out_hnotify; + } + + if (au_br_fhsm(perm)) { + err = au_fhsm_br_alloc(add_branch); + if (unlikely(err)) + goto out_wbr; + } + + root = sb->s_root; + err = au_sbr_realloc(au_sbi(sb), new_nbranch, /*may_shrink*/0); + if (!err) + err = au_di_realloc(au_di(root), new_nbranch, /*may_shrink*/0); + if (!err) { + inode = d_inode(root); + err = au_hinode_realloc(au_ii(inode), new_nbranch, + /*may_shrink*/0); + } + if (!err) + return add_branch; /* success */ + +out_wbr: + au_kfree_rcu(add_branch->br_wbr); +out_hnotify: + au_hnotify_fin_br(add_branch); +out_xino: + au_xino_put(add_branch); +out_br: + au_kfree_rcu(add_branch); +out: + return ERR_PTR(err); +} + +/* + * test if the branch permission is legal or not. + */ +static int test_br(struct inode *inode, int brperm, char *path) +{ + int err; + + err = (au_br_writable(brperm) && IS_RDONLY(inode)); + if (!err) + goto out; + + err = -EINVAL; + pr_err("write permission for readonly mount or inode, %s\n", path); + +out: + return err; +} + +/* + * returns: + * 0: success, the caller will add it + * plus: success, it is already unified, the caller should ignore it + * minus: error + */ +static int test_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bbot, bindex; + struct dentry *root, *h_dentry; + struct inode *inode, *h_inode; + + root = sb->s_root; + bbot = au_sbbot(sb); + if (unlikely(bbot >= 0 + && au_find_dbindex(root, add->path.dentry) >= 0)) { + err = 1; + if (!remount) { + err = -EINVAL; + pr_err("%s duplicated\n", add->pathname); + } + goto out; + } + + err = -ENOSPC; /* -E2BIG; */ + if (unlikely(AUFS_BRANCH_MAX <= add->bindex + || AUFS_BRANCH_MAX - 1 <= bbot)) { + pr_err("number of branches exceeded %s\n", add->pathname); + goto out; + } + + err = -EDOM; + if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) { + pr_err("bad index %d\n", add->bindex); + goto out; + } + + inode = d_inode(add->path.dentry); + err = -ENOENT; + if (unlikely(!inode->i_nlink)) { + pr_err("no existence %s\n", add->pathname); + goto out; + } + + err = -EINVAL; + if (unlikely(inode->i_sb == sb)) { + pr_err("%s must be outside\n", add->pathname); + goto out; + } + + if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) { + pr_err("unsupported filesystem, %s (%s)\n", + add->pathname, au_sbtype(inode->i_sb)); + goto out; + } + + if (unlikely(inode->i_sb->s_stack_depth)) { + pr_err("already stacked, %s (%s)\n", + add->pathname, au_sbtype(inode->i_sb)); + goto out; + } + + err = test_br(d_inode(add->path.dentry), add->perm, add->pathname); + if (unlikely(err)) + goto out; + + if (bbot < 0) + return 0; /* success */ + + err = -EINVAL; + for (bindex = 0; bindex <= bbot; bindex++) + if (unlikely(test_overlap(sb, add->path.dentry, + au_h_dptr(root, bindex)))) { + pr_err("%s is overlapped\n", add->pathname); + goto out; + } + + err = 0; + if (au_opt_test(au_mntflags(sb), WARN_PERM)) { + h_dentry = au_h_dptr(root, 0); + h_inode = d_inode(h_dentry); + if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO) + || !uid_eq(h_inode->i_uid, inode->i_uid) + || !gid_eq(h_inode->i_gid, inode->i_gid)) + pr_warn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n", + add->pathname, + i_uid_read(inode), i_gid_read(inode), + (inode->i_mode & S_IALLUGO), + i_uid_read(h_inode), i_gid_read(h_inode), + (h_inode->i_mode & S_IALLUGO)); + } + +out: + return err; +} + +/* + * initialize or clean the whiteouts for an adding branch + */ +static int au_br_init_wh(struct super_block *sb, struct au_branch *br, + int new_perm) +{ + int err, old_perm; + aufs_bindex_t bindex; + struct inode *h_inode; + struct au_wbr *wbr; + struct au_hinode *hdir; + struct dentry *h_dentry; + + err = vfsub_mnt_want_write(au_br_mnt(br)); + if (unlikely(err)) + goto out; + + wbr = br->br_wbr; + old_perm = br->br_perm; + br->br_perm = new_perm; + hdir = NULL; + h_inode = NULL; + bindex = au_br_index(sb, br->br_id); + if (0 <= bindex) { + hdir = au_hi(d_inode(sb->s_root), bindex); + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + } else { + h_dentry = au_br_dentry(br); + h_inode = d_inode(h_dentry); + inode_lock_nested(h_inode, AuLsc_I_PARENT); + } + if (!wbr) + err = au_wh_init(br, sb); + else { + wbr_wh_write_lock(wbr); + err = au_wh_init(br, sb); + wbr_wh_write_unlock(wbr); + } + if (hdir) + au_hn_inode_unlock(hdir); + else + inode_unlock(h_inode); + vfsub_mnt_drop_write(au_br_mnt(br)); + br->br_perm = old_perm; + + if (!err && wbr && !au_br_writable(new_perm)) { + au_kfree_rcu(wbr); + br->br_wbr = NULL; + } + +out: + return err; +} + +static int au_wbr_init(struct au_branch *br, struct super_block *sb, + int perm) +{ + int err; + struct kstatfs kst; + struct au_wbr *wbr; + + wbr = br->br_wbr; + au_rw_init(&wbr->wbr_wh_rwsem); + atomic_set(&wbr->wbr_wh_running, 0); + + /* + * a limit for rmdir/rename a dir + * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h + */ + err = vfs_statfs(&br->br_path, &kst); + if (unlikely(err)) + goto out; + err = -EINVAL; + if (kst.f_namelen >= NAME_MAX) + err = au_br_init_wh(sb, br, perm); + else + pr_err("%pd(%s), unsupported namelen %ld\n", + au_br_dentry(br), + au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen); + +out: + return err; +} + +/* initialize a new branch */ +static int au_br_init(struct au_branch *br, struct super_block *sb, + struct au_opt_add *add) +{ + int err; + struct au_branch *brbase; + struct file *xf; + struct inode *h_inode; + + err = 0; + br->br_perm = add->perm; + br->br_path = add->path; /* set first, path_get() later */ + spin_lock_init(&br->br_dykey_lock); + au_lcnt_init(&br->br_nfiles, /*release*/NULL); + au_lcnt_init(&br->br_count, /*release*/NULL); + br->br_id = au_new_br_id(sb); + AuDebugOn(br->br_id < 0); + + /* always, regardless the given option */ + err = au_dr_br_init(sb, br, &add->path); + if (unlikely(err)) + goto out_err; + + if (au_br_writable(add->perm)) { + err = au_wbr_init(br, sb, add->perm); + if (unlikely(err)) + goto out_err; + } + + if (au_opt_test(au_mntflags(sb), XINO)) { + brbase = au_sbr(sb, 0); + xf = au_xino_file(brbase->br_xino, /*idx*/-1); + AuDebugOn(!xf); + h_inode = d_inode(add->path.dentry); + err = au_xino_init_br(sb, br, h_inode->i_ino, &xf->f_path); + if (unlikely(err)) { + AuDebugOn(au_xino_file(br->br_xino, /*idx*/-1)); + goto out_err; + } + } + + sysaufs_br_init(br); + path_get(&br->br_path); + goto out; /* success */ + +out_err: + memset(&br->br_path, 0, sizeof(br->br_path)); +out: + return err; +} + +static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex, + struct au_branch *br, aufs_bindex_t bbot, + aufs_bindex_t amount) +{ + struct au_branch **brp; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + memmove(brp + 1, brp, sizeof(*brp) * amount); + *brp = br; + sbinfo->si_bbot++; + if (unlikely(bbot < 0)) + sbinfo->si_bbot = 0; +} + +static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, + aufs_bindex_t bbot, aufs_bindex_t amount) +{ + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = au_hdentry(dinfo, bindex); + memmove(hdp + 1, hdp, sizeof(*hdp) * amount); + au_h_dentry_init(hdp); + dinfo->di_bbot++; + if (unlikely(bbot < 0)) + dinfo->di_btop = 0; +} + +static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, + aufs_bindex_t bbot, aufs_bindex_t amount) +{ + struct au_hinode *hip; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = au_hinode(iinfo, bindex); + memmove(hip + 1, hip, sizeof(*hip) * amount); + au_hinode_init(hip); + iinfo->ii_bbot++; + if (unlikely(bbot < 0)) + iinfo->ii_btop = 0; +} + +static void au_br_do_add(struct super_block *sb, struct au_branch *br, + aufs_bindex_t bindex) +{ + struct dentry *root, *h_dentry; + struct inode *root_inode, *h_inode; + aufs_bindex_t bbot, amount; + + root = sb->s_root; + root_inode = d_inode(root); + bbot = au_sbbot(sb); + amount = bbot + 1 - bindex; + h_dentry = au_br_dentry(br); + au_sbilist_lock(); + au_br_do_add_brp(au_sbi(sb), bindex, br, bbot, amount); + au_br_do_add_hdp(au_di(root), bindex, bbot, amount); + au_br_do_add_hip(au_ii(root_inode), bindex, bbot, amount); + au_set_h_dptr(root, bindex, dget(h_dentry)); + h_inode = d_inode(h_dentry); + au_set_h_iptr(root_inode, bindex, au_igrab(h_inode), /*flags*/0); + au_sbilist_unlock(); +} + +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bbot, add_bindex; + struct dentry *root, *h_dentry; + struct inode *root_inode; + struct au_branch *add_branch; + + root = sb->s_root; + root_inode = d_inode(root); + IMustLock(root_inode); + IiMustWriteLock(root_inode); + err = test_add(sb, add, remount); + if (unlikely(err < 0)) + goto out; + if (err) { + err = 0; + goto out; /* success */ + } + + bbot = au_sbbot(sb); + add_branch = au_br_alloc(sb, bbot + 2, add->perm); + err = PTR_ERR(add_branch); + if (IS_ERR(add_branch)) + goto out; + + err = au_br_init(add_branch, sb, add); + if (unlikely(err)) { + au_br_do_free(add_branch); + goto out; + } + + add_bindex = add->bindex; + sysaufs_brs_del(sb, add_bindex); /* remove successors */ + au_br_do_add(sb, add_branch, add_bindex); + sysaufs_brs_add(sb, add_bindex); /* append successors */ + dbgaufs_brs_add(sb, add_bindex, /*topdown*/0); /* rename successors */ + + h_dentry = add->path.dentry; + if (!add_bindex) { + au_cpup_attr_all(root_inode, /*force*/1); + sb->s_maxbytes = h_dentry->d_sb->s_maxbytes; + } else + au_add_nlink(root_inode, d_inode(h_dentry)); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static unsigned long long au_farray_cb(struct super_block *sb, void *a, + unsigned long long max __maybe_unused, + void *arg) +{ + unsigned long long n; + struct file **p, *f; + struct hlist_bl_head *files; + struct hlist_bl_node *pos; + struct au_finfo *finfo; + + n = 0; + p = a; + files = &au_sbi(sb)->si_files; + hlist_bl_lock(files); + hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { + f = finfo->fi_file; + if (file_count(f) + && !special_file(file_inode(f)->i_mode)) { + get_file(f); + *p++ = f; + n++; + AuDebugOn(n > max); + } + } + hlist_bl_unlock(files); + + return n; +} + +static struct file **au_farray_alloc(struct super_block *sb, + unsigned long long *max) +{ + struct au_sbinfo *sbi; + + sbi = au_sbi(sb); + *max = au_lcnt_read(&sbi->si_nfiles, /*do_rev*/1); + return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL); +} + +static void au_farray_free(struct file **a, unsigned long long max) +{ + unsigned long long ull; + + for (ull = 0; ull < max; ull++) + if (a[ull]) + fput(a[ull]); + kvfree(a); +} + +/* ---------------------------------------------------------------------- */ + +/* + * delete a branch + */ + +/* to show the line number, do not make it inlined function */ +#define AuVerbose(do_info, fmt, ...) do { \ + if (do_info) \ + pr_info(fmt, ##__VA_ARGS__); \ +} while (0) + +static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop, + aufs_bindex_t bbot) +{ + return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot; +} + +static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop, + aufs_bindex_t bbot) +{ + return au_test_ibusy(d_inode(dentry), btop, bbot); +} + +/* + * test if the branch is deletable or not. + */ +static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err, i, j, ndentry; + aufs_bindex_t btop, bbot; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *d; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, root, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; !err && i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = 0; !err && j < ndentry; j++) { + d = dpage->dentries[j]; + AuDebugOn(au_dcount(d) <= 0); + if (!au_digen_test(d, sigen)) { + di_read_lock_child(d, AuLock_IR); + if (unlikely(au_dbrange_test(d))) { + di_read_unlock(d, AuLock_IR); + continue; + } + } else { + di_write_lock_child(d); + if (unlikely(au_dbrange_test(d))) { + di_write_unlock(d); + continue; + } + err = au_reval_dpath(d, sigen); + if (!err) + di_downgrade_lock(d, AuLock_IR); + else { + di_write_unlock(d); + break; + } + } + + /* AuDbgDentry(d); */ + btop = au_dbtop(d); + bbot = au_dbbot(d); + if (btop <= bindex + && bindex <= bbot + && au_h_dptr(d, bindex) + && au_test_dbusy(d, btop, bbot)) { + err = -EBUSY; + AuVerbose(verbose, "busy %pd\n", d); + AuDbgDentry(d); + } + di_read_unlock(d, AuLock_IR); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err; + unsigned long long max, ull; + struct inode *i, **array; + aufs_bindex_t btop, bbot; + + array = au_iarray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + AuDbg("b%d\n", bindex); + for (ull = 0; !err && ull < max; ull++) { + i = array[ull]; + if (unlikely(!i)) + break; + if (i->i_ino == AUFS_ROOT_INO) + continue; + + /* AuDbgInode(i); */ + if (au_iigen(i, NULL) == sigen) + ii_read_lock_child(i); + else { + ii_write_lock_child(i); + err = au_refresh_hinode_self(i); + au_iigen_dec(i); + if (!err) + ii_downgrade_lock(i); + else { + ii_write_unlock(i); + break; + } + } + + btop = au_ibtop(i); + bbot = au_ibbot(i); + if (btop <= bindex + && bindex <= bbot + && au_h_iptr(i, bindex) + && au_test_ibusy(i, btop, bbot)) { + err = -EBUSY; + AuVerbose(verbose, "busy i%lu\n", i->i_ino); + AuDbgInode(i); + } + ii_read_unlock(i); + } + au_iarray_free(array, max); + +out: + return err; +} + +static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, + const unsigned int verbose) +{ + int err; + unsigned int sigen; + + sigen = au_sigen(root->d_sb); + DiMustNoWaiters(root); + IiMustNoWaiters(d_inode(root)); + di_write_unlock(root); + err = test_dentry_busy(root, bindex, sigen, verbose); + if (!err) + err = test_inode_busy(root->d_sb, bindex, sigen, verbose); + di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */ + + return err; +} + +static int test_dir_busy(struct file *file, aufs_bindex_t br_id, + struct file **to_free, int *idx) +{ + int err; + unsigned char matched, root; + aufs_bindex_t bindex, bbot; + struct au_fidir *fidir; + struct au_hfile *hfile; + + err = 0; + root = IS_ROOT(file->f_path.dentry); + if (root) { + get_file(file); + to_free[*idx] = file; + (*idx)++; + goto out; + } + + matched = 0; + fidir = au_fi(file)->fi_hdir; + AuDebugOn(!fidir); + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); bindex <= bbot; bindex++) { + hfile = fidir->fd_hfile + bindex; + if (!hfile->hf_file) + continue; + + if (hfile->hf_br->br_id == br_id) { + matched = 1; + break; + } + } + if (matched) + err = -EBUSY; + +out: + return err; +} + +static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id, + struct file **to_free, int opened) +{ + int err, idx; + unsigned long long ull, max; + aufs_bindex_t btop; + struct file *file, **array; + struct dentry *root; + struct au_hfile *hfile; + + array = au_farray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + idx = 0; + root = sb->s_root; + di_write_unlock(root); + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + fi_read_lock(file); + btop = au_fbtop(file); + if (!d_is_dir(file->f_path.dentry)) { + hfile = &au_fi(file)->fi_htop; + if (hfile->hf_br->br_id == br_id) + err = -EBUSY; + } else + err = test_dir_busy(file, br_id, to_free, &idx); + fi_read_unlock(file); + if (unlikely(err)) + break; + } + di_write_lock_child(root); + au_farray_free(array, max); + AuDebugOn(idx > opened); + +out: + return err; +} + +static void br_del_file(struct file **to_free, unsigned long long opened, + aufs_bindex_t br_id) +{ + unsigned long long ull; + aufs_bindex_t bindex, btop, bbot, bfound; + struct file *file; + struct au_fidir *fidir; + struct au_hfile *hfile; + + for (ull = 0; ull < opened; ull++) { + file = to_free[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + AuDebugOn(!d_is_dir(file->f_path.dentry)); + bfound = -1; + fidir = au_fi(file)->fi_hdir; + AuDebugOn(!fidir); + fi_write_lock(file); + btop = au_fbtop(file); + bbot = au_fbbot_dir(file); + for (bindex = btop; bindex <= bbot; bindex++) { + hfile = fidir->fd_hfile + bindex; + if (!hfile->hf_file) + continue; + + if (hfile->hf_br->br_id == br_id) { + bfound = bindex; + break; + } + } + AuDebugOn(bfound < 0); + au_set_h_fptr(file, bfound, NULL); + if (bfound == btop) { + for (btop++; btop <= bbot; btop++) + if (au_hf_dir(file, btop)) { + au_set_fbtop(file, btop); + break; + } + } + fi_write_unlock(file); + } +} + +static void au_br_do_del_brp(struct au_sbinfo *sbinfo, + const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_branch **brp, **p; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + if (bindex < bbot) + memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex)); + sbinfo->si_branch[0 + bbot] = NULL; + sbinfo->si_bbot--; + + p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + sbinfo->si_branch = p; + /* harmless error */ +} + +static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_hdentry *hdp, *p; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = au_hdentry(dinfo, bindex); + if (bindex < bbot) + memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex)); + /* au_h_dentry_init(au_hdentry(dinfo, bbot); */ + dinfo->di_bbot--; + + p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + dinfo->di_hdentry = p; + /* harmless error */ +} + +static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bbot) +{ + struct au_hinode *hip, *p; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = au_hinode(iinfo, bindex); + if (bindex < bbot) + memmove(hip, hip + 1, sizeof(*hip) * (bbot - bindex)); + /* au_hinode_init(au_hinode(iinfo, bbot)); */ + iinfo->ii_bbot--; + + p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST, + /*may_shrink*/1); + if (p) + iinfo->ii_hinode = p; + /* harmless error */ +} + +static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, + struct au_branch *br) +{ + aufs_bindex_t bbot; + struct au_sbinfo *sbinfo; + struct dentry *root, *h_root; + struct inode *inode, *h_inode; + struct au_hinode *hinode; + + SiMustWriteLock(sb); + + root = sb->s_root; + inode = d_inode(root); + sbinfo = au_sbi(sb); + bbot = sbinfo->si_bbot; + + h_root = au_h_dptr(root, bindex); + hinode = au_hi(inode, bindex); + h_inode = au_igrab(hinode->hi_inode); + au_hiput(hinode); + + au_sbilist_lock(); + au_br_do_del_brp(sbinfo, bindex, bbot); + au_br_do_del_hdp(au_di(root), bindex, bbot); + au_br_do_del_hip(au_ii(inode), bindex, bbot); + au_sbilist_unlock(); + + /* ignore an error */ + au_dr_br_fin(sb, br); /* always, regardless the mount option */ + + dput(h_root); + iput(h_inode); + au_br_do_free(br); +} + +static unsigned long long empty_cb(struct super_block *sb, void *array, + unsigned long long max, void *arg) +{ + return max; +} + +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) +{ + int err, rerr, i; + unsigned long long opened; + unsigned int mnt_flags; + aufs_bindex_t bindex, bbot, br_id; + unsigned char do_wh, verbose; + struct au_branch *br; + struct au_wbr *wbr; + struct dentry *root; + struct file **to_free; + + err = 0; + opened = 0; + to_free = NULL; + root = sb->s_root; + bindex = au_find_dbindex(root, del->h_path.dentry); + if (bindex < 0) { + if (remount) + goto out; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", del->pathname); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = -EBUSY; + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + bbot = au_sbbot(sb); + if (unlikely(!bbot)) { + AuVerbose(verbose, "no more branches left\n"); + goto out; + } + + br = au_sbr(sb, bindex); + AuDebugOn(!path_equal(&br->br_path, &del->h_path)); + if (unlikely(au_lcnt_read(&br->br_count, /*do_rev*/1))) { + AuVerbose(verbose, "br %pd2 is busy now\n", del->h_path.dentry); + goto out; + } + + br_id = br->br_id; + opened = au_lcnt_read(&br->br_nfiles, /*do_rev*/1); + if (unlikely(opened)) { + to_free = au_array_alloc(&opened, empty_cb, sb, NULL); + err = PTR_ERR(to_free); + if (IS_ERR(to_free)) + goto out; + + err = test_file_busy(sb, br_id, to_free, opened); + if (unlikely(err)) { + AuVerbose(verbose, "%llu file(s) opened\n", opened); + goto out; + } + } + + wbr = br->br_wbr; + do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph); + if (do_wh) { + /* instead of WbrWhMustWriteLock(wbr) */ + SiMustWriteLock(sb); + for (i = 0; i < AuBrWh_Last; i++) { + dput(wbr->wbr_wh[i]); + wbr->wbr_wh[i] = NULL; + } + } + + err = test_children_busy(root, bindex, verbose); + if (unlikely(err)) { + if (do_wh) + goto out_wh; + goto out; + } + + err = 0; + if (to_free) { + /* + * now we confirmed the branch is deletable. + * let's free the remaining opened dirs on the branch. + */ + di_write_unlock(root); + br_del_file(to_free, opened, br_id); + di_write_lock_child(root); + } + + sysaufs_brs_del(sb, bindex); /* remove successors */ + dbgaufs_xino_del(br); /* remove one */ + au_br_do_del(sb, bindex, br); + sysaufs_brs_add(sb, bindex); /* append successors */ + dbgaufs_brs_add(sb, bindex, /*topdown*/1); /* rename successors */ + + if (!bindex) { + au_cpup_attr_all(d_inode(root), /*force*/1); + sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes; + } else + au_sub_nlink(d_inode(root), d_inode(del->h_path.dentry)); + if (au_opt_test(mnt_flags, PLINK)) + au_plink_half_refresh(sb, br_id); + + goto out; /* success */ + +out_wh: + /* revert */ + rerr = au_br_init_wh(sb, br, br->br_perm); + if (rerr) + pr_warn("failed re-creating base whiteout, %s. (%d)\n", + del->pathname, rerr); +out: + if (to_free) + au_farray_free(to_free, opened); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg) +{ + int err; + aufs_bindex_t btop, bbot; + struct aufs_ibusy ibusy; + struct inode *inode, *h_inode; + + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = copy_from_user(&ibusy, arg, sizeof(ibusy)); + if (!err) + /* VERIFY_WRITE */ + err = !access_ok(&arg->h_ino, sizeof(arg->h_ino)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + + err = -EINVAL; + si_read_lock(sb, AuLock_FLUSH); + if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb))) + goto out_unlock; + + err = 0; + ibusy.h_ino = 0; /* invalid */ + inode = ilookup(sb, ibusy.ino); + if (!inode + || inode->i_ino == AUFS_ROOT_INO + || au_is_bad_inode(inode)) + goto out_unlock; + + ii_read_lock_child(inode); + btop = au_ibtop(inode); + bbot = au_ibbot(inode); + if (btop <= ibusy.bindex && ibusy.bindex <= bbot) { + h_inode = au_h_iptr(inode, ibusy.bindex); + if (h_inode && au_test_ibusy(inode, btop, bbot)) + ibusy.h_ino = h_inode->i_ino; + } + ii_read_unlock(inode); + iput(inode); + +out_unlock: + si_read_unlock(sb); + if (!err) { + err = __put_user(ibusy.h_ino, &arg->h_ino); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + } + } +out: + return err; +} + +long au_ibusy_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg); +} + +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg)); +} +#endif + +/* ---------------------------------------------------------------------- */ + +/* + * change a branch permission + */ + +static void au_warn_ima(void) +{ +#ifdef CONFIG_IMA + /* since it doesn't support mark_files_ro() */ + AuWarn1("RW -> RO makes IMA to produce wrong message\n"); +#endif +} + +static int do_need_sigen_inc(int a, int b) +{ + return au_br_whable(a) && !au_br_whable(b); +} + +static int need_sigen_inc(int old, int new) +{ + return do_need_sigen_inc(old, new) + || do_need_sigen_inc(new, old); +} + +static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex) +{ + int err, do_warn; + unsigned int mnt_flags; + unsigned long long ull, max; + aufs_bindex_t br_id; + unsigned char verbose, writer; + struct file *file, *hf, **array; + struct au_hfile *hfile; + + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + + array = au_farray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + do_warn = 0; + br_id = au_sbr_id(sb, bindex); + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (unlikely(!file)) + break; + + /* AuDbg("%pD\n", file); */ + fi_read_lock(file); + if (unlikely(au_test_mmapped(file))) { + err = -EBUSY; + AuVerbose(verbose, "mmapped %pD\n", file); + AuDbgFile(file); + FiMustNoWaiters(file); + fi_read_unlock(file); + goto out_array; + } + + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + if (!d_is_reg(file->f_path.dentry) + || !(file->f_mode & FMODE_WRITE) + || hfile->hf_br->br_id != br_id + || !(hf->f_mode & FMODE_WRITE)) + array[ull] = NULL; + else { + do_warn = 1; + get_file(file); + } + + FiMustNoWaiters(file); + fi_read_unlock(file); + fput(file); + } + + err = 0; + if (do_warn) + au_warn_ima(); + + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (!file) + continue; + + /* todo: already flushed? */ + /* + * fs/super.c:mark_files_ro() is gone, but aufs keeps its + * approach which resets f_mode and calls mnt_drop_write() and + * file_release_write() for each file, because the branch + * attribute in aufs world is totally different from the native + * fs rw/ro mode. + */ + /* fi_read_lock(file); */ + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + /* fi_read_unlock(file); */ + spin_lock(&hf->f_lock); + writer = !!(hf->f_mode & FMODE_WRITER); + hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER); + spin_unlock(&hf->f_lock); + if (writer) { + put_write_access(file_inode(hf)); + __mnt_drop_write(hf->f_path.mnt); + } + } + +out_array: + au_farray_free(array, max); +out: + AuTraceErr(err); + return err; +} + +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh) +{ + int err, rerr; + aufs_bindex_t bindex; + struct dentry *root; + struct au_branch *br; + struct au_br_fhsm *bf; + + root = sb->s_root; + bindex = au_find_dbindex(root, mod->h_root); + if (bindex < 0) { + if (remount) + return 0; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", mod->path); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = test_br(d_inode(mod->h_root), mod->perm, mod->path); + if (unlikely(err)) + goto out; + + br = au_sbr(sb, bindex); + AuDebugOn(mod->h_root != au_br_dentry(br)); + if (br->br_perm == mod->perm) + return 0; /* success */ + + /* pre-allocate for non-fhsm --> fhsm */ + bf = NULL; + if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) { + err = au_fhsm_br_alloc(br); + if (unlikely(err)) + goto out; + bf = br->br_fhsm; + br->br_fhsm = NULL; + } + + if (au_br_writable(br->br_perm)) { + /* remove whiteout base */ + err = au_br_init_wh(sb, br, mod->perm); + if (unlikely(err)) + goto out_bf; + + if (!au_br_writable(mod->perm)) { + /* rw --> ro, file might be mmapped */ + DiMustNoWaiters(root); + IiMustNoWaiters(d_inode(root)); + di_write_unlock(root); + err = au_br_mod_files_ro(sb, bindex); + /* aufs_write_lock() calls ..._child() */ + di_write_lock_child(root); + + if (unlikely(err)) { + rerr = -ENOMEM; + br->br_wbr = kzalloc(sizeof(*br->br_wbr), + GFP_NOFS); + if (br->br_wbr) + rerr = au_wbr_init(br, sb, br->br_perm); + if (unlikely(rerr)) { + AuIOErr("nested error %d (%d)\n", + rerr, err); + br->br_perm = mod->perm; + } + } + } + } else if (au_br_writable(mod->perm)) { + /* ro --> rw */ + err = -ENOMEM; + br->br_wbr = kzalloc(sizeof(*br->br_wbr), GFP_NOFS); + if (br->br_wbr) { + err = au_wbr_init(br, sb, mod->perm); + if (unlikely(err)) { + au_kfree_rcu(br->br_wbr); + br->br_wbr = NULL; + } + } + } + if (unlikely(err)) + goto out_bf; + + if (au_br_fhsm(br->br_perm)) { + if (!au_br_fhsm(mod->perm)) { + /* fhsm --> non-fhsm */ + au_br_fhsm_fin(br->br_fhsm); + au_kfree_rcu(br->br_fhsm); + br->br_fhsm = NULL; + } + } else if (au_br_fhsm(mod->perm)) + /* non-fhsm --> fhsm */ + br->br_fhsm = bf; + + *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); + br->br_perm = mod->perm; + goto out; /* success */ + +out_bf: + au_kfree_try_rcu(bf); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs) +{ + int err; + struct kstatfs kstfs; + + err = vfs_statfs(&br->br_path, &kstfs); + if (!err) { + stfs->f_blocks = kstfs.f_blocks; + stfs->f_bavail = kstfs.f_bavail; + stfs->f_files = kstfs.f_files; + stfs->f_ffree = kstfs.f_ffree; + } + + return err; +} diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h new file mode 100644 index 000000000000..012459ad57f3 --- /dev/null +++ b/fs/aufs/branch.h @@ -0,0 +1,366 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * branch filesystems and xino for them + */ + +#ifndef __AUFS_BRANCH_H__ +#define __AUFS_BRANCH_H__ + +#ifdef __KERNEL__ + +#include <linux/mount.h> +#include "dirren.h" +#include "dynop.h" +#include "lcnt.h" +#include "rwsem.h" +#include "super.h" + +/* ---------------------------------------------------------------------- */ + +/* a xino file */ +struct au_xino { + struct file **xi_file; + unsigned int xi_nfile; + + struct { + spinlock_t spin; + ino_t *array; + int total; + /* reserved for future use */ + /* unsigned long *bitmap; */ + wait_queue_head_t wqh; + } xi_nondir; + + struct mutex xi_mtx; /* protects xi_file array */ + struct hlist_bl_head xi_writing; + + atomic_t xi_truncating; + + struct kref xi_kref; +}; + +/* File-based Hierarchical Storage Management */ +struct au_br_fhsm { +#ifdef CONFIG_AUFS_FHSM + struct mutex bf_lock; + unsigned long bf_jiffy; + struct aufs_stfs bf_stfs; + int bf_readable; +#endif +}; + +/* members for writable branch only */ +enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last}; +struct au_wbr { + struct au_rwsem wbr_wh_rwsem; + struct dentry *wbr_wh[AuBrWh_Last]; + atomic_t wbr_wh_running; +#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */ +#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */ +#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */ + + /* mfs mode */ + unsigned long long wbr_bytes; +}; + +/* ext2 has 3 types of operations at least, ext3 has 4 */ +#define AuBrDynOp (AuDyLast * 4) + +#ifdef CONFIG_AUFS_HFSNOTIFY +/* support for asynchronous destruction */ +struct au_br_hfsnotify { + struct fsnotify_group *hfsn_group; +}; +#endif + +/* sysfs entries */ +struct au_brsysfs { + char name[16]; + struct attribute attr; +}; + +enum { + AuBrSysfs_BR, + AuBrSysfs_BRID, + AuBrSysfs_Last +}; + +/* protected by superblock rwsem */ +struct au_branch { + struct au_xino *br_xino; + + aufs_bindex_t br_id; + + int br_perm; + struct path br_path; + spinlock_t br_dykey_lock; + struct au_dykey *br_dykey[AuBrDynOp]; + au_lcnt_t br_nfiles; /* opened files */ + au_lcnt_t br_count; /* in-use for other */ + + struct au_wbr *br_wbr; + struct au_br_fhsm *br_fhsm; + +#ifdef CONFIG_AUFS_HFSNOTIFY + struct au_br_hfsnotify *br_hfsn; +#endif + +#ifdef CONFIG_SYSFS + /* entries under sysfs per mount-point */ + struct au_brsysfs br_sysfs[AuBrSysfs_Last]; +#endif + +#ifdef CONFIG_DEBUG_FS + struct dentry *br_dbgaufs; /* xino */ +#endif + + struct au_dr_br br_dirren; +}; + +/* ---------------------------------------------------------------------- */ + +static inline struct vfsmount *au_br_mnt(struct au_branch *br) +{ + return br->br_path.mnt; +} + +static inline struct dentry *au_br_dentry(struct au_branch *br) +{ + return br->br_path.dentry; +} + +static inline struct super_block *au_br_sb(struct au_branch *br) +{ + return au_br_mnt(br)->mnt_sb; +} + +static inline int au_br_rdonly(struct au_branch *br) +{ + return (sb_rdonly(au_br_sb(br)) + || !au_br_writable(br->br_perm)) + ? -EROFS : 0; +} + +static inline int au_br_hnotifyable(int brperm __maybe_unused) +{ +#ifdef CONFIG_AUFS_HNOTIFY + return !(brperm & AuBrPerm_RR); +#else + return 0; +#endif +} + +static inline int au_br_test_oflag(int oflag, struct au_branch *br) +{ + int err, exec_flag; + + err = 0; + exec_flag = oflag & __FMODE_EXEC; + if (unlikely(exec_flag && path_noexec(&br->br_path))) + err = -EACCES; + + return err; +} + +static inline void au_xino_get(struct au_branch *br) +{ + struct au_xino *xi; + + xi = br->br_xino; + if (xi) + kref_get(&xi->xi_kref); +} + +static inline int au_xino_count(struct au_branch *br) +{ + int v; + struct au_xino *xi; + + v = 0; + xi = br->br_xino; + if (xi) + v = kref_read(&xi->xi_kref); + + return v; +} + +/* ---------------------------------------------------------------------- */ + +/* branch.c */ +struct au_sbinfo; +void au_br_free(struct au_sbinfo *sinfo); +int au_br_index(struct super_block *sb, aufs_bindex_t br_id); +struct au_opt_add; +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount); +struct au_opt_del; +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount); +long au_ibusy_ioctl(struct file *file, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg); +#endif +struct au_opt_mod; +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh); +struct aufs_stfs; +int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs); + +/* xino.c */ +static const loff_t au_loff_max = LLONG_MAX; + +aufs_bindex_t au_xi_root(struct super_block *sb, struct dentry *dentry); +struct file *au_xino_create(struct super_block *sb, char *fpath, int silent, + int wbrtop); +struct file *au_xino_create2(struct super_block *sb, struct path *base, + struct file *copy_src); +struct au_xi_new { + struct au_xino *xi; /* switch between xino and xigen */ + int idx; + struct path *base; + struct file *copy_src; +}; +struct file *au_xi_new(struct super_block *sb, struct au_xi_new *xinew); + +int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t *ino); +int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t ino); +ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size, + loff_t *pos); +ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, + size_t size, loff_t *pos); + +int au_xib_trunc(struct super_block *sb); +int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin); + +struct au_xino *au_xino_alloc(unsigned int nfile); +int au_xino_put(struct au_branch *br); +struct file *au_xino_file1(struct au_xino *xi); + +struct au_opt_xino; +void au_xino_clr(struct super_block *sb); +int au_xino_set(struct super_block *sb, struct au_opt_xino *xiopt, int remount); +struct file *au_xino_def(struct super_block *sb); +int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t hino, + struct path *base); + +ino_t au_xino_new_ino(struct super_block *sb); +void au_xino_delete_inode(struct inode *inode, const int unlinked); + +void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, + ino_t h_ino, int idx); +int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + int *idx); + +int au_xino_path(struct seq_file *seq, struct file *file); + +/* ---------------------------------------------------------------------- */ + +/* @idx is signed to accept -1 meaning the first file */ +static inline struct file *au_xino_file(struct au_xino *xi, int idx) +{ + struct file *file; + + file = NULL; + if (!xi) + goto out; + + if (idx >= 0) { + if (idx < xi->xi_nfile) + file = xi->xi_file[idx]; + } else + file = au_xino_file1(xi); + +out: + return file; +} + +/* ---------------------------------------------------------------------- */ + +/* Superblock to branch */ +static inline +aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_id; +} + +static inline +struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_mnt(au_sbr(sb, bindex)); +} + +static inline +struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_sb(au_sbr(sb, bindex)); +} + +static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_perm; +} + +static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_whable(au_sbr_perm(sb, bindex)); +} + +/* ---------------------------------------------------------------------- */ + +#define wbr_wh_read_lock(wbr) au_rw_read_lock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_lock(wbr) au_rw_write_lock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_read_trylock(wbr) au_rw_read_trylock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_trylock(wbr) au_rw_write_trylock(&(wbr)->wbr_wh_rwsem) +/* +#define wbr_wh_read_trylock_nested(wbr) \ + au_rw_read_trylock_nested(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_trylock_nested(wbr) \ + au_rw_write_trylock_nested(&(wbr)->wbr_wh_rwsem) +*/ + +#define wbr_wh_read_unlock(wbr) au_rw_read_unlock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_write_unlock(wbr) au_rw_write_unlock(&(wbr)->wbr_wh_rwsem) +#define wbr_wh_downgrade_lock(wbr) au_rw_dgrade_lock(&(wbr)->wbr_wh_rwsem) + +#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&(wbr)->wbr_wh_rwsem) +#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&(wbr)->wbr_wh_rwsem) +#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&(wbr)->wbr_wh_rwsem) + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_FHSM +static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm) +{ + mutex_init(&brfhsm->bf_lock); + brfhsm->bf_jiffy = 0; + brfhsm->bf_readable = 0; +} + +static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm) +{ + mutex_destroy(&brfhsm->bf_lock); +} +#else +AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm) +AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm) +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_BRANCH_H__ */ diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk new file mode 100644 index 000000000000..12782f8e0f38 --- /dev/null +++ b/fs/aufs/conf.mk @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 + +AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} + +define AuConf +ifdef ${1} +AuConfStr += ${1}=${${1}} +endif +endef + +AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ + SBILIST \ + HNOTIFY HFSNOTIFY \ + EXPORT INO_T_64 \ + XATTR \ + FHSM \ + RDU \ + DIRREN \ + SHWH \ + BR_RAMFS \ + BR_FUSE POLL \ + BR_HFSPLUS \ + BDEV_LOOP \ + DEBUG MAGIC_SYSRQ +$(foreach i, ${AuConfAll}, \ + $(eval $(call AuConf,CONFIG_AUFS_${i}))) + +AuConfName = ${obj}/conf.str +${AuConfName}.tmp: FORCE + @echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@ +${AuConfName}: ${AuConfName}.tmp + @diff -q $< $@ > /dev/null 2>&1 || { \ + echo ' GEN ' $@; \ + cp -p $< $@; \ + } +FORCE: +clean-files += ${AuConfName} ${AuConfName}.tmp +${obj}/sysfs.o: ${AuConfName} + +-include ${srctree}/${src}/conf_priv.mk diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c new file mode 100644 index 000000000000..21134b448967 --- /dev/null +++ b/fs/aufs/cpup.c @@ -0,0 +1,1458 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * copy-up functions, see wbr_policy.c for copy-down + */ + +#include <linux/fs_stack.h> +#include <linux/mm.h> +#include <linux/task_work.h> +#include "aufs.h" + +void au_cpup_attr_flags(struct inode *dst, unsigned int iflags) +{ + const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE + | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT; + + BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags)); + + dst->i_flags |= iflags & ~mask; + if (au_test_fs_notime(dst->i_sb)) + dst->i_flags |= S_NOATIME | S_NOCMTIME; +} + +void au_cpup_attr_timesizes(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + fsstack_copy_attr_times(inode, h_inode); + fsstack_copy_inode_size(inode, h_inode); +} + +void au_cpup_attr_nlink(struct inode *inode, int force) +{ + struct inode *h_inode; + struct super_block *sb; + aufs_bindex_t bindex, bbot; + + sb = inode->i_sb; + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (!force + && !S_ISDIR(h_inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode)) + return; + + /* + * 0 can happen in revalidating. + * h_inode->i_mutex may not be held here, but it is harmless since once + * i_nlink reaches 0, it will never become positive except O_TMPFILE + * case. + * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause + * the incorrect link count. + */ + set_nlink(inode, h_inode->i_nlink); + + /* + * fewer nlink makes find(1) noisy, but larger nlink doesn't. + * it may includes whplink directory. + */ + if (S_ISDIR(h_inode->i_mode)) { + bbot = au_ibbot(inode); + for (bindex++; bindex <= bbot; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) + au_add_nlink(inode, h_inode); + } + } +} + +void au_cpup_attr_changeable(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + inode->i_mode = h_inode->i_mode; + inode->i_uid = h_inode->i_uid; + inode->i_gid = h_inode->i_gid; + au_cpup_attr_timesizes(inode); + au_cpup_attr_flags(inode, h_inode->i_flags); +} + +void au_cpup_igen(struct inode *inode, struct inode *h_inode) +{ + struct au_iinfo *iinfo = au_ii(inode); + + IiMustWriteLock(inode); + + iinfo->ii_higen = h_inode->i_generation; + iinfo->ii_hsb1 = h_inode->i_sb; +} + +void au_cpup_attr_all(struct inode *inode, int force) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + au_cpup_attr_changeable(inode); + if (inode->i_nlink > 0) + au_cpup_attr_nlink(inode, force); + inode->i_rdev = h_inode->i_rdev; + inode->i_blkbits = h_inode->i_blkbits; + au_cpup_igen(inode, h_inode); +} + +/* ---------------------------------------------------------------------- */ + +/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ + +/* keep the timestamps of the parent dir when cpup */ +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path) +{ + struct inode *h_inode; + + dt->dt_dentry = dentry; + dt->dt_h_path = *h_path; + h_inode = d_inode(h_path->dentry); + dt->dt_atime = h_inode->i_atime; + dt->dt_mtime = h_inode->i_mtime; + /* smp_mb(); */ +} + +void au_dtime_revert(struct au_dtime *dt) +{ + struct iattr attr; + int err; + + attr.ia_atime = dt->dt_atime; + attr.ia_mtime = dt->dt_mtime; + attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET + | ATTR_ATIME | ATTR_ATIME_SET; + + /* no delegation since this is a directory */ + err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL); + if (unlikely(err)) + pr_warn("restoring timestamps failed(%d). ignored\n", err); +} + +/* ---------------------------------------------------------------------- */ + +/* internal use only */ +struct au_cpup_reg_attr { + int valid; + struct kstat st; + unsigned int iflags; /* inode->i_flags */ +}; + +static noinline_for_stack +int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src, + struct au_cpup_reg_attr *h_src_attr) +{ + int err, sbits, icex; + unsigned int mnt_flags; + unsigned char verbose; + struct iattr ia; + struct path h_path; + struct inode *h_isrc, *h_idst; + struct kstat *h_st; + struct au_branch *br; + + h_path.dentry = au_h_dptr(dst, bindex); + h_idst = d_inode(h_path.dentry); + br = au_sbr(dst->d_sb, bindex); + h_path.mnt = au_br_mnt(br); + h_isrc = d_inode(h_src); + ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID + | ATTR_ATIME | ATTR_MTIME + | ATTR_ATIME_SET | ATTR_MTIME_SET; + if (h_src_attr && h_src_attr->valid) { + h_st = &h_src_attr->st; + ia.ia_uid = h_st->uid; + ia.ia_gid = h_st->gid; + ia.ia_atime = h_st->atime; + ia.ia_mtime = h_st->mtime; + if (h_idst->i_mode != h_st->mode + && !S_ISLNK(h_idst->i_mode)) { + ia.ia_valid |= ATTR_MODE; + ia.ia_mode = h_st->mode; + } + sbits = !!(h_st->mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_idst, h_src_attr->iflags); + } else { + ia.ia_uid = h_isrc->i_uid; + ia.ia_gid = h_isrc->i_gid; + ia.ia_atime = h_isrc->i_atime; + ia.ia_mtime = h_isrc->i_mtime; + if (h_idst->i_mode != h_isrc->i_mode + && !S_ISLNK(h_idst->i_mode)) { + ia.ia_valid |= ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + } + sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_idst, h_isrc->i_flags); + } + /* no delegation since it is just created */ + err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); + + /* is this nfs only? */ + if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) { + ia.ia_valid = ATTR_FORCE | ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); + } + + icex = br->br_perm & AuBrAttr_ICEX; + if (!err) { + mnt_flags = au_mntflags(dst->d_sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, + char *buf, unsigned long blksize) +{ + int err; + size_t sz, rbytes, wbytes; + unsigned char all_zero; + char *p, *zp; + struct inode *h_inode; + /* reduce stack usage */ + struct iattr *ia; + + zp = page_address(ZERO_PAGE(0)); + if (unlikely(!zp)) + return -ENOMEM; /* possible? */ + + err = 0; + all_zero = 0; + while (len) { + AuDbg("len %lld\n", len); + sz = blksize; + if (len < blksize) + sz = len; + + rbytes = 0; + /* todo: signal_pending? */ + while (!rbytes || err == -EAGAIN || err == -EINTR) { + rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); + err = rbytes; + } + if (unlikely(err < 0)) + break; + + all_zero = 0; + if (len >= rbytes && rbytes == blksize) + all_zero = !memcmp(buf, zp, rbytes); + if (!all_zero) { + wbytes = rbytes; + p = buf; + while (wbytes) { + size_t b; + + b = vfsub_write_k(dst, p, wbytes, &dst->f_pos); + err = b; + /* todo: signal_pending? */ + if (unlikely(err == -EAGAIN || err == -EINTR)) + continue; + if (unlikely(err < 0)) + break; + wbytes -= b; + p += b; + } + if (unlikely(err < 0)) + break; + } else { + loff_t res; + + AuLabel(hole); + res = vfsub_llseek(dst, rbytes, SEEK_CUR); + err = res; + if (unlikely(res < 0)) + break; + } + len -= rbytes; + err = 0; + } + + /* the last block may be a hole */ + if (!err && all_zero) { + AuLabel(last hole); + + err = 1; + if (au_test_nfs(dst->f_path.dentry->d_sb)) { + /* nfs requires this step to make last hole */ + /* is this only nfs? */ + do { + /* todo: signal_pending? */ + err = vfsub_write_k(dst, "\0", 1, &dst->f_pos); + } while (err == -EAGAIN || err == -EINTR); + if (err == 1) + dst->f_pos--; + } + + if (err == 1) { + ia = (void *)buf; + ia->ia_size = dst->f_pos; + ia->ia_valid = ATTR_SIZE | ATTR_FILE; + ia->ia_file = dst; + h_inode = file_inode(dst); + inode_lock_nested(h_inode, AuLsc_I_CHILD2); + /* no delegation since it is just created */ + err = vfsub_notify_change(&dst->f_path, ia, + /*delegated*/NULL); + inode_unlock(h_inode); + } + } + + return err; +} + +int au_copy_file(struct file *dst, struct file *src, loff_t len) +{ + int err; + unsigned long blksize; + unsigned char do_kfree; + char *buf; + struct super_block *h_sb; + + err = -ENOMEM; + h_sb = file_inode(dst)->i_sb; + blksize = h_sb->s_blocksize; + if (!blksize || PAGE_SIZE < blksize) + blksize = PAGE_SIZE; + AuDbg("blksize %lu\n", blksize); + do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *)); + if (do_kfree) + buf = kmalloc(blksize, GFP_NOFS); + else + buf = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!buf)) + goto out; + + if (len > (1 << 22)) + AuDbg("copying a large file %lld\n", (long long)len); + + src->f_pos = 0; + dst->f_pos = 0; + err = au_do_copy_file(dst, src, len, buf, blksize); + if (do_kfree) { + AuDebugOn(!au_kfree_do_sz_test(blksize)); + au_kfree_do_rcu(buf); + } else + free_page((unsigned long)buf); + +out: + return err; +} + +static int au_do_copy(struct file *dst, struct file *src, loff_t len) +{ + int err; + struct super_block *h_src_sb; + struct inode *h_src_inode; + + h_src_inode = file_inode(src); + h_src_sb = h_src_inode->i_sb; + + /* XFS acquires inode_lock */ + if (!au_test_xfs(h_src_sb)) + err = au_copy_file(dst, src, len); + else { + inode_unlock_shared(h_src_inode); + err = au_copy_file(dst, src, len); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } + + return err; +} + +static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len) +{ + int err; + loff_t lo; + struct super_block *h_src_sb; + struct inode *h_src_inode; + + h_src_inode = file_inode(src); + h_src_sb = h_src_inode->i_sb; + if (h_src_sb != file_inode(dst)->i_sb + || !dst->f_op->remap_file_range) { + err = au_do_copy(dst, src, len); + goto out; + } + + if (!au_test_nfs(h_src_sb)) { + inode_unlock_shared(h_src_inode); + lo = vfsub_clone_file_range(src, dst, len); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } else + lo = vfsub_clone_file_range(src, dst, len); + if (lo == len) { + err = 0; + goto out; /* success */ + } else if (lo >= 0) + /* todo: possible? */ + /* paritially succeeded */ + AuDbg("lo %lld, len %lld. Retrying.\n", lo, len); + else if (lo != -EOPNOTSUPP) { + /* older XFS has a condition in cloning */ + err = lo; + goto out; + } + + /* the backend fs on NFS may not support cloning */ + err = au_do_copy(dst, src, len); + +out: + AuTraceErr(err); + return err; +} + +/* + * to support a sparse file which is opened with O_APPEND, + * we need to close the file. + */ +static int au_cp_regular(struct au_cp_generic *cpg) +{ + int err, i; + enum { SRC, DST }; + struct { + aufs_bindex_t bindex; + unsigned int flags; + struct dentry *dentry; + int force_wr; + struct file *file; + } *f, file[] = { + { + .bindex = cpg->bsrc, + .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, + }, + { + .bindex = cpg->bdst, + .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, + .force_wr = !!au_ftest_cpup(cpg->flags, RWDST), + } + }; + struct au_branch *br; + struct super_block *sb, *h_src_sb; + struct inode *h_src_inode; + struct task_struct *tsk = current; + + /* bsrc branch can be ro/rw. */ + sb = cpg->dentry->d_sb; + f = file; + for (i = 0; i < 2; i++, f++) { + f->dentry = au_h_dptr(cpg->dentry, f->bindex); + f->file = au_h_open(cpg->dentry, f->bindex, f->flags, + /*file*/NULL, f->force_wr); + if (IS_ERR(f->file)) { + err = PTR_ERR(f->file); + if (i == SRC) + goto out; + else + goto out_src; + } + } + + /* try stopping to update while we copyup */ + h_src_inode = d_inode(file[SRC].dentry); + h_src_sb = h_src_inode->i_sb; + if (!au_test_nfs(h_src_sb)) + IMustLock(h_src_inode); + err = au_clone_or_copy(file[DST].file, file[SRC].file, cpg->len); + + /* i wonder if we had O_NO_DELAY_FPUT flag */ + if (tsk->flags & PF_KTHREAD) + __fput_sync(file[DST].file); + else { + /* it happened actually */ + fput(file[DST].file); + /* + * too bad. + * we have to call both since we don't know which place the file + * was added to. + */ + task_work_run(); + flush_delayed_fput(); + } + br = au_sbr(sb, file[DST].bindex); + au_lcnt_dec(&br->br_nfiles); + +out_src: + fput(file[SRC].file); + br = au_sbr(sb, file[SRC].bindex); + au_lcnt_dec(&br->br_nfiles); +out: + return err; +} + +static int au_do_cpup_regular(struct au_cp_generic *cpg, + struct au_cpup_reg_attr *h_src_attr) +{ + int err, rerr; + loff_t l; + struct path h_path; + struct inode *h_src_inode, *h_dst_inode; + + err = 0; + h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc); + l = i_size_read(h_src_inode); + if (cpg->len == -1 || l < cpg->len) + cpg->len = l; + if (cpg->len) { + /* try stopping to update while we are referencing */ + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + au_pin_hdir_unlock(cpg->pin); + + h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc); + h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc); + h_src_attr->iflags = h_src_inode->i_flags; + if (!au_test_nfs(h_src_inode->i_sb)) + err = vfsub_getattr(&h_path, &h_src_attr->st); + else { + inode_unlock_shared(h_src_inode); + err = vfsub_getattr(&h_path, &h_src_attr->st); + inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); + } + if (unlikely(err)) { + inode_unlock_shared(h_src_inode); + goto out; + } + h_src_attr->valid = 1; + if (!au_test_nfs(h_src_inode->i_sb)) { + err = au_cp_regular(cpg); + inode_unlock_shared(h_src_inode); + } else { + inode_unlock_shared(h_src_inode); + err = au_cp_regular(cpg); + } + rerr = au_pin_hdir_relock(cpg->pin); + if (!err && rerr) + err = rerr; + } + if (!err && (h_src_inode->i_state & I_LINKABLE)) { + h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst); + h_dst_inode = d_inode(h_path.dentry); + spin_lock(&h_dst_inode->i_lock); + h_dst_inode->i_state |= I_LINKABLE; + spin_unlock(&h_dst_inode->i_lock); + } + +out: + return err; +} + +static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, + struct inode *h_dir) +{ + int err, symlen; + mm_segment_t old_fs; + union { + char *k; + char __user *u; + } sym; + + err = -ENOMEM; + sym.k = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!sym.k)) + goto out; + + /* unnecessary to support mmap_sem since symlink is not mmap-able */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + symlen = vfs_readlink(h_src, sym.u, PATH_MAX); + err = symlen; + set_fs(old_fs); + + if (symlen > 0) { + sym.k[symlen] = 0; + err = vfsub_symlink(h_dir, h_path, sym.k); + } + free_page((unsigned long)sym.k); + +out: + return err; +} + +/* + * regardless 'acl' option, reset all ACL. + * All ACL will be copied up later from the original entry on the lower branch. + */ +static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) +{ + int err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = h_path->dentry; + h_inode = d_inode(h_dentry); + /* forget_all_cached_acls(h_inode)); */ + err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); + AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; + if (!err) + err = vfsub_acl_chmod(h_inode, mode); + + AuTraceErr(err); + return err; +} + +static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent, + struct inode *h_dir, struct path *h_path) +{ + int err; + struct inode *dir, *inode; + + err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); + AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; + if (unlikely(err)) + goto out; + + /* + * strange behaviour from the users view, + * particularly setattr case + */ + dir = d_inode(dst_parent); + if (au_ibtop(dir) == cpg->bdst) + au_cpup_attr_nlink(dir, /*force*/1); + inode = d_inode(cpg->dentry); + au_cpup_attr_nlink(inode, /*force*/1); + +out: + return err; +} + +static noinline_for_stack +int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, + struct au_cpup_reg_attr *h_src_attr) +{ + int err; + umode_t mode; + unsigned int mnt_flags; + unsigned char isdir, isreg, force; + const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME); + struct au_dtime dt; + struct path h_path; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *h_inode, *h_dir; + struct super_block *sb; + + /* bsrc branch can be ro/rw. */ + h_src = au_h_dptr(cpg->dentry, cpg->bsrc); + h_inode = d_inode(h_src); + AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc)); + + /* try stopping to be referenced while we are creating */ + h_dst = au_h_dptr(cpg->dentry, cpg->bdst); + if (au_ftest_cpup(cpg->flags, RENAME)) + AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX, + AUFS_WH_PFX_LEN)); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + AuDebugOn(h_parent != h_dst->d_parent); + + sb = cpg->dentry->d_sb; + h_path.mnt = au_sbr_mnt(sb, cpg->bdst); + if (do_dt) { + h_path.dentry = h_parent; + au_dtime_store(&dt, dst_parent, &h_path); + } + h_path.dentry = h_dst; + + isreg = 0; + isdir = 0; + mode = h_inode->i_mode; + switch (mode & S_IFMT) { + case S_IFREG: + isreg = 1; + err = vfsub_create(h_dir, &h_path, 0600, /*want_excl*/true); + if (!err) + err = au_do_cpup_regular(cpg, h_src_attr); + break; + case S_IFDIR: + isdir = 1; + err = vfsub_mkdir(h_dir, &h_path, mode); + if (!err) + err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path); + break; + case S_IFLNK: + err = au_do_cpup_symlink(&h_path, h_src, h_dir); + break; + case S_IFCHR: + case S_IFBLK: + AuDebugOn(!capable(CAP_MKNOD)); + /*FALLTHROUGH*/ + case S_IFIFO: + case S_IFSOCK: + err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev); + break; + default: + AuIOErr("Unknown inode type 0%o\n", mode); + err = -EIO; + } + if (!err) + err = au_reset_acl(h_dir, &h_path, mode); + + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, UDBA_NONE) + && !isdir + && au_opt_test(mnt_flags, XINO) + && (h_inode->i_nlink == 1 + || (h_inode->i_state & I_LINKABLE)) + /* todo: unnecessary? */ + /* && d_inode(cpg->dentry)->i_nlink == 1 */ + && cpg->bdst < cpg->bsrc + && !au_ftest_cpup(cpg->flags, KEEPLINO)) + au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0); + /* ignore this error */ + + if (!err) { + force = 0; + if (isreg) { + force = !!cpg->len; + if (cpg->len == -1) + force = !!i_size_read(h_inode); + } + au_fhsm_wrote(sb, cpg->bdst, force); + } + + if (do_dt) + au_dtime_revert(&dt); + return err; +} + +static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path) +{ + int err; + struct dentry *dentry, *h_dentry, *h_parent, *parent; + struct inode *h_dir; + aufs_bindex_t bdst; + + dentry = cpg->dentry; + bdst = cpg->bdst; + h_dentry = au_h_dptr(dentry, bdst); + if (!au_ftest_cpup(cpg->flags, OVERWRITE)) { + dget(h_dentry); + au_set_h_dptr(dentry, bdst, NULL); + err = au_lkup_neg(dentry, bdst, /*wh*/0); + if (!err) + h_path->dentry = dget(au_h_dptr(dentry, bdst)); + au_set_h_dptr(dentry, bdst, h_dentry); + } else { + err = 0; + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + dput(parent); + h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent); + if (IS_ERR(h_path->dentry)) + err = PTR_ERR(h_path->dentry); + } + if (unlikely(err)) + goto out; + + h_parent = h_dentry->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + AuDbg("%pd %pd\n", h_dentry, h_path->dentry); + /* no delegation since it is just created */ + err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL, + /*flags*/0); + dput(h_path->dentry); + +out: + return err; +} + +/* + * copyup the @dentry from @bsrc to @bdst. + * the caller must set the both of lower dentries. + * @len is for truncating when it is -1 copyup the entire file. + * in link/rename cases, @dst_parent may be different from the real one. + * basic->bsrc can be larger than basic->bdst. + * aufs doesn't touch the credential so + * security_inode_copy_up{,_xattr}() are unnecessary. + */ +static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ + int err, rerr; + aufs_bindex_t old_ibtop; + unsigned char isdir, plink; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode; + struct super_block *sb; + struct au_branch *br; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct path h_path; + struct au_cpup_reg_attr h_src_attr; + } *a; + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + a->h_src_attr.valid = 0; + + sb = cpg->dentry->d_sb; + br = au_sbr(sb, cpg->bdst); + a->h_path.mnt = au_br_mnt(br); + h_dst = au_h_dptr(cpg->dentry, cpg->bdst); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = d_inode(h_parent); + IMustLock(h_dir); + + h_src = au_h_dptr(cpg->dentry, cpg->bsrc); + inode = d_inode(cpg->dentry); + + if (!dst_parent) + dst_parent = dget_parent(cpg->dentry); + else + dget(dst_parent); + + plink = !!au_opt_test(au_mntflags(sb), PLINK); + dst_inode = au_h_iptr(inode, cpg->bdst); + if (dst_inode) { + if (unlikely(!plink)) { + err = -EIO; + AuIOErr("hi%lu(i%lu) exists on b%d " + "but plink is disabled\n", + dst_inode->i_ino, inode->i_ino, cpg->bdst); + goto out_parent; + } + + if (dst_inode->i_nlink) { + const int do_dt = au_ftest_cpup(cpg->flags, DTIME); + + h_src = au_plink_lkup(inode, cpg->bdst); + err = PTR_ERR(h_src); + if (IS_ERR(h_src)) + goto out_parent; + if (unlikely(d_is_negative(h_src))) { + err = -EIO; + AuIOErr("i%lu exists on b%d " + "but not pseudo-linked\n", + inode->i_ino, cpg->bdst); + dput(h_src); + goto out_parent; + } + + if (do_dt) { + a->h_path.dentry = h_parent; + au_dtime_store(&a->dt, dst_parent, &a->h_path); + } + + a->h_path.dentry = h_dst; + delegated = NULL; + err = vfsub_link(h_src, h_dir, &a->h_path, &delegated); + if (!err && au_ftest_cpup(cpg->flags, RENAME)) + err = au_do_ren_after_cpup(cpg, &a->h_path); + if (do_dt) + au_dtime_revert(&a->dt); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + dput(h_src); + goto out_parent; + } else + /* todo: cpup_wh_file? */ + /* udba work */ + au_update_ibrange(inode, /*do_put_zero*/1); + } + + isdir = S_ISDIR(inode->i_mode); + old_ibtop = au_ibtop(inode); + err = cpup_entry(cpg, dst_parent, &a->h_src_attr); + if (unlikely(err)) + goto out_rev; + dst_inode = d_inode(h_dst); + inode_lock_nested(dst_inode, AuLsc_I_CHILD2); + /* todo: necessary? */ + /* au_pin_hdir_unlock(cpg->pin); */ + + err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr); + if (unlikely(err)) { + /* todo: necessary? */ + /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */ + inode_unlock(dst_inode); + goto out_rev; + } + + if (cpg->bdst < old_ibtop) { + if (S_ISREG(inode->i_mode)) { + err = au_dy_iaop(inode, cpg->bdst, dst_inode); + if (unlikely(err)) { + /* ignore an error */ + /* au_pin_hdir_relock(cpg->pin); */ + inode_unlock(dst_inode); + goto out_rev; + } + } + au_set_ibtop(inode, cpg->bdst); + } else + au_set_ibbot(inode, cpg->bdst); + au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode), + au_hi_flags(inode, isdir)); + + /* todo: necessary? */ + /* err = au_pin_hdir_relock(cpg->pin); */ + inode_unlock(dst_inode); + if (unlikely(err)) + goto out_rev; + + src_inode = d_inode(h_src); + if (!isdir + && (src_inode->i_nlink > 1 + || src_inode->i_state & I_LINKABLE) + && plink) + au_plink_append(inode, cpg->bdst, h_dst); + + if (au_ftest_cpup(cpg->flags, RENAME)) { + a->h_path.dentry = h_dst; + err = au_do_ren_after_cpup(cpg, &a->h_path); + } + if (!err) + goto out_parent; /* success */ + + /* revert */ +out_rev: + a->h_path.dentry = h_parent; + au_dtime_store(&a->dt, dst_parent, &a->h_path); + a->h_path.dentry = h_dst; + rerr = 0; + if (d_is_positive(h_dst)) { + if (!isdir) { + /* no delegation since it is just created */ + rerr = vfsub_unlink(h_dir, &a->h_path, + /*delegated*/NULL, /*force*/0); + } else + rerr = vfsub_rmdir(h_dir, &a->h_path); + } + au_dtime_revert(&a->dt); + if (rerr) { + AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr); + err = -EIO; + } +out_parent: + dput(dst_parent); + au_kfree_rcu(a); +out: + return err; +} + +#if 0 /* reserved */ +struct au_cpup_single_args { + int *errp; + struct au_cp_generic *cpg; + struct dentry *dst_parent; +}; + +static void au_call_cpup_single(void *args) +{ + struct au_cpup_single_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_single(a->cpg, a->dst_parent); + au_pin_hdir_release(a->cpg->pin); +} +#endif + +/* + * prevent SIGXFSZ in copy-up. + * testing CAP_MKNOD is for generic fs, + * but CAP_FSETID is for xfs only, currently. + */ +static int au_cpup_sio_test(struct au_pin *pin, umode_t mode) +{ + int do_sio; + struct super_block *sb; + struct inode *h_dir; + + do_sio = 0; + sb = au_pinned_parent(pin)->d_sb; + if (!au_wkq_test() + && (!au_sbi(sb)->si_plink_maint_pid + || au_plink_maint(sb, AuLock_NOPLM))) { + switch (mode & S_IFMT) { + case S_IFREG: + /* no condition about RLIMIT_FSIZE and the file size */ + do_sio = 1; + break; + case S_IFCHR: + case S_IFBLK: + do_sio = !capable(CAP_MKNOD); + break; + } + if (!do_sio) + do_sio = ((mode & (S_ISUID | S_ISGID)) + && !capable(CAP_FSETID)); + /* this workaround may be removed in the future */ + if (!do_sio) { + h_dir = au_pinned_h_dir(pin); + do_sio = h_dir->i_mode & S_ISVTX; + } + } + + return do_sio; +} + +#if 0 /* reserved */ +int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ + int err, wkq_err; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc); + if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode)) + err = au_cpup_single(cpg, dst_parent); + else { + struct au_cpup_single_args args = { + .errp = &err, + .cpg = cpg, + .dst_parent = dst_parent + }; + wkq_err = au_wkq_wait(au_call_cpup_single, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} +#endif + +/* + * copyup the @dentry from the first active lower branch to @bdst, + * using au_cpup_single(). + */ +static int au_cpup_simple(struct au_cp_generic *cpg) +{ + int err; + unsigned int flags_orig; + struct dentry *dentry; + + AuDebugOn(cpg->bsrc < 0); + + dentry = cpg->dentry; + DiMustWriteLock(dentry); + + err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1); + if (!err) { + flags_orig = cpg->flags; + au_fset_cpup(cpg->flags, RENAME); + err = au_cpup_single(cpg, NULL); + cpg->flags = flags_orig; + if (!err) + return 0; /* success */ + + /* revert */ + au_set_h_dptr(dentry, cpg->bdst, NULL); + au_set_dbtop(dentry, cpg->bsrc); + } + + return err; +} + +struct au_cpup_simple_args { + int *errp; + struct au_cp_generic *cpg; +}; + +static void au_call_cpup_simple(void *args) +{ + struct au_cpup_simple_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_simple(a->cpg); + au_pin_hdir_release(a->cpg->pin); +} + +static int au_do_sio_cpup_simple(struct au_cp_generic *cpg) +{ + int err, wkq_err; + struct dentry *dentry, *parent; + struct file *h_file; + struct inode *h_dir; + + dentry = cpg->dentry; + h_file = NULL; + if (au_ftest_cpup(cpg->flags, HOPEN)) { + AuDebugOn(cpg->bsrc < 0); + h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + } + + parent = dget_parent(dentry); + h_dir = au_h_iptr(d_inode(parent), cpg->bdst); + if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) + err = au_cpup_simple(cpg); + else { + struct au_cpup_simple_args args = { + .errp = &err, + .cpg = cpg + }; + wkq_err = au_wkq_wait(au_call_cpup_simple, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + dput(parent); + if (h_file) + au_h_open_post(dentry, cpg->bsrc, h_file); + +out: + return err; +} + +int au_sio_cpup_simple(struct au_cp_generic *cpg) +{ + aufs_bindex_t bsrc, bbot; + struct dentry *dentry, *h_dentry; + + if (cpg->bsrc < 0) { + dentry = cpg->dentry; + bbot = au_dbbot(dentry); + for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) { + h_dentry = au_h_dptr(dentry, bsrc); + if (h_dentry) { + AuDebugOn(d_is_negative(h_dentry)); + break; + } + } + AuDebugOn(bsrc > bbot); + cpg->bsrc = bsrc; + } + AuDebugOn(cpg->bsrc <= cpg->bdst); + return au_do_sio_cpup_simple(cpg); +} + +int au_sio_cpdown_simple(struct au_cp_generic *cpg) +{ + AuDebugOn(cpg->bdst <= cpg->bsrc); + return au_do_sio_cpup_simple(cpg); +} + +/* ---------------------------------------------------------------------- */ + +/* + * copyup the deleted file for writing. + */ +static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry, + struct file *file) +{ + int err; + unsigned int flags_orig; + aufs_bindex_t bsrc_orig; + struct au_dinfo *dinfo; + struct { + struct au_hdentry *hd; + struct dentry *h_dentry; + } hdst, hsrc; + + dinfo = au_di(cpg->dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + bsrc_orig = cpg->bsrc; + cpg->bsrc = dinfo->di_btop; + hdst.hd = au_hdentry(dinfo, cpg->bdst); + hdst.h_dentry = hdst.hd->hd_dentry; + hdst.hd->hd_dentry = wh_dentry; + dinfo->di_btop = cpg->bdst; + + hsrc.h_dentry = NULL; + if (file) { + hsrc.hd = au_hdentry(dinfo, cpg->bsrc); + hsrc.h_dentry = hsrc.hd->hd_dentry; + hsrc.hd->hd_dentry = au_hf_top(file)->f_path.dentry; + } + flags_orig = cpg->flags; + cpg->flags = !AuCpup_DTIME; + err = au_cpup_single(cpg, /*h_parent*/NULL); + cpg->flags = flags_orig; + if (file) { + if (!err) + err = au_reopen_nondir(file); + hsrc.hd->hd_dentry = hsrc.h_dentry; + } + hdst.hd->hd_dentry = hdst.h_dentry; + dinfo->di_btop = cpg->bsrc; + cpg->bsrc = bsrc_orig; + + return err; +} + +static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ + int err; + aufs_bindex_t bdst; + struct au_dtime dt; + struct dentry *dentry, *parent, *h_parent, *wh_dentry; + struct au_branch *br; + struct path h_path; + + dentry = cpg->dentry; + bdst = cpg->bdst; + br = au_sbr(dentry->d_sb, bdst); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out; + + h_path.dentry = h_parent; + h_path.mnt = au_br_mnt(br); + au_dtime_store(&dt, parent, &h_path); + err = au_do_cpup_wh(cpg, wh_dentry, file); + if (unlikely(err)) + goto out_wh; + + dget(wh_dentry); + h_path.dentry = wh_dentry; + if (!d_is_dir(wh_dentry)) { + /* no delegation since it is just created */ + err = vfsub_unlink(d_inode(h_parent), &h_path, + /*delegated*/NULL, /*force*/0); + } else + err = vfsub_rmdir(d_inode(h_parent), &h_path); + if (unlikely(err)) { + AuIOErr("failed remove copied-up tmp file %pd(%d)\n", + wh_dentry, err); + err = -EIO; + } + au_dtime_revert(&dt); + au_set_hi_wh(d_inode(dentry), bdst, wh_dentry); + +out_wh: + dput(wh_dentry); +out: + dput(parent); + return err; +} + +struct au_cpup_wh_args { + int *errp; + struct au_cp_generic *cpg; + struct file *file; +}; + +static void au_call_cpup_wh(void *args) +{ + struct au_cpup_wh_args *a = args; + + au_pin_hdir_acquire_nest(a->cpg->pin); + *a->errp = au_cpup_wh(a->cpg, a->file); + au_pin_hdir_release(a->cpg->pin); +} + +int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ + int err, wkq_err; + aufs_bindex_t bdst; + struct dentry *dentry, *parent, *h_orph, *h_parent; + struct inode *dir, *h_dir, *h_tmpdir; + struct au_wbr *wbr; + struct au_pin wh_pin, *pin_orig; + + dentry = cpg->dentry; + bdst = cpg->bdst; + parent = dget_parent(dentry); + dir = d_inode(parent); + h_orph = NULL; + h_parent = NULL; + h_dir = au_igrab(au_h_iptr(dir, bdst)); + h_tmpdir = h_dir; + pin_orig = NULL; + if (!h_dir->i_nlink) { + wbr = au_sbr(dentry->d_sb, bdst)->br_wbr; + h_orph = wbr->wbr_orph; + + h_parent = dget(au_h_dptr(parent, bdst)); + au_set_h_dptr(parent, bdst, dget(h_orph)); + h_tmpdir = d_inode(h_orph); + au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); + + inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3); + /* todo: au_h_open_pre()? */ + + pin_orig = cpg->pin; + au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT, + AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED); + cpg->pin = &wh_pin; + } + + if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) + err = au_cpup_wh(cpg, file); + else { + struct au_cpup_wh_args args = { + .errp = &err, + .cpg = cpg, + .file = file + }; + wkq_err = au_wkq_wait(au_call_cpup_wh, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + if (h_orph) { + inode_unlock(h_tmpdir); + /* todo: au_h_open_post()? */ + au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); + au_set_h_dptr(parent, bdst, h_parent); + AuDebugOn(!pin_orig); + cpg->pin = pin_orig; + } + iput(h_dir); + dput(parent); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * generic routine for both of copy-up and copy-down. + */ +/* cf. revalidate function in file.c */ +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent, void *arg), + void *arg) +{ + int err; + struct au_pin pin; + struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry; + + err = 0; + parent = dget_parent(dentry); + if (IS_ROOT(parent)) + goto out; + + au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, + au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); + + /* do not use au_dpage */ + real_parent = parent; + while (1) { + dput(parent); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + if (h_parent) + goto out; /* success */ + + /* find top dir which is necessary to cpup */ + do { + d = parent; + dput(parent); + parent = dget_parent(d); + di_read_lock_parent3(parent, !AuLock_IR); + h_parent = au_h_dptr(parent, bdst); + di_read_unlock(parent, !AuLock_IR); + } while (!h_parent); + + if (d != real_parent) + di_write_lock_child3(d); + + /* somebody else might create while we were sleeping */ + h_dentry = au_h_dptr(d, bdst); + if (!h_dentry || d_is_negative(h_dentry)) { + if (h_dentry) + au_update_dbtop(d); + + au_pin_set_dentry(&pin, d); + err = au_do_pin(&pin); + if (!err) { + err = cp(d, bdst, &pin, h_parent, arg); + au_unpin(&pin); + } + } + + if (d != real_parent) + di_write_unlock(d); + if (unlikely(err)) + break; + } + +out: + dput(parent); + return err; +} + +static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent __maybe_unused, + void *arg __maybe_unused) +{ + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = bdst, + .bsrc = -1, + .len = 0, + .pin = pin, + .flags = AuCpup_DTIME + }; + return au_sio_cpup_simple(&cpg); +} + +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); +} + +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + int err; + struct dentry *parent; + struct inode *dir; + + parent = dget_parent(dentry); + dir = d_inode(parent); + err = 0; + if (au_h_iptr(dir, bdst)) + goto out; + + di_read_unlock(parent, AuLock_IR); + di_write_lock_parent(parent); + /* someone else might change our inode while we were sleeping */ + if (!au_h_iptr(dir, bdst)) + err = au_cpup_dirs(dentry, bdst); + di_downgrade_lock(parent, AuLock_IR); + +out: + dput(parent); + return err; +} diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h new file mode 100644 index 000000000000..abcbfbc55a5c --- /dev/null +++ b/fs/aufs/cpup.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * copy-up/down functions + */ + +#ifndef __AUFS_CPUP_H__ +#define __AUFS_CPUP_H__ + +#ifdef __KERNEL__ + +#include <linux/path.h> + +struct inode; +struct file; +struct au_pin; + +void au_cpup_attr_flags(struct inode *dst, unsigned int iflags); +void au_cpup_attr_timesizes(struct inode *inode); +void au_cpup_attr_nlink(struct inode *inode, int force); +void au_cpup_attr_changeable(struct inode *inode); +void au_cpup_igen(struct inode *inode, struct inode *h_inode); +void au_cpup_attr_all(struct inode *inode, int force); + +/* ---------------------------------------------------------------------- */ + +struct au_cp_generic { + struct dentry *dentry; + aufs_bindex_t bdst, bsrc; + loff_t len; + struct au_pin *pin; + unsigned int flags; +}; + +/* cpup flags */ +#define AuCpup_DTIME 1 /* do dtime_store/revert */ +#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino, + for link(2) */ +#define AuCpup_RENAME (1 << 2) /* rename after cpup */ +#define AuCpup_HOPEN (1 << 3) /* call h_open_pre/post() in + cpup */ +#define AuCpup_OVERWRITE (1 << 4) /* allow overwriting the + existing entry */ +#define AuCpup_RWDST (1 << 5) /* force write target even if + the branch is marked as RO */ + +#ifndef CONFIG_AUFS_BR_HFSPLUS +#undef AuCpup_HOPEN +#define AuCpup_HOPEN 0 +#endif + +#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name) +#define au_fset_cpup(flags, name) \ + do { (flags) |= AuCpup_##name; } while (0) +#define au_fclr_cpup(flags, name) \ + do { (flags) &= ~AuCpup_##name; } while (0) + +int au_copy_file(struct file *dst, struct file *src, loff_t len); +int au_sio_cpup_simple(struct au_cp_generic *cpg); +int au_sio_cpdown_simple(struct au_cp_generic *cpg); +int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file); + +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct au_pin *pin, + struct dentry *h_parent, void *arg), + void *arg); +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); + +/* ---------------------------------------------------------------------- */ + +/* keep timestamps when copyup */ +struct au_dtime { + struct dentry *dt_dentry; + struct path dt_h_path; + struct timespec64 dt_atime, dt_mtime; +}; +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path); +void au_dtime_revert(struct au_dtime *dt); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_CPUP_H__ */ diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c new file mode 100644 index 000000000000..e32d91d1f638 --- /dev/null +++ b/fs/aufs/dbgaufs.c @@ -0,0 +1,526 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debugfs interface + */ + +#include <linux/debugfs.h> +#include "aufs.h" + +#ifndef CONFIG_SYSFS +#error DEBUG_FS depends upon SYSFS +#endif + +static struct dentry *dbgaufs; +static const mode_t dbgaufs_mode = 0444; + +/* 20 is max digits length of ulong 64 */ +struct dbgaufs_arg { + int n; + char a[20 * 4]; +}; + +/* + * common function for all XINO files + */ +static int dbgaufs_xi_release(struct inode *inode __maybe_unused, + struct file *file) +{ + void *p; + + p = file->private_data; + if (p) { + /* this is struct dbgaufs_arg */ + AuDebugOn(!au_kfree_sz_test(p)); + au_kfree_do_rcu(p); + } + return 0; +} + +static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt, + int cnt) +{ + int err; + struct kstat st; + struct dbgaufs_arg *p; + + err = -ENOMEM; + p = kmalloc(sizeof(*p), GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = 0; + p->n = 0; + file->private_data = p; + if (!xf) + goto out; + + err = vfsub_getattr(&xf->f_path, &st); + if (!err) { + if (do_fcnt) + p->n = snprintf + (p->a, sizeof(p->a), "%d, %llux%u %lld\n", + cnt, st.blocks, st.blksize, + (long long)st.size); + else + p->n = snprintf(p->a, sizeof(p->a), "%llux%u %lld\n", + st.blocks, st.blksize, + (long long)st.size); + AuDebugOn(p->n >= sizeof(p->a)); + } else { + p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err); + err = 0; + } + +out: + return err; +} + +static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dbgaufs_arg *p; + + p = file->private_data; + return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + +/* ---------------------------------------------------------------------- */ + +struct dbgaufs_plink_arg { + int n; + char a[]; +}; + +static int dbgaufs_plink_release(struct inode *inode __maybe_unused, + struct file *file) +{ + free_page((unsigned long)file->private_data); + return 0; +} + +static int dbgaufs_plink_open(struct inode *inode, struct file *file) +{ + int err, i, limit; + unsigned long n, sum; + struct dbgaufs_plink_arg *p; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct hlist_bl_head *hbl; + + err = -ENOMEM; + p = (void *)get_zeroed_page(GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = -EFBIG; + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + if (au_opt_test(au_mntflags(sb), PLINK)) { + limit = PAGE_SIZE - sizeof(p->n); + + /* the number of buckets */ + n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH); + p->n += n; + limit -= n; + + sum = 0; + for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH; + i++, hbl++) { + n = au_hbl_count(hbl); + sum += n; + + n = snprintf(p->a + p->n, limit, "%lu ", n); + p->n += n; + limit -= n; + if (unlikely(limit <= 0)) + goto out_free; + } + p->a[p->n - 1] = '\n'; + + /* the sum of plinks */ + n = snprintf(p->a + p->n, limit, "%lu\n", sum); + p->n += n; + limit -= n; + if (unlikely(limit <= 0)) + goto out_free; + } else { +#define str "1\n0\n0\n" + p->n = sizeof(str) - 1; + strcpy(p->a, str); +#undef str + } + si_read_unlock(sb); + + err = 0; + file->private_data = p; + goto out; /* success */ + +out_free: + free_page((unsigned long)p); +out: + return err; +} + +static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dbgaufs_plink_arg *p; + + p = file->private_data; + return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + +static const struct file_operations dbgaufs_plink_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_plink_open, + .release = dbgaufs_plink_release, + .read = dbgaufs_plink_read +}; + +/* ---------------------------------------------------------------------- */ + +static int dbgaufs_xib_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0, /*cnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xib_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xib_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +/* ---------------------------------------------------------------------- */ + +#define DbgaufsXi_PREFIX "xi" + +static int dbgaufs_xino_open(struct inode *inode, struct file *file) +{ + int err, idx; + long l; + aufs_bindex_t bindex; + char *p, a[sizeof(DbgaufsXi_PREFIX) + 8]; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct au_xino *xi; + struct file *xf; + struct qstr *name; + struct au_branch *br; + + err = -ENOENT; + name = &file->f_path.dentry->d_name; + if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) + || memcmp(name->name, DbgaufsXi_PREFIX, + sizeof(DbgaufsXi_PREFIX) - 1))) + goto out; + + AuDebugOn(name->len >= sizeof(a)); + memcpy(a, name->name, name->len); + a[name->len] = '\0'; + p = strchr(a, '-'); + if (p) + *p = '\0'; + err = kstrtol(a + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); + if (unlikely(err)) + goto out; + bindex = l; + idx = 0; + if (p) { + err = kstrtol(p + 1, 10, &l); + if (unlikely(err)) + goto out; + idx = l; + } + + err = -ENOENT; + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + if (unlikely(bindex < 0 || bindex > au_sbbot(sb))) + goto out_si; + br = au_sbr(sb, bindex); + xi = br->br_xino; + if (unlikely(idx >= xi->xi_nfile)) + goto out_si; + xf = au_xino_file(xi, idx); + if (xf) + err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1, + au_xino_count(br)); + +out_si: + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +static const struct file_operations dbgaufs_xino_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xino_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +void dbgaufs_xino_del(struct au_branch *br) +{ + struct dentry *dbgaufs; + + dbgaufs = br->br_dbgaufs; + if (!dbgaufs) + return; + + br->br_dbgaufs = NULL; + /* debugfs acquires the parent i_mutex */ + lockdep_off(); + debugfs_remove(dbgaufs); + lockdep_on(); +} + +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ + aufs_bindex_t bbot; + struct au_branch *br; + + if (!au_sbi(sb)->si_dbgaufs) + return; + + bbot = au_sbbot(sb); + for (; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + dbgaufs_xino_del(br); + } +} + +static void dbgaufs_br_do_add(struct super_block *sb, aufs_bindex_t bindex, + unsigned int idx, struct dentry *parent, + struct au_sbinfo *sbinfo) +{ + struct au_branch *br; + struct dentry *d; + /* "xi" bindex(5) "-" idx(2) NULL */ + char name[sizeof(DbgaufsXi_PREFIX) + 8]; + + if (!idx) + snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); + else + snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d-%u", + bindex, idx); + br = au_sbr(sb, bindex); + if (br->br_dbgaufs) { + struct qstr qstr = QSTR_INIT(name, strlen(name)); + + if (!au_qstreq(&br->br_dbgaufs->d_name, &qstr)) { + /* debugfs acquires the parent i_mutex */ + lockdep_off(); + d = debugfs_rename(parent, br->br_dbgaufs, parent, + name); + lockdep_on(); + if (unlikely(!d)) + pr_warn("failed renaming %pd/%s, ignored.\n", + parent, name); + } + } else { + lockdep_off(); + br->br_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, + sbinfo, &dbgaufs_xino_fop); + lockdep_on(); + if (unlikely(!br->br_dbgaufs)) + pr_warn("failed creating %pd/%s, ignored.\n", + parent, name); + } +} + +static void dbgaufs_br_add(struct super_block *sb, aufs_bindex_t bindex, + struct dentry *parent, struct au_sbinfo *sbinfo) +{ + struct au_branch *br; + struct au_xino *xi; + unsigned int u; + + br = au_sbr(sb, bindex); + xi = br->br_xino; + for (u = 0; u < xi->xi_nfile; u++) + dbgaufs_br_do_add(sb, bindex, u, parent, sbinfo); +} + +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown) +{ + struct au_sbinfo *sbinfo; + struct dentry *parent; + aufs_bindex_t bbot; + + if (!au_opt_test(au_mntflags(sb), XINO)) + return; + + sbinfo = au_sbi(sb); + parent = sbinfo->si_dbgaufs; + if (!parent) + return; + + bbot = au_sbbot(sb); + if (topdown) + for (; bindex <= bbot; bindex++) + dbgaufs_br_add(sb, bindex, parent, sbinfo); + else + for (; bbot >= bindex; bbot--) + dbgaufs_br_add(sb, bbot, parent, sbinfo); +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_EXPORT +static int dbgaufs_xigen_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0, /*cnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xigen_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xigen_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + int err; + + /* + * This function is a dynamic '__init' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -EIO; + sbinfo->si_dbgaufs_xigen = debugfs_create_file + ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xigen_fop); + if (sbinfo->si_dbgaufs_xigen) + err = 0; + + return err; +} +#else +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + return 0; +} +#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_si_fin(struct au_sbinfo *sbinfo) +{ + /* + * This function is a dynamic '__fin' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + debugfs_remove_recursive(sbinfo->si_dbgaufs); + sbinfo->si_dbgaufs = NULL; +} + +int dbgaufs_si_init(struct au_sbinfo *sbinfo) +{ + int err; + char name[SysaufsSiNameLen]; + + /* + * This function is a dynamic '__init' function actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -ENOENT; + if (!dbgaufs) { + AuErr1("/debug/aufs is uninitialized\n"); + goto out; + } + + err = -EIO; + sysaufs_name(sbinfo, name); + sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); + if (unlikely(!sbinfo->si_dbgaufs)) + goto out; + + /* regardless plink/noplink option */ + sbinfo->si_dbgaufs_plink = debugfs_create_file + ("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_plink_fop); + if (unlikely(!sbinfo->si_dbgaufs_plink)) + goto out_dir; + + /* regardless xino/noxino option */ + sbinfo->si_dbgaufs_xib = debugfs_create_file + ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xib_fop); + if (unlikely(!sbinfo->si_dbgaufs_xib)) + goto out_dir; + + err = dbgaufs_xigen_init(sbinfo); + if (!err) + goto out; /* success */ + +out_dir: + dbgaufs_si_fin(sbinfo); +out: + if (unlikely(err)) + pr_err("debugfs/aufs failed\n"); + return err; +} + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_fin(void) +{ + debugfs_remove(dbgaufs); +} + +int __init dbgaufs_init(void) +{ + int err; + + err = -EIO; + dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); + if (dbgaufs) + err = 0; + return err; +} diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h new file mode 100644 index 000000000000..1ea241bf0234 --- /dev/null +++ b/fs/aufs/dbgaufs.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debugfs interface + */ + +#ifndef __DBGAUFS_H__ +#define __DBGAUFS_H__ + +#ifdef __KERNEL__ + +struct super_block; +struct au_sbinfo; +struct au_branch; + +#ifdef CONFIG_DEBUG_FS +/* dbgaufs.c */ +void dbgaufs_xino_del(struct au_branch *br); +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown); +void dbgaufs_si_fin(struct au_sbinfo *sbinfo); +int dbgaufs_si_init(struct au_sbinfo *sbinfo); +void dbgaufs_fin(void); +int __init dbgaufs_init(void); +#else +AuStubVoid(dbgaufs_xino_del, struct au_branch *br) +AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex, + int topdown) +AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo) +AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo) +AuStubVoid(dbgaufs_fin, void) +AuStubInt0(__init dbgaufs_init, void) +#endif /* CONFIG_DEBUG_FS */ + +#endif /* __KERNEL__ */ +#endif /* __DBGAUFS_H__ */ diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c new file mode 100644 index 000000000000..0b9122307667 --- /dev/null +++ b/fs/aufs/dcsub.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for dentry cache + */ + +#include "aufs.h" + +static void au_dpage_free(struct au_dpage *dpage) +{ + int i; + struct dentry **p; + + p = dpage->dentries; + for (i = 0; i < dpage->ndentry; i++) + dput(*p++); + free_page((unsigned long)dpage->dentries); +} + +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) +{ + int err; + void *p; + + err = -ENOMEM; + dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); + if (unlikely(!dpages->dpages)) + goto out; + + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out_dpages; + + dpages->dpages[0].ndentry = 0; + dpages->dpages[0].dentries = p; + dpages->ndpage = 1; + return 0; /* success */ + +out_dpages: + au_kfree_try_rcu(dpages->dpages); +out: + return err; +} + +void au_dpages_free(struct au_dcsub_pages *dpages) +{ + int i; + struct au_dpage *p; + + p = dpages->dpages; + for (i = 0; i < dpages->ndpage; i++) + au_dpage_free(p++); + au_kfree_try_rcu(dpages->dpages); +} + +static int au_dpages_append(struct au_dcsub_pages *dpages, + struct dentry *dentry, gfp_t gfp) +{ + int err, sz; + struct au_dpage *dpage; + void *p; + + dpage = dpages->dpages + dpages->ndpage - 1; + sz = PAGE_SIZE / sizeof(dentry); + if (unlikely(dpage->ndentry >= sz)) { + AuLabel(new dpage); + err = -ENOMEM; + sz = dpages->ndpage * sizeof(*dpages->dpages); + p = au_kzrealloc(dpages->dpages, sz, + sz + sizeof(*dpages->dpages), gfp, + /*may_shrink*/0); + if (unlikely(!p)) + goto out; + + dpages->dpages = p; + dpage = dpages->dpages + dpages->ndpage; + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out; + + dpage->ndentry = 0; + dpage->dentries = p; + dpages->ndpage++; + } + + AuDebugOn(au_dcount(dentry) <= 0); + dpage->dentries[dpage->ndentry++] = dget_dlock(dentry); + return 0; /* success */ + +out: + return err; +} + +/* todo: BAD approach */ +/* copied from linux/fs/dcache.c */ +enum d_walk_ret { + D_WALK_CONTINUE, + D_WALK_QUIT, + D_WALK_NORETRY, + D_WALK_SKIP, +}; + +extern void d_walk(struct dentry *parent, void *data, + enum d_walk_ret (*enter)(void *, struct dentry *)); + +struct ac_dpages_arg { + int err; + struct au_dcsub_pages *dpages; + struct super_block *sb; + au_dpages_test test; + void *arg; +}; + +static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry) +{ + enum d_walk_ret ret; + struct ac_dpages_arg *arg = _arg; + + ret = D_WALK_CONTINUE; + if (dentry->d_sb == arg->sb + && !IS_ROOT(dentry) + && au_dcount(dentry) > 0 + && au_di(dentry) + && (!arg->test || arg->test(dentry, arg->arg))) { + arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC); + if (unlikely(arg->err)) + ret = D_WALK_QUIT; + } + + return ret; +} + +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg) +{ + struct ac_dpages_arg args = { + .err = 0, + .dpages = dpages, + .sb = root->d_sb, + .test = test, + .arg = arg + }; + + d_walk(root, &args, au_call_dpages_append); + + return args.err; +} + +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg) +{ + int err; + + err = 0; + write_seqlock(&rename_lock); + spin_lock(&dentry->d_lock); + if (do_include + && au_dcount(dentry) > 0 + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + goto out; + + /* + * RCU for vfsmount is unnecessary since this is a traverse in a single + * mount + */ + while (!IS_ROOT(dentry)) { + dentry = dentry->d_parent; /* rename_lock is locked */ + spin_lock(&dentry->d_lock); + if (au_dcount(dentry) > 0 + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + break; + } + +out: + write_sequnlock(&rename_lock); + return err; +} + +static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg) +{ + return au_di(dentry) && dentry->d_sb == arg; +} + +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include) +{ + return au_dcsub_pages_rev(dpages, dentry, do_include, + au_dcsub_dpages_aufs, dentry->d_sb); +} + +int au_test_subdir(struct dentry *d1, struct dentry *d2) +{ + struct path path[2] = { + { + .dentry = d1 + }, + { + .dentry = d2 + } + }; + + return path_is_under(path + 0, path + 1); +} diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h new file mode 100644 index 000000000000..5e578995c256 --- /dev/null +++ b/fs/aufs/dcsub.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for dentry cache + */ + +#ifndef __AUFS_DCSUB_H__ +#define __AUFS_DCSUB_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include <linux/fs.h> + +struct au_dpage { + int ndentry; + struct dentry **dentries; +}; + +struct au_dcsub_pages { + int ndpage; + struct au_dpage *dpages; +}; + +/* ---------------------------------------------------------------------- */ + +/* dcsub.c */ +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp); +void au_dpages_free(struct au_dcsub_pages *dpages); +typedef int (*au_dpages_test)(struct dentry *dentry, void *arg); +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg); +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg); +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include); +int au_test_subdir(struct dentry *d1, struct dentry *d2); + +/* ---------------------------------------------------------------------- */ + +/* + * todo: in linux-3.13, several similar (but faster) helpers are added to + * include/linux/dcache.h. Try them (in the future). + */ + +static inline int au_d_hashed_positive(struct dentry *d) +{ + int err; + struct inode *inode = d_inode(d); + + err = 0; + if (unlikely(d_unhashed(d) + || d_is_negative(d) + || !inode->i_nlink)) + err = -ENOENT; + return err; +} + +static inline int au_d_linkable(struct dentry *d) +{ + int err; + struct inode *inode = d_inode(d); + + err = au_d_hashed_positive(d); + if (err + && d_is_positive(d) + && (inode->i_state & I_LINKABLE)) + err = 0; + return err; +} + +static inline int au_d_alive(struct dentry *d) +{ + int err; + struct inode *inode; + + err = 0; + if (!IS_ROOT(d)) + err = au_d_hashed_positive(d); + else { + inode = d_inode(d); + if (unlikely(d_unlinked(d) + || d_is_negative(d) + || !inode->i_nlink)) + err = -ENOENT; + } + return err; +} + +static inline int au_alive_dir(struct dentry *d) +{ + int err; + + err = au_d_alive(d); + if (unlikely(err || IS_DEADDIR(d_inode(d)))) + err = -ENOENT; + return err; +} + +static inline int au_qstreq(struct qstr *a, struct qstr *b) +{ + return a->len == b->len + && !memcmp(a->name, b->name, a->len); +} + +/* + * by the commit + * 360f547 2015-01-25 dcache: let the dentry count go down to zero without + * taking d_lock + * the type of d_lockref.count became int, but the inlined function d_count() + * still returns unsigned int. + * I don't know why. Maybe it is for every d_count() users? + * Anyway au_dcount() lives on. + */ +static inline int au_dcount(struct dentry *d) +{ + return (int)d_count(d); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DCSUB_H__ */ diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c new file mode 100644 index 000000000000..b93bb4f565bf --- /dev/null +++ b/fs/aufs/debug.c @@ -0,0 +1,441 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debug print functions + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* Returns 0, or -errno. arg is in kp->arg. */ +static int param_atomic_t_set(const char *val, const struct kernel_param *kp) +{ + int err, n; + + err = kstrtoint(val, 0, &n); + if (!err) { + if (n > 0) + au_debug_on(); + else + au_debug_off(); + } + return err; +} + +/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ +static int param_atomic_t_get(char *buffer, const struct kernel_param *kp) +{ + atomic_t *a; + + a = kp->arg; + return sprintf(buffer, "%d", atomic_read(a)); +} + +static struct kernel_param_ops param_ops_atomic_t = { + .set = param_atomic_t_set, + .get = param_atomic_t_get + /* void (*free)(void *arg) */ +}; + +atomic_t aufs_debug = ATOMIC_INIT(0); +MODULE_PARM_DESC(debug, "debug print"); +module_param_named(debug, aufs_debug, atomic_t, 0664); + +DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */ +char *au_plevel = KERN_DEBUG; +#define dpri(fmt, ...) do { \ + if ((au_plevel \ + && strcmp(au_plevel, KERN_DEBUG)) \ + || au_debug_test()) \ + printk("%s" fmt, au_plevel, ##__VA_ARGS__); \ +} while (0) + +/* ---------------------------------------------------------------------- */ + +void au_dpri_whlist(struct au_nhash *whlist) +{ + unsigned long ul, n; + struct hlist_head *head; + struct au_vdir_wh *pos; + + n = whlist->nh_num; + head = whlist->nh_head; + for (ul = 0; ul < n; ul++) { + hlist_for_each_entry(pos, head, wh_hash) + dpri("b%d, %.*s, %d\n", + pos->wh_bindex, + pos->wh_str.len, pos->wh_str.name, + pos->wh_str.len); + head++; + } +} + +void au_dpri_vdir(struct au_vdir *vdir) +{ + unsigned long ul; + union au_vdir_deblk_p p; + unsigned char *o; + + if (!vdir || IS_ERR(vdir)) { + dpri("err %ld\n", PTR_ERR(vdir)); + return; + } + + dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %llu\n", + vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk, + vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version); + for (ul = 0; ul < vdir->vd_nblk; ul++) { + p.deblk = vdir->vd_deblk[ul]; + o = p.deblk; + dpri("[%lu]: %p\n", ul, o); + } +} + +static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, + struct dentry *wh) +{ + char *n = NULL; + int l = 0; + + if (!inode || IS_ERR(inode)) { + dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); + return -1; + } + + /* the type of i_blocks depends upon CONFIG_LBDAF */ + BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) + && sizeof(inode->i_blocks) != sizeof(u64)); + if (wh) { + n = (void *)wh->d_name.name; + l = wh->d_name.len; + } + + dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," + " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", + bindex, inode, + inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", + atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, + i_size_read(inode), (unsigned long long)inode->i_blocks, + hn, (long long)timespec64_to_ns(&inode->i_ctime) & 0x0ffff, + inode->i_mapping ? inode->i_mapping->nrpages : 0, + inode->i_state, inode->i_flags, inode_peek_iversion(inode), + inode->i_generation, + l ? ", wh " : "", l, n); + return 0; +} + +void au_dpri_inode(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct au_hinode *hi; + aufs_bindex_t bindex; + int err, hn; + + err = do_pri_inode(-1, inode, -1, NULL); + if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode)) + return; + + iinfo = au_ii(inode); + dpri("i-1: btop %d, bbot %d, gen %d\n", + iinfo->ii_btop, iinfo->ii_bbot, au_iigen(inode, NULL)); + if (iinfo->ii_btop < 0) + return; + hn = 0; + for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; bindex++) { + hi = au_hinode(iinfo, bindex); + hn = !!au_hn(hi); + do_pri_inode(bindex, hi->hi_inode, hn, hi->hi_whdentry); + } +} + +void au_dpri_dalias(struct inode *inode) +{ + struct dentry *d; + + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) + au_dpri_dentry(d); + spin_unlock(&inode->i_lock); +} + +static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) +{ + struct dentry *wh = NULL; + int hn; + struct inode *inode; + struct au_iinfo *iinfo; + struct au_hinode *hi; + + if (!dentry || IS_ERR(dentry)) { + dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); + return -1; + } + /* do not call dget_parent() here */ + /* note: access d_xxx without d_lock */ + dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n", + bindex, dentry, dentry, + dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", + au_dcount(dentry), dentry->d_flags, + d_unhashed(dentry) ? "un" : ""); + hn = -1; + inode = NULL; + if (d_is_positive(dentry)) + inode = d_inode(dentry); + if (inode + && au_test_aufs(dentry->d_sb) + && bindex >= 0 + && !au_is_bad_inode(inode)) { + iinfo = au_ii(inode); + hi = au_hinode(iinfo, bindex); + hn = !!au_hn(hi); + wh = hi->hi_whdentry; + } + do_pri_inode(bindex, inode, hn, wh); + return 0; +} + +void au_dpri_dentry(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + aufs_bindex_t bindex; + int err; + + err = do_pri_dentry(-1, dentry); + if (err || !au_test_aufs(dentry->d_sb)) + return; + + dinfo = au_di(dentry); + if (!dinfo) + return; + dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n", + dinfo->di_btop, dinfo->di_bbot, + dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry), + dinfo->di_tmpfile); + if (dinfo->di_btop < 0) + return; + for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++) + do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry); +} + +static int do_pri_file(aufs_bindex_t bindex, struct file *file) +{ + char a[32]; + + if (!file || IS_ERR(file)) { + dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); + return -1; + } + a[0] = 0; + if (bindex < 0 + && !IS_ERR_OR_NULL(file->f_path.dentry) + && au_test_aufs(file->f_path.dentry->d_sb) + && au_fi(file)) + snprintf(a, sizeof(a), ", gen %d, mmapped %d", + au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); + dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", + bindex, file->f_mode, file->f_flags, (long)file_count(file), + file->f_version, file->f_pos, a); + if (!IS_ERR_OR_NULL(file->f_path.dentry)) + do_pri_dentry(bindex, file->f_path.dentry); + return 0; +} + +void au_dpri_file(struct file *file) +{ + struct au_finfo *finfo; + struct au_fidir *fidir; + struct au_hfile *hfile; + aufs_bindex_t bindex; + int err; + + err = do_pri_file(-1, file); + if (err + || IS_ERR_OR_NULL(file->f_path.dentry) + || !au_test_aufs(file->f_path.dentry->d_sb)) + return; + + finfo = au_fi(file); + if (!finfo) + return; + if (finfo->fi_btop < 0) + return; + fidir = finfo->fi_hdir; + if (!fidir) + do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file); + else + for (bindex = finfo->fi_btop; + bindex >= 0 && bindex <= fidir->fd_bbot; + bindex++) { + hfile = fidir->fd_hfile + bindex; + do_pri_file(bindex, hfile ? hfile->hf_file : NULL); + } +} + +static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) +{ + struct vfsmount *mnt; + struct super_block *sb; + + if (!br || IS_ERR(br)) + goto out; + mnt = au_br_mnt(br); + if (!mnt || IS_ERR(mnt)) + goto out; + sb = mnt->mnt_sb; + if (!sb || IS_ERR(sb)) + goto out; + + dpri("s%d: {perm 0x%x, id %d, wbr %p}, " + "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " + "xino %d\n", + bindex, br->br_perm, br->br_id, br->br_wbr, + au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev), + sb->s_flags, sb->s_count, + atomic_read(&sb->s_active), + !!au_xino_file(br->br_xino, /*idx*/-1)); + return 0; + +out: + dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); + return -1; +} + +void au_dpri_sb(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + aufs_bindex_t bindex; + int err; + /* to reduce stack size */ + struct { + struct vfsmount mnt; + struct au_branch fake; + } *a; + + /* this function can be called from magic sysrq */ + a = kzalloc(sizeof(*a), GFP_ATOMIC); + if (unlikely(!a)) { + dpri("no memory\n"); + return; + } + + a->mnt.mnt_sb = sb; + a->fake.br_path.mnt = &a->mnt; + err = do_pri_br(-1, &a->fake); + au_kfree_rcu(a); + dpri("dev 0x%x\n", sb->s_dev); + if (err || !au_test_aufs(sb)) + return; + + sbinfo = au_sbi(sb); + if (!sbinfo) + return; + dpri("nw %d, gen %u, kobj %d\n", + atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation, + kref_read(&sbinfo->si_kobj.kref)); + for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++) + do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); +} + +/* ---------------------------------------------------------------------- */ + +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) +{ + struct inode *h_inode, *inode = d_inode(dentry); + struct dentry *h_dentry; + aufs_bindex_t bindex, bbot, bi; + + if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) + return; + + bbot = au_dbbot(dentry); + bi = au_ibbot(inode); + if (bi < bbot) + bbot = bi; + bindex = au_dbtop(dentry); + bi = au_ibtop(inode); + if (bi > bindex) + bindex = bi; + + for (; bindex <= bbot; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_inode = au_h_iptr(inode, bindex); + if (unlikely(h_inode != d_inode(h_dentry))) { + au_debug_on(); + AuDbg("b%d, %s:%d\n", bindex, func, line); + AuDbgDentry(dentry); + AuDbgInode(inode); + au_debug_off(); + BUG(); + } + } +} + +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) +{ + int err, i, j; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + AuDebugOn(err); + err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1); + AuDebugOn(err); + for (i = dpages.ndpage - 1; !err && i >= 0; i--) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + for (j = dpage->ndentry - 1; !err && j >= 0; j--) + AuDebugOn(au_digen_test(dentries[j], sigen)); + } + au_dpages_free(&dpages); +} + +void au_dbg_verify_kthread(void) +{ + if (au_wkq_test()) { + au_dbg_blocked(); + /* + * It may be recursive, but udba=notify between two aufs mounts, + * where a single ro branch is shared, is not a problem. + */ + /* WARN_ON(1); */ + } +} + +/* ---------------------------------------------------------------------- */ + +int __init au_debug_init(void) +{ + aufs_bindex_t bindex; + struct au_vdir_destr destr; + + bindex = -1; + AuDebugOn(bindex >= 0); + + destr.len = -1; + AuDebugOn(destr.len < NAME_MAX); + +#ifdef CONFIG_4KSTACKS + pr_warn("CONFIG_4KSTACKS is defined.\n"); +#endif + + return 0; +} diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h new file mode 100644 index 000000000000..9c52470a61fb --- /dev/null +++ b/fs/aufs/debug.h @@ -0,0 +1,226 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * debug print functions + */ + +#ifndef __AUFS_DEBUG_H__ +#define __AUFS_DEBUG_H__ + +#ifdef __KERNEL__ + +#include <linux/atomic.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/sysrq.h> + +#ifdef CONFIG_AUFS_DEBUG +#define AuDebugOn(a) BUG_ON(a) + +/* module parameter */ +extern atomic_t aufs_debug; +static inline void au_debug_on(void) +{ + atomic_inc(&aufs_debug); +} +static inline void au_debug_off(void) +{ + atomic_dec_if_positive(&aufs_debug); +} + +static inline int au_debug_test(void) +{ + return atomic_read(&aufs_debug) > 0; +} +#else +#define AuDebugOn(a) do {} while (0) +AuStubVoid(au_debug_on, void) +AuStubVoid(au_debug_off, void) +AuStubInt0(au_debug_test, void) +#endif /* CONFIG_AUFS_DEBUG */ + +#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t) + +/* ---------------------------------------------------------------------- */ + +/* debug print */ + +#define AuDbg(fmt, ...) do { \ + if (au_debug_test()) \ + pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \ +} while (0) +#define AuLabel(l) AuDbg(#l "\n") +#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__) +#define AuWarn1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_warn(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_err(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuIOErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + AuIOErr(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuUnsupportMsg "This operation is not supported." \ + " Please report this application to aufs-users ML." +#define AuUnsupport(fmt, ...) do { \ + pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \ + dump_stack(); \ +} while (0) + +#define AuTraceErr(e) do { \ + if (unlikely((e) < 0)) \ + AuDbg("err %d\n", (int)(e)); \ +} while (0) + +#define AuTraceErrPtr(p) do { \ + if (IS_ERR(p)) \ + AuDbg("err %ld\n", PTR_ERR(p)); \ +} while (0) + +/* dirty macros for debug print, use with "%.*s" and caution */ +#define AuLNPair(qstr) (qstr)->len, (qstr)->name + +/* ---------------------------------------------------------------------- */ + +struct dentry; +#ifdef CONFIG_AUFS_DEBUG +extern struct mutex au_dbg_mtx; +extern char *au_plevel; +struct au_nhash; +void au_dpri_whlist(struct au_nhash *whlist); +struct au_vdir; +void au_dpri_vdir(struct au_vdir *vdir); +struct inode; +void au_dpri_inode(struct inode *inode); +void au_dpri_dalias(struct inode *inode); +void au_dpri_dentry(struct dentry *dentry); +struct file; +void au_dpri_file(struct file *filp); +struct super_block; +void au_dpri_sb(struct super_block *sb); + +#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__) +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line); +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); +void au_dbg_verify_kthread(void); + +int __init au_debug_init(void); + +#define AuDbgWhlist(w) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#w "\n"); \ + au_dpri_whlist(w); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgVdir(v) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#v "\n"); \ + au_dpri_vdir(v); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgInode(i) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#i "\n"); \ + au_dpri_inode(i); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgDAlias(i) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#i "\n"); \ + au_dpri_dalias(i); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgDentry(d) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#d "\n"); \ + au_dpri_dentry(d); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgFile(f) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#f "\n"); \ + au_dpri_file(f); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgSb(sb) do { \ + mutex_lock(&au_dbg_mtx); \ + AuDbg(#sb "\n"); \ + au_dpri_sb(sb); \ + mutex_unlock(&au_dbg_mtx); \ +} while (0) + +#define AuDbgSym(addr) do { \ + char sym[KSYM_SYMBOL_LEN]; \ + sprint_symbol(sym, (unsigned long)addr); \ + AuDbg("%s\n", sym); \ +} while (0) +#else +AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry) +AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen) +AuStubVoid(au_dbg_verify_kthread, void) +AuStubInt0(__init au_debug_init, void) + +#define AuDbgWhlist(w) do {} while (0) +#define AuDbgVdir(v) do {} while (0) +#define AuDbgInode(i) do {} while (0) +#define AuDbgDAlias(i) do {} while (0) +#define AuDbgDentry(d) do {} while (0) +#define AuDbgFile(f) do {} while (0) +#define AuDbgSb(sb) do {} while (0) +#define AuDbgSym(addr) do {} while (0) +#endif /* CONFIG_AUFS_DEBUG */ + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +int __init au_sysrq_init(void); +void au_sysrq_fin(void); + +#ifdef CONFIG_HW_CONSOLE +#define au_dbg_blocked() do { \ + WARN_ON(1); \ + handle_sysrq('w'); \ +} while (0) +#else +AuStubVoid(au_dbg_blocked, void) +#endif + +#else +AuStubInt0(__init au_sysrq_init, void) +AuStubVoid(au_sysrq_fin, void) +AuStubVoid(au_dbg_blocked, void) +#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DEBUG_H__ */ diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c new file mode 100644 index 000000000000..faf664508e64 --- /dev/null +++ b/fs/aufs/dentry.c @@ -0,0 +1,1154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * lookup and dentry operations + */ + +#include <linux/iversion.h> +#include <linux/namei.h> +#include "aufs.h" + +/* + * returns positive/negative dentry, NULL or an error. + * NULL means whiteout-ed or not-found. + */ +static struct dentry* +au_do_lookup(struct dentry *h_parent, struct dentry *dentry, + aufs_bindex_t bindex, struct au_do_lookup_args *args) +{ + struct dentry *h_dentry; + struct inode *h_inode; + struct au_branch *br; + int wh_found, opq; + unsigned char wh_able; + const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); + const unsigned char ignore_perm = !!au_ftest_lkup(args->flags, + IGNORE_PERM); + + wh_found = 0; + br = au_sbr(dentry->d_sb, bindex); + wh_able = !!au_br_whable(br->br_perm); + if (wh_able) + wh_found = au_wh_test(h_parent, &args->whname, ignore_perm); + h_dentry = ERR_PTR(wh_found); + if (!wh_found) + goto real_lookup; + if (unlikely(wh_found < 0)) + goto out; + + /* We found a whiteout */ + /* au_set_dbbot(dentry, bindex); */ + au_set_dbwh(dentry, bindex); + if (!allow_neg) + return NULL; /* success */ + +real_lookup: + if (!ignore_perm) + h_dentry = vfsub_lkup_one(args->name, h_parent); + else + h_dentry = au_sio_lkup_one(args->name, h_parent); + if (IS_ERR(h_dentry)) { + if (PTR_ERR(h_dentry) == -ENAMETOOLONG + && !allow_neg) + h_dentry = NULL; + goto out; + } + + h_inode = d_inode(h_dentry); + if (d_is_negative(h_dentry)) { + if (!allow_neg) + goto out_neg; + } else if (wh_found + || (args->type && args->type != (h_inode->i_mode & S_IFMT))) + goto out_neg; + else if (au_ftest_lkup(args->flags, DIRREN) + /* && h_inode */ + && !au_dr_lkup_h_ino(args, bindex, h_inode->i_ino)) { + AuDbg("b%d %pd ignored hi%llu\n", bindex, h_dentry, + (unsigned long long)h_inode->i_ino); + goto out_neg; + } + + if (au_dbbot(dentry) <= bindex) + au_set_dbbot(dentry, bindex); + if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) + au_set_dbtop(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + + if (!d_is_dir(h_dentry) + || !wh_able + || (d_really_is_positive(dentry) && !d_is_dir(dentry))) + goto out; /* success */ + + inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); + opq = au_diropq_test(h_dentry); + inode_unlock_shared(h_inode); + if (opq > 0) + au_set_dbdiropq(dentry, bindex); + else if (unlikely(opq < 0)) { + au_set_h_dptr(dentry, bindex, NULL); + h_dentry = ERR_PTR(opq); + } + goto out; + +out_neg: + dput(h_dentry); + h_dentry = NULL; +out: + return h_dentry; +} + +static int au_test_shwh(struct super_block *sb, const struct qstr *name) +{ + if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) + && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) + return -EPERM; + return 0; +} + +/* + * returns the number of lower positive dentries, + * otherwise an error. + * can be called at unlinking with @type is zero. + */ +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, + unsigned int flags) +{ + int npositive, err; + aufs_bindex_t bindex, btail, bdiropq; + unsigned char isdir, dirperm1, dirren; + struct au_do_lookup_args args = { + .flags = flags, + .name = &dentry->d_name + }; + struct dentry *parent; + struct super_block *sb; + + sb = dentry->d_sb; + err = au_test_shwh(sb, args.name); + if (unlikely(err)) + goto out; + + err = au_wh_name_alloc(&args.whname, args.name); + if (unlikely(err)) + goto out; + + isdir = !!d_is_dir(dentry); + dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1); + dirren = !!au_opt_test(au_mntflags(sb), DIRREN); + if (dirren) + au_fset_lkup(args.flags, DIRREN); + + npositive = 0; + parent = dget_parent(dentry); + btail = au_dbtaildir(parent); + for (bindex = btop; bindex <= btail; bindex++) { + struct dentry *h_parent, *h_dentry; + struct inode *h_inode, *h_dir; + struct au_branch *br; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) { + if (d_is_positive(h_dentry)) + npositive++; + break; + } + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || !d_is_dir(h_parent)) + continue; + + if (dirren) { + /* if the inum matches, then use the prepared name */ + err = au_dr_lkup_name(&args, bindex); + if (unlikely(err)) + goto out_parent; + } + + h_dir = d_inode(h_parent); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + h_dentry = au_do_lookup(h_parent, dentry, bindex, &args); + inode_unlock_shared(h_dir); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out_parent; + if (h_dentry) + au_fclr_lkup(args.flags, ALLOW_NEG); + if (dirperm1) + au_fset_lkup(args.flags, IGNORE_PERM); + + if (au_dbwh(dentry) == bindex) + break; + if (!h_dentry) + continue; + if (d_is_negative(h_dentry)) + continue; + h_inode = d_inode(h_dentry); + npositive++; + if (!args.type) + args.type = h_inode->i_mode & S_IFMT; + if (args.type != S_IFDIR) + break; + else if (isdir) { + /* the type of lower may be different */ + bdiropq = au_dbdiropq(dentry); + if (bdiropq >= 0 && bdiropq <= bindex) + break; + } + br = au_sbr(sb, bindex); + if (dirren + && au_dr_hino_test_add(&br->br_dirren, h_inode->i_ino, + /*add_ent*/NULL)) { + /* prepare next name to lookup */ + err = au_dr_lkup(&args, dentry, bindex); + if (unlikely(err)) + goto out_parent; + } + } + + if (npositive) { + AuLabel(positive); + au_update_dbtop(dentry); + } + err = npositive; + if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE) + && au_dbtop(dentry) < 0)) { + err = -EIO; + AuIOErr("both of real entry and whiteout found, %pd, err %d\n", + dentry, err); + } + +out_parent: + dput(parent); + au_kfree_try_rcu(args.whname.name); + if (dirren) + au_dr_lkup_fin(&args); +out: + return err; +} + +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent) +{ + struct dentry *dentry; + int wkq_err; + + if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC)) + dentry = vfsub_lkup_one(name, parent); + else { + struct vfsub_lkup_one_args args = { + .errp = &dentry, + .name = name, + .parent = parent + }; + + wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args); + if (unlikely(wkq_err)) + dentry = ERR_PTR(wkq_err); + } + + return dentry; +} + +/* + * lookup @dentry on @bindex which should be negative. + */ +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh) +{ + int err; + struct dentry *parent, *h_parent, *h_dentry; + struct au_branch *br; + + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bindex); + br = au_sbr(dentry->d_sb, bindex); + if (wh) + h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); + else + h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out; + if (unlikely(d_is_positive(h_dentry))) { + err = -EIO; + AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex); + dput(h_dentry); + goto out; + } + + err = 0; + if (bindex < au_dbtop(dentry)) + au_set_dbtop(dentry, bindex); + if (au_dbbot(dentry) < bindex) + au_set_dbbot(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* subset of struct inode */ +struct au_iattr { + unsigned long i_ino; + /* unsigned int i_nlink; */ + kuid_t i_uid; + kgid_t i_gid; + u64 i_version; +/* + loff_t i_size; + blkcnt_t i_blocks; +*/ + umode_t i_mode; +}; + +static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) +{ + ia->i_ino = h_inode->i_ino; + /* ia->i_nlink = h_inode->i_nlink; */ + ia->i_uid = h_inode->i_uid; + ia->i_gid = h_inode->i_gid; + ia->i_version = inode_query_iversion(h_inode); +/* + ia->i_size = h_inode->i_size; + ia->i_blocks = h_inode->i_blocks; +*/ + ia->i_mode = (h_inode->i_mode & S_IFMT); +} + +static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode) +{ + return ia->i_ino != h_inode->i_ino + /* || ia->i_nlink != h_inode->i_nlink */ + || !uid_eq(ia->i_uid, h_inode->i_uid) + || !gid_eq(ia->i_gid, h_inode->i_gid) + || !inode_eq_iversion(h_inode, ia->i_version) +/* + || ia->i_size != h_inode->i_size + || ia->i_blocks != h_inode->i_blocks +*/ + || ia->i_mode != (h_inode->i_mode & S_IFMT); +} + +static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, + struct au_branch *br) +{ + int err; + struct au_iattr ia; + struct inode *h_inode; + struct dentry *h_d; + struct super_block *h_sb; + + err = 0; + memset(&ia, -1, sizeof(ia)); + h_sb = h_dentry->d_sb; + h_inode = NULL; + if (d_is_positive(h_dentry)) { + h_inode = d_inode(h_dentry); + au_iattr_save(&ia, h_inode); + } else if (au_test_nfs(h_sb) || au_test_fuse(h_sb)) + /* nfs d_revalidate may return 0 for negative dentry */ + /* fuse d_revalidate always return 0 for negative dentry */ + goto out; + + /* main purpose is namei.c:cached_lookup() and d_revalidate */ + h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent); + err = PTR_ERR(h_d); + if (IS_ERR(h_d)) + goto out; + + err = 0; + if (unlikely(h_d != h_dentry + || d_inode(h_d) != h_inode + || (h_inode && au_iattr_test(&ia, h_inode)))) + err = au_busy_or_stale(); + dput(h_d); + +out: + AuTraceErr(err); + return err; +} + +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br) +{ + int err; + + err = 0; + if (udba == AuOpt_UDBA_REVAL + && !au_test_fs_remote(h_dentry->d_sb)) { + IMustLock(h_dir); + err = (d_inode(h_dentry->d_parent) != h_dir); + } else if (udba != AuOpt_UDBA_NONE) + err = au_h_verify_dentry(h_dentry, h_parent, br); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) +{ + int err; + aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq; + struct au_hdentry tmp, *p, *q; + struct au_dinfo *dinfo; + struct super_block *sb; + + DiMustWriteLock(dentry); + + sb = dentry->d_sb; + dinfo = au_di(dentry); + bbot = dinfo->di_bbot; + bwh = dinfo->di_bwh; + bdiropq = dinfo->di_bdiropq; + bindex = dinfo->di_btop; + p = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, p++) { + if (!p->hd_dentry) + continue; + + new_bindex = au_br_index(sb, p->hd_id); + if (new_bindex == bindex) + continue; + + if (dinfo->di_bwh == bindex) + bwh = new_bindex; + if (dinfo->di_bdiropq == bindex) + bdiropq = new_bindex; + if (new_bindex < 0) { + au_hdput(p); + p->hd_dentry = NULL; + continue; + } + + /* swap two lower dentries, and loop again */ + q = au_hdentry(dinfo, new_bindex); + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hd_dentry) { + bindex--; + p--; + } + } + + dinfo->di_bwh = -1; + if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh)) + dinfo->di_bwh = bwh; + + dinfo->di_bdiropq = -1; + if (bdiropq >= 0 + && bdiropq <= au_sbbot(sb) + && au_sbr_whable(sb, bdiropq)) + dinfo->di_bdiropq = bdiropq; + + err = -EIO; + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + bbot = au_dbbot(parent); + bindex = 0; + p = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, p++) + if (p->hd_dentry) { + dinfo->di_btop = bindex; + break; + } + + if (dinfo->di_btop >= 0) { + bindex = bbot; + p = au_hdentry(dinfo, bindex); + for (; bindex >= 0; bindex--, p--) + if (p->hd_dentry) { + dinfo->di_bbot = bindex; + err = 0; + break; + } + } + + return err; +} + +static void au_do_hide(struct dentry *dentry) +{ + struct inode *inode; + + if (d_really_is_positive(dentry)) { + inode = d_inode(dentry); + if (!d_is_dir(dentry)) { + if (inode->i_nlink && !d_unhashed(dentry)) + drop_nlink(inode); + } else { + clear_nlink(inode); + /* stop next lookup */ + inode->i_flags |= S_DEAD; + } + smp_mb(); /* necessary? */ + } + d_drop(dentry); +} + +static int au_hide_children(struct dentry *parent) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *dentry; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, parent, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + /* in reverse order */ + for (i = dpages.ndpage - 1; i >= 0; i--) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = ndentry - 1; j >= 0; j--) { + dentry = dpage->dentries[j]; + if (dentry != parent) + au_do_hide(dentry); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static void au_hide(struct dentry *dentry) +{ + int err; + + AuDbgDentry(dentry); + if (d_is_dir(dentry)) { + /* shrink_dcache_parent(dentry); */ + err = au_hide_children(dentry); + if (unlikely(err)) + AuIOErr("%pd, failed hiding children, ignored %d\n", + dentry, err); + } + au_do_hide(dentry); +} + +/* + * By adding a dirty branch, a cached dentry may be affected in various ways. + * + * a dirty branch is added + * - on the top of layers + * - in the middle of layers + * - to the bottom of layers + * + * on the added branch there exists + * - a whiteout + * - a diropq + * - a same named entry + * + exist + * * negative --> positive + * * positive --> positive + * - type is unchanged + * - type is changed + * + doesn't exist + * * negative --> negative + * * positive --> negative (rejected by au_br_del() for non-dir case) + * - none + */ +static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo, + struct au_dinfo *tmp) +{ + int err; + aufs_bindex_t bindex, bbot; + struct { + struct dentry *dentry; + struct inode *inode; + mode_t mode; + } orig_h, tmp_h = { + .dentry = NULL + }; + struct au_hdentry *hd; + struct inode *inode, *h_inode; + struct dentry *h_dentry; + + err = 0; + AuDebugOn(dinfo->di_btop < 0); + orig_h.mode = 0; + orig_h.dentry = au_hdentry(dinfo, dinfo->di_btop)->hd_dentry; + orig_h.inode = NULL; + if (d_is_positive(orig_h.dentry)) { + orig_h.inode = d_inode(orig_h.dentry); + orig_h.mode = orig_h.inode->i_mode & S_IFMT; + } + if (tmp->di_btop >= 0) { + tmp_h.dentry = au_hdentry(tmp, tmp->di_btop)->hd_dentry; + if (d_is_positive(tmp_h.dentry)) { + tmp_h.inode = d_inode(tmp_h.dentry); + tmp_h.mode = tmp_h.inode->i_mode & S_IFMT; + } + } + + inode = NULL; + if (d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (!orig_h.inode) { + AuDbg("negative originally\n"); + if (inode) { + au_hide(dentry); + goto out; + } + AuDebugOn(inode); + AuDebugOn(dinfo->di_btop != dinfo->di_bbot); + AuDebugOn(dinfo->di_bdiropq != -1); + + if (!tmp_h.inode) { + AuDbg("negative --> negative\n"); + /* should have only one negative lower */ + if (tmp->di_btop >= 0 + && tmp->di_btop < dinfo->di_btop) { + AuDebugOn(tmp->di_btop != tmp->di_bbot); + AuDebugOn(dinfo->di_btop != dinfo->di_bbot); + au_set_h_dptr(dentry, dinfo->di_btop, NULL); + au_di_cp(dinfo, tmp); + hd = au_hdentry(tmp, tmp->di_btop); + au_set_h_dptr(dentry, tmp->di_btop, + dget(hd->hd_dentry)); + } + au_dbg_verify_dinode(dentry); + } else { + AuDbg("negative --> positive\n"); + /* + * similar to the behaviour of creating with bypassing + * aufs. + * unhash it in order to force an error in the + * succeeding create operation. + * we should not set S_DEAD here. + */ + d_drop(dentry); + /* au_di_swap(tmp, dinfo); */ + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive originally\n"); + /* inode may be NULL */ + AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode); + if (!tmp_h.inode) { + AuDbg("positive --> negative\n"); + /* or bypassing aufs */ + au_hide(dentry); + if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop) + dinfo->di_bwh = tmp->di_bwh; + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else if (orig_h.mode == tmp_h.mode) { + AuDbg("positive --> positive, same type\n"); + if (!S_ISDIR(orig_h.mode) + && dinfo->di_btop > tmp->di_btop) { + /* + * similar to the behaviour of removing and + * creating. + */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else { + /* fill empty slots */ + if (dinfo->di_btop > tmp->di_btop) + dinfo->di_btop = tmp->di_btop; + if (dinfo->di_bbot < tmp->di_bbot) + dinfo->di_bbot = tmp->di_bbot; + dinfo->di_bwh = tmp->di_bwh; + dinfo->di_bdiropq = tmp->di_bdiropq; + bbot = dinfo->di_bbot; + bindex = tmp->di_btop; + hd = au_hdentry(tmp, bindex); + for (; bindex <= bbot; bindex++, hd++) { + if (au_h_dptr(dentry, bindex)) + continue; + h_dentry = hd->hd_dentry; + if (!h_dentry) + continue; + AuDebugOn(d_is_negative(h_dentry)); + h_inode = d_inode(h_dentry); + AuDebugOn(orig_h.mode + != (h_inode->i_mode + & S_IFMT)); + au_set_h_dptr(dentry, bindex, + dget(h_dentry)); + } + if (inode) + err = au_refresh_hinode(inode, dentry); + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive --> positive, different type\n"); + /* similar to the behaviour of removing and creating */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } + } + +out: + return err; +} + +void au_refresh_dop(struct dentry *dentry, int force_reval) +{ + const struct dentry_operations *dop + = force_reval ? &aufs_dop : dentry->d_sb->s_d_op; + static const unsigned int mask + = DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE; + + BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags)); + + if (dentry->d_op == dop) + return; + + AuDbg("%pd\n", dentry); + spin_lock(&dentry->d_lock); + if (dop == &aufs_dop) + dentry->d_flags |= mask; + else + dentry->d_flags &= ~mask; + dentry->d_op = dop; + spin_unlock(&dentry->d_lock); +} + +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) +{ + int err, ebrange, nbr; + unsigned int sigen; + struct au_dinfo *dinfo, *tmp; + struct super_block *sb; + struct inode *inode; + + DiMustWriteLock(dentry); + AuDebugOn(IS_ROOT(dentry)); + AuDebugOn(d_really_is_negative(parent)); + + sb = dentry->d_sb; + sigen = au_sigen(sb); + err = au_digen_test(parent, sigen); + if (unlikely(err)) + goto out; + + nbr = au_sbbot(sb) + 1; + dinfo = au_di(dentry); + err = au_di_realloc(dinfo, nbr, /*may_shrink*/0); + if (unlikely(err)) + goto out; + ebrange = au_dbrange_test(dentry); + if (!ebrange) + ebrange = au_do_refresh_hdentry(dentry, parent); + + if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) { + AuDebugOn(au_dbtop(dentry) < 0 && au_dbbot(dentry) >= 0); + if (d_really_is_positive(dentry)) { + inode = d_inode(dentry); + err = au_refresh_hinode_self(inode); + } + au_dbg_verify_dinode(dentry); + if (!err) + goto out_dgen; /* success */ + goto out; + } + + /* temporary dinfo */ + AuDbgDentry(dentry); + err = -ENOMEM; + tmp = au_di_alloc(sb, AuLsc_DI_TMP); + if (unlikely(!tmp)) + goto out; + au_di_swap(tmp, dinfo); + /* returns the number of positive dentries */ + /* + * if current working dir is removed, it returns an error. + * but the dentry is legal. + */ + err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); + AuDbgDentry(dentry); + au_di_swap(tmp, dinfo); + if (err == -ENOENT) + err = 0; + if (err >= 0) { + /* compare/refresh by dinfo */ + AuDbgDentry(dentry); + err = au_refresh_by_dinfo(dentry, dinfo, tmp); + au_dbg_verify_dinode(dentry); + AuTraceErr(err); + } + au_di_realloc(dinfo, nbr, /*may_shrink*/1); /* harmless if err */ + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + if (unlikely(err)) + goto out; + +out_dgen: + au_update_digen(dentry); +out: + if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) { + AuIOErr("failed refreshing %pd, %d\n", dentry, err); + AuDbgDentry(dentry); + } + AuTraceErr(err); + return err; +} + +static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags, + struct dentry *dentry, aufs_bindex_t bindex) +{ + int err, valid; + + err = 0; + if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) + goto out; + + AuDbg("b%d\n", bindex); + /* + * gave up supporting LOOKUP_CREATE/OPEN for lower fs, + * due to whiteout and branch permission. + */ + flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE + | LOOKUP_FOLLOW | LOOKUP_EXCL); + /* it may return tri-state */ + valid = h_dentry->d_op->d_revalidate(h_dentry, flags); + + if (unlikely(valid < 0)) + err = valid; + else if (!valid) + err = -EINVAL; + +out: + AuTraceErr(err); + return err; +} + +/* todo: remove this */ +static int h_d_revalidate(struct dentry *dentry, struct inode *inode, + unsigned int flags, int do_udba, int dirren) +{ + int err; + umode_t mode, h_mode; + aufs_bindex_t bindex, btail, btop, ibs, ibe; + unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile; + struct inode *h_inode, *h_cached_inode; + struct dentry *h_dentry; + struct qstr *name, *h_name; + + err = 0; + plus = 0; + mode = 0; + ibs = -1; + ibe = -1; + unhashed = !!d_unhashed(dentry); + is_root = !!IS_ROOT(dentry); + name = &dentry->d_name; + tmpfile = au_di(dentry)->di_tmpfile; + + /* + * Theoretically, REVAL test should be unnecessary in case of + * {FS,I}NOTIFY. + * But {fs,i}notify doesn't fire some necessary events, + * IN_ATTRIB for atime/nlink/pageio + * Let's do REVAL test too. + */ + if (do_udba && inode) { + mode = (inode->i_mode & S_IFMT); + plus = (inode->i_nlink > 0); + ibs = au_ibtop(inode); + ibe = au_ibbot(inode); + } + + btop = au_dbtop(dentry); + btail = btop; + if (inode && S_ISDIR(inode->i_mode)) + btail = au_dbtaildir(dentry); + for (bindex = btop; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + AuDbg("b%d, %pd\n", bindex, h_dentry); + h_nfs = !!au_test_nfs(h_dentry->d_sb); + spin_lock(&h_dentry->d_lock); + h_name = &h_dentry->d_name; + if (unlikely(do_udba + && !is_root + && ((!h_nfs + && (unhashed != !!d_unhashed(h_dentry) + || (!tmpfile && !dirren + && !au_qstreq(name, h_name)) + )) + || (h_nfs + && !(flags & LOOKUP_OPEN) + && (h_dentry->d_flags + & DCACHE_NFSFS_RENAMED))) + )) { + int h_unhashed; + + h_unhashed = d_unhashed(h_dentry); + spin_unlock(&h_dentry->d_lock); + AuDbg("unhash 0x%x 0x%x, %pd %pd\n", + unhashed, h_unhashed, dentry, h_dentry); + goto err; + } + spin_unlock(&h_dentry->d_lock); + + err = au_do_h_d_reval(h_dentry, flags, dentry, bindex); + if (unlikely(err)) + /* do not goto err, to keep the errno */ + break; + + /* todo: plink too? */ + if (!do_udba) + continue; + + /* UDBA tests */ + if (unlikely(!!inode != d_is_positive(h_dentry))) + goto err; + + h_inode = NULL; + if (d_is_positive(h_dentry)) + h_inode = d_inode(h_dentry); + h_plus = plus; + h_mode = mode; + h_cached_inode = h_inode; + if (h_inode) { + h_mode = (h_inode->i_mode & S_IFMT); + h_plus = (h_inode->i_nlink > 0); + } + if (inode && ibs <= bindex && bindex <= ibe) + h_cached_inode = au_h_iptr(inode, bindex); + + if (!h_nfs) { + if (unlikely(plus != h_plus && !tmpfile)) + goto err; + } else { + if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED) + && !is_root + && !IS_ROOT(h_dentry) + && unhashed != d_unhashed(h_dentry))) + goto err; + } + if (unlikely(mode != h_mode + || h_cached_inode != h_inode)) + goto err; + continue; + +err: + err = -EINVAL; + break; + } + + AuTraceErr(err); + return err; +} + +/* todo: consolidate with do_refresh() and au_reval_for_attr() */ +static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *parent; + + if (!au_digen_test(dentry, sigen)) + return 0; + + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + AuDebugOn(au_digen_test(parent, sigen)); + au_dbg_verify_gen(parent, sigen); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + AuTraceErr(err); + return err; +} + +int au_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *d, *parent; + + if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) + return simple_reval_dpath(dentry, sigen); + + /* slow loop, keep it simple and stupid */ + /* cf: au_cpup_dirs() */ + err = 0; + parent = NULL; + while (au_digen_test(dentry, sigen)) { + d = dentry; + while (1) { + dput(parent); + parent = dget_parent(d); + if (!au_digen_test(parent, sigen)) + break; + d = parent; + } + + if (d != dentry) + di_write_lock_child2(d); + + /* someone might update our dentry while we were sleeping */ + if (au_digen_test(d, sigen)) { + /* + * todo: consolidate with simple_reval_dpath(), + * do_refresh() and au_reval_for_attr(). + */ + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(d, parent); + di_read_unlock(parent, AuLock_IR); + } + + if (d != dentry) + di_write_unlock(d); + dput(parent); + if (unlikely(err)) + break; + } + + return err; +} + +/* + * if valid returns 1, otherwise 0. + */ +static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + int valid, err; + unsigned int sigen; + unsigned char do_udba, dirren; + struct super_block *sb; + struct inode *inode; + + /* todo: support rcu-walk? */ + if (flags & LOOKUP_RCU) + return -ECHILD; + + valid = 0; + if (unlikely(!au_di(dentry))) + goto out; + + valid = 1; + sb = dentry->d_sb; + /* + * todo: very ugly + * i_mutex of parent dir may be held, + * but we should not return 'invalid' due to busy. + */ + err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM); + if (unlikely(err)) { + valid = err; + AuTraceErr(err); + goto out; + } + inode = NULL; + if (d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (unlikely(inode && au_is_bad_inode(inode))) { + err = -EINVAL; + AuTraceErr(err); + goto out_dgrade; + } + if (unlikely(au_dbrange_test(dentry))) { + err = -EINVAL; + AuTraceErr(err); + goto out_dgrade; + } + + sigen = au_sigen(sb); + if (au_digen_test(dentry, sigen)) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_dpath(dentry, sigen); + if (unlikely(err)) { + AuTraceErr(err); + goto out_dgrade; + } + } + di_downgrade_lock(dentry, AuLock_IR); + + err = -EINVAL; + if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY)) + && inode + && !(inode->i_state && I_LINKABLE) + && (IS_DEADDIR(inode) || !inode->i_nlink)) { + AuTraceErr(err); + goto out_inval; + } + + do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE); + if (do_udba && inode) { + aufs_bindex_t btop = au_ibtop(inode); + struct inode *h_inode; + + if (btop >= 0) { + h_inode = au_h_iptr(inode, btop); + if (h_inode && au_test_higen(inode, h_inode)) { + AuTraceErr(err); + goto out_inval; + } + } + } + + dirren = !!au_opt_test(au_mntflags(sb), DIRREN); + err = h_d_revalidate(dentry, inode, flags, do_udba, dirren); + if (unlikely(!err && do_udba && au_dbtop(dentry) < 0)) { + err = -EIO; + AuDbg("both of real entry and whiteout found, %p, err %d\n", + dentry, err); + } + goto out_inval; + +out_dgrade: + di_downgrade_lock(dentry, AuLock_IR); +out_inval: + aufs_read_unlock(dentry, AuLock_IR); + AuTraceErr(err); + valid = !err; +out: + if (!valid) { + AuDbg("%pd invalid, %d\n", dentry, valid); + d_drop(dentry); + } + return valid; +} + +static void aufs_d_release(struct dentry *dentry) +{ + if (au_di(dentry)) { + au_di_fin(dentry); + au_hn_di_reinit(dentry); + } +} + +const struct dentry_operations aufs_dop = { + .d_revalidate = aufs_d_revalidate, + .d_weak_revalidate = aufs_d_revalidate, + .d_release = aufs_d_release +}; + +/* aufs_dop without d_revalidate */ +const struct dentry_operations aufs_dop_noreval = { + .d_release = aufs_d_release +}; diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h new file mode 100644 index 000000000000..3b443fc7eef0 --- /dev/null +++ b/fs/aufs/dentry.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * lookup and dentry operations + */ + +#ifndef __AUFS_DENTRY_H__ +#define __AUFS_DENTRY_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include "dirren.h" +#include "rwsem.h" + +struct au_hdentry { + struct dentry *hd_dentry; + aufs_bindex_t hd_id; +}; + +struct au_dinfo { + atomic_t di_generation; + + struct au_rwsem di_rwsem; + aufs_bindex_t di_btop, di_bbot, di_bwh, di_bdiropq; + unsigned char di_tmpfile; /* to allow the different name */ + struct au_hdentry *di_hdentry; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* flags for au_lkup_dentry() */ +#define AuLkup_ALLOW_NEG 1 +#define AuLkup_IGNORE_PERM (1 << 1) +#define AuLkup_DIRREN (1 << 2) +#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name) +#define au_fset_lkup(flags, name) \ + do { (flags) |= AuLkup_##name; } while (0) +#define au_fclr_lkup(flags, name) \ + do { (flags) &= ~AuLkup_##name; } while (0) + +#ifndef CONFIG_AUFS_DIRREN +#undef AuLkup_DIRREN +#define AuLkup_DIRREN 0 +#endif + +struct au_do_lookup_args { + unsigned int flags; + mode_t type; + struct qstr whname, *name; + struct au_dr_lookup dirren; +}; + +/* ---------------------------------------------------------------------- */ + +/* dentry.c */ +extern const struct dentry_operations aufs_dop, aufs_dop_noreval; +struct au_branch; +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent); +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br); + +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, + unsigned int flags); +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh); +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent); +int au_reval_dpath(struct dentry *dentry, unsigned int sigen); +void au_refresh_dop(struct dentry *dentry, int force_reval); + +/* dinfo.c */ +void au_di_init_once(void *_di); +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc); +void au_di_free(struct au_dinfo *dinfo); +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b); +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src); +int au_di_init(struct dentry *dentry); +void au_di_fin(struct dentry *dentry); +int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink); + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc); +void di_read_unlock(struct dentry *d, int flags); +void di_downgrade_lock(struct dentry *d, int flags); +void di_write_lock(struct dentry *d, unsigned int lsc); +void di_write_unlock(struct dentry *d); +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_unlock2(struct dentry *d1, struct dentry *d2); + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex); +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex); +aufs_bindex_t au_dbtail(struct dentry *dentry); +aufs_bindex_t au_dbtaildir(struct dentry *dentry); + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry); +int au_digen_test(struct dentry *dentry, unsigned int sigen); +int au_dbrange_test(struct dentry *dentry); +void au_update_digen(struct dentry *dentry); +void au_update_dbrange(struct dentry *dentry, int do_put_zero); +void au_update_dbtop(struct dentry *dentry); +void au_update_dbbot(struct dentry *dentry); +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry); + +/* ---------------------------------------------------------------------- */ + +static inline struct au_dinfo *au_di(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for dinfo */ +enum { + AuLsc_DI_CHILD, /* child first */ + AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hnotify */ + AuLsc_DI_CHILD3, /* copyup dirs */ + AuLsc_DI_PARENT, + AuLsc_DI_PARENT2, + AuLsc_DI_PARENT3, + AuLsc_DI_TMP /* temp for replacing dinfo */ +}; + +/* + * di_read_lock_child, di_write_lock_child, + * di_read_lock_child2, di_write_lock_child2, + * di_read_lock_child3, di_write_lock_child3, + * di_read_lock_parent, di_write_lock_parent, + * di_read_lock_parent2, di_write_lock_parent2, + * di_read_lock_parent3, di_write_lock_parent3, + */ +#define AuReadLockFunc(name, lsc) \ +static inline void di_read_lock_##name(struct dentry *d, int flags) \ +{ di_read_lock(d, flags, AuLsc_DI_##lsc); } + +#define AuWriteLockFunc(name, lsc) \ +static inline void di_write_lock_##name(struct dentry *d) \ +{ di_write_lock(d, AuLsc_DI_##lsc); } + +#define AuRWLockFuncs(name, lsc) \ + AuReadLockFunc(name, lsc) \ + AuWriteLockFunc(name, lsc) + +AuRWLockFuncs(child, CHILD); +AuRWLockFuncs(child2, CHILD2); +AuRWLockFuncs(child3, CHILD3); +AuRWLockFuncs(parent, PARENT); +AuRWLockFuncs(parent2, PARENT2); +AuRWLockFuncs(parent3, PARENT3); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem) +#define DiMustAnyLock(d) AuRwMustAnyLock(&au_di(d)->di_rwsem) +#define DiMustWriteLock(d) AuRwMustWriteLock(&au_di(d)->di_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: memory barrier? */ +static inline unsigned int au_digen(struct dentry *d) +{ + return atomic_read(&au_di(d)->di_generation); +} + +static inline void au_h_dentry_init(struct au_hdentry *hdentry) +{ + hdentry->hd_dentry = NULL; +} + +static inline struct au_hdentry *au_hdentry(struct au_dinfo *di, + aufs_bindex_t bindex) +{ + return di->di_hdentry + bindex; +} + +static inline void au_hdput(struct au_hdentry *hd) +{ + if (hd) + dput(hd->hd_dentry); +} + +static inline aufs_bindex_t au_dbtop(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_btop; +} + +static inline aufs_bindex_t au_dbbot(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bbot; +} + +static inline aufs_bindex_t au_dbwh(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bwh; +} + +static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bdiropq; +} + +/* todo: hard/soft set? */ +static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_btop = bindex; +} + +static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bbot = bindex; +} + +static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + /* dbwh can be outside of btop - bbot range */ + au_di(dentry)->di_bwh = bindex; +} + +static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bdiropq = bindex; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_HNOTIFY +static inline void au_digen_dec(struct dentry *d) +{ + atomic_dec(&au_di(d)->di_generation); +} + +static inline void au_hn_di_reinit(struct dentry *dentry) +{ + dentry->d_fsdata = NULL; +} +#else +AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) +#endif /* CONFIG_AUFS_HNOTIFY */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DENTRY_H__ */ diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c new file mode 100644 index 000000000000..86140548f046 --- /dev/null +++ b/fs/aufs/dinfo.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dentry private data + */ + +#include "aufs.h" + +void au_di_init_once(void *_dinfo) +{ + struct au_dinfo *dinfo = _dinfo; + + au_rw_init(&dinfo->di_rwsem); +} + +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) +{ + struct au_dinfo *dinfo; + int nbr, i; + + dinfo = au_cache_alloc_dinfo(); + if (unlikely(!dinfo)) + goto out; + + nbr = au_sbbot(sb) + 1; + if (nbr <= 0) + nbr = 1; + dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); + if (dinfo->di_hdentry) { + au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + dinfo->di_bwh = -1; + dinfo->di_bdiropq = -1; + dinfo->di_tmpfile = 0; + for (i = 0; i < nbr; i++) + dinfo->di_hdentry[i].hd_id = -1; + goto out; + } + + au_cache_free_dinfo(dinfo); + dinfo = NULL; + +out: + return dinfo; +} + +void au_di_free(struct au_dinfo *dinfo) +{ + struct au_hdentry *p; + aufs_bindex_t bbot, bindex; + + /* dentry may not be revalidated */ + bindex = dinfo->di_btop; + if (bindex >= 0) { + bbot = dinfo->di_bbot; + p = au_hdentry(dinfo, bindex); + while (bindex++ <= bbot) + au_hdput(p++); + } + au_kfree_try_rcu(dinfo->di_hdentry); + au_cache_free_dinfo(dinfo); +} + +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) +{ + struct au_hdentry *p; + aufs_bindex_t bi; + + AuRwMustWriteLock(&a->di_rwsem); + AuRwMustWriteLock(&b->di_rwsem); + +#define DiSwap(v, name) \ + do { \ + v = a->di_##name; \ + a->di_##name = b->di_##name; \ + b->di_##name = v; \ + } while (0) + + DiSwap(p, hdentry); + DiSwap(bi, btop); + DiSwap(bi, bbot); + DiSwap(bi, bwh); + DiSwap(bi, bdiropq); + /* smp_mb(); */ + +#undef DiSwap +} + +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) +{ + AuRwMustWriteLock(&dst->di_rwsem); + AuRwMustWriteLock(&src->di_rwsem); + + dst->di_btop = src->di_btop; + dst->di_bbot = src->di_bbot; + dst->di_bwh = src->di_bwh; + dst->di_bdiropq = src->di_bdiropq; + /* smp_mb(); */ +} + +int au_di_init(struct dentry *dentry) +{ + int err; + struct super_block *sb; + struct au_dinfo *dinfo; + + err = 0; + sb = dentry->d_sb; + dinfo = au_di_alloc(sb, AuLsc_DI_CHILD); + if (dinfo) { + atomic_set(&dinfo->di_generation, au_sigen(sb)); + /* smp_mb(); */ /* atomic_set */ + dentry->d_fsdata = dinfo; + } else + err = -ENOMEM; + + return err; +} + +void au_di_fin(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + + dinfo = au_di(dentry); + AuRwDestroy(&dinfo->di_rwsem); + au_di_free(dinfo); +} + +int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink) +{ + int err, sz; + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + err = -ENOMEM; + sz = sizeof(*hdp) * (dinfo->di_bbot + 1); + if (!sz) + sz = sizeof(*hdp); + hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS, + may_shrink); + if (hdp) { + dinfo->di_hdentry = hdp; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void do_ii_write_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_write_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_write_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_write_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_write_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_write_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_write_lock_parent3(inode); + break; + default: + BUG(); + } +} + +static void do_ii_read_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_read_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_read_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_read_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_read_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_read_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_read_lock_parent3(inode); + break; + default: + BUG(); + } +} + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc) +{ + struct inode *inode; + + au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d_really_is_positive(d)) { + inode = d_inode(d); + if (au_ftest_lock(flags, IW)) + do_ii_write_lock(inode, lsc); + else if (au_ftest_lock(flags, IR)) + do_ii_read_lock(inode, lsc); + } +} + +void di_read_unlock(struct dentry *d, int flags) +{ + struct inode *inode; + + if (d_really_is_positive(d)) { + inode = d_inode(d); + if (au_ftest_lock(flags, IW)) { + au_dbg_verify_dinode(d); + ii_write_unlock(inode); + } else if (au_ftest_lock(flags, IR)) { + au_dbg_verify_dinode(d); + ii_read_unlock(inode); + } + } + au_rw_read_unlock(&au_di(d)->di_rwsem); +} + +void di_downgrade_lock(struct dentry *d, int flags) +{ + if (d_really_is_positive(d) && au_ftest_lock(flags, IR)) + ii_downgrade_lock(d_inode(d)); + au_rw_dgrade_lock(&au_di(d)->di_rwsem); +} + +void di_write_lock(struct dentry *d, unsigned int lsc) +{ + au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d_really_is_positive(d)) + do_ii_write_lock(d_inode(d), lsc); +} + +void di_write_unlock(struct dentry *d) +{ + au_dbg_verify_dinode(d); + if (d_really_is_positive(d)) + ii_write_unlock(d_inode(d)); + au_rw_write_unlock(&au_di(d)->di_rwsem); +} + +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d_inode(d1) == d_inode(d2) + || d1->d_sb != d2->d_sb); + + if ((isdir && au_test_subdir(d1, d2)) + || d1 < d2) { + di_write_lock_child(d1); + di_write_lock_child2(d2); + } else { + di_write_lock_child(d2); + di_write_lock_child2(d1); + } +} + +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d_inode(d1) == d_inode(d2) + || d1->d_sb != d2->d_sb); + + if ((isdir && au_test_subdir(d1, d2)) + || d1 < d2) { + di_write_lock_parent(d1); + di_write_lock_parent2(d2); + } else { + di_write_lock_parent(d2); + di_write_lock_parent2(d1); + } +} + +void di_write_unlock2(struct dentry *d1, struct dentry *d2) +{ + di_write_unlock(d1); + if (d_inode(d1) == d_inode(d2)) + au_rw_write_unlock(&au_di(d2)->di_rwsem); + else + di_write_unlock(d2); +} + +/* ---------------------------------------------------------------------- */ + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *d; + + DiMustAnyLock(dentry); + + if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) + return NULL; + AuDebugOn(bindex < 0); + d = au_hdentry(au_di(dentry), bindex)->hd_dentry; + AuDebugOn(d && au_dcount(d) <= 0); + return d; +} + +/* + * extended version of au_h_dptr(). + * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or + * error. + */ +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *h_dentry; + struct inode *inode, *h_inode; + + AuDebugOn(d_really_is_negative(dentry)); + + h_dentry = NULL; + if (au_dbtop(dentry) <= bindex + && bindex <= au_dbbot(dentry)) + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && !au_d_linkable(h_dentry)) { + dget(h_dentry); + goto out; /* success */ + } + + inode = d_inode(dentry); + AuDebugOn(bindex < au_ibtop(inode)); + AuDebugOn(au_ibbot(inode) < bindex); + h_inode = au_h_iptr(inode, bindex); + h_dentry = d_find_alias(h_inode); + if (h_dentry) { + if (!IS_ERR(h_dentry)) { + if (!au_d_linkable(h_dentry)) + goto out; /* success */ + dput(h_dentry); + } else + goto out; + } + + if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) { + h_dentry = au_plink_lkup(inode, bindex); + AuDebugOn(!h_dentry); + if (!IS_ERR(h_dentry)) { + if (!au_d_hashed_positive(h_dentry)) + goto out; /* success */ + dput(h_dentry); + h_dentry = NULL; + } + } + +out: + AuDbgDentry(h_dentry); + return h_dentry; +} + +aufs_bindex_t au_dbtail(struct dentry *dentry) +{ + aufs_bindex_t bbot, bwh; + + bbot = au_dbbot(dentry); + if (0 <= bbot) { + bwh = au_dbwh(dentry); + if (!bwh) + return bwh; + if (0 < bwh && bwh < bbot) + return bwh - 1; + } + return bbot; +} + +aufs_bindex_t au_dbtaildir(struct dentry *dentry) +{ + aufs_bindex_t bbot, bopq; + + bbot = au_dbtail(dentry); + if (0 <= bbot) { + bopq = au_dbdiropq(dentry); + if (0 <= bopq && bopq < bbot) + bbot = bopq; + } + return bbot; +} + +/* ---------------------------------------------------------------------- */ + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry) +{ + struct au_dinfo *dinfo; + struct au_hdentry *hd; + struct au_branch *br; + + DiMustWriteLock(dentry); + + dinfo = au_di(dentry); + hd = au_hdentry(dinfo, bindex); + au_hdput(hd); + hd->hd_dentry = h_dentry; + if (h_dentry) { + br = au_sbr(dentry->d_sb, bindex); + hd->hd_id = br->br_id; + } +} + +int au_dbrange_test(struct dentry *dentry) +{ + int err; + aufs_bindex_t btop, bbot; + + err = 0; + btop = au_dbtop(dentry); + bbot = au_dbbot(dentry); + if (btop >= 0) + AuDebugOn(bbot < 0 && btop > bbot); + else { + err = -EIO; + AuDebugOn(bbot >= 0); + } + + return err; +} + +int au_digen_test(struct dentry *dentry, unsigned int sigen) +{ + int err; + + err = 0; + if (unlikely(au_digen(dentry) != sigen + || au_iigen_test(d_inode(dentry), sigen))) + err = -EIO; + + return err; +} + +void au_update_digen(struct dentry *dentry) +{ + atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); + /* smp_mb(); */ /* atomic_set */ +} + +void au_update_dbrange(struct dentry *dentry, int do_put_zero) +{ + struct au_dinfo *dinfo; + struct dentry *h_d; + struct au_hdentry *hdp; + aufs_bindex_t bindex, bbot; + + DiMustWriteLock(dentry); + + dinfo = au_di(dentry); + if (!dinfo || dinfo->di_btop < 0) + return; + + if (do_put_zero) { + bbot = dinfo->di_bbot; + bindex = dinfo->di_btop; + hdp = au_hdentry(dinfo, bindex); + for (; bindex <= bbot; bindex++, hdp++) { + h_d = hdp->hd_dentry; + if (h_d && d_is_negative(h_d)) + au_set_h_dptr(dentry, bindex, NULL); + } + } + + dinfo->di_btop = 0; + hdp = au_hdentry(dinfo, dinfo->di_btop); + for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++) + if (hdp->hd_dentry) + break; + if (dinfo->di_btop > dinfo->di_bbot) { + dinfo->di_btop = -1; + dinfo->di_bbot = -1; + return; + } + + hdp = au_hdentry(dinfo, dinfo->di_bbot); + for (; dinfo->di_bbot >= 0; dinfo->di_bbot--, hdp--) + if (hdp->hd_dentry) + break; + AuDebugOn(dinfo->di_btop > dinfo->di_bbot || dinfo->di_bbot < 0); +} + +void au_update_dbtop(struct dentry *dentry) +{ + aufs_bindex_t bindex, bbot; + struct dentry *h_dentry; + + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (d_is_positive(h_dentry)) { + au_set_dbtop(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +void au_update_dbbot(struct dentry *dentry) +{ + aufs_bindex_t bindex, btop; + struct dentry *h_dentry; + + btop = au_dbtop(dentry); + for (bindex = au_dbbot(dentry); bindex >= btop; bindex--) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (d_is_positive(h_dentry)) { + au_set_dbbot(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) +{ + aufs_bindex_t bindex, bbot; + + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) + if (au_h_dptr(dentry, bindex) == h_dentry) + return bindex; + return -1; +} diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c new file mode 100644 index 000000000000..68e87d6f287e --- /dev/null +++ b/fs/aufs/dir.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * directory operations + */ + +#include <linux/fs_stack.h> +#include <linux/iversion.h> +#include "aufs.h" + +void au_add_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink += h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink += 2; + smp_mb(); /* for i_nlink */ + /* 0 can happen in revaliding */ + set_nlink(dir, nlink); +} + +void au_sub_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink -= h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink -= 2; + smp_mb(); /* for i_nlink */ + /* nlink == 0 means the branch-fs is broken */ + set_nlink(dir, nlink); +} + +loff_t au_dir_size(struct file *file, struct dentry *dentry) +{ + loff_t sz; + aufs_bindex_t bindex, bbot; + struct file *h_file; + struct dentry *h_dentry; + + sz = 0; + if (file) { + AuDebugOn(!d_is_dir(file->f_path.dentry)); + + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); + bindex <= bbot && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file && file_inode(h_file)) + sz += vfsub_f_size_read(h_file); + } + } else { + AuDebugOn(!dentry); + AuDebugOn(!d_is_dir(dentry)); + + bbot = au_dbtaildir(dentry); + for (bindex = au_dbtop(dentry); + bindex <= bbot && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) + sz += i_size_read(d_inode(h_dentry)); + } + } + if (sz < KMALLOC_MAX_SIZE) + sz = roundup_pow_of_two(sz); + if (sz > KMALLOC_MAX_SIZE) + sz = KMALLOC_MAX_SIZE; + else if (sz < NAME_MAX) { + BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); + sz = AUFS_RDBLK_DEF; + } + return sz; +} + +struct au_dir_ts_arg { + struct dentry *dentry; + aufs_bindex_t brid; +}; + +static void au_do_dir_ts(void *arg) +{ + struct au_dir_ts_arg *a = arg; + struct au_dtime dt; + struct path h_path; + struct inode *dir, *h_dir; + struct super_block *sb; + struct au_branch *br; + struct au_hinode *hdir; + int err; + aufs_bindex_t btop, bindex; + + sb = a->dentry->d_sb; + if (d_really_is_negative(a->dentry)) + goto out; + /* no dir->i_mutex lock */ + aufs_read_lock(a->dentry, AuLock_DW); /* noflush */ + + dir = d_inode(a->dentry); + btop = au_ibtop(dir); + bindex = au_br_index(sb, a->brid); + if (bindex < btop) + goto out_unlock; + + br = au_sbr(sb, bindex); + h_path.dentry = au_h_dptr(a->dentry, bindex); + if (!h_path.dentry) + goto out_unlock; + h_path.mnt = au_br_mnt(br); + au_dtime_store(&dt, a->dentry, &h_path); + + br = au_sbr(sb, btop); + if (!au_br_writable(br->br_perm)) + goto out_unlock; + h_path.dentry = au_h_dptr(a->dentry, btop); + h_path.mnt = au_br_mnt(br); + err = vfsub_mnt_want_write(h_path.mnt); + if (err) + goto out_unlock; + hdir = au_hi(dir, btop); + au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); + h_dir = au_h_iptr(dir, btop); + if (h_dir->i_nlink + && timespec64_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) { + dt.dt_h_path = h_path; + au_dtime_revert(&dt); + } + au_hn_inode_unlock(hdir); + vfsub_mnt_drop_write(h_path.mnt); + au_cpup_attr_timesizes(dir); + +out_unlock: + aufs_read_unlock(a->dentry, AuLock_DW); +out: + dput(a->dentry); + au_nwt_done(&au_sbi(sb)->si_nowait); + au_kfree_try_rcu(arg); +} + +void au_dir_ts(struct inode *dir, aufs_bindex_t bindex) +{ + int perm, wkq_err; + aufs_bindex_t btop; + struct au_dir_ts_arg *arg; + struct dentry *dentry; + struct super_block *sb; + + IMustLock(dir); + + dentry = d_find_any_alias(dir); + AuDebugOn(!dentry); + sb = dentry->d_sb; + btop = au_ibtop(dir); + if (btop == bindex) { + au_cpup_attr_timesizes(dir); + goto out; + } + + perm = au_sbr_perm(sb, btop); + if (!au_br_writable(perm)) + goto out; + + arg = kmalloc(sizeof(*arg), GFP_NOFS); + if (!arg) + goto out; + + arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */ + arg->brid = au_sbr_id(sb, bindex); + wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0); + if (unlikely(wkq_err)) { + pr_err("wkq %d\n", wkq_err); + dput(dentry); + au_kfree_try_rcu(arg); + } + +out: + dput(dentry); +} + +/* ---------------------------------------------------------------------- */ + +static int reopen_dir(struct file *file) +{ + int err; + unsigned int flags; + aufs_bindex_t bindex, btail, btop; + struct dentry *dentry, *h_dentry; + struct file *h_file; + + /* open all lower dirs */ + dentry = file->f_path.dentry; + btop = au_dbtop(dentry); + for (bindex = au_fbtop(file); bindex < btop; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbtop(file, btop); + + btail = au_dbtaildir(dentry); + for (bindex = au_fbbot_dir(file); btail < bindex; bindex--) + au_set_h_fptr(file, bindex, NULL); + au_set_fbbot_dir(file, btail); + + flags = vfsub_file_flags(file); + for (bindex = btop; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_file = au_hf_dir(file, bindex); + if (h_file) + continue; + + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; /* close all? */ + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + err = 0; + +out: + return err; +} + +static int do_open_dir(struct file *file, int flags, struct file *h_file) +{ + int err; + aufs_bindex_t bindex, btail; + struct dentry *dentry, *h_dentry; + struct vfsmount *mnt; + + FiMustWriteLock(file); + AuDebugOn(h_file); + + err = 0; + mnt = file->f_path.mnt; + dentry = file->f_path.dentry; + file->f_version = inode_query_iversion(d_inode(dentry)); + bindex = au_dbtop(dentry); + au_set_fbtop(file, bindex); + btail = au_dbtaildir(dentry); + au_set_fbbot_dir(file, btail); + for (; !err && bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + err = vfsub_test_mntns(mnt, h_dentry->d_sb); + if (unlikely(err)) + break; + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + break; + } + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + if (!err) + return 0; /* success */ + + /* close all */ + for (bindex = au_fbtop(file); bindex <= btail; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbtop(file, -1); + au_set_fbbot_dir(file, -1); + + return err; +} + +static int aufs_open_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + struct au_fidir *fidir; + + err = -ENOMEM; + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + fidir = au_fidir_alloc(sb); + if (fidir) { + struct au_do_open_args args = { + .open = do_open_dir, + .fidir = fidir + }; + err = au_do_open(file, &args); + if (unlikely(err)) + au_kfree_rcu(fidir); + } + si_read_unlock(sb); + return err; +} + +static int aufs_release_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + struct au_vdir *vdir_cache; + struct au_finfo *finfo; + struct au_fidir *fidir; + struct au_hfile *hf; + aufs_bindex_t bindex, bbot; + + finfo = au_fi(file); + fidir = finfo->fi_hdir; + if (fidir) { + au_hbl_del(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + vdir_cache = fidir->fd_vdir_cache; /* lock-free */ + if (vdir_cache) + au_vdir_free(vdir_cache); + + bindex = finfo->fi_btop; + if (bindex >= 0) { + hf = fidir->fd_hfile + bindex; + /* + * calls fput() instead of filp_close(), + * since no dnotify or lock for the lower file. + */ + bbot = fidir->fd_bbot; + for (; bindex <= bbot; bindex++, hf++) + if (hf->hf_file) + au_hfput(hf, /*execed*/0); + } + au_kfree_rcu(fidir); + finfo->fi_hdir = NULL; + } + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_dir(struct file *file, fl_owner_t id) +{ + int err; + aufs_bindex_t bindex, bbot; + struct file *h_file; + + err = 0; + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file) + err = vfsub_flush(h_file, id); + } + return err; +} + +static int aufs_flush_dir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_dir); +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) +{ + int err; + aufs_bindex_t bbot, bindex; + struct inode *inode; + struct super_block *sb; + + err = 0; + sb = dentry->d_sb; + inode = d_inode(dentry); + IMustLock(inode); + bbot = au_dbbot(dentry); + for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) { + struct path h_path; + + if (au_test_ro(sb, bindex, inode)) + continue; + h_path.dentry = au_h_dptr(dentry, bindex); + if (!h_path.dentry) + continue; + + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_fsync(NULL, &h_path, datasync); + } + + return err; +} + +static int au_do_fsync_dir(struct file *file, int datasync) +{ + int err; + aufs_bindex_t bbot, bindex; + struct file *h_file; + struct super_block *sb; + struct inode *inode; + + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); + if (unlikely(err)) + goto out; + + inode = file_inode(file); + sb = inode->i_sb; + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) { + h_file = au_hf_dir(file, bindex); + if (!h_file || au_test_ro(sb, bindex, inode)) + continue; + + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + } + +out: + return err; +} + +/* + * @file may be NULL + */ +static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct dentry *dentry; + struct inode *inode; + struct super_block *sb; + + err = 0; + dentry = file->f_path.dentry; + inode = d_inode(dentry); + inode_lock(inode); + sb = dentry->d_sb; + si_noflush_read_lock(sb); + if (file) + err = au_do_fsync_dir(file, datasync); + else { + di_write_lock_child(dentry); + err = au_do_fsync_dir_no_file(dentry, datasync); + } + au_cpup_attr_timesizes(inode); + di_write_unlock(dentry); + if (file) + fi_write_unlock(file); + + si_read_unlock(sb); + inode_unlock(inode); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_iterate_shared(struct file *file, struct dir_context *ctx) +{ + int err; + struct dentry *dentry; + struct inode *inode, *h_inode; + struct super_block *sb; + + AuDbg("%pD, ctx{%ps, %llu}\n", file, ctx->actor, ctx->pos); + + dentry = file->f_path.dentry; + inode = d_inode(dentry); + IMustLock(inode); + + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); + if (unlikely(err)) + goto out; + err = au_alive_dir(dentry); + if (!err) + err = au_vdir_init(file); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + + h_inode = au_h_iptr(inode, au_ibtop(inode)); + if (!au_test_nfsd()) { + err = au_vdir_fill_de(file, ctx); + fsstack_copy_attr_atime(inode, h_inode); + } else { + /* + * nfsd filldir may call lookup_one_len(), vfs_getattr(), + * encode_fh() and others. + */ + atomic_inc(&h_inode->i_count); + di_read_unlock(dentry, AuLock_IR); + si_read_unlock(sb); + err = au_vdir_fill_de(file, ctx); + fsstack_copy_attr_atime(inode, h_inode); + fi_write_unlock(file); + iput(h_inode); + + AuTraceErr(err); + return err; + } + +out_unlock: + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +#define AuTestEmpty_WHONLY 1 +#define AuTestEmpty_CALLED (1 << 1) +#define AuTestEmpty_SHWH (1 << 2) +#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) +#define au_fset_testempty(flags, name) \ + do { (flags) |= AuTestEmpty_##name; } while (0) +#define au_fclr_testempty(flags, name) \ + do { (flags) &= ~AuTestEmpty_##name; } while (0) + +#ifndef CONFIG_AUFS_SHWH +#undef AuTestEmpty_SHWH +#define AuTestEmpty_SHWH 0 +#endif + +struct test_empty_arg { + struct dir_context ctx; + struct au_nhash *whlist; + unsigned int flags; + int err; + aufs_bindex_t bindex; +}; + +static int test_empty_cb(struct dir_context *ctx, const char *__name, + int namelen, loff_t offset __maybe_unused, u64 ino, + unsigned int d_type) +{ + struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg, + ctx); + char *name = (void *)__name; + + arg->err = 0; + au_fset_testempty(arg->flags, CALLED); + /* smp_mb(); */ + if (name[0] == '.' + && (namelen == 1 || (name[1] == '.' && namelen == 2))) + goto out; /* success */ + + if (namelen <= AUFS_WH_PFX_LEN + || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + if (au_ftest_testempty(arg->flags, WHONLY) + && !au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = -ENOTEMPTY; + goto out; + } + + name += AUFS_WH_PFX_LEN; + namelen -= AUFS_WH_PFX_LEN; + if (!au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = au_nhash_append_wh + (arg->whlist, name, namelen, ino, d_type, arg->bindex, + au_ftest_testempty(arg->flags, SHWH)); + +out: + /* smp_mb(); */ + AuTraceErr(arg->err); + return arg->err; +} + +static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err; + struct file *h_file; + struct au_branch *br; + + h_file = au_h_open(dentry, arg->bindex, + O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE, + /*file*/NULL, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = 0; + if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) + && !file_inode(h_file)->i_nlink) + goto out_put; + + do { + arg->err = 0; + au_fclr_testempty(arg->flags, CALLED); + /* smp_mb(); */ + err = vfsub_iterate_dir(h_file, &arg->ctx); + if (err >= 0) + err = arg->err; + } while (!err && au_ftest_testempty(arg->flags, CALLED)); + +out_put: + fput(h_file); + br = au_sbr(dentry->d_sb, arg->bindex); + au_lcnt_dec(&br->br_nfiles); +out: + return err; +} + +struct do_test_empty_args { + int *errp; + struct dentry *dentry; + struct test_empty_arg *arg; +}; + +static void call_do_test_empty(void *args) +{ + struct do_test_empty_args *a = args; + *a->errp = do_test_empty(a->dentry, a->arg); +} + +static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err, wkq_err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = au_h_dptr(dentry, arg->bindex); + h_inode = d_inode(h_dentry); + /* todo: i_mode changes anytime? */ + inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); + err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); + inode_unlock_shared(h_inode); + if (!err) + err = do_test_empty(dentry, arg); + else { + struct do_test_empty_args args = { + .errp = &err, + .dentry = dentry, + .arg = arg + }; + unsigned int flags = arg->flags; + + wkq_err = au_wkq_wait(call_do_test_empty, &args); + if (unlikely(wkq_err)) + err = wkq_err; + arg->flags = flags; + } + + return err; +} + +int au_test_empty_lower(struct dentry *dentry) +{ + int err; + unsigned int rdhash; + aufs_bindex_t bindex, btop, btail; + struct au_nhash whlist; + struct test_empty_arg arg = { + .ctx = { + .actor = test_empty_cb + } + }; + int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg); + + SiMustAnyLock(dentry->d_sb); + + rdhash = au_sbi(dentry->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry)); + err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + + arg.flags = 0; + arg.whlist = &whlist; + btop = au_dbtop(dentry); + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + test_empty = do_test_empty; + if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1)) + test_empty = sio_test_empty; + arg.bindex = btop; + err = test_empty(dentry, &arg); + if (unlikely(err)) + goto out_whlist; + + au_fset_testempty(arg.flags, WHONLY); + btail = au_dbtaildir(dentry); + for (bindex = btop + 1; !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) { + arg.bindex = bindex; + err = test_empty(dentry, &arg); + } + } + +out_whlist: + au_nhash_wh_free(&whlist); +out: + return err; +} + +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) +{ + int err; + struct test_empty_arg arg = { + .ctx = { + .actor = test_empty_cb + } + }; + aufs_bindex_t bindex, btail; + + err = 0; + arg.whlist = whlist; + arg.flags = AuTestEmpty_WHONLY; + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + btail = au_dbtaildir(dentry); + for (bindex = au_dbtop(dentry); !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && d_is_positive(h_dentry)) { + arg.bindex = bindex; + err = sio_test_empty(dentry, &arg); + } + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_dir_fop = { + .owner = THIS_MODULE, + .llseek = default_llseek, + .read = generic_read_dir, + .iterate_shared = aufs_iterate_shared, + .unlocked_ioctl = aufs_ioctl_dir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_compat_ioctl_dir, +#endif + .open = aufs_open_dir, + .release = aufs_release_dir, + .flush = aufs_flush_dir, + .fsync = aufs_fsync_dir +}; diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h new file mode 100644 index 000000000000..5c8065d258bf --- /dev/null +++ b/fs/aufs/dir.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * directory operations + */ + +#ifndef __AUFS_DIR_H__ +#define __AUFS_DIR_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> + +/* ---------------------------------------------------------------------- */ + +/* need to be faster and smaller */ + +struct au_nhash { + unsigned int nh_num; + struct hlist_head *nh_head; +}; + +struct au_vdir_destr { + unsigned char len; + unsigned char name[0]; +} __packed; + +struct au_vdir_dehstr { + struct hlist_node hash; + struct au_vdir_destr *str; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +struct au_vdir_de { + ino_t de_ino; + unsigned char de_type; + /* caution: packed */ + struct au_vdir_destr de_str; +} __packed; + +struct au_vdir_wh { + struct hlist_node wh_hash; +#ifdef CONFIG_AUFS_SHWH + ino_t wh_ino; + aufs_bindex_t wh_bindex; + unsigned char wh_type; +#else + aufs_bindex_t wh_bindex; +#endif + /* caution: packed */ + struct au_vdir_destr wh_str; +} __packed; + +union au_vdir_deblk_p { + unsigned char *deblk; + struct au_vdir_de *de; +}; + +struct au_vdir { + unsigned char **vd_deblk; + unsigned long vd_nblk; + struct { + unsigned long ul; + union au_vdir_deblk_p p; + } vd_last; + + u64 vd_version; + unsigned int vd_deblk_sz; + unsigned long vd_jiffy; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* dir.c */ +extern const struct file_operations aufs_dir_fop; +void au_add_nlink(struct inode *dir, struct inode *h_dir); +void au_sub_nlink(struct inode *dir, struct inode *h_dir); +loff_t au_dir_size(struct file *file, struct dentry *dentry); +void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc); +int au_test_empty_lower(struct dentry *dentry); +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist); + +/* vdir.c */ +unsigned int au_rdhash_est(loff_t sz); +int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp); +void au_nhash_wh_free(struct au_nhash *whlist); +int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, + int limit); +int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen); +int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, + unsigned int d_type, aufs_bindex_t bindex, + unsigned char shwh); +void au_vdir_free(struct au_vdir *vdir); +int au_vdir_init(struct file *file); +int au_vdir_fill_de(struct file *file, struct dir_context *ctx); + +/* ioctl.c */ +long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); + +#ifdef CONFIG_AUFS_RDU +/* rdu.c */ +long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#endif +#else +AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file, + unsigned int cmd, unsigned long arg) +#ifdef CONFIG_COMPAT +AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file, + unsigned int cmd, unsigned long arg) +#endif +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DIR_H__ */ diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c new file mode 100644 index 000000000000..0bd412ab68c9 --- /dev/null +++ b/fs/aufs/dirren.c @@ -0,0 +1,1316 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2017-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * special handling in renaming a directory + * in order to support looking-up the before-renamed name on the lower readonly + * branches + */ + +#include <linux/byteorder/generic.h> +#include "aufs.h" + +static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent) +{ + int idx; + + idx = au_dr_ihash(ent->dr_h_ino); + au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx); +} + +static int au_dr_hino_test_empty(struct au_dr_br *dr) +{ + int ret, i; + struct hlist_bl_head *hbl; + + ret = 1; + for (i = 0; ret && i < AuDirren_NHASH; i++) { + hbl = dr->dr_h_ino + i; + hlist_bl_lock(hbl); + ret &= hlist_bl_empty(hbl); + hlist_bl_unlock(hbl); + } + + return ret; +} + +static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino) +{ + struct au_dr_hino *found, *ent; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + int idx; + + found = NULL; + idx = au_dr_ihash(ino); + hbl = dr->dr_h_ino + idx; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) + if (ent->dr_h_ino == ino) { + found = ent; + break; + } + hlist_bl_unlock(hbl); + + return found; +} + +int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino, + struct au_dr_hino *add_ent) +{ + int found, idx; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_dr_hino *ent; + + found = 0; + idx = au_dr_ihash(ino); + hbl = dr->dr_h_ino + idx; +#if 0 + { + struct hlist_bl_node *tmp; + + hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) + AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino); + } +#endif + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) + if (ent->dr_h_ino == ino) { + found = 1; + break; + } + if (!found && add_ent) + hlist_bl_add_head(&add_ent->dr_hnode, hbl); + hlist_bl_unlock(hbl); + + if (!found && add_ent) + AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino); + + return found; +} + +void au_dr_hino_free(struct au_dr_br *dr) +{ + int i; + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos, *tmp; + struct au_dr_hino *ent; + + /* SiMustWriteLock(sb); */ + + for (i = 0; i < AuDirren_NHASH; i++) { + hbl = dr->dr_h_ino + i; + /* no spinlock since sbinfo must be write-locked */ + hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) + au_kfree_rcu(ent); + INIT_HLIST_BL_HEAD(hbl); + } +} + +/* returns the number of inodes or an error */ +static int au_dr_hino_store(struct super_block *sb, struct au_branch *br, + struct file *hinofile) +{ + int err, i; + ssize_t ssz; + loff_t pos, oldsize; + __be64 u64; + struct inode *hinoinode; + struct hlist_bl_head *hbl; + struct hlist_bl_node *n1, *n2; + struct au_dr_hino *ent; + + SiMustWriteLock(sb); + AuDebugOn(!au_br_writable(br->br_perm)); + + hinoinode = file_inode(hinofile); + oldsize = i_size_read(hinoinode); + + err = 0; + pos = 0; + hbl = br->br_dirren.dr_h_ino; + for (i = 0; !err && i < AuDirren_NHASH; i++, hbl++) { + /* no bit-lock since sbinfo must be write-locked */ + hlist_bl_for_each_entry_safe(ent, n1, n2, hbl, dr_hnode) { + AuDbg("hi%llu, %pD2\n", + (unsigned long long)ent->dr_h_ino, hinofile); + u64 = cpu_to_be64(ent->dr_h_ino); + ssz = vfsub_write_k(hinofile, &u64, sizeof(u64), &pos); + if (ssz == sizeof(u64)) + continue; + + /* write error */ + pr_err("ssz %zd, %pD2\n", ssz, hinofile); + err = -ENOSPC; + if (ssz < 0) + err = ssz; + break; + } + } + /* regardless the error */ + if (pos < oldsize) { + err = vfsub_trunc(&hinofile->f_path, pos, /*attr*/0, hinofile); + AuTraceErr(err); + } + + AuTraceErr(err); + return err; +} + +static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile) +{ + int err, hidx; + ssize_t ssz; + size_t sz, n; + loff_t pos; + uint64_t u64; + struct au_dr_hino *ent; + struct inode *hinoinode; + struct hlist_bl_head *hbl; + + err = 0; + pos = 0; + hbl = dr->dr_h_ino; + hinoinode = file_inode(hinofile); + sz = i_size_read(hinoinode); + AuDebugOn(sz % sizeof(u64)); + n = sz / sizeof(u64); + while (n--) { + ssz = vfsub_read_k(hinofile, &u64, sizeof(u64), &pos); + if (unlikely(ssz != sizeof(u64))) { + pr_err("ssz %zd, %pD2\n", ssz, hinofile); + err = -EINVAL; + if (ssz < 0) + err = ssz; + goto out_free; + } + + ent = kmalloc(sizeof(*ent), GFP_NOFS); + if (!ent) { + err = -ENOMEM; + AuTraceErr(err); + goto out_free; + } + ent->dr_h_ino = be64_to_cpu((__force __be64)u64); + AuDbg("hi%llu, %pD2\n", + (unsigned long long)ent->dr_h_ino, hinofile); + hidx = au_dr_ihash(ent->dr_h_ino); + au_hbl_add(&ent->dr_hnode, hbl + hidx); + } + goto out; /* success */ + +out_free: + au_dr_hino_free(dr); +out: + AuTraceErr(err); + return err; +} + +/* + * @bindex/@br is a switch to distinguish whether suspending hnotify or not. + * @path is a switch to distinguish load and store. + */ +static int au_dr_hino(struct super_block *sb, aufs_bindex_t bindex, + struct au_branch *br, const struct path *path) +{ + int err, flags; + unsigned char load, suspend; + struct file *hinofile; + struct au_hinode *hdir; + struct inode *dir, *delegated; + struct path hinopath; + struct qstr hinoname = QSTR_INIT(AUFS_WH_DR_BRHINO, + sizeof(AUFS_WH_DR_BRHINO) - 1); + + AuDebugOn(bindex < 0 && !br); + AuDebugOn(bindex >= 0 && br); + + err = -EINVAL; + suspend = !br; + if (suspend) + br = au_sbr(sb, bindex); + load = !!path; + if (!load) { + path = &br->br_path; + AuDebugOn(!au_br_writable(br->br_perm)); + if (unlikely(!au_br_writable(br->br_perm))) + goto out; + } + + hdir = NULL; + if (suspend) { + dir = d_inode(sb->s_root); + hdir = au_hinode(au_ii(dir), bindex); + dir = hdir->hi_inode; + au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); + } else { + dir = d_inode(path->dentry); + inode_lock_nested(dir, AuLsc_I_CHILD); + } + hinopath.dentry = vfsub_lkup_one(&hinoname, path->dentry); + err = PTR_ERR(hinopath.dentry); + if (IS_ERR(hinopath.dentry)) + goto out_unlock; + + err = 0; + flags = O_RDONLY; + if (load) { + if (d_is_negative(hinopath.dentry)) + goto out_dput; /* success */ + } else { + if (au_dr_hino_test_empty(&br->br_dirren)) { + if (d_is_positive(hinopath.dentry)) { + delegated = NULL; + err = vfsub_unlink(dir, &hinopath, &delegated, + /*force*/0); + AuTraceErr(err); + if (unlikely(err)) + pr_err("ignored err %d, %pd2\n", + err, hinopath.dentry); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + err = 0; + } + goto out_dput; + } else if (!d_is_positive(hinopath.dentry)) { + err = vfsub_create(dir, &hinopath, 0600, + /*want_excl*/false); + AuTraceErr(err); + if (unlikely(err)) + goto out_dput; + } + flags = O_WRONLY; + } + hinopath.mnt = path->mnt; + hinofile = vfsub_dentry_open(&hinopath, flags); + if (suspend) + au_hn_inode_unlock(hdir); + else + inode_unlock(dir); + dput(hinopath.dentry); + AuTraceErrPtr(hinofile); + if (IS_ERR(hinofile)) { + err = PTR_ERR(hinofile); + goto out; + } + + if (load) + err = au_dr_hino_load(&br->br_dirren, hinofile); + else + err = au_dr_hino_store(sb, br, hinofile); + fput(hinofile); + goto out; + +out_dput: + dput(hinopath.dentry); +out_unlock: + if (suspend) + au_hn_inode_unlock(hdir); + else + inode_unlock(dir); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path) +{ + int err; + struct kstatfs kstfs; + dev_t dev; + struct dentry *dentry; + struct super_block *sb; + + err = vfs_statfs((void *)path, &kstfs); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + /* todo: support for UUID */ + + if (kstfs.f_fsid.val[0] || kstfs.f_fsid.val[1]) { + brid->type = AuBrid_FSID; + brid->fsid = kstfs.f_fsid; + } else { + dentry = path->dentry; + sb = dentry->d_sb; + dev = sb->s_dev; + if (dev) { + brid->type = AuBrid_DEV; + brid->dev = dev; + } + } + +out: + return err; +} + +int au_dr_br_init(struct super_block *sb, struct au_branch *br, + const struct path *path) +{ + int err, i; + struct au_dr_br *dr; + struct hlist_bl_head *hbl; + + dr = &br->br_dirren; + hbl = dr->dr_h_ino; + for (i = 0; i < AuDirren_NHASH; i++, hbl++) + INIT_HLIST_BL_HEAD(hbl); + + err = au_dr_brid_init(&dr->dr_brid, path); + if (unlikely(err)) + goto out; + + if (au_opt_test(au_mntflags(sb), DIRREN)) + err = au_dr_hino(sb, /*bindex*/-1, br, path); + +out: + AuTraceErr(err); + return err; +} + +int au_dr_br_fin(struct super_block *sb, struct au_branch *br) +{ + int err; + + err = 0; + if (au_br_writable(br->br_perm)) + err = au_dr_hino(sb, /*bindex*/-1, br, /*path*/NULL); + if (!err) + au_dr_hino_free(&br->br_dirren); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode, + char *buf, size_t sz) +{ + int err; + unsigned int major, minor; + char *p; + + p = buf; + err = snprintf(p, sz, "%d_", brid->type); + AuDebugOn(err > sz); + p += err; + sz -= err; + switch (brid->type) { + case AuBrid_Unset: + return -EINVAL; + case AuBrid_UUID: + err = snprintf(p, sz, "%pU", brid->uuid.b); + break; + case AuBrid_FSID: + err = snprintf(p, sz, "%08x-%08x", + brid->fsid.val[0], brid->fsid.val[1]); + break; + case AuBrid_DEV: + major = MAJOR(brid->dev); + minor = MINOR(brid->dev); + if (major <= 0xff && minor <= 0xff) + err = snprintf(p, sz, "%02x%02x", major, minor); + else + err = snprintf(p, sz, "%03x:%05x", major, minor); + break; + } + AuDebugOn(err > sz); + p += err; + sz -= err; + err = snprintf(p, sz, "_%llu", (unsigned long long)h_inode->i_ino); + AuDebugOn(err > sz); + p += err; + sz -= err; + + return p - buf; +} + +static int au_drinfo_name(struct au_branch *br, char *name, int len) +{ + int rlen; + struct dentry *br_dentry; + struct inode *br_inode; + + br_dentry = au_br_dentry(br); + br_inode = d_inode(br_dentry); + rlen = au_brid_str(&br->br_dirren.dr_brid, br_inode, name, len); + AuDebugOn(rlen >= AUFS_DIRREN_ENV_VAL_SZ); + AuDebugOn(rlen > len); + + return rlen; +} + +/* ---------------------------------------------------------------------- */ + +/* + * from the given @h_dentry, construct drinfo at @*fdata. + * when the size of @*fdata is not enough, reallocate and return new @fdata and + * @allocated. + */ +static int au_drinfo_construct(struct au_drinfo_fdata **fdata, + struct dentry *h_dentry, + unsigned char *allocated) +{ + int err, v; + struct au_drinfo_fdata *f, *p; + struct au_drinfo *drinfo; + struct inode *h_inode; + struct qstr *qname; + + err = 0; + f = *fdata; + h_inode = d_inode(h_dentry); + qname = &h_dentry->d_name; + drinfo = &f->drinfo; + drinfo->ino = (__force uint64_t)cpu_to_be64(h_inode->i_ino); + drinfo->oldnamelen = qname->len; + if (*allocated < sizeof(*f) + qname->len) { + v = roundup_pow_of_two(*allocated + qname->len); + p = au_krealloc(f, v, GFP_NOFS, /*may_shrink*/0); + if (unlikely(!p)) { + err = -ENOMEM; + AuTraceErr(err); + goto out; + } + f = p; + *fdata = f; + *allocated = v; + drinfo = &f->drinfo; + } + memcpy(drinfo->oldname, qname->name, qname->len); + AuDbg("i%llu, %.*s\n", + be64_to_cpu((__force __be64)drinfo->ino), drinfo->oldnamelen, + drinfo->oldname); + +out: + AuTraceErr(err); + return err; +} + +/* callers have to free the return value */ +static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino) +{ + struct au_drinfo *ret, *drinfo; + struct au_drinfo_fdata fdata; + int len; + loff_t pos; + ssize_t ssz; + + ret = ERR_PTR(-EIO); + pos = 0; + ssz = vfsub_read_k(file, &fdata, sizeof(fdata), &pos); + if (unlikely(ssz != sizeof(fdata))) { + AuIOErr("ssz %zd, %u, %pD2\n", + ssz, (unsigned int)sizeof(fdata), file); + goto out; + } + + fdata.magic = ntohl((__force __be32)fdata.magic); + switch (fdata.magic) { + case AUFS_DRINFO_MAGIC_V1: + break; + default: + AuIOErr("magic-num 0x%x, 0x%x, %pD2\n", + fdata.magic, AUFS_DRINFO_MAGIC_V1, file); + goto out; + } + + drinfo = &fdata.drinfo; + len = drinfo->oldnamelen; + if (!len) { + AuIOErr("broken drinfo %pD2\n", file); + goto out; + } + + ret = NULL; + drinfo->ino = be64_to_cpu((__force __be64)drinfo->ino); + if (unlikely(h_ino && drinfo->ino != h_ino)) { + AuDbg("ignored i%llu, i%llu, %pD2\n", + (unsigned long long)drinfo->ino, + (unsigned long long)h_ino, file); + goto out; /* success */ + } + + ret = kmalloc(sizeof(*ret) + len, GFP_NOFS); + if (unlikely(!ret)) { + ret = ERR_PTR(-ENOMEM); + AuTraceErrPtr(ret); + goto out; + } + + *ret = *drinfo; + ssz = vfsub_read_k(file, (void *)ret->oldname, len, &pos); + if (unlikely(ssz != len)) { + au_kfree_rcu(ret); + ret = ERR_PTR(-EIO); + AuIOErr("ssz %zd, %u, %pD2\n", ssz, len, file); + goto out; + } + + AuDbg("oldname %.*s\n", ret->oldnamelen, ret->oldname); + +out: + return ret; +} + +/* ---------------------------------------------------------------------- */ + +/* in order to be revertible */ +struct au_drinfo_rev_elm { + int created; + struct dentry *info_dentry; + struct au_drinfo *info_last; +}; + +struct au_drinfo_rev { + unsigned char already; + aufs_bindex_t nelm; + struct au_drinfo_rev_elm elm[0]; +}; + +/* todo: isn't it too large? */ +struct au_drinfo_store { + struct path h_ppath; + struct dentry *h_dentry; + struct au_drinfo_fdata *fdata; + char *infoname; /* inside of whname, just after PFX */ + char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ]; + aufs_bindex_t btgt, btail; + unsigned char no_sio, + allocated, /* current size of *fdata */ + infonamelen, /* room size for p */ + whnamelen, /* length of the generated name */ + renameback; /* renamed back */ +}; + +/* on rename(2) error, the caller should revert it using @elm */ +static int au_drinfo_do_store(struct au_drinfo_store *w, + struct au_drinfo_rev_elm *elm) +{ + int err, len; + ssize_t ssz; + loff_t pos; + struct path infopath = { + .mnt = w->h_ppath.mnt + }; + struct inode *h_dir, *h_inode, *delegated; + struct file *infofile; + struct qstr *qname; + + AuDebugOn(elm + && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm))); + + infopath.dentry = vfsub_lookup_one_len(w->whname, w->h_ppath.dentry, + w->whnamelen); + AuTraceErrPtr(infopath.dentry); + if (IS_ERR(infopath.dentry)) { + err = PTR_ERR(infopath.dentry); + goto out; + } + + err = 0; + h_dir = d_inode(w->h_ppath.dentry); + if (elm && d_is_negative(infopath.dentry)) { + err = vfsub_create(h_dir, &infopath, 0600, /*want_excl*/true); + AuTraceErr(err); + if (unlikely(err)) + goto out_dput; + elm->created = 1; + elm->info_dentry = dget(infopath.dentry); + } + + infofile = vfsub_dentry_open(&infopath, O_RDWR); + AuTraceErrPtr(infofile); + if (IS_ERR(infofile)) { + err = PTR_ERR(infofile); + goto out_dput; + } + + h_inode = d_inode(infopath.dentry); + if (elm && i_size_read(h_inode)) { + h_inode = d_inode(w->h_dentry); + elm->info_last = au_drinfo_read_k(infofile, h_inode->i_ino); + AuTraceErrPtr(elm->info_last); + if (IS_ERR(elm->info_last)) { + err = PTR_ERR(elm->info_last); + elm->info_last = NULL; + AuDebugOn(elm->info_dentry); + goto out_fput; + } + } + + if (elm && w->renameback) { + delegated = NULL; + err = vfsub_unlink(h_dir, &infopath, &delegated, /*force*/0); + AuTraceErr(err); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + goto out_fput; + } + + pos = 0; + qname = &w->h_dentry->d_name; + len = sizeof(*w->fdata) + qname->len; + if (!elm) + len = sizeof(*w->fdata) + w->fdata->drinfo.oldnamelen; + ssz = vfsub_write_k(infofile, w->fdata, len, &pos); + if (ssz == len) { + AuDbg("hi%llu, %.*s\n", w->fdata->drinfo.ino, + w->fdata->drinfo.oldnamelen, w->fdata->drinfo.oldname); + goto out_fput; /* success */ + } else { + err = -EIO; + if (ssz < 0) + err = ssz; + /* the caller should revert it using @elm */ + } + +out_fput: + fput(infofile); +out_dput: + dput(infopath.dentry); +out: + AuTraceErr(err); + return err; +} + +struct au_call_drinfo_do_store_args { + int *errp; + struct au_drinfo_store *w; + struct au_drinfo_rev_elm *elm; +}; + +static void au_call_drinfo_do_store(void *args) +{ + struct au_call_drinfo_do_store_args *a = args; + + *a->errp = au_drinfo_do_store(a->w, a->elm); +} + +static int au_drinfo_store_sio(struct au_drinfo_store *w, + struct au_drinfo_rev_elm *elm) +{ + int err, wkq_err; + + if (w->no_sio) + err = au_drinfo_do_store(w, elm); + else { + struct au_call_drinfo_do_store_args a = { + .errp = &err, + .w = w, + .elm = elm + }; + wkq_err = au_wkq_wait(au_call_drinfo_do_store, &a); + if (unlikely(wkq_err)) + err = wkq_err; + } + AuTraceErr(err); + + return err; +} + +static int au_drinfo_store_work_init(struct au_drinfo_store *w, + aufs_bindex_t btgt) +{ + int err; + + memset(w, 0, sizeof(*w)); + w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40); + strcpy(w->whname, AUFS_WH_DR_INFO_PFX); + w->infoname = w->whname + sizeof(AUFS_WH_DR_INFO_PFX) - 1; + w->infonamelen = sizeof(w->whname) - sizeof(AUFS_WH_DR_INFO_PFX); + w->btgt = btgt; + w->no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); + + err = -ENOMEM; + w->fdata = kcalloc(1, w->allocated, GFP_NOFS); + if (unlikely(!w->fdata)) { + AuTraceErr(err); + goto out; + } + w->fdata->magic = (__force uint32_t)htonl(AUFS_DRINFO_MAGIC_V1); + err = 0; + +out: + return err; +} + +static void au_drinfo_store_work_fin(struct au_drinfo_store *w) +{ + au_kfree_rcu(w->fdata); +} + +static void au_drinfo_store_rev(struct au_drinfo_rev *rev, + struct au_drinfo_store *w) +{ + struct au_drinfo_rev_elm *elm; + struct inode *h_dir, *delegated; + int err, nelm; + struct path infopath = { + .mnt = w->h_ppath.mnt + }; + + h_dir = d_inode(w->h_ppath.dentry); + IMustLock(h_dir); + + err = 0; + elm = rev->elm; + for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { + AuDebugOn(elm->created && elm->info_last); + if (elm->created) { + AuDbg("here\n"); + delegated = NULL; + infopath.dentry = elm->info_dentry; + err = vfsub_unlink(h_dir, &infopath, &delegated, + !w->no_sio); + AuTraceErr(err); + if (unlikely(err == -EWOULDBLOCK)) + iput(delegated); + dput(elm->info_dentry); + } else if (elm->info_last) { + AuDbg("here\n"); + w->fdata->drinfo = *elm->info_last; + memcpy(w->fdata->drinfo.oldname, + elm->info_last->oldname, + elm->info_last->oldnamelen); + err = au_drinfo_store_sio(w, /*elm*/NULL); + au_kfree_rcu(elm->info_last); + } + if (unlikely(err)) + AuIOErr("%d, %s\n", err, w->whname); + /* go on even if err */ + } +} + +/* caller has to call au_dr_rename_fin() later */ +static int au_drinfo_store(struct dentry *dentry, aufs_bindex_t btgt, + struct qstr *dst_name, void *_rev) +{ + int err, sz, nelm; + aufs_bindex_t bindex, btail; + struct au_drinfo_store work; + struct au_drinfo_rev *rev, **p; + struct au_drinfo_rev_elm *elm; + struct super_block *sb; + struct au_branch *br; + struct au_hinode *hdir; + + err = au_drinfo_store_work_init(&work, btgt); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + err = -ENOMEM; + btail = au_dbtaildir(dentry); + nelm = btail - btgt; + sz = sizeof(*rev) + sizeof(*elm) * nelm; + rev = kcalloc(1, sz, GFP_NOFS); + if (unlikely(!rev)) { + AuTraceErr(err); + goto out_args; + } + rev->nelm = nelm; + elm = rev->elm; + p = _rev; + *p = rev; + + err = 0; + sb = dentry->d_sb; + work.h_ppath.dentry = au_h_dptr(dentry, btgt); + work.h_ppath.mnt = au_sbr_mnt(sb, btgt); + hdir = au_hi(d_inode(dentry), btgt); + au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); + for (bindex = btgt + 1; bindex <= btail; bindex++, elm++) { + work.h_dentry = au_h_dptr(dentry, bindex); + if (!work.h_dentry) + continue; + + err = au_drinfo_construct(&work.fdata, work.h_dentry, + &work.allocated); + AuTraceErr(err); + if (unlikely(err)) + break; + + work.renameback = au_qstreq(&work.h_dentry->d_name, dst_name); + br = au_sbr(sb, bindex); + work.whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; + work.whnamelen += au_drinfo_name(br, work.infoname, + work.infonamelen); + AuDbg("whname %.*s, i%llu, %.*s\n", + work.whnamelen, work.whname, + be64_to_cpu((__force __be64)work.fdata->drinfo.ino), + work.fdata->drinfo.oldnamelen, + work.fdata->drinfo.oldname); + + err = au_drinfo_store_sio(&work, elm); + AuTraceErr(err); + if (unlikely(err)) + break; + } + if (unlikely(err)) { + /* revert all drinfo */ + au_drinfo_store_rev(rev, &work); + au_kfree_try_rcu(rev); + *p = NULL; + } + au_hn_inode_unlock(hdir); + +out_args: + au_drinfo_store_work_fin(&work); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev) +{ + int err, already; + ino_t ino; + struct super_block *sb; + struct au_branch *br; + struct au_dr_br *dr; + struct dentry *h_dentry; + struct inode *h_inode; + struct au_dr_hino *ent; + struct au_drinfo_rev *rev, **p; + + AuDbg("bindex %d\n", bindex); + + err = -ENOMEM; + ent = kmalloc(sizeof(*ent), GFP_NOFS); + if (unlikely(!ent)) + goto out; + + sb = src->d_sb; + br = au_sbr(sb, bindex); + dr = &br->br_dirren; + h_dentry = au_h_dptr(src, bindex); + h_inode = d_inode(h_dentry); + ino = h_inode->i_ino; + ent->dr_h_ino = ino; + already = au_dr_hino_test_add(dr, ino, ent); + AuDbg("b%d, hi%llu, already %d\n", + bindex, (unsigned long long)ino, already); + + err = au_drinfo_store(src, bindex, dst_name, _rev); + AuTraceErr(err); + if (!err) { + p = _rev; + rev = *p; + rev->already = already; + goto out; /* success */ + } + + /* revert */ + if (!already) + au_dr_hino_del(dr, ent); + au_kfree_rcu(ent); + +out: + AuTraceErr(err); + return err; +} + +void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ + struct au_drinfo_rev *rev; + struct au_drinfo_rev_elm *elm; + int nelm; + + rev = _rev; + elm = rev->elm; + for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { + dput(elm->info_dentry); + au_kfree_rcu(elm->info_last); + } + au_kfree_try_rcu(rev); +} + +void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ + int err; + struct au_drinfo_store work; + struct au_drinfo_rev *rev = _rev; + struct super_block *sb; + struct au_branch *br; + struct inode *h_inode; + struct au_dr_br *dr; + struct au_dr_hino *ent; + + err = au_drinfo_store_work_init(&work, btgt); + if (unlikely(err)) + goto out; + + sb = src->d_sb; + br = au_sbr(sb, btgt); + work.h_ppath.dentry = au_h_dptr(src, btgt); + work.h_ppath.mnt = au_br_mnt(br); + au_drinfo_store_rev(rev, &work); + au_drinfo_store_work_fin(&work); + if (rev->already) + goto out; + + dr = &br->br_dirren; + h_inode = d_inode(work.h_ppath.dentry); + ent = au_dr_hino_find(dr, h_inode->i_ino); + BUG_ON(!ent); + au_dr_hino_del(dr, ent); + au_kfree_rcu(ent); + +out: + au_kfree_try_rcu(rev); + if (unlikely(err)) + pr_err("failed to remove dirren info\n"); +} + +/* ---------------------------------------------------------------------- */ + +static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath, + char *whname, int whnamelen, + struct dentry **info_dentry) +{ + struct au_drinfo *drinfo; + struct file *f; + struct inode *h_dir; + struct path infopath; + int unlocked; + + AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname); + + *info_dentry = NULL; + drinfo = NULL; + unlocked = 0; + h_dir = d_inode(h_ppath->dentry); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + infopath.dentry = vfsub_lookup_one_len(whname, h_ppath->dentry, + whnamelen); + if (IS_ERR(infopath.dentry)) { + drinfo = (void *)infopath.dentry; + goto out; + } + + if (d_is_negative(infopath.dentry)) + goto out_dput; /* success */ + + infopath.mnt = h_ppath->mnt; + f = vfsub_dentry_open(&infopath, O_RDONLY); + inode_unlock_shared(h_dir); + unlocked = 1; + if (IS_ERR(f)) { + drinfo = (void *)f; + goto out_dput; + } + + drinfo = au_drinfo_read_k(f, /*h_ino*/0); + if (IS_ERR_OR_NULL(drinfo)) + goto out_fput; + + AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname); + *info_dentry = dget(infopath.dentry); /* keep it alive */ + +out_fput: + fput(f); +out_dput: + dput(infopath.dentry); +out: + if (!unlocked) + inode_unlock_shared(h_dir); + AuTraceErrPtr(drinfo); + return drinfo; +} + +struct au_drinfo_do_load_args { + struct au_drinfo **drinfop; + struct path *h_ppath; + char *whname; + int whnamelen; + struct dentry **info_dentry; +}; + +static void au_call_drinfo_do_load(void *args) +{ + struct au_drinfo_do_load_args *a = args; + + *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen, + a->info_dentry); +} + +struct au_drinfo_load { + struct path h_ppath; + struct qstr *qname; + unsigned char no_sio; + + aufs_bindex_t ninfo; + struct au_drinfo **drinfo; +}; + +static int au_drinfo_load(struct au_drinfo_load *w, aufs_bindex_t bindex, + struct au_branch *br) +{ + int err, wkq_err, whnamelen, e; + char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ] + = AUFS_WH_DR_INFO_PFX; + struct au_drinfo *drinfo; + struct qstr oldname; + struct inode *h_dir, *delegated; + struct dentry *info_dentry; + struct path infopath; + + whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; + whnamelen += au_drinfo_name(br, whname + whnamelen, + sizeof(whname) - whnamelen); + if (w->no_sio) + drinfo = au_drinfo_do_load(&w->h_ppath, whname, whnamelen, + &info_dentry); + else { + struct au_drinfo_do_load_args args = { + .drinfop = &drinfo, + .h_ppath = &w->h_ppath, + .whname = whname, + .whnamelen = whnamelen, + .info_dentry = &info_dentry + }; + wkq_err = au_wkq_wait(au_call_drinfo_do_load, &args); + if (unlikely(wkq_err)) + drinfo = ERR_PTR(wkq_err); + } + err = PTR_ERR(drinfo); + if (IS_ERR_OR_NULL(drinfo)) + goto out; + + err = 0; + oldname.len = drinfo->oldnamelen; + oldname.name = drinfo->oldname; + if (au_qstreq(w->qname, &oldname)) { + /* the name is renamed back */ + au_kfree_rcu(drinfo); + drinfo = NULL; + + infopath.dentry = info_dentry; + infopath.mnt = w->h_ppath.mnt; + h_dir = d_inode(w->h_ppath.dentry); + delegated = NULL; + inode_lock_nested(h_dir, AuLsc_I_PARENT); + e = vfsub_unlink(h_dir, &infopath, &delegated, !w->no_sio); + inode_unlock(h_dir); + if (unlikely(e)) + AuIOErr("ignored %d, %pd2\n", e, &infopath.dentry); + if (unlikely(e == -EWOULDBLOCK)) + iput(delegated); + } + au_kfree_rcu(w->drinfo[bindex]); + w->drinfo[bindex] = drinfo; + dput(info_dentry); + +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_dr_lkup_free(struct au_drinfo **drinfo, int n) +{ + struct au_drinfo **p = drinfo; + + while (n-- > 0) + au_kfree_rcu(*drinfo++); + au_kfree_try_rcu(p); +} + +int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t btgt) +{ + int err, ninfo; + struct au_drinfo_load w; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + struct inode *h_dir; + struct au_dr_hino *ent; + struct super_block *sb; + + AuDbg("%.*s, name %.*s, whname %.*s, b%d\n", + AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name), + AuLNPair(&lkup->whname), btgt); + + sb = dentry->d_sb; + bbot = au_sbbot(sb); + w.ninfo = bbot + 1; + if (!lkup->dirren.drinfo) { + lkup->dirren.drinfo = kcalloc(w.ninfo, + sizeof(*lkup->dirren.drinfo), + GFP_NOFS); + if (unlikely(!lkup->dirren.drinfo)) { + err = -ENOMEM; + goto out; + } + lkup->dirren.ninfo = w.ninfo; + } + w.drinfo = lkup->dirren.drinfo; + w.no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); + w.h_ppath.dentry = au_h_dptr(dentry, btgt); + AuDebugOn(!w.h_ppath.dentry); + w.h_ppath.mnt = au_sbr_mnt(sb, btgt); + w.qname = &dentry->d_name; + + ninfo = 0; + for (bindex = btgt + 1; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_drinfo_load(&w, bindex, br); + if (unlikely(err)) + goto out_free; + if (w.drinfo[bindex]) + ninfo++; + } + if (!ninfo) { + br = au_sbr(sb, btgt); + h_dir = d_inode(w.h_ppath.dentry); + ent = au_dr_hino_find(&br->br_dirren, h_dir->i_ino); + AuDebugOn(!ent); + au_dr_hino_del(&br->br_dirren, ent); + au_kfree_rcu(ent); + } + goto out; /* success */ + +out_free: + au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); + lkup->dirren.ninfo = 0; + lkup->dirren.drinfo = NULL; +out: + AuTraceErr(err); + return err; +} + +void au_dr_lkup_fin(struct au_do_lookup_args *lkup) +{ + au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); +} + +int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt) +{ + int err; + struct au_drinfo *drinfo; + + err = 0; + if (!lkup->dirren.drinfo) + goto out; + AuDebugOn(lkup->dirren.ninfo < btgt + 1); + drinfo = lkup->dirren.drinfo[btgt + 1]; + if (!drinfo) + goto out; + + au_kfree_try_rcu(lkup->whname.name); + lkup->whname.name = NULL; + lkup->dirren.dr_name.len = drinfo->oldnamelen; + lkup->dirren.dr_name.name = drinfo->oldname; + lkup->name = &lkup->dirren.dr_name; + err = au_wh_name_alloc(&lkup->whname, lkup->name); + if (!err) + AuDbg("name %.*s, whname %.*s, b%d\n", + AuLNPair(lkup->name), AuLNPair(&lkup->whname), + btgt); + +out: + AuTraceErr(err); + return err; +} + +int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, + ino_t h_ino) +{ + int match; + struct au_drinfo *drinfo; + + match = 1; + if (!lkup->dirren.drinfo) + goto out; + AuDebugOn(lkup->dirren.ninfo < bindex + 1); + drinfo = lkup->dirren.drinfo[bindex + 1]; + if (!drinfo) + goto out; + + match = (drinfo->ino == h_ino); + AuDbg("match %d\n", match); + +out: + return match; +} + +/* ---------------------------------------------------------------------- */ + +int au_dr_opt_set(struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path); + } + + return err; +} + +int au_dr_opt_flush(struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + bbot = au_sbbot(sb); + for (bindex = 0; !err && bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm)) + err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL); + } + + return err; +} + +int au_dr_opt_clr(struct super_block *sb, int no_flush) +{ + int err; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + err = 0; + if (!no_flush) { + err = au_dr_opt_flush(sb); + if (unlikely(err)) + goto out; + } + + bbot = au_sbbot(sb); + for (bindex = 0; bindex <= bbot; bindex++) { + br = au_sbr(sb, bindex); + au_dr_hino_free(&br->br_dirren); + } + +out: + return err; +} diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h new file mode 100644 index 000000000000..a986736462c3 --- /dev/null +++ b/fs/aufs/dirren.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * renamed dir info + */ + +#ifndef __AUFS_DIRREN_H__ +#define __AUFS_DIRREN_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include <linux/statfs.h> +#include <linux/uuid.h> +#include "hbl.h" + +#define AuDirren_NHASH 100 + +#ifdef CONFIG_AUFS_DIRREN +enum au_brid_type { + AuBrid_Unset, + AuBrid_UUID, + AuBrid_FSID, + AuBrid_DEV +}; + +struct au_dr_brid { + enum au_brid_type type; + union { + uuid_t uuid; /* unimplemented yet */ + fsid_t fsid; + dev_t dev; + }; +}; + +/* 20 is the max digits length of ulong 64 */ +/* brid-type "_" uuid "_" inum */ +#define AUFS_DIRREN_FNAME_SZ (1 + 1 + UUID_STRING_LEN + 20) +#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20) + +struct au_dr_hino { + struct hlist_bl_node dr_hnode; + ino_t dr_h_ino; +}; + +struct au_dr_br { + struct hlist_bl_head dr_h_ino[AuDirren_NHASH]; + struct au_dr_brid dr_brid; +}; + +struct au_dr_lookup { + /* dr_name is pointed by struct au_do_lookup_args.name */ + struct qstr dr_name; /* subset of dr_info */ + aufs_bindex_t ninfo; + struct au_drinfo **drinfo; +}; +#else +struct au_dr_hino; +/* empty */ +struct au_dr_br { }; +struct au_dr_lookup { }; +#endif + +/* ---------------------------------------------------------------------- */ + +struct au_branch; +struct au_do_lookup_args; +struct au_hinode; +#ifdef CONFIG_AUFS_DIRREN +int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino, + struct au_dr_hino *add_ent); +void au_dr_hino_free(struct au_dr_br *dr); +int au_dr_br_init(struct super_block *sb, struct au_branch *br, + const struct path *path); +int au_dr_br_fin(struct super_block *sb, struct au_branch *br); +int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev); +void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev); +void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev); +int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t bindex); +int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt); +int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, + ino_t h_ino); +void au_dr_lkup_fin(struct au_do_lookup_args *lkup); +int au_dr_opt_set(struct super_block *sb); +int au_dr_opt_flush(struct super_block *sb); +int au_dr_opt_clr(struct super_block *sb, int no_flush); +#else +AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino, + struct au_dr_hino *add_ent); +AuStubVoid(au_dr_hino_free, struct au_dr_br *dr); +AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br, + const struct path *path); +AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br); +AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex, + struct qstr *dst_name, void *_rev); +AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev); +AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex, + void *rev); +AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry, + aufs_bindex_t bindex); +AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt); +AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup, + aufs_bindex_t bindex, ino_t h_ino); +AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup); +AuStubInt0(au_dr_opt_set, struct super_block *sb); +AuStubInt0(au_dr_opt_flush, struct super_block *sb); +AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush); +#endif + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_DIRREN +static inline int au_dr_ihash(ino_t h_ino) +{ + return h_ino % AuDirren_NHASH; +} +#else +AuStubInt0(au_dr_ihash, ino_t h_ino); +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DIRREN_H__ */ diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c new file mode 100644 index 000000000000..ed79f8255a8f --- /dev/null +++ b/fs/aufs/dynop.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dynamically customizable operations for regular files + */ + +#include "aufs.h" + +#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) + +/* + * How large will these lists be? + * Usually just a few elements, 20-30 at most for each, I guess. + */ +static struct hlist_bl_head dynop[AuDyLast]; + +static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl, + const void *h_op) +{ + struct au_dykey *key, *tmp; + struct hlist_bl_node *pos; + + key = NULL; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) + if (tmp->dk_op.dy_hop == h_op) { + if (kref_get_unless_zero(&tmp->dk_kref)) + key = tmp; + break; + } + hlist_bl_unlock(hbl); + + return key; +} + +static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) +{ + struct au_dykey **k, *found; + const void *h_op = key->dk_op.dy_hop; + int i; + + found = NULL; + k = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else + break; + if (!found) { + spin_lock(&br->br_dykey_lock); + for (; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else { + k[i] = key; + break; + } + spin_unlock(&br->br_dykey_lock); + BUG_ON(i == AuBrDynOp); /* expand the array */ + } + + return found; +} + +/* kref_get() if @key is already added */ +static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key) +{ + struct au_dykey *tmp, *found; + struct hlist_bl_node *pos; + const void *h_op = key->dk_op.dy_hop; + + found = NULL; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) + if (tmp->dk_op.dy_hop == h_op) { + if (kref_get_unless_zero(&tmp->dk_kref)) + found = tmp; + break; + } + if (!found) + hlist_bl_add_head(&key->dk_hnode, hbl); + hlist_bl_unlock(hbl); + + if (!found) + DyPrSym(key); + return found; +} + +static void dy_free_rcu(struct rcu_head *rcu) +{ + struct au_dykey *key; + + key = container_of(rcu, struct au_dykey, dk_rcu); + DyPrSym(key); + kfree(key); +} + +static void dy_free(struct kref *kref) +{ + struct au_dykey *key; + struct hlist_bl_head *hbl; + + key = container_of(kref, struct au_dykey, dk_kref); + hbl = dynop + key->dk_op.dy_type; + au_hbl_del(&key->dk_hnode, hbl); + call_rcu(&key->dk_rcu, dy_free_rcu); +} + +void au_dy_put(struct au_dykey *key) +{ + kref_put(&key->dk_kref, dy_free); +} + +/* ---------------------------------------------------------------------- */ + +#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) + +#ifdef CONFIG_AUFS_DEBUG +#define DyDbgDeclare(cnt) unsigned int cnt = 0 +#define DyDbgInc(cnt) do { cnt++; } while (0) +#else +#define DyDbgDeclare(cnt) do {} while (0) +#define DyDbgInc(cnt) do {} while (0) +#endif + +#define DySet(func, dst, src, h_op, h_sb) do { \ + DyDbgInc(cnt); \ + if (h_op->func) { \ + if (src.func) \ + dst.func = src.func; \ + else \ + AuDbg("%s %s\n", au_sbtype(h_sb), #func); \ + } \ +} while (0) + +#define DySetForce(func, dst, src) do { \ + AuDebugOn(!src.func); \ + DyDbgInc(cnt); \ + dst.func = src.func; \ +} while (0) + +#define DySetAop(func) \ + DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) +#define DySetAopForce(func) \ + DySetForce(func, dyaop->da_op, aufs_aop) + +static void dy_aop(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused) +{ + struct au_dyaop *dyaop = (void *)key; + const struct address_space_operations *h_aop = h_op; + DyDbgDeclare(cnt); + + AuDbg("%s\n", au_sbtype(h_sb)); + + DySetAop(writepage); + DySetAopForce(readpage); /* force */ + DySetAop(writepages); + DySetAop(set_page_dirty); + DySetAop(readpages); + DySetAop(write_begin); + DySetAop(write_end); + DySetAop(bmap); + DySetAop(invalidatepage); + DySetAop(releasepage); + DySetAop(freepage); + /* this one will be changed according to an aufs mount option */ + DySetAop(direct_IO); + DySetAop(migratepage); + DySetAop(isolate_page); + DySetAop(putback_page); + DySetAop(launder_page); + DySetAop(is_partially_uptodate); + DySetAop(is_dirty_writeback); + DySetAop(error_remove_page); + DySetAop(swap_activate); + DySetAop(swap_deactivate); + + DyDbgSize(cnt, *h_aop); +} + +/* ---------------------------------------------------------------------- */ + +static void dy_bug(struct kref *kref) +{ + BUG(); +} + +static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br) +{ + struct au_dykey *key, *old; + struct hlist_bl_head *hbl; + struct op { + unsigned int sz; + void (*set)(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused); + }; + static const struct op a[] = { + [AuDy_AOP] = { + .sz = sizeof(struct au_dyaop), + .set = dy_aop + } + }; + const struct op *p; + + hbl = dynop + op->dy_type; + key = dy_gfind_get(hbl, op->dy_hop); + if (key) + goto out_add; /* success */ + + p = a + op->dy_type; + key = kzalloc(p->sz, GFP_NOFS); + if (unlikely(!key)) { + key = ERR_PTR(-ENOMEM); + goto out; + } + + key->dk_op.dy_hop = op->dy_hop; + kref_init(&key->dk_kref); + p->set(key, op->dy_hop, au_br_sb(br)); + old = dy_gadd(hbl, key); + if (old) { + au_kfree_rcu(key); + key = old; + } + +out_add: + old = dy_bradd(br, key); + if (old) + /* its ref-count should never be zero here */ + kref_put(&key->dk_kref, dy_bug); +out: + return key; +} + +/* ---------------------------------------------------------------------- */ +/* + * Aufs prohibits O_DIRECT by default even if the branch supports it. + * This behaviour is necessary to return an error from open(O_DIRECT) instead + * of the succeeding I/O. The dio mount option enables O_DIRECT and makes + * open(O_DIRECT) always succeed, but the succeeding I/O may return an error. + * See the aufs manual in detail. + */ +static void dy_adx(struct au_dyaop *dyaop, int do_dx) +{ + if (!do_dx) + dyaop->da_op.direct_IO = NULL; + else + dyaop->da_op.direct_IO = aufs_aop.direct_IO; +} + +static struct au_dyaop *dy_aget(struct au_branch *br, + const struct address_space_operations *h_aop, + int do_dx) +{ + struct au_dyaop *dyaop; + struct au_dynop op; + + op.dy_type = AuDy_AOP; + op.dy_haop = h_aop; + dyaop = (void *)dy_get(&op, br); + if (IS_ERR(dyaop)) + goto out; + dy_adx(dyaop, do_dx); + +out: + return dyaop; +} + +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode) +{ + int err, do_dx; + struct super_block *sb; + struct au_branch *br; + struct au_dyaop *dyaop; + + AuDebugOn(!S_ISREG(h_inode->i_mode)); + IiMustWriteLock(inode); + + sb = inode->i_sb; + br = au_sbr(sb, bindex); + do_dx = !!au_opt_test(au_mntflags(sb), DIO); + dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx); + err = PTR_ERR(dyaop); + if (IS_ERR(dyaop)) + /* unnecessary to call dy_fput() */ + goto out; + + err = 0; + inode->i_mapping->a_ops = &dyaop->da_op; + +out: + return err; +} + +/* + * Is it safe to replace a_ops during the inode/file is in operation? + * Yes, I hope so. + */ +int au_dy_irefresh(struct inode *inode) +{ + int err; + aufs_bindex_t btop; + struct inode *h_inode; + + err = 0; + if (S_ISREG(inode->i_mode)) { + btop = au_ibtop(inode); + h_inode = au_h_iptr(inode, btop); + err = au_dy_iaop(inode, btop, h_inode); + } + return err; +} + +void au_dy_arefresh(int do_dx) +{ + struct hlist_bl_head *hbl; + struct hlist_bl_node *pos; + struct au_dykey *key; + + hbl = dynop + AuDy_AOP; + hlist_bl_lock(hbl); + hlist_bl_for_each_entry(key, pos, hbl, dk_hnode) + dy_adx((void *)key, do_dx); + hlist_bl_unlock(hbl); +} + +/* ---------------------------------------------------------------------- */ + +void __init au_dy_init(void) +{ + int i; + + for (i = 0; i < AuDyLast; i++) + INIT_HLIST_BL_HEAD(dynop + i); +} + +void au_dy_fin(void) +{ + int i; + + for (i = 0; i < AuDyLast; i++) + WARN_ON(!hlist_bl_empty(dynop + i)); +} diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h new file mode 100644 index 000000000000..5d0b36559425 --- /dev/null +++ b/fs/aufs/dynop.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2010-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * dynamically customizable operations (for regular files only) + */ + +#ifndef __AUFS_DYNOP_H__ +#define __AUFS_DYNOP_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/kref.h> + +enum {AuDy_AOP, AuDyLast}; + +struct au_dynop { + int dy_type; + union { + const void *dy_hop; + const struct address_space_operations *dy_haop; + }; +}; + +struct au_dykey { + union { + struct hlist_bl_node dk_hnode; + struct rcu_head dk_rcu; + }; + struct au_dynop dk_op; + + /* + * during I am in the branch local array, kref is gotten. when the + * branch is removed, kref is put. + */ + struct kref dk_kref; +}; + +/* stop unioning since their sizes are very different from each other */ +struct au_dyaop { + struct au_dykey da_key; + struct address_space_operations da_op; /* not const */ +}; +/* make sure that 'struct au_dykey *' can be any type */ +static_assert(!offsetof(struct au_dyaop, da_key)); + +/* ---------------------------------------------------------------------- */ + +/* dynop.c */ +struct au_branch; +void au_dy_put(struct au_dykey *key); +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode); +int au_dy_irefresh(struct inode *inode); +void au_dy_arefresh(int do_dio); + +void __init au_dy_init(void); +void au_dy_fin(void); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DYNOP_H__ */ diff --git a/fs/aufs/export.c b/fs/aufs/export.c new file mode 100644 index 000000000000..1da2ca0a969b --- /dev/null +++ b/fs/aufs/export.c @@ -0,0 +1,838 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * export via nfs + */ + +#include <linux/exportfs.h> +#include <linux/fs_struct.h> +#include <linux/namei.h> +#include <linux/nsproxy.h> +#include <linux/random.h> +#include <linux/writeback.h> +#include "aufs.h" + +union conv { +#ifdef CONFIG_AUFS_INO_T_64 + __u32 a[2]; +#else + __u32 a[1]; +#endif + ino_t ino; +}; + +static ino_t decode_ino(__u32 *a) +{ + union conv u; + + BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); + u.a[0] = a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + u.a[1] = a[1]; +#endif + return u.ino; +} + +static void encode_ino(__u32 *a, ino_t ino) +{ + union conv u; + + u.ino = ino; + a[0] = u.a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + a[1] = u.a[1]; +#endif +} + +/* NFS file handle */ +enum { + Fh_br_id, + Fh_sigen, +#ifdef CONFIG_AUFS_INO_T_64 + /* support 64bit inode number */ + Fh_ino1, + Fh_ino2, + Fh_dir_ino1, + Fh_dir_ino2, +#else + Fh_ino1, + Fh_dir_ino1, +#endif + Fh_igen, + Fh_h_type, + Fh_tail, + + Fh_ino = Fh_ino1, + Fh_dir_ino = Fh_dir_ino1 +}; + +static int au_test_anon(struct dentry *dentry) +{ + /* note: read d_flags without d_lock */ + return !!(dentry->d_flags & DCACHE_DISCONNECTED); +} + +int au_test_nfsd(void) +{ + int ret; + struct task_struct *tsk = current; + char comm[sizeof(tsk->comm)]; + + ret = 0; + if (tsk->flags & PF_KTHREAD) { + get_task_comm(comm, tsk); + ret = !strcmp(comm, "nfsd"); + } + + return ret; +} + +/* ---------------------------------------------------------------------- */ +/* inode generation external table */ + +void au_xigen_inc(struct inode *inode) +{ + loff_t pos; + ssize_t sz; + __u32 igen; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + sb = inode->i_sb; + AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); + + sbinfo = au_sbi(sb); + pos = inode->i_ino; + pos *= sizeof(igen); + igen = inode->i_generation + 1; + sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, + sizeof(igen), &pos); + if (sz == sizeof(igen)) + return; /* success */ + + if (unlikely(sz >= 0)) + AuIOErr("xigen error (%zd)\n", sz); +} + +int au_xigen_new(struct inode *inode) +{ + int err; + loff_t pos; + ssize_t sz; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct file *file; + + err = 0; + /* todo: dirty, at mount time */ + if (inode->i_ino == AUFS_ROOT_INO) + goto out; + sb = inode->i_sb; + SiMustAnyLock(sb); + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + goto out; + + err = -EFBIG; + pos = inode->i_ino; + if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { + AuIOErr1("too large i%lld\n", pos); + goto out; + } + pos *= sizeof(inode->i_generation); + + err = 0; + sbinfo = au_sbi(sb); + file = sbinfo->si_xigen; + BUG_ON(!file); + + if (vfsub_f_size_read(file) + < pos + sizeof(inode->i_generation)) { + inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); + sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + } else + sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + if (sz == sizeof(inode->i_generation)) + goto out; /* success */ + + err = sz; + if (unlikely(sz >= 0)) { + err = -EIO; + AuIOErr("xigen error (%zd)\n", sz); + } + +out: + return err; +} + +int au_xigen_set(struct super_block *sb, struct path *path) +{ + int err; + struct au_sbinfo *sbinfo; + struct file *file; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + file = au_xino_create2(sb, path, sbinfo->si_xigen); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + err = 0; + if (sbinfo->si_xigen) + fput(sbinfo->si_xigen); + sbinfo->si_xigen = file; + +out: + AuTraceErr(err); + return err; +} + +void au_xigen_clr(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + if (sbinfo->si_xigen) { + fput(sbinfo->si_xigen); + sbinfo->si_xigen = NULL; + } +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino) +{ + struct dentry *dentry, *d; + struct inode *inode; + unsigned int sigen; + + dentry = NULL; + inode = ilookup(sb, ino); + if (!inode) + goto out; + + dentry = ERR_PTR(-ESTALE); + sigen = au_sigen(sb); + if (unlikely(au_is_bad_inode(inode) + || IS_DEADDIR(inode) + || sigen != au_iigen(inode, NULL))) + goto out_iput; + + dentry = NULL; + if (!dir_ino || S_ISDIR(inode->i_mode)) + dentry = d_find_alias(inode); + else { + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { + spin_lock(&d->d_lock); + if (!au_test_anon(d) + && d_inode(d->d_parent)->i_ino == dir_ino) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&d->d_lock); + } + spin_unlock(&inode->i_lock); + } + if (unlikely(dentry && au_digen_test(dentry, sigen))) { + /* need to refresh */ + dput(dentry); + dentry = NULL; + } + +out_iput: + iput(inode); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +/* todo: dirty? */ +/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ + +struct au_compare_mnt_args { + /* input */ + struct super_block *sb; + + /* output */ + struct vfsmount *mnt; +}; + +static int au_compare_mnt(struct vfsmount *mnt, void *arg) +{ + struct au_compare_mnt_args *a = arg; + + if (mnt->mnt_sb != a->sb) + return 0; + a->mnt = mntget(mnt); + return 1; +} + +static struct vfsmount *au_mnt_get(struct super_block *sb) +{ + int err; + struct path root; + struct au_compare_mnt_args args = { + .sb = sb + }; + + get_fs_root(current->fs, &root); + rcu_read_lock(); + err = iterate_mounts(au_compare_mnt, &args, root.mnt); + rcu_read_unlock(); + path_put(&root); + AuDebugOn(!err); + AuDebugOn(!args.mnt); + return args.mnt; +} + +struct au_nfsd_si_lock { + unsigned int sigen; + aufs_bindex_t bindex, br_id; + unsigned char force_lock; +}; + +static int si_nfsd_read_lock(struct super_block *sb, + struct au_nfsd_si_lock *nsi_lock) +{ + int err; + aufs_bindex_t bindex; + + si_read_lock(sb, AuLock_FLUSH); + + /* branch id may be wrapped around */ + err = 0; + bindex = au_br_index(sb, nsi_lock->br_id); + if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb)) + goto out; /* success */ + + err = -ESTALE; + bindex = -1; + if (!nsi_lock->force_lock) + si_read_unlock(sb); + +out: + nsi_lock->bindex = bindex; + return err; +} + +struct find_name_by_ino { + struct dir_context ctx; + int called, found; + ino_t ino; + char *name; + int namelen; +}; + +static int +find_name_by_ino(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino, + ctx); + + a->called++; + if (a->ino != ino) + return 0; + + memcpy(a->name, name, namelen); + a->namelen = namelen; + a->found = 1; + return 1; +} + +static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *parent; + struct file *file; + struct inode *dir; + struct find_name_by_ino arg = { + .ctx = { + .actor = find_name_by_ino + } + }; + int err; + + parent = path->dentry; + if (nsi_lock) + si_read_unlock(parent->d_sb); + file = vfsub_dentry_open(path, au_dir_roflags); + dentry = (void *)file; + if (IS_ERR(file)) + goto out; + + dentry = ERR_PTR(-ENOMEM); + arg.name = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!arg.name)) + goto out_file; + arg.ino = ino; + arg.found = 0; + do { + arg.called = 0; + /* smp_mb(); */ + err = vfsub_iterate_dir(file, &arg.ctx); + } while (!err && !arg.found && arg.called); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_name; + /* instead of ENOENT */ + dentry = ERR_PTR(-ESTALE); + if (!arg.found) + goto out_name; + + /* do not call vfsub_lkup_one() */ + dir = d_inode(parent); + dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen); + AuTraceErrPtr(dentry); + if (IS_ERR(dentry)) + goto out_name; + AuDebugOn(au_test_anon(dentry)); + if (unlikely(d_really_is_negative(dentry))) { + dput(dentry); + dentry = ERR_PTR(-ENOENT); + } + +out_name: + free_page((unsigned long)arg.name); +out_file: + fput(file); +out: + if (unlikely(nsi_lock + && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } + AuTraceErrPtr(dentry); + return dentry; +} + +static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry; + struct path path; + + if (dir_ino != AUFS_ROOT_INO) { + path.dentry = decode_by_ino(sb, dir_ino, 0); + dentry = path.dentry; + if (!path.dentry || IS_ERR(path.dentry)) + goto out; + AuDebugOn(au_test_anon(path.dentry)); + } else + path.dentry = dget(sb->s_root); + + path.mnt = au_mnt_get(sb); + dentry = au_lkup_by_ino(&path, ino, nsi_lock); + path_put(&path); + +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static int h_acceptable(void *expv, struct dentry *dentry) +{ + return 1; +} + +static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, + char *buf, int len, struct super_block *sb) +{ + char *p; + int n; + struct path path; + + p = d_path(h_rootpath, buf, len); + if (IS_ERR(p)) + goto out; + n = strlen(p); + + path.mnt = h_rootpath->mnt; + path.dentry = h_parent; + p = d_path(&path, buf, len); + if (IS_ERR(p)) + goto out; + if (n != 1) + p += n; + + path.mnt = au_mnt_get(sb); + path.dentry = sb->s_root; + p = d_path(&path, buf, len - strlen(p)); + mntput(path.mnt); + if (IS_ERR(p)) + goto out; + if (n != 1) + p[strlen(p)] = '/'; + +out: + AuTraceErrPtr(p); + return p; +} + +static +struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh, + int fh_len, struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *h_parent, *root; + struct super_block *h_sb; + char *pathname, *p; + struct vfsmount *h_mnt; + struct au_branch *br; + int err; + struct path path; + + br = au_sbr(sb, nsi_lock->bindex); + h_mnt = au_br_mnt(br); + h_sb = h_mnt->mnt_sb; + /* todo: call lower fh_to_dentry()? fh_to_parent()? */ + lockdep_off(); + h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail), + fh_len - Fh_tail, fh[Fh_h_type], + h_acceptable, /*context*/NULL); + lockdep_on(); + dentry = h_parent; + if (unlikely(!h_parent || IS_ERR(h_parent))) { + AuWarn1("%s decode_fh failed, %ld\n", + au_sbtype(h_sb), PTR_ERR(h_parent)); + goto out; + } + dentry = NULL; + if (unlikely(au_test_anon(h_parent))) { + AuWarn1("%s decode_fh returned a disconnected dentry\n", + au_sbtype(h_sb)); + goto out_h_parent; + } + + dentry = ERR_PTR(-ENOMEM); + pathname = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!pathname)) + goto out_h_parent; + + root = sb->s_root; + path.mnt = h_mnt; + di_read_lock_parent(root, !AuLock_IR); + path.dentry = au_h_dptr(root, nsi_lock->bindex); + di_read_unlock(root, !AuLock_IR); + p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb); + dentry = (void *)p; + if (IS_ERR(p)) + goto out_pathname; + + si_read_unlock(sb); + err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_relock; + + dentry = ERR_PTR(-ENOENT); + AuDebugOn(au_test_anon(path.dentry)); + if (unlikely(d_really_is_negative(path.dentry))) + goto out_path; + + if (ino != d_inode(path.dentry)->i_ino) + dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); + else + dentry = dget(path.dentry); + +out_path: + path_put(&path); +out_relock: + if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } +out_pathname: + free_page((unsigned long)pathname); +out_h_parent: + dput(h_parent); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry * +aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, + int fh_type) +{ + struct dentry *dentry; + __u32 *fh = fid->raw; + struct au_branch *br; + ino_t ino, dir_ino; + struct au_nfsd_si_lock nsi_lock = { + .force_lock = 0 + }; + + dentry = ERR_PTR(-ESTALE); + /* it should never happen, but the file handle is unreliable */ + if (unlikely(fh_len < Fh_tail)) + goto out; + nsi_lock.sigen = fh[Fh_sigen]; + nsi_lock.br_id = fh[Fh_br_id]; + + /* branch id may be wrapped around */ + br = NULL; + if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) + goto out; + nsi_lock.force_lock = 1; + + /* is this inode still cached? */ + ino = decode_ino(fh + Fh_ino); + /* it should never happen */ + if (unlikely(ino == AUFS_ROOT_INO)) + goto out_unlock; + + dir_ino = decode_ino(fh + Fh_dir_ino); + dentry = decode_by_ino(sb, ino, dir_ino); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* is the parent dir cached? */ + br = au_sbr(sb, nsi_lock.bindex); + au_lcnt_inc(&br->br_nfiles); + dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* lookup path */ + dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (unlikely(!dentry)) + /* todo?: make it ESTALE */ + goto out_unlock; + +accept: + if (!au_digen_test(dentry, au_sigen(sb)) + && d_inode(dentry)->i_generation == fh[Fh_igen]) + goto out_unlock; /* success */ + + dput(dentry); + dentry = ERR_PTR(-ESTALE); +out_unlock: + if (br) + au_lcnt_dec(&br->br_nfiles); + si_read_unlock(sb); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +#if 0 /* reserved for future use */ +/* support subtreecheck option */ +static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + struct dentry *parent; + __u32 *fh = fid->raw; + ino_t dir_ino; + + dir_ino = decode_ino(fh + Fh_dir_ino); + parent = decode_by_ino(sb, dir_ino, 0); + if (IS_ERR(parent)) + goto out; + if (!parent) + parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), + dir_ino, fh, fh_len); + +out: + AuTraceErrPtr(parent); + return parent; +} +#endif + +/* ---------------------------------------------------------------------- */ + +static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, + struct inode *dir) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb, *h_sb; + struct dentry *dentry, *parent, *h_parent; + struct inode *h_dir; + struct au_branch *br; + + err = -ENOSPC; + if (unlikely(*max_len <= Fh_tail)) { + AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); + goto out; + } + + err = FILEID_ROOT; + if (inode->i_ino == AUFS_ROOT_INO) { + AuDebugOn(inode->i_ino != AUFS_ROOT_INO); + goto out; + } + + h_parent = NULL; + sb = inode->i_sb; + err = si_read_lock(sb, AuLock_FLUSH); + if (unlikely(err)) + goto out; + +#ifdef CONFIG_AUFS_DEBUG + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + AuWarn1("NFS-exporting requires xino\n"); +#endif + err = -EIO; + parent = NULL; + ii_read_lock_child(inode); + bindex = au_ibtop(inode); + if (!dir) { + dentry = d_find_any_alias(inode); + if (unlikely(!dentry)) + goto out_unlock; + AuDebugOn(au_test_anon(dentry)); + parent = dget_parent(dentry); + dput(dentry); + if (unlikely(!parent)) + goto out_unlock; + if (d_really_is_positive(parent)) + dir = d_inode(parent); + } + + ii_read_lock_parent(dir); + h_dir = au_h_iptr(dir, bindex); + ii_read_unlock(dir); + if (unlikely(!h_dir)) + goto out_parent; + h_parent = d_find_any_alias(h_dir); + if (unlikely(!h_parent)) + goto out_hparent; + + err = -EPERM; + br = au_sbr(sb, bindex); + h_sb = au_br_sb(br); + if (unlikely(!h_sb->s_export_op)) { + AuErr1("%s branch is not exportable\n", au_sbtype(h_sb)); + goto out_hparent; + } + + fh[Fh_br_id] = br->br_id; + fh[Fh_sigen] = au_sigen(sb); + encode_ino(fh + Fh_ino, inode->i_ino); + encode_ino(fh + Fh_dir_ino, dir->i_ino); + fh[Fh_igen] = inode->i_generation; + + *max_len -= Fh_tail; + fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail), + max_len, + /*connectable or subtreecheck*/0); + err = fh[Fh_h_type]; + *max_len += Fh_tail; + /* todo: macros? */ + if (err != FILEID_INVALID) + err = 99; + else + AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb)); + +out_hparent: + dput(h_parent); +out_parent: + dput(parent); +out_unlock: + ii_read_unlock(inode); + si_read_unlock(sb); +out: + if (unlikely(err < 0)) + err = FILEID_INVALID; + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_commit_metadata(struct inode *inode) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct inode *h_inode; + int (*f)(struct inode *inode); + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + ii_write_lock_child(inode); + bindex = au_ibtop(inode); + AuDebugOn(bindex < 0); + h_inode = au_h_iptr(inode, bindex); + + f = h_inode->i_sb->s_export_op->commit_metadata; + if (f) + err = f(h_inode); + else { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0 /* metadata only */ + }; + + err = sync_inode(h_inode, &wbc); + } + + au_cpup_attr_timesizes(inode); + ii_write_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct export_operations aufs_export_op = { + .fh_to_dentry = aufs_fh_to_dentry, + /* .fh_to_parent = aufs_fh_to_parent, */ + .encode_fh = aufs_encode_fh, + .commit_metadata = aufs_commit_metadata +}; + +void au_export_init(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + __u32 u; + + BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS) + && IS_MODULE(CONFIG_EXPORTFS), + AUFS_NAME ": unsupported configuration " + "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y"); + + sb->s_export_op = &aufs_export_op; + sbinfo = au_sbi(sb); + sbinfo->si_xigen = NULL; + get_random_bytes(&u, sizeof(u)); + BUILD_BUG_ON(sizeof(u) != sizeof(int)); + atomic_set(&sbinfo->si_xigen_next, u); +} diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c new file mode 100644 index 000000000000..5254b5cd3942 --- /dev/null +++ b/fs/aufs/f_op.c @@ -0,0 +1,819 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file and vm operations + */ + +#include <linux/aio.h> +#include <linux/fs_stack.h> +#include <linux/mman.h> +#include <linux/security.h> +#include "aufs.h" + +int au_do_open_nondir(struct file *file, int flags, struct file *h_file) +{ + int err; + aufs_bindex_t bindex; + struct dentry *dentry, *h_dentry; + struct au_finfo *finfo; + struct inode *h_inode; + + FiMustWriteLock(file); + + err = 0; + dentry = file->f_path.dentry; + AuDebugOn(IS_ERR_OR_NULL(dentry)); + finfo = au_fi(file); + memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop)); + atomic_set(&finfo->fi_mmapped, 0); + bindex = au_dbtop(dentry); + if (!h_file) { + h_dentry = au_h_dptr(dentry, bindex); + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; + h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + goto out; + } + } else { + h_dentry = h_file->f_path.dentry; + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; + /* br ref is already inc-ed */ + } + + if ((flags & __O_TMPFILE) + && !(flags & O_EXCL)) { + h_inode = file_inode(h_file); + spin_lock(&h_inode->i_lock); + h_inode->i_state |= I_LINKABLE; + spin_unlock(&h_inode->i_lock); + } + au_set_fbtop(file, bindex); + au_set_h_fptr(file, bindex, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + +out: + return err; +} + +static int aufs_open_nondir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + struct au_do_open_args args = { + .open = au_do_open_nondir + }; + + AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n", + file, vfsub_file_flags(file), file->f_mode); + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_do_open(file, &args); + si_read_unlock(sb); + return err; +} + +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) +{ + struct au_finfo *finfo; + aufs_bindex_t bindex; + + finfo = au_fi(file); + au_hbl_del(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + bindex = finfo->fi_btop; + if (bindex >= 0) + au_set_h_fptr(file, bindex, NULL); + + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_nondir(struct file *file, fl_owner_t id) +{ + int err; + struct file *h_file; + + err = 0; + h_file = au_hf_top(file); + if (h_file) + err = vfsub_flush(h_file, id); + return err; +} + +static int aufs_flush_nondir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_nondir); +} + +/* ---------------------------------------------------------------------- */ +/* + * read and write functions acquire [fdi]_rwsem once, but release before + * mmap_sem. This is because to stop a race condition between mmap(2). + * Releasing these aufs-rwsem should be safe, no branch-management (by keeping + * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in + * read functions after [fdi]_rwsem are released, but it should be harmless. + */ + +/* Callers should call au_read_post() or fput() in the end */ +struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc) +{ + struct file *h_file; + int err; + + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc); + if (!err) { + di_read_unlock(file->f_path.dentry, AuLock_IR); + h_file = au_hf_top(file); + get_file(h_file); + if (!keep_fi) + fi_read_unlock(file); + } else + h_file = ERR_PTR(err); + + return h_file; +} + +static void au_read_post(struct inode *inode, struct file *h_file) +{ + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(inode, file_inode(h_file)); + fput(h_file); +} + +struct au_write_pre { + /* input */ + unsigned int lsc; + + /* output */ + blkcnt_t blks; + aufs_bindex_t btop; +}; + +/* + * return with iinfo is write-locked + * callers should call au_write_post() or iinfo_write_unlock() + fput() in the + * end + */ +static struct file *au_write_pre(struct file *file, int do_ready, + struct au_write_pre *wpre) +{ + struct file *h_file; + struct dentry *dentry; + int err; + unsigned int lsc; + struct au_pin pin; + + lsc = 0; + if (wpre) + lsc = wpre->lsc; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc); + h_file = ERR_PTR(err); + if (unlikely(err)) + goto out; + + dentry = file->f_path.dentry; + if (do_ready) { + err = au_ready_to_write(file, -1, &pin); + if (unlikely(err)) { + h_file = ERR_PTR(err); + di_write_unlock(dentry); + goto out_fi; + } + } + + di_downgrade_lock(dentry, /*flags*/0); + if (wpre) + wpre->btop = au_fbtop(file); + h_file = au_hf_top(file); + get_file(h_file); + if (wpre) + wpre->blks = file_inode(h_file)->i_blocks; + if (do_ready) + au_unpin(&pin); + di_read_unlock(dentry, /*flags*/0); + +out_fi: + fi_write_unlock(file); +out: + return h_file; +} + +static void au_write_post(struct inode *inode, struct file *h_file, + struct au_write_pre *wpre, ssize_t written) +{ + struct inode *h_inode; + + au_cpup_attr_timesizes(inode); + AuDebugOn(au_ibtop(inode) != wpre->btop); + h_inode = file_inode(h_file); + inode->i_mode = h_inode->i_mode; + ii_write_unlock(inode); + /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */ + if (written > 0) + au_fhsm_wrote(inode->i_sb, wpre->btop, + /*force*/h_inode->i_blocks > wpre->blks); + fput(h_file); +} + +static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + ssize_t err; + struct inode *inode; + struct file *h_file; + struct super_block *sb; + + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + /* filedata may be obsoleted by concurrent copyup, but no problem */ + err = vfsub_read_u(h_file, buf, count, ppos); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +/* + * todo: very ugly + * it locks both of i_mutex and si_rwsem for read in safe. + * if the plink maintenance mode continues forever (that is the problem), + * may loop forever. + */ +static void au_mtx_and_read_lock(struct inode *inode) +{ + int err; + struct super_block *sb = inode->i_sb; + + while (1) { + inode_lock(inode); + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (!err) + break; + inode_unlock(inode); + si_read_lock(sb, AuLock_NOPLMW); + si_read_unlock(sb); + } +} + +static ssize_t aufs_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + char __user *buf = (char __user *)ubuf; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_write_u(h_file, buf, count, ppos); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio, + struct iov_iter *iov_iter) +{ + ssize_t err; + struct file *file; + ssize_t (*iter)(struct kiocb *, struct iov_iter *); + + err = security_file_permission(h_file, rw); + if (unlikely(err)) + goto out; + + err = -ENOSYS; + iter = NULL; + if (rw == MAY_READ) + iter = h_file->f_op->read_iter; + else if (rw == MAY_WRITE) + iter = h_file->f_op->write_iter; + + file = kio->ki_filp; + kio->ki_filp = h_file; + if (iter) { + lockdep_off(); + err = iter(kio, iov_iter); + lockdep_on(); + } else + /* currently there is no such fs */ + WARN_ON_ONCE(1); + kio->ki_filp = file; + +out: + return err; +} + +static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ + ssize_t err; + struct file *file, *h_file; + struct inode *inode; + struct super_block *sb; + + file = kio->ki_filp; + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + if (au_test_loopback_kthread()) { + au_warn_loopback(h_file->f_path.dentry->d_sb); + if (file->f_mapping != h_file->f_mapping) { + file->f_mapping = h_file->f_mapping; + smp_mb(); /* unnecessary? */ + } + } + fi_read_unlock(file); + + err = au_do_iter(h_file, MAY_READ, kio, iov_iter); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *file, *h_file; + + file = kio->ki_filp; + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t err; + struct file *h_file; + struct inode *inode; + struct super_block *sb; + + inode = file_inode(file); + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_splice_to(h_file, ppos, pipe, len, flags); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + au_read_post(inode, h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t +aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, + size_t len, unsigned int flags) +{ + ssize_t err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = vfsub_splice_from(pipe, h_file, ppos, len, flags); + au_write_post(inode, h_file, &wpre, err); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static long aufs_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + long err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + lockdep_off(); + err = vfs_fallocate(h_file, mode, offset, len); + lockdep_on(); + au_write_post(inode, h_file, &wpre, /*written*/1); + +out: + si_read_unlock(inode->i_sb); + inode_unlock(inode); + return err; +} + +static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos, + struct file *dst, loff_t dst_pos, + size_t len, unsigned int flags) +{ + ssize_t err; + struct au_write_pre wpre; + enum { SRC, DST }; + struct { + struct inode *inode; + struct file *h_file; + struct super_block *h_sb; + } a[2]; +#define a_src a[SRC] +#define a_dst a[DST] + + err = -EINVAL; + a_src.inode = file_inode(src); + if (unlikely(!S_ISREG(a_src.inode->i_mode))) + goto out; + a_dst.inode = file_inode(dst); + if (unlikely(!S_ISREG(a_dst.inode->i_mode))) + goto out; + + au_mtx_and_read_lock(a_dst.inode); + /* + * in order to match the order in di_write_lock2_{child,parent}(), + * use f_path.dentry for this comparison. + */ + if (src->f_path.dentry < dst->f_path.dentry) { + a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1); + err = PTR_ERR(a_src.h_file); + if (IS_ERR(a_src.h_file)) + goto out_si; + + wpre.lsc = AuLsc_FI_2; + a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); + err = PTR_ERR(a_dst.h_file); + if (IS_ERR(a_dst.h_file)) { + au_read_post(a_src.inode, a_src.h_file); + goto out_si; + } + } else { + wpre.lsc = AuLsc_FI_1; + a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre); + err = PTR_ERR(a_dst.h_file); + if (IS_ERR(a_dst.h_file)) + goto out_si; + + a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2); + err = PTR_ERR(a_src.h_file); + if (IS_ERR(a_src.h_file)) { + au_write_post(a_dst.inode, a_dst.h_file, &wpre, + /*written*/0); + goto out_si; + } + } + + err = -EXDEV; + a_src.h_sb = file_inode(a_src.h_file)->i_sb; + a_dst.h_sb = file_inode(a_dst.h_file)->i_sb; + if (unlikely(a_src.h_sb != a_dst.h_sb)) { + AuDbgFile(src); + AuDbgFile(dst); + goto out_file; + } + + err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file, + dst_pos, len, flags); + +out_file: + au_write_post(a_dst.inode, a_dst.h_file, &wpre, err); + fi_read_unlock(src); + au_read_post(a_src.inode, a_src.h_file); +out_si: + si_read_unlock(a_dst.inode->i_sb); + inode_unlock(a_dst.inode); +out: + return err; +#undef a_src +#undef a_dst +} + +/* ---------------------------------------------------------------------- */ + +/* + * The locking order around current->mmap_sem. + * - in most and regular cases + * file I/O syscall -- aufs_read() or something + * -- si_rwsem for read -- mmap_sem + * (Note that [fdi]i_rwsem are released before mmap_sem). + * - in mmap case + * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem + * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for + * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held + * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though. + * It means that when aufs acquires si_rwsem for write, the process should never + * acquire mmap_sem. + * + * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a + * problem either since any directory is not able to be mmap-ed. + * The similar scenario is applied to aufs_readlink() too. + */ + +#if 0 /* stop calling security_file_mmap() */ +/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */ +#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b) + +static unsigned long au_arch_prot_conv(unsigned long flags) +{ + /* currently ppc64 only */ +#ifdef CONFIG_PPC64 + /* cf. linux/arch/powerpc/include/asm/mman.h */ + AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO); + return AuConv_VM_PROT(flags, SAO); +#else + AuDebugOn(arch_calc_vm_prot_bits(-1)); + return 0; +#endif +} + +static unsigned long au_prot_conv(unsigned long flags) +{ + return AuConv_VM_PROT(flags, READ) + | AuConv_VM_PROT(flags, WRITE) + | AuConv_VM_PROT(flags, EXEC) + | au_arch_prot_conv(flags); +} + +/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ +#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) + +static unsigned long au_flag_conv(unsigned long flags) +{ + return AuConv_VM_MAP(flags, GROWSDOWN) + | AuConv_VM_MAP(flags, DENYWRITE) + | AuConv_VM_MAP(flags, LOCKED); +} +#endif + +static int aufs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err; + const unsigned char wlock + = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED); + struct super_block *sb; + struct file *h_file; + struct inode *inode; + + AuDbgVmRegion(file, vma); + + inode = file_inode(file); + sb = inode->i_sb; + lockdep_off(); + si_read_lock(sb, AuLock_NOPLMW); + + h_file = au_write_pre(file, wlock, /*wpre*/NULL); + lockdep_on(); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = 0; + au_set_mmapped(file); + au_vm_file_reset(vma, h_file); + /* + * we cannot call security_mmap_file() here since it may acquire + * mmap_sem or i_mutex. + * + * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags), + * au_flag_conv(vma->vm_flags)); + */ + if (!err) + err = call_mmap(h_file, vma); + if (!err) { + au_vm_prfile_set(vma, file); + fsstack_copy_attr_atime(inode, file_inode(h_file)); + goto out_fput; /* success */ + } + au_unset_mmapped(file); + au_vm_file_reset(vma, file); + +out_fput: + lockdep_off(); + ii_write_unlock(inode); + lockdep_on(); + fput(h_file); +out: + lockdep_off(); + si_read_unlock(sb); + lockdep_on(); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct au_write_pre wpre; + struct inode *inode; + struct file *h_file; + + err = 0; /* -EBADF; */ /* posix? */ + if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out; + + inode = file_inode(file); + au_mtx_and_read_lock(inode); + + wpre.lsc = 0; + h_file = au_write_pre(file, /*do_ready*/1, &wpre); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out_unlock; + + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + au_write_post(inode, h_file, &wpre, /*written*/0); + +out_unlock: + si_read_unlock(inode->i_sb); + inode_unlock(inode); +out: + return err; +} + +static int aufs_fasync(int fd, struct file *file, int flag) +{ + int err; + struct file *h_file; + struct super_block *sb; + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + if (h_file->f_op->fasync) + err = h_file->f_op->fasync(fd, h_file, flag); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + return err; +} + +static int aufs_setfl(struct file *file, unsigned long arg) +{ + int err; + struct file *h_file; + struct super_block *sb; + + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + + h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + /* stop calling h_file->fasync */ + arg |= vfsub_file_flags(file) & FASYNC; + err = setfl(/*unused fd*/-1, h_file, arg); + fput(h_file); /* instead of au_read_post() */ + +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* no one supports this operation, currently */ +#if 0 +static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, + size_t len, loff_t *pos, int more) +{ +} +#endif + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_file_fop = { + .owner = THIS_MODULE, + + .llseek = default_llseek, + + .read = aufs_read, + .write = aufs_write, + .read_iter = aufs_read_iter, + .write_iter = aufs_write_iter, + +#ifdef CONFIG_AUFS_POLL + .poll = aufs_poll, +#endif + .unlocked_ioctl = aufs_ioctl_nondir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_compat_ioctl_nondir, +#endif + .mmap = aufs_mmap, + .open = aufs_open_nondir, + .flush = aufs_flush_nondir, + .release = aufs_release_nondir, + .fsync = aufs_fsync_nondir, + .fasync = aufs_fasync, + /* .sendpage = aufs_sendpage, */ + .setfl = aufs_setfl, + .splice_write = aufs_splice_write, + .splice_read = aufs_splice_read, +#if 0 + .aio_splice_write = aufs_aio_splice_write, + .aio_splice_read = aufs_aio_splice_read, +#endif + .fallocate = aufs_fallocate, + .copy_file_range = aufs_copy_file_range +}; diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c new file mode 100644 index 000000000000..f86a4c24fb26 --- /dev/null +++ b/fs/aufs/fhsm.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2011-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * File-based Hierarchy Storage Management + */ + +#include <linux/anon_inodes.h> +#include <linux/poll.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include "aufs.h" + +static aufs_bindex_t au_fhsm_bottom(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + AuDebugOn(!fhsm); + return fhsm->fhsm_bottom; +} + +void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + AuDebugOn(!fhsm); + fhsm->fhsm_bottom = bindex; +} + +/* ---------------------------------------------------------------------- */ + +static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br) +{ + struct au_br_fhsm *bf; + + bf = br->br_fhsm; + MtxMustLock(&bf->bf_lock); + + return !bf->bf_readable + || time_after(jiffies, + bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire); +} + +/* ---------------------------------------------------------------------- */ + +static void au_fhsm_notify(struct super_block *sb, int val) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + if (au_fhsm_pid(fhsm) + && atomic_read(&fhsm->fhsm_readable) != -1) { + atomic_set(&fhsm->fhsm_readable, val); + if (val) + wake_up(&fhsm->fhsm_wqh); + } +} + +static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex, + struct aufs_stfs *rstfs, int do_lock, int do_notify) +{ + int err; + struct au_branch *br; + struct au_br_fhsm *bf; + + br = au_sbr(sb, bindex); + AuDebugOn(au_br_rdonly(br)); + bf = br->br_fhsm; + AuDebugOn(!bf); + + if (do_lock) + mutex_lock(&bf->bf_lock); + else + MtxMustLock(&bf->bf_lock); + + /* sb->s_root for NFS is unreliable */ + err = au_br_stfs(br, &bf->bf_stfs); + if (unlikely(err)) { + AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err); + goto out; + } + + bf->bf_jiffy = jiffies; + bf->bf_readable = 1; + if (do_notify) + au_fhsm_notify(sb, /*val*/1); + if (rstfs) + *rstfs = bf->bf_stfs; + +out: + if (do_lock) + mutex_unlock(&bf->bf_lock); + au_fhsm_notify(sb, /*val*/1); + + return err; +} + +void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force) +{ + int err; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + struct au_branch *br; + struct au_br_fhsm *bf; + + AuDbg("b%d, force %d\n", bindex, force); + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + if (!au_ftest_si(sbinfo, FHSM) + || fhsm->fhsm_bottom == bindex) + return; + + br = au_sbr(sb, bindex); + bf = br->br_fhsm; + AuDebugOn(!bf); + mutex_lock(&bf->bf_lock); + if (force + || au_fhsm_pid(fhsm) + || au_fhsm_test_jiffy(sbinfo, br)) + err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0, + /*do_notify*/1); + mutex_unlock(&bf->bf_lock); +} + +void au_fhsm_wrote_all(struct super_block *sb, int force) +{ + aufs_bindex_t bindex, bbot; + struct au_branch *br; + + /* exclude the bottom */ + bbot = au_fhsm_bottom(sb); + for (bindex = 0; bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm)) + au_fhsm_wrote(sb, bindex, force); + } +} + +/* ---------------------------------------------------------------------- */ + +static __poll_t au_fhsm_poll(struct file *file, struct poll_table_struct *wait) +{ + __poll_t mask; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + mask = 0; + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; + poll_wait(file, &fhsm->fhsm_wqh, wait); + if (atomic_read(&fhsm->fhsm_readable)) + mask = EPOLLIN /* | EPOLLRDNORM */; + + if (!mask) + AuDbg("mask 0x%x\n", mask); + return mask; +} + +static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr, + struct aufs_stfs *stfs, __s16 brid) +{ + int err; + + err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs)); + if (!err) + err = __put_user(brid, &stbr->brid); + if (unlikely(err)) + err = -EFAULT; + + return err; +} + +static ssize_t au_fhsm_do_read(struct super_block *sb, + struct aufs_stbr __user *stbr, size_t count) +{ + ssize_t err; + int nstbr; + aufs_bindex_t bindex, bbot; + struct au_branch *br; + struct au_br_fhsm *bf; + + /* except the bottom branch */ + err = 0; + nstbr = 0; + bbot = au_fhsm_bottom(sb); + for (bindex = 0; !err && bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (!au_br_fhsm(br->br_perm)) + continue; + + bf = br->br_fhsm; + mutex_lock(&bf->bf_lock); + if (bf->bf_readable) { + err = -EFAULT; + if (count >= sizeof(*stbr)) + err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs, + br->br_id); + if (!err) { + bf->bf_readable = 0; + count -= sizeof(*stbr); + nstbr++; + } + } + mutex_unlock(&bf->bf_lock); + } + if (!err) + err = sizeof(*stbr) * nstbr; + + return err; +} + +static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count, + loff_t *pos) +{ + ssize_t err; + int readable; + aufs_bindex_t nfhsm, bindex, bbot; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + struct au_branch *br; + struct super_block *sb; + + err = 0; + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; +need_data: + spin_lock_irq(&fhsm->fhsm_wqh.lock); + if (!atomic_read(&fhsm->fhsm_readable)) { + if (vfsub_file_flags(file) & O_NONBLOCK) + err = -EAGAIN; + else + err = wait_event_interruptible_locked_irq + (fhsm->fhsm_wqh, + atomic_read(&fhsm->fhsm_readable)); + } + spin_unlock_irq(&fhsm->fhsm_wqh.lock); + if (unlikely(err)) + goto out; + + /* sb may already be dead */ + au_rw_read_lock(&sbinfo->si_rwsem); + readable = atomic_read(&fhsm->fhsm_readable); + if (readable > 0) { + sb = sbinfo->si_sb; + AuDebugOn(!sb); + /* exclude the bottom branch */ + nfhsm = 0; + bbot = au_fhsm_bottom(sb); + for (bindex = 0; bindex < bbot; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_fhsm(br->br_perm)) + nfhsm++; + } + err = -EMSGSIZE; + if (nfhsm * sizeof(struct aufs_stbr) <= count) { + atomic_set(&fhsm->fhsm_readable, 0); + err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf, + count); + } + } + au_rw_read_unlock(&sbinfo->si_rwsem); + if (!readable) + goto need_data; + +out: + return err; +} + +static int au_fhsm_release(struct inode *inode, struct file *file) +{ + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + /* sb may already be dead */ + sbinfo = file->private_data; + fhsm = &sbinfo->si_fhsm; + spin_lock(&fhsm->fhsm_spin); + fhsm->fhsm_pid = 0; + spin_unlock(&fhsm->fhsm_spin); + kobject_put(&sbinfo->si_kobj); + + return 0; +} + +static const struct file_operations au_fhsm_fops = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .read = au_fhsm_read, + .poll = au_fhsm_poll, + .release = au_fhsm_release +}; + +int au_fhsm_fd(struct super_block *sb, int oflags) +{ + int err, fd; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = -EINVAL; + if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK))) + goto out; + + err = 0; + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + spin_lock(&fhsm->fhsm_spin); + if (!fhsm->fhsm_pid) + fhsm->fhsm_pid = current->pid; + else + err = -EBUSY; + spin_unlock(&fhsm->fhsm_spin); + if (unlikely(err)) + goto out; + + oflags |= O_RDONLY; + /* oflags |= FMODE_NONOTIFY; */ + fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags); + err = fd; + if (unlikely(fd < 0)) + goto out_pid; + + /* succeed regardless 'fhsm' status */ + kobject_get(&sbinfo->si_kobj); + si_noflush_read_lock(sb); + if (au_ftest_si(sbinfo, FHSM)) + au_fhsm_wrote_all(sb, /*force*/0); + si_read_unlock(sb); + goto out; /* success */ + +out_pid: + spin_lock(&fhsm->fhsm_spin); + fhsm->fhsm_pid = 0; + spin_unlock(&fhsm->fhsm_spin); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_fhsm_br_alloc(struct au_branch *br) +{ + int err; + + err = 0; + br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS); + if (br->br_fhsm) + au_br_fhsm_init(br->br_fhsm); + else + err = -ENOMEM; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_fhsm_fin(struct super_block *sb) +{ + au_fhsm_notify(sb, /*val*/-1); +} + +void au_fhsm_init(struct au_sbinfo *sbinfo) +{ + struct au_fhsm *fhsm; + + fhsm = &sbinfo->si_fhsm; + spin_lock_init(&fhsm->fhsm_spin); + init_waitqueue_head(&fhsm->fhsm_wqh); + atomic_set(&fhsm->fhsm_readable, 0); + fhsm->fhsm_expire + = msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC); + fhsm->fhsm_bottom = -1; +} + +void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec) +{ + sbinfo->si_fhsm.fhsm_expire + = msecs_to_jiffies(sec * MSEC_PER_SEC); +} + +void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo) +{ + unsigned int u; + + if (!au_ftest_si(sbinfo, FHSM)) + return; + + u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC; + if (u != AUFS_FHSM_CACHE_DEF_SEC) + seq_printf(seq, ",fhsm_sec=%u", u); +} diff --git a/fs/aufs/file.c b/fs/aufs/file.c new file mode 100644 index 000000000000..dbb33855d226 --- /dev/null +++ b/fs/aufs/file.c @@ -0,0 +1,863 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * handling file/dir, and address_space operation + */ + +#ifdef CONFIG_AUFS_DEBUG +#include <linux/migrate.h> +#endif +#include <linux/pagemap.h> +#include "aufs.h" + +/* drop flags for writing */ +unsigned int au_file_roflags(unsigned int flags) +{ + flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC); + flags |= O_RDONLY | O_NOATIME; + return flags; +} + +/* common functions to regular file and dir */ +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file, int force_wr) +{ + struct file *h_file; + struct dentry *h_dentry; + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + struct path h_path; + int err; + + /* a race condition can happen between open and unlink/rmdir */ + h_file = ERR_PTR(-ENOENT); + h_dentry = au_h_dptr(dentry, bindex); + if (au_test_nfsd() && (!h_dentry || d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); + spin_lock(&h_dentry->d_lock); + err = (!d_unhashed(dentry) && d_unlinked(h_dentry)) + /* || !d_inode(dentry)->i_nlink */ + ; + spin_unlock(&h_dentry->d_lock); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + br = au_sbr(sb, bindex); + err = au_br_test_oflag(flags, br); + h_file = ERR_PTR(err); + if (unlikely(err)) + goto out; + + /* drop flags for writing */ + if (au_test_ro(sb, bindex, d_inode(dentry))) { + if (force_wr && !(flags & O_WRONLY)) + force_wr = 0; + flags = au_file_roflags(flags); + if (force_wr) { + h_file = ERR_PTR(-EROFS); + flags = au_file_roflags(flags); + if (unlikely(vfsub_native_ro(h_inode) + || IS_APPEND(h_inode))) + goto out; + flags &= ~O_ACCMODE; + flags |= O_WRONLY; + } + } + flags &= ~O_CREAT; + au_lcnt_inc(&br->br_nfiles); + h_path.dentry = h_dentry; + h_path.mnt = au_br_mnt(br); + h_file = vfsub_dentry_open(&h_path, flags); + if (IS_ERR(h_file)) + goto out_br; + + if (flags & __FMODE_EXEC) { + err = deny_write_access(h_file); + if (unlikely(err)) { + fput(h_file); + h_file = ERR_PTR(err); + goto out_br; + } + } + fsnotify_open(h_file); + goto out; /* success */ + +out_br: + au_lcnt_dec(&br->br_nfiles); +out: + return h_file; +} + +static int au_cmoo(struct dentry *dentry) +{ + int err, cmoo, matched; + unsigned int udba; + struct path h_path; + struct au_pin pin; + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = -1, + .bsrc = -1, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + struct inode *delegated; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct au_fhsm *fhsm; + pid_t pid; + struct au_branch *br; + struct dentry *parent; + struct au_hinode *hdir; + + DiMustWriteLock(dentry); + IiMustWriteLock(d_inode(dentry)); + + err = 0; + if (IS_ROOT(dentry)) + goto out; + cpg.bsrc = au_dbtop(dentry); + if (!cpg.bsrc) + goto out; + + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + pid = au_fhsm_pid(fhsm); + rcu_read_lock(); + matched = (pid + && (current->pid == pid + || rcu_dereference(current->real_parent)->pid == pid)); + rcu_read_unlock(); + if (matched) + goto out; + + br = au_sbr(sb, cpg.bsrc); + cmoo = au_br_cmoo(br->br_perm); + if (!cmoo) + goto out; + if (!d_is_reg(dentry)) + cmoo &= AuBrAttr_COO_ALL; + if (!cmoo) + goto out; + + parent = dget_parent(dentry); + di_write_lock_parent(parent); + err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1); + cpg.bdst = err; + if (unlikely(err < 0)) { + err = 0; /* there is no upper writable branch */ + goto out_dgrade; + } + AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst); + + /* do not respect the coo attrib for the target branch */ + err = au_cpup_dirs(dentry, cpg.bdst); + if (unlikely(err)) + goto out_dgrade; + + di_downgrade_lock(parent, AuLock_IR); + udba = au_opt_udba(sb); + err = au_pin(&pin, dentry, cpg.bdst, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_parent; + + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + if (unlikely(err)) + goto out_parent; + if (!(cmoo & AuBrWAttr_MOO)) + goto out_parent; /* success */ + + err = au_pin(&pin, dentry, cpg.bsrc, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_parent; + + h_path.mnt = au_br_mnt(br); + h_path.dentry = au_h_dptr(dentry, cpg.bsrc); + hdir = au_hi(d_inode(parent), cpg.bsrc); + delegated = NULL; + err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1); + au_unpin(&pin); + /* todo: keep h_dentry or not? */ + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal unlink\n"); + iput(delegated); + } + if (unlikely(err)) { + pr_err("unlink %pd after coo failed (%d), ignored\n", + dentry, err); + err = 0; + } + goto out_parent; /* success */ + +out_dgrade: + di_downgrade_lock(parent, AuLock_IR); +out_parent: + di_read_unlock(parent, AuLock_IR); + dput(parent); +out: + AuTraceErr(err); + return err; +} + +int au_do_open(struct file *file, struct au_do_open_args *args) +{ + int err, aopen = args->aopen; + struct dentry *dentry; + struct au_finfo *finfo; + + if (!aopen) + err = au_finfo_init(file, args->fidir); + else { + lockdep_off(); + err = au_finfo_init(file, args->fidir); + lockdep_on(); + } + if (unlikely(err)) + goto out; + + dentry = file->f_path.dentry; + AuDebugOn(IS_ERR_OR_NULL(dentry)); + di_write_lock_child(dentry); + err = au_cmoo(dentry); + di_downgrade_lock(dentry, AuLock_IR); + if (!err) { + if (!aopen) + err = args->open(file, vfsub_file_flags(file), NULL); + else { + lockdep_off(); + err = args->open(file, vfsub_file_flags(file), + args->h_file); + lockdep_on(); + } + } + di_read_unlock(dentry, AuLock_IR); + + finfo = au_fi(file); + if (!err) { + finfo->fi_file = file; + au_hbl_add(&finfo->fi_hlist, + &au_sbi(file->f_path.dentry->d_sb)->si_files); + } + if (!aopen) + fi_write_unlock(file); + else { + lockdep_off(); + fi_write_unlock(file); + lockdep_on(); + } + if (unlikely(err)) { + finfo->fi_hdir = NULL; + au_finfo_fin(file); + } + +out: + AuTraceErr(err); + return err; +} + +int au_reopen_nondir(struct file *file) +{ + int err; + aufs_bindex_t btop; + struct dentry *dentry; + struct au_branch *br; + struct file *h_file, *h_file_tmp; + + dentry = file->f_path.dentry; + btop = au_dbtop(dentry); + br = au_sbr(dentry->d_sb, btop); + h_file_tmp = NULL; + if (au_fbtop(file) == btop) { + h_file = au_hf_top(file); + if (file->f_mode == h_file->f_mode) + return 0; /* success */ + h_file_tmp = h_file; + get_file(h_file_tmp); + au_lcnt_inc(&br->br_nfiles); + au_set_h_fptr(file, btop, NULL); + } + AuDebugOn(au_fi(file)->fi_hdir); + /* + * it can happen + * file exists on both of rw and ro + * open --> dbtop and fbtop are both 0 + * prepend a branch as rw, "rw" become ro + * remove rw/file + * delete the top branch, "rw" becomes rw again + * --> dbtop is 1, fbtop is still 0 + * write --> fbtop is 0 but dbtop is 1 + */ + /* AuDebugOn(au_fbtop(file) < btop); */ + + h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC, + file, /*force_wr*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) { + if (h_file_tmp) { + /* revert */ + au_set_h_fptr(file, btop, h_file_tmp); + h_file_tmp = NULL; + } + goto out; /* todo: close all? */ + } + + err = 0; + au_set_fbtop(file, btop); + au_set_h_fptr(file, btop, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + +out: + if (h_file_tmp) { + fput(h_file_tmp); + au_lcnt_dec(&br->br_nfiles); + } + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_reopen_wh(struct file *file, aufs_bindex_t btgt, + struct dentry *hi_wh) +{ + int err; + aufs_bindex_t btop; + struct au_dinfo *dinfo; + struct dentry *h_dentry; + struct au_hdentry *hdp; + + dinfo = au_di(file->f_path.dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + btop = dinfo->di_btop; + dinfo->di_btop = btgt; + hdp = au_hdentry(dinfo, btgt); + h_dentry = hdp->hd_dentry; + hdp->hd_dentry = hi_wh; + err = au_reopen_nondir(file); + hdp->hd_dentry = h_dentry; + dinfo->di_btop = btop; + + return err; +} + +static int au_ready_to_write_wh(struct file *file, loff_t len, + aufs_bindex_t bcpup, struct au_pin *pin) +{ + int err; + struct inode *inode, *h_inode; + struct dentry *h_dentry, *hi_wh; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = bcpup, + .bsrc = -1, + .len = len, + .pin = pin + }; + + au_update_dbtop(cpg.dentry); + inode = d_inode(cpg.dentry); + h_inode = NULL; + if (au_dbtop(cpg.dentry) <= bcpup + && au_dbbot(cpg.dentry) >= bcpup) { + h_dentry = au_h_dptr(cpg.dentry, bcpup); + if (h_dentry && d_is_positive(h_dentry)) + h_inode = d_inode(h_dentry); + } + hi_wh = au_hi_wh(inode, bcpup); + if (!hi_wh && !h_inode) + err = au_sio_cpup_wh(&cpg, file); + else + /* already copied-up after unlink */ + err = au_reopen_wh(file, bcpup, hi_wh); + + if (!err + && (inode->i_nlink > 1 + || (inode->i_state & I_LINKABLE)) + && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK)) + au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup)); + + return err; +} + +/* + * prepare the @file for writing. + */ +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin) +{ + int err; + aufs_bindex_t dbtop; + struct dentry *parent; + struct inode *inode; + struct super_block *sb; + struct file *h_file; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = -1, + .bsrc = -1, + .len = len, + .pin = pin, + .flags = AuCpup_DTIME + }; + + sb = cpg.dentry->d_sb; + inode = d_inode(cpg.dentry); + cpg.bsrc = au_fbtop(file); + err = au_test_ro(sb, cpg.bsrc, inode); + if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) { + err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE, + /*flags*/0); + goto out; + } + + /* need to cpup or reopen */ + parent = dget_parent(cpg.dentry); + di_write_lock_parent(parent); + err = AuWbrCopyup(au_sbi(sb), cpg.dentry); + cpg.bdst = err; + if (unlikely(err < 0)) + goto out_dgrade; + err = 0; + + if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) { + err = au_cpup_dirs(cpg.dentry, cpg.bdst); + if (unlikely(err)) + goto out_dgrade; + } + + err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_dgrade; + + dbtop = au_dbtop(cpg.dentry); + if (dbtop <= cpg.bdst) + cpg.bsrc = cpg.bdst; + + if (dbtop <= cpg.bdst /* just reopen */ + || !d_unhashed(cpg.dentry) /* copyup and reopen */ + ) { + h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0); + if (IS_ERR(h_file)) + err = PTR_ERR(h_file); + else { + di_downgrade_lock(parent, AuLock_IR); + if (dbtop > cpg.bdst) + err = au_sio_cpup_simple(&cpg); + if (!err) + err = au_reopen_nondir(file); + au_h_open_post(cpg.dentry, cpg.bsrc, h_file); + } + } else { /* copyup as wh and reopen */ + /* + * since writable hfsplus branch is not supported, + * h_open_pre/post() are unnecessary. + */ + err = au_ready_to_write_wh(file, len, cpg.bdst, pin); + di_downgrade_lock(parent, AuLock_IR); + } + + if (!err) { + au_pin_set_parent_lflag(pin, /*lflag*/0); + goto out_dput; /* success */ + } + au_unpin(pin); + goto out_unlock; + +out_dgrade: + di_downgrade_lock(parent, AuLock_IR); +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_dput: + dput(parent); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)) +{ + int err; + struct super_block *sb; + struct inode *inode; + + inode = file_inode(file); + sb = inode->i_sb; + si_noflush_read_lock(sb); + fi_read_lock(file); + ii_read_lock_child(inode); + + err = flush(file, id); + au_cpup_attr_timesizes(inode); + + ii_read_unlock(inode); + fi_read_unlock(file); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_file_refresh_by_inode(struct file *file, int *need_reopen) +{ + int err; + struct au_pin pin; + struct au_finfo *finfo; + struct dentry *parent, *hi_wh; + struct inode *inode; + struct super_block *sb; + struct au_cp_generic cpg = { + .dentry = file->f_path.dentry, + .bdst = -1, + .bsrc = -1, + .len = -1, + .pin = &pin, + .flags = AuCpup_DTIME + }; + + FiMustWriteLock(file); + + err = 0; + finfo = au_fi(file); + sb = cpg.dentry->d_sb; + inode = d_inode(cpg.dentry); + cpg.bdst = au_ibtop(inode); + if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry)) + goto out; + + parent = dget_parent(cpg.dentry); + if (au_test_ro(sb, cpg.bdst, inode)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(au_sbi(sb), cpg.dentry); + cpg.bdst = err; + di_read_unlock(parent, !AuLock_IR); + if (unlikely(err < 0)) + goto out_parent; + err = 0; + } + + di_read_lock_parent(parent, AuLock_IR); + hi_wh = au_hi_wh(inode, cpg.bdst); + if (!S_ISDIR(inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode) + && !d_unhashed(cpg.dentry) + && cpg.bdst < au_dbtop(cpg.dentry)) { + err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst); + if (unlikely(err)) + goto out_unlock; + + /* always superio. */ + err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (!err) { + err = au_sio_cpup_simple(&cpg); + au_unpin(&pin); + } + } else if (hi_wh) { + /* already copied-up after unlink */ + err = au_reopen_wh(file, cpg.bdst, hi_wh); + *need_reopen = 0; + } + +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_parent: + dput(parent); +out: + return err; +} + +static void au_do_refresh_dir(struct file *file) +{ + aufs_bindex_t bindex, bbot, new_bindex, brid; + struct au_hfile *p, tmp, *q; + struct au_finfo *finfo; + struct super_block *sb; + struct au_fidir *fidir; + + FiMustWriteLock(file); + + sb = file->f_path.dentry->d_sb; + finfo = au_fi(file); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + p = fidir->fd_hfile + finfo->fi_btop; + brid = p->hf_br->br_id; + bbot = fidir->fd_bbot; + for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) { + if (!p->hf_file) + continue; + + new_bindex = au_br_index(sb, p->hf_br->br_id); + if (new_bindex == bindex) + continue; + if (new_bindex < 0) { + au_set_h_fptr(file, bindex, NULL); + continue; + } + + /* swap two lower inode, and loop again */ + q = fidir->fd_hfile + new_bindex; + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hf_file) { + bindex--; + p--; + } + } + + p = fidir->fd_hfile; + if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) { + bbot = au_sbbot(sb); + for (finfo->fi_btop = 0; finfo->fi_btop <= bbot; + finfo->fi_btop++, p++) + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; + au_hfput(p, /*execed*/0); + } + } else { + bbot = au_br_index(sb, brid); + for (finfo->fi_btop = 0; finfo->fi_btop < bbot; + finfo->fi_btop++, p++) + if (p->hf_file) + au_hfput(p, /*execed*/0); + bbot = au_sbbot(sb); + } + + p = fidir->fd_hfile + bbot; + for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop; + fidir->fd_bbot--, p--) + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; + au_hfput(p, /*execed*/0); + } + AuDebugOn(fidir->fd_bbot < finfo->fi_btop); +} + +/* + * after branch manipulating, refresh the file. + */ +static int refresh_file(struct file *file, int (*reopen)(struct file *file)) +{ + int err, need_reopen, nbr; + aufs_bindex_t bbot, bindex; + struct dentry *dentry; + struct super_block *sb; + struct au_finfo *finfo; + struct au_hfile *hfile; + + dentry = file->f_path.dentry; + sb = dentry->d_sb; + nbr = au_sbbot(sb) + 1; + finfo = au_fi(file); + if (!finfo->fi_hdir) { + hfile = &finfo->fi_htop; + AuDebugOn(!hfile->hf_file); + bindex = au_br_index(sb, hfile->hf_br->br_id); + AuDebugOn(bindex < 0); + if (bindex != finfo->fi_btop) + au_set_fbtop(file, bindex); + } else { + err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0); + if (unlikely(err)) + goto out; + au_do_refresh_dir(file); + } + + err = 0; + need_reopen = 1; + if (!au_test_mmapped(file)) + err = au_file_refresh_by_inode(file, &need_reopen); + if (finfo->fi_hdir) + /* harmless if err */ + au_fidir_realloc(finfo, nbr, /*may_shrink*/1); + if (!err && need_reopen && !d_unlinked(dentry)) + err = reopen(file); + if (!err) { + au_update_figen(file); + goto out; /* success */ + } + + /* error, close all lower files */ + if (finfo->fi_hdir) { + bbot = au_fbbot_dir(file); + for (bindex = au_fbtop(file); bindex <= bbot; bindex++) + au_set_h_fptr(file, bindex, NULL); + } + +out: + return err; +} + +/* common function to regular file and dir */ +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock, unsigned int fi_lsc) +{ + int err; + unsigned int sigen, figen; + aufs_bindex_t btop; + unsigned char pseudo_link; + struct dentry *dentry; + struct inode *inode; + + err = 0; + dentry = file->f_path.dentry; + inode = d_inode(dentry); + sigen = au_sigen(dentry->d_sb); + fi_write_lock_nested(file, fi_lsc); + figen = au_figen(file); + if (!fi_lsc) + di_write_lock_child(dentry); + else + di_write_lock_child2(dentry); + btop = au_dbtop(dentry); + pseudo_link = (btop != au_ibtop(inode)); + if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + goto out; /* success */ + } + + AuDbg("sigen %d, figen %d\n", sigen, figen); + if (au_digen_test(dentry, sigen)) { + err = au_reval_dpath(dentry, sigen); + AuDebugOn(!err && au_digen_test(dentry, sigen)); + } + + if (!err) + err = refresh_file(file, reopen); + if (!err) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + } else { + di_write_unlock(dentry); + fi_write_unlock(file); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* cf. aufs_nopage() */ +/* for madvise(2) */ +static int aufs_readpage(struct file *file __maybe_unused, struct page *page) +{ + unlock_page(page); + return 0; +} + +/* it will never be called, but necessary to support O_DIRECT */ +static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ BUG(); return 0; } + +/* they will never be called. */ +#ifdef CONFIG_AUFS_DEBUG +static int aufs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ AuUnsupport(); return 0; } +static int aufs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ AuUnsupport(); return 0; } +static int aufs_writepage(struct page *page, struct writeback_control *wbc) +{ AuUnsupport(); return 0; } + +static int aufs_set_page_dirty(struct page *page) +{ AuUnsupport(); return 0; } +static void aufs_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) +{ AuUnsupport(); } +static int aufs_releasepage(struct page *page, gfp_t gfp) +{ AuUnsupport(); return 0; } +#if 0 /* called by memory compaction regardless file */ +static int aufs_migratepage(struct address_space *mapping, struct page *newpage, + struct page *page, enum migrate_mode mode) +{ AuUnsupport(); return 0; } +#endif +static bool aufs_isolate_page(struct page *page, isolate_mode_t mode) +{ AuUnsupport(); return true; } +static void aufs_putback_page(struct page *page) +{ AuUnsupport(); } +static int aufs_launder_page(struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_is_partially_uptodate(struct page *page, + unsigned long from, + unsigned long count) +{ AuUnsupport(); return 0; } +static void aufs_is_dirty_writeback(struct page *page, bool *dirty, + bool *writeback) +{ AuUnsupport(); } +static int aufs_error_remove_page(struct address_space *mapping, + struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ AuUnsupport(); return 0; } +static void aufs_swap_deactivate(struct file *file) +{ AuUnsupport(); } +#endif /* CONFIG_AUFS_DEBUG */ + +const struct address_space_operations aufs_aop = { + .readpage = aufs_readpage, + .direct_IO = aufs_direct_IO, +#ifdef CONFIG_AUFS_DEBUG + .writepage = aufs_writepage, + /* no writepages, because of writepage */ + .set_page_dirty = aufs_set_page_dirty, + /* no readpages, because of readpage */ + .write_begin = aufs_write_begin, + .write_end = aufs_write_end, + /* no bmap, no block device */ + .invalidatepage = aufs_invalidatepage, + .releasepage = aufs_releasepage, + /* is fallback_migrate_page ok? */ + /* .migratepage = aufs_migratepage, */ + .isolate_page = aufs_isolate_page, + .putback_page = aufs_putback_page, + .launder_page = aufs_launder_page, + .is_partially_uptodate = aufs_is_partially_uptodate, + .is_dirty_writeback = aufs_is_dirty_writeback, + .error_remove_page = aufs_error_remove_page, + .swap_activate = aufs_swap_activate, + .swap_deactivate = aufs_swap_deactivate +#endif /* CONFIG_AUFS_DEBUG */ +}; diff --git a/fs/aufs/file.h b/fs/aufs/file.h new file mode 100644 index 000000000000..c679a19df528 --- /dev/null +++ b/fs/aufs/file.h @@ -0,0 +1,342 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file operations + */ + +#ifndef __AUFS_FILE_H__ +#define __AUFS_FILE_H__ + +#ifdef __KERNEL__ + +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/mm_types.h> +#include <linux/poll.h> +#include "rwsem.h" + +struct au_branch; +struct au_hfile { + struct file *hf_file; + struct au_branch *hf_br; +}; + +struct au_vdir; +struct au_fidir { + aufs_bindex_t fd_bbot; + aufs_bindex_t fd_nent; + struct au_vdir *fd_vdir_cache; + struct au_hfile fd_hfile[]; +}; + +static inline int au_fidir_sz(int nent) +{ + AuDebugOn(nent < 0); + return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent; +} + +struct au_finfo { + atomic_t fi_generation; + + struct au_rwsem fi_rwsem; + aufs_bindex_t fi_btop; + + /* do not union them */ + struct { /* for non-dir */ + struct au_hfile fi_htop; + atomic_t fi_mmapped; + }; + struct au_fidir *fi_hdir; /* for dir only */ + + struct hlist_bl_node fi_hlist; + struct file *fi_file; /* very ugly */ + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* file.c */ +extern const struct address_space_operations aufs_aop; +unsigned int au_file_roflags(unsigned int flags); +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file, int force_wr); +struct au_do_open_args { + int aopen; + int (*open)(struct file *file, int flags, + struct file *h_file); + struct au_fidir *fidir; + struct file *h_file; +}; +int au_do_open(struct file *file, struct au_do_open_args *args); +int au_reopen_nondir(struct file *file); +struct au_pin; +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin); +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock, unsigned int fi_lsc); +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)); + +/* poll.c */ +#ifdef CONFIG_AUFS_POLL +__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt); +#endif + +#ifdef CONFIG_AUFS_BR_HFSPLUS +/* hfsplus.c */ +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, + int force_wr); +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#else +AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry, + aufs_bindex_t bindex, int force_wr) +AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#endif + +/* f_op.c */ +extern const struct file_operations aufs_file_fop; +int au_do_open_nondir(struct file *file, int flags, struct file *h_file); +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file); +struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc); + +/* finfo.c */ +void au_hfput(struct au_hfile *hf, int execed); +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, + struct file *h_file); + +void au_update_figen(struct file *file); +struct au_fidir *au_fidir_alloc(struct super_block *sb); +int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink); + +void au_fi_init_once(void *_fi); +void au_finfo_fin(struct file *file); +int au_finfo_init(struct file *file, struct au_fidir *fidir); + +/* ioctl.c */ +long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, + unsigned long arg); +long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, + unsigned long arg); +#endif + +/* ---------------------------------------------------------------------- */ + +static inline struct au_finfo *au_fi(struct file *file) +{ + return file->private_data; +} + +/* ---------------------------------------------------------------------- */ + +#define fi_read_lock(f) au_rw_read_lock(&au_fi(f)->fi_rwsem) +#define fi_write_lock(f) au_rw_write_lock(&au_fi(f)->fi_rwsem) +#define fi_read_trylock(f) au_rw_read_trylock(&au_fi(f)->fi_rwsem) +#define fi_write_trylock(f) au_rw_write_trylock(&au_fi(f)->fi_rwsem) +/* +#define fi_read_trylock_nested(f) \ + au_rw_read_trylock_nested(&au_fi(f)->fi_rwsem) +#define fi_write_trylock_nested(f) \ + au_rw_write_trylock_nested(&au_fi(f)->fi_rwsem) +*/ + +#define fi_read_unlock(f) au_rw_read_unlock(&au_fi(f)->fi_rwsem) +#define fi_write_unlock(f) au_rw_write_unlock(&au_fi(f)->fi_rwsem) +#define fi_downgrade_lock(f) au_rw_dgrade_lock(&au_fi(f)->fi_rwsem) + +/* lock subclass for finfo */ +enum { + AuLsc_FI_1, + AuLsc_FI_2 +}; + +static inline void fi_read_lock_nested(struct file *f, unsigned int lsc) +{ + au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + +static inline void fi_write_lock_nested(struct file *f, unsigned int lsc) +{ + au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + +/* + * fi_read_lock_1, fi_write_lock_1, + * fi_read_lock_2, fi_write_lock_2 + */ +#define AuReadLockFunc(name) \ +static inline void fi_read_lock_##name(struct file *f) \ +{ fi_read_lock_nested(f, AuLsc_FI_##name); } + +#define AuWriteLockFunc(name) \ +static inline void fi_write_lock_##name(struct file *f) \ +{ fi_write_lock_nested(f, AuLsc_FI_##name); } + +#define AuRWLockFuncs(name) \ + AuReadLockFunc(name) \ + AuWriteLockFunc(name) + +AuRWLockFuncs(1); +AuRWLockFuncs(2); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem) +#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem) +#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: hard/soft set? */ +static inline aufs_bindex_t au_fbtop(struct file *file) +{ + FiMustAnyLock(file); + return au_fi(file)->fi_btop; +} + +static inline aufs_bindex_t au_fbbot_dir(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_bbot; +} + +static inline struct au_vdir *au_fvdir_cache(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_vdir_cache; +} + +static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + au_fi(file)->fi_btop = bindex; +} + +static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_bbot = bindex; +} + +static inline void au_set_fvdir_cache(struct file *file, + struct au_vdir *vdir_cache) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache; +} + +static inline struct file *au_hf_top(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(au_fi(file)->fi_hdir); + return au_fi(file)->fi_htop.hf_file; +} + +static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file; +} + +/* todo: memory barrier? */ +static inline unsigned int au_figen(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_generation); +} + +static inline void au_set_mmapped(struct file *f) +{ + if (atomic_inc_return(&au_fi(f)->fi_mmapped)) + return; + pr_warn("fi_mmapped wrapped around\n"); + while (!atomic_inc_return(&au_fi(f)->fi_mmapped)) + ; +} + +static inline void au_unset_mmapped(struct file *f) +{ + atomic_dec(&au_fi(f)->fi_mmapped); +} + +static inline int au_test_mmapped(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_mmapped); +} + +/* customize vma->vm_file */ + +static inline void au_do_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + f = vma->vm_file; + get_file(file); + vma->vm_file = file; + fput(f); +} + +#ifdef CONFIG_MMU +#define AuDbgVmRegion(file, vma) do {} while (0) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + au_do_vm_file_reset(vma, file); +} +#else +#define AuDbgVmRegion(file, vma) \ + AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file)) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + au_do_vm_file_reset(vma, file); + f = vma->vm_region->vm_file; + get_file(file); + vma->vm_region->vm_file = file; + fput(f); +} +#endif /* CONFIG_MMU */ + +/* handle vma->vm_prfile */ +static inline void au_vm_prfile_set(struct vm_area_struct *vma, + struct file *file) +{ + get_file(file); + vma->vm_prfile = file; +#ifndef CONFIG_MMU + get_file(file); + vma->vm_region->vm_prfile = file; +#endif +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FILE_H__ */ diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c new file mode 100644 index 000000000000..448c5e9cd85d --- /dev/null +++ b/fs/aufs/finfo.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * file private data + */ + +#include "aufs.h" + +void au_hfput(struct au_hfile *hf, int execed) +{ + if (execed) + allow_write_access(hf->hf_file); + fput(hf->hf_file); + hf->hf_file = NULL; + au_lcnt_dec(&hf->hf_br->br_nfiles); + hf->hf_br = NULL; +} + +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val) +{ + struct au_finfo *finfo = au_fi(file); + struct au_hfile *hf; + struct au_fidir *fidir; + + fidir = finfo->fi_hdir; + if (!fidir) { + AuDebugOn(finfo->fi_btop != bindex); + hf = &finfo->fi_htop; + } else + hf = fidir->fd_hfile + bindex; + + if (hf && hf->hf_file) + au_hfput(hf, vfsub_file_execed(file)); + if (val) { + FiMustWriteLock(file); + AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry)); + hf->hf_file = val; + hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex); + } +} + +void au_update_figen(struct file *file) +{ + atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry)); + /* smp_mb(); */ /* atomic_set */ +} + +/* ---------------------------------------------------------------------- */ + +struct au_fidir *au_fidir_alloc(struct super_block *sb) +{ + struct au_fidir *fidir; + int nbr; + + nbr = au_sbbot(sb) + 1; + if (nbr < 2) + nbr = 2; /* initial allocate for 2 branches */ + fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS); + if (fidir) { + fidir->fd_bbot = -1; + fidir->fd_nent = nbr; + } + + return fidir; +} + +int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink) +{ + int err; + struct au_fidir *fidir, *p; + + AuRwMustWriteLock(&finfo->fi_rwsem); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + + err = -ENOMEM; + p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr), + GFP_NOFS, may_shrink); + if (p) { + p->fd_nent = nbr; + finfo->fi_hdir = p; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_finfo_fin(struct file *file) +{ + struct au_finfo *finfo; + + au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles); + + finfo = au_fi(file); + AuDebugOn(finfo->fi_hdir); + AuRwDestroy(&finfo->fi_rwsem); + au_cache_free_finfo(finfo); +} + +void au_fi_init_once(void *_finfo) +{ + struct au_finfo *finfo = _finfo; + + au_rw_init(&finfo->fi_rwsem); +} + +int au_finfo_init(struct file *file, struct au_fidir *fidir) +{ + int err; + struct au_finfo *finfo; + struct dentry *dentry; + + err = -ENOMEM; + dentry = file->f_path.dentry; + finfo = au_cache_alloc_finfo(); + if (unlikely(!finfo)) + goto out; + + err = 0; + au_lcnt_inc(&au_sbi(dentry->d_sb)->si_nfiles); + au_rw_write_lock(&finfo->fi_rwsem); + finfo->fi_btop = -1; + finfo->fi_hdir = fidir; + atomic_set(&finfo->fi_generation, au_digen(dentry)); + /* smp_mb(); */ /* atomic_set */ + + file->private_data = finfo; + +out: + return err; +} diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h new file mode 100644 index 000000000000..510bd87e9404 --- /dev/null +++ b/fs/aufs/fstype.h @@ -0,0 +1,401 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * judging filesystem type + */ + +#ifndef __AUFS_FSTYPE_H__ +#define __AUFS_FSTYPE_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/magic.h> +#include <linux/nfs_fs.h> +#include <linux/romfs_fs.h> + +static inline int au_test_aufs(struct super_block *sb) +{ + return sb->s_magic == AUFS_SUPER_MAGIC; +} + +static inline const char *au_sbtype(struct super_block *sb) +{ + return sb->s_type->name; +} + +static inline int au_test_iso9660(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ISO9660_FS) + return sb->s_magic == ISOFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_romfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ROMFS_FS) + return sb->s_magic == ROMFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_cramfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_CRAMFS) + return sb->s_magic == CRAMFS_MAGIC; +#endif + return 0; +} + +static inline int au_test_nfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NFS_FS) + return sb->s_magic == NFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_fuse(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_FUSE_FS) + return sb->s_magic == FUSE_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_XFS_FS) + return sb->s_magic == XFS_SB_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_tmpfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_TMPFS + return sb->s_magic == TMPFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_ECRYPT_FS) + return !strcmp(au_sbtype(sb), "ecryptfs"); +#else + return 0; +#endif +} + +static inline int au_test_ramfs(struct super_block *sb) +{ + return sb->s_magic == RAMFS_MAGIC; +} + +static inline int au_test_ubifs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_UBIFS_FS) + return sb->s_magic == UBIFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_procfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_PROC_FS + return sb->s_magic == PROC_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_sysfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SYSFS + return sb->s_magic == SYSFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_configfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_CONFIGFS_FS) + return sb->s_magic == CONFIGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_minix(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_MINIX_FS) + return sb->s_magic == MINIX3_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC2 + || sb->s_magic == MINIX_SUPER_MAGIC + || sb->s_magic == MINIX_SUPER_MAGIC2; +#else + return 0; +#endif +} + +static inline int au_test_fat(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_FAT_FS) + return sb->s_magic == MSDOS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_msdos(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_vfat(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_securityfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SECURITYFS + return sb->s_magic == SECURITYFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_squashfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_SQUASHFS) + return sb->s_magic == SQUASHFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_btrfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_BTRFS_FS) + return sb->s_magic == BTRFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xenfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_XENFS) + return sb->s_magic == XENFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_debugfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_DEBUG_FS + return sb->s_magic == DEBUGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_nilfs(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NILFS) + return sb->s_magic == NILFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_hfsplus(struct super_block *sb __maybe_unused) +{ +#if IS_ENABLED(CONFIG_HFSPLUS_FS) + return sb->s_magic == HFSPLUS_SUPER_MAGIC; +#else + return 0; +#endif +} + +/* ---------------------------------------------------------------------- */ +/* + * they can't be an aufs branch. + */ +static inline int au_test_fs_unsuppoted(struct super_block *sb) +{ + return +#ifndef CONFIG_AUFS_BR_RAMFS + au_test_ramfs(sb) || +#endif + au_test_procfs(sb) + || au_test_sysfs(sb) + || au_test_configfs(sb) + || au_test_debugfs(sb) + || au_test_securityfs(sb) + || au_test_xenfs(sb) + || au_test_ecryptfs(sb) + /* || !strcmp(au_sbtype(sb), "unionfs") */ + || au_test_aufs(sb); /* will be supported in next version */ +} + +static inline int au_test_fs_remote(struct super_block *sb) +{ + return !au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + && !au_test_ramfs(sb) +#endif + && !(sb->s_type->fs_flags & FS_REQUIRES_DEV); +} + +/* ---------------------------------------------------------------------- */ + +/* + * Note: these functions (below) are created after reading ->getattr() in all + * filesystems under linux/fs. it means we have to do so in every update... + */ + +/* + * some filesystems require getattr to refresh the inode attributes before + * referencing. + * in most cases, we can rely on the inode attribute in NFS (or every remote fs) + * and leave the work for d_revalidate() + */ +static inline int au_test_fs_refresh_iattr(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + /* || au_test_btrfs(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't maintain i_size or i_blocks. + */ +static inline int au_test_fs_bad_iattr_size(struct super_block *sb) +{ + return au_test_xfs(sb) + || au_test_btrfs(sb) + || au_test_ubifs(sb) + || au_test_hfsplus(sb) /* maintained, but incorrect */ + /* || au_test_minix(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't store the correct value in some of their inode + * attributes. + */ +static inline int au_test_fs_bad_iattr(struct super_block *sb) +{ + return au_test_fs_bad_iattr_size(sb) + || au_test_fat(sb) + || au_test_msdos(sb) + || au_test_vfat(sb); +} + +/* they don't check i_nlink in link(2) */ +static inline int au_test_fs_no_limit_nlink(struct super_block *sb) +{ + return au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + || au_test_ramfs(sb) +#endif + || au_test_ubifs(sb) + || au_test_hfsplus(sb); +} + +/* + * filesystems which sets S_NOATIME and S_NOCMTIME. + */ +static inline int au_test_fs_notime(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + || au_test_ubifs(sb) + ; +} + +/* temporary support for i#1 in cramfs */ +static inline int au_test_fs_unique_ino(struct inode *inode) +{ + if (au_test_cramfs(inode->i_sb)) + return inode->i_ino != 1; + return 1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * the filesystem where the xino files placed must support i/o after unlink and + * maintain i_size and i_blocks. + */ +static inline int au_test_fs_bad_xino(struct super_block *sb) +{ + return au_test_fs_remote(sb) + || au_test_fs_bad_iattr_size(sb) + /* don't want unnecessary work for xino */ + || au_test_aufs(sb) + || au_test_ecryptfs(sb) + || au_test_nilfs(sb); +} + +static inline int au_test_fs_trunc_xino(struct super_block *sb) +{ + return au_test_tmpfs(sb) + || au_test_ramfs(sb); +} + +/* + * test if the @sb is real-readonly. + */ +static inline int au_test_fs_rr(struct super_block *sb) +{ + return au_test_squashfs(sb) + || au_test_iso9660(sb) + || au_test_cramfs(sb) + || au_test_romfs(sb); +} + +/* + * test if the @inode is nfs with 'noacl' option + * NFS always sets SB_POSIXACL regardless its mount option 'noacl.' + */ +static inline int au_test_nfs_noacl(struct inode *inode) +{ + return au_test_nfs(inode->i_sb) + /* && IS_POSIXACL(inode) */ + && !nfs_server_capable(inode, NFS_CAP_ACLS); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FSTYPE_H__ */ diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h new file mode 100644 index 000000000000..6db65b16b08a --- /dev/null +++ b/fs/aufs/hbl.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * helpers for hlist_bl.h + */ + +#ifndef __AUFS_HBL_H__ +#define __AUFS_HBL_H__ + +#ifdef __KERNEL__ + +#include <linux/list_bl.h> + +static inline void au_hbl_add(struct hlist_bl_node *node, + struct hlist_bl_head *hbl) +{ + hlist_bl_lock(hbl); + hlist_bl_add_head(node, hbl); + hlist_bl_unlock(hbl); +} + +static inline void au_hbl_del(struct hlist_bl_node *node, + struct hlist_bl_head *hbl) +{ + hlist_bl_lock(hbl); + hlist_bl_del(node); + hlist_bl_unlock(hbl); +} + +#define au_hbl_for_each(pos, head) \ + for (pos = hlist_bl_first(head); \ + pos; \ + pos = pos->next) + +static inline unsigned long au_hbl_count(struct hlist_bl_head *hbl) +{ + unsigned long cnt; + struct hlist_bl_node *pos; + + cnt = 0; + hlist_bl_lock(hbl); + au_hbl_for_each(pos, hbl) + cnt++; + hlist_bl_unlock(hbl); + return cnt; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_HBL_H__ */ diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c new file mode 100644 index 000000000000..7945ae3ca073 --- /dev/null +++ b/fs/aufs/hfsnotify.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * fsnotify for the lower directories + */ + +#include "aufs.h" + +/* FS_IN_IGNORED is unnecessary */ +static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE + | FS_CREATE | FS_EVENT_ON_CHILD); +static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq); +static __cacheline_aligned_in_smp atomic64_t au_hfsn_ifree = ATOMIC64_INIT(0); + +static void au_hfsn_free_mark(struct fsnotify_mark *mark) +{ + struct au_hnotify *hn = container_of(mark, struct au_hnotify, + hn_mark); + /* AuDbg("here\n"); */ + au_cache_free_hnotify(hn); + smp_mb__before_atomic(); /* for atomic64_dec */ + if (atomic64_dec_and_test(&au_hfsn_ifree)) + wake_up(&au_hfsn_wq); +} + +static int au_hfsn_alloc(struct au_hinode *hinode) +{ + int err; + struct au_hnotify *hn; + struct super_block *sb; + struct au_branch *br; + struct fsnotify_mark *mark; + aufs_bindex_t bindex; + + hn = hinode->hi_notify; + sb = hn->hn_aufs_inode->i_sb; + bindex = au_br_index(sb, hinode->hi_id); + br = au_sbr(sb, bindex); + AuDebugOn(!br->br_hfsn); + + mark = &hn->hn_mark; + fsnotify_init_mark(mark, br->br_hfsn->hfsn_group); + mark->mask = AuHfsnMask; + /* + * by udba rename or rmdir, aufs assign a new inode to the known + * h_inode, so specify 1 to allow dups. + */ + lockdep_off(); + err = fsnotify_add_inode_mark(mark, hinode->hi_inode, /*allow_dups*/1); + lockdep_on(); + + return err; +} + +static int au_hfsn_free(struct au_hinode *hinode, struct au_hnotify *hn) +{ + struct fsnotify_mark *mark; + unsigned long long ull; + struct fsnotify_group *group; + + ull = atomic64_inc_return(&au_hfsn_ifree); + BUG_ON(!ull); + + mark = &hn->hn_mark; + spin_lock(&mark->lock); + group = mark->group; + fsnotify_get_group(group); + spin_unlock(&mark->lock); + lockdep_off(); + fsnotify_destroy_mark(mark, group); + fsnotify_put_mark(mark); + fsnotify_put_group(group); + lockdep_on(); + + /* free hn by myself */ + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_ctl(struct au_hinode *hinode, int do_set) +{ + struct fsnotify_mark *mark; + + mark = &hinode->hi_notify->hn_mark; + spin_lock(&mark->lock); + if (do_set) { + AuDebugOn(mark->mask & AuHfsnMask); + mark->mask |= AuHfsnMask; + } else { + AuDebugOn(!(mark->mask & AuHfsnMask)); + mark->mask &= ~AuHfsnMask; + } + spin_unlock(&mark->lock); + /* fsnotify_recalc_inode_mask(hinode->hi_inode); */ +} + +/* ---------------------------------------------------------------------- */ + +/* #define AuDbgHnotify */ +#ifdef AuDbgHnotify +static char *au_hfsn_name(u32 mask) +{ +#ifdef CONFIG_AUFS_DEBUG +#define test_ret(flag) \ + do { \ + if (mask & flag) \ + return #flag; \ + } while (0) + test_ret(FS_ACCESS); + test_ret(FS_MODIFY); + test_ret(FS_ATTRIB); + test_ret(FS_CLOSE_WRITE); + test_ret(FS_CLOSE_NOWRITE); + test_ret(FS_OPEN); + test_ret(FS_MOVED_FROM); + test_ret(FS_MOVED_TO); + test_ret(FS_CREATE); + test_ret(FS_DELETE); + test_ret(FS_DELETE_SELF); + test_ret(FS_MOVE_SELF); + test_ret(FS_UNMOUNT); + test_ret(FS_Q_OVERFLOW); + test_ret(FS_IN_IGNORED); + test_ret(FS_ISDIR); + test_ret(FS_IN_ONESHOT); + test_ret(FS_EVENT_ON_CHILD); + return ""; +#undef test_ret +#else + return "??"; +#endif +} +#endif + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_free_group(struct fsnotify_group *group) +{ + struct au_br_hfsnotify *hfsn = group->private; + + /* AuDbg("here\n"); */ + au_kfree_try_rcu(hfsn); +} + +static int au_hfsn_handle_event(struct fsnotify_group *group, + struct inode *inode, + u32 mask, const void *data, int data_type, + const struct qstr *file_name, u32 cookie, + struct fsnotify_iter_info *iter_info) +{ + int err; + struct au_hnotify *hnotify; + struct inode *h_dir, *h_inode; + struct fsnotify_mark *inode_mark; + + AuDebugOn(data_type != FSNOTIFY_EVENT_INODE); + + err = 0; + /* if FS_UNMOUNT happens, there must be another bug */ + AuDebugOn(mask & FS_UNMOUNT); + if (mask & (FS_IN_IGNORED | FS_UNMOUNT)) + goto out; + + h_dir = inode; + h_inode = NULL; +#ifdef AuDbgHnotify + au_debug_on(); + if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1 + || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) { + AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n", + h_dir->i_ino, mask, au_hfsn_name(mask), + AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0); + /* WARN_ON(1); */ + } + au_debug_off(); +#endif + + inode_mark = fsnotify_iter_inode_mark(iter_info); + AuDebugOn(!inode_mark); + hnotify = container_of(inode_mark, struct au_hnotify, hn_mark); + err = au_hnotify(h_dir, hnotify, mask, file_name, h_inode); + +out: + return err; +} + +static struct fsnotify_ops au_hfsn_ops = { + .handle_event = au_hfsn_handle_event, + .free_group_priv = au_hfsn_free_group, + .free_mark = au_hfsn_free_mark +}; + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_fin_br(struct au_branch *br) +{ + struct au_br_hfsnotify *hfsn; + + hfsn = br->br_hfsn; + if (hfsn) { + lockdep_off(); + fsnotify_put_group(hfsn->hfsn_group); + lockdep_on(); + } +} + +static int au_hfsn_init_br(struct au_branch *br, int perm) +{ + int err; + struct fsnotify_group *group; + struct au_br_hfsnotify *hfsn; + + err = 0; + br->br_hfsn = NULL; + if (!au_br_hnotifyable(perm)) + goto out; + + err = -ENOMEM; + hfsn = kmalloc(sizeof(*hfsn), GFP_NOFS); + if (unlikely(!hfsn)) + goto out; + + err = 0; + group = fsnotify_alloc_group(&au_hfsn_ops); + if (IS_ERR(group)) { + err = PTR_ERR(group); + pr_err("fsnotify_alloc_group() failed, %d\n", err); + goto out_hfsn; + } + + group->private = hfsn; + hfsn->hfsn_group = group; + br->br_hfsn = hfsn; + goto out; /* success */ + +out_hfsn: + au_kfree_try_rcu(hfsn); +out: + return err; +} + +static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (!br->br_hfsn) + err = au_hfsn_init_br(br, perm); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_fin(void) +{ + AuDbg("au_hfsn_ifree %lld\n", (long long)atomic64_read(&au_hfsn_ifree)); + wait_event(au_hfsn_wq, !atomic64_read(&au_hfsn_ifree)); +} + +const struct au_hnotify_op au_hnotify_op = { + .ctl = au_hfsn_ctl, + .alloc = au_hfsn_alloc, + .free = au_hfsn_free, + + .fin = au_hfsn_fin, + + .reset_br = au_hfsn_reset_br, + .fin_br = au_hfsn_fin_br, + .init_br = au_hfsn_init_br +}; diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c new file mode 100644 index 000000000000..3bd869a69c8f --- /dev/null +++ b/fs/aufs/hfsplus.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * special support for filesystems which acquires an inode mutex + * at final closing a file, eg, hfsplus. + * + * This trick is very simple and stupid, just to open the file before really + * necessary open to tell hfsplus that this is not the final closing. + * The caller should call au_h_open_pre() after acquiring the inode mutex, + * and au_h_open_post() after releasing it. + */ + +#include "aufs.h" + +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex, + int force_wr) +{ + struct file *h_file; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + AuDebugOn(!h_dentry); + AuDebugOn(d_is_negative(h_dentry)); + + h_file = NULL; + if (au_test_hfsplus(h_dentry->d_sb) + && d_is_reg(h_dentry)) + h_file = au_h_open(dentry, bindex, + O_RDONLY | O_NOATIME | O_LARGEFILE, + /*file*/NULL, force_wr); + return h_file; +} + +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file) +{ + struct au_branch *br; + + if (h_file) { + fput(h_file); + br = au_sbr(dentry->d_sb, bindex); + au_lcnt_dec(&br->br_nfiles); + } +} diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c new file mode 100644 index 000000000000..2e7c2cdb8202 --- /dev/null +++ b/fs/aufs/hnotify.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * abstraction to notify the direct changes on lower directories + */ + +/* #include <linux/iversion.h> */ +#include "aufs.h" + +int au_hn_alloc(struct au_hinode *hinode, struct inode *inode) +{ + int err; + struct au_hnotify *hn; + + err = -ENOMEM; + hn = au_cache_alloc_hnotify(); + if (hn) { + hn->hn_aufs_inode = inode; + hinode->hi_notify = hn; + err = au_hnotify_op.alloc(hinode); + AuTraceErr(err); + if (unlikely(err)) { + hinode->hi_notify = NULL; + au_cache_free_hnotify(hn); + /* + * The upper dir was removed by udba, but the same named + * dir left. In this case, aufs assigns a new inode + * number and set the monitor again. + * For the lower dir, the old monitor is still left. + */ + if (err == -EEXIST) + err = 0; + } + } + + AuTraceErr(err); + return err; +} + +void au_hn_free(struct au_hinode *hinode) +{ + struct au_hnotify *hn; + + hn = hinode->hi_notify; + if (hn) { + hinode->hi_notify = NULL; + if (au_hnotify_op.free(hinode, hn)) + au_cache_free_hnotify(hn); + } +} + +/* ---------------------------------------------------------------------- */ + +void au_hn_ctl(struct au_hinode *hinode, int do_set) +{ + if (hinode->hi_notify) + au_hnotify_op.ctl(hinode, do_set); +} + +void au_hn_reset(struct inode *inode, unsigned int flags) +{ + aufs_bindex_t bindex, bbot; + struct inode *hi; + struct dentry *iwhdentry; + + bbot = au_ibbot(inode); + for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) { + hi = au_h_iptr(inode, bindex); + if (!hi) + continue; + + /* inode_lock_nested(hi, AuLsc_I_CHILD); */ + iwhdentry = au_hi_wh(inode, bindex); + if (iwhdentry) + dget(iwhdentry); + au_igrab(hi); + au_set_h_iptr(inode, bindex, NULL, 0); + au_set_h_iptr(inode, bindex, au_igrab(hi), + flags & ~AuHi_XINO); + iput(hi); + dput(iwhdentry); + /* inode_unlock(hi); */ + } +} + +/* ---------------------------------------------------------------------- */ + +static int hn_xino(struct inode *inode, struct inode *h_inode) +{ + int err; + aufs_bindex_t bindex, bbot, bfound, btop; + struct inode *h_i; + + err = 0; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("branch root dir was changed\n"); + goto out; + } + + bfound = -1; + bbot = au_ibbot(inode); + btop = au_ibtop(inode); +#if 0 /* reserved for future use */ + if (bindex == bbot) { + /* keep this ino in rename case */ + goto out; + } +#endif + for (bindex = btop; bindex <= bbot; bindex++) + if (au_h_iptr(inode, bindex) == h_inode) { + bfound = bindex; + break; + } + if (bfound < 0) + goto out; + + for (bindex = btop; bindex <= bbot; bindex++) { + h_i = au_h_iptr(inode, bindex); + if (!h_i) + continue; + + err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0); + /* ignore this error */ + /* bad action? */ + } + + /* children inode number will be broken */ + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_tree(struct dentry *dentry) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, dentry, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + struct dentry *d; + + d = dentries[j]; + if (IS_ROOT(d)) + continue; + + au_digen_dec(d); + if (d_really_is_positive(d)) + /* todo: reset children xino? + cached children only? */ + au_iigen_dec(d_inode(d)); + } + } + +out_dpages: + au_dpages_free(&dpages); + +#if 0 + /* discard children */ + dentry_unhash(dentry); + dput(dentry); +#endif +out: + return err; +} + +/* + * return 0 if processed. + */ +static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode, + const unsigned int isdir) +{ + int err; + struct dentry *d; + struct qstr *dname; + + err = 1; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("branch root dir was changed\n"); + err = 0; + goto out; + } + + if (!isdir) { + AuDebugOn(!name); + au_iigen_dec(inode); + spin_lock(&inode->i_lock); + hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) { + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len != nlen + && memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + continue; + } + err = 0; + au_digen_dec(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&inode->i_lock); + } else { + au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR); + d = d_find_any_alias(inode); + if (!d) { + au_iigen_dec(inode); + goto out; + } + + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len == nlen && !memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + err = hn_gen_tree(d); + spin_lock(&d->d_lock); + } + spin_unlock(&d->d_lock); + dput(d); + } + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir) +{ + int err; + + if (IS_ROOT(dentry)) { + pr_warn("branch root dir was changed\n"); + return 0; + } + + err = 0; + if (!isdir) { + au_digen_dec(dentry); + if (d_really_is_positive(dentry)) + au_iigen_dec(d_inode(dentry)); + } else { + au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR); + if (d_really_is_positive(dentry)) + err = hn_gen_tree(dentry); + } + + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* hnotify job flags */ +#define AuHnJob_XINO0 1 +#define AuHnJob_GEN (1 << 1) +#define AuHnJob_DIRENT (1 << 2) +#define AuHnJob_ISDIR (1 << 3) +#define AuHnJob_TRYXINO0 (1 << 4) +#define AuHnJob_MNTPNT (1 << 5) +#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name) +#define au_fset_hnjob(flags, name) \ + do { (flags) |= AuHnJob_##name; } while (0) +#define au_fclr_hnjob(flags, name) \ + do { (flags) &= ~AuHnJob_##name; } while (0) + +enum { + AuHn_CHILD, + AuHn_PARENT, + AuHnLast +}; + +struct au_hnotify_args { + struct inode *h_dir, *dir, *h_child_inode; + u32 mask; + unsigned int flags[AuHnLast]; + unsigned int h_child_nlen; + char h_child_name[]; +}; + +struct hn_job_args { + unsigned int flags; + struct inode *inode, *h_inode, *dir, *h_dir; + struct dentry *dentry; + char *h_name; + int h_nlen; +}; + +static int hn_job(struct hn_job_args *a) +{ + const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR); + int e; + + /* reset xino */ + if (au_ftest_hnjob(a->flags, XINO0) && a->inode) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + + if (au_ftest_hnjob(a->flags, TRYXINO0) + && a->inode + && a->h_inode) { + inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); + if (!a->h_inode->i_nlink + && !(a->h_inode->i_state & I_LINKABLE)) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + inode_unlock_shared(a->h_inode); + } + + /* make the generation obsolete */ + if (au_ftest_hnjob(a->flags, GEN)) { + e = -1; + if (a->inode) + e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode, + isdir); + if (e && a->dentry) + hn_gen_by_name(a->dentry, isdir); + /* ignore this error */ + } + + /* make dir entries obsolete */ + if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) { + struct au_vdir *vdir; + + vdir = au_ivdir(a->inode); + if (vdir) + vdir->vd_jiffy = 0; + /* IMustLock(a->inode); */ + /* inode_inc_iversion(a->inode); */ + } + + /* can do nothing but warn */ + if (au_ftest_hnjob(a->flags, MNTPNT) + && a->dentry + && d_mountpoint(a->dentry)) + pr_warn("mount-point %pd is removed or renamed\n", a->dentry); + + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen, + struct inode *dir) +{ + struct dentry *dentry, *d, *parent; + struct qstr *dname; + + parent = d_find_any_alias(dir); + if (!parent) + return NULL; + + dentry = NULL; + spin_lock(&parent->d_lock); + list_for_each_entry(d, &parent->d_subdirs, d_child) { + /* AuDbg("%pd\n", d); */ + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + dname = &d->d_name; + if (dname->len != nlen || memcmp(dname->name, name, nlen)) + goto cont_unlock; + if (au_di(d)) + au_digen_dec(d); + else + goto cont_unlock; + if (au_dcount(d) > 0) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + +cont_unlock: + spin_unlock(&d->d_lock); + } + spin_unlock(&parent->d_lock); + dput(parent); + + if (dentry) + di_write_lock_child(dentry); + + return dentry; +} + +static struct inode *lookup_wlock_by_ino(struct super_block *sb, + aufs_bindex_t bindex, ino_t h_ino) +{ + struct inode *inode; + ino_t ino; + int err; + + inode = NULL; + err = au_xino_read(sb, bindex, h_ino, &ino); + if (!err && ino) + inode = ilookup(sb, ino); + if (!inode) + goto out; + + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warn("wrong root branch\n"); + iput(inode); + inode = NULL; + goto out; + } + + ii_write_lock_child(inode); + +out: + return inode; +} + +static void au_hn_bh(void *_args) +{ + struct au_hnotify_args *a = _args; + struct super_block *sb; + aufs_bindex_t bindex, bbot, bfound; + unsigned char xino, try_iput; + int err; + struct inode *inode; + ino_t h_ino; + struct hn_job_args args; + struct dentry *dentry; + struct au_sbinfo *sbinfo; + + AuDebugOn(!_args); + AuDebugOn(!a->h_dir); + AuDebugOn(!a->dir); + AuDebugOn(!a->mask); + AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n", + a->mask, a->dir->i_ino, a->h_dir->i_ino, + a->h_child_inode ? a->h_child_inode->i_ino : 0); + + inode = NULL; + dentry = NULL; + /* + * do not lock a->dir->i_mutex here + * because of d_revalidate() may cause a deadlock. + */ + sb = a->dir->i_sb; + AuDebugOn(!sb); + sbinfo = au_sbi(sb); + AuDebugOn(!sbinfo); + si_write_lock(sb, AuLock_NOPLMW); + + if (au_opt_test(sbinfo->si_mntflags, DIRREN)) + switch (a->mask & FS_EVENTS_POSS_ON_CHILD) { + case FS_MOVED_FROM: + case FS_MOVED_TO: + AuWarn1("DIRREN with UDBA may not work correctly " + "for the direct rename(2)\n"); + } + + ii_read_lock_parent(a->dir); + bfound = -1; + bbot = au_ibbot(a->dir); + for (bindex = au_ibtop(a->dir); bindex <= bbot; bindex++) + if (au_h_iptr(a->dir, bindex) == a->h_dir) { + bfound = bindex; + break; + } + ii_read_unlock(a->dir); + if (unlikely(bfound < 0)) + goto out; + + xino = !!au_opt_test(au_mntflags(sb), XINO); + h_ino = 0; + if (a->h_child_inode) + h_ino = a->h_child_inode->i_ino; + + if (a->h_child_nlen + && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN) + || au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT))) + dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen, + a->dir); + try_iput = 0; + if (dentry && d_really_is_positive(dentry)) + inode = d_inode(dentry); + if (xino && !inode && h_ino + && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) { + inode = lookup_wlock_by_ino(sb, bfound, h_ino); + try_iput = 1; + } + + args.flags = a->flags[AuHn_CHILD]; + args.dentry = dentry; + args.inode = inode; + args.h_inode = a->h_child_inode; + args.dir = a->dir; + args.h_dir = a->h_dir; + args.h_name = a->h_child_name; + args.h_nlen = a->h_child_nlen; + err = hn_job(&args); + if (dentry) { + if (au_di(dentry)) + di_write_unlock(dentry); + dput(dentry); + } + if (inode && try_iput) { + ii_write_unlock(inode); + iput(inode); + } + + ii_write_lock_parent(a->dir); + args.flags = a->flags[AuHn_PARENT]; + args.dentry = NULL; + args.inode = a->dir; + args.h_inode = a->h_dir; + args.dir = NULL; + args.h_dir = NULL; + args.h_name = NULL; + args.h_nlen = 0; + err = hn_job(&args); + ii_write_unlock(a->dir); + +out: + iput(a->h_child_inode); + iput(a->h_dir); + iput(a->dir); + si_write_unlock(sb); + au_nwt_done(&sbinfo->si_nowait); + au_kfree_rcu(a); +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, + const struct qstr *h_child_qstr, struct inode *h_child_inode) +{ + int err, len; + unsigned int flags[AuHnLast], f; + unsigned char isdir, isroot, wh; + struct inode *dir; + struct au_hnotify_args *args; + char *p, *h_child_name; + + err = 0; + AuDebugOn(!hnotify || !hnotify->hn_aufs_inode); + dir = igrab(hnotify->hn_aufs_inode); + if (!dir) + goto out; + + isroot = (dir->i_ino == AUFS_ROOT_INO); + wh = 0; + h_child_name = (void *)h_child_qstr->name; + len = h_child_qstr->len; + if (h_child_name) { + if (len > AUFS_WH_PFX_LEN + && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + h_child_name += AUFS_WH_PFX_LEN; + len -= AUFS_WH_PFX_LEN; + wh = 1; + } + } + + isdir = 0; + if (h_child_inode) + isdir = !!S_ISDIR(h_child_inode->i_mode); + flags[AuHn_PARENT] = AuHnJob_ISDIR; + flags[AuHn_CHILD] = 0; + if (isdir) + flags[AuHn_CHILD] = AuHnJob_ISDIR; + au_fset_hnjob(flags[AuHn_PARENT], DIRENT); + au_fset_hnjob(flags[AuHn_CHILD], GEN); + switch (mask & ALL_FSNOTIFY_DIRENT_EVENTS) { + case FS_MOVED_FROM: + case FS_MOVED_TO: + au_fset_hnjob(flags[AuHn_CHILD], XINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + /*FALLTHROUGH*/ + case FS_CREATE: + AuDebugOn(!h_child_name); + break; + + case FS_DELETE: + /* + * aufs never be able to get this child inode. + * revalidation should be in d_revalidate() + * by checking i_nlink, i_generation or d_unhashed(). + */ + AuDebugOn(!h_child_name); + au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + break; + + default: + AuDebugOn(1); + } + + if (wh) + h_child_inode = NULL; + + err = -ENOMEM; + /* iput() and kfree() will be called in au_hnotify() */ + args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS); + if (unlikely(!args)) { + AuErr1("no memory\n"); + iput(dir); + goto out; + } + args->flags[AuHn_PARENT] = flags[AuHn_PARENT]; + args->flags[AuHn_CHILD] = flags[AuHn_CHILD]; + args->mask = mask; + args->dir = dir; + args->h_dir = igrab(h_dir); + if (h_child_inode) + h_child_inode = igrab(h_child_inode); /* can be NULL */ + args->h_child_inode = h_child_inode; + args->h_child_nlen = len; + if (len) { + p = (void *)args; + p += sizeof(*args); + memcpy(p, h_child_name, len); + p[len] = 0; + } + + /* NFS fires the event for silly-renamed one from kworker */ + f = 0; + if (!dir->i_nlink + || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE))) + f = AuWkq_NEST; + err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); + if (unlikely(err)) { + pr_err("wkq %d\n", err); + iput(args->h_child_inode); + iput(args->h_dir); + iput(args->dir); + au_kfree_rcu(args); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + AuDebugOn(!(udba & AuOptMask_UDBA)); + + err = 0; + if (au_hnotify_op.reset_br) + err = au_hnotify_op.reset_br(udba, br, perm); + + return err; +} + +int au_hnotify_init_br(struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (au_hnotify_op.init_br) + err = au_hnotify_op.init_br(br, perm); + + return err; +} + +void au_hnotify_fin_br(struct au_branch *br) +{ + if (au_hnotify_op.fin_br) + au_hnotify_op.fin_br(br); +} + +static void au_hn_destroy_cache(void) +{ + kmem_cache_destroy(au_cache[AuCache_HNOTIFY]); + au_cache[AuCache_HNOTIFY] = NULL; +} + +int __init au_hnotify_init(void) +{ + int err; + + err = -ENOMEM; + au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify); + if (au_cache[AuCache_HNOTIFY]) { + err = 0; + if (au_hnotify_op.init) + err = au_hnotify_op.init(); + if (unlikely(err)) + au_hn_destroy_cache(); + } + AuTraceErr(err); + return err; +} + +void au_hnotify_fin(void) +{ + if (au_hnotify_op.fin) + au_hnotify_op.fin(); + + /* cf. au_cache_fin() */ + if (au_cache[AuCache_HNOTIFY]) + au_hn_destroy_cache(); +} diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c new file mode 100644 index 000000000000..4f5001ebd0f4 --- /dev/null +++ b/fs/aufs/i_op.c @@ -0,0 +1,1507 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (except add/del/rename) + */ + +#include <linux/device_cgroup.h> +#include <linux/fs_stack.h> +#include <linux/iversion.h> +#include <linux/namei.h> +#include <linux/security.h> +#include "aufs.h" + +static int h_permission(struct inode *h_inode, int mask, + struct path *h_path, int brperm) +{ + int err; + const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + + err = -EPERM; + if (write_mask && IS_IMMUTABLE(h_inode)) + goto out; + + err = -EACCES; + if (((mask & MAY_EXEC) + && S_ISREG(h_inode->i_mode) + && (path_noexec(h_path) + || !(h_inode->i_mode & 0111)))) + goto out; + + /* + * - skip the lower fs test in the case of write to ro branch. + * - nfs dir permission write check is optimized, but a policy for + * link/rename requires a real check. + * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.' + * in this case, generic_permission() returns -EOPNOTSUPP. + */ + if ((write_mask && !au_br_writable(brperm)) + || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) + && write_mask && !(mask & MAY_READ)) + || !h_inode->i_op->permission) { + /* AuLabel(generic_permission); */ + /* AuDbg("get_acl %ps\n", h_inode->i_op->get_acl); */ + err = generic_permission(h_inode, mask); + if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode)) + err = h_inode->i_op->permission(h_inode, mask); + AuTraceErr(err); + } else { + /* AuLabel(h_inode->permission); */ + err = h_inode->i_op->permission(h_inode, mask); + AuTraceErr(err); + } + + if (!err) + err = devcgroup_inode_permission(h_inode, mask); + if (!err) + err = security_inode_permission(h_inode, mask); + +#if 0 + if (!err) { + /* todo: do we need to call ima_path_check()? */ + struct path h_path = { + .dentry = + .mnt = h_mnt + }; + err = ima_path_check(&h_path, + mask & (MAY_READ | MAY_WRITE | MAY_EXEC), + IMA_COUNT_LEAVE); + } +#endif + +out: + return err; +} + +static int aufs_permission(struct inode *inode, int mask) +{ + int err; + aufs_bindex_t bindex, bbot; + const unsigned char isdir = !!S_ISDIR(inode->i_mode), + write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + + /* todo: support rcu-walk? */ + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH); + ii_read_lock_child(inode); +#if 0 + err = au_iigen_test(inode, au_sigen(sb)); + if (unlikely(err)) + goto out; +#endif + + if (!isdir + || write_mask + || au_opt_test(au_mntflags(sb), DIRPERM1)) { + err = au_busy_or_stale(); + h_inode = au_h_iptr(inode, au_ibtop(inode)); + if (unlikely(!h_inode + || (h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT))) + goto out; + + err = 0; + bindex = au_ibtop(inode); + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, &br->br_path, br->br_perm); + if (write_mask + && !err + && !special_file(h_inode->i_mode)) { + /* test whether the upper writable branch exists */ + err = -EROFS; + for (; bindex >= 0; bindex--) + if (!au_br_rdonly(au_sbr(sb, bindex))) { + err = 0; + break; + } + } + goto out; + } + + /* non-write to dir */ + err = 0; + bbot = au_ibbot(inode); + for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) { + err = au_busy_or_stale(); + if (unlikely(!S_ISDIR(h_inode->i_mode))) + break; + + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, &br->br_path, + br->br_perm); + } + } + +out: + ii_read_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret, *parent; + struct inode *inode; + struct super_block *sb; + int err, npositive; + + IMustLock(dir); + + /* todo: support rcu-walk? */ + ret = ERR_PTR(-ECHILD); + if (flags & LOOKUP_RCU) + goto out; + + ret = ERR_PTR(-ENAMETOOLONG); + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out; + + sb = dir->i_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out; + + err = au_di_init(dentry); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out_si; + + inode = NULL; + npositive = 0; /* suppress a warning */ + parent = dentry->d_parent; /* dir inode is locked */ + di_read_lock_parent(parent, AuLock_IR); + err = au_alive_dir(parent); + if (!err) + err = au_digen_test(parent, au_sigen(sb)); + if (!err) { + /* regardless LOOKUP_CREATE, always ALLOW_NEG */ + npositive = au_lkup_dentry(dentry, au_dbtop(parent), + AuLkup_ALLOW_NEG); + err = npositive; + } + di_read_unlock(parent, AuLock_IR); + ret = ERR_PTR(err); + if (unlikely(err < 0)) + goto out_unlock; + + if (npositive) { + inode = au_new_inode(dentry, /*must_new*/0); + if (IS_ERR(inode)) { + ret = (void *)inode; + inode = NULL; + goto out_unlock; + } + } + + if (inode) + atomic_inc(&inode->i_count); + ret = d_splice_alias(inode, dentry); +#if 0 + if (unlikely(d_need_lookup(dentry))) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_NEED_LOOKUP; + spin_unlock(&dentry->d_lock); + } else +#endif + if (inode) { + if (!IS_ERR(ret)) { + iput(inode); + if (ret && ret != dentry) + ii_write_unlock(inode); + } else { + ii_write_unlock(inode); + iput(inode); + inode = NULL; + } + } + +out_unlock: + di_write_unlock(dentry); +out_si: + si_read_unlock(sb); +out: + return ret; +} + +/* ---------------------------------------------------------------------- */ + +/* + * very dirty and complicated aufs ->atomic_open(). + * aufs_atomic_open() + * + au_aopen_or_create() + * + add_simple() + * + vfsub_atomic_open() + * + branch fs ->atomic_open() + * may call the actual 'open' for h_file + * + inc br_nfiles only if opened + * + au_aopen_no_open() or au_aopen_do_open() + * + * au_aopen_do_open() + * + finish_open() + * + au_do_aopen() + * + au_do_open() the body of all 'open' + * + au_do_open_nondir() + * set the passed h_file + * + * au_aopen_no_open() + * + finish_no_open() + */ + +struct aopen_node { + struct hlist_bl_node hblist; + struct file *file, *h_file; +}; + +static int au_do_aopen(struct inode *inode, struct file *file) +{ + struct hlist_bl_head *aopen; + struct hlist_bl_node *pos; + struct aopen_node *node; + struct au_do_open_args args = { + .aopen = 1, + .open = au_do_open_nondir + }; + + aopen = &au_sbi(inode->i_sb)->si_aopen; + hlist_bl_lock(aopen); + hlist_bl_for_each_entry(node, pos, aopen, hblist) + if (node->file == file) { + args.h_file = node->h_file; + break; + } + hlist_bl_unlock(aopen); + /* AuDebugOn(!args.h_file); */ + + return au_do_open(file, &args); +} + +static int au_aopen_do_open(struct file *file, struct dentry *dentry, + struct aopen_node *aopen_node) +{ + int err; + struct hlist_bl_head *aopen; + + AuLabel(here); + aopen = &au_sbi(dentry->d_sb)->si_aopen; + au_hbl_add(&aopen_node->hblist, aopen); + err = finish_open(file, dentry, au_do_aopen); + au_hbl_del(&aopen_node->hblist, aopen); + /* AuDbgFile(file); */ + AuDbg("%pd%s%s\n", dentry, + (file->f_mode & FMODE_CREATED) ? " created" : "", + (file->f_mode & FMODE_OPENED) ? " opened" : ""); + + AuTraceErr(err); + return err; +} + +static int au_aopen_no_open(struct file *file, struct dentry *dentry) +{ + int err; + + AuLabel(here); + dget(dentry); + err = finish_no_open(file, dentry); + + AuTraceErr(err); + return err; +} + +static int aufs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flag, + umode_t create_mode) +{ + int err, did_open; + unsigned int lkup_flags; + aufs_bindex_t bindex; + struct super_block *sb; + struct dentry *parent, *d; + struct vfsub_aopen_args args = { + .open_flag = open_flag, + .create_mode = create_mode + }; + struct aopen_node aopen_node = { + .file = file + }; + + IMustLock(dir); + AuDbg("open_flag 0%o\n", open_flag); + AuDbgDentry(dentry); + + err = 0; + if (!au_di(dentry)) { + lkup_flags = LOOKUP_OPEN; + if (open_flag & O_CREAT) + lkup_flags |= LOOKUP_CREATE; + d = aufs_lookup(dir, dentry, lkup_flags); + if (IS_ERR(d)) { + err = PTR_ERR(d); + AuTraceErr(err); + goto out; + } else if (d) { + /* + * obsoleted dentry found. + * another error will be returned later. + */ + d_drop(d); + AuDbgDentry(d); + dput(d); + } + AuDbgDentry(dentry); + } + + if (d_is_positive(dentry) + || d_unhashed(dentry) + || d_unlinked(dentry) + || !(open_flag & O_CREAT)) { + err = au_aopen_no_open(file, dentry); + goto out; /* success */ + } + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + parent = dentry->d_parent; /* dir is locked */ + di_write_lock_parent(parent); + err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG); + if (unlikely(err < 0)) + goto out_parent; + + AuDbgDentry(dentry); + if (d_is_positive(dentry)) { + err = au_aopen_no_open(file, dentry); + goto out_parent; /* success */ + } + + args.file = alloc_empty_file(file->f_flags, current_cred()); + err = PTR_ERR(args.file); + if (IS_ERR(args.file)) + goto out_parent; + + bindex = au_dbtop(dentry); + err = au_aopen_or_create(dir, dentry, &args); + AuTraceErr(err); + AuDbgFile(args.file); + file->f_mode = args.file->f_mode & ~FMODE_OPENED; + did_open = !!(args.file->f_mode & FMODE_OPENED); + if (!did_open) { + fput(args.file); + args.file = NULL; + } + di_write_unlock(parent); + di_write_unlock(dentry); + if (unlikely(err < 0)) { + if (args.file) + fput(args.file); + goto out_sb; + } + + if (!did_open) + err = au_aopen_no_open(file, dentry); + else { + aopen_node.h_file = args.file; + err = au_aopen_do_open(file, dentry, &aopen_node); + } + if (unlikely(err < 0)) { + if (args.file) + fput(args.file); + if (did_open) + au_lcnt_dec(&args.br->br_nfiles); + } + goto out_sb; /* success */ + +out_parent: + di_write_unlock(parent); + di_write_unlock(dentry); +out_sb: + si_read_unlock(sb); +out: + AuTraceErr(err); + AuDbgFile(file); + return err; +} + + +/* ---------------------------------------------------------------------- */ + +static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, + const unsigned char add_entry, aufs_bindex_t bcpup, + aufs_bindex_t btop) +{ + int err; + struct dentry *h_parent; + struct inode *h_dir; + + if (add_entry) + IMustLock(d_inode(parent)); + else + di_write_lock_parent(parent); + + err = 0; + if (!au_h_dptr(parent, bcpup)) { + if (btop > bcpup) + err = au_cpup_dirs(dentry, bcpup); + else if (btop < bcpup) + err = au_cpdown_dirs(dentry, bcpup); + else + BUG(); + } + if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) { + h_parent = au_h_dptr(parent, bcpup); + h_dir = d_inode(h_parent); + inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); + err = au_lkup_neg(dentry, bcpup, /*wh*/0); + /* todo: no unlock here */ + inode_unlock_shared(h_dir); + + AuDbg("bcpup %d\n", bcpup); + if (!err) { + if (d_really_is_negative(dentry)) + au_set_h_dptr(dentry, btop, NULL); + au_update_dbrange(dentry, /*do_put_zero*/0); + } + } + + if (!add_entry) + di_write_unlock(parent); + if (!err) + err = bcpup; /* success */ + + AuTraceErr(err); + return err; +} + +/* + * decide the branch and the parent dir where we will create a new entry. + * returns new bindex or an error. + * copyup the parent dir if needed. + */ +int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, + struct au_wr_dir_args *args) +{ + int err; + unsigned int flags; + aufs_bindex_t bcpup, btop, src_btop; + const unsigned char add_entry + = au_ftest_wrdir(args->flags, ADD_ENTRY) + | au_ftest_wrdir(args->flags, TMPFILE); + struct super_block *sb; + struct dentry *parent; + struct au_sbinfo *sbinfo; + + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + parent = dget_parent(dentry); + btop = au_dbtop(dentry); + bcpup = btop; + if (args->force_btgt < 0) { + if (src_dentry) { + src_btop = au_dbtop(src_dentry); + if (src_btop < btop) + bcpup = src_btop; + } else if (add_entry) { + flags = 0; + if (au_ftest_wrdir(args->flags, ISDIR)) + au_fset_wbr(flags, DIR); + err = AuWbrCreate(sbinfo, dentry, flags); + bcpup = err; + } + + if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) { + if (add_entry) + err = AuWbrCopyup(sbinfo, dentry); + else { + if (!IS_ROOT(dentry)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(sbinfo, dentry); + di_read_unlock(parent, !AuLock_IR); + } else + err = AuWbrCopyup(sbinfo, dentry); + } + bcpup = err; + if (unlikely(err < 0)) + goto out; + } + } else { + bcpup = args->force_btgt; + AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry))); + } + + AuDbg("btop %d, bcpup %d\n", btop, bcpup); + err = bcpup; + if (bcpup == btop) + goto out; /* success */ + + /* copyup the new parent into the branch we process */ + err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop); + if (err >= 0) { + if (d_really_is_negative(dentry)) { + au_set_h_dptr(dentry, btop, NULL); + au_set_dbtop(dentry, bcpup); + au_set_dbbot(dentry, bcpup); + } + AuDebugOn(add_entry + && !au_ftest_wrdir(args->flags, TMPFILE) + && !au_h_dptr(dentry, bcpup)); + } + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_pin_hdir_unlock(struct au_pin *p) +{ + if (p->hdir) + au_hn_inode_unlock(p->hdir); +} + +int au_pin_hdir_lock(struct au_pin *p) +{ + int err; + + err = 0; + if (!p->hdir) + goto out; + + /* even if an error happens later, keep this lock */ + au_hn_inode_lock_nested(p->hdir, p->lsc_hi); + + err = -EBUSY; + if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent))) + goto out; + + err = 0; + if (p->h_dentry) + err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode, + p->h_parent, p->br); + +out: + return err; +} + +int au_pin_hdir_relock(struct au_pin *p) +{ + int err, i; + struct inode *h_i; + struct dentry *h_d[] = { + p->h_dentry, + p->h_parent + }; + + err = au_pin_hdir_lock(p); + if (unlikely(err)) + goto out; + + for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) { + if (!h_d[i]) + continue; + if (d_is_positive(h_d[i])) { + h_i = d_inode(h_d[i]); + err = !h_i->i_nlink; + } + } + +out: + return err; +} + +static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task) +{ +#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER) + p->hdir->hi_inode->i_rwsem.owner = task; +#endif +} + +void au_pin_hdir_acquire_nest(struct au_pin *p) +{ + if (p->hdir) { + rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map, + p->lsc_hi, 0, NULL, _RET_IP_); + au_pin_hdir_set_owner(p, current); + } +} + +void au_pin_hdir_release(struct au_pin *p) +{ + if (p->hdir) { + au_pin_hdir_set_owner(p, p->task); + rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_); + } +} + +struct dentry *au_pinned_h_parent(struct au_pin *pin) +{ + if (pin && pin->parent) + return au_h_dptr(pin->parent, pin->bindex); + return NULL; +} + +void au_unpin(struct au_pin *p) +{ + if (p->hdir) + au_pin_hdir_unlock(p); + if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE)) + vfsub_mnt_drop_write(p->h_mnt); + if (!p->hdir) + return; + + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + iput(p->hdir->hi_inode); + dput(p->parent); + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; + /* do not clear p->task */ +} + +int au_do_pin(struct au_pin *p) +{ + int err; + struct super_block *sb; + struct inode *h_dir; + + err = 0; + sb = p->dentry->d_sb; + p->br = au_sbr(sb, p->bindex); + if (IS_ROOT(p->dentry)) { + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = au_br_mnt(p->br); + err = vfsub_mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + goto out_err; + } + } + goto out; + } + + p->h_dentry = NULL; + if (p->bindex <= au_dbbot(p->dentry)) + p->h_dentry = au_h_dptr(p->dentry, p->bindex); + + p->parent = dget_parent(p->dentry); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_lock(p->parent, AuLock_IR, p->lsc_di); + + h_dir = NULL; + p->h_parent = au_h_dptr(p->parent, p->bindex); + p->hdir = au_hi(d_inode(p->parent), p->bindex); + if (p->hdir) + h_dir = p->hdir->hi_inode; + + /* + * udba case, or + * if DI_LOCKED is not set, then p->parent may be different + * and h_parent can be NULL. + */ + if (unlikely(!p->hdir || !h_dir || !p->h_parent)) { + err = -EBUSY; + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + dput(p->parent); + p->parent = NULL; + goto out_err; + } + + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = au_br_mnt(p->br); + err = vfsub_mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + dput(p->parent); + p->parent = NULL; + goto out_err; + } + } + + au_igrab(h_dir); + err = au_pin_hdir_lock(p); + if (!err) + goto out; /* success */ + + au_unpin(p); + +out_err: + pr_err("err %d\n", err); + err = au_busy_or_stale(); +out: + return err; +} + +void au_pin_init(struct au_pin *p, struct dentry *dentry, + aufs_bindex_t bindex, int lsc_di, int lsc_hi, + unsigned int udba, unsigned char flags) +{ + p->dentry = dentry; + p->udba = udba; + p->lsc_di = lsc_di; + p->lsc_hi = lsc_hi; + p->flags = flags; + p->bindex = bindex; + + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; + + p->h_dentry = NULL; + p->h_parent = NULL; + p->br = NULL; + p->task = current; +} + +int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, + unsigned int udba, unsigned char flags) +{ + au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2, + udba, flags); + return au_do_pin(pin); +} + +/* ---------------------------------------------------------------------- */ + +/* + * ->setattr() and ->getattr() are called in various cases. + * chmod, stat: dentry is revalidated. + * fchmod, fstat: file and dentry are not revalidated, additionally they may be + * unhashed. + * for ->setattr(), ia->ia_file is passed from ftruncate only. + */ +/* todo: consolidate with do_refresh() and simple_reval_dpath() */ +int au_reval_for_attr(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *parent; + + err = 0; + if (au_digen_test(dentry, sigen)) { + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + } + + AuTraceErr(err); + return err; +} + +int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, + struct au_icpup_args *a) +{ + int err; + loff_t sz; + aufs_bindex_t btop, ibtop; + struct dentry *hi_wh, *parent; + struct inode *inode; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = 0 + }; + + if (d_is_dir(dentry)) + au_fset_wrdir(wr_dir_args.flags, ISDIR); + /* plink or hi_wh() case */ + btop = au_dbtop(dentry); + inode = d_inode(dentry); + ibtop = au_ibtop(inode); + if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode)) + wr_dir_args.force_btgt = ibtop; + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + if (unlikely(err < 0)) + goto out; + a->btgt = err; + if (err != btop) + au_fset_icpup(a->flags, DID_CPUP); + + err = 0; + a->pin_flags = AuPin_MNT_WRITE; + parent = NULL; + if (!IS_ROOT(dentry)) { + au_fset_pin(a->pin_flags, DI_LOCKED); + parent = dget_parent(dentry); + di_write_lock_parent(parent); + } + + err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); + if (unlikely(err)) + goto out_parent; + + sz = -1; + a->h_path.dentry = au_h_dptr(dentry, btop); + a->h_inode = d_inode(a->h_path.dentry); + if (ia && (ia->ia_valid & ATTR_SIZE)) { + inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); + if (ia->ia_size < i_size_read(a->h_inode)) + sz = ia->ia_size; + inode_unlock_shared(a->h_inode); + } + + hi_wh = NULL; + if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) { + hi_wh = au_hi_wh(inode, a->btgt); + if (!hi_wh) { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->btgt, + .bsrc = -1, + .len = sz, + .pin = &a->pin + }; + err = au_sio_cpup_wh(&cpg, /*file*/NULL); + if (unlikely(err)) + goto out_unlock; + hi_wh = au_hi_wh(inode, a->btgt); + /* todo: revalidate hi_wh? */ + } + } + + if (parent) { + au_pin_set_parent_lflag(&a->pin, /*lflag*/0); + di_downgrade_lock(parent, AuLock_IR); + dput(parent); + parent = NULL; + } + if (!au_ftest_icpup(a->flags, DID_CPUP)) + goto out; /* success */ + + if (!d_unhashed(dentry)) { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->btgt, + .bsrc = btop, + .len = sz, + .pin = &a->pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN + }; + err = au_sio_cpup_simple(&cpg); + if (!err) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + } else if (!hi_wh) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + else + a->h_path.dentry = hi_wh; /* do not dget here */ + +out_unlock: + a->h_inode = d_inode(a->h_path.dentry); + if (!err) + goto out; /* success */ + au_unpin(&a->pin); +out_parent: + if (parent) { + di_write_unlock(parent); + dput(parent); + } +out: + if (!err) + inode_lock_nested(a->h_inode, AuLsc_I_CHILD); + return err; +} + +static int aufs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; + struct inode *inode, *delegated; + struct super_block *sb; + struct file *file; + struct au_icpup_args *a; + + inode = d_inode(dentry); + IMustLock(inode); + + err = setattr_prepare(dentry, ia); + if (unlikely(err)) + goto out; + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + ia->ia_valid &= ~ATTR_MODE; + + file = NULL; + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_kfree; + + if (ia->ia_valid & ATTR_FILE) { + /* currently ftruncate(2) only */ + AuDebugOn(!d_is_reg(dentry)); + file = ia->ia_file; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, + /*fi_lsc*/0); + if (unlikely(err)) + goto out_si; + ia->ia_file = au_hf_top(file); + a->udba = AuOpt_UDBA_NONE; + } else { + /* fchmod() doesn't pass ia_file */ + a->udba = au_opt_udba(sb); + di_write_lock_child(dentry); + /* no d_unlinked(), to set UDBA_NONE for root */ + if (d_unhashed(dentry)) + a->udba = AuOpt_UDBA_NONE; + if (a->udba != AuOpt_UDBA_NONE) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out_dentry; + } + } + + err = au_pin_and_icpup(dentry, ia, a); + if (unlikely(err < 0)) + goto out_dentry; + if (au_ftest_icpup(a->flags, DID_CPUP)) { + ia->ia_file = NULL; + ia->ia_valid &= ~ATTR_FILE; + } + + a->h_path.mnt = au_sbr_mnt(sb, a->btgt); + if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME)) + == (ATTR_MODE | ATTR_CTIME)) { + err = security_path_chmod(&a->h_path, ia->ia_mode); + if (unlikely(err)) + goto out_unlock; + } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID)) + && (ia->ia_valid & ATTR_CTIME)) { + err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid); + if (unlikely(err)) + goto out_unlock; + } + + if (ia->ia_valid & ATTR_SIZE) { + struct file *f; + + if (ia->ia_size < i_size_read(inode)) + /* unmap only */ + truncate_setsize(inode, ia->ia_size); + + f = NULL; + if (ia->ia_valid & ATTR_FILE) + f = ia->ia_file; + inode_unlock(a->h_inode); + err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); + inode_lock_nested(a->h_inode, AuLsc_I_CHILD); + } else { + delegated = NULL; + while (1) { + err = vfsub_notify_change(&a->h_path, ia, &delegated); + if (delegated) { + err = break_deleg_wait(&delegated); + if (!err) + continue; + } + break; + } + } + /* + * regardless aufs 'acl' option setting. + * why don't all acl-aware fs call this func from their ->setattr()? + */ + if (!err && (ia->ia_valid & ATTR_MODE)) + err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); + if (!err) + au_cpup_attr_changeable(inode); + +out_unlock: + inode_unlock(a->h_inode); + au_unpin(&a->pin); + if (unlikely(err)) + au_update_dbtop(dentry); +out_dentry: + di_write_unlock(dentry); + if (file) { + fi_write_unlock(file); + ia->ia_file = file; + ia->ia_valid |= ATTR_FILE; + } +out_si: + si_read_unlock(sb); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} + +#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) +static int au_h_path_to_set_attr(struct dentry *dentry, + struct au_icpup_args *a, struct path *h_path) +{ + int err; + struct super_block *sb; + + sb = dentry->d_sb; + a->udba = au_opt_udba(sb); + /* no d_unlinked(), to set UDBA_NONE for root */ + if (d_unhashed(dentry)) + a->udba = AuOpt_UDBA_NONE; + if (a->udba != AuOpt_UDBA_NONE) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out; + } + err = au_pin_and_icpup(dentry, /*ia*/NULL, a); + if (unlikely(err < 0)) + goto out; + + h_path->dentry = a->h_path.dentry; + h_path->mnt = au_sbr_mnt(sb, a->btgt); + +out: + return err; +} + +ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, + struct au_sxattr *arg) +{ + int err; + struct path h_path; + struct super_block *sb; + struct au_icpup_args *a; + struct inode *h_inode; + + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_kfree; + + h_path.dentry = NULL; /* silence gcc */ + di_write_lock_child(dentry); + err = au_h_path_to_set_attr(dentry, a, &h_path); + if (unlikely(err)) + goto out_di; + + inode_unlock(a->h_inode); + switch (arg->type) { + case AU_XATTR_SET: + AuDebugOn(d_is_negative(h_path.dentry)); + err = vfsub_setxattr(h_path.dentry, + arg->u.set.name, arg->u.set.value, + arg->u.set.size, arg->u.set.flags); + break; + case AU_ACL_SET: + err = -EOPNOTSUPP; + h_inode = d_inode(h_path.dentry); + if (h_inode->i_op->set_acl) + /* this will call posix_acl_update_mode */ + err = h_inode->i_op->set_acl(h_inode, + arg->u.acl_set.acl, + arg->u.acl_set.type); + break; + } + if (!err) + au_cpup_attr_timesizes(inode); + + au_unpin(&a->pin); + if (unlikely(err)) + au_update_dbtop(dentry); + +out_di: + di_write_unlock(dentry); + si_read_unlock(sb); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} +#endif + +static void au_refresh_iattr(struct inode *inode, struct kstat *st, + unsigned int nlink) +{ + unsigned int n; + + inode->i_mode = st->mode; + /* don't i_[ug]id_write() here */ + inode->i_uid = st->uid; + inode->i_gid = st->gid; + inode->i_atime = st->atime; + inode->i_mtime = st->mtime; + inode->i_ctime = st->ctime; + + au_cpup_attr_nlink(inode, /*force*/0); + if (S_ISDIR(inode->i_mode)) { + n = inode->i_nlink; + n -= nlink; + n += st->nlink; + smp_mb(); /* for i_nlink */ + /* 0 can happen */ + set_nlink(inode, n); + } + + spin_lock(&inode->i_lock); + inode->i_blocks = st->blocks; + i_size_write(inode, st->size); + spin_unlock(&inode->i_lock); +} + +/* + * common routine for aufs_getattr() and au_getxattr(). + * returns zero or negative (an error). + * @dentry will be read-locked in success. + */ +int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path, + int locked) +{ + int err; + unsigned int mnt_flags, sigen; + unsigned char udba_none; + aufs_bindex_t bindex; + struct super_block *sb, *h_sb; + struct inode *inode; + + h_path->mnt = NULL; + h_path->dentry = NULL; + + err = 0; + sb = dentry->d_sb; + mnt_flags = au_mntflags(sb); + udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); + + if (unlikely(locked)) + goto body; /* skip locking dinfo */ + + /* support fstat(2) */ + if (!d_unlinked(dentry) && !udba_none) { + sigen = au_sigen(sb); + err = au_digen_test(dentry, sigen); + if (!err) { + di_read_lock_child(dentry, AuLock_IR); + err = au_dbrange_test(dentry); + if (unlikely(err)) { + di_read_unlock(dentry, AuLock_IR); + goto out; + } + } else { + AuDebugOn(IS_ROOT(dentry)); + di_write_lock_child(dentry); + err = au_dbrange_test(dentry); + if (!err) + err = au_reval_for_attr(dentry, sigen); + if (!err) + di_downgrade_lock(dentry, AuLock_IR); + else { + di_write_unlock(dentry); + goto out; + } + } + } else + di_read_lock_child(dentry, AuLock_IR); + +body: + inode = d_inode(dentry); + bindex = au_ibtop(inode); + h_path->mnt = au_sbr_mnt(sb, bindex); + h_sb = h_path->mnt->mnt_sb; + if (!force + && !au_test_fs_bad_iattr(h_sb) + && udba_none) + goto out; /* success */ + + if (au_dbtop(dentry) == bindex) + h_path->dentry = au_h_dptr(dentry, bindex); + else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { + h_path->dentry = au_plink_lkup(inode, bindex); + if (IS_ERR(h_path->dentry)) + /* pretending success */ + h_path->dentry = NULL; + else + dput(h_path->dentry); + } + +out: + return err; +} + +static int aufs_getattr(const struct path *path, struct kstat *st, + u32 request, unsigned int query) +{ + int err; + unsigned char positive; + struct path h_path; + struct dentry *dentry; + struct inode *inode; + struct super_block *sb; + + dentry = path->dentry; + inode = d_inode(dentry); + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + err = au_h_path_getattr(dentry, /*force*/0, &h_path, /*locked*/0); + if (unlikely(err)) + goto out_si; + if (unlikely(!h_path.dentry)) + /* illegally overlapped or something */ + goto out_fill; /* pretending success */ + + positive = d_is_positive(h_path.dentry); + if (positive) + /* no vfsub version */ + err = vfs_getattr(&h_path, st, request, query); + if (!err) { + if (positive) + au_refresh_iattr(inode, st, + d_inode(h_path.dentry)->i_nlink); + goto out_fill; /* success */ + } + AuTraceErr(err); + goto out_di; + +out_fill: + generic_fillattr(inode, st); +out_di: + di_read_unlock(dentry, AuLock_IR); +out_si: + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static const char *aufs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + const char *ret; + struct dentry *h_dentry; + struct inode *h_inode; + int err; + aufs_bindex_t bindex; + + ret = NULL; /* suppress a warning */ + err = -ECHILD; + if (!dentry) + goto out; + + err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); + if (unlikely(err)) + goto out; + + err = au_d_hashed_positive(dentry); + if (unlikely(err)) + goto out_unlock; + + err = -EINVAL; + inode = d_inode(dentry); + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (unlikely(!h_inode->i_op->get_link)) + goto out_unlock; + + err = -EBUSY; + h_dentry = NULL; + if (au_dbtop(dentry) <= bindex) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) + dget(h_dentry); + } + if (!h_dentry) { + h_dentry = d_find_any_alias(h_inode); + if (IS_ERR(h_dentry)) { + err = PTR_ERR(h_dentry); + goto out_unlock; + } + } + if (unlikely(!h_dentry)) + goto out_unlock; + + err = 0; + AuDbg("%ps\n", h_inode->i_op->get_link); + AuDbgDentry(h_dentry); + ret = vfs_get_link(h_dentry, done); + dput(h_dentry); + if (IS_ERR(ret)) + err = PTR_ERR(ret); + +out_unlock: + aufs_read_unlock(dentry, AuLock_IR); +out: + if (unlikely(err)) + ret = ERR_PTR(err); + AuTraceErrPtr(ret); + return ret; +} + +/* ---------------------------------------------------------------------- */ + +static int au_is_special(struct inode *inode) +{ + return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK)); +} + +static int aufs_update_time(struct inode *inode, struct timespec64 *ts, + int flags) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct inode *h_inode; + struct vfsmount *h_mnt; + + sb = inode->i_sb; + WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode), + "unexpected s_flags 0x%lx", sb->s_flags); + + /* mmap_sem might be acquired already, cf. aufs_mmap() */ + lockdep_off(); + si_read_lock(sb, AuLock_FLUSH); + ii_write_lock_child(inode); + + err = 0; + bindex = au_ibtop(inode); + h_inode = au_h_iptr(inode, bindex); + if (!au_test_ro(sb, bindex, inode)) { + h_mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mnt_want_write(h_mnt); + if (!err) { + err = vfsub_update_time(h_inode, ts, flags); + vfsub_mnt_drop_write(h_mnt); + } + } else if (au_is_special(h_inode)) { + /* + * Never copy-up here. + * These special files may already be opened and used for + * communicating. If we copied it up, then the communication + * would be corrupted. + */ + AuWarn1("timestamps for i%lu are ignored " + "since it is on readonly branch (hi%lu).\n", + inode->i_ino, h_inode->i_ino); + } else if (flags & ~S_ATIME) { + err = -EIO; + AuIOErr1("unexpected flags 0x%x\n", flags); + AuDebugOn(1); + } + + if (!err) + au_cpup_attr_timesizes(inode); + ii_write_unlock(inode); + si_read_unlock(sb); + lockdep_on(); + + if (!err && (flags & S_VERSION)) + inode_inc_iversion(inode); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* no getattr version will be set by module.c:aufs_init() */ +struct inode_operations aufs_iop_nogetattr[AuIop_Last], + aufs_iop[] = { + [AuIop_SYMLINK] = { + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, /* unsupport for symlink? */ +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .get_link = aufs_get_link, + + /* .update_time = aufs_update_time */ + }, + [AuIop_DIR] = { + .create = aufs_create, + .lookup = aufs_lookup, + .link = aufs_link, + .unlink = aufs_unlink, + .symlink = aufs_symlink, + .mkdir = aufs_mkdir, + .rmdir = aufs_rmdir, + .mknod = aufs_mknod, + .rename = aufs_rename, + + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .update_time = aufs_update_time, + .atomic_open = aufs_atomic_open, + .tmpfile = aufs_tmpfile + }, + [AuIop_OTHER] = { + .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL + .get_acl = aufs_get_acl, + .set_acl = aufs_set_acl, +#endif + + .setattr = aufs_setattr, + .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR + .listxattr = aufs_listxattr, +#endif + + .update_time = aufs_update_time + } +}; diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c new file mode 100644 index 000000000000..af6893e61066 --- /dev/null +++ b/fs/aufs/i_op_add.c @@ -0,0 +1,936 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (add entry) + */ + +#include <linux/iversion.h> +#include "aufs.h" + +/* + * final procedure of adding a new entry, except link(2). + * remove whiteout, instantiate, copyup the parent dir's times and size + * and update version. + * if it failed, re-create the removed whiteout. + */ +static int epilog(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct dentry *dentry) +{ + int err, rerr; + aufs_bindex_t bwh; + struct path h_path; + struct super_block *sb; + struct inode *inode, *h_dir; + struct dentry *wh; + + bwh = -1; + sb = dir->i_sb; + if (wh_dentry) { + h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */ + IMustLock(h_dir); + AuDebugOn(au_h_iptr(dir, bindex) != h_dir); + bwh = au_dbwh(dentry); + h_path.dentry = wh_dentry; + h_path.mnt = au_sbr_mnt(sb, bindex); + err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, + dentry); + if (unlikely(err)) + goto out; + } + + inode = au_new_inode(dentry, /*must_new*/1); + if (!IS_ERR(inode)) { + d_instantiate(dentry, inode); + dir = d_inode(dentry->d_parent); /* dir inode is locked */ + IMustLock(dir); + au_dir_ts(dir, bindex); + inode_inc_iversion(dir); + au_fhsm_wrote(sb, bindex, /*force*/0); + return 0; /* success */ + } + + err = PTR_ERR(inode); + if (!wh_dentry) + goto out; + + /* revert */ + /* dir inode is locked */ + wh = au_wh_create(dentry, bwh, wh_dentry->d_parent); + rerr = PTR_ERR(wh); + if (IS_ERR(wh)) { + AuIOErr("%pd reverting whiteout failed(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } else + dput(wh); + +out: + return err; +} + +static int au_d_may_add(struct dentry *dentry) +{ + int err; + + err = 0; + if (unlikely(d_unhashed(dentry))) + err = -ENOENT; + if (unlikely(d_really_is_positive(dentry))) + err = -EEXIST; + return err; +} + +/* + * simple tests for the adding inode operations. + * following the checks in vfs, plus the parent-child relationship. + */ +int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir) +{ + int err; + umode_t h_mode; + struct dentry *h_dentry; + struct inode *h_inode; + + err = -ENAMETOOLONG; + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out; + + h_dentry = au_h_dptr(dentry, bindex); + if (d_really_is_negative(dentry)) { + err = -EEXIST; + if (unlikely(d_is_positive(h_dentry))) + goto out; + } else { + /* rename(2) case */ + err = -EIO; + if (unlikely(d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); + if (unlikely(!h_inode->i_nlink)) + goto out; + + h_mode = h_inode->i_mode; + if (!isdir) { + err = -EISDIR; + if (unlikely(S_ISDIR(h_mode))) + goto out; + } else if (unlikely(!S_ISDIR(h_mode))) { + err = -ENOTDIR; + goto out; + } + } + + err = 0; + /* expected parent dir is locked */ + if (unlikely(h_parent != h_dentry->d_parent)) + err = -EIO; + +out: + AuTraceErr(err); + return err; +} + +/* + * initial procedure of adding a new entry. + * prepare writable branch and the parent dir, lock it, + * and lookup whiteout for the new entry. + */ +static struct dentry* +lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt, + struct dentry *src_dentry, struct au_pin *pin, + struct au_wr_dir_args *wr_dir_args) +{ + struct dentry *wh_dentry, *h_parent; + struct super_block *sb; + struct au_branch *br; + int err; + unsigned int udba; + aufs_bindex_t bcpup; + + AuDbg("%pd\n", dentry); + + err = au_wr_dir(dentry, src_dentry, wr_dir_args); + bcpup = err; + wh_dentry = ERR_PTR(err); + if (unlikely(err < 0)) + goto out; + + sb = dentry->d_sb; + udba = au_opt_udba(sb); + err = au_pin(pin, dentry, bcpup, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out; + + h_parent = au_pinned_h_parent(pin); + if (udba != AuOpt_UDBA_NONE + && au_dbtop(dentry) == bcpup) + err = au_may_add(dentry, bcpup, h_parent, + au_ftest_wrdir(wr_dir_args->flags, ISDIR)); + else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + err = -ENAMETOOLONG; + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_unpin; + + br = au_sbr(sb, bcpup); + if (dt) { + struct path tmp = { + .dentry = h_parent, + .mnt = au_br_mnt(br) + }; + au_dtime_store(dt, au_pinned_parent(pin), &tmp); + } + + wh_dentry = NULL; + if (bcpup != au_dbwh(dentry)) + goto out; /* success */ + + /* + * ENAMETOOLONG here means that if we allowed create such name, then it + * would not be able to removed in the future. So we don't allow such + * name here and we don't handle ENAMETOOLONG differently here. + */ + wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br); + +out_unpin: + if (IS_ERR(wh_dentry)) + au_unpin(pin); +out: + return wh_dentry; +} + +/* ---------------------------------------------------------------------- */ + +enum { Mknod, Symlink, Creat }; +struct simple_arg { + int type; + union { + struct { + umode_t mode; + bool want_excl; + bool try_aopen; + struct vfsub_aopen_args *aopen; + } c; + struct { + const char *symname; + } s; + struct { + umode_t mode; + dev_t dev; + } m; + } u; +}; + +static int add_simple(struct inode *dir, struct dentry *dentry, + struct simple_arg *arg) +{ + int err, rerr; + aufs_bindex_t btop; + unsigned char created; + const unsigned char try_aopen + = (arg->type == Creat && arg->u.c.try_aopen); + struct vfsub_aopen_args *aopen = arg->u.c.aopen; + struct dentry *wh_dentry, *parent; + struct inode *h_dir; + struct super_block *sb; + struct au_branch *br; + /* to reduce stack size */ + struct { + struct au_dtime dt; + struct au_pin pin; + struct path h_path; + struct au_wr_dir_args wr_dir_args; + } *a; + + AuDbg("%pd\n", dentry); + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + a->wr_dir_args.force_btgt = -1; + a->wr_dir_args.flags = AuWrDir_ADD_ENTRY; + + parent = dentry->d_parent; /* dir inode is locked */ + if (!try_aopen) { + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + } + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + if (!try_aopen) + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, + &a->pin, &a->wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + btop = au_dbtop(dentry); + sb = dentry->d_sb; + br = au_sbr(sb, btop); + a->h_path.dentry = au_h_dptr(dentry, btop); + a->h_path.mnt = au_br_mnt(br); + h_dir = au_pinned_h_dir(&a->pin); + switch (arg->type) { + case Creat: + if (!try_aopen || !h_dir->i_op->atomic_open) { + err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode, + arg->u.c.want_excl); + created = !err; + if (!err && try_aopen) + aopen->file->f_mode |= FMODE_CREATED; + } else { + aopen->br = br; + err = vfsub_atomic_open(h_dir, a->h_path.dentry, aopen); + AuDbg("err %d\n", err); + AuDbgFile(aopen->file); + created = err >= 0 + && !!(aopen->file->f_mode & FMODE_CREATED); + } + break; + case Symlink: + err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname); + created = !err; + break; + case Mknod: + err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode, + arg->u.m.dev); + created = !err; + break; + default: + BUG(); + } + if (unlikely(err < 0)) + goto out_unpin; + + err = epilog(dir, btop, wh_dentry, dentry); + if (!err) + goto out_unpin; /* success */ + + /* revert */ + if (created /* && d_is_positive(a->h_path.dentry) */) { + /* no delegation since it is just created */ + rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL, + /*force*/0); + if (rerr) { + AuIOErr("%pd revert failure(%d, %d)\n", + dentry, err, rerr); + err = -EIO; + } + au_dtime_revert(&a->dt); + } + if (try_aopen && h_dir->i_op->atomic_open + && (aopen->file->f_mode & FMODE_OPENED)) + /* aopen->file is still opened */ + au_lcnt_dec(&aopen->br->br_nfiles); + +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); +out_parent: + if (!try_aopen) + di_write_unlock(parent); +out_unlock: + if (unlikely(err)) { + au_update_dbtop(dentry); + d_drop(dentry); + } + if (!try_aopen) + aufs_read_unlock(dentry, AuLock_DW); +out_free: + au_kfree_rcu(a); +out: + return err; +} + +int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t dev) +{ + struct simple_arg arg = { + .type = Mknod, + .u.m = { + .mode = mode, + .dev = dev + } + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + struct simple_arg arg = { + .type = Symlink, + .u.s.symname = symname + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool want_excl) +{ + struct simple_arg arg = { + .type = Creat, + .u.c = { + .mode = mode, + .want_excl = want_excl + } + }; + return add_simple(dir, dentry, &arg); +} + +int au_aopen_or_create(struct inode *dir, struct dentry *dentry, + struct vfsub_aopen_args *aopen_args) +{ + struct simple_arg arg = { + .type = Creat, + .u.c = { + .mode = aopen_args->create_mode, + .want_excl = aopen_args->open_flag & O_EXCL, + .try_aopen = true, + .aopen = aopen_args + } + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct dentry *parent, *h_parent, *h_dentry; + struct inode *h_dir, *inode; + struct vfsmount *h_mnt; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_TMPFILE + }; + + /* copy-up may happen */ + inode_lock(dir); + + sb = dir->i_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + + err = au_di_init(dentry); + if (unlikely(err)) + goto out_si; + + err = -EBUSY; + parent = d_find_any_alias(dir); + AuDebugOn(!parent); + di_write_lock_parent(parent); + if (unlikely(d_inode(parent) != dir)) + goto out_parent; + + err = au_digen_test(parent, au_sigen(sb)); + if (unlikely(err)) + goto out_parent; + + bindex = au_dbtop(parent); + au_set_dbtop(dentry, bindex); + au_set_dbbot(dentry, bindex); + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + bindex = err; + if (unlikely(err < 0)) + goto out_parent; + + err = -EOPNOTSUPP; + h_dir = au_h_iptr(dir, bindex); + if (unlikely(!h_dir->i_op->tmpfile)) + goto out_parent; + + h_mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mnt_want_write(h_mnt); + if (unlikely(err)) + goto out_parent; + + h_parent = au_h_dptr(parent, bindex); + h_dentry = vfs_tmpfile(h_parent, mode, /*open_flag*/0); + if (IS_ERR(h_dentry)) { + err = PTR_ERR(h_dentry); + goto out_mnt; + } + + au_set_dbtop(dentry, bindex); + au_set_dbbot(dentry, bindex); + au_set_h_dptr(dentry, bindex, dget(h_dentry)); + inode = au_new_inode(dentry, /*must_new*/1); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + au_set_h_dptr(dentry, bindex, NULL); + au_set_dbtop(dentry, -1); + au_set_dbbot(dentry, -1); + } else { + if (!inode->i_nlink) + set_nlink(inode, 1); + d_tmpfile(dentry, inode); + au_di(dentry)->di_tmpfile = 1; + + /* update without i_mutex */ + if (au_ibtop(dir) == au_dbtop(dentry)) + au_cpup_attr_timesizes(dir); + } + dput(h_dentry); + +out_mnt: + vfsub_mnt_drop_write(h_mnt); +out_parent: + di_write_unlock(parent); + dput(parent); + di_write_unlock(dentry); + if (unlikely(err)) { + au_di_fin(dentry); + dentry->d_fsdata = NULL; + } +out_si: + si_read_unlock(sb); +out: + inode_unlock(dir); + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct au_link_args { + aufs_bindex_t bdst, bsrc; + struct au_pin pin; + struct path h_path; + struct dentry *src_parent, *parent; +}; + +static int au_cpup_before_link(struct dentry *src_dentry, + struct au_link_args *a) +{ + int err; + struct dentry *h_src_dentry; + struct au_cp_generic cpg = { + .dentry = src_dentry, + .bdst = a->bdst, + .bsrc = a->bsrc, + .len = -1, + .pin = &a->pin, + .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */ + }; + + di_read_lock_parent(a->src_parent, AuLock_IR); + err = au_test_and_cpup_dirs(src_dentry, a->bdst); + if (unlikely(err)) + goto out; + + h_src_dentry = au_h_dptr(src_dentry, a->bsrc); + err = au_pin(&a->pin, src_dentry, a->bdst, + au_opt_udba(src_dentry->d_sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out; + + err = au_sio_cpup_simple(&cpg); + au_unpin(&a->pin); + +out: + di_read_unlock(a->src_parent, AuLock_IR); + return err; +} + +static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry, + struct au_link_args *a) +{ + int err; + unsigned char plink; + aufs_bindex_t bbot; + struct dentry *h_src_dentry; + struct inode *h_inode, *inode, *delegated; + struct super_block *sb; + struct file *h_file; + + plink = 0; + h_inode = NULL; + sb = src_dentry->d_sb; + inode = d_inode(src_dentry); + if (au_ibtop(inode) <= a->bdst) + h_inode = au_h_iptr(inode, a->bdst); + if (!h_inode || !h_inode->i_nlink) { + /* copyup src_dentry as the name of dentry. */ + bbot = au_dbbot(dentry); + if (bbot < a->bsrc) + au_set_dbbot(dentry, a->bsrc); + au_set_h_dptr(dentry, a->bsrc, + dget(au_h_dptr(src_dentry, a->bsrc))); + dget(a->h_path.dentry); + au_set_h_dptr(dentry, a->bdst, NULL); + AuDbg("temporary d_inode...\n"); + spin_lock(&dentry->d_lock); + dentry->d_inode = d_inode(src_dentry); /* tmp */ + spin_unlock(&dentry->d_lock); + h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0); + if (IS_ERR(h_file)) + err = PTR_ERR(h_file); + else { + struct au_cp_generic cpg = { + .dentry = dentry, + .bdst = a->bdst, + .bsrc = -1, + .len = -1, + .pin = &a->pin, + .flags = AuCpup_KEEPLINO + }; + err = au_sio_cpup_simple(&cpg); + au_h_open_post(dentry, a->bsrc, h_file); + if (!err) { + dput(a->h_path.dentry); + a->h_path.dentry = au_h_dptr(dentry, a->bdst); + } else + au_set_h_dptr(dentry, a->bdst, + a->h_path.dentry); + } + spin_lock(&dentry->d_lock); + dentry->d_inode = NULL; /* restore */ + spin_unlock(&dentry->d_lock); + AuDbg("temporary d_inode...done\n"); + au_set_h_dptr(dentry, a->bsrc, NULL); + au_set_dbbot(dentry, bbot); + } else { + /* the inode of src_dentry already exists on a.bdst branch */ + h_src_dentry = d_find_alias(h_inode); + if (!h_src_dentry && au_plink_test(inode)) { + plink = 1; + h_src_dentry = au_plink_lkup(inode, a->bdst); + err = PTR_ERR(h_src_dentry); + if (IS_ERR(h_src_dentry)) + goto out; + + if (unlikely(d_is_negative(h_src_dentry))) { + dput(h_src_dentry); + h_src_dentry = NULL; + } + + } + if (h_src_dentry) { + delegated = NULL; + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + dput(h_src_dentry); + } else { + AuIOErr("no dentry found for hi%lu on b%d\n", + h_inode->i_ino, a->bdst); + err = -EIO; + } + } + + if (!err && !plink) + au_plink_append(inode, a->bdst, a->h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +int aufs_link(struct dentry *src_dentry, struct inode *dir, + struct dentry *dentry) +{ + int err, rerr; + struct au_dtime dt; + struct au_link_args *a; + struct dentry *wh_dentry, *h_src_dentry; + struct inode *inode, *delegated; + struct super_block *sb; + struct au_wr_dir_args wr_dir_args = { + /* .force_btgt = -1, */ + .flags = AuWrDir_ADD_ENTRY + }; + + IMustLock(dir); + inode = d_inode(src_dentry); + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + a->parent = dentry->d_parent; /* dir inode is locked */ + err = aufs_read_and_write_lock2(dentry, src_dentry, + AuLock_NOPLM | AuLock_GEN); + if (unlikely(err)) + goto out_kfree; + err = au_d_linkable(src_dentry); + if (unlikely(err)) + goto out_unlock; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + a->src_parent = dget_parent(src_dentry); + wr_dir_args.force_btgt = au_ibtop(inode); + + di_write_lock_parent(a->parent); + wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt); + wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin, + &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + err = 0; + sb = dentry->d_sb; + a->bdst = au_dbtop(dentry); + a->h_path.dentry = au_h_dptr(dentry, a->bdst); + a->h_path.mnt = au_sbr_mnt(sb, a->bdst); + a->bsrc = au_ibtop(inode); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + if (!h_src_dentry && au_di(src_dentry)->di_tmpfile) + h_src_dentry = dget(au_hi_wh(inode, a->bsrc)); + if (!h_src_dentry) { + a->bsrc = au_dbtop(src_dentry); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + AuDebugOn(!h_src_dentry); + } else if (IS_ERR(h_src_dentry)) { + err = PTR_ERR(h_src_dentry); + goto out_parent; + } + + /* + * aufs doesn't touch the credential so + * security_dentry_create_files_as() is unnecessary. + */ + if (au_opt_test(au_mntflags(sb), PLINK)) { + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) + err = au_cpup_or_link(src_dentry, dentry, a); + else { + delegated = NULL; + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + } + dput(h_src_dentry); + } else { + /* + * copyup src_dentry to the branch we process, + * and then link(2) to it. + */ + dput(h_src_dentry); + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) { + au_unpin(&a->pin); + di_write_unlock(a->parent); + err = au_cpup_before_link(src_dentry, a); + di_write_lock_parent(a->parent); + if (!err) + err = au_pin(&a->pin, dentry, a->bdst, + au_opt_udba(sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_wh; + } + if (!err) { + h_src_dentry = au_h_dptr(src_dentry, a->bdst); + err = -ENOENT; + if (h_src_dentry && d_is_positive(h_src_dentry)) { + delegated = NULL; + err = vfsub_link(h_src_dentry, + au_pinned_h_dir(&a->pin), + &a->h_path, &delegated); + if (unlikely(err == -EWOULDBLOCK)) { + pr_warn("cannot retry" + " for NFSv4 delegation" + " for an internal link\n"); + iput(delegated); + } + } + } + } + if (unlikely(err)) + goto out_unpin; + + if (wh_dentry) { + a->h_path.dentry = wh_dentry; + err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path, + dentry); + if (unlikely(err)) + goto out_revert; + } + + au_dir_ts(dir, a->bdst); + inode_inc_iversion(dir); + inc_nlink(inode); + inode->i_ctime = dir->i_ctime; + d_instantiate(dentry, au_igrab(inode)); + if (d_unhashed(a->h_path.dentry)) + /* some filesystem calls d_drop() */ + d_drop(dentry); + /* some filesystems consume an inode even hardlink */ + au_fhsm_wrote(sb, a->bdst, /*force*/0); + goto out_unpin; /* success */ + +out_revert: + /* no delegation since it is just created */ + rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, + /*delegated*/NULL, /*force*/0); + if (unlikely(rerr)) { + AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr); + err = -EIO; + } + au_dtime_revert(&dt); +out_unpin: + au_unpin(&a->pin); +out_wh: + dput(wh_dentry); +out_parent: + di_write_unlock(a->parent); + dput(a->src_parent); +out_unlock: + if (unlikely(err)) { + au_update_dbtop(dentry); + d_drop(dentry); + } + aufs_read_and_write_unlock2(dentry, src_dentry); +out_kfree: + au_kfree_rcu(a); +out: + AuTraceErr(err); + return err; +} + +int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err, rerr; + aufs_bindex_t bindex; + unsigned char diropq; + struct path h_path; + struct dentry *wh_dentry, *parent, *opq_dentry; + struct inode *h_inode; + struct super_block *sb; + struct { + struct au_pin pin; + struct au_dtime dt; + } *a; /* reduce the stack usage */ + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR + }; + + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, + &a->pin, &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + sb = dentry->d_sb; + bindex = au_dbtop(dentry); + h_path.dentry = au_h_dptr(dentry, bindex); + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode); + if (unlikely(err)) + goto out_unpin; + + /* make the dir opaque */ + diropq = 0; + h_inode = d_inode(h_path.dentry); + if (wh_dentry + || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) { + inode_lock_nested(h_inode, AuLsc_I_CHILD); + opq_dentry = au_diropq_create(dentry, bindex); + inode_unlock(h_inode); + err = PTR_ERR(opq_dentry); + if (IS_ERR(opq_dentry)) + goto out_dir; + dput(opq_dentry); + diropq = 1; + } + + err = epilog(dir, bindex, wh_dentry, dentry); + if (!err) { + inc_nlink(dir); + goto out_unpin; /* success */ + } + + /* revert */ + if (diropq) { + 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..1c459dbea5db --- /dev/null +++ b/fs/aufs/i_op_del.c @@ -0,0 +1,513 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations (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..91aa66594a42 --- /dev/null +++ b/fs/aufs/i_op_ren.c @@ -0,0 +1,1250 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode 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 + 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..098fd115052a --- /dev/null +++ b/fs/aufs/iinfo.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode 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..985377d9bf66 --- /dev/null +++ b/fs/aufs/inode.c @@ -0,0 +1,529 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode 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; + 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..e387ef16e999 --- /dev/null +++ b/fs/aufs/inode.h @@ -0,0 +1,698 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * inode operations + */ + +#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], + 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, 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..fb2fb758283e --- /dev/null +++ b/fs/aufs/ioctl.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..d8508f875f28 --- /dev/null +++ b/fs/aufs/lcnt.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..bfcb9f994c2d --- /dev/null +++ b/fs/aufs/loop.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..7fc394e72d75 --- /dev/null +++ b/fs/aufs/loop.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..295736adfc3c --- /dev/null +++ b/fs/aufs/module.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..3036754b90d0 --- /dev/null +++ b/fs/aufs/module.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..cbac849ead31 --- /dev/null +++ b/fs/aufs/mvdown.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2011-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, 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..c92ca14574ff --- /dev/null +++ b/fs/aufs/opts.c @@ -0,0 +1,1877 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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); + 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; + case Opt_prepend: + opt->add.bindex = 0; + 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 + 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..6326b54340c7 --- /dev/null +++ b/fs/aufs/opts.h @@ -0,0 +1,225 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..718edb8827a3 --- /dev/null +++ b/fs/aufs/plink.c @@ -0,0 +1,516 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..c48c6cb6491f --- /dev/null +++ b/fs/aufs/poll.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..67a4bbffdf5f --- /dev/null +++ b/fs/aufs/posix_acl.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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_OR_NULL(acl)) + 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); + dput(dentry); + err = ssz; + if (ssz >= 0) { + err = 0; + set_cached_acl(inode, type, acl); + } + +out: + return err; +} diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c new file mode 100644 index 000000000000..582dd486fcd3 --- /dev/null +++ b/fs/aufs/procfs.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2010-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 file_operations au_procfs_plm_fop = { + .write = au_procfs_plm_write, + .release = au_procfs_plm_release, + .owner = THIS_MODULE +}; + +/* ---------------------------------------------------------------------- */ + +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_fop); + 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..3805e79627eb --- /dev/null +++ b/fs/aufs/rdu.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..2f8988fa1bda --- /dev/null +++ b/fs/aufs/rwsem.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..500a920b4ea1 --- /dev/null +++ b/fs/aufs/sbinfo.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..44ee4685b218 --- /dev/null +++ b/fs/aufs/super.c @@ -0,0 +1,1047 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 + 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..37f02bb21324 --- /dev/null +++ b/fs/aufs/super.h @@ -0,0 +1,589 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 */ + 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..32a0811c54de --- /dev/null +++ b/fs/aufs/sysaufs.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..195fe279b820 --- /dev/null +++ b/fs/aufs/sysaufs.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..eda987628dbb --- /dev/null +++ b/fs/aufs/sysfs.c @@ -0,0 +1,374 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..db10ec528f5d --- /dev/null +++ b/fs/aufs/sysrq.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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; + + 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 + pr("root dentry\n"); + au_dpri_dentry(sb->s_root); + pr("root inode\n"); + au_dpri_inode(d_inode(sb->s_root)); +#endif + +#if 0 + 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 + +#if 1 + { + struct inode *i; + + 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 (1 || hlist_empty(&i->i_dentry)) + au_dpri_inode(i); + spin_unlock(&i->i_lock); + } + spin_unlock(&sb->s_inode_list_lock); + } +#endif + 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..dc768f5d90c6 --- /dev/null +++ b/fs/aufs/vdir.c @@ -0,0 +1,896 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 + 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..d6945e22593e --- /dev/null +++ b/fs/aufs/vfsub.c @@ -0,0 +1,902 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for 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) +{ + struct file *file; + + file = dentry_open(path, flags /* | __FMODE_NONOTIFY */, + current_cred()); + if (!IS_ERR_OR_NULL(file) + && (file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) + i_readcount_inc(d_inode(path->dentry)); + + return file; +} + +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..51e677c7f6b7 --- /dev/null +++ b/fs/aufs/vfsub.h @@ -0,0 +1,354 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * sub-routines for 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..64954145c0ec --- /dev/null +++ b/fs/aufs/wbr_policy.c @@ -0,0 +1,830 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..6c9c8501562a --- /dev/null +++ b/fs/aufs/whout.c @@ -0,0 +1,1062 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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; +} + +/* 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..06f69b24e5c1 --- /dev/null +++ b/fs/aufs/whout.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..b0dd8df4e414 --- /dev/null +++ b/fs/aufs/wkq.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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 + if (0 && au_debug_test()) /* left for debugging */ + 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, 0, /*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. + */ +#if 1 /* defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS) */ +#define AuWkqCompDeclare(name) struct completion *comp = NULL + +static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) +{ + *comp = kmalloc(sizeof(**comp), GFP_NOFS); + if (*comp) { + init_completion(*comp); + wkinfo->comp = *comp; + return 0; + } + return -ENOMEM; +} + +static void au_wkq_comp_free(struct completion *comp) +{ + au_kfree_rcu(comp); +} + +#else + +/* no braces */ +#define AuWkqCompDeclare(name) \ + DECLARE_COMPLETION_ONSTACK(_ ## name); \ + struct completion *comp = &_ ## name + +static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) +{ + wkinfo->comp = *comp; + return 0; +} + +static void au_wkq_comp_free(struct completion *comp __maybe_unused) +{ + /* empty */ +} +#endif /* 4KSTACKS */ + +static void au_wkq_run(struct au_wkinfo *wkinfo) +{ + 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..235370d91693 --- /dev/null +++ b/fs/aufs/wkq.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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..8e56b15c53b5 --- /dev/null +++ b/fs/aufs/xattr.c @@ -0,0 +1,356 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * handling 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) + /* + * 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 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, /*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, &arg); +} + +static ssize_t au_getxattr(struct dentry *dentry, + struct inode *inode __maybe_unused, + 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, &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..35ea33469d36 --- /dev/null +++ b/fs/aufs/xino.c @@ -0,0 +1,1965 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * 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); + au_kfree_rcu(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/backref.c b/fs/btrfs/backref.c index 69f8ab4d91f2..110636757d95 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1422,6 +1422,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); + *roots = NULL; return ret; } node = ulist_next(tmp, &uiter); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 54d9af9ddb1a..fc5c9b797e31 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1511,9 +1511,16 @@ int btrfs_init_fs_root(struct btrfs_root *root) spin_lock_init(&root->ino_cache_lock); init_waitqueue_head(&root->ino_cache_wait); - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + /* + * Don't assign anonymous block device to roots that are not exposed to + * userspace, the id pool is limited to 1M + */ + if (is_fstree(root->root_key.objectid) && + btrfs_root_refs(&root->root_item) > 0) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } mutex_lock(&root->objectid_mutex); ret = btrfs_find_highest_objectid(root, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ff1a61e9f713..38ac638665a6 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1902,7 +1902,8 @@ static int __process_pages_contig(struct address_space *mapping, if (!PageDirty(pages[i]) || pages[i]->mapping != mapping) { unlock_page(pages[i]); - put_page(pages[i]); + for (; i < ret; i++) + put_page(pages[i]); err = -EAGAIN; goto out; } @@ -4448,6 +4449,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) /* once for us */ free_extent_map(em); + + cond_resched(); /* Allow large-extent preemption. */ } } return try_release_extent_state(tree, page, mask); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4efc36c35dd9..eaf1a31ceaf2 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2166,7 +2166,7 @@ out: static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { - struct btrfs_free_space *left_info; + struct btrfs_free_space *left_info = NULL; struct btrfs_free_space *right_info; bool merged = false; u64 offset = info->offset; @@ -2181,7 +2181,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, if (right_info && rb_prev(&right_info->offset_index)) left_info = rb_entry(rb_prev(&right_info->offset_index), struct btrfs_free_space, offset_index); - else + else if (!right_info) left_info = tree_search_offset(ctl, offset - 1, 0, 0); if (right_info && !right_info->bitmap) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6a57bf38e761..fe10da44a4d2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4547,6 +4547,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) } } + free_anon_bdev(dest->anon_dev); + dest->anon_dev = 0; out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 454a1015d026..9a2f15f4c80e 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info, exist_re = insert_root_entry(&exist->roots, re); if (exist_re) kfree(re); + } else { + kfree(re); } kfree(be); return exist; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 48b17ffc9d7d..4147b569c64c 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2482,12 +2482,10 @@ again: reloc_root = list_entry(reloc_roots.next, struct btrfs_root, root_list); + root = read_fs_root(fs_info, reloc_root->root_key.offset); if (btrfs_root_refs(&reloc_root->root_item) > 0) { - root = read_fs_root(fs_info, - reloc_root->root_key.offset); BUG_ON(IS_ERR(root)); BUG_ON(root->reloc_root != reloc_root); - ret = merge_reloc_root(rc, root); if (ret) { if (list_empty(&reloc_root->root_list)) @@ -2496,6 +2494,13 @@ again: goto out; } } else { + if (!IS_ERR(root)) { + if (root->reloc_root == reloc_root) + root->reloc_root = NULL; + clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, + &root->state); + } + list_del_init(&reloc_root->root_list); /* Don't forget to queue this reloc root for cleanup */ list_add_tail(&reloc_root->reloc_dirty_list, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 620a9b3962a8..0050eb146b96 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -432,6 +432,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, char *compress_type; bool compress_force = false; enum btrfs_compression_type saved_compress_type; + int saved_compress_level; bool saved_compress_force; int no_compress = 0; @@ -514,6 +515,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, info->compress_type : BTRFS_COMPRESS_NONE; saved_compress_force = btrfs_test_opt(info, FORCE_COMPRESS); + saved_compress_level = info->compress_level; if (token == Opt_compress || token == Opt_compress_force || strncmp(args[0].from, "zlib", 4) == 0) { @@ -558,6 +560,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; + info->compress_level = 0; + info->compress_type = 0; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; @@ -578,11 +582,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, */ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); } - if ((btrfs_test_opt(info, COMPRESS) && - (info->compress_type != saved_compress_type || - compress_force != saved_compress_force)) || - (!btrfs_test_opt(info, COMPRESS) && - no_compress == 1)) { + if (no_compress == 1) { + btrfs_info(info, "use no compression"); + } else if ((info->compress_type != saved_compress_type) || + (compress_force != saved_compress_force) || + (info->compress_level != saved_compress_level)) { btrfs_info(info, "%s %s compression, level %d", (compress_force) ? "force" : "use", compress_type, info->compress_level); @@ -2265,9 +2269,7 @@ static int btrfs_unfreeze(struct super_block *sb) static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); - struct btrfs_fs_devices *cur_devices; struct btrfs_device *dev, *first_dev = NULL; - struct list_head *head; /* * Lightweight locking of the devices. We should not need @@ -2277,18 +2279,13 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) * least until the rcu_read_unlock. */ rcu_read_lock(); - cur_devices = fs_info->fs_devices; - while (cur_devices) { - head = &cur_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) - continue; - if (!dev->name) - continue; - if (!first_dev || dev->devid < first_dev->devid) - first_dev = dev; - } - cur_devices = cur_devices->seed; + list_for_each_entry_rcu(dev, &fs_info->fs_devices->devices, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) + continue; + if (!dev->name) + continue; + if (!first_dev || dev->devid < first_dev->devid) + first_dev = dev; } if (first_dev) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 40683b2b9707..e2e361d09959 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4049,11 +4049,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, fs_info->csum_root, ds + cs, ds + cs + cl - 1, &ordered_sums, 0); - if (ret) { - btrfs_release_path(dst_path); - kfree(ins_data); - return ret; - } + if (ret) + break; } } } @@ -4066,7 +4063,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, * we have to do this after the loop above to avoid changing the * log tree while trying to change the log tree. */ - ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 7a17dd7dadde..81edabb2524d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -216,7 +216,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * * global::fs_devs - add, remove, updates to the global list * - * does not protect: manipulation of the fs_devices::devices list! + * does not protect: manipulation of the fs_devices::devices list in general + * but in mount context it could be used to exclude list modifications by eg. + * scan ioctl * * btrfs_device::name - renames (write side), read is RCU * @@ -229,6 +231,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * may be used to exclude some operations from running concurrently without any * modifications to the list (see write_all_supers) * + * Is not required at mount and close times, because our device list is + * protected by the uuid_mutex at that point. + * * balance_mutex * ------------- * protects balance structures (status, state) and context accessed from @@ -786,6 +791,11 @@ static int btrfs_free_stale_devices(const char *path, return ret; } +/* + * This is only used on mount, and we are protected from competing things + * messing with our fs_devices by the uuid_mutex, thus we do not need the + * fs_devices->device_list_mutex here. + */ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device, fmode_t flags, void *holder) @@ -1422,8 +1432,14 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, int ret; lockdep_assert_held(&uuid_mutex); + /* + * The device_list_mutex cannot be taken here in case opening the + * underlying device takes further locks like bd_mutex. + * + * We also don't need the lock here as this is called during mount and + * exclusion is provided by uuid_mutex + */ - mutex_lock(&fs_devices->device_list_mutex); if (fs_devices->opened) { fs_devices->opened++; ret = 0; @@ -1431,7 +1447,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, list_sort(NULL, &fs_devices->devices, devid_cmp); ret = open_fs_devices(fs_devices, flags, holder); } - mutex_unlock(&fs_devices->device_list_mutex); return ret; } @@ -7230,7 +7245,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * otherwise we don't need it. */ mutex_lock(&uuid_mutex); - mutex_lock(&fs_info->chunk_mutex); + + /* + * It is possible for mount and umount to race in such a way that + * we execute this code path, but open_fs_devices failed to clear + * total_rw_bytes. We certainly want it cleared before reading the + * device items, so clear it here. + */ + fs_info->fs_devices->total_rw_bytes = 0; /* * Read all device items, and then all the chunk items. All @@ -7267,7 +7289,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); + mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } @@ -7297,7 +7321,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } ret = 0; error: - mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&uuid_mutex); btrfs_free_path(path); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 7d5d66116724..6eddc935d8ce 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3053,8 +3053,10 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_64_safe(&p, end, features, bad); - p += len - sizeof(features); + if (len) { + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); + } } mutex_lock(&mdsc->mutex); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ddfde6cc0c2c..97d826a26478 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1783,7 +1783,6 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; - bool new_target = d_really_is_negative(target_dentry); if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -1860,13 +1859,8 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, */ unlink_target: - /* - * If the target dentry was created during the rename, try - * unlinking it if it's not negative - */ - if (new_target && - d_really_is_positive(target_dentry) && - (rc == -EACCES || rc == -EEXIST)) { + /* Try unlinking the target dentry if it's not negative */ + if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { if (d_is_dir(target_dentry)) tmprc = cifs_rmdir(target_dir, target_dentry); else diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 14265b4bbcc0..2fc96f7923ee 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -509,15 +509,31 @@ cifs_ses_oplock_break(struct work_struct *work) kfree(lw); } +static void +smb2_queue_pending_open_break(struct tcon_link *tlink, __u8 *lease_key, + __le32 new_lease_state) +{ + struct smb2_lease_break_work *lw; + + lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); + if (!lw) { + cifs_put_tlink(tlink); + return; + } + + INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); + lw->tlink = tlink; + lw->lease_state = new_lease_state; + memcpy(lw->lease_key, lease_key, SMB2_LEASE_KEY_SIZE); + queue_work(cifsiod_wq, &lw->lease_break); +} + static bool -smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, - struct smb2_lease_break_work *lw) +smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) { - bool found; __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); @@ -556,22 +572,29 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, &cinode->flags); cifs_queue_oplock_break(cfile); - kfree(lw); return true; } - found = false; + return false; +} + +static struct cifs_pending_open * +smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, + struct smb2_lease_break *rsp) +{ + __u8 lease_state = le32_to_cpu(rsp->NewLeaseState); + int ack_req = le32_to_cpu(rsp->Flags & + SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); + struct cifs_pending_open *open; + struct cifs_pending_open *found = NULL; + list_for_each_entry(open, &tcon->pending_opens, olist) { if (memcmp(open->lease_key, rsp->LeaseKey, SMB2_LEASE_KEY_SIZE)) continue; if (!found && ack_req) { - found = true; - memcpy(lw->lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - lw->tlink = cifs_get_tlink(open->tlink); - queue_work(cifsiod_wq, &lw->lease_break); + found = open; } cifs_dbg(FYI, "found in the pending open list\n"); @@ -592,14 +615,7 @@ smb2_is_valid_lease_break(char *buffer) struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct smb2_lease_break_work *lw; - - lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); - if (!lw) - return false; - - INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); - lw->lease_state = rsp->NewLeaseState; + struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); @@ -617,11 +633,27 @@ smb2_is_valid_lease_break(char *buffer) spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp, lw)) { + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } spin_unlock(&tcon->open_file_lock); if (tcon->crfid.is_valid && @@ -639,7 +671,6 @@ smb2_is_valid_lease_break(char *buffer) } } spin_unlock(&cifs_tcp_ses_lock); - kfree(lw); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); return false; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index bfc8a7d38a8b..78f4cd690dc2 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1298,6 +1298,8 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) spnego_key = cifs_get_spnego_key(ses); if (IS_ERR(spnego_key)) { rc = PTR_ERR(spnego_key); + if (rc == -ENOKEY) + cifs_dbg(VFS, "Verify user has a krb5 ticket and keyutils is installed\n"); spnego_key = NULL; goto out; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 5bb87a61d913..44079b1a0456 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -528,7 +528,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, const int timeout, const int flags, unsigned int *instance) { - int rc; + long rc; int *credits; int optype; long int t; diff --git a/fs/dcache.c b/fs/dcache.c index c435398f2c81..3fc74e471924 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1247,7 +1247,7 @@ enum d_walk_ret { * * The @enter() callbacks are called with d_lock held. */ -static void d_walk(struct dentry *parent, void *data, +void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; @@ -1352,6 +1352,7 @@ rename_retry: seq = 1; goto again; } +EXPORT_SYMBOL_GPL(d_walk); struct check_mount { struct vfsmount *mnt; @@ -2850,6 +2851,7 @@ 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/debugfs/file.c b/fs/debugfs/file.c index d7cfc8fb4632..6cfe9c175977 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -148,7 +148,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) real_fops = debugfs_real_fops(filp); if (!fops_get(real_fops)) { -#ifdef MODULE +#ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) goto out; @@ -278,7 +278,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) real_fops = debugfs_real_fops(filp); if (!fops_get(real_fops)) { -#ifdef MODULE +#ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) goto out; diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 4c2c85a223ac..3dd6e0189d39 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -631,6 +631,9 @@ static int new_lockspace(const char *name, const char *cluster, wait_event(ls->ls_recover_lock_wait, test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags)); + /* let kobject handle freeing of ls if there's an error */ + do_unreg = 1; + ls->ls_kobj.kset = dlm_kset; error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, "%s", ls->ls_name); @@ -638,9 +641,6 @@ static int new_lockspace(const char *name, const char *cluster, goto out_recoverd; kobject_uevent(&ls->ls_kobj, KOBJ_ADD); - /* let kobject handle freeing of ls if there's an error */ - do_unreg = 1; - /* This uevent triggers dlm_controld in userspace to add us to the group of nodes that are members of this lockspace (managed by the cluster infrastructure.) Once it's done that, it tells us who the diff --git a/fs/exec.c b/fs/exec.c index 114f1b474fed..fa3faa50b592 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -110,6 +110,7 @@ bool path_noexec(const struct path *path) return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } +EXPORT_SYMBOL_GPL(path_noexec); #ifdef CONFIG_USELIB /* diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index a0c5ea91fcd4..8c29d4d6bfd5 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -80,6 +80,7 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir) if (dir) le16_add_cpu(&desc->bg_used_dirs_count, -1); spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); + percpu_counter_inc(&EXT2_SB(sb)->s_freeinodes_counter); if (dir) percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); mark_buffer_dirty(bh); @@ -529,7 +530,7 @@ got: goto fail; } - percpu_counter_add(&sbi->s_freeinodes_counter, -1); + percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e5327cefc566..7335cff90a7d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3872,6 +3872,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; + loff_t offset = iocb->ki_pos; + loff_t size = i_size_read(inode); + + if (offset >= size) + return 0; /* * Shared inode_lock is enough for us - it protects against concurrent diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 1901f683404a..8e1d5912556a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1391,8 +1391,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf, + buf_size, offset)) return -1; *res_dir = de; return 1; @@ -1853,7 +1853,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); - /* Split the existing block in the middle, size-wise */ + /* Ensure that neither split block is over half full */ size = 0; move = 0; for (i = count-1; i >= 0; i--) { @@ -1863,8 +1863,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, size += map[i].size; move++; } - /* map index at which we will split */ - split = count - move; + /* + * map index at which we will split + * + * If the sum of active entries didn't exceed half the block size, just + * split it in half by count; each resulting block will have at least + * half the space free. + */ + if (i > 0) + split = count - move; + else + split = count/2; + hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n", @@ -2473,7 +2483,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8f66e4f4256e..19f2e7c77be8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -365,12 +365,12 @@ static void __save_error_info(struct super_block *sb, const char *func, 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); 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/fat/Kconfig b/fs/fat/Kconfig index 718163d0c621..c52e80a9c12e 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 814ad2c2ba80..b21c74647175 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -369,7 +369,8 @@ 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 */ @@ -501,6 +502,13 @@ 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 @@ -514,6 +522,7 @@ 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; @@ -605,6 +614,8 @@ 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; } @@ -963,6 +974,10 @@ 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 3d40771e8e7c..d4ad34463848 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_table.c b/fs/file_table.c index b07b53f24ff5..34b9bbf4c556 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. @@ -327,6 +328,7 @@ void flush_delayed_fput(void) { delayed_fput(NULL); } +EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); @@ -374,6 +376,7 @@ 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 186468fba82e..9b7ddd7f9691 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -905,7 +905,8 @@ static int fuse_check_page(struct page *page) 1 << PG_uptodate | 1 << PG_lru | 1 << PG_active | - 1 << PG_reclaim))) { + 1 << PG_reclaim | + 1 << PG_waiters))) { pr_warn("trying to steal weird page\n"); pr_warn(" page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping); return 1; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b39e25f55e1d..c053266235e2 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -18,6 +18,7 @@ #include <linux/swap.h> #include <linux/falloc.h> #include <linux/uio.h> +#include <linux/fs.h> static int fuse_send_open(struct fuse_conn *fc, u64 nodeid, struct file *file, int opcode, struct fuse_open_out *outargp) @@ -2006,10 +2007,8 @@ static int fuse_writepages(struct address_space *mapping, err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data); if (data.req) { - /* Ignore errors if we can write at least one page */ BUG_ON(!data.req->num_pages); fuse_writepages_send(&data); - err = 0; } if (data.ff) fuse_file_put(data.ff, false, false); @@ -2616,7 +2615,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, struct iovec *iov = iov_page; iov->iov_base = (void __user *)arg; - iov->iov_len = _IOC_SIZE(cmd); + + switch (cmd) { + case FS_IOC_GETFLAGS: + case FS_IOC_SETFLAGS: + iov->iov_len = sizeof(int); + break; + default: + iov->iov_len = _IOC_SIZE(cmd); + break; + } if (_IOC_DIR(cmd) & _IOC_WRITE) { in_iov = iov; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index bc32e11c9cee..aa98abd177c3 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1158,7 +1158,17 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent goto fail_per_node; } - if (!sb_rdonly(sb)) { + if (sb_rdonly(sb)) { + struct gfs2_holder freeze_gh; + + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + GL_EXACT, &freeze_gh); + if (error) { + fs_err(sdp, "can't make FS RO: %d\n", error); + goto fail_per_node; + } + gfs2_glock_dq_uninit(&freeze_gh); + } else { error = gfs2_make_fs_rw(sdp); if (error) { fs_err(sdp, "can't make FS RW: %d\n", error); diff --git a/fs/inode.c b/fs/inode.c index 7aab0cb0eca4..b6748888f140 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1678,7 +1678,7 @@ EXPORT_SYMBOL(generic_update_time); * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ -static int update_time(struct inode *inode, struct timespec64 *time, int flags) +int update_time(struct inode *inode, struct timespec64 *time, int flags) { int (*update_time)(struct inode *, struct timespec64 *, int); @@ -1687,6 +1687,7 @@ static int update_time(struct inode *inode, struct timespec64 *time, int flags) return update_time(inode, time, flags); } +EXPORT_SYMBOL_GPL(update_time); /** * touch_atime - update the access time diff --git a/fs/ioctl.c b/fs/ioctl.c index fef3a6bf7c78..3118da0de158 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> +#include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> @@ -719,3 +720,37 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { return ksys_ioctl(fd, cmd, arg); } + +#ifdef CONFIG_COMPAT +/** + * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation + * + * This is not normally called as a function, but instead set in struct + * file_operations as + * + * .compat_ioctl = compat_ptr_ioctl, + * + * On most architectures, the compat_ptr_ioctl() just passes all arguments + * to the corresponding ->ioctl handler. The exception is arch/s390, where + * compat_ptr() clears the top bit of a 32-bit pointer value, so user space + * pointers to the second 2GB alias the first 2GB, as is the case for + * native 32-bit s390 user space. + * + * The compat_ptr_ioctl() function must therefore be used only with ioctl + * functions that either ignore the argument or pass a pointer to a + * compatible data type. + * + * If any ioctl command handled by fops->unlocked_ioctl passes a plain + * integer instead of a pointer, or any of the passed data types + * is incompatible between 32-bit and 64-bit architectures, a proper + * handler is required instead of compat_ptr_ioctl. + */ +long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + if (!file->f_op->unlocked_ioctl) + return -ENOIOCTLCMD; + + return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +EXPORT_SYMBOL(compat_ptr_ioctl); +#endif diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 094e15e1ccaa..92a1df0a9e56 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1353,8 +1353,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) int ret; /* Buffer got discarded which means block device got invalidated */ - if (!buffer_mapped(bh)) + if (!buffer_mapped(bh)) { + unlock_buffer(bh); return -EIO; + } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e8c792b49616..c35bbaa19486 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -912,7 +912,7 @@ repeat: } fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - &name, 0); + NULL, 0); iput(inode); } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index f96073f25432..53337020d9d0 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -150,6 +150,25 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) return 0; } +static bool minix_check_superblock(struct super_block *sb) +{ + struct minix_sb_info *sbi = minix_sb(sb); + + if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) + return false; + + /* + * s_max_size must not exceed the block mapping limitation. This check + * is only needed for V1 filesystems, since V2/V3 support an extra level + * of indirect blocks which places the limit well above U32_MAX. + */ + if (sbi->s_version == MINIX_V1 && + sb->s_maxbytes > (7 + 512 + 512*512) * BLOCK_SIZE) + return false; + + return true; +} + static int minix_fill_super(struct super_block *s, void *data, int silent) { struct buffer_head *bh; @@ -185,7 +204,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = ms->s_zmap_blocks; sbi->s_firstdatazone = ms->s_firstdatazone; sbi->s_log_zone_size = ms->s_log_zone_size; - sbi->s_max_size = ms->s_max_size; + s->s_maxbytes = ms->s_max_size; s->s_magic = ms->s_magic; if (s->s_magic == MINIX_SUPER_MAGIC) { sbi->s_version = MINIX_V1; @@ -216,7 +235,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) sbi->s_zmap_blocks = m3s->s_zmap_blocks; sbi->s_firstdatazone = m3s->s_firstdatazone; sbi->s_log_zone_size = m3s->s_log_zone_size; - sbi->s_max_size = m3s->s_max_size; + s->s_maxbytes = m3s->s_max_size; sbi->s_ninodes = m3s->s_ninodes; sbi->s_nzones = m3s->s_zones; sbi->s_dirsize = 64; @@ -228,11 +247,12 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) } else goto out_no_fs; + if (!minix_check_superblock(s)) + goto out_illegal_sb; + /* * Allocate the buffer map to keep the superblock small. */ - if (sbi->s_imap_blocks == 0 || sbi->s_zmap_blocks == 0) - goto out_illegal_sb; i = (sbi->s_imap_blocks + sbi->s_zmap_blocks) * sizeof(bh); map = kzalloc(i, GFP_KERNEL); if (!map) @@ -466,6 +486,13 @@ static struct inode *V1_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); @@ -499,6 +526,13 @@ static struct inode *V2_minix_iget(struct inode *inode) iget_failed(inode); return ERR_PTR(-EIO); } + if (raw_inode->i_nlinks == 0) { + printk("MINIX-fs: deleted inode referenced: %lu\n", + inode->i_ino); + brelse(bh); + iget_failed(inode); + return ERR_PTR(-ESTALE); + } inode->i_mode = raw_inode->i_mode; i_uid_write(inode, raw_inode->i_uid); i_gid_write(inode, raw_inode->i_gid); diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index 043c3fdbc8e7..446148792f41 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -75,6 +75,7 @@ static int alloc_branch(struct inode *inode, int n = 0; int i; int parent = minix_new_block(inode); + int err = -ENOSPC; branch[0].key = cpu_to_block(parent); if (parent) for (n = 1; n < num; n++) { @@ -85,6 +86,11 @@ static int alloc_branch(struct inode *inode, break; branch[n].key = cpu_to_block(nr); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + minix_free_block(inode, nr); + err = -ENOMEM; + break; + } lock_buffer(bh); memset(bh->b_data, 0, bh->b_size); branch[n].bh = bh; @@ -103,7 +109,7 @@ static int alloc_branch(struct inode *inode, bforget(branch[i].bh); for (i = 0; i < n; i++) minix_free_block(inode, block_to_cpu(branch[i].key)); - return -ENOSPC; + return err; } static inline int splice_branch(struct inode *inode, diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c index 046cc96ee7ad..1fed906042aa 100644 --- a/fs/minix/itree_v1.c +++ b/fs/minix/itree_v1.c @@ -29,12 +29,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, inode->i_sb->s_bdev); - } else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, inode->i_sb->s_bdev); - } else if (block < 7) { + return 0; + } + if ((u64)block * BLOCK_SIZE >= inode->i_sb->s_maxbytes) + return 0; + + if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { offsets[n++] = 7; diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index f7fc7ecccccc..9d00f31a2d9d 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -32,13 +32,12 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) if (block < 0) { printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", block, sb->s_bdev); - } else if ((u64)block * (u64)sb->s_blocksize >= - minix_sb(sb)->s_max_size) { - if (printk_ratelimit()) - printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %pg\n", - block, sb->s_bdev); - } else if (block < DIRCOUNT) { + return 0; + } + if ((u64)block * (u64)sb->s_blocksize >= sb->s_maxbytes) + return 0; + + if (block < DIRCOUNT) { offsets[n++] = block; } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { offsets[n++] = DIRCOUNT; diff --git a/fs/minix/minix.h b/fs/minix/minix.h index df081e8afcc3..168d45d3de73 100644 --- a/fs/minix/minix.h +++ b/fs/minix/minix.h @@ -32,7 +32,6 @@ struct minix_sb_info { unsigned long s_zmap_blocks; unsigned long s_firstdatazone; unsigned long s_log_zone_size; - unsigned long s_max_size; int s_dirsize; int s_namelen; struct buffer_head ** s_imap; diff --git a/fs/namespace.c b/fs/namespace.c index 1508a402ce14..7083e1388150 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -436,6 +436,7 @@ 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 @@ -770,6 +771,13 @@ 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 */ @@ -1902,6 +1910,7 @@ 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 e7dd07f47825..5b1b365939b5 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/client.c b/fs/nfs/client.c index cbd06b916d30..913a37fc3e11 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -5,7 +5,6 @@ * Written by David Howells (dhowells@redhat.com) */ - #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> @@ -66,7 +65,7 @@ static const struct rpc_version *nfs_version[5] = { [4] = NULL, }; -const struct rpc_program nfs_program = { +struct rpc_program nfs_program = { .name = "nfs", .number = NFS_PROGRAM, .nrvers = ARRAY_SIZE(nfs_version), @@ -158,6 +157,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) goto error_dealloc; clp->rpc_ops = clp->cl_nfs_mod->rpc_ops; + clp->nfs_prog = cl_init->nfs_prog; refcount_set(&clp->cl_count, 1); clp->cl_cons_state = NFS_CS_INITING; @@ -311,6 +311,9 @@ again: /* Match nfsv4 minorversion */ if (clp->cl_minorversion != data->minorversion) continue; + if (clp->nfs_prog != data->nfs_prog) + continue; + /* Match the full socket address */ if (!rpc_cmp_addr_port(sap, clap)) /* Match all xprt_switch full socket addresses */ @@ -517,6 +520,10 @@ int nfs_create_rpc_client(struct nfs_client *clp, if (!IS_ERR(clp->cl_rpcclient)) return 0; + if (clp->nfs_prog) + nfs_program.number = clp->nfs_prog; + else + nfs_program.number = NFS_PROGRAM; clnt = rpc_create(&args); if (IS_ERR(clnt)) { dprintk("%s: cannot create RPC client. Error = %ld\n", @@ -659,6 +666,7 @@ static int nfs_init_server(struct nfs_server *server, .net = data->net, .timeparms = &timeparms, .cred = server->cred, + .nfs_prog = data->nfs_prog, }; struct nfs_client *clp; int error; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index eeac41249bc4..1aae0606dd87 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -397,6 +397,8 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) { struct inode *inode = dreq->inode; + inode_dio_end(inode); + if (dreq->iocb) { long res = (long) dreq->error; if (dreq->count != 0) { @@ -408,10 +410,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) complete(&dreq->completion); - igrab(inode); nfs_direct_req_release(dreq); - inode_dio_end(inode); - iput(inode); } static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) @@ -541,10 +540,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - igrab(inode); - nfs_direct_req_release(dreq); inode_dio_end(inode); - iput(inode); + nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } @@ -968,10 +965,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - igrab(inode); - nfs_direct_req_release(dreq); inode_dio_end(inode); - iput(inode); + nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 7b3136753205..387a2cfa7e17 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -83,7 +83,6 @@ nfs_file_release(struct inode *inode, struct file *filp) dprintk("NFS: release(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); - inode_dio_wait(inode); nfs_file_clear_open_context(filp); return 0; } @@ -141,6 +140,7 @@ static int nfs_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -149,7 +149,9 @@ nfs_file_flush(struct file *file, fl_owner_t id) return 0; /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } ssize_t @@ -581,12 +583,14 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .page_mkwrite = nfs_vm_page_mkwrite, }; -static int nfs_need_check_write(struct file *filp, struct inode *inode) +static int nfs_need_check_write(struct file *filp, struct inode *inode, + int error) { struct nfs_open_context *ctx; ctx = nfs_file_open_context(filp); - if (nfs_ctx_key_to_expire(ctx, inode)) + if (nfs_error_is_fatal_on_server(error) || + nfs_ctx_key_to_expire(ctx, inode)) return 1; return 0; } @@ -597,6 +601,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); unsigned long written = 0; ssize_t result; + errseq_t since; + int error; result = nfs_key_timeout_notify(file, inode); if (result) @@ -621,6 +627,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos > i_size_read(inode)) nfs_revalidate_mapping(inode, file->f_mapping); + since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); if (result > 0) { @@ -639,7 +646,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; /* Return error values */ - if (nfs_need_check_write(file, inode)) { + error = filemap_check_wb_err(file->f_mapping, since); + if (nfs_need_check_write(file, inode, error)) { int err = nfs_wb_all(inode); if (err < 0) result = err; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 9ab9427405f3..18113980a4fb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -84,6 +84,7 @@ struct nfs_client_initdata { struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; + int nfs_prog; }; /* @@ -95,6 +96,8 @@ struct nfs_parsed_mount_data { unsigned int timeo, retrans; unsigned int acregmin, acregmax, acdirmin, acdirmax; + int nfs_prog; + int mount_prog; unsigned int namlen; unsigned int options; unsigned int bsize; @@ -151,11 +154,11 @@ struct nfs_mount_info { struct nfs_fh *mntfh; }; -extern int nfs_mount(struct nfs_mount_request *info); +extern int nfs_mount(struct nfs_mount_request *info, int prog); extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ -extern const struct rpc_program nfs_program; +extern struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index dda5c3e65d8d..1f2f6f45e174 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -65,7 +65,7 @@ enum { MOUNTPROC3_EXPORT = 5, }; -static const struct rpc_program mnt_program; +static struct rpc_program mnt_program; /* * Defined by OpenGroup XNFS Version 3W, chapter 8 @@ -142,7 +142,7 @@ struct mnt_fhstatus { * with the list from the server or a faked-up list if the server didn't * provide one. */ -int nfs_mount(struct nfs_mount_request *info) +int nfs_mount(struct nfs_mount_request *info, int m_prog) { struct mountres result = { .fh = info->fh, @@ -177,6 +177,7 @@ int nfs_mount(struct nfs_mount_request *info) if (info->noresvport) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + mnt_program.number = m_prog; mnt_clnt = rpc_create(&args); if (IS_ERR(mnt_clnt)) goto out_clnt_err; @@ -531,7 +532,7 @@ static const struct rpc_version *mnt_version[] = { static struct rpc_stat mnt_stats; -static const struct rpc_program mnt_program = { +static struct rpc_program mnt_program = { .name = "mount", .number = NFS_MNT_PROGRAM, .nrvers = ARRAY_SIZE(mnt_version), diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index cec32338562a..f39651196a7e 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -109,6 +109,7 @@ static int nfs4_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); + errseq_t since; dprintk("NFS: flush(%pD2)\n", file); @@ -124,7 +125,9 @@ nfs4_file_flush(struct file *file, fl_owner_t id) return filemap_fdatawrite(file->f_mapping); /* Flush writes to the server and return any errors */ - return nfs_wb_all(inode); + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); } #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index beee0332adf7..f3c17c8fb022 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -757,6 +757,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, slot->seq_nr_last_acked = seqnr; } +static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred, + struct nfs4_slot *slot) +{ + struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true); + if (!IS_ERR(task)) + rpc_put_task_async(task); +} + static int nfs41_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) { @@ -773,6 +781,7 @@ static int nfs41_sequence_process(struct rpc_task *task, goto out; session = slot->table->session; + clp = session->clp; trace_nfs4_sequence_done(session, res); @@ -787,7 +796,6 @@ static int nfs41_sequence_process(struct rpc_task *task, nfs4_slot_sequence_acked(slot, slot->seq_nr); /* Update the slot's sequence and clientid lease timer */ slot->seq_done = 1; - clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags, @@ -835,10 +843,18 @@ static int nfs41_sequence_process(struct rpc_task *task, /* * Were one or more calls using this slot interrupted? * If the server never received the request, then our - * transmitted slot sequence number may be too high. + * transmitted slot sequence number may be too high. However, + * if the server did receive the request then it might + * accidentally give us a reply with a mismatched operation. + * We can sort this out by sending a lone sequence operation + * to the server on the same slot. */ if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) { slot->seq_nr--; + if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) { + nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot); + res->sr_slot = NULL; + } goto retry_nowait; } /* @@ -5713,8 +5729,6 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, return ret; if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) return -ENOENT; - if (buflen < label.len) - return -ERANGE; return 0; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 6a92a6eac911..d554baabef3e 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4163,7 +4163,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; if (len < NFS4_MAXLABELLEN) { if (label) { - memcpy(label->label, p, len); + if (label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); + } label->len = len; label->pi = pi; label->lfs = lfs; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5308aade081b..9b58894eb9b7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1188,31 +1188,27 @@ out: return status; } +static bool +pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo, + enum pnfs_iomode iomode, + u32 seq) +{ + struct pnfs_layout_range recall_range = { + .length = NFS4_MAX_UINT64, + .iomode = iomode, + }; + return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &recall_range, seq) != -EBUSY; +} + /* Return true if layoutreturn is needed */ static bool pnfs_layout_need_return(struct pnfs_layout_hdr *lo) { - struct pnfs_layout_segment *s; - enum pnfs_iomode iomode; - u32 seq; - if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) return false; - - seq = lo->plh_return_seq; - iomode = lo->plh_return_iomode; - - /* Defer layoutreturn until all recalled lsegs are done */ - list_for_each_entry(s, &lo->plh_segs, pls_list) { - if (seq && pnfs_seqid_is_newer(s->pls_seq, seq)) - continue; - if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode) - continue; - if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - } - - return true; + return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode, + lo->plh_return_seq); } static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) @@ -2301,16 +2297,6 @@ out_forget: return ERR_PTR(-EAGAIN); } -static int -mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg, - struct list_head *tmp_list) -{ - if (!mark_lseg_invalid(lseg, tmp_list)) - return 0; - pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg); - return 1; -} - /** * pnfs_mark_matching_lsegs_return - Free or return matching layout segments * @lo: pointer to layout header @@ -2347,7 +2333,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); - if (mark_lseg_invalid_or_return(lseg, tmp_list)) + if (mark_lseg_invalid(lseg, tmp_list)) continue; remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 4d375b517eda..aa828b1cb58f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -103,6 +103,8 @@ enum { Opt_mountport, Opt_mountvers, Opt_minorversion, + Opt_mountprog, + Opt_nfsprog, /* Mount options that take string arguments */ Opt_nfsvers, @@ -169,6 +171,8 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_mountport, "mountport=%s" }, { Opt_mountvers, "mountvers=%s" }, { Opt_minorversion, "minorversion=%s" }, + { Opt_mountprog, "mountprog=%s" }, + { Opt_nfsprog, "nfsprog=%s" }, { Opt_nfsvers, "nfsvers=%s" }, { Opt_nfsvers, "vers=%s" }, @@ -927,6 +931,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data->acregmax = NFS_DEF_ACREGMAX; data->acdirmin = NFS_DEF_ACDIRMIN; data->acdirmax = NFS_DEF_ACDIRMAX; + data->nfs_prog = NFS_PROGRAM; + data->mount_prog = NFS_MNT_PROGRAM; data->mount_server.port = NFS_UNSPEC_PORT; data->nfs_server.port = NFS_UNSPEC_PORT; data->nfs_server.protocol = XPRT_TRANSPORT_TCP; @@ -1389,6 +1395,26 @@ static int nfs_parse_mount_options(char *raw, goto out_invalid_value; mnt->acdirmax = option; break; + case Opt_mountprog: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = kstrtoul(string, 10, &option); + kfree(string); + if (rc != 0) + goto out_invalid_value; + mnt->mount_prog = option; + break; + case Opt_nfsprog: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = kstrtoul(string, 10, &option); + kfree(string); + if (rc != 0) + goto out_invalid_value; + mnt->nfs_prog = option; + break; case Opt_actimeo: if (nfs_get_option_ul(args, &option)) goto out_invalid_value; @@ -1788,7 +1814,7 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args, * Now ask the mount server to map our export path * to a file handle. */ - status = nfs_mount(&request); + status = nfs_mount(&request,args->mount_prog); if (status != 0) { dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", request.hostname, status); @@ -2097,6 +2123,9 @@ static int nfs23_validate_mount_data(void *options, } break; + case 7: + args->nfs_prog = (data->version >= 7) ? data->nfs_prog : NFS_PROGRAM; + break; default: return NFS_TEXT_DATA; } @@ -2159,6 +2188,7 @@ static int nfs_validate_text_mount_data(void *options, int max_namelen = PAGE_SIZE; int max_pathlen = NFS_MAXPATHLEN; struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + args->nfs_prog = NFS_PROGRAM; if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; @@ -2803,6 +2833,8 @@ static int nfs4_validate_mount_data(void *options, args->version = 4; + args->nfs_prog = NFS_PROGRAM; + switch (data->version) { case 1: if (data->host_addrlen > sizeof(args->nfs_server.address)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 52c4f6daa649..7a1cc8b77d42 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3535,17 +3535,17 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, u32 zzz = 0; int pad; + /* + * svcrdma requires every READ payload to start somewhere + * in xdr->pages. + */ + if (xdr->iov == xdr->buf->head) { + xdr->iov = NULL; + xdr->end = xdr->p; + } + len = maxcount; v = 0; - - thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p)); - p = xdr_reserve_space(xdr, (thislen+3)&~3); - WARN_ON_ONCE(!p); - resp->rqstp->rq_vec[v].iov_base = p; - resp->rqstp->rq_vec[v].iov_len = thislen; - v++; - len -= thislen; - while (len) { thislen = min_t(long, len, PAGE_SIZE); p = xdr_reserve_space(xdr, (thislen+3)&~3); @@ -3563,6 +3563,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, read->rd_length = maxcount; if (nfserr) return nfserr; + if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount)) + return nfserr_io; xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3)); eof = nfsd_eof_on_read(len, maxcount, read->rd_offset, diff --git a/fs/notify/group.c b/fs/notify/group.c index 0391190305cc..0b9f7f6d8390 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -99,6 +99,7 @@ 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. @@ -108,6 +109,7 @@ void fsnotify_put_group(struct fsnotify_group *group) if (refcount_dec_and_test(&group->refcnt)) fsnotify_final_destroy_group(group); } +EXPORT_SYMBOL_GPL(fsnotify_put_group); /* * Create a new fsnotify_group and hold a reference for the group returned. @@ -137,6 +139,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) return group; } +EXPORT_SYMBOL_GPL(fsnotify_alloc_group); int fsnotify_fasync(int fd, struct file *file, int on) { diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 99ddd126f6f0..2154d69a2c7a 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -276,6 +276,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } +EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object @@ -430,6 +431,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark, mutex_unlock(&group->mark_mutex); fsnotify_free_mark(mark); } +EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. @@ -685,6 +687,7 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, mutex_unlock(&group->mark_mutex); return ret; } +EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found @@ -809,6 +812,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, mark->group = group; WRITE_ONCE(mark->connector, NULL); } +EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index f75b1735e8ec..b5934e995a69 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2850,9 +2850,15 @@ int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex) status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE, 0, 0); - if (status < 0) + if (status < 0) { mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status); + if (ex) + up_write(&osb->nfs_sync_rwlock); + else + up_read(&osb->nfs_sync_rwlock); + } + return status; } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 6133d4889694..b07eb2a30be5 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -324,8 +324,8 @@ struct ocfs2_super spinlock_t osb_lock; u32 s_next_generation; unsigned long osb_flags; - s16 s_inode_steal_slot; - s16 s_meta_steal_slot; + u16 s_inode_steal_slot; + u16 s_meta_steal_slot; atomic_t s_num_inodes_stolen; atomic_t s_num_meta_stolen; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 503e724d39f5..5e0eaea47405 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -879,9 +879,9 @@ static void __ocfs2_set_steal_slot(struct ocfs2_super *osb, int slot, int type) { spin_lock(&osb->osb_lock); if (type == INODE_ALLOC_SYSTEM_INODE) - osb->s_inode_steal_slot = slot; + osb->s_inode_steal_slot = (u16)slot; else if (type == EXTENT_ALLOC_SYSTEM_INODE) - osb->s_meta_steal_slot = slot; + osb->s_meta_steal_slot = (u16)slot; spin_unlock(&osb->osb_lock); } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index a201f9780b35..e9cb264c5aae 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -78,7 +78,7 @@ struct mount_options unsigned long commit_interval; unsigned long mount_opt; unsigned int atime_quantum; - signed short slot; + unsigned short slot; int localalloc_opt; unsigned int resv_level; int dir_resv_level; @@ -1354,7 +1354,7 @@ static int ocfs2_parse_options(struct super_block *sb, goto bail; } if (option) - mopt->slot = (s16)option; + mopt->slot = (u16)option; break; case Opt_commit: if (match_int(&args[0], &option)) { diff --git a/fs/open.c b/fs/open.c index 01c55f88b573..2941aa2c233e 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/orangefs/file.c b/fs/orangefs/file.c index a35c17017210..59ec1cb0e158 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -313,23 +313,8 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { int ret; - struct orangefs_read_options *ro; - orangefs_stats.reads++; - /* - * Remember how they set "count" in read(2) or pread(2) or whatever - - * users can use count as a knob to control orangefs io size and later - * we can try to help them fill as many pages as possible in readpage. - */ - if (!iocb->ki_filp->private_data) { - iocb->ki_filp->private_data = kmalloc(sizeof *ro, GFP_KERNEL); - if (!iocb->ki_filp->private_data) - return(ENOMEM); - ro = iocb->ki_filp->private_data; - ro->blksiz = iter->count; - } - down_read(&file_inode(iocb->ki_filp)->i_rwsem); ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp)); if (ret) @@ -598,12 +583,6 @@ static int orangefs_lock(struct file *filp, int cmd, struct file_lock *fl) return rc; } -static int orangefs_file_open(struct inode * inode, struct file *file) -{ - file->private_data = NULL; - return generic_file_open(inode, file); -} - static int orangefs_flush(struct file *file, fl_owner_t id) { /* @@ -617,9 +596,6 @@ static int orangefs_flush(struct file *file, fl_owner_t id) struct inode *inode = file->f_mapping->host; int r; - kfree(file->private_data); - file->private_data = NULL; - if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); inode->i_state &= ~I_DIRTY_TIME; @@ -642,7 +618,7 @@ const struct file_operations orangefs_file_operations = { .lock = orangefs_lock, .unlocked_ioctl = orangefs_ioctl, .mmap = orangefs_file_mmap, - .open = orangefs_file_open, + .open = generic_file_open, .flush = orangefs_flush, .release = orangefs_file_release, .fsync = orangefs_fsync, diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 0c337d8bdaab..c9b3e5ec8221 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -259,46 +259,19 @@ static int orangefs_readpage(struct file *file, struct page *page) pgoff_t index; /* which page */ struct page *next_page; char *kaddr; - struct orangefs_read_options *ro = file->private_data; loff_t read_size; - loff_t roundedup; int buffer_index = -1; /* orangefs shared memory slot */ int slot_index; /* index into slot */ int remaining; /* - * If they set some miniscule size for "count" in read(2) - * (for example) then let's try to read a page, or the whole file - * if it is smaller than a page. Once "count" goes over a page - * then lets round up to the highest page size multiple that is - * less than or equal to "count" and do that much orangefs IO and - * try to fill as many pages as we can from it. - * - * "count" should be represented in ro->blksiz. - * - * inode->i_size = file size. + * Get up to this many bytes from Orangefs at a time and try + * to fill them into the page cache at once. Tests with dd made + * this seem like a reasonable static number, if there was + * interest perhaps this number could be made setable through + * sysfs... */ - if (ro) { - if (ro->blksiz < PAGE_SIZE) { - if (inode->i_size < PAGE_SIZE) - read_size = inode->i_size; - else - read_size = PAGE_SIZE; - } else { - roundedup = ((PAGE_SIZE - 1) & ro->blksiz) ? - ((ro->blksiz + PAGE_SIZE) & ~(PAGE_SIZE -1)) : - ro->blksiz; - if (roundedup > inode->i_size) - read_size = inode->i_size; - else - read_size = roundedup; - - } - } else { - read_size = PAGE_SIZE; - } - if (!read_size) - read_size = PAGE_SIZE; + read_size = 524288; if (PageDirty(page)) orangefs_launder_page(page); diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 572dd29fbd54..884cdf134f3e 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -239,10 +239,6 @@ struct orangefs_write_range { kgid_t gid; }; -struct orangefs_read_options { - ssize_t blksiz; -}; - extern struct orangefs_stats orangefs_stats; /* diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 73c9775215b3..11dd8177770d 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -482,7 +482,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, if (IS_ERR_OR_NULL(this)) return this; - if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) { + if (ovl_dentry_real_at(this, layer->idx) != real) { dput(this); this = ERR_PTR(-EIO); } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 15e4fa288475..7a08a576f7b2 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -21,13 +21,16 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode) return 'm'; } +/* No atime modificaton nor notify on underlying */ +#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY) + static struct file *ovl_open_realfile(const struct file *file, struct inode *realinode) { struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; - int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY; + int flags = file->f_flags | OVL_OPEN_FLAGS; old_cred = ovl_override_creds(inode->i_sb); realfile = open_with_fake_path(&file->f_path, flags, realinode, @@ -48,8 +51,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags) struct inode *inode = file_inode(file); int err; - /* No atime modificaton on underlying */ - flags |= O_NOATIME | FMODE_NONOTIFY; + flags |= OVL_OPEN_FLAGS; /* If some flag changed that cannot be changed then something's amiss */ if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK)) @@ -102,7 +104,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, } /* Did the flags change since open? */ - if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME)) + if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS)) return ovl_change_flags(real->file, file->f_flags); return 0; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 1e4cb019defd..d6b724beb304 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1258,6 +1258,18 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) if (!ofs->config.nfs_export && !ofs->upper_mnt) return true; + /* + * We allow using single lower with null uuid for index and nfs_export + * for example to support those features with single lower squashfs. + * To avoid regressions in setups of overlay with re-formatted lower + * squashfs, do not allow decoding origin with lower null uuid unless + * user opted-in to one of the new features that require following the + * lower inode of non-dir upper. + */ + if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino && + uuid_is_null(uuid)) + return false; + for (i = 0; i < ofs->numlowerfs; i++) { /* * We use uuid to associate an overlay lower file handle with a diff --git a/fs/proc/base.c b/fs/proc/base.c index e781af70d10d..97aee11aee79 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2038,7 +2038,7 @@ 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 14c2badb8fd9..65afe5287e43 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -41,7 +41,10 @@ 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 7f84d1477b5b..3d9ee997b3d0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -309,7 +309,10 @@ 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; @@ -1774,7 +1777,7 @@ 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 mm_walk walk = { .hugetlb_entry = gather_hugetlb_stats, diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 7907e6419e57..d17209cf52bc 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/pstore/platform.c b/fs/pstore/platform.c index cdf5b8ae2583..74a60bae2b23 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -275,6 +275,9 @@ static int pstore_compress(const void *in, void *out, { int ret; + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION)) + return -EINVAL; + ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); if (ret) { pr_err("crypto_comp_compress failed, ret = %d!\n", ret); @@ -661,7 +664,7 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *unzipped, *workspace; - if (!record->compressed) + if (!IS_ENABLED(CONFIG_PSTORE_COMPRESSION) || !record->compressed) return; /* Only PSTORE_TYPE_DMESG support compression. */ diff --git a/fs/read_write.c b/fs/read_write.c index 35ea7a676484..95b3f902fd19 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -468,6 +468,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) 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) { @@ -498,6 +499,30 @@ static ssize_t __vfs_write(struct file *file, const char __user *p, return -EINVAL; } +vfs_readf_t vfs_readf(struct file *file) +{ + const struct file_operations *fop = file->f_op; + + if (fop->read) + return fop->read; + if (fop->read_iter) + return new_sync_read; + return ERR_PTR(-ENOSYS); +} +EXPORT_SYMBOL_GPL(vfs_readf); + +vfs_writef_t vfs_writef(struct file *file) +{ + const struct file_operations *fop = file->f_op; + + if (fop->write) + return fop->write; + if (fop->write_iter) + return new_sync_write; + return ERR_PTR(-ENOSYS); +} +EXPORT_SYMBOL_GPL(vfs_writef); + ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; @@ -566,6 +591,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return ret; } +EXPORT_SYMBOL_GPL(vfs_write); /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) diff --git a/fs/splice.c b/fs/splice.c index 81980805de2b..e3059110adb6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -834,8 +834,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); /* * Attempt to initiate a splice from pipe to file. */ -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); @@ -847,13 +847,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return splice_write(pipe, out, ppos, len, flags); } +EXPORT_SYMBOL_GPL(do_splice_from); /* * Attempt to initiate a splice from a file to a pipe. */ -static long do_splice_to(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -876,6 +877,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, return splice_read(in, ppos, pipe, len, flags); } +EXPORT_SYMBOL_GPL(do_splice_to); /** * splice_direct_to_actor - splices data directly between two non-pipes diff --git a/fs/sync.c b/fs/sync.c index 4d1ff010bc5a..67c66358f3fe 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/ubifs/journal.c b/fs/ubifs/journal.c index 826dad0243dc..a6ae2428e4c9 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -539,7 +539,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, const struct fscrypt_name *nm, const struct inode *inode, int deletion, int xent) { - int err, dlen, ilen, len, lnum, ino_offs, dent_offs; + int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0; int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir); int last_reference = !!(deletion && inode->i_nlink == 0); struct ubifs_inode *ui = ubifs_inode(inode); @@ -630,6 +630,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, goto out_finish; } ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync); @@ -702,7 +703,7 @@ out_release: kfree(dent); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, inode->i_ino); finish_reservation(c); return err; @@ -1217,7 +1218,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, void *p; union ubifs_key key; struct ubifs_dent_node *dent, *dent2; - int err, dlen1, dlen2, ilen, lnum, offs, len; + int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0; int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ; int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); @@ -1333,6 +1334,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, goto out_finish; } new_ui->del_cmtno = c->cmt_no; + orphan_added = 1; } err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync); @@ -1414,7 +1416,7 @@ out_release: release_head(c, BASEHD); out_ro: ubifs_ro_mode(c, err); - if (last_reference) + if (orphan_added) ubifs_delete_orphan(c, new_inode->i_ino); out_finish: finish_reservation(c); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 3d247c0d92aa..15677eebef4c 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -101,7 +101,7 @@ static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 gene struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; struct inode *inode; - if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg) + if (ino < UFS_ROOTINO || ino > (u64)uspi->s_ncg * uspi->s_ipg) return ERR_PTR(-ESTALE); inode = ufs_iget(sb, ino); diff --git a/fs/xattr.c b/fs/xattr.c index 90dd78f0eb27..494313bce9cc 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, return error; } - +/** + * __vfs_setxattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - xattr name to set + * @value - value to set @name to + * @size - size of @value + * @flags - flags to pass into filesystem operations + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +__vfs_setxattr_locked(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (error) return error; - inode_lock(inode); error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); + +int +vfs_setxattr(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_setxattr_locked(dentry, name, value, size, flags, + &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); @@ -296,6 +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, @@ -378,8 +416,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name) } EXPORT_SYMBOL(__vfs_removexattr); +/** + * __vfs_removexattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - name of xattr to remove + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_removexattr(struct dentry *dentry, const char *name) +__vfs_removexattr_locked(struct dentry *dentry, const char *name, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -388,11 +436,14 @@ vfs_removexattr(struct dentry *dentry, const char *name) if (error) return error; - inode_lock(inode); error = security_inode_removexattr(dentry, name); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_removexattr(dentry, name); if (!error) { @@ -401,12 +452,32 @@ vfs_removexattr(struct dentry *dentry, const char *name) } out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); + +int +vfs_removexattr(struct dentry *dentry, const char *name) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } + return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); - /* * Extended attribute SET operations */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 1f6e3965ff74..f09dcf9a96ee 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -926,8 +926,10 @@ xfs_attr_shortform_verify( * struct xfs_attr_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. + * xfs_attr_sf_entry is defined with a 1-byte variable + * array at the end, so we must subtract that off. */ - if (((char *)sfep + sizeof(*sfep)) >= endp) + if (((char *)sfep + sizeof(*sfep) - 1) >= endp) return __this_address; /* Don't allow names with known bad length. */ diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index a62fb950bef1..0c02d76eeb4d 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -57,7 +57,7 @@ XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK) #define XFS_IALLOC_SPACE_RES(mp) \ ((mp)->m_ialloc_blks + \ - (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \ + ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \ ((mp)->m_in_maxlevels - 1))) /* diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index a703cd58a90e..3fe938968348 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -53,9 +53,27 @@ xchk_setup_inode_bmap( */ if (S_ISREG(VFS_I(sc->ip)->i_mode) && sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) { + struct address_space *mapping = VFS_I(sc->ip)->i_mapping; + inode_dio_wait(VFS_I(sc->ip)); - error = filemap_write_and_wait(VFS_I(sc->ip)->i_mapping); - if (error) + + /* + * Try to flush all incore state to disk before we examine the + * space mappings for the data fork. Leave accumulated errors + * in the mapping for the writer threads to consume. + * + * On ENOSPC or EIO writeback errors, we continue into the + * extent mapping checks because write failures do not + * necessarily imply anything about the correctness of the file + * metadata. The metadata and the file data could be on + * completely separate devices; a media failure might only + * affect a subset of the disk, etc. We can handle delalloc + * extents in the scrubber, so leaving them in memory is fine. + */ + error = filemap_fdatawrite(mapping); + if (!error) + error = filemap_fdatawait_keep_errors(mapping); + if (error && (error != -ENOSPC && error != -EIO)) goto out; } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 96add09582db..5919e1714d5f 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1023,6 +1023,7 @@ xfs_reflink_remap_extent( xfs_filblks_t rlen; xfs_filblks_t unmap_len; xfs_off_t newlen; + int64_t qres; int error; unmap_len = irec->br_startoff + irec->br_blockcount - destoff; @@ -1045,13 +1046,19 @@ xfs_reflink_remap_extent( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - /* If we're not just clearing space, then do we have enough quota? */ - if (real_extent) { - error = xfs_trans_reserve_quota_nblks(tp, ip, - irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS); - if (error) - goto out_cancel; - } + /* + * Reserve quota for this operation. We don't know if the first unmap + * in the dest file will cause a bmap btree split, so we always reserve + * at least enough blocks for that split. If the extent being mapped + * in is written, we need to reserve quota for that too. + */ + qres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); + if (real_extent) + qres += irec->br_blockcount; + error = xfs_trans_reserve_quota_nblks(tp, ip, qres, 0, + XFS_QMOPT_RES_REGBLKS); + if (error) + goto out_cancel; trace_xfs_reflink_remap(ip, irec->br_startoff, irec->br_blockcount, irec->br_startblock); 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..f9a9fb1bfdd4 --- /dev/null +++ b/fs/yaffs2/Makefile @@ -0,0 +1,18 @@ +# +# 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_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..c8f2861c53ee --- /dev/null +++ b/fs/yaffs2/yaffs_allocator.c @@ -0,0 +1,357 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..a8cc3226421f --- /dev/null +++ b/fs/yaffs2/yaffs_allocator.h @@ -0,0 +1,30 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..fdc7f2162ce6 --- /dev/null +++ b/fs/yaffs2/yaffs_attribs.c @@ -0,0 +1,124 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" + +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 = ia_uid_read(attr); + if (valid & ATTR_GID) + obj->yst_gid = ia_gid_read(attr); + + 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; + ia_uid_write( attr, obj->yst_uid ); + valid |= ATTR_UID; + ia_gid_write( attr, 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..121d99d38b48 --- /dev/null +++ b/fs/yaffs2/yaffs_attribs.h @@ -0,0 +1,71 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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); + + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 5, 0)) +static inline uid_t ia_uid_read(const struct iattr *iattr) +{ + return from_kuid(&init_user_ns, iattr->ia_uid); +} + +static inline gid_t ia_gid_read(const struct iattr *iattr) +{ + return from_kgid(&init_user_ns, iattr->ia_gid); +} + +static inline void ia_uid_write(struct iattr *iattr, uid_t uid) +{ + iattr->ia_uid = make_kuid(&init_user_ns, uid); +} + +static inline void ia_gid_write(struct iattr *iattr, gid_t gid) +{ + iattr->ia_gid = make_kgid(&init_user_ns, gid); +} +#else +static inline uid_t ia_uid_read(const struct iattr *iattr) +{ + return iattr->ia_uid; +} + +static inline gid_t ia_gid_read(const struct iattr *inode) +{ + return iattr->ia_gid; +} + +static inline void ia_uid_write(struct iattr *iattr, uid_t uid) +{ + iattr->ia_uid = uid; +} + +static inline void ia_gid_write(struct iattr *iattr, gid_t gid) +{ + iattr->ia_gid = gid; +} +#endif + +#endif diff --git a/fs/yaffs2/yaffs_bitmap.c b/fs/yaffs2/yaffs_bitmap.c new file mode 100644 index 000000000000..4440e930d6bc --- /dev/null +++ b/fs/yaffs2/yaffs_bitmap.c @@ -0,0 +1,97 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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 < dev->internal_start_block || blk > 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 < dev->internal_start_block || blk > dev->internal_end_block || + chunk < 0 || chunk >= 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..e26b37d89ae4 --- /dev/null +++ b/fs/yaffs2/yaffs_bitmap.h @@ -0,0 +1,33 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..e739fb4a104b --- /dev/null +++ b/fs/yaffs2/yaffs_checkptrw.c @@ -0,0 +1,474 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" + +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_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); + + 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)); + + 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) +{ + int 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) +{ + int 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 <= 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) +{ + int 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) +{ + int 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; + 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 >= 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 >= 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; + int ok = 1; + 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 && ok) { + + if (dev->checkpt_byte_offs < 0 || + dev->checkpt_byte_offs >= dev->data_bytes_per_chunk) { + + if (dev->checkpt_cur_block < 0) { + yaffs2_checkpt_find_block(dev); + dev->checkpt_cur_chunk = 0; + } + + if (dev->checkpt_cur_block < 0) { + ok = 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); + + if (tags.chunk_id != (dev->checkpt_page_seq + 1) || + tags.ecc_result > YAFFS_ECC_RESULT_FIXED || + tags.seq_number != YAFFS_SEQUENCE_CHECKPOINT_DATA) { + ok = 0; + break; + } + if(!yaffs2_checkpt_check_chunk_hdr(dev)) { + ok = 0; + break; + } + + dev->checkpt_page_seq++; + dev->checkpt_cur_chunk++; + + if (dev->checkpt_cur_chunk >= + 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; +} + +int yaffs_checkpt_close(struct yaffs_dev *dev) +{ + int 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 (dev->internal_start_block <= blk && + blk <= 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; + } + kfree(dev->checkpt_block_list); + dev->checkpt_block_list = NULL; + } + + 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) { + /* free the buffer */ + kfree(dev->checkpt_buffer); + dev->checkpt_buffer = NULL; + 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..cdbaba7153ed --- /dev/null +++ b/fs/yaffs2/yaffs_checkptrw.h @@ -0,0 +1,33 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..9294107c150d --- /dev/null +++ b/fs/yaffs2/yaffs_ecc.c @@ -0,0 +1,281 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..17d47bd80f3e --- /dev/null +++ b/fs/yaffs2/yaffs_ecc.h @@ -0,0 +1,44 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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_getblockinfo.h b/fs/yaffs2/yaffs_getblockinfo.h new file mode 100644 index 000000000000..8fd0802bdddb --- /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) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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 < dev->internal_start_block || blk > 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..1fd464d68af7 --- /dev/null +++ b/fs/yaffs2/yaffs_guts.c @@ -0,0 +1,5082 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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_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 (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 (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) +{ + int 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 < dev->internal_start_block + || dev->alloc_block_finder > 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 < 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) +{ + int 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 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 == chunk_obj && + tags->obj_id == 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_file_cache(struct yaffs_obj *obj) +{ + struct yaffs_dev *dev = obj->my_dev; + int lowest = -99; /* Stop compiler whining. */ + int i; + struct yaffs_cache *cache; + int chunk_written = 0; + int n_caches = obj->my_dev->param.n_caches; + + if (n_caches < 1) + return; + do { + cache = NULL; + + /* Find the lowest dirty chunk for this object */ + for (i = 0; i < n_caches; i++) { + if (dev->cache[i].object == obj && + dev->cache[i].dirty) { + if (!cache || + dev->cache[i].chunk_id < lowest) { + cache = &dev->cache[i]; + lowest = cache->chunk_id; + } + } + } + + if (cache && !cache->locked) { + /* Write it out and free it up */ + chunk_written = + yaffs_wr_data_obj(cache->object, + cache->chunk_id, + cache->data, + cache->n_bytes, 1); + cache->dirty = 0; + cache->object = NULL; + } + } while (cache && chunk_written > 0); + + if (cache) + /* Hoosterman, disk full while writing cache out. */ + yaffs_trace(YAFFS_TRACE_ERROR, + "yaffs tragedy: no space during cache write"); +} + +/*yaffs_flush_whole_cache(dev) + * + * + */ + +void yaffs_flush_whole_cache(struct yaffs_dev *dev) +{ + 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); + } while (obj); + +} + +/* Grab us a 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) +{ + int 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; + struct yaffs_obj *the_obj; + int usage; + int i; + int pushout; + + if (dev->param.n_caches < 1) + return NULL; + + /* Try find a non-dirty one... */ + + cache = yaffs_grab_chunk_worker(dev); + + if (!cache) { + /* They were all dirty, find the LRU object and flush + * its cache, then find again. + * NB what's here is not very accurate, + * we actually flush the object with the LRU chunk. + */ + + /* With locking we can't assume we can use entry zero, + * Set the_obj to a valid pointer for Coverity. */ + the_obj = dev->cache[0].object; + usage = -1; + cache = NULL; + pushout = -1; + + 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; + the_obj = dev->cache[i].object; + cache = &dev->cache[i]; + pushout = i; + } + } + + if (!cache || cache->dirty) { + /* Flush and try again */ + yaffs_flush_file_cache(the_obj); + cache = yaffs_grab_chunk_worker(dev); + } + } + 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; + int 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) +{ + int 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) +{ + int 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. + */ + + while (!found) { + found = 1; + n += YAFFS_NOBJECT_BUCKETS; + if (1 || dev->obj_bucket[bucket].count > 0) { + list_for_each(i, &dev->obj_bucket[bucket].list) { + /* If there is already one in the list */ + 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.scanned_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; + int 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 == 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 == 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. + */ + 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(oh, + object->variant.file_variant.file_size); + tags.extra_file_size = + object->variant.file_variant.file_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; + int 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) +{ + int i; + int iterations; + unsigned selected = 0; + int prioritised = 0; + int prioritised_exist = 0; + struct yaffs_block_info *bi; + int 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) { + int 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 { + int 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 < (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 < 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; + + 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 > dev->param.total_bytes_per_chunk) { + yaffs_trace(YAFFS_TRACE_ERROR, + "Writing %d bytes to chunk!!!!!!!!!", + n_bytes); + BUG(); + } + + 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(x_buffer, x_size, xmod->name, xmod->data, + xmod->size, xmod->flags); + else + retval = nval_del(x_buffer, x_size, xmod->name); + + obj->has_xattr = nval_hasvalues(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(x_buffer, x_size); + obj->xattr_known = 1; + } + + if (name) + retval = nval_get(x_buffer, x_size, name, value, size); + else + retval = nval_list(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; + int alloc_failed = 0; + + if (!in || !in->lazy_loaded || in->hdr_chunk < 1) + return; + + dev = in->my_dev; + in->lazy_loaded = 0; + buf = yaffs_get_temp_buffer(dev); + + result = yaffs_rd_chunk_tags_nand(dev, in->hdr_chunk, buf, &tags); + oh = (struct yaffs_obj_hdr *)buf; + + 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); + if (!in->variant.symlink_variant.alias) + alloc_failed = 1; /* Not returned */ + } + yaffs_release_temp_buffer(dev, buf); +} + +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; + 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); + } +} + +/* UpdateObjectHeader updates the header on NAND for an object. + * If name is not NULL, then that new name is used. + */ +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) { + result = yaffs_rd_chunk_tags_nand(dev, prev_chunk_id, + buffer, &old_tags); + + yaffs_verify_oh(in, oh, &old_tags, 0); + memcpy(old_name, oh->name, sizeof(oh->name)); + memset(buffer, 0xff, sizeof(struct yaffs_obj_hdr)); + } 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.file_size; + yaffs_oh_size_load(oh, file_size); + 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; + 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 != 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", + 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 > 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 != 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 (chunk_id < + (dev->internal_start_block * dev->param.chunks_per_block) || + 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; + + 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); + 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) +{ + if (!in->dirty) + return YAFFS_OK; + + yaffs_flush_file_cache(in); + + 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 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); + } +} + +static 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); + } + 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 = dev->root_dir = NULL; + dev->unlinked_dir = 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) { + 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_format_dev(struct yaffs_dev *dev) +{ + int 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; + unsigned x; + int 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; + + /* 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) { + int i; + void *buf; + int 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) { + int 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->is_mounted = 0; + + yaffs_deinit_nand(dev); + } +} + +int yaffs_count_free_chunks(struct yaffs_dev *dev) +{ + int n_free = 0; + int 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; + int 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_obj_hdr *oh, loff_t fsize) +{ + oh->file_size_low = (fsize & 0xFFFFFFFF); + oh->file_size_high = ((fsize >> 32) & 0xFFFFFFFF); +} + +loff_t yaffs_oh_to_size(struct yaffs_obj_hdr *oh) +{ + loff_t retval; + + if (sizeof(loff_t) >= 8 && ~(oh->file_size_high)) + retval = (((loff_t) oh->file_size_high) << 32) | + (((loff_t) oh->file_size_low) & 0xFFFFFFFF); + else + retval = (loff_t) oh->file_size_low; + + return retval; +} + + +void yaffs_count_blocks_by_state(struct yaffs_dev *dev, int bs[10]) +{ + int 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..05785367cb2e --- /dev/null +++ b/fs/yaffs2/yaffs_guts.h @@ -0,0 +1,1003 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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 +#define YAFFS_CHECKPOINT_VERSION 7 + +#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 { + unsigned chunk_id:20; + unsigned serial_number:2; + unsigned n_bytes_lsb:10; + unsigned obj_id:18; + unsigned ecc:12; + unsigned n_bytes_msb:2; +}; + +union yaffs_tags_union { + struct yaffs_tags as_tags; + u8 as_bytes[8]; +}; + + +/* 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 +}; + +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 { + + int soft_del_pages:10; /* number of soft deleted pages */ + int pages_in_use:10; /* number of pages in use */ + unsigned 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 */ + +}; + +/* -------------------------- Object structure -------------------------------*/ +/* This is the object structure as stored on NAND */ + +struct yaffs_obj_hdr { + enum yaffs_obj_type type; + + /* Apply to everything */ + int 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 + */ + +struct yaffs_file_var { + loff_t file_size; + loff_t scanned_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; + + enum yaffs_obj_type variant_type; + + union yaffs_obj_var variant; + +}; + +struct yaffs_obj_bucket { + struct list_head list; + int count; +}; + +/* yaffs_checkpt_obj holds the definition of an object as dumped + * by checkpointing. + */ + +struct yaffs_checkpt_obj { + int struct_type; + u32 obj_id; + u32 parent_id; + int hdr_chunk; + enum yaffs_obj_type variant_type:3; + u8 deleted:1; + u8 soft_del:1; + u8 unlinked:1; + u8 fake:1; + u8 rename_allowed:1; + u8 unlink_allowed:1; + u8 serial; + int n_data_chunks; + loff_t size_or_equiv_obj; +}; + +/*--------------------- 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 */ + int chunks_per_block; /* does not need to be a power of 2 */ + int spare_bytes_per_chunk; /* spare area size */ + int start_block; /* Start block we're allowed to use */ + int end_block; /* End block we're allowed to use */ + int n_reserved_blocks; /* Tuneable so that we can reduce + * reserved blocks on NOR and RAM. */ + + int 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. + */ + + /* 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. */ + int 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 */ + + /* 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; + + /* Stuff to support block offsetting to support start block zero */ + int internal_start_block; + int 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; + int blocks_in_checkpt; + int checkpt_cur_chunk; + int checkpt_cur_block; + int checkpt_next_block; + int *checkpt_block_list; + int 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 */ + unsigned block_info_alt:1; /* allocated using alternative alloc */ + unsigned 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_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; + +}; + +/* 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_unlinker(struct yaffs_obj *dir, const YCHAR * name); +int yaffs_del_obj(struct yaffs_obj *obj); + +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 *obj, int update_time, int data_sync); + +/* Flushing and checkpointing */ +void yaffs_flush_whole_cache(struct yaffs_dev *dev); + +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_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 aand out of + * object headers. + */ +void yaffs_oh_size_load(struct yaffs_obj_hdr *oh, loff_t fsize); +loff_t yaffs_oh_to_size(struct yaffs_obj_hdr *oh); +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); + +#endif diff --git a/fs/yaffs2/yaffs_linux.h b/fs/yaffs2/yaffs_linux.h new file mode 100644 index 000000000000..c20ab14b7fa2 --- /dev/null +++ b/fs/yaffs2/yaffs_linux.h @@ -0,0 +1,48 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..054e251a2c18 --- /dev/null +++ b/fs/yaffs2/yaffs_mtdif.c @@ -0,0 +1,308 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" +#include "linux/mtd/rawnand.h" +#include "linux/kernel.h" +#include "linux/version.h" +#include "linux/types.h" + +#include "uapi/linux/major.h" + +#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; + + ei.addr = addr; + ei.len = dev->param.total_bytes_per_chunk * dev->param.chunks_per_block; + + 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; + + ei.addr = addr; + ei.len = block_size; + + 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..9cff224c6dec --- /dev/null +++ b/fs/yaffs2/yaffs_mtdif.h @@ -0,0 +1,25 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..4bdf4ed743a7 --- /dev/null +++ b/fs/yaffs2/yaffs_nameval.c @@ -0,0 +1,208 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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(int) 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 "yportenv.h" + +static int nval_find(const char *xb, int xb_size, const YCHAR *name, + int *exist_size) +{ + int pos = 0; + int size; + + memcpy(&size, xb, sizeof(int)); + while (size > 0 && (size < xb_size) && (pos + size < xb_size)) { + if (!strncmp((YCHAR *) (xb + pos + sizeof(int)), + name, size)) { + if (exist_size) + *exist_size = size; + return pos; + } + pos += size; + if (pos < xb_size - sizeof(int)) + memcpy(&size, xb + pos, sizeof(int)); + else + size = 0; + } + if (exist_size) + *exist_size = 0; + return -ENODATA; +} + +static int nval_used(const char *xb, int xb_size) +{ + int pos = 0; + int size; + + memcpy(&size, xb + pos, sizeof(int)); + while (size > 0 && (size < xb_size) && (pos + size < xb_size)) { + pos += size; + if (pos < xb_size - sizeof(int)) + memcpy(&size, xb + pos, sizeof(int)); + else + size = 0; + } + return pos; +} + +int nval_del(char *xb, int xb_size, const YCHAR *name) +{ + int pos = nval_find(xb, xb_size, name, NULL); + int 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(int)); + memcpy(xb + pos, xb + pos + size, xb_size - (pos + size)); + memset(xb + (xb_size - size), 0, size); + return 0; +} + +int nval_set(char *xb, int xb_size, const YCHAR *name, const char *buf, + int bsize, int flags) +{ + int pos; + int namelen = strnlen(name, xb_size); + int reclen; + int size_exist = 0; + int space; + int start; + + pos = nval_find(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(xb, xb_size); + space = xb_size - start + size_exist; + + reclen = (sizeof(int) + namelen + 1 + bsize); + + if (reclen > space) + return -ENOSPC; + + if (pos >= 0) { + nval_del(xb, xb_size, name); + start = nval_used(xb, xb_size); + } + + pos = start; + + memcpy(xb + pos, &reclen, sizeof(int)); + pos += sizeof(int); + strncpy((YCHAR *) (xb + pos), name, reclen); + pos += (namelen + 1); + memcpy(xb + pos, buf, bsize); + return 0; +} + +int nval_get(const char *xb, int xb_size, const YCHAR * name, char *buf, + int bsize) +{ + int pos = nval_find(xb, xb_size, name, NULL); + int size; + + if (pos >= 0 && pos < xb_size) { + + memcpy(&size, xb + pos, sizeof(int)); + pos += sizeof(int); /* advance past record length */ + size -= sizeof(int); + + /* 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(const char *xb, int xb_size, char *buf, int bsize) +{ + int pos = 0; + int size; + int name_len; + int ncopied = 0; + int filled = 0; + + memcpy(&size, xb + pos, sizeof(int)); + while (size > sizeof(int) && + size <= xb_size && + (pos + size) < xb_size && + !filled) { + pos += sizeof(int); + size -= sizeof(int); + 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 < xb_size - sizeof(int)) + memcpy(&size, xb + pos, sizeof(int)); + else + size = 0; + } + return ncopied; +} + +int nval_hasvalues(const char *xb, int xb_size) +{ + return nval_used(xb, xb_size) > 0; +} diff --git a/fs/yaffs2/yaffs_nameval.h b/fs/yaffs2/yaffs_nameval.h new file mode 100644 index 000000000000..951e64f872b6 --- /dev/null +++ b/fs/yaffs2/yaffs_nameval.h @@ -0,0 +1,28 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" + +int nval_del(char *xb, int xb_size, const YCHAR * name); +int nval_set(char *xb, int xb_size, const YCHAR * name, const char *buf, + int bsize, int flags); +int nval_get(const char *xb, int xb_size, const YCHAR * name, char *buf, + int bsize); +int nval_list(const char *xb, int xb_size, char *buf, int bsize); +int nval_hasvalues(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..0d8499bdc630 --- /dev/null +++ b/fs/yaffs2/yaffs_nand.c @@ -0,0 +1,122 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..804e97ad66d0 --- /dev/null +++ b/fs/yaffs2/yaffs_nand.h @@ -0,0 +1,39 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..dd9a331d8fc4 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags1.c @@ -0,0 +1,56 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..b80f0a5b1574 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags1.h @@ -0,0 +1,39 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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 { + unsigned chunk_id:20; + unsigned serial_number:2; + unsigned n_bytes:10; + unsigned obj_id:18; + unsigned ecc:12; + unsigned deleted:1; + unsigned 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..e1d18cc33c68 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags2.c @@ -0,0 +1,197 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" + +/* 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_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); +} + +void yaffs_pack_tags2(struct yaffs_packed_tags2 *pt, + const struct yaffs_ext_tags *t, int tags_ecc) +{ + yaffs_pack_tags2_tags_only(&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_ext_tags *t, + struct yaffs_packed_tags2_tags_only *ptt) +{ + memset(t, 0, sizeof(struct yaffs_ext_tags)); + + if (ptt->seq_number == 0xffffffff) + return; + + t->block_bad = 0; + t->chunk_used = 1; + t->obj_id = ptt->obj_id; + t->chunk_id = ptt->chunk_id; + t->n_bytes = ptt->n_bytes; + t->is_deleted = 0; + t->serial_number = 0; + t->seq_number = ptt->seq_number; + + /* Do extra header info stuff */ + if (ptt->chunk_id & EXTRA_HEADER_INFO_FLAG) { + t->chunk_id = 0; + t->n_bytes = 0; + + t->extra_available = 1; + t->extra_parent_id = ptt->chunk_id & (~(ALL_EXTRA_FLAGS)); + t->extra_is_shrink = ptt->chunk_id & EXTRA_SHRINK_FLAG ? 1 : 0; + t->extra_shadows = ptt->chunk_id & EXTRA_SHADOWS_FLAG ? 1 : 0; + t->extra_obj_type = ptt->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->n_bytes; + else + t->extra_file_size = ptt->n_bytes; + } + yaffs_dump_packed_tags2_tags_only(ptt); + yaffs_dump_tags2(t); +} + +void yaffs_unpack_tags2(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(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..675e719460a8 --- /dev/null +++ b/fs/yaffs2/yaffs_packedtags2.h @@ -0,0 +1,47 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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_packed_tags2 *pt, + const struct yaffs_ext_tags *t, int tags_ecc); +void yaffs_unpack_tags2(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_packed_tags2_tags_only *pt, + const struct yaffs_ext_tags *t); +void yaffs_unpack_tags2_tags_only(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..6f3c7839fa6f --- /dev/null +++ b/fs/yaffs2/yaffs_summary.c @@ -0,0 +1,313 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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; + int 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); + int sum_tags_bytes; + + sum_tags_bytes = sizeof(struct yaffs_summary_tags) * + dev->chunks_per_summary; + 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.block != blk || + 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(&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(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); + int 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..be141d073369 --- /dev/null +++ b/fs/yaffs2/yaffs_summary.h @@ -0,0 +1,37 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..092430beccb7 --- /dev/null +++ b/fs/yaffs2/yaffs_tagscompat.c @@ -0,0 +1,381 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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_tagscompat.h" +#include "yaffs_ecc.h" +#include "yaffs_getblockinfo.h" +#include "yaffs_trace.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 **********/ + +static void yaffs_load_tags_to_spare(struct yaffs_spare *spare_ptr, + struct yaffs_tags *tags_ptr) +{ + union yaffs_tags_union *tu = (union yaffs_tags_union *)tags_ptr; + + yaffs_calc_tags_ecc(tags_ptr); + + spare_ptr->tb0 = tu->as_bytes[0]; + spare_ptr->tb1 = tu->as_bytes[1]; + spare_ptr->tb2 = tu->as_bytes[2]; + spare_ptr->tb3 = tu->as_bytes[3]; + spare_ptr->tb4 = tu->as_bytes[4]; + spare_ptr->tb5 = tu->as_bytes[5]; + spare_ptr->tb6 = tu->as_bytes[6]; + spare_ptr->tb7 = tu->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; + int result; + + tu->as_bytes[0] = spare_ptr->tb0; + tu->as_bytes[1] = spare_ptr->tb1; + tu->as_bytes[2] = spare_ptr->tb2; + tu->as_bytes[3] = spare_ptr->tb3; + tu->as_bytes[4] = spare_ptr->tb4; + tu->as_bytes[5] = spare_ptr->tb5; + tu->as_bytes[6] = spare_ptr->tb6; + tu->as_bytes[7] = spare_ptr->tb7; + + 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(&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..92d298a6f582 --- /dev/null +++ b/fs/yaffs2/yaffs_tagscompat.h @@ -0,0 +1,44 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..44a83b12ca4d --- /dev/null +++ b/fs/yaffs2/yaffs_tagsmarshall.c @@ -0,0 +1,199 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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_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(pt2tp, tags); + } else { + yaffs_pack_tags2(&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 (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(tags, pt2tp); + } + } else if (tags) { + memcpy(packed_tags_ptr, spare_buffer, packed_tags_size); + yaffs_unpack_tags2(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..bf3e68a1a5be --- /dev/null +++ b/fs/yaffs2/yaffs_tagsmarshall.h @@ -0,0 +1,22 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..fd26054d3912 --- /dev/null +++ b/fs/yaffs2/yaffs_trace.h @@ -0,0 +1,57 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..e8f2f0a6c2be --- /dev/null +++ b/fs/yaffs2/yaffs_verify.c @@ -0,0 +1,529 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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 > dev->param.chunks_per_block || + bi->soft_del_pages < 0 || + bi->soft_del_pages > dev->param.chunks_per_block || + actually_used < 0 || actually_used > 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) +{ + int i; + int 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 != 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 actual_depth; + int last_chunk; + u32 offset_in_chunk; + u32 the_chunk; + + u32 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++; + } + + actual_depth = obj->variant.file_variant.top_level; + + /* 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 != 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; + + if (!directory) { + BUG(); + 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..4f4af8d29aa4 --- /dev/null +++ b/fs/yaffs2/yaffs_verify.h @@ -0,0 +1,43 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..db77316a0f95 --- /dev/null +++ b/fs/yaffs2/yaffs_vfs.c @@ -0,0 +1,3673 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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(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)) +#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) +#else +#define Y_INIT_TIMER(a) timer_setup_on_stack(a, NULL, 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 <linux/cred.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 + + +#define update_dir_time(dir) do {\ + (dir)->i_ctime = (dir)->i_mtime = current_time(dir); \ + } while (0) + +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(f->f_path.dentry); + + 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_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_SHIFT; + + if (page->index < end_index) + n_bytes = PAGE_SIZE; + else { + n_bytes = i_size & (PAGE_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_SHIFT, + inode->i_size); + yaffs_trace(YAFFS_TRACE_OS, + " -> don't care!!"); + + zero_user_segment(page, 0, PAGE_SIZE); + set_page_writeback(page); + unlock_page(page); + end_page_writeback(page); + return 0; + } + } + + if (n_bytes != PAGE_SIZE) + zero_user_segment(page, n_bytes, PAGE_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_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_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(f->f_path.dentry); + + 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(f->f_path.dentry); + + 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_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); + put_page(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(f->f_path.dentry); + + 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 = f->f_path.dentry->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_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); + put_page(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_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(3, 5, 0)) +#define YCRED_FSUID() from_kuid(&init_user_ns, current_fsuid()) +#define YCRED_FSGID() from_kgid(&init_user_ns, current_fsgid()) +#else +#define YCRED_FSUID() YCRED(current)->fsuid +#define YCRED_FSGID() YCRED(current)->fsgid + +static inline uid_t i_uid_read(const struct inode *inode) +{ + return inode->i_uid; +} + +static inline gid_t i_gid_read(const struct inode *inode) +{ + return inode->i_gid; +} + +static inline void i_uid_write(struct inode *inode, uid_t uid) +{ + inode->i_uid = uid; +} + +static inline void i_gid_write(struct inode *inode, gid_t gid) +{ + inode->i_gid = gid; +} +#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(file->f_path.dentry); + + 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); + + 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); + yaffs_gross_unlock(dev); + return 0; +} + + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 22)) +static const struct file_operations yaffs_file_operations = { + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap = generic_file_mmap, + .flush = yaffs_file_flush, + .fsync = yaffs_sync_object, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .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; +} + +static int yaffs_setxattr(struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) +{ + 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; +} + +static ssize_t yaffs_getxattr(struct dentry * dentry, struct inode *inode, + const char *name, void *buff, size_t size) +{ + 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; +} + +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, + .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; + + ret = readlink_copy(buffer, buflen, alias); + kfree(alias); + return ret; +} + +#if (YAFFS_NEW_FOLLOW_LINK == 1) +static const char *yaffs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + 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; + + 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) { + ret_int = -ENOMEM; + goto out; + } +#if (YAFFS_NEW_FOLLOW_LINK == 1) + set_delayed_call(done, kfree_link, 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 +} + + +#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 + +static const struct inode_operations yaffs_symlink_inode_operations = { + .readlink = yaffs_readlink, +#if (YAFFS_NEW_FOLLOW_LINK == 1) + .get_link = yaffs_get_link, +#else + .follow_link = yaffs_follow_link, +#endif + .setattr = yaffs_setattr, + .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, 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 = YCRED_FSUID(); + gid_t gid = (dir->i_mode & S_ISGID) ? i_gid_read(dir) : YCRED_FSGID(); + + 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 = YCRED_FSUID(); + gid_t gid = (dir->i_mode & S_ISGID) ? i_gid_read(dir) : YCRED_FSGID(); + + 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 + */ +static int yaffs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct yaffs_dev *dev; + int ret_val = YAFFS_FAIL; + struct yaffs_obj *target; + + if (flags) + return -EINVAL; + + 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); + atomic64_inc(&dir->i_version); + 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, +}; + +/*-----------------------------------------------------------------*/ +/* 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); + } + +} + + +/*-----------------------------------------------------------------*/ + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 12, 0)) +static int yaffs_readdir(struct file *file, struct dir_context *ctx) +{ + struct yaffs_obj *obj; + struct yaffs_dev *dev; + struct yaffs_search_context *sc; + struct inode *inode = file->f_path.dentry->d_inode; + unsigned long offset, curoffs; + struct yaffs_obj *l; + int ret_val = 0; + + char name[YAFFS_MAX_NAME_LENGTH + 1]; + u64 i_version; + + obj = yaffs_dentry_to_obj(file->f_path.dentry); + dev = obj->my_dev; + + yaffs_gross_lock(dev); + + yaffs_dev_to_lc(dev)->readdir_process = current; + + offset = ctx->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 (!dir_emit_dot(file, ctx)) { + yaffs_gross_lock(dev); + goto out; + } + yaffs_gross_lock(dev); + offset++; + ctx->pos++; + } + if (offset == 1) { + yaffs_trace(YAFFS_TRACE_OS, + "yaffs_readdir: entry .. ino %d", + (int)file->f_path.dentry->d_parent->d_inode->i_ino); + yaffs_gross_unlock(dev); + if (!dir_emit_dotdot(file, ctx)) { + yaffs_gross_lock(dev); + goto out; + } + yaffs_gross_lock(dev); + offset++; + ctx->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 (file->f_version != i_version) { + offset = 2; + ctx->pos = offset; + file->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 (!dir_emit(ctx, name, strlen(name), + this_inode, this_type)) { + yaffs_gross_lock(dev); + goto out; + } + + yaffs_gross_lock(dev); + + offset++; + ctx->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 = f->f_path.dentry->d_inode; + unsigned long offset, curoffs; + struct yaffs_obj *l; + int ret_val = 0; + + char name[YAFFS_MAX_NAME_LENGTH + 1]; + + obj = yaffs_dentry_to_obj(f->f_path.dentry); + 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_path.dentry->d_parent->d_inode->i_ino); + yaffs_gross_unlock(dev); + if (filldir(dirent, "..", 2, offset, + f->f_path.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. */ + if (f->f_version != inode->i_version) { + offset = 2; + f->f_pos = offset; + f->f_version = inode->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, +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 12, 0)) + .iterate = yaffs_readdir, +#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; + i_uid_write(inode, obj->yst_uid); + i_gid_write(inode, 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 = (time_t) (obj->yst_atime); + inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = (time_t) obj->yst_mtime; + inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = (time_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, i_uid_read(inode), i_gid_read(inode), + 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 +struct yaffs_timer { + struct timer_list timer; + struct task_struct *tsk; +}; + +void yaffs_background_waker(struct timer_list *t) +{ + struct yaffs_timer *yt = from_timer(yt, t, timer); + + wake_up_process(yt->tsk); +} + +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; + struct yaffs_timer yt; + + 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); +#if 1 + expires = next_dir_update; + if (time_before(next_gc, expires)) + expires = next_gc; + if (time_before(expires, now)) + expires = now + HZ; + + Y_INIT_TIMER(&yt.timer); + yt.timer.function = yaffs_background_waker; + yt.timer.expires = expires + 1; + yt.tsk = current; + + set_current_state(TASK_INTERRUPTIBLE); + add_timer(&yt.timer); + schedule(); + del_timer_sync(&yt.timer); +#else + msleep(10); +#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); + } + } +} + +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); + 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 int yaffs_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buff, size_t size) +{ + return yaffs_getxattr(dentry, inode, name, buff, size); +} + +static int yaffs_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, const void *value, size_t size, + int flags) +{ + if (value) + return yaffs_setxattr(dentry, inode, name, value, size, flags); + else + return yaffs_removexattr(dentry, name); +} + +static const struct xattr_handler yaffs_xattr_handler = { + .prefix = "", /* match anything */ + .get = yaffs_xattr_get, + .set = yaffs_xattr_set, +}; + +static const struct xattr_handler *yaffs_xattr_handlers[] = { + &yaffs_xattr_handler, + NULL +}; + +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_xattr = yaffs_xattr_handlers; + 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_SIZE; + sb->s_blocksize_bits = PAGE_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 (!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) { + if (dev) + kfree(dev); + if (context) + kfree(context); + dev = NULL; + context = NULL; + } + + if (!dev) { + /* 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 + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0)) +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, void *data) +{ + 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, void *data) +{ + + 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(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; +} + +static int yaffs_proc_write(struct file *file, const char *buf, + unsigned long count, void *data) +{ + if (buf[0] == '.') + return yaffs_proc_debug_write(file, buf, count, data); + return yaffs_proc_write_trace_options(file, buf, count, data); +} +#endif + +/* 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} +}; + +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); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0)) + /* 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; + } else { + return -ENOMEM; + } +#endif + + /* 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."); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3, 9, 0)) + remove_proc_entry("yaffs", YPROC_ROOT); +#endif + + 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..d277e20e2a55 --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs1.c @@ -0,0 +1,422 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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; + int blk; + int result; + int chunk; + int 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); + + /* 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.scanned_size < + endpos) { + in->variant.file_variant.scanned_size = + endpos; + if (!dev->param.use_header_file_size) { + in->variant. + file_variant.file_size = + in->variant. + file_variant.scanned_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(oh); + 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..97e2fdd08a5d --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs1.h @@ -0,0 +1,22 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..f1dc972276f7 --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs2.c @@ -0,0 +1,1532 @@ +/* + * YAFFS: Yet Another Flash File System. A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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" + +/* + * 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) +{ + int 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 && + (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 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; + + 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)); + + 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->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 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; + + /* Write device runtime values */ + yaffs2_dev_to_checkpt_dev(&cp, dev); + cp.struct_type = sizeof(cp); + + ok = (yaffs2_checkpt_wr(dev, &cp, sizeof(cp)) == sizeof(cp)); + if (!ok) + return 0; + + /* Write block info */ + n_bytes = n_blocks * sizeof(struct yaffs_block_info); + ok = (yaffs2_checkpt_wr(dev, dev->block_info, n_bytes) == n_bytes); + if (!ok) + return 0; + + /* Write chunk bits */ + n_bytes = n_blocks * dev->chunk_bit_stride; + ok = (yaffs2_checkpt_wr(dev, dev->chunk_bits, n_bytes) == 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; + + 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) == n_bytes); + + if (!ok) + return 0; + + n_bytes = n_blocks * dev->chunk_bit_stride; + + ok = (yaffs2_checkpt_rd(dev, dev->chunk_bits, n_bytes) == n_bytes); + + return ok ? 1 : 0; +} + +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; + cp->variant_type = obj->variant_type; + cp->deleted = obj->deleted; + cp->soft_del = obj->soft_del; + cp->unlinked = obj->unlinked; + cp->fake = obj->fake; + cp->rename_allowed = obj->rename_allowed; + cp->unlink_allowed = obj->unlink_allowed; + cp->serial = 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; + + 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 = cp->variant_type; + obj->deleted = cp->deleted; + obj->soft_del = cp->soft_del; + obj->unlinked = cp->unlinked; + obj->fake = cp->fake; + obj->rename_allowed = cp->rename_allowed; + obj->unlink_allowed = cp->unlink_allowed; + obj->serial = cp->serial; + 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; + 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 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; + ok = (yaffs2_checkpt_wr(dev, &base_offset, sizeof(base_offset)) == + sizeof(base_offset)); + if (ok) + ok = (yaffs2_checkpt_wr(dev, tn, dev->tnode_size) == + 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)); + + 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) == + dev->tnode_size); + 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_trace(YAFFS_TRACE_CHECKPOINT, + "Checkpoint read tnodes %d records, last %d. ok %d", + nread, base_chunk, ok); + + return ok ? 1 : 0; +} + +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; + + /* 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); + + 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); + + 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); + + 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; + LIST_HEAD(hard_list); + + + while (ok && !done) { + ok = (yaffs2_checkpt_rd(dev, &cp, sizeof(cp)) == sizeof(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; + } + + 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 == ~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); + + 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; + + 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; +} + +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 > 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; +} + +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++; + } + + /* 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.scanned_size < endpos) { + in->variant.file_variant. + scanned_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; + + 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(oh) : + tags.extra_file_size; + u32 parent_obj_id = (oh) ? + 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 object 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); + + 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(oh); + 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->scanned_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->scanned_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) +{ + int blk; + int block_iter; + int start_iter; + int end_iter; + int n_to_scan = 0; + enum yaffs_block_state state; + int c; + int deleted; + 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_SCAN, "%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); + deleted = 0; + + 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..2363bfd8bcab --- /dev/null +++ b/fs/yaffs2/yaffs_yaffs2.h @@ -0,0 +1,39 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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..0e4e64e45f47 --- /dev/null +++ b/fs/yaffs2/yportenv.h @@ -0,0 +1,85 @@ +/* + * YAFFS: Yet another Flash File System . A NAND-flash specific file system. + * + * Copyright (C) 2002-2011 Aleph One Ltd. + * for Toby Churchill Ltd and Brightstar Engineering + * + * 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)) +#define Y_CURRENT_TIME ktime_get_real_seconds() +#define Y_TIME_CONVERT(x) (x).tv_sec +#else +#define Y_CURRENT_TIME CURRENT_TIME +#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/asm-generic/mmiowb.h b/include/asm-generic/mmiowb.h index 9439ff037b2d..5698fca3bf56 100644 --- a/include/asm-generic/mmiowb.h +++ b/include/asm-generic/mmiowb.h @@ -27,7 +27,7 @@ #include <asm/smp.h> DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state); -#define __mmiowb_state() this_cpu_ptr(&__mmiowb_state) +#define __mmiowb_state() raw_cpu_ptr(&__mmiowb_state) #else #define __mmiowb_state() arch_mmiowb_state() #endif /* arch_mmiowb_state */ @@ -35,7 +35,9 @@ DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state); static inline void mmiowb_set_pending(void) { struct mmiowb_state *ms = __mmiowb_state(); - ms->mmiowb_pending = ms->nesting_count; + + if (likely(ms->nesting_count)) + ms->mmiowb_pending = ms->nesting_count; } static inline void mmiowb_spin_lock(void) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 088987e9a3ea..6def18cb8238 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -284,7 +284,8 @@ #define PAGE_ALIGNED_DATA(page_align) \ . = ALIGN(page_align); \ - *(.data..page_aligned) + *(.data..page_aligned) \ + . = ALIGN(page_align); #define READ_MOSTLY_DATA(align) \ . = ALIGN(align); \ @@ -317,6 +318,7 @@ */ #ifndef RO_AFTER_INIT_DATA #define RO_AFTER_INIT_DATA \ + . = ALIGN(8); \ __start_ro_after_init = .; \ *(.data..ro_after_init) \ JUMP_TABLE_DATA \ @@ -655,7 +657,9 @@ . = ALIGN(bss_align); \ .bss : AT(ADDR(.bss) - LOAD_OFFSET) { \ BSS_FIRST_SECTIONS \ + . = ALIGN(PAGE_SIZE); \ *(.bss..page_aligned) \ + . = ALIGN(PAGE_SIZE); \ *(.dynbss) \ *(BSS_MAIN) \ *(COMMON) \ diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 864849e942c4..c1a8d4a41bb1 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -135,6 +135,7 @@ struct af_alg_async_req { * SG? * @enc: Cryptographic operation to be performed when * recvmsg is invoked. + * @init: True if metadata has been sent. * @len: Length of memory allocated for this data structure. */ struct af_alg_ctx { @@ -151,6 +152,7 @@ struct af_alg_ctx { bool more; bool merge; bool enc; + bool init; unsigned int len; }; @@ -226,7 +228,7 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset); void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, size_t dst_offset); void af_alg_wmem_wakeup(struct sock *sk); -int af_alg_wait_for_data(struct sock *sk, unsigned flags); +int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min); int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unsigned int ivsize); ssize_t af_alg_sendpage(struct socket *sock, struct page *page, diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 7f60e8eb269a..f1cdea2d475c 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -868,6 +868,18 @@ struct drm_mode_config { bool async_page_flip; /** + * @fbdev_use_iomem: + * + * Set to true if framebuffer reside in iomem. + * When set to true memcpy_toio() is used when copying the framebuffer in + * drm_fb_helper.drm_fb_helper_dirty_blit_real(). + * + * FIXME: This should be replaced with a per-mapping is_iomem + * flag (like ttm does), and then used everywhere in fbdev code. + */ + bool fbdev_use_iomem; + + /** * @allow_fb_modifiers: * * Whether the driver supports fb modifiers in the ADDFB2.1 ioctl call. diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4bbb5f1c8b5b..4c0224ff0a14 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -64,7 +64,7 @@ */ #define FIELD_FIT(_mask, _val) \ ({ \ - __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_FIT: "); \ + __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: "); \ !((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \ }) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ab54e897eb47..0db80f6327eb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -589,6 +589,7 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; +/* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index b4e766e93f6e..6a5604d3ea24 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -797,7 +797,9 @@ struct sock_cgroup_data { union { #ifdef __LITTLE_ENDIAN struct { - u8 is_data; + u8 is_data : 1; + u8 no_refcnt : 1; + u8 unused : 6; u8 padding; u16 prioidx; u32 classid; @@ -807,7 +809,9 @@ struct sock_cgroup_data { u32 classid; u16 prioidx; u8 padding; - u8 is_data; + u8 unused : 6; + u8 no_refcnt : 1; + u8 is_data : 1; } __packed; #endif u64 val; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 62df5facf63c..b4409b3ce927 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -818,6 +818,7 @@ extern spinlock_t cgroup_sk_update_lock; void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); +void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) @@ -831,7 +832,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) */ v = READ_ONCE(skcd->val); - if (v & 1) + if (v & 3) return &cgrp_dfl_root.cgrp; return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; @@ -843,6 +844,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} +static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 79cdcf0fd635..60cd22b5c30f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1334,6 +1334,7 @@ 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); @@ -1705,6 +1706,13 @@ int vfs_mkobj(struct dentry *, umode_t, extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#else +#define compat_ptr_ioctl NULL +#endif + /* * VFS file helper functions. */ @@ -1813,6 +1821,7 @@ 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); @@ -1883,6 +1892,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, struct iovec *fast_pointer, struct iovec **ret_pointer); +typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t, + loff_t *); +vfs_readf_t vfs_readf(struct file *file); +vfs_writef_t vfs_writef(struct file *file); + extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); @@ -2316,6 +2331,7 @@ 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; @@ -2604,6 +2620,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return false; } #endif +extern int __sync_filesystem(struct super_block *, int); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6256cc34c4a6..e02b3dd76242 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -420,6 +420,8 @@ enum vmbus_channel_message_type { CHANNELMSG_19 = 19, CHANNELMSG_20 = 20, CHANNELMSG_TL_CONNECT_REQUEST = 21, + CHANNELMSG_22 = 22, + CHANNELMSG_TL_CONNECT_RESULT = 23, CHANNELMSG_COUNT }; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 244278d5c222..077e74daf19a 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -25,6 +25,8 @@ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ +#define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ + /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID @@ -588,10 +590,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { - unsigned int vlan_depth = skb->mac_len; + unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at @@ -606,13 +608,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, vlan_depth = ETH_HLEN; } do { - struct vlan_hdr *vh; + struct vlan_hdr vhdr, *vh; - if (unlikely(!pskb_may_pull(skb, - vlan_depth + VLAN_HLEN))) + vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + if (unlikely(!vh || !--parse_depth)) return 0; - vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); @@ -631,11 +632,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type, * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 vlan_get_protocol(struct sk_buff *skb) +static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* A getter for the SKB protocol field which will handle VLAN tags consistently + * whether VLAN acceleration is enabled or not. + */ +static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) +{ + if (!skip_vlan) + /* VLAN acceleration strips the VLAN header from the skb and + * moves it to skb->vlan_proto + */ + return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; + + return vlan_get_protocol(skb); +} + static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 6dd07c852e6d..5f943486e405 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -357,8 +357,8 @@ enum { #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) -#define QI_DEV_EIOTLB_GLOB(g) ((u64)g) -#define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) +#define QI_DEV_EIOTLB_GLOB(g) ((u64)(g) & 0x1) +#define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 6e125e9b4187..b9c91d321240 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -108,9 +108,12 @@ io_mapping_init_wc(struct io_mapping *iomap, resource_size_t base, unsigned long size) { + iomap->iomem = ioremap_wc(base, size); + if (!iomap->iomem) + return NULL; + iomap->base = base; iomap->size = size; - iomap->iomem = ioremap_wc(base, size); #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); #elif defined(pgprot_writecombine) diff --git a/include/linux/irq.h b/include/linux/irq.h index f8755e5fcd74..8060a53805a0 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -211,6 +211,10 @@ struct irq_data { * IRQD_CAN_RESERVE - Can use reservation mode * IRQD_MSI_NOMASK_QUIRK - Non-maskable MSI quirk for affinity change * required + * IRQD_HANDLE_ENFORCE_IRQCTX - Enforce that handle_irq_*() is only invoked + * from actual interrupt context. + * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call + * irq_chip::irq_set_affinity() when deactivated. */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -234,6 +238,8 @@ enum { IRQD_DEFAULT_TRIGGER_SET = (1 << 25), IRQD_CAN_RESERVE = (1 << 26), IRQD_MSI_NOMASK_QUIRK = (1 << 27), + IRQD_HANDLE_ENFORCE_IRQCTX = (1 << 28), + IRQD_AFFINITY_ON_ACTIVATE = (1 << 29), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -303,6 +309,16 @@ static inline bool irqd_is_single_target(struct irq_data *d) return __irqd_to_state(d) & IRQD_SINGLE_TARGET; } +static inline void irqd_set_handle_enforce_irqctx(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_HANDLE_ENFORCE_IRQCTX; +} + +static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX; +} + static inline bool irqd_is_wakeup_set(struct irq_data *d) { return __irqd_to_state(d) & IRQD_WAKEUP_STATE; @@ -408,6 +424,16 @@ static inline bool irqd_msi_nomask_quirk(struct irq_data *d) return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; } +static inline void irqd_set_affinity_on_activate(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE; +} + +static inline bool irqd_affinity_on_activate(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6e2377e6c1d6..5a945d18a72a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -325,6 +325,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock, return lock->key == key; } +struct lock_class *lockdep_hlock_class(struct held_lock *hlock); + /* * Acquire a lock. * @@ -463,6 +465,7 @@ struct lockdep_map { }; #define lockdep_depth(tsk) (0) +#define lockdep_is_held(lock) (1) #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3d1e4a53b9e4..9310a7e1057b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3929,6 +3929,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_UPLINK = 0x2, }; struct mlx5_ifc_arm_monitor_counter_in_bits { diff --git a/include/linux/mm.h b/include/linux/mm.h index 9b7e3da416d1..c4f0864be4df 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1565,6 +1565,28 @@ 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 20d1077f30e6..a43a74a67d50 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -258,6 +258,7 @@ 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 @@ -332,6 +333,7 @@ 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) */ atomic_long_t swap_readahead_info; diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 35942084cd40..24f5fd1a789d 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -6,11 +6,14 @@ struct mnt_namespace; struct fs_struct; struct user_namespace; +struct vfsmount; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); +extern int is_current_mnt_ns(struct vfsmount *mnt); + extern const struct file_operations proc_mounts_operations; extern const struct file_operations proc_mountinfo_operations; extern const struct file_operations proc_mountstats_operations; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 9673b1d060d7..5f6eb23644b3 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -299,7 +299,7 @@ struct pcmcia_device_id { #define INPUT_DEVICE_ID_LED_MAX 0x0f #define INPUT_DEVICE_ID_SND_MAX 0x07 #define INPUT_DEVICE_ID_FF_MAX 0x7f -#define INPUT_DEVICE_ID_SW_MAX 0x0f +#define INPUT_DEVICE_ID_SW_MAX 0x10 #define INPUT_DEVICE_ID_PROP_MAX 0x1f #define INPUT_DEVICE_ID_MATCH_BUS 1 diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1e78032a174b..2484cf531e9b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -59,6 +59,7 @@ struct nfs_client { u32 cl_minorversion;/* NFSv4 minorversion */ const char * cl_principal; /* used for machine cred */ + int nfs_prog; #if IS_ENABLED(CONFIG_NFS_V4) struct list_head cl_ds_clients; /* auth flavor data servers */ @@ -81,6 +82,7 @@ struct nfs_client { const char * cl_owner_id; u32 cl_cb_ident; /* v4.0 callback identifier */ + const struct nfs4_minor_version_ops *cl_mvops; unsigned long cl_mig_gen; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 99d327d0bccb..06cd135a2958 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/prandom.h b/include/linux/prandom.h new file mode 100644 index 000000000000..aa16e6468f91 --- /dev/null +++ b/include/linux/prandom.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/prandom.h + * + * Include file for the fast pseudo-random 32-bit + * generation. + */ +#ifndef _LINUX_PRANDOM_H +#define _LINUX_PRANDOM_H + +#include <linux/types.h> +#include <linux/percpu.h> + +u32 prandom_u32(void); +void prandom_bytes(void *buf, size_t nbytes); +void prandom_seed(u32 seed); +void prandom_reseed_late(void); + +struct rnd_state { + __u32 s1, s2, s3, s4; +}; + +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + +u32 prandom_u32_state(struct rnd_state *state); +void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) + +/** + * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) + * @ep_ro: right open interval endpoint + * + * Returns a pseudo-random number that is in interval [0, ep_ro). Note + * that the result depends on PRNG being well distributed in [0, ~0U] + * u32 space. Here we use maximally equidistributed combined Tausworthe + * generator, that is, prandom_u32(). This is useful when requesting a + * random index of an array containing ep_ro elements, for example. + * + * Returns: pseudo-random number in interval [0, ep_ro) + */ +static inline u32 prandom_u32_max(u32 ep_ro) +{ + return (u32)(((u64) prandom_u32() * ep_ro) >> 32); +} + +/* + * Handle minimum values for seeds + */ +static inline u32 __seed(u32 x, u32 m) +{ + return (x < m) ? x + m : x; +} + +/** + * prandom_seed_state - set seed for prandom_u32_state(). + * @state: pointer to state structure to receive the seed. + * @seed: arbitrary 64-bit value to use as a seed. + */ +static inline void prandom_seed_state(struct rnd_state *state, u64 seed) +{ + u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + + state->s1 = __seed(i, 2U); + state->s2 = __seed(i, 8U); + state->s3 = __seed(i, 16U); + state->s4 = __seed(i, 128U); +} + +/* Pseudo random number generator from numerical recipes. */ +static inline u32 next_pseudo_random32(u32 seed) +{ + return seed * 1664525 + 1013904223; +} + +#endif diff --git a/include/linux/random.h b/include/linux/random.h index 1033542ec67f..2f902463c408 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,7 +9,6 @@ #include <linux/list.h> #include <linux/once.h> -#include <asm/percpu.h> #include <uapi/linux/random.h> @@ -108,63 +107,12 @@ declare_get_random_var_wait(long) unsigned long randomize_page(unsigned long start, unsigned long range); -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -struct rnd_state { - __u32 s1, s2, s3, s4; -}; - -DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; - -u32 prandom_u32_state(struct rnd_state *state); -void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); -void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); - -#define prandom_init_once(pcpu_state) \ - DO_ONCE(prandom_seed_full_state, (pcpu_state)) - -/** - * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) - * @ep_ro: right open interval endpoint - * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. - * - * Returns: pseudo-random number in interval [0, ep_ro) - */ -static inline u32 prandom_u32_max(u32 ep_ro) -{ - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); -} - /* - * Handle minimum values for seeds - */ -static inline u32 __seed(u32 x, u32 m) -{ - return (x < m) ? x + m : x; -} - -/** - * prandom_seed_state - set seed for prandom_u32_state(). - * @state: pointer to state structure to receive the seed. - * @seed: arbitrary 64-bit value to use as a seed. + * This is designed to be standalone for just prandom + * users, but for now we include it from <linux/random.h> + * for legacy reasons. */ -static inline void prandom_seed_state(struct rnd_state *state, u64 seed) -{ - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; - - state->s1 = __seed(i, 2U); - state->s2 = __seed(i, 8U); - state->s3 = __seed(i, 16U); - state->s4 = __seed(i, 128U); -} +#include <linux/prandom.h> #ifdef CONFIG_ARCH_RANDOM # include <asm/archrandom.h> @@ -195,10 +143,4 @@ static inline bool arch_has_random_seed(void) } #endif -/* Pseudo random number generator from numerical recipes. */ -static inline u32 next_pseudo_random32(u32 seed) -{ - return seed * 1664525 + 1013904223; -} - #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a5359aee7e51..0ddf7543f45d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -384,6 +384,24 @@ static inline void rcu_preempt_sleep_check(void) { } }) /** + * rcu_replace_pointer() - replace an RCU pointer, returning its old value + * @rcu_ptr: RCU pointer, whose old value is returned + * @ptr: regular pointer + * @c: the lockdep conditions under which the dereference will take place + * + * Perform a replacement, where @rcu_ptr is an RCU-annotated + * pointer and @c is the lockdep argument that is passed to the + * rcu_dereference_protected() call used to read that pointer. The old + * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. + */ +#define rcu_replace_pointer(rcu_ptr, ptr, c) \ +({ \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + __tmp; \ +}) + +/** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer * @ptr: regular pointer diff --git a/include/linux/splice.h b/include/linux/splice.h index 74b4911ac16d..19789fbea567 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -87,4 +87,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; extern const struct pipe_buf_operations default_pipe_buf_ops; + +extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); +extern long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); #endif diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 1afe38eb33f7..82665ff360fd 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -517,6 +517,9 @@ void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); char * svc_print_addr(struct svc_rqst *, char *, size_t); +int svc_encode_read_payload(struct svc_rqst *rqstp, + unsigned int offset, + unsigned int length); unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, struct kvec *first, size_t total); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 7b0ab2c86148..9f588f923fe4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -136,6 +136,8 @@ struct svc_rdma_recv_ctxt { unsigned int rc_page_count; unsigned int rc_hdr_count; u32 rc_inv_rkey; + unsigned int rc_read_payload_offset; + unsigned int rc_read_payload_length; struct page *rc_pages[RPCSVC_MAXPAGES]; }; @@ -170,7 +172,9 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, struct svc_rdma_recv_ctxt *head, __be32 *p); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, - __be32 *wr_ch, struct xdr_buf *xdr); + __be32 *wr_ch, struct xdr_buf *xdr, + unsigned int offset, + unsigned long length); extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch, bool writelist, struct xdr_buf *xdr); @@ -189,6 +193,8 @@ extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt, struct xdr_buf *xdr, __be32 *wr_lst); extern int svc_rdma_sendto(struct svc_rqst *); +extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length); /* svc_rdma_transport.c */ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ea6f46be9cb7..9e1e046de176 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -21,6 +21,8 @@ struct svc_xprt_ops { int (*xpo_has_wspace)(struct svc_xprt *); int (*xpo_recvfrom)(struct svc_rqst *); int (*xpo_sendto)(struct svc_rqst *); + int (*xpo_read_payload)(struct svc_rqst *, unsigned int, + unsigned int); void (*xpo_release_rqst)(struct svc_rqst *); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3eb7f9a27364..908e1fa07586 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -221,6 +221,8 @@ struct tcp_sock { } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; + u8 tlp_retrans:1, /* TLP is a retransmission */ + unused_1:7; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -243,7 +245,7 @@ struct tcp_sock { save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ syn_smc:1; /* SYN includes SMC */ - u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 53c0ea9ec9df..77fdc988c610 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -93,6 +93,7 @@ struct tpm_space { u8 *context_buf; u32 session_tbl[3]; u8 *session_buf; + u32 buf_size; }; struct tpm_bios_log { diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 1fb11daa5c53..57ce5af258a3 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -362,7 +362,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static const char *___tp_str __tracepoint_string = str; \ ___tp_str; \ }) -#define __tracepoint_string __attribute__((section("__tracepoint_str"))) +#define __tracepoint_string __attribute__((section("__tracepoint_str"), used)) #else /* * tracepoint_string() is used to save the string address for userspace diff --git a/include/linux/unaligned/generic.h b/include/linux/unaligned/generic.h index 57d3114656e5..303289492859 100644 --- a/include/linux/unaligned/generic.h +++ b/include/linux/unaligned/generic.h @@ -2,6 +2,8 @@ #ifndef _LINUX_UNALIGNED_GENERIC_H #define _LINUX_UNALIGNED_GENERIC_H +#include <linux/types.h> + /* * Cause a link-time error if we try an unaligned access other than * 1,2,4 or 8 bytes long @@ -66,4 +68,48 @@ extern void __bad_unaligned_access_size(void); } \ (void)0; }) +static inline u32 __get_unaligned_be24(const u8 *p) +{ + return p[0] << 16 | p[1] << 8 | p[2]; +} + +static inline u32 get_unaligned_be24(const void *p) +{ + return __get_unaligned_be24(p); +} + +static inline u32 __get_unaligned_le24(const u8 *p) +{ + return p[0] | p[1] << 8 | p[2] << 16; +} + +static inline u32 get_unaligned_le24(const void *p) +{ + return __get_unaligned_le24(p); +} + +static inline void __put_unaligned_be24(const u32 val, u8 *p) +{ + *p++ = val >> 16; + *p++ = val >> 8; + *p++ = val; +} + +static inline void put_unaligned_be24(const u32 val, void *p) +{ + __put_unaligned_be24(val, p); +} + +static inline void __put_unaligned_le24(const u32 val, u8 *p) +{ + *p++ = val; + *p++ = val >> 8; + *p++ = val >> 16; +} + +static inline void put_unaligned_le24(const u32 val, void *p) +{ + __put_unaligned_le24(val, p); +} + #endif /* _LINUX_UNALIGNED_GENERIC_H */ diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 22c1f579afe3..5e4c497f54d6 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -69,7 +69,7 @@ /* Hub needs extra delay after resetting its port. */ #define USB_QUIRK_HUB_SLOW_RESET BIT(14) -/* device has blacklisted endpoints */ -#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15) +/* device has endpoints that should be ignored */ +#define USB_QUIRK_ENDPOINT_IGNORE BIT(15) #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 6dad031be3c2..3a71ad716da5 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -51,8 +51,10 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); +int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); +int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 3f62b347b04a..ab8b3eb53d4b 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -273,6 +273,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index ab988940bf04..55b980b21f4b 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/net/dst.h b/include/net/dst.h index 4d61945d5d74..2fbb03797d14 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -401,7 +401,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - struct neighbour *n = dst->ops->neigh_lookup(dst, skb, NULL); + struct neighbour *n = NULL; + + /* The packets from tunnel devices (eg bareudp) may have only + * metadata in the dst pointer of skb. Hence a pointer check of + * neigh_lookup is needed. + */ + if (dst->ops->neigh_lookup) + n = dst->ops->neigh_lookup(dst, skb, NULL); + return IS_ERR(n) ? NULL : n; } diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9292f1c588b7..2d9e67a69cbe 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -35,12 +35,6 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks - * @mcast_bind: a socket bound to the given multicast group (which - * is given as the offset into the groups array) - * @mcast_unbind: a socket was unbound from the given multicast group. - * Note that unbind() will not be called symmetrically if the - * generic netlink family is removed while there are still open - * sockets. * @attrbuf: buffer to store parsed attributes (private) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups @@ -64,8 +58,6 @@ struct genl_family { void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); - int (*mcast_bind)(struct net *net, int group); - void (*mcast_unbind)(struct net *net, int group); struct nlattr ** attrbuf; /* private */ const struct genl_ops * ops; const struct genl_multicast_group *mcgrps; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c57d53e7e02c..1ba40380b4df 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -309,6 +309,10 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); +/* update the fast reuse flag when adding a socket */ +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk); + struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); #define TCP_PINGPONG_THRESH 3 diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 0f0d1efe06dd..e1eaf1780288 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -4,6 +4,7 @@ #include <linux/ip.h> #include <linux/skbuff.h> +#include <linux/if_vlan.h> #include <net/inet_sock.h> #include <net/dsfield.h> @@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) static inline int INET_ECN_set_ce(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) static inline int INET_ECN_set_ect1(struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): if (skb_network_header(skb) + sizeof(struct iphdr) <= skb_tail_pointer(skb)) @@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, oiph->tos, inner); } @@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, { __u8 inner; - if (skb->protocol == htons(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): inner = ip_hdr(skb)->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + break; + case htons(ETH_P_IPV6): inner = ipv6_get_dsfield(ipv6_hdr(skb)); - else + break; + default: return 0; + } return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); } diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b71ad28fdc98..01e034774c5b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1616,18 +1616,16 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) } #endif /* CONFIG_IP_VS_NFCT */ -/* Really using conntrack? */ -static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp, - struct sk_buff *skb) +/* Using old conntrack that can not be redirected to another real server? */ +static inline bool ip_vs_conn_uses_old_conntrack(struct ip_vs_conn *cp, + struct sk_buff *skb) { #ifdef CONFIG_IP_VS_NFCT enum ip_conntrack_info ctinfo; struct nf_conn *ct; - if (!(cp->flags & IP_VS_CONN_F_NFCT)) - return false; ct = nf_ct_get(skb, &ctinfo); - if (ct) + if (ct && nf_ct_is_confirmed(ct)) return true; #endif return false; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index aa99c73c3fbd..2abecd015f6d 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -128,17 +128,6 @@ static inline void qdisc_run(struct Qdisc *q) } } -static inline __be16 tc_skb_protocol(const struct sk_buff *skb) -{ - /* We need to take extra care in case the skb came via - * vlan accelerated path. In that case, use skb->vlan_proto - * as the original vlan header was already stripped. - */ - if (skb_vlan_tag_present(skb)) - return skb->vlan_proto; - return skb->protocol; -} - /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/include/net/sock.h b/include/net/sock.h index d17d6086a39d..86ec9c407746 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -849,6 +849,8 @@ static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } + +void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) @@ -856,6 +858,8 @@ static inline int sk_memalloc_socks(void) return 0; } +static inline void __receive_sock(struct file *file) +{ } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ae7fd77f72dd..e410d02d0524 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -950,7 +950,7 @@ struct xfrm_dst { static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; @@ -962,7 +962,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } diff --git a/include/sound/rt5670.h b/include/sound/rt5670.h index f9024c7a1600..02e1d7778354 100644 --- a/include/sound/rt5670.h +++ b/include/sound/rt5670.h @@ -12,6 +12,7 @@ struct rt5670_platform_data { int jd_mode; bool in2_diff; bool dev_gpio; + bool gpio1_is_ext_spk_en; bool dmic_en; unsigned int dmic1_data_pin; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 51b6f50eabee..1b752d8ea529 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -116,10 +116,4 @@ static inline bool target_dev_configured(struct se_device *se_dev) return !!(se_dev->dev_flags & DF_CONFIGURED); } -/* Only use get_unaligned_be24() if reading p - 1 is allowed. */ -static inline uint32_t get_unaligned_be24(const uint8_t *const p) -{ - return get_unaligned_be32(p - 1) & 0xffffffU; -} - #endif /* TARGET_CORE_BACKEND_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d62ae02900aa..5c5764f5e1d4 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -406,7 +406,7 @@ enum rxrpc_tx_point { EM(rxrpc_cong_begin_retransmission, " Retrans") \ EM(rxrpc_cong_cleared_nacks, " Cleared") \ EM(rxrpc_cong_new_low_nack, " NewLowN") \ - EM(rxrpc_cong_no_change, "") \ + EM(rxrpc_cong_no_change, " -") \ EM(rxrpc_cong_progress, " Progres") \ EM(rxrpc_cong_retransmit_again, " ReTxAgn") \ EM(rxrpc_cong_rtt_window_end, " RttWinE") \ @@ -612,10 +612,10 @@ TRACE_EVENT(rxrpc_client, ); TRACE_EVENT(rxrpc_call, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_call_trace op, + TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op, int usage, const void *where, const void *aux), - TP_ARGS(call, op, usage, where, aux), + TP_ARGS(call_debug_id, op, usage, where, aux), TP_STRUCT__entry( __field(unsigned int, call ) @@ -626,7 +626,7 @@ TRACE_EVENT(rxrpc_call, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; diff --git a/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h new file mode 100644 index 000000000000..0e3e2b175f7a --- /dev/null +++ b/include/uapi/linux/aufs_type.h @@ -0,0 +1,448 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2005-2019 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#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 +#else +#include <stdint.h> +#include <sys/types.h> +#endif /* __KERNEL__ */ + +#include <linux/limits.h> + +#define AUFS_VERSION "5.x-rcN-20190610" + +/* todo? move this to linux-2.6.19/include/magic.h */ +#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_BRANCH_MAX_127 +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 + +#ifdef __KERNEL__ +#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 +#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) +#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[0]; +} __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[0]; +} __aligned(8); + +struct au_drinfo_fdata { + uint32_t magic; + struct au_drinfo drinfo; +} __aligned(8); + +#define AUFS_DRINFO_MAGIC_V1 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x01) +/* future */ +#define AUFS_DRINFO_MAGIC_V2 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x02) + +/* ---------------------------------------------------------------------- */ + +struct aufs_wbr_fd { + uint32_t oflags; + int16_t brid; +} __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[0]; + }; +} __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/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 85387c76c24f..472cd5bc5567 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -808,7 +808,8 @@ #define SW_LINEIN_INSERT 0x0d /* set = inserted */ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ #define SW_PEN_INSERTED 0x0f /* set = pen inserted */ -#define SW_MAX 0x0f +#define SW_MACHINE_COVER 0x10 /* set = cover closed */ +#define SW_MAX 0x10 #define SW_CNT (SW_MAX+1) /* 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/nfs_mount.h b/include/uapi/linux/nfs_mount.h index e3bcfc6aa3b0..ed57fec0beef 100644 --- a/include/uapi/linux/nfs_mount.h +++ b/include/uapi/linux/nfs_mount.h @@ -21,7 +21,7 @@ * mount-to-kernel version compatibility. Some of these aren't used yet * but here they are anyway. */ -#define NFS_MOUNT_VERSION 6 +#define NFS_MOUNT_VERSION 7 #define NFS_MAX_CONTEXT_LEN 256 struct nfs_mount_data { @@ -44,6 +44,8 @@ struct nfs_mount_data { struct nfs3_fh root; /* 4 */ int pseudoflavor; /* 5 */ char context[NFS_MAX_CONTEXT_LEN + 1]; /* 6 */ + int nfs_prog; /* 7 */ + int mount_prog; /* 7 */ }; /* bits in the flags field visible to user space */ diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 90734aa5aa36..b5f901af79f0 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -93,5 +93,6 @@ struct seccomp_notif_resp { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) + #endif /* _UAPI_LINUX_SECCOMP_H */ diff --git a/include/uapi/linux/vboxguest.h b/include/uapi/linux/vboxguest.h index 612f0c7d3558..ded39da305d0 100644 --- a/include/uapi/linux/vboxguest.h +++ b/include/uapi/linux/vboxguest.h @@ -103,7 +103,7 @@ VMMDEV_ASSERT_SIZE(vbg_ioctl_driver_version_info, 24 + 20); /* IOCTL to perform a VMM Device request larger then 1KB. */ -#define VBG_IOCTL_VMMDEV_REQUEST_BIG _IOC(_IOC_READ | _IOC_WRITE, 'V', 3, 0) +#define VBG_IOCTL_VMMDEV_REQUEST_BIG _IO('V', 3) /** VBG_IOCTL_HGCM_CONNECT data structure. */ @@ -198,7 +198,7 @@ struct vbg_ioctl_log { } u; }; -#define VBG_IOCTL_LOG(s) _IOC(_IOC_READ | _IOC_WRITE, 'V', 9, s) +#define VBG_IOCTL_LOG(s) _IO('V', 9) /** VBG_IOCTL_WAIT_FOR_EVENTS data structure. */ diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index 86eca3208b6b..24f3371ad826 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -74,6 +74,12 @@ #include <linux/socket.h> /* for "struct sockaddr" et al */ #include <linux/if.h> /* for IFNAMSIZ and co... */ +#ifdef __KERNEL__ +# include <linux/stddef.h> /* for offsetof */ +#else +# include <stddef.h> /* for offsetof */ +#endif + /***************************** VERSION *****************************/ /* * This constant is used to know the availability of the wireless @@ -1090,8 +1096,7 @@ struct iw_event { /* iw_point events are special. First, the payload (extra data) come at * the end of the event, so they are bigger than IW_EV_POINT_LEN. Second, * we omit the pointer, so start at an offset. */ -#define IW_EV_POINT_OFF (((char *) &(((struct iw_point *) NULL)->length)) - \ - (char *) NULL) +#define IW_EV_POINT_OFF offsetof(struct iw_point, length) #define IW_EV_POINT_LEN (IW_EV_LCP_LEN + sizeof(struct iw_point) - \ IW_EV_POINT_OFF) 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/Kconfig b/init/Kconfig index f87efed9c215..c77705e7dc7d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1203,6 +1203,31 @@ menuconfig EXPERT environments which can tolerate a "non-standard" kernel. Only use this if you really know what you are doing. +config UPTIME_LIMITED_KERNEL + bool "Create a kernel with uptime limitations" + default n + help + Limit the amount of time a kernel can run. The associated UPTIME_LIMIT* + kernel config options should be used to tune the behaviour. + +config UPTIME_LIMIT_DURATION + int "Kernel uptime limit in minutes" + depends on UPTIME_LIMITED_KERNEL + range 0 14400 + default 0 + help + Define the uptime limitation on a kernel in minutes. Once + the defined time expires the kernel will emit a warning, cease + to be usable and eventually restart. The valid range is 0 (disable) + to 14400 (10 days) + +config UPTIME_LIMIT_KERNEL_REBOOT + bool "Reboot a time limited kernel at expiration" + depends on UPTIME_LIMITED_KERNEL + default y + help + Reboot an uptime limited kernel at expiration. + config UID16 bool "Enable 16-bit UID system calls" if EXPERT depends on HAVE_UID16 && MULTIUSER diff --git a/init/do_mounts.c b/init/do_mounts.c index 2d1ea3028454..5981c8375a10 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -440,7 +440,9 @@ 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; @@ -456,7 +458,9 @@ retry: #ifdef CONFIG_BLOCK __bdevname(ROOT_DEV, b); #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"); out: put_page(page); } diff --git a/init/main.c b/init/main.c index e7592e8241e2..d1ce0179d343 100644 --- a/init/main.c +++ b/init/main.c @@ -1136,6 +1136,9 @@ static int __ref kernel_init(void *unused) 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. */ @@ -1169,6 +1172,18 @@ static noinline void __init kernel_init_freeable(void) do_basic_setup(); +#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 on the rootfs, 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"); diff --git a/kernel/Makefile b/kernel/Makefile index a8d923b5481b..eb5beb6d927d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ +obj-$(CONFIG_UPTIME_LIMITED_KERNEL) += uptime_limit.o obj-$(CONFIG_FUTEX) += futex.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 583df5cb302d..09ba58465758 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -679,15 +679,20 @@ static void htab_elem_free_rcu(struct rcu_head *head) preempt_enable(); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -739,6 +744,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 09f6aaa714ff..fb24e7424411 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6291,17 +6291,8 @@ void cgroup_sk_alloc_disable(void) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) - return; - - /* Socket clone path */ - if (skcd->val) { - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); + if (cgroup_sk_alloc_disabled) { + skcd->no_refcnt = 1; return; } @@ -6325,8 +6316,24 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) rcu_read_unlock(); } +void cgroup_sk_clone(struct sock_cgroup_data *skcd) +{ + /* Socket clone path */ + if (skcd->val) { + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(sock_cgroup_ptr(skcd)); + } +} + void cgroup_sk_free(struct sock_cgroup_data *skcd) { + if (skcd->no_refcnt) + return; + cgroup_put(sock_cgroup_ptr(skcd)); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 9ecfa37c7fbf..bb5dec762b69 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1103,12 +1103,12 @@ static int handle_ctrl_cmd(char *cmd) case CTRL_P: if (cmdptr != cmd_tail) cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT; - strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); return 1; case CTRL_N: if (cmdptr != cmd_head) cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT; - strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); return 1; } return 0; @@ -1315,7 +1315,7 @@ do_full_getstr: if (*cmdbuf != '\n') { if (*cmdbuf < 32) { if (cmdptr == cmd_head) { - strncpy(cmd_hist[cmd_head], cmd_cur, + strscpy(cmd_hist[cmd_head], cmd_cur, CMD_BUFLEN); *(cmd_hist[cmd_head] + strlen(cmd_hist[cmd_head])-1) = '\0'; @@ -1325,7 +1325,7 @@ do_full_getstr: cmdbuf = cmd_cur; goto do_full_getstr; } else { - strncpy(cmd_hist[cmd_head], cmd_cur, + strscpy(cmd_hist[cmd_head], cmd_cur, CMD_BUFLEN); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ccfeb313be21..673044edd9ad 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2153,7 +2153,7 @@ static void handle_swbp(struct pt_regs *regs) if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + force_sig(SIGTRAP, current); } else { /* * Either we raced with uprobe_unregister() or we can't diff --git a/kernel/fork.c b/kernel/fork.c index d4c26c3052f3..cfd1ad92c890 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -553,7 +553,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; - get_file(file); + vma_get_file(tmp); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); i_mmap_lock_write(mapping); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ed4843df6220..207bac6ad4c3 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -422,6 +422,10 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } +static inline bool handle_enforce_irqctx(struct irq_data *data) +{ + return irqd_is_handle_enforce_irqctx(data); +} bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) @@ -448,6 +452,10 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } +static inline bool handle_enforce_irqctx(struct irq_data *data) +{ + return false; +} #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9be995fc3c5a..6a27603fe1cf 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -638,9 +638,15 @@ void irq_init_desc(unsigned int irq) int generic_handle_irq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); + struct irq_data *data; if (!desc) return -EINVAL; + + data = irq_desc_get_irq_data(desc); + if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data))) + return -EPERM; + generic_handle_irq_desc(desc); return 0; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e88faff5bea5..e557a375cd02 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -194,9 +194,9 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -204,9 +204,19 @@ static void irq_validate_effective_affinity(struct irq_data *data) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); -#endif } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) +{ + cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); +} +#else +static inline void irq_validate_effective_affinity(struct irq_data *data) { } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) { } +#endif + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -265,6 +275,30 @@ static int irq_try_set_affinity(struct irq_data *data, return ret; } +static bool irq_set_affinity_deactivated(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + /* + * Handle irq chips which can handle affinity only in activated + * state correctly + * + * If the interrupt is not yet activated, just store the affinity + * mask and do not call the chip driver at all. On activation the + * driver has to make sure anyway that the interrupt is in a + * useable state so startup works. + */ + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || + irqd_is_activated(data) || !irqd_affinity_on_activate(data)) + return false; + + cpumask_copy(desc->irq_common_data.affinity, mask); + irq_init_effective_affinity(data, mask); + irqd_set(data, IRQD_AFFINITY_SET); + return true; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -275,6 +309,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; + if (irq_set_affinity_deactivated(data, mask, force)) + return 0; + if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { ret = irq_try_set_affinity(data, mask, force); } else { diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 98c04ca5fa43..5064b13b80d6 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -72,8 +72,9 @@ void check_irq_resend(struct irq_desc *desc) desc->istate &= ~IRQS_PENDING; desc->istate |= IRQS_REPLAY; - if (!desc->irq_data.chip->irq_retrigger || - !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) { + if ((!desc->irq_data.chip->irq_retrigger || + !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) && + !handle_enforce_irqctx(&desc->irq_data)) { #ifdef CONFIG_HARDIRQS_SW_RESEND unsigned int irq = irq_desc_get_irq(desc); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b640e0abd636..a0dfc7d425f0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1052,9 +1052,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p) return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ -#define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) (-ENODEV) -#define disarm_kprobe_ftrace(p) (-ENODEV) +static inline int prepare_kprobe(struct kprobe *p) +{ + return arch_prepare_kprobe(p); +} + +static inline int arm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} + +static inline int disarm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} #endif /* Arm a kprobe with text_mutex */ @@ -2080,6 +2091,13 @@ static void kill_kprobe(struct kprobe *p) * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); + + /* + * The module is going away. We should disarm the kprobe which + * is using ftrace. + */ + if (kprobe_ftrace(p)) + disarm_kprobe_ftrace(p); } /* Disable one kprobe */ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 0b956fde19de..98bdba3161d7 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -152,7 +152,7 @@ static #endif struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; -static inline struct lock_class *hlock_class(struct held_lock *hlock) +inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock) { if (!hlock->class_idx) { /* @@ -163,6 +163,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) } return lock_classes + hlock->class_idx - 1; } +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 78e750dd9fb5..9f35e1927807 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1462,18 +1462,34 @@ struct module_sect_attrs { struct module_sect_attr attrs[0]; }; +#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4)) static ssize_t module_sect_read(struct file *file, struct kobject *kobj, struct bin_attribute *battr, char *buf, loff_t pos, size_t count) { struct module_sect_attr *sattr = container_of(battr, struct module_sect_attr, battr); + char bounce[MODULE_SECT_READ_SIZE + 1]; + size_t wrote; if (pos != 0) return -EINVAL; - return sprintf(buf, "0x%px\n", - kallsyms_show_value(file->f_cred) ? (void *)sattr->address : NULL); + /* + * Since we're a binary read handler, we must account for the + * trailing NUL byte that sprintf will write: if "buf" is + * too small to hold the NUL, or the NUL is exactly the last + * byte, the read will look like it got truncated by one byte. + * Since there is no way to ask sprintf nicely to not write + * the NUL, we have to use a bounce buffer. + */ + wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n", + kallsyms_show_value(file->f_cred) + ? (void *)sattr->address : NULL); + count = min(count, wrote); + memcpy(buf, bounce, count); + + return count; } static void free_sect_attrs(struct module_sect_attrs *sect_attrs) @@ -1523,7 +1539,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) goto out; sect_attrs->nsections++; sattr->battr.read = module_sect_read; - sattr->battr.size = 3 /* "0x", "\n" */ + (BITS_PER_LONG / 4); + sattr->battr.size = MODULE_SECT_READ_SIZE; sattr->battr.attr.mode = 0400; *(gattr++) = &(sattr++)->battr; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d2297106c92..dcc54d44fcde 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2338,6 +2338,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * Silence PROVE_RCU. */ raw_spin_lock_irqsave(&p->pi_lock, flags); + rseq_migrate(p); /* * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). @@ -2402,6 +2403,7 @@ void wake_up_new_task(struct task_struct *p) * as we're not fully set-up yet. */ p->recent_used_cpu = task_cpu(p); + rseq_migrate(p); __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4702f3afa5ac..50f4b19a5387 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3806,7 +3806,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; } - rq->misfit_task_load = task_h_load(p); + /* + * Make sure that misfit_task_load will not be null even if + * task_h_load() returns 0. + */ + rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1); } #else /* CONFIG_SMP */ @@ -7658,7 +7662,15 @@ static int detach_tasks(struct lb_env *env) if (!can_migrate_task(p, env)) goto next; - load = task_h_load(p); + /* + * Depending of the number of CPUs and tasks and the + * cgroup hierarchy, task_h_load() can return a null + * value. Make sure that env->imbalance decreases + * otherwise detach_tasks() will stop only after + * detaching up to loop_max tasks. + */ + load = max_t(unsigned long, task_h_load(p), 1); + if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) goto next; @@ -9661,7 +9673,12 @@ static void kick_ilb(unsigned int flags) { int ilb_cpu; - nohz.next_balance++; + /* + * Increase nohz.next_balance only when if full ilb is triggered but + * not if we only update stats. + */ + if (flags & NOHZ_BALANCE_KICK) + nohz.next_balance = jiffies+1; ilb_cpu = find_new_ilb(); @@ -9980,6 +9997,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, } } + /* + * next_balance will be updated only when there is a need. + * When the CPU is attached to null domain for ex, it will not be + * updated. + */ + if (likely(update_next_balance)) + nohz.next_balance = next_balance; + /* Newly idle CPU doesn't need an update */ if (idle != CPU_NEWLY_IDLE) { update_blocked_averages(this_cpu); @@ -10000,14 +10025,6 @@ abort: if (has_blocked_load) WRITE_ONCE(nohz.has_blocked, 1); - /* - * next_balance will be updated only when there is a need. - * When the CPU is attached to null domain for ex, it will not be - * updated. - */ - if (likely(update_next_balance)) - nohz.next_balance = next_balance; - return ret; } diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index a906d2535710..6fb3e636fbe1 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1332,7 +1332,7 @@ sd_init(struct sched_domain_topology_level *tl, sd_flags = (*tl->sd_flags)(); if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, "wrong sd_flags in topology description\n")) - sd_flags &= ~TOPOLOGY_SD_FLAGS; + sd_flags &= TOPOLOGY_SD_FLAGS; /* Apply detected topology flags */ sd_flags |= dflags; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 733f7524a2c3..e914d72b3290 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -42,6 +42,14 @@ #include <linux/uaccess.h> #include <linux/anon_inodes.h> +/* + * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the + * wrong direction flag in the ioctl number. This is the broken one, + * which the kernel needs to keep supporting until all userspaces stop + * using the wrong command number. + */ +#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) + enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, @@ -1161,6 +1169,7 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd, return seccomp_notify_recv(filter, buf); case SECCOMP_IOCTL_NOTIF_SEND: return seccomp_notify_send(filter, buf); + case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR: case SECCOMP_IOCTL_NOTIF_ID_VALID: return seccomp_notify_id_valid(filter, buf); default: diff --git a/kernel/task_work.c b/kernel/task_work.c index 0fef395662a6..83fb1ecfc33d 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -116,3 +116,4 @@ void task_work_run(void) } while (work); } } +EXPORT_SYMBOL_GPL(task_work_run); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 7c8f465ae02f..e70451eb2495 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -519,8 +519,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk) * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ - if (expires >= WHEEL_TIMEOUT_CUTOFF) - expires = WHEEL_TIMEOUT_MAX; + if (delta >= WHEEL_TIMEOUT_CUTOFF) + expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1); } @@ -582,7 +582,15 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * Set the next expiry time and kick the CPU so it can reevaluate the * wheel: */ - base->next_expiry = timer->expires; + if (time_before(timer->expires, base->clk)) { + /* + * Prevent from forward_timer_base() moving the base->clk + * backward + */ + base->next_expiry = base->clk; + } else { + base->next_expiry = timer->expires; + } wake_up_nohz_cpu(base->cpu); } @@ -894,10 +902,13 @@ static inline void forward_timer_base(struct timer_base *base) * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ - if (time_after(base->next_expiry, jnow)) + if (time_after(base->next_expiry, jnow)) { base->clk = jnow; - else + } else { + if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) + return; base->clk = base->next_expiry; + } #endif } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 45369eccbc01..8f18311f9be5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -348,7 +348,8 @@ static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; - bt = xchg(&q->blk_trace, NULL); + bt = rcu_replace_pointer(q->blk_trace, NULL, + lockdep_is_held(&q->blk_trace_mutex)); if (!bt) return -EINVAL; @@ -483,6 +484,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct dentry *dir = NULL; int ret; + lockdep_assert_held(&q->blk_trace_mutex); + if (!buts->buf_size || !buts->buf_nr) return -EINVAL; @@ -502,7 +505,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * bdev can be NULL, as with scsi-generic, this is a helpful as * we can be. */ - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; @@ -521,13 +525,31 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->msg_data) goto err; - ret = -ENOENT; - - dir = debugfs_lookup(buts->name, blk_debugfs_root); - if (!dir) +#ifdef CONFIG_BLK_DEBUG_FS + /* + * When tracing whole make_request drivers (multiqueue) block devices, + * reuse the existing debugfs directory created by the block layer on + * init. For request-based block devices, all partitions block devices, + * and scsi-generic block devices we create a temporary new debugfs + * directory that will be removed once the trace ends. + */ + if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains) + dir = q->debugfs_dir; + else +#endif bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); - if (!dir) + + /* + * As blktrace relies on debugfs for its interface the debugfs directory + * is required, contrary to the usual mantra of not checking for debugfs + * files or directories. + */ + if (IS_ERR_OR_NULL(dir)) { + pr_warn("debugfs_dir not present for %s so skipping\n", + buts->name); + ret = -ENOENT; goto err; + } bt->dev = dev; atomic_set(&bt->dropped, 0); @@ -536,12 +558,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = -EIO; bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); - if (!bt->dropped_file) - goto err; bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); - if (!bt->msg_file) - goto err; bt->rchan = relay_open("trace", dir, buts->buf_size, buts->buf_nr, &blk_relay_callbacks, bt); @@ -563,16 +581,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, bt->pid = buts->pid; bt->trace_state = Blktrace_setup; - ret = -EBUSY; - if (cmpxchg(&q->blk_trace, NULL, bt)) - goto err; - + rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); ret = 0; err: - if (dir && !bt->dir) - dput(dir); if (ret) blk_trace_free(bt); return ret; @@ -1640,7 +1653,8 @@ static int blk_trace_remove_queue(struct request_queue *q) { struct blk_trace *bt; - bt = xchg(&q->blk_trace, NULL); + bt = rcu_replace_pointer(q->blk_trace, NULL, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -1672,10 +1686,7 @@ static int blk_trace_setup_queue(struct request_queue *q, blk_trace_setup_lba(bt, bdev); - ret = -EBUSY; - if (cmpxchg(&q->blk_trace, NULL, bt)) - goto free_bt; - + rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); return 0; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ed0db562b267..98751023c05a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5678,8 +5678,11 @@ static int referenced_filters(struct dyn_ftrace *rec) int cnt = 0; for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops_references_rec(ops, rec)) - cnt++; + if (ops_references_rec(ops, rec)) { + cnt++; + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; + } } return cnt; @@ -5856,8 +5859,8 @@ void ftrace_module_enable(struct module *mod) if (ftrace_start_up) cnt += referenced_filters(rec); - /* This clears FTRACE_FL_DISABLED */ - rec->flags = cnt; + rec->flags &= ~FTRACE_FL_DISABLED; + rec->flags += cnt; if (ftrace_start_up && cnt) { int failed = __ftrace_replace_code(rec, 1); @@ -6442,12 +6445,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } else { unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 08d4e9a04f82..42d4afd2fc4f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -534,12 +534,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork, tr, INT_MIN); - register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit, + register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit, tr, INT_MAX); } else { unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork, tr); - unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit, + unregister_trace_sched_process_free(event_filter_pid_sched_process_exit, tr); } } diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 8030e24dbf14..568918fae8d4 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -270,6 +270,7 @@ static bool disable_migrate; static void move_to_next_cpu(void) { struct cpumask *current_mask = &save_cpumask; + struct trace_array *tr = hwlat_trace; int next_cpu; if (disable_migrate) @@ -283,7 +284,7 @@ static void move_to_next_cpu(void) goto disable; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); next_cpu = cpumask_next(smp_processor_id(), current_mask); put_online_cpus(); @@ -360,7 +361,7 @@ static int start_kthread(struct trace_array *tr) /* Just pick the first CPU on first iteration */ current_mask = &save_cpumask; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); put_online_cpus(); next_cpu = cpumask_first(current_mask); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 568068782e11..5b4f50932478 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -158,6 +158,20 @@ static void check_stack(unsigned long ip, unsigned long *stack) i++; } +#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER + /* + * Some archs will store the link register before calling + * nested functions. This means the saved return address + * comes after the local storage, and we need to shift + * for that. + */ + if (x > 1) { + memmove(&stack_trace_index[0], &stack_trace_index[1], + sizeof(stack_trace_index[0]) * (x - 1)); + x--; + } +#endif + stack_trace_nr_entries = x; if (task_stack_end_corrupted(current)) { diff --git a/kernel/uptime_limit.c b/kernel/uptime_limit.c new file mode 100644 index 000000000000..b6a1a5e4f9d9 --- /dev/null +++ b/kernel/uptime_limit.c @@ -0,0 +1,166 @@ +/* + * uptime_limit.c + * + * This file contains the functions which can limit kernel uptime + * + * Copyright (C) 2011 Bruce Ashfield (bruce.ashfield@windriver.com) + * + * 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., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * + * This functionality is somewhat close to the softdog watchdog + * implementation, but it cannot be used directly for several reasons: + * + * - The soft watchdog should be available while this functionality is active + * - The duration range is different between this and the softdog. The + * timeout available here is potentially quite a bit longer. + * - At expiration, there are different expiration requirements and actions. + * - This functionality is specific to a particular use case and should + * not impact mainline functionality + * + */ +#include <linux/kernel.h> +#include <linux/reboot.h> +#include <linux/timer.h> +#include <linux/delay.h> +#include <linux/kthread.h> + +#define UPTIME_LIMIT_IN_SECONDS (CONFIG_UPTIME_LIMIT_DURATION * 60) +#define MIN(X, Y) ((X) <= (Y) ? (X) : (Y)) +#define TEN_MINUTES_IN_SECONDS 600 + +enum uptime_expiration_type { + uptime_no_action, + uptime_reboot +}; + +static enum uptime_expiration_type uptime_expiration_action = uptime_no_action; +static struct timer_list timelimit_timer; +static struct task_struct *uptime_worker_task; + +static void timelimit_expire(unsigned long timeout_seconds) +{ + char msg[128]; + int msglen = 127; + + if (timeout_seconds) { + if (timeout_seconds >= 60) + snprintf(msg, msglen, + "Uptime: kernel validity duration has %d %s remaining\n", + (int) timeout_seconds / 60, "minute(s)"); + else + snprintf(msg, msglen, + "Uptime: kernel validity duration has %d %s remaining\n", + (int) timeout_seconds, "seconds"); + + printk(KERN_CRIT "%s", msg); + + timelimit_timer.expires = jiffies + timeout_seconds * HZ; + timelimit_timer.data = 0; + add_timer_on(&timelimit_timer, cpumask_first(cpu_online_mask)); + } else { + printk(KERN_CRIT "Uptime: Kernel validity timeout has expired\n"); +#ifdef CONFIG_UPTIME_LIMIT_KERNEL_REBOOT + uptime_expiration_action = uptime_reboot; + wake_up_process(uptime_worker_task); + } +#endif +} + +/* + * This thread starts and then immediately goes to sleep. When it is woken + * up, it carries out the instructions left in uptime_expiration_action. If + * no action was specified it simply goes back to sleep. + */ +static int uptime_worker(void *unused) +{ + set_current_state(TASK_INTERRUPTIBLE); + + while (!kthread_should_stop()) { + schedule(); + + if (kthread_should_stop()) + break; + + if (uptime_expiration_action == uptime_reboot) { + printk(KERN_CRIT "Uptime: restarting machine\n"); + kernel_restart(NULL); + } + + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + return 0; +} + +static int timeout_enable(int cpu) +{ + int err = 0; + int warning_limit; + + /* + * Create an uptime worker thread. This thread is required since the + * safe version of kernel restart cannot be called from a + * non-interruptible context. Which means we cannot call it directly + * from a timer callback. So we arrange for the timer expiration to + * wakeup a thread, which performs the action. + */ + uptime_worker_task = kthread_create(uptime_worker, + (void *)(unsigned long)cpu, + "uptime_worker/%d", cpu); + if (IS_ERR(uptime_worker_task)) { + printk(KERN_ERR "Uptime: task for cpu %i failed\n", cpu); + err = PTR_ERR(uptime_worker_task); + goto out; + } + /* bind to cpu0 to avoid migration and hot plug nastiness */ + kthread_bind(uptime_worker_task, cpu); + wake_up_process(uptime_worker_task); + + /* Create the timer that will wake the uptime thread at expiration */ + init_timer(&timelimit_timer); + timelimit_timer.function = timelimit_expire; + /* + * Fire two timers. One warning timeout and the final timer + * which will carry out the expiration action. The warning timer will + * expire at the minimum of half the original time or ten minutes. + */ + warning_limit = MIN(UPTIME_LIMIT_IN_SECONDS/2, TEN_MINUTES_IN_SECONDS); + timelimit_timer.expires = jiffies + warning_limit * HZ; + timelimit_timer.data = UPTIME_LIMIT_IN_SECONDS - warning_limit; + + add_timer_on(&timelimit_timer, cpumask_first(cpu_online_mask)); +out: + return err; +} + +static int __init timelimit_init(void) +{ + int err = 0; + + printk(KERN_INFO "Uptime: system uptime restrictions enabled\n"); + + /* + * Enable the timeout thread for cpu 0 only, assuming that the + * uptime limit is non-zero, to protect against any cpu + * migration issues. + */ + if (UPTIME_LIMIT_IN_SECONDS) + err = timeout_enable(0); + + return err; +} +device_initcall(timelimit_init); diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c index 8cc01a603416..c9acf1c12cfc 100644 --- a/lib/crc-t10dif.c +++ b/lib/crc-t10dif.c @@ -19,39 +19,46 @@ static struct crypto_shash __rcu *crct10dif_tfm; static struct static_key crct10dif_fallback __read_mostly; static DEFINE_MUTEX(crc_t10dif_mutex); +static struct work_struct crct10dif_rehash_work; -static int crc_t10dif_rehash(struct notifier_block *self, unsigned long val, void *data) +static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data) { struct crypto_alg *alg = data; - struct crypto_shash *new, *old; if (val != CRYPTO_MSG_ALG_LOADED || static_key_false(&crct10dif_fallback) || strncmp(alg->cra_name, CRC_T10DIF_STRING, strlen(CRC_T10DIF_STRING))) return 0; + schedule_work(&crct10dif_rehash_work); + return 0; +} + +static void crc_t10dif_rehash(struct work_struct *work) +{ + struct crypto_shash *new, *old; + mutex_lock(&crc_t10dif_mutex); old = rcu_dereference_protected(crct10dif_tfm, lockdep_is_held(&crc_t10dif_mutex)); if (!old) { mutex_unlock(&crc_t10dif_mutex); - return 0; + return; } new = crypto_alloc_shash("crct10dif", 0, 0); if (IS_ERR(new)) { mutex_unlock(&crc_t10dif_mutex); - return 0; + return; } rcu_assign_pointer(crct10dif_tfm, new); mutex_unlock(&crc_t10dif_mutex); synchronize_rcu(); crypto_free_shash(old); - return 0; } static struct notifier_block crc_t10dif_nb = { - .notifier_call = crc_t10dif_rehash, + .notifier_call = crc_t10dif_notify, }; __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len) @@ -86,19 +93,26 @@ EXPORT_SYMBOL(crc_t10dif); static int __init crc_t10dif_mod_init(void) { + struct crypto_shash *tfm; + + INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash); crypto_register_notifier(&crc_t10dif_nb); - crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0); - if (IS_ERR(crct10dif_tfm)) { + mutex_lock(&crc_t10dif_mutex); + tfm = crypto_alloc_shash("crct10dif", 0, 0); + if (IS_ERR(tfm)) { static_key_slow_inc(&crct10dif_fallback); - crct10dif_tfm = NULL; + tfm = NULL; } + RCU_INIT_POINTER(crct10dif_tfm, tfm); + mutex_unlock(&crc_t10dif_mutex); return 0; } static void __exit crc_t10dif_mod_fini(void) { crypto_unregister_notifier(&crc_t10dif_nb); - crypto_free_shash(crct10dif_tfm); + cancel_work_sync(&crct10dif_rehash_work); + crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1)); } module_init(crc_t10dif_mod_init); @@ -106,11 +120,27 @@ module_exit(crc_t10dif_mod_fini); static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp) { + struct crypto_shash *tfm; + const char *name; + int len; + if (static_key_false(&crct10dif_fallback)) return sprintf(buffer, "fallback\n"); - return sprintf(buffer, "%s\n", - crypto_tfm_alg_driver_name(crypto_shash_tfm(crct10dif_tfm))); + rcu_read_lock(); + tfm = rcu_dereference(crct10dif_tfm); + if (!tfm) { + len = sprintf(buffer, "init\n"); + goto unlock; + } + + name = crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm)); + len = sprintf(buffer, "%s\n", name); + +unlock: + rcu_read_unlock(); + + return len; } module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0644); diff --git a/lib/devres.c b/lib/devres.c index 17624d35e82d..77c80ca9e485 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -155,6 +155,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, { resource_size_t size; void __iomem *dest_ptr; + char *pretty_name; BUG_ON(!dev); @@ -165,7 +166,15 @@ void __iomem *devm_ioremap_resource(struct device *dev, size = resource_size(res); - if (!devm_request_mem_region(dev, res->start, size, dev_name(dev))) { + if (res->name) + pretty_name = devm_kasprintf(dev, GFP_KERNEL, "%s %s", + dev_name(dev), res->name); + else + pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); + if (!pretty_name) + return IOMEM_ERR_PTR(-ENOMEM); + + if (!devm_request_mem_region(dev, res->start, size, pretty_name)) { dev_err(dev, "can't request region for resource %pR\n", res); return IOMEM_ERR_PTR(-EBUSY); } diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 8a16c2d498e9..af9aba06c59f 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -87,22 +87,22 @@ static struct { unsigned flag:8; char opt_char; } opt_array[] = { { _DPRINTK_FLAGS_NONE, '_' }, }; +struct flagsbuf { char buf[ARRAY_SIZE(opt_array)+1]; }; + /* format a string into buf[] which describes the _ddebug's flags */ -static char *ddebug_describe_flags(struct _ddebug *dp, char *buf, - size_t maxlen) +static char *ddebug_describe_flags(unsigned int flags, struct flagsbuf *fb) { - char *p = buf; + char *p = fb->buf; int i; - BUG_ON(maxlen < 6); for (i = 0; i < ARRAY_SIZE(opt_array); ++i) - if (dp->flags & opt_array[i].flag) + if (flags & opt_array[i].flag) *p++ = opt_array[i].opt_char; - if (p == buf) + if (p == fb->buf) *p++ = '_'; *p = '\0'; - return buf; + return fb->buf; } #define vpr_info(fmt, ...) \ @@ -144,7 +144,7 @@ static int ddebug_change(const struct ddebug_query *query, struct ddebug_table *dt; unsigned int newflags; unsigned int nfound = 0; - char flagbuf[10]; + struct flagsbuf fbuf; /* search for matching ddebugs */ mutex_lock(&ddebug_lock); @@ -201,8 +201,7 @@ static int ddebug_change(const struct ddebug_query *query, vpr_info("changed %s:%d [%s]%s =%s\n", trim_prefix(dp->filename), dp->lineno, dt->mod_name, dp->function, - ddebug_describe_flags(dp, flagbuf, - sizeof(flagbuf))); + ddebug_describe_flags(dp->flags, &fbuf)); } } mutex_unlock(&ddebug_lock); @@ -816,7 +815,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p) { struct ddebug_iter *iter = m->private; struct _ddebug *dp = p; - char flagsbuf[10]; + struct flagsbuf flags; vpr_info("called m=%p p=%p\n", m, p); @@ -829,7 +828,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p) seq_printf(m, "%s:%u [%s]%s =%s \"", trim_prefix(dp->filename), dp->lineno, iter->table->mod_name, dp->function, - ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf))); + ddebug_describe_flags(dp->flags, &flags)); seq_escape(m, dp->format, "\t\r\n\""); seq_puts(m, "\"\n"); diff --git a/lib/random32.c b/lib/random32.c index c4d317be2997..3d749abb9e80 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void) } #endif -DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state); /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/test_kmod.c b/lib/test_kmod.c index 9cf77628fc91..87a0cc750ea2 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -745,7 +745,7 @@ static int trigger_config_run_type(struct kmod_test_device *test_dev, break; case TEST_KMOD_FS_TYPE: kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; copied = config_copy_test_fs(config, test_str, strlen(test_str)); break; diff --git a/mm/Makefile b/mm/Makefile index ac5e5ba78874..5decb22d13a0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -39,7 +39,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o vmacache.o \ interval_tree.o list_lru.o workingset.o \ - debug.o $(mmu-y) + prfile.o debug.o $(mmu-y) # 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 56dcc7c15366..7301431fb34e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2459,7 +2459,7 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ - if (vmf->vma->vm_flags & VM_RAND_READ) + if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; if (ra->mmap_miss > 0) ra->mmap_miss--; @@ -2703,7 +2703,7 @@ 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/hugetlb.c b/mm/hugetlb.c index acabe9928049..1eedc7003380 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3013,6 +3013,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array) } #ifdef CONFIG_SYSCTL +static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos, unsigned long *out) +{ + struct ctl_table dup_table; + + /* + * In order to avoid races with __do_proc_doulongvec_minmax(), we + * can duplicate the @table and alter the duplicate of it. + */ + dup_table = *table; + dup_table.data = out; + + return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); +} + static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) @@ -3024,9 +3040,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, if (!hugepages_supported()) return -EOPNOTSUPP; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; @@ -3070,9 +3085,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, if (write && hstate_is_gigantic(h)) return -EINVAL; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; diff --git a/mm/madvise.c b/mm/madvise.c index ae56d0ef337d..9c43c8515cef 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -308,9 +308,9 @@ static long madvise_willneed(struct vm_area_struct *vma, */ *prev = NULL; /* tell sys_madvise we drop mmap_sem */ get_file(file); - up_read(¤t->mm->mmap_sem); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); down_read(¤t->mm->mmap_sem); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e05bb6ea5771..996f4cbe612f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5300,7 +5300,6 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - mem_cgroup_id_get_many(mc.to, mc.moved_swap); css_put_many(&mc.to->css, mc.moved_swap); mc.moved_swap = 0; @@ -5491,7 +5490,8 @@ put: /* get_mctgt_type() gets the page */ ent = target.ent; if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) { mc.precharge--; - /* we fixup refcnts and charges later. */ + mem_cgroup_id_get_many(mc.to, 1); + /* we fixup other refcnts and charges later. */ mc.moved_swap++; } break; diff --git a/mm/mmap.c b/mm/mmap.c index 93aeb7130d91..bc841e98bb92 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -176,7 +176,7 @@ 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; @@ -925,7 +925,7 @@ 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); @@ -1841,8 +1841,8 @@ 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); @@ -2611,7 +2611,7 @@ static void unmap_region(struct mm_struct *mm, * Create a list of vma's touched by the unmap, removing them from the mm's * vma list as we go.. */ -static void +static bool detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long end) { @@ -2636,6 +2636,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, /* Kill the cache */ vmacache_invalidate(mm); + + /* + * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or + * VM_GROWSUP VMA. Such VMAs can change their size under + * down_read(mmap_lock) and collide with the VMA we are about to unmap. + */ + if (vma && (vma->vm_flags & VM_GROWSDOWN)) + return false; + if (prev && (prev->vm_flags & VM_GROWSUP)) + return false; + return true; } /* @@ -2674,7 +2685,7 @@ 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); @@ -2693,7 +2704,7 @@ 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)); @@ -2816,7 +2827,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, } /* Detach vmas from rbtree */ - detach_vmas_to_be_unmapped(mm, vma, prev, end); + if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) + downgrade = false; if (downgrade) downgrade_write(&mm->mmap_sem); @@ -2884,7 +2896,7 @@ 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); @@ -2959,10 +2971,27 @@ 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: up_write(&mm->mmap_sem); if (populate) @@ -3148,6 +3177,7 @@ void exit_mmap(struct mm_struct *mm) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma = remove_vma(vma); + cond_resched(); } vm_unacct_memory(nr_accounted); } @@ -3252,7 +3282,7 @@ 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 aec5a3599a30..690c26ac8b27 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -644,7 +644,7 @@ 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 */ @@ -782,7 +782,7 @@ 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); } @@ -1305,7 +1305,7 @@ 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; @@ -1380,10 +1380,10 @@ 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/page_counter.c b/mm/page_counter.c index de31470655f6..147ff99187b8 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -77,7 +77,7 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) long new; new = atomic_long_add_return(nr_pages, &c->usage); - propagate_protected_usage(counter, new); + propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. @@ -121,7 +121,7 @@ bool page_counter_try_charge(struct page_counter *counter, new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); - propagate_protected_usage(counter, new); + propagate_protected_usage(c, new); /* * This is racy, but we can live with some * inaccuracy in the failcnt. @@ -130,7 +130,7 @@ bool page_counter_try_charge(struct page_counter *counter, *fail = c; goto failed; } - propagate_protected_usage(counter, new); + propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. diff --git a/mm/prfile.c b/mm/prfile.c new file mode 100644 index 000000000000..024cdcfae1b1 --- /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) 2014-2019 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/slab_common.c b/mm/slab_common.c index f2e9911023a0..70fb7eec7360 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -130,6 +130,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, #ifdef CONFIG_MEMCG_KMEM LIST_HEAD(slab_root_caches); +static DEFINE_SPINLOCK(memcg_kmem_wq_lock); void slab_init_memcg_params(struct kmem_cache *s) { @@ -310,6 +311,14 @@ int slab_unmergeable(struct kmem_cache *s) if (s->refcount < 0) return 1; +#ifdef CONFIG_MEMCG_KMEM + /* + * Skip the dying kmem_cache. + */ + if (s->memcg_params.dying) + return 1; +#endif + return 0; } @@ -744,14 +753,22 @@ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, WARN_ON_ONCE(s->memcg_params.deact_fn)) return; + /* + * memcg_kmem_wq_lock is used to synchronize memcg_params.dying + * flag and make sure that no new kmem_cache deactivation tasks + * are queued (see flush_memcg_workqueue() ). + */ + spin_lock_irq(&memcg_kmem_wq_lock); if (s->memcg_params.root_cache->memcg_params.dying) - return; + goto unlock; /* pin memcg so that @s doesn't get destroyed in the middle */ css_get(&s->memcg_params.memcg->css); s->memcg_params.deact_fn = deact_fn; call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn); +unlock: + spin_unlock_irq(&memcg_kmem_wq_lock); } void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) @@ -859,12 +876,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s) return 0; } -static void flush_memcg_workqueue(struct kmem_cache *s) +static void memcg_set_kmem_cache_dying(struct kmem_cache *s) { - mutex_lock(&slab_mutex); + spin_lock_irq(&memcg_kmem_wq_lock); s->memcg_params.dying = true; - mutex_unlock(&slab_mutex); + spin_unlock_irq(&memcg_kmem_wq_lock); +} +static void flush_memcg_workqueue(struct kmem_cache *s) +{ /* * SLUB deactivates the kmem_caches through call_rcu. Make * sure all registered rcu callbacks have been invoked. @@ -897,10 +917,6 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s) { return 0; } - -static inline void flush_memcg_workqueue(struct kmem_cache *s) -{ -} #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) @@ -918,8 +934,6 @@ void kmem_cache_destroy(struct kmem_cache *s) if (unlikely(!s)) return; - flush_memcg_workqueue(s); - get_online_cpus(); get_online_mems(); @@ -929,6 +943,22 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; +#ifdef CONFIG_MEMCG_KMEM + memcg_set_kmem_cache_dying(s); + + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); + + flush_memcg_workqueue(s); + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); +#endif + err = shutdown_memcg_caches(s); if (!err) err = shutdown_cache(s); diff --git a/mm/slub.c b/mm/slub.c index 9e7da3b8bd0a..04a46eaea862 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -645,12 +645,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...) } static bool freelist_corrupted(struct kmem_cache *s, struct page *page, - void *freelist, void *nextfree) + void **freelist, void *nextfree) { if ((s->flags & SLAB_CONSISTENCY_CHECKS) && - !check_valid_pointer(s, page, nextfree)) { - object_err(s, page, freelist, "Freechain corrupt"); - freelist = NULL; + !check_valid_pointer(s, page, nextfree) && freelist) { + object_err(s, page, *freelist, "Freechain corrupt"); + *freelist = NULL; slab_fix(s, "Isolate corrupted freechain"); return true; } @@ -1391,7 +1391,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} static bool freelist_corrupted(struct kmem_cache *s, struct page *page, - void *freelist, void *nextfree) + void **freelist, void *nextfree) { return false; } @@ -2089,7 +2089,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * 'freelist' is already corrupted. So isolate all objects * starting at 'freelist'. */ - if (freelist_corrupted(s, page, freelist, nextfree)) + if (freelist_corrupted(s, page, &freelist, nextfree)) break; do { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 13cd683a658a..12ecacf0c55f 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work) if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); + } else if (m->rreq->status == REQ_STATUS_FLSHD) { + /* Ignore replies associated with a cancelled request. */ + p9_debug(P9_DEBUG_TRANS, + "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->client->lock); p9_debug(P9_DEBUG_ERROR, @@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + spin_lock(&client->lock); + /* Ignore cancelled request if message has been received + * before lock. + */ + if (req->status == REQ_STATUS_RCVD) { + spin_unlock(&client->lock); + return 0; + } + /* we haven't received a response for oldreq, * remove it from the list. */ - spin_lock(&client->lock); list_del(&req->req_list); + req->status = REQ_STATUS_FLSHD; spin_unlock(&client->lock); p9_req_put(req); @@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) return -ENOMEM; ts->rd = fget(rfd); + if (!ts->rd) + goto out_free_ts; + if (!(ts->rd->f_mode & FMODE_READ)) + goto out_put_rd; ts->wr = fget(wfd); - if (!ts->rd || !ts->wr) { - if (ts->rd) - fput(ts->rd); - if (ts->wr) - fput(ts->wr); - kfree(ts); - return -EIO; - } + if (!ts->wr) + goto out_put_rd; + if (!(ts->wr->f_mode & FMODE_WRITE)) + goto out_put_wr; client->trans = ts; client->status = Connected; return 0; + +out_put_wr: + fput(ts->wr); +out_put_rd: + fput(ts->rd); +out_free_ts: + kfree(ts); + return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 550c6ca007cc..9c1241292d1d 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -229,6 +229,8 @@ int __init atalk_proc_init(void) sizeof(struct aarp_iter_state), NULL)) goto out; + return 0; + out: remove_proc_subtree("atalk", init_net.proc_net); return -ENOMEM; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index e5a3dc28116d..2fdb1b573e8c 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1187,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock, if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ - if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) { + if (fsa->fsa_ax25.sax25_ndigis < 1 || + fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } @@ -1507,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ - if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) { + if (usax->sax25_ndigis < 1 || + usax->sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9001bf331d56..120529290d99 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -50,6 +50,7 @@ static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; +static DEFINE_MUTEX(set_lock); struct lowpan_peer { struct list_head list; @@ -1075,12 +1076,14 @@ static void do_enable_set(struct work_struct *work) enable_6lowpan = set_enable->flag; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); + mutex_unlock(&set_lock); kfree(set_enable); } @@ -1132,11 +1135,13 @@ static ssize_t lowpan_control_write(struct file *fp, if (ret == -EINVAL) return ret; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); listen_chan = NULL; } + mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 041c37f7ae89..b323c65a4485 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1229,6 +1229,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; + if (len > HCI_MAX_AD_LENGTH) + return; + bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; @@ -2396,7 +2399,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -3992,6 +3995,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct inquiry_info_with_rssi_and_pscan_mode *info; info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4013,6 +4019,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } else { struct inquiry_info_with_rssi *info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4033,6 +4042,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } } +unlock: hci_dev_unlock(hdev); } @@ -4195,7 +4205,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -5159,7 +5169,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len) + u8 direct_addr_type, s8 rssi, u8 *data, u8 len, + bool ext_adv) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -5181,6 +5192,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } + if (!ext_adv && len > HCI_MAX_AD_LENGTH) { + bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * @@ -5240,7 +5256,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, direct_addr); - if (conn && type == LE_ADV_IND) { + if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -5294,7 +5310,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!has_pending_adv_report(hdev)) { + if (!ext_adv && !has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ @@ -5329,7 +5345,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the new report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; @@ -5369,7 +5386,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + ev->data, ev->length, false); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } @@ -5443,7 +5460,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, - ev->data, ev->length); + ev->data, ev->length, + !(evt_type & LE_EXT_ADV_LEGACY_PDU)); } ptr += sizeof(*ev) + ev->length; @@ -5641,7 +5659,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, - ev->direct_addr_type, ev->rssi, NULL, 0); + ev->direct_addr_type, ev->rssi, NULL, 0, + false); ptr += sizeof(*ev); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index c370b1eb8203..bb85787f9237 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -453,6 +453,7 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; + dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->paused = src->paused; diff --git a/net/compat.c b/net/compat.c index 3f9ce609397f..24906536870f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -290,6 +290,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ + __receive_sock(fp[i]); fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/dev.c b/net/core/dev.c index 5f2f1a8df3c8..cff7f1d91bf3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5319,7 +5319,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } diff --git a/net/core/filter.c b/net/core/filter.c index f311dde6600a..633b048792b2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2916,7 +2916,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { - __be16 from_proto = skb->protocol; + __be16 from_proto = skb_protocol(skb, true); if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) @@ -2989,7 +2989,7 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = { static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): @@ -3157,7 +3157,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = __bpf_skb_max_len(skb); - __be16 proto = skb->protocol; + __be16 proto = skb_protocol(skb, true); bool shrink = len_diff < 0; u32 off; int ret; @@ -4922,7 +4922,7 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: - if (skb->protocol != htons(ETH_P_IPV6)) + if (skb_protocol(skb, true) != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 865ba6ca16eb..229ecf256f4e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1031,7 +1031,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); - return sprintf(buf, "%lu", trans_timeout); + return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) diff --git a/net/core/sock.c b/net/core/sock.c index ffd832bf4646..fb83335a5abb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1833,7 +1833,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; - cgroup_sk_alloc(&newsk->sk_cgrp_data); + cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -2729,6 +2729,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct * } EXPORT_SYMBOL(sock_no_mmap); +/* + * When a file is received (via SCM_RIGHTS, etc), we must bump the + * various sock-based usage counts. + */ +void __receive_sock(struct file *file) +{ + struct socket *sock; + int error; + + /* + * The resulting value of "error" is ignored here since we only + * need to take action when the file is a socket and testing + * "sock" for NULL is sufficient. + */ + sock = sock_from_file(file, &error); + if (sock) { + sock_update_netprioidx(&sock->sk->sk_cgrp_data); + sock_update_classid(&sock->sk->sk_cgrp_data); + } +} + ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 05eb42f347e8..fc5b492184ed 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/fib_trie.c b/net/ipv4/fib_trie.c index 77da7df84494..4c6f04b6afba 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1738,7 +1738,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 4de7e962d3da..c840141876bc 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + bool need_csum, need_recompute_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, gso_partial; if (!skb->encapsulation) goto out; @@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); + need_recompute_csum = skb->csum_not_inet; skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; @@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - *pcsum = gso_make_checksum(skb, 0); + if (need_recompute_csum && !skb_is_gso(skb)) { + __wsum csum; + + csum = skb_checksum(skb, gre_offset, + skb->len - gre_offset, 0); + *pcsum = csum_fold(csum); + } else { + *pcsum = gso_make_checksum(skb, 0); + } } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 9f7dc49d761a..92b31d251da8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -284,6 +284,57 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, ipv6_only_sock(sk), true, false); } +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk) +{ + kuid_t uid = sock_i_uid(sk); + bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; + + if (hlist_empty(&tb->owners)) { + tb->fastreuse = reuse; + if (sk->sk_reuseport) { + tb->fastreuseport = FASTREUSEPORT_ANY; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } else { + tb->fastreuseport = 0; + } + } else { + if (!reuse) + tb->fastreuse = 0; + if (sk->sk_reuseport) { + /* We didn't match or we don't have fastreuseport set on + * the tb, but we have sk_reuseport set on this socket + * and we know that there are no bind conflicts with + * this socket in this tb, so reset our tb's reuseport + * settings so that any subsequent sockets that match + * our current socket will be put on the fast path. + * + * If we reset we need to set FASTREUSEPORT_STRICT so we + * do extra checking for all subsequent sk_reuseport + * socks. + */ + if (!sk_reuseport_match(tb, sk)) { + tb->fastreuseport = FASTREUSEPORT_STRICT; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } + } else { + tb->fastreuseport = 0; + } + } +} + /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) @@ -296,7 +347,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); struct inet_bind_bucket *tb = NULL; - kuid_t uid = sock_i_uid(sk); int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -333,49 +383,8 @@ tb_found: goto fail_unlock; } success: - if (hlist_empty(&tb->owners)) { - tb->fastreuse = reuse; - if (sk->sk_reuseport) { - tb->fastreuseport = FASTREUSEPORT_ANY; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } else { - tb->fastreuseport = 0; - } - } else { - if (!reuse) - tb->fastreuse = 0; - if (sk->sk_reuseport) { - /* We didn't match or we don't have fastreuseport set on - * the tb, but we have sk_reuseport set on this socket - * and we know that there are no bind conflicts with - * this socket in this tb, so reset our tb's reuseport - * settings so that any subsequent sockets that match - * our current socket will be put on the fast path. - * - * If we reset we need to set FASTREUSEPORT_STRICT so we - * do extra checking for all subsequent sk_reuseport - * socks. - */ - if (!sk_reuseport_match(tb, sk)) { - tb->fastreuseport = FASTREUSEPORT_STRICT; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } - } else { - tb->fastreuseport = 0; - } - } + inet_csk_update_fastreuse(tb, sk); + if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9a02663f1ef6..7a4e50f060ae 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) return -ENOMEM; } } + inet_csk_update_fastreuse(tb, child); } inet_bind_hash(child, tb, port); spin_unlock(&head->lock); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9d24ef5c5d8f..ce723a526b73 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = user_icmph.type; + fl4.fl4_icmp_code = user_icmph.code; + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 32df5a808e34..86ae03c1c54b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2630,6 +2630,9 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3060,10 +3063,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -3806,10 +3806,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* tcp_md5_do_add() might change key->key under us */ return crypto_ahash_update(hp->md5_req); } EXPORT_SYMBOL(tcp_md5_hash_key); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index c445a81d144e..d7a1f2ef6c52 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0f16cf2794a9..755b44c7506a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2940,6 +2940,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); ca_rtt_us = seq_rtt_us; } @@ -3501,10 +3503,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } } -/* This routine deals with acks during a TLP episode. - * We mark the end of a TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. +/* This routine deals with acks during a TLP episode and ends an episode by + * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3513,7 +3513,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (before(ack, tp->tlp_high_seq)) return; - if (flag & FLAG_DSACKING_ACK) { + if (!tp->tlp_retrans) { + /* TLP of new data has been acknowledged */ + tp->tlp_high_seq = 0; + } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { @@ -4517,6 +4520,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4759,6 +4763,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 16591cccbeff..ef4aa931d044 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1067,9 +1067,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { - /* Pre-existing entry - just update that one. */ + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + */ memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1085,7 +1094,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a7c9728d7fca..807dc290fb7d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -662,7 +662,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -677,7 +678,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -2533,6 +2535,11 @@ void tcp_send_loss_probe(struct sock *sk) int pcount; int mss = tcp_current_mss(sk); + /* At most one outstanding TLP */ + if (tp->tlp_high_seq) + goto rearm_timer; + + tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; @@ -2550,10 +2557,6 @@ void tcp_send_loss_probe(struct sock *sk) return; } - /* At most one outstanding TLP retransmission. */ - if (tp->tlp_high_seq) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2575,10 +2578,12 @@ void tcp_send_loss_probe(struct sock *sk) if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; + tp->tlp_retrans = 1; + +probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; -probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; @@ -3291,7 +3296,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cd59c74efc4f..1009a9e1b779 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2043,7 +2043,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index fed91ab7ec46..cf3a88a10ddd 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 7bef41308be7..0716282ea85d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -205,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1f5a33d0c68c..a71b115e65fe 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2989,7 +2989,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && - !(flags & RTF_LOCAL))) + !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9b4ebe8fa1d2..e0ff2f60f53c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -658,7 +658,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index b9f02f1407ac..4399c8466fe0 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1030,6 +1030,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; + skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); @@ -1101,10 +1102,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } - /* Get routing info from the tunnel socket */ - skb_dst_drop(skb); - skb_dst_set(skb, sk_dst_check(sk, 0)); - inet = inet_sk(sk); fl = &inet->cork.fl; switch (tunnel->encap) { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2017b7d780f5..e56b3ef0d5bc 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -269,6 +269,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (addr->sllc_arphrd != ARPHRD_ETHER) + goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); @@ -324,7 +328,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; - if (unlikely(addr->sllc_family != AF_LLC)) + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; @@ -332,8 +338,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { - if (!addr->sllc_arphrd) - addr->sllc_arphrd = llc->dev->type; if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 496cc4074e74..573b7de8a870 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2134,6 +2134,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..aca608ae313f 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f9fb8ed934a9..5062532a4028 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2305,6 +2305,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { + struct ieee80211_hdr *hdr = (void *)rx->skb->data; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -2315,6 +2316,31 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) if (status->flag & RX_FLAG_DECRYPTED) return 0; + /* check mesh EAPOL frames first */ + if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) && + ieee80211_is_data(fc))) { + struct ieee80211s_hdr *mesh_hdr; + u16 hdr_len = ieee80211_hdrlen(fc); + u16 ethertype_offset; + __be16 ethertype; + + if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr)) + goto drop_check; + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdr_len + 6)) + goto drop_check; + + mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len); + ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) + + sizeof(rfc1042_header); + + if (skb_copy_bits(rx->skb, ethertype_offset, ðertype, 2) == 0 && + ethertype == rx->sdata->control_port_protocol) + return 0; + } + +drop_check: /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_any_nullfunc(fc) && diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index b0b3ea3cbd56..2e217664f146 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -992,7 +992,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) might_sleep(); lockdep_assert_held(&local->sta_mtx); - while (sta->sta_state == IEEE80211_STA_AUTHORIZED) { + if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); WARN_ON_ONCE(ret); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d5103a9eb302..c85752f8bd1a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1955,14 +1955,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { - bool uses_ct = false, resched = false; + bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (is_new_conn_expected(cp, conn_reuse_mode)) { - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { @@ -1970,15 +1970,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int * that uses conntrack while it is still * referenced by controlled connection(s). */ - resched = !uses_ct; + resched = !old_ct; } } if (resched) { + if (!old_ct) + cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); - if (uses_ct) + if (old_ct) return NF_DROP; cp = NULL; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8dc892a9dc91..0c1bc654245c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; + struct sock *sk = tinfo->sock->sk; + struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data) ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { - wait_event_interruptible(*sk_sleep(tinfo->sock->sk), - !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) - || kthread_should_stop()); + wait_event_interruptible(*sk_sleep(sk), + !skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue) || + kthread_should_stop()); /* do we have data now? */ - while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { + while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index efccd1ac9a66..102b8d6b5612 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -989,60 +989,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index ba5ffd3badd3..b5c867fe3232 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock, if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW) + if (sock->type == SOCK_RAW) { + if (!capable(CAP_NET_RAW)) + return -EPERM; sock->ops = &rawsock_raw_ops; - else + } else { sock->ops = &rawsock_ops; + } sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); if (!sk) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 1d418d1eef5d..8d66222a65df 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -#define IN6_ADDR_INITIALIZER(ADDR) \ - { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ - (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } - int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { @@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey, if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { - struct ovs_key_ct_tuple_ipv4 orig = { - output->ipv4.ct_orig.src, - output->ipv4.ct_orig.dst, - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv4 orig; + + memset(&orig, 0, sizeof(orig)); + orig.ipv4_src = output->ipv4.ct_orig.src; + orig.ipv4_dst = output->ipv4.ct_orig.dst; + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv4_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - struct ovs_key_ct_tuple_ipv6 orig = { - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv6 orig; + + memset(&orig, 0, sizeof(orig)); + memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, + sizeof(orig.ipv6_src)); + memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, + sizeof(orig.ipv6_dst)); + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv6_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3fc423b63d9b..b2e4c4b192e6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -384,7 +384,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) smp_wmb(); } -static int __packet_get_status(struct packet_sock *po, void *frame) +static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; @@ -460,10 +460,10 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, return ts_status; } -static void *packet_lookup_frame(struct packet_sock *po, - struct packet_ring_buffer *rb, - unsigned int position, - int status) +static void *packet_lookup_frame(const struct packet_sock *po, + const struct packet_ring_buffer *rb, + unsigned int position, + int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; @@ -759,7 +759,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; - if (po->stats.stats3.tp_drops) + if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; @@ -1084,10 +1084,10 @@ static void *packet_current_rx_frame(struct packet_sock *po, } } -static void *prb_lookup_block(struct packet_sock *po, - struct packet_ring_buffer *rb, - unsigned int idx, - int status) +static void *prb_lookup_block(const struct packet_sock *po, + const struct packet_ring_buffer *rb, + unsigned int idx, + int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); @@ -1200,12 +1200,12 @@ static void packet_free_pending(struct packet_sock *po) #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 -static bool __tpacket_has_room(struct packet_sock *po, int pow_off) +static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; - len = po->rx_ring.frame_max + 1; - idx = po->rx_ring.head; + len = READ_ONCE(po->rx_ring.frame_max) + 1; + idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) @@ -1213,12 +1213,12 @@ static bool __tpacket_has_room(struct packet_sock *po, int pow_off) return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } -static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off) +static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; - len = po->rx_ring.prb_bdqc.knum_blocks; - idx = po->rx_ring.prb_bdqc.kactive_blk_num; + len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); + idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) @@ -1226,15 +1226,18 @@ static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off) return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } -static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) +static int __packet_rcv_has_room(const struct packet_sock *po, + const struct sk_buff *skb) { - struct sock *sk = &po->sk; + const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { - int avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc) - - (skb ? skb->truesize : 0); - if (avail > (sk->sk_rcvbuf >> ROOM_POW_OFF)) + int rcvbuf = READ_ONCE(sk->sk_rcvbuf); + int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) + - (skb ? skb->truesize : 0); + + if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; @@ -1259,19 +1262,24 @@ static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { - int ret; - bool has_room; + int pressure, ret; - spin_lock_bh(&po->sk.sk_receive_queue.lock); ret = __packet_rcv_has_room(po, skb); - has_room = ret == ROOM_NORMAL; - if (po->pressure == has_room) - po->pressure = !has_room; - spin_unlock_bh(&po->sk.sk_receive_queue.lock); + pressure = ret != ROOM_NORMAL; + + if (READ_ONCE(po->pressure) != pressure) + WRITE_ONCE(po->pressure, pressure); return ret; } +static void packet_rcv_try_clear_pressure(struct packet_sock *po) +{ + if (READ_ONCE(po->pressure) && + __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) + WRITE_ONCE(po->pressure, 0); +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -1358,7 +1366,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(f->arr[i]); - if (po_next != po_skip && !po_next->pressure && + if (po_next != po_skip && !READ_ONCE(po_next->pressure) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; @@ -2133,10 +2141,8 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, drop_n_acct: is_drop_n_account = true; - spin_lock(&sk->sk_receive_queue.lock); - po->stats.stats1.tp_drops++; + atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); - spin_unlock(&sk->sk_receive_queue.lock); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -2162,7 +2168,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec ts; __u32 ts_status; @@ -2201,6 +2208,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!res) goto drop_n_restore; + /* If we are flooded, just give up */ + if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && @@ -2225,6 +2238,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && @@ -2285,7 +2302,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ - if (po->stats.stats1.tp_drops) + if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } @@ -2398,9 +2415,9 @@ drop: return 0; drop_n_account: - is_drop_n_account = true; - po->stats.stats1.tp_drops++; spin_unlock(&sk->sk_receive_queue.lock); + atomic_inc(&po->tp_drops); + is_drop_n_account = true; sk->sk_data_ready(sk); kfree_skb(copy_skb); @@ -3344,8 +3361,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb == NULL) goto out; - if (pkt_sk(sk)->pressure) - packet_rcv_has_room(pkt_sk(sk), NULL); + packet_rcv_try_clear_pressure(pkt_sk(sk)); if (pkt_sk(sk)->has_vnet_hdr) { err = packet_rcv_vnet(msg, skb, &len); @@ -3917,6 +3933,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; + int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3933,14 +3950,17 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); + drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); - st.stats3.tp_packets += st.stats3.tp_drops; + st.stats3.tp_drops = drops; + st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); - st.stats1.tp_packets += st.stats1.tp_drops; + st.stats1.tp_drops = drops; + st.stats1.tp_packets += drops; data = &st.stats1; } @@ -4159,8 +4179,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } - if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) - po->pressure = 0; + packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { diff --git a/net/packet/internal.h b/net/packet/internal.h index f10294800aaf..907f4cd2a718 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -135,6 +135,7 @@ struct packet_sock { struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); struct packet_type prot_hook ____cacheline_aligned_in_smp; + atomic_t tp_drops ____cacheline_aligned_in_smp; }; static struct packet_sock *pkt_sk(struct sock *sk) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 14c101e104ce..1ce1e710d025 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1004,6 +1004,7 @@ static int qrtr_release(struct socket *sock) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); sock->sk = NULL; if (!sock_flag(sk, SOCK_ZAPPED)) diff --git a/net/rds/recv.c b/net/rds/recv.c index a42ba7fa06d5..dd15f93d2ef1 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 2b8a5cb93c26..7d8574f6b2da 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call, rxrpc_call_new_service, + trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, atomic_read(&call->usage), here, (const void *)user_call_ID); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f596139a822a..d7f5db7b74fb 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -239,7 +239,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, + atomic_read(&call->usage), here, (const void *)p->user_call_ID); /* We need to protect a partially set up call against the user as we @@ -287,10 +288,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_connected, + atomic_read(&call->usage), here, NULL); rxrpc_start_call_timer(call); @@ -307,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); + RX_CALL_DEAD, -EEXIST); + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* @@ -375,7 +387,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call) if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -390,7 +403,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call) int n = atomic_read(&call->usage); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -405,7 +419,8 @@ void rxrpc_see_call(struct rxrpc_call *call) if (call) { int n = atomic_read(&call->usage); - trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, + here, NULL); } } @@ -417,7 +432,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n, here, NULL); } /* @@ -432,7 +447,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_release, + atomic_read(&call->usage), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -525,12 +541,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); + unsigned int debug_id = call->debug_id; int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(debug_id, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 5ff9d5e12bfe..d76868acfa1a 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index efce27802a74..e011594adcd1 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -500,11 +500,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer); * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer smoothed RTT. + * Get the call's peer smoothed RTT in uS. */ -u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->srtt_us >> 3; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 9a7e1bc9791d..ba5d9c2885b0 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -449,7 +449,7 @@ try_again: list_empty(&rx->recvmsg_q) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); - return -ENODATA; + return -EAGAIN; } if (list_empty(&rx->recvmsg_q)) { @@ -526,7 +526,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 8b97108ca6df..732c7ae56afd 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -306,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_shutdown & SEND_SHUTDOWN) return -EPIPE; more = msg->msg_flags & MSG_MORE; @@ -682,6 +682,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b43cacf82af..1a8f2f85ea1a 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index d3cfad88dc3a..428b1ae00123 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6a8d3337c577..f98b2791ecec 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d2b836771e96..2b94d6f02dbb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1727,7 +1727,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 295401c6f73e..5e112f9e6078 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -289,7 +289,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index ff9c9b711a74..8de4968177bd 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index f4f9b8cdbffb..6385995dc700 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); + p->link.vcc = NULL; + p->link.sock = NULL; + p->link.common.classid = sch->handle; + p->link.ref = 1; err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, extack); if (err) return err; - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 5d605bab9afc..896c0562cb42 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static void cake_update_flowkeys(struct flow_keys *keys, struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1521,7 +1521,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..2b88710994d7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..2f1f0a378408 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c1a100d2fed3..e13cbd5c0193 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,17 +22,11 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> -/* Migrates chunks from stream queues to new stream queues if needed, - * but not across associations. Also, removes those chunks to streams - * higher than the new max. - */ -static void sctp_stream_outq_migrate(struct sctp_stream *stream, - struct sctp_stream *new, __u16 outcnt) +static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; struct sctp_chunk *ch, *temp; struct sctp_outq *outq; - int i; asoc = container_of(stream, struct sctp_association, stream); outq = &asoc->outqueue; @@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, sctp_chunk_free(ch); } +} + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + int i; + + if (stream->outcnt > outcnt) + sctp_stream_shrink_out(stream, outcnt); if (new) { /* Here we actually move the old ext stuff into the new @@ -1038,11 +1045,13 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = ntohs(addstrm->number_of_streams); number = stream->outcnt - nums; - if (result == SCTP_STRRESET_PERFORMED) + if (result == SCTP_STRRESET_PERFORMED) { for (i = number; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - else + } else { + sctp_stream_shrink_out(stream, number); stream->outcnt = number; + } *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, 0, nums, GFP_ATOMIC); diff --git a/net/socket.c b/net/socket.c index fd8679682dfb..81ee3118dfa1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -496,7 +496,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) if (f.file) { sock = sock_from_file(f.file, err); if (likely(sock)) { - *fput_needed = f.flags; + *fput_needed = f.flags & FDPUT_FPUT; return sock; } fdput(f); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index cf0fd170ac18..90b8329fef82 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -584,7 +584,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - (GSS_KRB5_TOK_HDR_LEN + headskip); /* Trim off the trailing "extra count" and checksum blob */ xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 0f95372bffe2..0bd2df7f2503 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -949,7 +949,6 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to * move it around. */ diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index c9bacb3c930f..82035fa65b8f 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -56,4 +56,5 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr, int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); +void auth_domain_cleanup(void); #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index f9edaa9174a4..236fadc4a439 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -23,6 +23,7 @@ #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/xprtsock.h> +#include "sunrpc.h" #include "netns.h" unsigned int sunrpc_net_id; @@ -131,6 +132,7 @@ cleanup_sunrpc(void) unregister_rpc_pipefs(); rpc_destroy_mempool(); unregister_pernet_subsys(&sunrpc_net_ops); + auth_domain_cleanup(); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_unregister_sysctl(); #endif diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index e15cb704453e..f843d27452c9 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1635,6 +1635,22 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) EXPORT_SYMBOL_GPL(svc_max_payload); /** + * svc_encode_read_payload - mark a range of bytes as a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in rqstp->rq_res + * @length: size of payload, in bytes + * + * Returns zero on success, or a negative errno if a permanent + * error occurred. + */ +int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length); +} +EXPORT_SYMBOL_GPL(svc_encode_read_payload); + +/** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on * @pages: list of pages containing data payload diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 550b214cb001..998b196b6176 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -19,6 +19,10 @@ #include <linux/err.h> #include <linux/hash.h> +#include <trace/events/sunrpc.h> + +#include "sunrpc.h" + #define RPCDBG_FACILITY RPCDBG_AUTH @@ -203,3 +207,26 @@ struct auth_domain *auth_domain_find(char *name) return NULL; } EXPORT_SYMBOL_GPL(auth_domain_find); + +/** + * auth_domain_cleanup - check that the auth_domain table is empty + * + * On module unload the auth_domain_table must be empty. To make it + * easier to catch bugs which don't clean up domains properly, we + * warn if anything remains in the table at cleanup time. + * + * Note that we cannot proactively remove the domains at this stage. + * The ->release() function might be in a module that has already been + * unloaded. + */ + +void auth_domain_cleanup(void) +{ + int h; + struct auth_domain *hp; + + for (h = 0; h < DN_HASHMAX; h++) + hlist_for_each_entry(hp, &auth_domain_table[h], hash) + pr_warn("svc: domain %s still present at module unload.\n", + hp->name); +} diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 4260924ad9db..d52abde51f1b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -279,6 +279,12 @@ out: return len; } +static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return 0; +} + /* * Report socket names for nfsdfs */ @@ -655,6 +661,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_create = svc_udp_create, .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_udp_skb, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, @@ -1175,6 +1182,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_skb, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index ff76926b3d67..77a911d14015 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Read list size */ - size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); + size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ @@ -96,7 +96,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Write list size */ - size = sizeof(__be32); /* segment count */ + size += sizeof(__be32); /* segment count */ size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index b5b77c7ecee7..6566620912d6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -193,6 +193,7 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma) out: ctxt->rc_page_count = 0; + ctxt->rc_read_payload_length = 0; return ctxt; out_empty: diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 7d4faf309601..04ec2a83af69 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -480,18 +480,19 @@ static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info, vec->iov_len); } -/* Send an xdr_buf's page list by itself. A Write chunk is - * just the page list. a Reply chunk is the head, page list, - * and tail. This function is shared between the two types - * of chunk. +/* Send an xdr_buf's page list by itself. A Write chunk is just + * the page list. A Reply chunk is @xdr's head, page list, and + * tail. This function is shared between the two types of chunk. */ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, + unsigned long length) { info->wi_xdr = xdr; - info->wi_next_off = 0; + info->wi_next_off = offset - xdr->head[0].iov_len; return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg, - xdr->page_len); + length); } /** @@ -499,6 +500,8 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * @rdma: controlling RDMA transport * @wr_ch: Write chunk provided by client * @xdr: xdr_buf containing the data payload + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Write chunk, @@ -508,19 +511,20 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * %-EIO if rdma_rw initialization failed (DMA mapping, etc). */ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, unsigned long length) { struct svc_rdma_write_info *info; int ret; - if (!xdr->page_len) + if (!length) return 0; info = svc_rdma_write_info_alloc(rdma, wr_ch); if (!info) return -ENOMEM; - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length); if (ret < 0) goto out_err; @@ -529,7 +533,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, goto out_err; trace_svcrdma_encode_write(xdr->page_len); - return xdr->page_len; + return length; out_err: svc_rdma_write_info_free(info); @@ -569,7 +573,9 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch, * client did not provide Write chunks. */ if (!writelist && xdr->page_len) { - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, + xdr->head[0].iov_len, + xdr->page_len); if (ret < 0) goto out_err; consumed += xdr->page_len; @@ -670,7 +676,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_read_info *info, __be32 *p) { - unsigned int i; int ret; ret = -EINVAL; @@ -693,12 +698,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, info->ri_chunklen += rs_length; } - /* Pages under I/O have been copied to head->rc_pages. - * Prevent their premature release by svc_xprt_release() . - */ - for (i = 0; i < info->ri_readctxt->rc_page_count; i++) - rqstp->rq_pages[i] = NULL; - return ret; } @@ -793,6 +792,26 @@ out: return ret; } +/* Pages under I/O have been copied to head->rc_pages. Ensure they + * are not released by svc_xprt_release() until the I/O is complete. + * + * This has to be done after all Read WRs are constructed to properly + * handle a page that is part of I/O on behalf of two different RDMA + * segments. + * + * Do this only if I/O has been posted. Otherwise, we do indeed want + * svc_xprt_release() to clean things up properly. + */ +static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, + const unsigned int start, + const unsigned int num_pages) +{ + unsigned int i; + + for (i = start; i < num_pages + start; i++) + rqstp->rq_pages[i] = NULL; +} + /** * svc_rdma_recv_read_chunk - Pull a Read chunk from the client * @rdma: controlling RDMA transport @@ -846,6 +865,7 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); if (ret < 0) goto out_err; + svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count); return 0; out_err: diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 93ff7967389a..217106c66a13 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -856,7 +856,18 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) if (wr_lst) { /* XXX: Presume the client sent only one Write chunk */ - ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr); + unsigned long offset; + unsigned int length; + + if (rctxt->rc_read_payload_length) { + offset = rctxt->rc_read_payload_offset; + length = rctxt->rc_read_payload_length; + } else { + offset = xdr->head[0].iov_len; + length = xdr->page_len; + } + ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset, + length); if (ret < 0) goto err2; svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret); @@ -891,3 +902,30 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) set_bit(XPT_CLOSE, &xprt->xpt_flags); return -ENOTCONN; } + +/** + * svc_rdma_read_payload - special processing for a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes + * + * Returns zero on success. + * + * For the moment, just record the xdr_buf location of the READ + * payload. svc_rdma_sendto will use that location later when + * we actually send the payload. + */ +int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt; + + /* XXX: Just one READ payload slot for now, since our + * transport implementation currently supports only one + * Write chunk. + */ + rctxt->rc_read_payload_offset = offset; + rctxt->rc_read_payload_length = length; + + return 0; +} diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index fb96283745d1..acb7c558e4fd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -81,6 +81,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_create = svc_rdma_create, .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, + .xpo_read_payload = svc_rdma_read_payload, .xpo_release_rqst = svc_rdma_release_rqst, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 2bed6589f41e..17ed11af2a13 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -138,10 +138,7 @@ 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/tls/tls_device.c b/net/tls/tls_device.c index 3b850a02ca00..3b0c363e7f83 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -477,7 +477,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; - char *kaddr = kmap(page); + char *kaddr; struct kvec iov; int rc; @@ -492,6 +492,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, goto out; } + kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 79e3e1f8a62c..f4f2d3e23a54 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12760,13 +12760,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index e51eb060244e..2e89eb2c2688 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -30,6 +30,8 @@ #define BPF_M_MAP 1 #define BPF_M_PROG 2 +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + static void usage(void) { printf("Usage: fds_example [...]\n"); @@ -57,7 +59,6 @@ static int bpf_prog_create(const char *object) BPF_EXIT_INSN(), }; size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn); - char bpf_log_buf[BPF_LOG_BUF_SIZE]; struct bpf_object *obj; int prog_fd; diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh index c812872d7f9d..65a9b9e5b8a6 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 f277e116e0eb..119d8dddd602 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -382,9 +382,10 @@ failed: * spaces in the beginning of the line is trimmed away. * Return a pointer to a static buffer. **/ +#define MODPOST_MAX_LINE 32768 char *get_next_line(unsigned long *pos, void *file, unsigned long size) { - static char line[4096]; + static char line[MODPOST_MAX_LINE]; int skip = 1; size_t len = 0; signed char *p = (signed char *)file + *pos; @@ -399,8 +400,11 @@ char *get_next_line(unsigned long *pos, void *file, unsigned long size) if (*p != '\n' && (*pos < size)) { len++; *s++ = *p++; - if (len > 4095) + if (len > (sizeof(line)-1)) { + warn(" %s: line exceeds buffer size %zu bytes\n" + , __func__, sizeof(line)); break; /* Too long, stop */ + } } else { /* End of string */ *s = '\0'; @@ -1944,7 +1948,7 @@ static void read_symbols(const char *modname) char *version; char *license; struct module *mod; - struct elf_info info = { }; + struct elf_info info = { .hdr = NULL }; Elf_Sym *sym; if (!parse_elf(&info, modname)) @@ -2393,7 +2397,7 @@ 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; int n; @@ -2420,7 +2424,7 @@ struct ext_sym_list { int main(int argc, char **argv) { struct module *mod; - struct buffer buf = { }; + struct buffer buf = { NULL, 0, 0 }; char *kernel_read = NULL, *module_read = NULL; char *dump_write = NULL, *files_source = NULL; int opt; diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 9660dc632b54..5f58c8e7cb59 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -43,6 +43,8 @@ #define R_ARM_THM_CALL 10 #define R_ARM_CALL 28 +#define R_AARCH64_CALL26 283 + static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ @@ -430,6 +432,11 @@ static int arm_is_fake_mcount(Elf32_Rel const *rp) return 1; } +static int arm64_is_fake_mcount(Elf64_Rel const *rp) +{ + return ELF64_R_TYPE(w(rp->r_info)) != R_AARCH64_CALL26; +} + /* 64-bit EM_MIPS has weird ELF64_Rela.r_info. * http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf * We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40] @@ -538,6 +545,7 @@ do_file(char const *const fname) make_nop = make_nop_arm64; rel_type_nop = R_AARCH64_NONE; ideal_nop = ideal_nop4_arm64; + is_fake_mcount64 = arm64_is_fake_mcount; gpfx = '_'; break; case EM_IA_64: reltype = R_IA64_IMM64; gpfx = '_'; break; diff --git a/security/apparmor/match.c b/security/apparmor/match.c index 6ccd3734a841..43669403f755 100644 --- a/security/apparmor/match.c +++ b/security/apparmor/match.c @@ -97,6 +97,9 @@ static struct table_header *unpack_table(char *blob, size_t bsize) th.td_flags == YYTD_DATA8)) goto out; + /* if we have a table it must have some entries */ + if (th.td_lolen == 0) + goto out; tsize = table_size(th.td_lolen, th.td_flags); if (bsize < tsize) goto out; @@ -198,6 +201,8 @@ static int verify_dfa(struct aa_dfa *dfa) state_count = dfa->tables[YYTD_ID_BASE]->td_lolen; trans_count = dfa->tables[YYTD_ID_NXT]->td_lolen; + if (state_count == 0) + goto out; for (i = 0; i < state_count; i++) { if (!(BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE) && (DEFAULT_TABLE(dfa)[i] >= state_count)) diff --git a/security/device_cgroup.c b/security/device_cgroup.c index dc28914fa72e..c2ddfea2b280 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -824,3 +824,4 @@ int __devcgroup_check_permission(short type, u32 major, u32 minor, return 0; } +EXPORT_SYMBOL_GPL(__devcgroup_check_permission); diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 2692c7358c2c..3ae199689d17 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -226,7 +226,7 @@ config IMA_APPRAISE_REQUIRE_POLICY_SIGS config IMA_APPRAISE_BOOTPARAM bool "ima_appraise boot parameter" - depends on IMA_APPRAISE && !IMA_ARCH_POLICY + depends on IMA_APPRAISE default y help This option enables the different "ima_appraise=" modes diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index f0cd67cab6aa..9e2a3993a922 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -18,6 +18,12 @@ static int __init default_appraise_setup(char *str) { #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM + if (arch_ima_get_secureboot()) { + pr_info("Secure boot enabled: ignoring ima_appraise=%s boot parameter option", + str); + return 1; + } + if (strncmp(str, "off", 3) == 0) ima_appraise = 0; else if (strncmp(str, "log", 3) == 0) diff --git a/security/security.c b/security/security.c index f493db0bf62a..96f118be469f 100644 --- a/security/security.c +++ b/security/security.c @@ -993,6 +993,7 @@ 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) { @@ -1009,6 +1010,7 @@ 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) @@ -1017,6 +1019,7 @@ 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, @@ -1044,6 +1047,7 @@ 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) { @@ -1051,6 +1055,7 @@ 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) { @@ -1058,6 +1063,7 @@ 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) { @@ -1158,6 +1164,7 @@ 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) { @@ -1335,6 +1342,7 @@ 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/security/smack/smackfs.c b/security/smack/smackfs.c index 20de7f1f1f41..8c000344b7ec 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -883,7 +883,7 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, } ret = sscanf(rule, "%d", &maplevel); - if (ret != 1 || maplevel > SMACK_CIPSO_MAXLEVEL) + if (ret != 1 || maplevel < 0 || maplevel > SMACK_CIPSO_MAXLEVEL) goto out; rule += SMK_DIGITLEN; @@ -904,6 +904,10 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, for (i = 0; i < catlen; i++) { rule += SMK_DIGITLEN; + if (rule > data + count) { + rc = -EOVERFLOW; + goto out; + } ret = sscanf(rule, "%u", &cat); if (ret != 1 || cat > SMACK_CIPSO_MAXCATNUM) goto out; @@ -2719,7 +2723,6 @@ static int smk_open_relabel_self(struct inode *inode, struct file *file) static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct task_smack *tsp = smack_cred(current_cred()); char *data; int rc; LIST_HEAD(list_tmp); @@ -2744,11 +2747,21 @@ static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf, kfree(data); if (!rc || (rc == -EINVAL && list_empty(&list_tmp))) { + struct cred *new; + struct task_smack *tsp; + + new = prepare_creds(); + if (!new) { + rc = -ENOMEM; + goto out; + } + tsp = smack_cred(new); smk_destroy_label_list(&tsp->smk_relabel); list_splice(&list_tmp, &tsp->smk_relabel); + commit_creds(new); return count; } - +out: smk_destroy_label_list(&list_tmp); return rc; } diff --git a/sound/core/info.c b/sound/core/info.c index e051a029ccfb..f18f4ef6661e 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -608,7 +608,9 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) { int c = -1; - if (snd_BUG_ON(!buffer || !buffer->buffer)) + if (snd_BUG_ON(!buffer)) + return 1; + if (!buffer->buffer) return 1; if (len <= 0 || buffer->stop || buffer->error) return 1; diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index 17f913657304..c8b9c0b315d8 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -168,10 +168,16 @@ static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seq_oss_devinfo *dp; + long rc; + dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; - return snd_seq_oss_ioctl(dp, cmd, arg); + + mutex_lock(®ister_mutex); + rc = snd_seq_oss_ioctl(dp, cmd, arg); + mutex_unlock(®ister_mutex); + return rc; } #ifdef CONFIG_COMPAT diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index b612a536a5a1..0e15d497946a 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -2199,7 +2199,6 @@ static int snd_echo_resume(struct device *dev) if (err < 0) { kfree(commpage_bak); dev_err(dev, "resume init_hw err=%d\n", err); - snd_echo_free(chip); return err; } @@ -2226,7 +2225,6 @@ static int snd_echo_resume(struct device *dev) if (request_irq(pci->irq, snd_echo_interrupt, IRQF_SHARED, KBUILD_MODNAME, chip)) { dev_err(chip->card->dev, "cannot grab irq\n"); - snd_echo_free(chip); return -EBUSY; } chip->irq = pci->irq; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 71228bbcb580..0922a8bb32d0 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2924,6 +2924,10 @@ static int hda_codec_runtime_suspend(struct device *dev) struct hda_codec *codec = dev_to_hda_codec(dev); unsigned int state; + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + cancel_delayed_work_sync(&codec->jackpoll_work); state = hda_call_codec_suspend(codec); if (codec->link_down_at_suspend || @@ -2938,6 +2942,10 @@ static int hda_codec_runtime_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + codec_display_power(codec, true); snd_hdac_codec_link_up(&codec->core); hda_call_codec_resume(codec); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e3693371fe19..011f8e958743 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2332,7 +2332,6 @@ static int azx_probe_continue(struct azx *chip) if (azx_has_pm_runtime(chip)) { pm_runtime_use_autosuspend(&pci->dev); - pm_runtime_allow(&pci->dev); pm_runtime_put_autosuspend(&pci->dev); } diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index bc08a9f3dd9a..08bf3c2888a0 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1182,6 +1182,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI), 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), {} }; @@ -4670,7 +4671,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec) tmp = FLOAT_ONE; break; case QUIRK_AE5: - ca0113_mmio_command_set(codec, 0x48, 0x28, 0x00); + ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00); tmp = FLOAT_THREE; break; default: @@ -4716,7 +4717,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec) r3di_gpio_mic_set(codec, R3DI_REAR_MIC); break; case QUIRK_AE5: - ca0113_mmio_command_set(codec, 0x48, 0x28, 0x00); + ca0113_mmio_command_set(codec, 0x30, 0x28, 0x00); break; default: break; @@ -4755,7 +4756,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec) tmp = FLOAT_ONE; break; case QUIRK_AE5: - ca0113_mmio_command_set(codec, 0x48, 0x28, 0x3f); + ca0113_mmio_command_set(codec, 0x30, 0x28, 0x3f); tmp = FLOAT_THREE; break; default: @@ -5747,6 +5748,11 @@ static int ca0132_switch_get(struct snd_kcontrol *kcontrol, return 0; } + if (nid == ZXR_HEADPHONE_GAIN) { + *valp = spec->zxr_gain_set; + return 0; + } + return 0; } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index dd770e968548..499e671bc2cc 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1801,33 +1801,43 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) static int hdmi_parse_codec(struct hda_codec *codec) { - hda_nid_t nid; + hda_nid_t start_nid; + unsigned int caps; int i, nodes; - nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &nid); - if (!nid || nodes < 0) { + nodes = snd_hda_get_sub_nodes(codec, codec->core.afg, &start_nid); + if (!start_nid || nodes < 0) { codec_warn(codec, "HDMI: failed to get afg sub nodes\n"); return -EINVAL; } - for (i = 0; i < nodes; i++, nid++) { - unsigned int caps; - unsigned int type; + /* + * hdmi_add_pin() assumes total amount of converters to + * be known, so first discover all converters + */ + for (i = 0; i < nodes; i++) { + hda_nid_t nid = start_nid + i; caps = get_wcaps(codec, nid); - type = get_wcaps_type(caps); if (!(caps & AC_WCAP_DIGITAL)) continue; - switch (type) { - case AC_WID_AUD_OUT: + if (get_wcaps_type(caps) == AC_WID_AUD_OUT) hdmi_add_cvt(codec, nid); - break; - case AC_WID_PIN: + } + + /* discover audio pins */ + for (i = 0; i < nodes; i++) { + hda_nid_t nid = start_nid + i; + + caps = get_wcaps(codec, nid); + + if (!(caps & AC_WCAP_DIGITAL)) + continue; + + if (get_wcaps_type(caps) == AC_WID_PIN) hdmi_add_pin(codec, nid); - break; - } } return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8a8da01bb6f4..d496ad64a880 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4390,6 +4390,7 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec, { struct alc_spec *spec = codec->spec; + spec->micmute_led_polarity = 1; alc_fixup_hp_gpio_led(codec, action, 0, 0x04); if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->init_amp = ALC_INIT_DEFAULT; @@ -5847,6 +5848,39 @@ static void alc275_fixup_gpio4_off(struct hda_codec *codec, } } +/* Quirk for Thinkpad X1 7th and 8th Gen + * The following fixed routing needed + * DAC1 (NID 0x02) -> Speaker (NID 0x14); some eq applied secretly + * DAC2 (NID 0x03) -> Bass (NID 0x17) & Headphone (NID 0x21); sharing a DAC + * DAC3 (NID 0x06) -> Unused, due to the lack of volume amp + */ +static void alc285_fixup_thinkpad_x1_gen7(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const hda_nid_t conn[] = { 0x02, 0x03 }; /* exclude 0x06 */ + static const hda_nid_t preferred_pairs[] = { + 0x14, 0x02, 0x17, 0x03, 0x21, 0x03, 0 + }; + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); + spec->gen.preferred_dacs = preferred_pairs; + break; + case HDA_FIXUP_ACT_BUILD: + /* The generic parser creates somewhat unintuitive volume ctls + * with the fixed routing above, and the shared DAC2 may be + * confusing for PA. + * Rename those to unique names so that PA doesn't touch them + * and use only Master volume. + */ + rename_ctl(codec, "Front Playback Volume", "DAC1 Playback Volume"); + rename_ctl(codec, "Bass Speaker Playback Volume", "DAC2 Playback Volume"); + break; + } +} + static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5939,6 +5973,16 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec, snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); } +static void alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_INIT) + return; + + msleep(100); + alc_write_coef_idx(codec, 0x65, 0x0); +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6103,6 +6147,7 @@ enum { ALC289_FIXUP_DUAL_SPK, ALC294_FIXUP_SPK2_TO_DAC1, ALC294_FIXUP_ASUS_DUAL_SPK, + ALC285_FIXUP_THINKPAD_X1_GEN7, ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, ALC294_FIXUP_ASUS_COEF_1B, @@ -6114,6 +6159,15 @@ enum { ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS, ALC269VC_FIXUP_ACER_HEADSET_MIC, ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE, + ALC289_FIXUP_ASUS_GA401, + ALC289_FIXUP_ASUS_GA502, + ALC256_FIXUP_ACER_MIC_NO_PRESENCE, + ALC285_FIXUP_HP_GPIO_AMP_INIT, + ALC269_FIXUP_CZC_B20, + ALC269_FIXUP_CZC_TMI, + ALC269_FIXUP_CZC_L101, + ALC269_FIXUP_LEMOTE_A1802, + ALC269_FIXUP_LEMOTE_A190X, }; static const struct hda_fixup alc269_fixups[] = { @@ -7063,7 +7117,7 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, - .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + .chain_id = ALC269_FIXUP_HEADSET_MIC }, [ALC294_FIXUP_ASUS_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, @@ -7072,7 +7126,7 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, - .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + .chain_id = ALC269_FIXUP_HEADSET_MIC }, [ALC294_FIXUP_ASUS_SPK] = { .type = HDA_FIXUP_VERBS, @@ -7080,6 +7134,8 @@ static const struct hda_fixup alc269_fixups[] = { /* Set EAPD high */ { 0x20, AC_VERB_SET_COEF_INDEX, 0x40 }, { 0x20, AC_VERB_SET_PROC_COEF, 0x8800 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x7774 }, { } }, .chained = true, @@ -7220,11 +7276,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, + [ALC285_FIXUP_THINKPAD_X1_GEN7] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_thinkpad_x1_gen7, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI + }, [ALC285_FIXUP_THINKPAD_HEADSET_JACK] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_jack, .chained = true, - .chain_id = ALC285_FIXUP_SPEAKER2_TO_DAC1 + .chain_id = ALC285_FIXUP_THINKPAD_X1_GEN7 }, [ALC294_FIXUP_ASUS_HPE] = { .type = HDA_FIXUP_VERBS, @@ -7305,6 +7367,118 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, + [ALC289_FIXUP_ASUS_GA401] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11020 }, /* headset mic with jack detect */ + { } + }, + }, + [ALC289_FIXUP_ASUS_GA502] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11020 }, /* headset mic with jack detect */ + { } + }, + }, + [ALC256_FIXUP_ACER_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x02a11120 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE + }, + [ALC285_FIXUP_HP_GPIO_AMP_INIT] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_gpio_amp_init, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED + }, + [ALC269_FIXUP_CZC_B20] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x12, 0x411111f0 }, + { 0x14, 0x90170110 }, /* speaker */ + { 0x15, 0x032f1020 }, /* HP out */ + { 0x17, 0x411111f0 }, + { 0x18, 0x03ab1040 }, /* mic */ + { 0x19, 0xb7a7013f }, + { 0x1a, 0x0181305f }, + { 0x1b, 0x411111f0 }, + { 0x1d, 0x411111f0 }, + { 0x1e, 0x411111f0 }, + { } + }, + .chain_id = ALC269_FIXUP_DMIC, + }, + [ALC269_FIXUP_CZC_TMI] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x12, 0x4000c000 }, + { 0x14, 0x90170110 }, /* speaker */ + { 0x15, 0x0421401f }, /* HP out */ + { 0x17, 0x411111f0 }, + { 0x18, 0x04a19020 }, /* mic */ + { 0x19, 0x411111f0 }, + { 0x1a, 0x411111f0 }, + { 0x1b, 0x411111f0 }, + { 0x1d, 0x40448505 }, + { 0x1e, 0x411111f0 }, + { 0x20, 0x8000ffff }, + { } + }, + .chain_id = ALC269_FIXUP_DMIC, + }, + [ALC269_FIXUP_CZC_L101] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x12, 0x40000000 }, + { 0x14, 0x01014010 }, /* speaker */ + { 0x15, 0x411111f0 }, /* HP out */ + { 0x16, 0x411111f0 }, + { 0x18, 0x01a19020 }, /* mic */ + { 0x19, 0x02a19021 }, + { 0x1a, 0x0181302f }, + { 0x1b, 0x0221401f }, + { 0x1c, 0x411111f0 }, + { 0x1d, 0x4044c601 }, + { 0x1e, 0x411111f0 }, + { } + }, + .chain_id = ALC269_FIXUP_DMIC, + }, + [ALC269_FIXUP_LEMOTE_A1802] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x12, 0x40000000 }, + { 0x14, 0x90170110 }, /* speaker */ + { 0x17, 0x411111f0 }, + { 0x18, 0x03a19040 }, /* mic1 */ + { 0x19, 0x90a70130 }, /* mic2 */ + { 0x1a, 0x411111f0 }, + { 0x1b, 0x411111f0 }, + { 0x1d, 0x40489d2d }, + { 0x1e, 0x411111f0 }, + { 0x20, 0x0003ffff }, + { 0x21, 0x03214020 }, + { } + }, + .chain_id = ALC269_FIXUP_DMIC, + }, + [ALC269_FIXUP_LEMOTE_A190X] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x99130110 }, /* speaker */ + { 0x15, 0x0121401f }, /* HP out */ + { 0x18, 0x01a19c20 }, /* rear mic */ + { 0x19, 0x99a3092f }, /* front mic */ + { 0x1b, 0x0201401f }, /* front lineout */ + { } + }, + .chain_id = ALC269_FIXUP_DMIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7333,6 +7507,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X), @@ -7454,7 +7629,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), 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_LED), + SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), 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), @@ -7476,6 +7651,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), @@ -7485,6 +7661,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), + SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -7504,11 +7682,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), + SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), + SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), @@ -7588,9 +7768,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), + SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), + SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI), + SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101), SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), + SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), + SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), #if 0 /* Below is a quirk table taken from the old code. @@ -8830,6 +9015,7 @@ enum { ALC662_FIXUP_LED_GPIO1, ALC662_FIXUP_IDEAPAD, ALC272_FIXUP_MARIO, + ALC662_FIXUP_CZC_ET26, ALC662_FIXUP_CZC_P10T, ALC662_FIXUP_SKU_IGNORE, ALC662_FIXUP_HP_RP5800, @@ -8897,6 +9083,25 @@ static const struct hda_fixup alc662_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc272_fixup_mario, }, + [ALC662_FIXUP_CZC_ET26] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + {0x12, 0x403cc000}, + {0x14, 0x90170110}, /* speaker */ + {0x15, 0x411111f0}, + {0x16, 0x411111f0}, + {0x18, 0x01a19030}, /* mic */ + {0x19, 0x90a7013f}, /* int-mic */ + {0x1a, 0x01014020}, + {0x1b, 0x0121401f}, + {0x1c, 0x411111f0}, + {0x1d, 0x411111f0}, + {0x1e, 0x40478e35}, + {} + }, + .chained = true, + .chain_id = ALC662_FIXUP_SKU_IGNORE + }, [ALC662_FIXUP_CZC_P10T] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9265,6 +9470,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO), SND_PCI_QUIRK(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68), SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON), + SND_PCI_QUIRK(0x1b35, 0x1234, "CZC ET26", ALC662_FIXUP_CZC_ET26), SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T), #if 0 diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c index 70fee6849ab0..f21181734170 100644 --- a/sound/soc/codecs/rt5670.c +++ b/sound/soc/codecs/rt5670.c @@ -31,18 +31,19 @@ #include "rt5670.h" #include "rt5670-dsp.h" -#define RT5670_DEV_GPIO BIT(0) -#define RT5670_IN2_DIFF BIT(1) -#define RT5670_DMIC_EN BIT(2) -#define RT5670_DMIC1_IN2P BIT(3) -#define RT5670_DMIC1_GPIO6 BIT(4) -#define RT5670_DMIC1_GPIO7 BIT(5) -#define RT5670_DMIC2_INR BIT(6) -#define RT5670_DMIC2_GPIO8 BIT(7) -#define RT5670_DMIC3_GPIO5 BIT(8) -#define RT5670_JD_MODE1 BIT(9) -#define RT5670_JD_MODE2 BIT(10) -#define RT5670_JD_MODE3 BIT(11) +#define RT5670_DEV_GPIO BIT(0) +#define RT5670_IN2_DIFF BIT(1) +#define RT5670_DMIC_EN BIT(2) +#define RT5670_DMIC1_IN2P BIT(3) +#define RT5670_DMIC1_GPIO6 BIT(4) +#define RT5670_DMIC1_GPIO7 BIT(5) +#define RT5670_DMIC2_INR BIT(6) +#define RT5670_DMIC2_GPIO8 BIT(7) +#define RT5670_DMIC3_GPIO5 BIT(8) +#define RT5670_JD_MODE1 BIT(9) +#define RT5670_JD_MODE2 BIT(10) +#define RT5670_JD_MODE3 BIT(11) +#define RT5670_GPIO1_IS_EXT_SPK_EN BIT(12) static unsigned long rt5670_quirk; static unsigned int quirk_override; @@ -1447,6 +1448,33 @@ static int rt5670_hp_event(struct snd_soc_dapm_widget *w, return 0; } +static int rt5670_spk_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component); + + if (!rt5670->pdata.gpio1_is_ext_spk_en) + return 0; + + switch (event) { + case SND_SOC_DAPM_POST_PMU: + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_HI); + break; + + case SND_SOC_DAPM_PRE_PMD: + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_LO); + break; + + default: + return 0; + } + + return 0; +} + static int rt5670_bst1_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { @@ -1860,7 +1888,9 @@ static const struct snd_soc_dapm_widget rt5670_specific_dapm_widgets[] = { }; static const struct snd_soc_dapm_widget rt5672_specific_dapm_widgets[] = { - SND_SOC_DAPM_PGA("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_PGA_E("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0, + rt5670_spk_event, SND_SOC_DAPM_PRE_PMD | + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_OUTPUT("SPOLP"), SND_SOC_DAPM_OUTPUT("SPOLN"), SND_SOC_DAPM_OUTPUT("SPORP"), @@ -2857,14 +2887,14 @@ static const struct dmi_system_id dmi_platform_intel_quirks[] = { }, { .callback = rt5670_quirk_cb, - .ident = "Lenovo Thinkpad Tablet 10", + .ident = "Lenovo Miix 2 10", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Miix 2 10"), }, .driver_data = (unsigned long *)(RT5670_DMIC_EN | RT5670_DMIC1_IN2P | - RT5670_DEV_GPIO | + RT5670_GPIO1_IS_EXT_SPK_EN | RT5670_JD_MODE2), }, { @@ -2924,6 +2954,10 @@ static int rt5670_i2c_probe(struct i2c_client *i2c, rt5670->pdata.dev_gpio = true; dev_info(&i2c->dev, "quirk dev_gpio\n"); } + if (rt5670_quirk & RT5670_GPIO1_IS_EXT_SPK_EN) { + rt5670->pdata.gpio1_is_ext_spk_en = true; + dev_info(&i2c->dev, "quirk GPIO1 is external speaker enable\n"); + } if (rt5670_quirk & RT5670_IN2_DIFF) { rt5670->pdata.in2_diff = true; dev_info(&i2c->dev, "quirk IN2_DIFF\n"); @@ -3023,6 +3057,13 @@ static int rt5670_i2c_probe(struct i2c_client *i2c, RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT); } + if (rt5670->pdata.gpio1_is_ext_spk_en) { + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL1, + RT5670_GP1_PIN_MASK, RT5670_GP1_PIN_GPIO1); + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT); + } + if (rt5670->pdata.jd_mode) { regmap_update_bits(rt5670->regmap, RT5670_GLB_CLK, RT5670_SCLK_SRC_MASK, RT5670_SCLK_SRC_RCCLK); diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h index a8c3e44770b8..de0203369b7c 100644 --- a/sound/soc/codecs/rt5670.h +++ b/sound/soc/codecs/rt5670.h @@ -757,7 +757,7 @@ #define RT5670_PWR_VREF2_BIT 4 #define RT5670_PWR_FV2 (0x1 << 3) #define RT5670_PWR_FV2_BIT 3 -#define RT5670_LDO_SEL_MASK (0x3) +#define RT5670_LDO_SEL_MASK (0x7) #define RT5670_LDO_SEL_SFT 0 /* Power Management for Analog 2 (0x64) */ diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c index 771df36fbbaf..82d4fdacfcf7 100644 --- a/sound/soc/intel/boards/bxt_rt298.c +++ b/sound/soc/intel/boards/bxt_rt298.c @@ -537,6 +537,7 @@ static int bxt_card_late_probe(struct snd_soc_card *card) /* broxton audio machine driver for SPT + RT298S */ static struct snd_soc_card broxton_rt298 = { .name = "broxton-rt298", + .owner = THIS_MODULE, .dai_link = broxton_rt298_dais, .num_links = ARRAY_SIZE(broxton_rt298_dais), .controls = broxton_controls, @@ -552,6 +553,7 @@ static struct snd_soc_card broxton_rt298 = { static struct snd_soc_card geminilake_rt298 = { .name = "geminilake-rt298", + .owner = THIS_MODULE, .dai_link = broxton_rt298_dais, .num_links = ARRAY_SIZE(broxton_rt298_dais), .controls = broxton_controls, diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 4602c4f41c16..1d2fe84bd3d7 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -547,8 +547,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) if (cnt) { ret = device_add_properties(codec_dev, props); - if (ret) + if (ret) { + put_device(codec_dev); return ret; + } } devm_acpi_dev_add_driver_gpios(codec_dev, byt_cht_es8316_gpios); diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c index 0c6cce5c5773..9bcaf4b8b57e 100644 --- a/sound/soc/meson/axg-tdm-formatter.c +++ b/sound/soc/meson/axg-tdm-formatter.c @@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks); static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter) { struct axg_tdm_stream *ts = formatter->stream; - bool invert = formatter->drv->quirks->invert_sclk; + bool invert; int ret; /* Do nothing if the formatter is already enabled */ @@ -76,11 +76,12 @@ static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter) return 0; /* - * If sclk is inverted, invert it back and provide the inversion - * required by the formatter + * If sclk is inverted, it means the bit should latched on the + * rising edge which is what our HW expects. If not, we need to + * invert it before the formatter. */ - invert ^= axg_tdm_sclk_invert(ts->iface->fmt); - ret = clk_set_phase(formatter->sclk, invert ? 180 : 0); + invert = axg_tdm_sclk_invert(ts->iface->fmt); + ret = clk_set_phase(formatter->sclk, invert ? 0 : 180); if (ret) return ret; diff --git a/sound/soc/meson/axg-tdm-formatter.h b/sound/soc/meson/axg-tdm-formatter.h index 9ef98e955cb2..a1f0dcc0ff13 100644 --- a/sound/soc/meson/axg-tdm-formatter.h +++ b/sound/soc/meson/axg-tdm-formatter.h @@ -16,7 +16,6 @@ struct snd_kcontrol; struct axg_tdm_formatter_hw { unsigned int skew_offset; - bool invert_sclk; }; struct axg_tdm_formatter_ops { diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 585ce030b79b..702595715f94 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -119,18 +119,25 @@ static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai); - /* These modes are not supported */ - if (fmt & (SND_SOC_DAIFMT_CBS_CFM | SND_SOC_DAIFMT_CBM_CFS)) { + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { + case SND_SOC_DAIFMT_CBS_CFS: + if (!iface->mclk) { + dev_err(dai->dev, "cpu clock master: mclk missing\n"); + return -ENODEV; + } + break; + + case SND_SOC_DAIFMT_CBM_CFM: + break; + + case SND_SOC_DAIFMT_CBS_CFM: + case SND_SOC_DAIFMT_CBM_CFS: dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n"); + /* Fall-through */ + default: return -EINVAL; } - /* If the TDM interface is the clock master, it requires mclk */ - if (!iface->mclk && (fmt & SND_SOC_DAIFMT_CBS_CFS)) { - dev_err(dai->dev, "cpu clock master: mclk missing\n"); - return -ENODEV; - } - iface->fmt = fmt; return 0; } @@ -319,7 +326,8 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream, if (ret) return ret; - if (iface->fmt & SND_SOC_DAIFMT_CBS_CFS) { + if ((iface->fmt & SND_SOC_DAIFMT_MASTER_MASK) == + SND_SOC_DAIFMT_CBS_CFS) { ret = axg_tdm_iface_set_sclk(dai, params); if (ret) return ret; diff --git a/sound/soc/meson/axg-tdmin.c b/sound/soc/meson/axg-tdmin.c index a790f925a4ef..396a8201001b 100644 --- a/sound/soc/meson/axg-tdmin.c +++ b/sound/soc/meson/axg-tdmin.c @@ -208,15 +208,29 @@ static const struct axg_tdm_formatter_driver axg_tdmin_drv = { .regmap_cfg = &axg_tdmin_regmap_cfg, .ops = &axg_tdmin_ops, .quirks = &(const struct axg_tdm_formatter_hw) { - .invert_sclk = false, .skew_offset = 2, }, }; +static const struct axg_tdm_formatter_driver g12a_tdmin_drv = { + .component_drv = &axg_tdmin_component_drv, + .regmap_cfg = &axg_tdmin_regmap_cfg, + .ops = &axg_tdmin_ops, + .quirks = &(const struct axg_tdm_formatter_hw) { + .skew_offset = 3, + }, +}; + static const struct of_device_id axg_tdmin_of_match[] = { { .compatible = "amlogic,axg-tdmin", .data = &axg_tdmin_drv, + }, { + .compatible = "amlogic,g12a-tdmin", + .data = &g12a_tdmin_drv, + }, { + .compatible = "amlogic,sm1-tdmin", + .data = &g12a_tdmin_drv, }, {} }; MODULE_DEVICE_TABLE(of, axg_tdmin_of_match); diff --git a/sound/soc/meson/axg-tdmout.c b/sound/soc/meson/axg-tdmout.c index 527bfc4487e0..3ceabddae629 100644 --- a/sound/soc/meson/axg-tdmout.c +++ b/sound/soc/meson/axg-tdmout.c @@ -24,6 +24,7 @@ #define TDMOUT_CTRL1 0x04 #define TDMOUT_CTRL1_TYPE_MASK GENMASK(6, 4) #define TDMOUT_CTRL1_TYPE(x) ((x) << 4) +#define SM1_TDMOUT_CTRL1_GAIN_EN 7 #define TDMOUT_CTRL1_MSB_POS_MASK GENMASK(12, 8) #define TDMOUT_CTRL1_MSB_POS(x) ((x) << 8) #define TDMOUT_CTRL1_SEL_SHIFT 24 @@ -51,25 +52,6 @@ static const struct regmap_config axg_tdmout_regmap_cfg = { .max_register = TDMOUT_MASK_VAL, }; -static const struct snd_kcontrol_new axg_tdmout_controls[] = { - SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0, 0, 8, 255, 0), - SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0), - SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1, 0, 8, 255, 0), - SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0), - SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1, - TDMOUT_CTRL1_GAIN_EN, 1, 0), -}; - -static const char * const tdmout_sel_texts[] = { - "IN 0", "IN 1", "IN 2", -}; - -static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1, - TDMOUT_CTRL1_SEL_SHIFT, tdmout_sel_texts); - -static const struct snd_kcontrol_new axg_tdmout_in_mux = - SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum); - static struct snd_soc_dai * axg_tdmout_get_be(struct snd_soc_dapm_widget *w) { @@ -137,7 +119,6 @@ static int axg_tdmout_prepare(struct regmap *map, break; case SND_SOC_DAIFMT_LEFT_J: - case SND_SOC_DAIFMT_RIGHT_J: case SND_SOC_DAIFMT_DSP_B: skew += 1; break; @@ -198,6 +179,25 @@ static int axg_tdmout_prepare(struct regmap *map, return axg_tdm_formatter_set_channel_masks(map, ts, TDMOUT_MASK0); } +static const struct snd_kcontrol_new axg_tdmout_controls[] = { + SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0, 0, 8, 255, 0), + SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0), + SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1, 0, 8, 255, 0), + SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0), + SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1, + TDMOUT_CTRL1_GAIN_EN, 1, 0), +}; + +static const char * const axg_tdmout_sel_texts[] = { + "IN 0", "IN 1", "IN 2", +}; + +static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1, + TDMOUT_CTRL1_SEL_SHIFT, axg_tdmout_sel_texts); + +static const struct snd_kcontrol_new axg_tdmout_in_mux = + SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum); + static const struct snd_soc_dapm_widget axg_tdmout_dapm_widgets[] = { SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0), @@ -238,7 +238,6 @@ static const struct axg_tdm_formatter_driver axg_tdmout_drv = { .regmap_cfg = &axg_tdmout_regmap_cfg, .ops = &axg_tdmout_ops, .quirks = &(const struct axg_tdm_formatter_hw) { - .invert_sclk = true, .skew_offset = 1, }, }; @@ -248,7 +247,66 @@ static const struct axg_tdm_formatter_driver g12a_tdmout_drv = { .regmap_cfg = &axg_tdmout_regmap_cfg, .ops = &axg_tdmout_ops, .quirks = &(const struct axg_tdm_formatter_hw) { - .invert_sclk = true, + .skew_offset = 2, + }, +}; + +static const struct snd_kcontrol_new sm1_tdmout_controls[] = { + SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0, 0, 8, 255, 0), + SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0), + SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1, 0, 8, 255, 0), + SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0), + SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1, + SM1_TDMOUT_CTRL1_GAIN_EN, 1, 0), +}; + +static const char * const sm1_tdmout_sel_texts[] = { + "IN 0", "IN 1", "IN 2", "IN 3", "IN 4", +}; + +static SOC_ENUM_SINGLE_DECL(sm1_tdmout_sel_enum, TDMOUT_CTRL1, + TDMOUT_CTRL1_SEL_SHIFT, sm1_tdmout_sel_texts); + +static const struct snd_kcontrol_new sm1_tdmout_in_mux = + SOC_DAPM_ENUM("Input Source", sm1_tdmout_sel_enum); + +static const struct snd_soc_dapm_widget sm1_tdmout_dapm_widgets[] = { + SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &sm1_tdmout_in_mux), + SND_SOC_DAPM_PGA_E("ENC", SND_SOC_NOPM, 0, 0, NULL, 0, + axg_tdm_formatter_event, + (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)), + SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0), +}; + +static const struct snd_soc_dapm_route sm1_tdmout_dapm_routes[] = { + { "SRC SEL", "IN 0", "IN 0" }, + { "SRC SEL", "IN 1", "IN 1" }, + { "SRC SEL", "IN 2", "IN 2" }, + { "SRC SEL", "IN 3", "IN 3" }, + { "SRC SEL", "IN 4", "IN 4" }, + { "ENC", NULL, "SRC SEL" }, + { "OUT", NULL, "ENC" }, +}; + +static const struct snd_soc_component_driver sm1_tdmout_component_drv = { + .controls = sm1_tdmout_controls, + .num_controls = ARRAY_SIZE(sm1_tdmout_controls), + .dapm_widgets = sm1_tdmout_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(sm1_tdmout_dapm_widgets), + .dapm_routes = sm1_tdmout_dapm_routes, + .num_dapm_routes = ARRAY_SIZE(sm1_tdmout_dapm_routes), +}; + +static const struct axg_tdm_formatter_driver sm1_tdmout_drv = { + .component_drv = &sm1_tdmout_component_drv, + .regmap_cfg = &axg_tdmout_regmap_cfg, + .ops = &axg_tdmout_ops, + .quirks = &(const struct axg_tdm_formatter_hw) { .skew_offset = 2, }, }; @@ -260,6 +318,9 @@ static const struct of_device_id axg_tdmout_of_match[] = { }, { .compatible = "amlogic,g12a-tdmout", .data = &g12a_tdmout_drv, + }, { + .compatible = "amlogic,sm1-tdmout", + .data = &sm1_tdmout_drv, }, {} }; MODULE_DEVICE_TABLE(of, axg_tdmout_of_match); diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 3570d714ee88..b14bea746875 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1281,17 +1281,29 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, list_add(&routes[i]->dobj.list, &tplg->comp->dobj_list); ret = soc_tplg_add_route(tplg, routes[i]); - if (ret < 0) + if (ret < 0) { + /* + * this route was added to the list, it will + * be freed in remove_route() so increment the + * counter to skip it in the error handling + * below. + */ + i++; break; + } /* add route, but keep going if some fail */ snd_soc_dapm_add_routes(dapm, routes[i], 1); } - /* free memory allocated for all dapm routes in case of error */ - if (ret < 0) - for (i = 0; i < count ; i++) - kfree(routes[i]); + /* + * free memory allocated for all dapm routes not added to the + * list in case of error + */ + if (ret < 0) { + while (i < count) + kfree(routes[i++]); + } /* * free pointer to array of dapm routes as this is no longer needed. diff --git a/sound/soc/sof/nocodec.c b/sound/soc/sof/nocodec.c index dcdb36a46a6c..906cd6bdd54f 100644 --- a/sound/soc/sof/nocodec.c +++ b/sound/soc/sof/nocodec.c @@ -14,6 +14,7 @@ static struct snd_soc_card sof_nocodec_card = { .name = "nocodec", /* the sof- prefix is added by the core */ + .owner = THIS_MODULE }; static int sof_nocodec_bes_setup(struct device *dev, diff --git a/sound/usb/card.c b/sound/usb/card.c index f9a64e9526f5..230d862cfa3a 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -659,10 +659,14 @@ static int usb_audio_probe(struct usb_interface *intf, goto __error; } - /* we are allowed to call snd_card_register() many times */ - err = snd_card_register(chip->card); - if (err < 0) - goto __error; + /* we are allowed to call snd_card_register() many times, but first + * check to see if a device needs to skip it or do anything special + */ + if (!snd_usb_registration_quirk(chip, ifnum)) { + err = snd_card_register(chip->card); + if (err < 0) + goto __error; + } if (quirk && quirk->shares_media_device) { /* don't want to fail when snd_media_device_create() fails */ diff --git a/sound/usb/card.h b/sound/usb/card.h index de43267b9c8a..5351d7183b1b 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -137,6 +137,7 @@ struct snd_usb_substream { unsigned int tx_length_quirk:1; /* add length specifier to transfers */ unsigned int fmt_type; /* USB audio format type (1-3) */ unsigned int pkt_offset_adj; /* Bytes to drop from beginning of packets (for non-compliant devices) */ + unsigned int stream_offset_adj; /* Bytes to drop from beginning of stream (for non-compliant devices) */ unsigned int running: 1; /* running status */ diff --git a/sound/usb/clock.c b/sound/usb/clock.c index a48313dfa967..b118cf97607f 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -151,16 +151,15 @@ static int uac_clock_selector_set_val(struct snd_usb_audio *chip, int selector_i return ret; } -/* - * Assume the clock is valid if clock source supports only one single sample - * rate, the terminal is connected directly to it (there is no clock selector) - * and clock type is internal. This is to deal with some Denon DJ controllers - * that always reports that clock is invalid. - */ static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip, struct audioformat *fmt, int source_id) { + bool ret = false; + int count; + unsigned char data; + struct usb_device *dev = chip->dev; + if (fmt->protocol == UAC_VERSION_2) { struct uac_clock_source_descriptor *cs_desc = snd_usb_find_clock_source(chip->ctrl_intf, source_id); @@ -168,13 +167,51 @@ static bool uac_clock_source_is_valid_quirk(struct snd_usb_audio *chip, if (!cs_desc) return false; - return (fmt->nr_rates == 1 && - (fmt->clock & 0xff) == cs_desc->bClockID && - (cs_desc->bmAttributes & 0x3) != - UAC_CLOCK_SOURCE_TYPE_EXT); + /* + * Assume the clock is valid if clock source supports only one + * single sample rate, the terminal is connected directly to it + * (there is no clock selector) and clock type is internal. + * This is to deal with some Denon DJ controllers that always + * reports that clock is invalid. + */ + if (fmt->nr_rates == 1 && + (fmt->clock & 0xff) == cs_desc->bClockID && + (cs_desc->bmAttributes & 0x3) != + UAC_CLOCK_SOURCE_TYPE_EXT) + return true; + } + + /* + * MOTU MicroBook IIc + * Sample rate changes takes more than 2 seconds for this device. Clock + * validity request returns false during that period. + */ + if (chip->usb_id == USB_ID(0x07fd, 0x0004)) { + count = 0; + + while ((!ret) && (count < 50)) { + int err; + + msleep(100); + + err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR, + USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN, + UAC2_CS_CONTROL_CLOCK_VALID << 8, + snd_usb_ctrl_intf(chip) | (source_id << 8), + &data, sizeof(data)); + if (err < 0) { + dev_warn(&dev->dev, + "%s(): cannot get clock validity for id %d\n", + __func__, source_id); + return false; + } + + ret = !!data; + count++; + } } - return false; + return ret; } static bool uac_clock_source_is_valid(struct snd_usb_audio *chip, diff --git a/sound/usb/line6/capture.c b/sound/usb/line6/capture.c index 82abef3fe90d..4b6e99e055dc 100644 --- a/sound/usb/line6/capture.c +++ b/sound/usb/line6/capture.c @@ -287,6 +287,8 @@ int line6_create_audio_in_urbs(struct snd_line6_pcm *line6pcm) urb->interval = LINE6_ISO_INTERVAL; urb->error_count = 0; urb->complete = audio_in_callback; + if (usb_urb_ep_type_check(urb)) + return -EINVAL; } return 0; diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index b52961076659..9eac35587f9d 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -831,7 +831,7 @@ void line6_disconnect(struct usb_interface *interface) if (WARN_ON(usbdev != line6->usbdev)) return; - cancel_delayed_work(&line6->startup_work); + cancel_delayed_work_sync(&line6->startup_work); if (line6->urb_listen != NULL) line6_stop_listen(line6); diff --git a/sound/usb/line6/playback.c b/sound/usb/line6/playback.c index 2e8ead3f9bc2..797ced329b79 100644 --- a/sound/usb/line6/playback.c +++ b/sound/usb/line6/playback.c @@ -432,6 +432,8 @@ int line6_create_audio_out_urbs(struct snd_line6_pcm *line6pcm) urb->interval = LINE6_ISO_INTERVAL; urb->error_count = 0; urb->complete = audio_out_callback; + if (usb_urb_ep_type_check(urb)) + return -EINVAL; } return 0; diff --git a/sound/usb/midi.c b/sound/usb/midi.c index b737f0ec77d0..0cb4142b05f6 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1499,6 +1499,8 @@ void snd_usbmidi_disconnect(struct list_head *p) spin_unlock_irq(&umidi->disc_lock); up_write(&umidi->disc_rwsem); + del_timer_sync(&umidi->error_timer); + for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i) { struct snd_usb_midi_endpoint *ep = &umidi->endpoints[i]; if (ep->out) @@ -1525,7 +1527,6 @@ void snd_usbmidi_disconnect(struct list_head *p) ep->in = NULL; } } - del_timer_sync(&umidi->error_timer); } EXPORT_SYMBOL(snd_usbmidi_disconnect); @@ -2282,16 +2283,22 @@ void snd_usbmidi_input_stop(struct list_head *p) } EXPORT_SYMBOL(snd_usbmidi_input_stop); -static void snd_usbmidi_input_start_ep(struct snd_usb_midi_in_endpoint *ep) +static void snd_usbmidi_input_start_ep(struct snd_usb_midi *umidi, + struct snd_usb_midi_in_endpoint *ep) { unsigned int i; + unsigned long flags; if (!ep) return; for (i = 0; i < INPUT_URBS; ++i) { struct urb *urb = ep->urbs[i]; - urb->dev = ep->umidi->dev; - snd_usbmidi_submit_urb(urb, GFP_KERNEL); + spin_lock_irqsave(&umidi->disc_lock, flags); + if (!atomic_read(&urb->use_count)) { + urb->dev = ep->umidi->dev; + snd_usbmidi_submit_urb(urb, GFP_ATOMIC); + } + spin_unlock_irqrestore(&umidi->disc_lock, flags); } } @@ -2307,7 +2314,7 @@ void snd_usbmidi_input_start(struct list_head *p) if (umidi->input_running || !umidi->opened[1]) return; for (i = 0; i < MIDI_MAX_ENDPOINTS; ++i) - snd_usbmidi_input_start_ep(umidi->endpoints[i].in); + snd_usbmidi_input_start_ep(umidi, umidi->endpoints[i].in); umidi->input_running = 1; } EXPORT_SYMBOL(snd_usbmidi_input_start); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 27d9b47ef7d3..c48104208fed 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -183,6 +183,7 @@ static const struct rc_config { { USB_ID(0x041e, 0x3042), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 */ { USB_ID(0x041e, 0x30df), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ { USB_ID(0x041e, 0x3237), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ + { USB_ID(0x041e, 0x3263), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */ { USB_ID(0x041e, 0x3048), 2, 2, 6, 6, 2, 0x6e91 }, /* Toshiba SB0500 */ }; diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 4a9fcbd235a0..e837ce55f6ad 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -344,11 +344,17 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ep = 0x81; ifnum = 1; goto add_sync_ep_from_ifnum; - case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II */ + case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II/IIc */ + /* MicroBook IIc */ + if (altsd->bInterfaceClass == USB_CLASS_AUDIO) + return 0; + + /* MicroBook II */ ep = 0x84; ifnum = 0; goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */ case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ case USB_ID(0x0d9a, 0x00df): /* RTX6001 */ ep = 0x81; @@ -1411,6 +1417,12 @@ static void retire_capture_urb(struct snd_usb_substream *subs, // continue; } bytes = urb->iso_frame_desc[i].actual_length; + if (subs->stream_offset_adj > 0) { + unsigned int adj = min(subs->stream_offset_adj, bytes); + cp += adj; + bytes -= adj; + subs->stream_offset_adj -= adj; + } frames = bytes / stride; if (!subs->txfr_quirk) bytes = frames * stride; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 09484e3b7a11..f55b605cfeb7 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2776,90 +2776,6 @@ YAMAHA_DEVICE(0x7010, "UB99"), .type = QUIRK_MIDI_NOVATION } }, -{ - /* - * Focusrite Scarlett Solo 2nd generation - * Reports that playback should use Synch: Synchronous - * while still providing a feedback endpoint. Synchronous causes - * snapping on some sample rates. - * Force it to use Synch: Asynchronous. - */ - USB_DEVICE(0x1235, 0x8205), - .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { - .ifnum = QUIRK_ANY_INTERFACE, - .type = QUIRK_COMPOSITE, - .data = (const struct snd_usb_audio_quirk[]) { - { - .ifnum = 1, - .type = QUIRK_AUDIO_FIXED_ENDPOINT, - .data = & (const struct audioformat) { - .formats = SNDRV_PCM_FMTBIT_S32_LE, - .channels = 2, - .iface = 1, - .altsetting = 1, - .altset_idx = 1, - .attributes = 0, - .endpoint = 0x01, - .ep_attr = USB_ENDPOINT_XFER_ISOC | - USB_ENDPOINT_SYNC_ASYNC, - .protocol = UAC_VERSION_2, - .rates = SNDRV_PCM_RATE_44100 | - SNDRV_PCM_RATE_48000 | - SNDRV_PCM_RATE_88200 | - SNDRV_PCM_RATE_96000 | - SNDRV_PCM_RATE_176400 | - SNDRV_PCM_RATE_192000, - .rate_min = 44100, - .rate_max = 192000, - .nr_rates = 6, - .rate_table = (unsigned int[]) { - 44100, 48000, 88200, - 96000, 176400, 192000 - }, - .clock = 41 - } - }, - { - .ifnum = 2, - .type = QUIRK_AUDIO_FIXED_ENDPOINT, - .data = & (const struct audioformat) { - .formats = SNDRV_PCM_FMTBIT_S32_LE, - .channels = 2, - .iface = 2, - .altsetting = 1, - .altset_idx = 1, - .attributes = 0, - .endpoint = 0x82, - .ep_attr = USB_ENDPOINT_XFER_ISOC | - USB_ENDPOINT_SYNC_ASYNC | - USB_ENDPOINT_USAGE_IMPLICIT_FB, - .protocol = UAC_VERSION_2, - .rates = SNDRV_PCM_RATE_44100 | - SNDRV_PCM_RATE_48000 | - SNDRV_PCM_RATE_88200 | - SNDRV_PCM_RATE_96000 | - SNDRV_PCM_RATE_176400 | - SNDRV_PCM_RATE_192000, - .rate_min = 44100, - .rate_max = 192000, - .nr_rates = 6, - .rate_table = (unsigned int[]) { - 44100, 48000, 88200, - 96000, 176400, 192000 - }, - .clock = 41 - } - }, - { - .ifnum = 3, - .type = QUIRK_IGNORE_INTERFACE - }, - { - .ifnum = -1 - } - } - } -}, /* Access Music devices */ { @@ -3492,7 +3408,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), }, /* MOTU Microbook II */ { - USB_DEVICE(0x07fd, 0x0004), + USB_DEVICE_VENDOR_SPEC(0x07fd, 0x0004), .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { .vendor_name = "MOTU", .product_name = "MicroBookII", @@ -3597,6 +3513,62 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } } }, +{ + /* + * PIONEER DJ DDJ-RB + * PCM is 4 channels out, 2 dummy channels in @ 44.1 fixed + * The feedback for the output is the dummy input. + */ + USB_DEVICE_VENDOR_SPEC(0x2b73, 0x000e), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 4, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .endpoint = 0x01, + .ep_attr = USB_ENDPOINT_XFER_ISOC| + USB_ENDPOINT_SYNC_ASYNC, + .rates = SNDRV_PCM_RATE_44100, + .rate_min = 44100, + .rate_max = 44100, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 44100 } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 2, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC| + USB_ENDPOINT_SYNC_ASYNC| + USB_ENDPOINT_USAGE_IMPLICIT_FB, + .rates = SNDRV_PCM_RATE_44100, + .rate_min = 44100, + .rate_max = 44100, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 44100 } + } + }, + { + .ifnum = -1 + } + } + } +}, #define ALC1220_VB_DESKTOP(vend, prod) { \ USB_DEVICE(vend, prod), \ @@ -3646,11 +3618,17 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ * they pretend to be 96kHz mono as a workaround for stereo being broken * by that... * - * They also have swapped L-R channels, but that's for userspace to deal - * with. + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. */ { - USB_DEVICE(0x534d, 0x2109), + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | + USB_DEVICE_ID_MATCH_INT_CLASS | + USB_DEVICE_ID_MATCH_INT_SUBCLASS, + .idVendor = 0x534d, + .idProduct = 0x2109, + .bInterfaceClass = USB_CLASS_AUDIO, + .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { .vendor_name = "MacroSilicon", .product_name = "MS2109", diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index bf5083a20b6d..a756f50d9f07 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1316,7 +1316,15 @@ int snd_usb_apply_boot_quirk(struct usb_device *dev, case USB_ID(0x2466, 0x8010): /* Fractal Audio Axe-Fx 3 */ return snd_usb_axefx3_boot_quirk(dev); case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook II */ - return snd_usb_motu_microbookii_boot_quirk(dev); + /* + * For some reason interface 3 with vendor-spec class is + * detected on MicroBook IIc. + */ + if (get_iface_desc(intf->altsetting)->bInterfaceClass == + USB_CLASS_VENDOR_SPEC && + get_iface_desc(intf->altsetting)->bInterfaceNumber < 3) + return snd_usb_motu_microbookii_boot_quirk(dev); + break; } return 0; @@ -1424,6 +1432,9 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */ set_format_emu_quirk(subs, fmt); break; + case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */ + subs->stream_offset_adj = 2; + break; } } @@ -1764,5 +1775,62 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip, else fp->ep_attr |= USB_ENDPOINT_SYNC_SYNC; break; + case USB_ID(0x07fd, 0x0004): /* MOTU MicroBook IIc */ + /* + * MaxPacketsOnly attribute is erroneously set in endpoint + * descriptors. As a result this card produces noise with + * all sample rates other than 96 KHz. + */ + fp->attributes &= ~UAC_EP_CS_ATTR_FILL_MAX; + break; + case USB_ID(0x1235, 0x8202): /* Focusrite Scarlett 2i2 2nd gen */ + case USB_ID(0x1235, 0x8205): /* Focusrite Scarlett Solo 2nd gen */ + /* + * Reports that playback should use Synch: Synchronous + * while still providing a feedback endpoint. + * Synchronous causes snapping on some sample rates. + * Force it to use Synch: Asynchronous. + */ + if (stream == SNDRV_PCM_STREAM_PLAYBACK) { + fp->ep_attr &= ~USB_ENDPOINT_SYNCTYPE; + fp->ep_attr |= USB_ENDPOINT_SYNC_ASYNC; + } + break; } } + +/* + * registration quirk: + * the registration is skipped if a device matches with the given ID, + * unless the interface reaches to the defined one. This is for delaying + * the registration until the last known interface, so that the card and + * devices appear at the same time. + */ + +struct registration_quirk { + unsigned int usb_id; /* composed via USB_ID() */ + unsigned int interface; /* the interface to trigger register */ +}; + +#define REG_QUIRK_ENTRY(vendor, product, iface) \ + { .usb_id = USB_ID(vendor, product), .interface = (iface) } + +static const struct registration_quirk registration_quirks[] = { + REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */ + REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */ + REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */ + { 0 } /* terminator */ +}; + +/* return true if skipping registration */ +bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface) +{ + const struct registration_quirk *q; + + for (q = registration_quirks; q->usb_id; q++) + if (chip->usb_id == q->usb_id) + return iface != q->interface; + + /* Register as normal */ + return false; +} diff --git a/sound/usb/quirks.h b/sound/usb/quirks.h index df0355843a4c..c76cf24a640a 100644 --- a/sound/usb/quirks.h +++ b/sound/usb/quirks.h @@ -51,4 +51,6 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip, struct audioformat *fp, int stream); +bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface); + #endif /* __USBAUDIO_QUIRKS_H */ diff --git a/sound/usb/stream.c b/sound/usb/stream.c index a0649c8ae460..3a17c4c53f87 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -89,6 +89,7 @@ static void snd_usb_init_substream(struct snd_usb_stream *as, subs->tx_length_quirk = as->chip->tx_length_quirk; subs->speed = snd_usb_get_speed(subs->dev); subs->pkt_offset_adj = 0; + subs->stream_offset_adj = 0; snd_usb_set_pcm_ops(as->pcm, stream); diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 1fbf353364d6..5c67bbcdf914 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -539,7 +539,7 @@ static int do_dump(int argc, char **argv) goto done; } if (!btf) { - err = ENOENT; + err = -ENOENT; p_err("can't find btf with ID (%u)", btf_id); goto done; } diff --git a/tools/build/Build.include b/tools/build/Build.include index 9ec01f4454f9..585486e40995 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -74,7 +74,8 @@ dep-cmd = $(if $(wildcard $(fixdep)), # dependencies in the cmd file if_changed_dep = $(if $(strip $(any-prereq) $(arg-check)), \ @set -e; \ - $(echo-cmd) $(cmd_$(1)) && $(dep-cmd)) + $(echo-cmd) $(cmd_$(1)); \ + $(dep-cmd)) # if_changed - execute command if any prerequisite is newer than # target, or command line has changed diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 3b24231c58a2..5cc7a3131e20 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -8,7 +8,7 @@ endif feature_check = $(eval $(feature_check_code)) define feature_check_code - feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0) + feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC="$(CC)" CXX="$(CXX)" CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0) endef feature_set = $(eval $(feature_set_code)) diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 4b8244ee65ce..a8dbda61f034 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -67,8 +67,6 @@ FILES= \ FILES := $(addprefix $(OUTPUT),$(FILES)) -CC ?= $(CROSS_COMPILE)gcc -CXX ?= $(CROSS_COMPILE)g++ PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 1827c2f973f9..2868ec890b37 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -38,6 +38,7 @@ #define __always_inline inline #endif +#undef __user #define __user #define __rcu #define __read_mostly diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 1864b11c1117..8d5b83c1ee10 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -270,7 +270,7 @@ define do_generate_dynamic_list_file xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\ echo '};'; \ ) > $2; \ else \ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 3d6c9c5b455c..36af2bec523c 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2828,6 +2828,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; + free_token(token); type = read_token(&token); *tok = token; diff --git a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..1c2832e9f77d 100644 --- a/tools/objtool/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/objtool/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/perf/Makefile.config b/tools/perf/Makefile.config index 6718dc74ad64..45997e10a335 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -654,8 +654,9 @@ ifndef NO_SLANG endif endif ifndef NO_SLANG - # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h - CFLAGS += -I/usr/include/slang + # 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 $(call detected,CONFIG_SLANG) @@ -690,6 +691,7 @@ else FLAGS_PERL_EMBED=$(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 4d46ca6d7e20..4fe5b4dc0422 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -894,7 +894,7 @@ 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/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 1ce6bdbda561..b9d471a0babd 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -54,7 +54,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct perf_evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -72,12 +72,12 @@ struct auxtrace_record evsel->attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -94,7 +94,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* 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/bench.h b/tools/perf/bench/bench.h index fddb3ced9db6..4aa6de1aa67d 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -2,6 +2,10 @@ #ifndef BENCH_H #define BENCH_H +#include <sys/time.h> + +extern struct timeval bench__start, bench__end, bench__runtime; + /* * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 2af067859966..8a383c3e0967 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -33,7 +33,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool done, __verbose, randomize; /* @@ -92,8 +91,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void nest_epollfd(void) @@ -359,7 +358,7 @@ int bench_epoll_ctl(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index fe85448abd45..235e3aa28aad 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -88,7 +88,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool wdone, done, __verbose, randomize, nonblocking; /* @@ -274,8 +273,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -285,7 +284,7 @@ static void print_summary(void) printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static int do_threads(struct worker *worker, struct cpu_map *cpu) @@ -477,7 +476,7 @@ int bench_epoll_wait(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); @@ -517,7 +516,7 @@ int bench_epoll_wait(int argc, const char **argv) qsort(worker, nthreads, sizeof(struct worker), cmpworker); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 9aa3a674829b..ee9b28065109 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -35,7 +35,7 @@ static unsigned int nfutexes = 1024; static bool fshared = false, done = false, silent = false; static int futex_flag = 0; -struct timeval start, end, runtime; +struct timeval bench__start, bench__end, bench__runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -101,8 +101,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -112,7 +112,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } int bench_futex_hash(int argc, const char **argv) @@ -159,7 +159,7 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); for (i = 0; i < nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); @@ -202,7 +202,7 @@ int bench_futex_hash(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) { if (nfutexes == 1) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 8e9c4753e304..017609ae3590 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -35,7 +35,6 @@ static bool silent = false, multi = false; static bool done = false, fshared = false; static unsigned int nthreads = 0; static int futex_flag = 0; -struct timeval start, end, runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -62,7 +61,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static void toggle_done(int sig __maybe_unused, @@ -71,8 +70,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void *workerfn(void *arg) @@ -183,7 +182,7 @@ int bench_futex_lock_pi(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); create_threads(worker, thread_attr, cpu); pthread_attr_destroy(&thread_attr); @@ -209,7 +208,7 @@ int bench_futex_lock_pi(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index 0251dd348124..4864fc67d01b 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -222,12 +222,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info * return 0; } -static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst) +static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst) { - u64 cycle_start = 0ULL, cycle_end = 0ULL; - memcpy_t fn = r->fn.memcpy; - int i; - /* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */ memset(src, 0, size); @@ -236,6 +232,15 @@ static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, vo * to not measure page fault overhead: */ fn(dst, src, size); +} + +static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + memcpy_t fn = r->fn.memcpy; + int i; + + memcpy_prefault(fn, size, src, dst); cycle_start = get_cycles(); for (i = 0; i < nr_loops; ++i) @@ -251,11 +256,7 @@ static double do_memcpy_gettimeofday(const struct function *r, size_t size, void memcpy_t fn = r->fn.memcpy; int i; - /* - * We prefault the freshly allocated memory range here, - * to not measure page fault overhead: - */ - fn(dst, src, size); + memcpy_prefault(fn, size, src, dst); BUG_ON(gettimeofday(&tv_start, NULL)); for (i = 0; i < nr_loops; ++i) diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 23c27ca48abf..8004982a1204 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -27,6 +27,7 @@ #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> @@ -1195,7 +1196,7 @@ 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/perf.h b/tools/perf/perf.h index a26555baf692..c16c3b4b6455 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -14,6 +14,8 @@ void test_attr__init(void); void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, int fd, int group_fd, unsigned long flags); +#include <stdbool.h> + #define HAVE_ATTR_TEST #include "perf-sys.h" diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 217568bc29ce..b7db978a95ce 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 "../../../perf.h" #include "../../../util/trace-event.h" diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index d8426547219b..16b4dfd619df 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -73,7 +73,7 @@ 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) { @@ -82,7 +82,7 @@ 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; @@ -98,10 +98,10 @@ 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"); @@ -132,10 +132,10 @@ 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_account.c b/tools/perf/tests/bp_account.c index 57fc544aedb0..92226772d3c4 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -21,7 +21,7 @@ #include "perf.h" #include "cloexec.h" -volatile long the_var; +static volatile long the_var; static noinline int test_function(void) { diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index 6cf00650602e..0f32a9c11023 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -120,7 +120,7 @@ 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 ca962559e845..35e1de86b295 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -95,7 +95,7 @@ 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/annotate.c b/tools/perf/util/annotate.c index 95690b2cad86..4d15bb50b854 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1899,7 +1899,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand", + " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|sed 's/\t/ /g'", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6a3eaf7d9353..725bf9270762 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -322,11 +322,11 @@ static const char *normalize_arch(char *arch) const char *perf_env__arch(struct perf_env *env) { - struct utsname uts; char *arch_name; if (!env || !env->arch) { /* Assume local operation */ - if (uname(&uts) < 0) + static struct utsname uts = { .machine[0] = '\0', }; + if (uts.machine[0] == '\0' && uname(&uts) < 0) return NULL; arch_name = uts.machine; } else diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk index ddd5c4c21129..d236058fc4e2 100644 --- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk +++ b/tools/perf/util/intel-pt-decoder/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/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9d189e90fbdc..b030de6eb546 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1120,6 +1120,7 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) return 0; if (err == -EAGAIN || intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; if (intel_pt_fup_event(decoder)) return 0; return -EAGAIN; @@ -1783,17 +1784,13 @@ next: } if (decoder->set_fup_mwait) no_tip = true; + if (no_tip) + decoder->pkt_state = INTEL_PT_STATE_FUP_NO_TIP; + else + decoder->pkt_state = INTEL_PT_STATE_FUP; err = intel_pt_walk_fup(decoder); - if (err != -EAGAIN) { - if (err) - return err; - if (no_tip) - decoder->pkt_state = - INTEL_PT_STATE_FUP_NO_TIP; - else - decoder->pkt_state = INTEL_PT_STATE_FUP; - return 0; - } + if (err != -EAGAIN) + return err; if (no_tip) { no_tip = false; break; @@ -2382,15 +2379,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_walk_tip(decoder); break; case INTEL_PT_STATE_FUP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_fup_tip(decoder); - else if (!err) - decoder->pkt_state = INTEL_PT_STATE_FUP; break; case INTEL_PT_STATE_FUP_NO_TIP: - decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_fup(decoder); if (err == -EAGAIN) err = intel_pt_walk_trace(decoder); diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index c5e568188e19..d493f96b806d 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 "debug.h" #include "libunwind-x86.h" diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index d3b472cc88dc..8fc2c3e5b83c 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/perf/util/stat.c b/tools/perf/util/stat.c index e2ce6021e6c4..17cd7e4a645e 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -358,8 +358,10 @@ int perf_stat_process_counter(struct perf_stat_config *config, * interval mode, otherwise overall avg running * averages will be shown for each interval. */ - if (config->interval) - init_stats(ps->res_stats); + if (config->interval) { + for (i = 0; i < 3; i++) + init_stats(&ps->res_stats[i]); + } if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 0bee09661651..ff07ea319406 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -406,7 +406,7 @@ int perf_time__parse_for_ranges_reltime(const char *time_str, { bool has_percent = strchr(time_str, '%'); struct perf_time_interval *ptime_range; - int size, num, ret; + int size, num, ret = -EINVAL; ptime_range = perf_time__range_alloc(time_str, &size); if (!ptime_range) @@ -418,7 +418,6 @@ int perf_time__parse_for_ranges_reltime(const char *time_str, pr_err("HINT: no first/last sample time found in perf data.\n" "Please use latest perf binary to execute 'perf record'\n" "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n"); - ret = -EINVAL; goto error; } } @@ -430,11 +429,8 @@ int perf_time__parse_for_ranges_reltime(const char *time_str, session->evlist->first_sample_time, session->evlist->last_sample_time); - if (num < 0) { - pr_err("Invalid time string\n"); - ret = -EINVAL; - goto error; - } + if (num < 0) + goto error_invalid; } else { if (perf_time__parse_str(ptime_range, time_str)) goto error_invalid; @@ -455,6 +451,8 @@ int perf_time__parse_for_ranges_reltime(const char *time_str, *ranges = ptime_range; return 0; +error_invalid: + pr_err("Invalid time string\n"); error: free(ptime_range); return ret; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c9ea4d33a807..c33e8efa9139 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -162,6 +162,7 @@ endif endif TEST_PROGS_CFLAGS := -I. -I$(OUTPUT) +TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier ifneq ($(SUBREG_CODEGEN),) @@ -213,16 +214,14 @@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif -PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h -test_progs.c: $(PROG_TESTS_H) -$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: prog_tests/*.c - PROG_TESTS_DIR = $(OUTPUT)/prog_tests $(PROG_TESTS_DIR): mkdir -p $@ - +PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) +test_progs.c: $(PROG_TESTS_H) +$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ @@ -236,7 +235,6 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) echo '#endif' \ ) > $(PROG_TESTS_H)) -TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) MAP_TESTS_DIR = $(OUTPUT)/map_tests $(MAP_TESTS_DIR): mkdir -p $@ @@ -258,17 +256,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) echo '#endif' \ ) > $(MAP_TESTS_H)) -VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h -test_verifier.c: $(VERIFIER_TESTS_H) -$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) -$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) - VERIFIER_TESTS_DIR = $(OUTPUT)/verifier $(VERIFIER_TESTS_DIR): mkdir -p $@ - +VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) -$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) +test_verifier.c: $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) +$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef FILL_ARRAY'; \ diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index a3fbc571280a..116aa8f7b691 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -778,19 +778,19 @@ static void test_sockmap(unsigned int tasks, void *data) } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER); - if (err) { + if (!err) { printf("Failed empty parser prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT); - if (err) { + if (!err) { printf("Failed empty verdict prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_MSG_VERDICT); - if (err) { + if (!err) { printf("Failed empty msg verdict prog detach\n"); goto out_sockmap; } @@ -1079,19 +1079,19 @@ static void test_sockmap(unsigned int tasks, void *data) assert(status == 0); } - err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE); + err = bpf_prog_detach2(parse_prog, map_fd_rx, __MAX_BPF_ATTACH_TYPE); if (!err) { printf("Detached an invalid prog type.\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER); + err = bpf_prog_detach2(parse_prog, map_fd_rx, BPF_SK_SKB_STREAM_PARSER); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); + err = bpf_prog_detach2(verdict_prog, map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 15d3489ecd9c..ceb7ad4dbd94 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,6 +6,8 @@ set +x set -e +modprobe -q nf_defrag_ipv6 + readonly NETNS="ns-$(mktemp -u XXXXXX)" setup() { diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 4b02933cab8a..bdc03a2097e8 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -125,9 +125,8 @@ static int do_setcpu(int cpu) CPU_ZERO(&mask); CPU_SET(cpu, &mask); if (sched_setaffinity(0, sizeof(mask), &mask)) - error(1, 0, "setaffinity %d", cpu); - - if (cfg_verbose) + fprintf(stderr, "cpu: unable to pin, may increase variance.\n"); + else if (cfg_verbose) fprintf(stderr, "cpu: %u\n", cpu); return 0; diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c index a2e8c9da7fa5..d50cc05df495 100644 --- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -19,6 +19,7 @@ #include <limits.h> #include <sys/time.h> #include <sys/syscall.h> +#include <sys/sysinfo.h> #include <sys/types.h> #include <sys/shm.h> #include <linux/futex.h> @@ -104,8 +105,9 @@ static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu) static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu) { - int pid; - cpu_set_t cpuset; + int pid, ncpus; + cpu_set_t *cpuset; + size_t size; pid = fork(); if (pid == -1) { @@ -116,14 +118,23 @@ static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu) if (pid) return; - CPU_ZERO(&cpuset); - CPU_SET(cpu, &cpuset); + ncpus = get_nprocs(); + size = CPU_ALLOC_SIZE(ncpus); + cpuset = CPU_ALLOC(ncpus); + if (!cpuset) { + perror("malloc"); + exit(1); + } + CPU_ZERO_S(size, cpuset); + CPU_SET_S(cpu, size, cpuset); - if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) { + if (sched_setaffinity(0, size, cpuset)) { perror("sched_setaffinity"); + CPU_FREE(cpuset); exit(1); } + CPU_FREE(cpuset); fn(arg); exit(0); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c index bdbbbe8431e0..3694613f418f 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c @@ -44,7 +44,7 @@ struct shared_info { unsigned long amr2; /* AMR value that ptrace should refuse to write to the child. */ - unsigned long amr3; + unsigned long invalid_amr; /* IAMR value the parent expects to read from the child. */ unsigned long expected_iamr; @@ -57,8 +57,8 @@ struct shared_info { * (even though they're valid ones) because userspace doesn't have * access to those registers. */ - unsigned long new_iamr; - unsigned long new_uamor; + unsigned long invalid_iamr; + unsigned long invalid_uamor; }; static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) @@ -66,11 +66,6 @@ static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights) return syscall(__NR_pkey_alloc, flags, init_access_rights); } -static int sys_pkey_free(int pkey) -{ - return syscall(__NR_pkey_free, pkey); -} - static int child(struct shared_info *info) { unsigned long reg; @@ -100,28 +95,32 @@ static int child(struct shared_info *info) info->amr1 |= 3ul << pkeyshift(pkey1); info->amr2 |= 3ul << pkeyshift(pkey2); - info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3); + /* + * invalid amr value where we try to force write + * things which are deined by a uamor setting. + */ + info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor); + /* + * if PKEY_DISABLE_EXECUTE succeeded we should update the expected_iamr + */ if (disable_execute) info->expected_iamr |= 1ul << pkeyshift(pkey1); else info->expected_iamr &= ~(1ul << pkeyshift(pkey1)); - info->expected_iamr &= ~(1ul << pkeyshift(pkey2) | 1ul << pkeyshift(pkey3)); - - info->expected_uamor |= 3ul << pkeyshift(pkey1) | - 3ul << pkeyshift(pkey2); - info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2); - info->new_uamor |= 3ul << pkeyshift(pkey1); + /* + * We allocated pkey2 and pkey 3 above. Clear the IAMR bits. + */ + info->expected_iamr &= ~(1ul << pkeyshift(pkey2)); + info->expected_iamr &= ~(1ul << pkeyshift(pkey3)); /* - * We won't use pkey3. We just want a plausible but invalid key to test - * whether ptrace will let us write to AMR bits we are not supposed to. - * - * This also tests whether the kernel restores the UAMOR permissions - * after a key is freed. + * Create an IAMR value different from expected value. + * Kernel will reject an IAMR and UAMOR change. */ - sys_pkey_free(pkey3); + info->invalid_iamr = info->expected_iamr | (1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2)); + info->invalid_uamor = info->expected_uamor & ~(0x3ul << pkeyshift(pkey1)); printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n", user_write, info->amr1, pkey1, pkey2, pkey3); @@ -196,9 +195,9 @@ static int parent(struct shared_info *info, pid_t pid) PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync); PARENT_FAIL_IF(ret, &info->child_sync); - info->amr1 = info->amr2 = info->amr3 = regs[0]; - info->expected_iamr = info->new_iamr = regs[1]; - info->expected_uamor = info->new_uamor = regs[2]; + info->amr1 = info->amr2 = regs[0]; + info->expected_iamr = regs[1]; + info->expected_uamor = regs[2]; /* Wake up child so that it can set itself up. */ ret = prod_child(&info->child_sync); @@ -234,10 +233,10 @@ static int parent(struct shared_info *info, pid_t pid) return ret; /* Write invalid AMR value in child. */ - ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1); + ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->invalid_amr, 1); PARENT_FAIL_IF(ret, &info->child_sync); - printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3); + printf("%-30s AMR: %016lx\n", ptrace_write_running, info->invalid_amr); /* Wake up child so that it can verify it didn't change. */ ret = prod_child(&info->child_sync); @@ -249,7 +248,7 @@ static int parent(struct shared_info *info, pid_t pid) /* Try to write to IAMR. */ regs[0] = info->amr1; - regs[1] = info->new_iamr; + regs[1] = info->invalid_iamr; ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2); PARENT_FAIL_IF(!ret, &info->child_sync); @@ -257,7 +256,7 @@ static int parent(struct shared_info *info, pid_t pid) ptrace_write_running, regs[0], regs[1]); /* Try to write to IAMR and UAMOR. */ - regs[2] = info->new_uamor; + regs[2] = info->invalid_uamor; ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3); PARENT_FAIL_IF(!ret, &info->child_sync); diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index c02d24835db4..176102eca994 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -16,6 +16,7 @@ #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> +#include <sys/sysinfo.h> #include <sys/types.h> #include <sys/utsname.h> #include <unistd.h> @@ -88,28 +89,40 @@ void *get_auxv_entry(int type) int pick_online_cpu(void) { - cpu_set_t mask; - int cpu; + int ncpus, cpu = -1; + cpu_set_t *mask; + size_t size; + + ncpus = get_nprocs_conf(); + size = CPU_ALLOC_SIZE(ncpus); + mask = CPU_ALLOC(ncpus); + if (!mask) { + perror("malloc"); + return -1; + } - CPU_ZERO(&mask); + CPU_ZERO_S(size, mask); - if (sched_getaffinity(0, sizeof(mask), &mask)) { + if (sched_getaffinity(0, size, mask)) { perror("sched_getaffinity"); - return -1; + goto done; } /* We prefer a primary thread, but skip 0 */ - for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8) - if (CPU_ISSET(cpu, &mask)) - return cpu; + for (cpu = 8; cpu < ncpus; cpu += 8) + if (CPU_ISSET_S(cpu, size, mask)) + goto done; /* Search for anything, but in reverse */ - for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--) - if (CPU_ISSET(cpu, &mask)) - return cpu; + for (cpu = ncpus - 1; cpu >= 0; cpu--) + if (CPU_ISSET_S(cpu, size, mask)) + goto done; printf("No cpus in affinity mask?!\n"); - return -1; + +done: + CPU_FREE(mask); + return cpu; } bool is_ppc64le(void) 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/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index b60ef2e2267a..40629f92ea05 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -177,7 +177,7 @@ struct seccomp_metadata { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) struct seccomp_notif { __u64 id; diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 7656c7ce79d9..0e73a16874c4 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \ TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) +TEST_FILES := settings include ../lib.mk diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/timers/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/usr/Makefile b/usr/Makefile index bdb3f52fadc4..433af5945907 100644 --- a/usr/Makefile +++ b/usr/Makefile @@ -27,7 +27,7 @@ $(obj)/initramfs_data.o: $(obj)/$(datafile_y) FORCE # Generate the initramfs cpio archive hostprogs-y := gen_init_cpio -initramfs := $(CONFIG_SHELL) $(srctree)/$(src)/gen_initramfs_list.sh +initramfs := $(INITRAMFS_WRAPPER) $(CONFIG_SHELL) $(srctree)/$(src)/gen_initramfs_list.sh ramfs-input := $(if $(filter-out "",$(CONFIG_INITRAMFS_SOURCE)), \ $(shell echo $(CONFIG_INITRAMFS_SOURCE)),-d) ramfs-args := \ diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 1aa8523082a5..1f0d95c2f5f9 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1199,7 +1199,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, return true; } -static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz) { pud_t *pudp; pmd_t *pmdp; @@ -1211,11 +1211,11 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) return false; if (pudp) - return kvm_s2pud_exec(pudp); + return sz <= PUD_SIZE && kvm_s2pud_exec(pudp); else if (pmdp) - return kvm_s2pmd_exec(pmdp); + return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp); else - return kvm_s2pte_exec(ptep); + return sz == PAGE_SIZE && kvm_s2pte_exec(ptep); } static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, @@ -1805,7 +1805,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * execute permissions, and we preserve whatever we have. */ needs_exec = exec_fault || - (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa)); + (fault_status == FSC_PERM && + stage2_is_exec(kvm, fault_ipa, vma_pagesize)); if (vma_pagesize == PUD_SIZE) { pud_t new_pud = kvm_pfn_pud(pfn, mem_type); |