--- linux-4.14.0.orig/Documentation/ABI/testing/debugfs-aufs +++ linux-4.14.0/Documentation/ABI/testing/debugfs-aufs @@ -0,0 +1,50 @@ +What: /debug/aufs/si_/ +Date: March 2009 +Contact: J. R. Okajima +Description: + Under /debug/aufs, a directory named si_ is created + per aufs mount, where is a unique id generated + internally. + +What: /debug/aufs/si_/plink +Date: Apr 2013 +Contact: J. R. Okajima +Description: + It has three lines and shows the information about the + pseudo-link. The first line is a single number + representing a number of buckets. The second line is a + number of pseudo-links per buckets (separated by a + blank). The last line is a single number representing a + total number of psedo-links. + When the aufs mount option 'noplink' is specified, it + will show "1\n0\n0\n". + +What: /debug/aufs/si_/xib +Date: March 2009 +Contact: J. R. Okajima +Description: + It shows the consumed blocks by xib (External Inode Number + Bitmap), its block size and file size. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. + +What: /debug/aufs/si_/xino0, xino1 ... xinoN +Date: March 2009 +Contact: J. R. Okajima +Description: + It shows the consumed blocks by xino (External Inode Number + Translation Table), its link count, block size and file + size. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. + +What: /debug/aufs/si_/xigen +Date: March 2009 +Contact: J. R. Okajima +Description: + It shows the consumed blocks by xigen (External Inode + Generation Table), its block size and file size. + If CONFIG_AUFS_EXPORT is disabled, this entry will not + be created. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. --- linux-4.14.0.orig/Documentation/ABI/testing/sysfs-aufs +++ linux-4.14.0/Documentation/ABI/testing/sysfs-aufs @@ -0,0 +1,31 @@ +What: /sys/fs/aufs/si_/ +Date: March 2009 +Contact: J. R. Okajima +Description: + Under /sys/fs/aufs, a directory named si_ is created + per aufs mount, where is a unique id generated + internally. + +What: /sys/fs/aufs/si_/br0, br1 ... brN +Date: March 2009 +Contact: J. R. Okajima +Description: + It shows the abolute path of a member directory (which + is called branch) in aufs, and its permission. + +What: /sys/fs/aufs/si_/brid0, brid1 ... bridN +Date: July 2013 +Contact: J. R. Okajima +Description: + It shows the id of a member directory (which is called + branch) in aufs. + +What: /sys/fs/aufs/si_/xi_path +Date: March 2009 +Contact: J. R. Okajima +Description: + It shows the abolute path of XINO (External Inode Number + Bitmap, Translation Table and Generation Table) file + even if it is the default path. + When the aufs mount option 'noxino' is specified, it + will be empty. About XINO files, see the aufs manual. --- linux-4.14.0.orig/Documentation/admin-guide/LSM/index.rst +++ linux-4.14.0/Documentation/admin-guide/LSM/index.rst @@ -17,11 +17,16 @@ specific changes to system operation when these tweaks are not available in the core functionality of Linux itself. -Without a specific LSM built into the kernel, the default LSM will be the -Linux capabilities system. Most LSMs choose to extend the capabilities -system, building their checks on top of the defined capability hooks. -For more details on capabilities, see ``capabilities(7)`` in the Linux -man-pages project. +The Linux capabilities modules will always be included. For more details +on capabilities, see ``capabilities(7)`` in the Linux man-pages project. + +Security modules that do not use the security data blobs maintained +by the LSM infrastructure are considered "minor" modules. These may be +included at compile time and stacked explicitly. Security modules that +use the LSM maintained security blobs are considered "major" modules. +These may only be stacked if the CONFIG_LSM_STACKED configuration +option is used. If this is chosen all of the security modules selected +will be used. A list of the active security modules can be found by reading ``/sys/kernel/security/lsm``. This is a comma separated list, and @@ -30,6 +35,22 @@ be first, followed by any "minor" modules (e.g. Yama) and then the one "major" module (e.g. SELinux) if there is one configured. +Process attributes associated with "major" security modules should +be accessed and maintained using the special files in ``/proc/.../attr``. +A security module may maintain a module specific subdirectory there, +named after the module. ``/proc/.../attr/smack`` is provided by the Smack +security module and contains all its special files. The files directly +in ``/proc/.../attr`` remain as legacy interfaces for modules that provide +subdirectories. + +The files named "context" in the attr directories contain the +same information as the "current" files, but formatted to +identify the module it comes from. + +if selinux is the active security module: + /proc/self/attr/context could contain selinux='unconfined_t' + /proc/self/attr/selinux/context could contain selinux='unconfined_t' + .. toctree:: :maxdepth: 1 --- linux-4.14.0.orig/Documentation/admin-guide/kernel-parameters.txt +++ linux-4.14.0/Documentation/admin-guide/kernel-parameters.txt @@ -656,6 +656,10 @@ 0: default value, disable debugging 1: enable debugging at boot time + cpufreq_driver= [X86] Allow only the named cpu frequency scaling driver + to register. Example: cpufreq_driver=powernow-k8 + Format: { none | STRING } + cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system @@ -2685,6 +2689,8 @@ steal time is computed, but won't influence scheduler behaviour + nopti [X86-64] Disable kernel page table isolation + nolapic [X86-32,APIC] Do not enable or use the local APIC. nolapic_timer [X86-32,APIC] Do not use the local APIC timer. @@ -3253,6 +3259,12 @@ pt. [PARIDE] See Documentation/blockdev/paride.txt. + pti= [X86_64] + Control user/kernel address space isolation: + on - enable + off - disable + auto - default setting + pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in default number. --- linux-4.14.0.orig/Documentation/arm64/silicon-errata.txt +++ linux-4.14.0/Documentation/arm64/silicon-errata.txt @@ -74,3 +74,4 @@ | Qualcomm Tech. | Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | | Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | +| Qualcomm Tech. | Falkor v{1,2} | E1041 | QCOM_FALKOR_ERRATUM_1041 | --- linux-4.14.0.orig/Documentation/cgroups/namespace.txt +++ linux-4.14.0/Documentation/cgroups/namespace.txt @@ -0,0 +1,142 @@ + CGroup Namespaces + +CGroup Namespace provides a mechanism to virtualize the view of the +/proc//cgroup file. The CLONE_NEWCGROUP clone-flag can be used with +clone() and unshare() syscalls to create a new cgroup namespace. +The process running inside the cgroup namespace will have its /proc//cgroup +output restricted to cgroupns-root. cgroupns-root is the cgroup of the process +at the time of creation of the cgroup namespace. + +Prior to CGroup Namespace, the /proc//cgroup file used to show complete +path of the cgroup of a process. In a container setup (where a set of cgroups +and namespaces are intended to isolate processes), the /proc//cgroup file +may leak potential system level information to the isolated processes. + +For Example: + $ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + +The path '/batchjobs/container_id1' can generally be considered as system-data +and its desirable to not expose it to the isolated process. + +CGroup Namespaces can be used to restrict visibility of this path. +For Example: + # Before creating cgroup namespace + $ ls -l /proc/self/ns/cgroup + lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835] + $ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + + # unshare(CLONE_NEWCGROUP) and exec /bin/bash + $ ~/unshare -c + [ns]$ ls -l /proc/self/ns/cgroup + lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183] + # From within new cgroupns, process sees that its in the root cgroup + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/ + + # From global cgroupns: + $ cat /proc//cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + + # Unshare cgroupns along with userns and mountns + # Following calls unshare(CLONE_NEWCGROUP|CLONE_NEWUSER|CLONE_NEWNS), then + # sets up uid/gid map and execs /bin/bash + $ ~/unshare -c -u -m + # Originally, we were in /batchjobs/container_id1 cgroup. Mount our own cgroup + # hierarchy. + [ns]$ mount -t cgroup cgroup /tmp/cgroup + [ns]$ ls -l /tmp/cgroup + total 0 + -r--r--r-- 1 root root 0 2014-10-13 09:32 cgroup.controllers + -r--r--r-- 1 root root 0 2014-10-13 09:32 cgroup.populated + -rw-r--r-- 1 root root 0 2014-10-13 09:25 cgroup.procs + -rw-r--r-- 1 root root 0 2014-10-13 09:32 cgroup.subtree_control + +The cgroupns-root (/batchjobs/container_id1 in above example) becomes the +filesystem root for the namespace specific cgroupfs mount. + +The virtualization of /proc/self/cgroup file combined with restricting +the view of cgroup hierarchy by namespace-private cgroupfs mount +should provide a completely isolated cgroup view inside the container. + +In its current form, the cgroup namespaces patcheset provides following +behavior: + +(1) The 'cgroupns-root' for a cgroup namespace is the cgroup in which + the process calling unshare is running. + For ex. if a process in /batchjobs/container_id1 cgroup calls unshare, + cgroup /batchjobs/container_id1 becomes the cgroupns-root. + For the init_cgroup_ns, this is the real root ('/') cgroup + (identified in code as cgrp_dfl_root.cgrp). + +(2) The cgroupns-root cgroup does not change even if the namespace + creator process later moves to a different cgroup. + $ ~/unshare -c # unshare cgroupns in some cgroup + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/ + [ns]$ mkdir sub_cgrp_1 + [ns]$ echo 0 > sub_cgrp_1/cgroup.procs + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + +(3) Each process gets its CGROUPNS specific view of /proc//cgroup +(a) Processes running inside the cgroup namespace will be able to see + cgroup paths (in /proc/self/cgroup) only inside their root cgroup + [ns]$ sleep 100000 & # From within unshared cgroupns + [1] 7353 + [ns]$ echo 7353 > sub_cgrp_1/cgroup.procs + [ns]$ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + +(b) From global cgroupns, the real cgroup path will be visible: + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1/sub_cgrp_1 + +(c) From a sibling cgroupns (cgroupns root-ed at a different cgroup), cgroup + path relative to its own cgroupns-root will be shown: + # ns2's cgroupns-root is at '/batchjobs/container_id2' + [ns2]$ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/../container_id2/sub_cgrp_1 + + Note that the relative path always starts with '/' to indicate that its + relative to the cgroupns-root of the caller. + +(4) Processes inside a cgroupns can move in-and-out of the cgroupns-root + (if they have proper access to external cgroups). + # From inside cgroupns (with cgroupns-root at /batchjobs/container_id1), and + # assuming that the global hierarchy is still accessible inside cgroupns: + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + $ echo 7353 > batchjobs/container_id2/cgroup.procs + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/../container_id2 + + Note that this kind of setup is not encouraged. A task inside cgroupns + should only be exposed to its own cgroupns hierarchy. Otherwise it makes + the virtualization of /proc//cgroup less useful. + +(5) Setns to another cgroup namespace is allowed when: + (a) the process has CAP_SYS_ADMIN in its current userns + (b) the process has CAP_SYS_ADMIN in the target cgroupns' userns + No implicit cgroup changes happen with attaching to another cgroupns. It + is expected that the somone moves the attaching process under the target + cgroupns-root. + +(6) When some thread from a multi-threaded process unshares its + cgroup-namespace, the new cgroupns gets applied to the entire process (all + the threads). For the unified-hierarchy this is expected as it only allows + process-level containerization. For the legacy hierarchies this may be + unexpected. So all the threads in the process will have the same cgroup. + +(7) The cgroup namespace is alive as long as there is atleast 1 + process inside it. When the last process exits, the cgroup + namespace is destroyed. The cgroupns-root and the actual cgroups + remain though. + +(8) Namespace specific cgroup hierarchy can be mounted by a process running + inside cgroupns: + $ mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT + + This will mount the unified cgroup hierarchy with cgroupns-root as the + filesystem root. The process needs CAP_SYS_ADMIN in its userns and mntns. --- linux-4.14.0.orig/Documentation/devicetree/bindings/hwmon/jc42.txt +++ linux-4.14.0/Documentation/devicetree/bindings/hwmon/jc42.txt @@ -34,6 +34,10 @@ - reg: I2C address +Optional properties: +- smbus-timeout-disable: When set, the smbus timeout function will be disabled. + This is not supported on all chips. + Example: temp-sensor@1a { --- linux-4.14.0.orig/Documentation/devicetree/bindings/timer/renesas,cmt.txt +++ linux-4.14.0/Documentation/devicetree/bindings/timer/renesas,cmt.txt @@ -20,16 +20,16 @@ (CMT1 on sh73a0 and r8a7740) This is a fallback for the above renesas,cmt-48-* entries. - - "renesas,cmt0-r8a73a4" for the 32-bit CMT0 device included in r8a73a4. - - "renesas,cmt1-r8a73a4" for the 48-bit CMT1 device included in r8a73a4. - - "renesas,cmt0-r8a7790" for the 32-bit CMT0 device included in r8a7790. - - "renesas,cmt1-r8a7790" for the 48-bit CMT1 device included in r8a7790. - - "renesas,cmt0-r8a7791" for the 32-bit CMT0 device included in r8a7791. - - "renesas,cmt1-r8a7791" for the 48-bit CMT1 device included in r8a7791. - - "renesas,cmt0-r8a7793" for the 32-bit CMT0 device included in r8a7793. - - "renesas,cmt1-r8a7793" for the 48-bit CMT1 device included in r8a7793. - - "renesas,cmt0-r8a7794" for the 32-bit CMT0 device included in r8a7794. - - "renesas,cmt1-r8a7794" for the 48-bit CMT1 device included in r8a7794. + - "renesas,r8a73a4-cmt0" for the 32-bit CMT0 device included in r8a73a4. + - "renesas,r8a73a4-cmt1" for the 48-bit CMT1 device included in r8a73a4. + - "renesas,r8a7790-cmt0" for the 32-bit CMT0 device included in r8a7790. + - "renesas,r8a7790-cmt1" for the 48-bit CMT1 device included in r8a7790. + - "renesas,r8a7791-cmt0" for the 32-bit CMT0 device included in r8a7791. + - "renesas,r8a7791-cmt1" for the 48-bit CMT1 device included in r8a7791. + - "renesas,r8a7793-cmt0" for the 32-bit CMT0 device included in r8a7793. + - "renesas,r8a7793-cmt1" for the 48-bit CMT1 device included in r8a7793. + - "renesas,r8a7794-cmt0" for the 32-bit CMT0 device included in r8a7794. + - "renesas,r8a7794-cmt1" for the 48-bit CMT1 device included in r8a7794. - "renesas,rcar-gen2-cmt0" for 32-bit CMT0 devices included in R-Car Gen2. - "renesas,rcar-gen2-cmt1" for 48-bit CMT1 devices included in R-Car Gen2. @@ -46,7 +46,7 @@ Example: R8A7790 (R-Car H2) CMT0 and CMT1 nodes cmt0: timer@ffca0000 { - compatible = "renesas,cmt0-r8a7790", "renesas,rcar-gen2-cmt0"; + compatible = "renesas,r8a7790-cmt0", "renesas,rcar-gen2-cmt0"; reg = <0 0xffca0000 0 0x1004>; interrupts = <0 142 IRQ_TYPE_LEVEL_HIGH>, <0 142 IRQ_TYPE_LEVEL_HIGH>; @@ -55,7 +55,7 @@ }; cmt1: timer@e6130000 { - compatible = "renesas,cmt1-r8a7790", "renesas,rcar-gen2-cmt1"; + compatible = "renesas,r8a7790-cmt1", "renesas,rcar-gen2-cmt1"; reg = <0 0xe6130000 0 0x1004>; interrupts = <0 120 IRQ_TYPE_LEVEL_HIGH>, <0 121 IRQ_TYPE_LEVEL_HIGH>, --- linux-4.14.0.orig/Documentation/devicetree/bindings/usb/usb-device.txt +++ linux-4.14.0/Documentation/devicetree/bindings/usb/usb-device.txt @@ -11,7 +11,7 @@ be used, but a device adhering to this binding may leave out all except for usbVID,PID. - reg: the port number which this device is connecting to, the range - is 1-31. + is 1-255. Example: --- linux-4.14.0.orig/Documentation/filesystems/aufs/README +++ linux-4.14.0/Documentation/filesystems/aufs/README @@ -0,0 +1,393 @@ + +Aufs4 -- advanced multi layered unification filesystem version 4.x +http://aufs.sf.net +Junjiro R. Okajima + + +0. Introduction +---------------------------------------- +In the early days, aufs was entirely re-designed and re-implemented +Unionfs Version 1.x series. Adding many original ideas, approaches, +improvements and implementations, it becomes totally different from +Unionfs while keeping the basic features. +Recently, Unionfs Version 2.x series begin taking some of the same +approaches to aufs1's. +Unionfs is being developed by Professor Erez Zadok at Stony Brook +University and his team. + +Aufs4 supports linux-4.0 and later, and for linux-3.x series try aufs3. +If you want older kernel version support, try aufs2-2.6.git or +aufs2-standalone.git repository, aufs1 from CVS on SourceForge. + +Note: it becomes clear that "Aufs was rejected. Let's give it up." + According to Christoph Hellwig, linux rejects all union-type + filesystems but UnionMount. + + +PS. Al Viro seems have a plan to merge aufs as well as overlayfs and + UnionMount, and he pointed out an issue around a directory mutex + lock and aufs addressed it. But it is still unsure whether aufs will + be merged (or any other union solution). + + + +1. Features +---------------------------------------- +- unite several directories into a single virtual filesystem. The member + directory is called as a branch. +- you can specify the permission flags to the branch, which are 'readonly', + 'readwrite' and 'whiteout-able.' +- by upper writable branch, internal copyup and whiteout, files/dirs on + readonly branch are modifiable logically. +- dynamic branch manipulation, add, del. +- etc... + +Also there are many enhancements in aufs, such as: +- test only the highest one for the directory permission (dirperm1) +- copyup on open (coo=) +- 'move' policy for copy-up between two writable branches, after + checking free space. +- xattr, acl +- readdir(3) in userspace. +- keep inode number by external inode number table +- keep the timestamps of file/dir in internal copyup operation +- seekable directory, supporting NFS readdir. +- whiteout is hardlinked in order to reduce the consumption of inodes + on branch +- do not copyup, nor create a whiteout when it is unnecessary +- revert a single systemcall when an error occurs in aufs +- remount interface instead of ioctl +- maintain /etc/mtab by an external command, /sbin/mount.aufs. +- loopback mounted filesystem as a branch +- kernel thread for removing the dir who has a plenty of whiteouts +- support copyup sparse file (a file which has a 'hole' in it) +- default permission flags for branches +- selectable permission flags for ro branch, whether whiteout can + exist or not +- export via NFS. +- support /fs/aufs and /aufs. +- support multiple writable branches, some policies to select one + among multiple writable branches. +- a new semantics for link(2) and rename(2) to support multiple + writable branches. +- no glibc changes are required. +- pseudo hardlink (hardlink over branches) +- allow a direct access manually to a file on branch, e.g. bypassing aufs. + including NFS or remote filesystem branch. +- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX. +- and more... + +Currently these features are dropped temporary from aufs4. +See design/08plan.txt in detail. +- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs + (robr) +- statistics of aufs thread (/sys/fs/aufs/stat) + +Features or just an idea in the future (see also design/*.txt), +- reorder the branch index without del/re-add. +- permanent xino files for NFSD +- an option for refreshing the opened files after add/del branches +- light version, without branch manipulation. (unnecessary?) +- copyup in userspace +- inotify in userspace +- readv/writev + + +2. Download +---------------------------------------- +There are three GIT trees for aufs4, aufs4-linux.git, +aufs4-standalone.git, and aufs-util.git. Note that there is no "4" in +"aufs-util.git." +While the aufs-util is always necessary, you need either of aufs4-linux +or aufs4-standalone. + +The aufs4-linux tree includes the whole linux mainline GIT tree, +git://git.kernel.org/.../torvalds/linux.git. +And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot +build aufs4 as an external kernel module. +Several extra patches are not included in this tree. Only +aufs4-standalone tree contains them. They are described in the later +section "Configuration and Compilation." + +On the other hand, the aufs4-standalone tree has only aufs source files +and necessary patches, and you can select CONFIG_AUFS_FS=m. +But you need to apply all aufs patches manually. + +You will find GIT branches whose name is in form of "aufs4.x" where "x" +represents the linux kernel version, "linux-4.x". For instance, +"aufs4.0" is for linux-4.0. For latest "linux-4.x-rcN", use +"aufs4.x-rcN" branch. + +o aufs4-linux tree +$ git clone --reference /your/linux/git/tree \ + git://github.com/sfjro/aufs4-linux.git aufs4-linux.git +- if you don't have linux GIT tree, then remove "--reference ..." +$ cd aufs4-linux.git +$ git checkout origin/aufs4.0 + +Or You may want to directly git-pull aufs into your linux GIT tree, and +leave the patch-work to GIT. +$ cd /your/linux/git/tree +$ git remote add aufs4 git://github.com/sfjro/aufs4-linux.git +$ git fetch aufs4 +$ git checkout -b my4.0 v4.0 +$ (add your local change...) +$ git pull aufs4 aufs4.0 +- now you have v4.0 + your_changes + aufs4.0 in you my4.0 branch. +- you may need to solve some conflicts between your_changes and + aufs4.0. in this case, git-rerere is recommended so that you can + solve the similar conflicts automatically when you upgrade to 4.1 or + later in the future. + +o aufs4-standalone tree +$ git clone git://github.com/sfjro/aufs4-standalone.git aufs4-standalone.git +$ cd aufs4-standalone.git +$ git checkout origin/aufs4.0 + +o aufs-util tree +$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git +- note that the public aufs-util.git is on SourceForge instead of + GitHUB. +$ cd aufs-util.git +$ git checkout origin/aufs4.0 + +Note: The 4.x-rcN branch is to be used with `rc' kernel versions ONLY. +The minor version number, 'x' in '4.x', of aufs may not always +follow the minor version number of the kernel. +Because changes in the kernel that cause the use of a new +minor version number do not always require changes to aufs-util. + +Since aufs-util has its own minor version number, you may not be +able to find a GIT branch in aufs-util for your kernel's +exact minor version number. +In this case, you should git-checkout the branch for the +nearest lower number. + +For (an unreleased) example: +If you are using "linux-4.10" and the "aufs4.10" branch +does not exist in aufs-util repository, then "aufs4.9", "aufs4.8" +or something numerically smaller is the branch for your kernel. + +Also you can view all branches by + $ git branch -a + + +3. Configuration and Compilation +---------------------------------------- +Make sure you have git-checkout'ed the correct branch. + +For aufs4-linux tree, +- enable CONFIG_AUFS_FS. +- set other aufs configurations if necessary. + +For aufs4-standalone tree, +There are several ways to build. + +1. +- apply ./aufs4-kbuild.patch to your kernel source files. +- apply ./aufs4-base.patch too. +- apply ./aufs4-mmap.patch too. +- apply ./aufs4-standalone.patch too, if you have a plan to set + CONFIG_AUFS_FS=m. otherwise you don't need ./aufs4-standalone.patch. +- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your + kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild. +- enable CONFIG_AUFS_FS, you can select either + =m or =y. +- and build your kernel as usual. +- install the built kernel. + Note: Since linux-3.9, every filesystem module requires an alias + "fs-". You should make sure that "fs-aufs" is listed in your + modules.aliases file if you set CONFIG_AUFS_FS=m. +- install the header files too by "make headers_install" to the + directory where you specify. By default, it is $PWD/usr. + "make help" shows a brief note for headers_install. +- and reboot your system. + +2. +- module only (CONFIG_AUFS_FS=m). +- apply ./aufs4-base.patch to your kernel source files. +- apply ./aufs4-mmap.patch too. +- apply ./aufs4-standalone.patch too. +- build your kernel, don't forget "make headers_install", and reboot. +- edit ./config.mk and set other aufs configurations if necessary. + Note: You should read $PWD/fs/aufs/Kconfig carefully which describes + every aufs configurations. +- build the module by simple "make". + Note: Since linux-3.9, every filesystem module requires an alias + "fs-". You should make sure that "fs-aufs" is listed in your + modules.aliases file. +- you can specify ${KDIR} make variable which points to your kernel + source tree. +- install the files + + run "make install" to install the aufs module, or copy the built + $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply). + + run "make install_headers" (instead of headers_install) to install + the modified aufs header file (you can specify DESTDIR which is + available in aufs standalone version's Makefile only), or copy + $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever + you like manually. By default, the target directory is $PWD/usr. +- no need to apply aufs4-kbuild.patch, nor copying source files to your + kernel source tree. + +Note: The header file aufs_type.h is necessary to build aufs-util + as well as "make headers_install" in the kernel source tree. + headers_install is subject to be forgotten, but it is essentially + necessary, not only for building aufs-util. + You may not meet problems without headers_install in some older + version though. + +And then, +- read README in aufs-util, build and install it +- note that your distribution may contain an obsoleted version of + aufs_type.h in /usr/include/linux or something. When you build aufs + utilities, make sure that your compiler refers the correct aufs header + file which is built by "make headers_install." +- if you want to use readdir(3) in userspace or pathconf(3) wrapper, + then run "make install_ulib" too. And refer to the aufs manual in + detail. + +There several other patches in aufs4-standalone.git. They are all +optional. When you meet some problems, they will help you. +- aufs4-loopback.patch + Supports a nested loopback mount in a branch-fs. This patch is + unnecessary until aufs produces a message like "you may want to try + another patch for loopback file". +- vfs-ino.patch + Modifies a system global kernel internal function get_next_ino() in + order to stop assigning 0 for an inode-number. Not directly related to + aufs, but recommended generally. +- tmpfs-idr.patch + Keeps the tmpfs inode number as the lowest value. Effective to reduce + the size of aufs XINO files for tmpfs branch. Also it prevents the + duplication of inode number, which is important for backup tools and + other utilities. When you find aufs XINO files for tmpfs branch + growing too much, try this patch. +- lockdep-debug.patch + Because aufs is not only an ordinary filesystem (callee of VFS), but + also a caller of VFS functions for branch filesystems, subclassing of + the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging + feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will + need to apply this debug patch to expand several constant values. + If don't know what LOCKDEP, then you don't have apply this patch. + + +4. Usage +---------------------------------------- +At first, make sure aufs-util are installed, and please read the aufs +manual, aufs.5 in aufs-util.git tree. +$ man -l aufs.5 + +And then, +$ mkdir /tmp/rw /tmp/aufs +# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs + +Here is another example. The result is equivalent. +# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs + Or +# mount -t aufs -o br:/tmp/rw none /tmp/aufs +# mount -o remount,append:${HOME} /tmp/aufs + +Then, you can see whole tree of your home dir through /tmp/aufs. If +you modify a file under /tmp/aufs, the one on your home directory is +not affected, instead the same named file will be newly created under +/tmp/rw. And all of your modification to a file will be applied to +the one under /tmp/rw. This is called the file based Copy on Write +(COW) method. +Aufs mount options are described in aufs.5. +If you run chroot or something and make your aufs as a root directory, +then you need to customize the shutdown script. See the aufs manual in +detail. + +Additionally, there are some sample usages of aufs which are a +diskless system with network booting, and LiveCD over NFS. +See sample dir in CVS tree on SourceForge. + + +5. Contact +---------------------------------------- +When you have any problems or strange behaviour in aufs, please let me +know with: +- /proc/mounts (instead of the output of mount(8)) +- /sys/module/aufs/* +- /sys/fs/aufs/* (if you have them) +- /debug/aufs/* (if you have them) +- linux kernel version + if your kernel is not plain, for example modified by distributor, + the url where i can download its source is necessary too. +- aufs version which was printed at loading the module or booting the + system, instead of the date you downloaded. +- configuration (define/undefine CONFIG_AUFS_xxx) +- kernel configuration or /proc/config.gz (if you have it) +- behaviour which you think to be incorrect +- actual operation, reproducible one is better +- mailto: aufs-users at lists.sourceforge.net + +Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches, +and Feature Requests) on SourceForge. Please join and write to +aufs-users ML. + + +6. Acknowledgements +---------------------------------------- +Thanks to everyone who have tried and are using aufs, whoever +have reported a bug or any feedback. + +Especially donators: +Tomas Matejicek(slax.org) made a donation (much more than once). + Since Apr 2010, Tomas M (the author of Slax and Linux Live + scripts) is making "doubling" donations. + Unfortunately I cannot list all of the donators, but I really + appreciate. + It ends Aug 2010, but the ordinary donation URL is still available. + +Dai Itasaka made a donation (2007/8). +Chuck Smith made a donation (2008/4, 10 and 12). +Henk Schoneveld made a donation (2008/9). +Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). +Francois Dupoux made a donation (2008/11). +Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public + aufs2 GIT tree (2009/2). +William Grant made a donation (2009/3). +Patrick Lane made a donation (2009/4). +The Mail Archive (mail-archive.com) made donations (2009/5). +Nippy Networks (Ed Wildgoose) made a donation (2009/7). +New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). +Pavel Pronskiy made a donation (2011/2). +Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy + Networks (Ed Wildgoose) made a donation for hardware (2011/3). +Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and +11). +Sam Liddicott made a donation (2011/9). +Era Scarecrow made a donation (2013/4). +Bor Ratajc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +POIRETTE Marc made a donation (2013/4). +Alessandro Gorreta made a donation (2013/4). +lauri kasvandik made a donation (2013/5). +"pemasu from Finland" made a donation (2013/7). +The Parted Magic Project made a donation (2013/9 and 11). +Pavel Barta made a donation (2013/10). +Nikolay Pertsev made a donation (2014/5). +James B made a donation (2014/7 and 2015/7). +Stefano Di Biase made a donation (2014/8). +Daniel Epellei made a donation (2015/1). +OmegaPhil made a donation (2016/1). +Tomasz Szewczyk made a donation (2016/4). +James Burry made a donation (2016/12). + +Thank you very much. +Donations are always, including future donations, very important and +helpful for me to keep on developing aufs. + + +7. +---------------------------------------- +If you are an experienced user, no explanation is needed. Aufs is +just a linux filesystem. + + +Enjoy! + +# Local variables: ; +# mode: text; +# End: ; --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/01intro.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/01intro.txt @@ -0,0 +1,171 @@ + +# Copyright (C) 2005-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Introduction +---------------------------------------- + +aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s] +1. abbrev. for "advanced multi-layered unification filesystem". +2. abbrev. for "another unionfs". +3. abbrev. for "auf das" in German which means "on the" in English. + Ex. "Butter aufs Brot"(G) means "butter onto bread"(E). + But "Filesystem aufs Filesystem" is hard to understand. +4. abbrev. for "African Urban Fashion Show". + +AUFS is a filesystem with features: +- multi layered stackable unification filesystem, the member directory + is called as a branch. +- branch permission and attribute, 'readonly', 'real-readonly', + 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their + combination. +- internal "file copy-on-write". +- logical deletion, whiteout. +- dynamic branch manipulation, adding, deleting and changing permission. +- allow bypassing aufs, user's direct branch access. +- external inode number translation table and bitmap which maintains the + persistent aufs inode number. +- seekable directory, including NFS readdir. +- file mapping, mmap and sharing pages. +- pseudo-link, hardlink over branches. +- loopback mounted filesystem as a branch. +- several policies to select one among multiple writable branches. +- revert a single systemcall when an error occurs in aufs. +- and more... + + +Multi Layered Stackable Unification Filesystem +---------------------------------------------------------------------- +Most people already knows what it is. +It is a filesystem which unifies several directories and provides a +merged single directory. When users access a file, the access will be +passed/re-directed/converted (sorry, I am not sure which English word is +correct) to the real file on the member filesystem. The member +filesystem is called 'lower filesystem' or 'branch' and has a mode +'readonly' and 'readwrite.' And the deletion for a file on the lower +readonly branch is handled by creating 'whiteout' on the upper writable +branch. + +On LKML, there have been discussions about UnionMount (Jan Blunck, +Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took +different approaches to implement the merged-view. +The former tries putting it into VFS, and the latter implements as a +separate filesystem. +(If I misunderstand about these implementations, please let me know and +I shall correct it. Because it is a long time ago when I read their +source files last time). + +UnionMount's approach will be able to small, but may be hard to share +branches between several UnionMount since the whiteout in it is +implemented in the inode on branch filesystem and always +shared. According to Bharata's post, readdir does not seems to be +finished yet. +There are several missing features known in this implementations such as +- for users, the inode number may change silently. eg. copy-up. +- link(2) may break by copy-up. +- read(2) may get an obsoleted filedata (fstat(2) too). +- fcntl(F_SETLK) may be broken by copy-up. +- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after + open(O_RDWR). + +In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was +merged into mainline. This is another implementation of UnionMount as a +separated filesystem. All the limitations and known problems which +UnionMount are equally inherited to "overlay" filesystem. + +Unionfs has a longer history. When I started implementing a stackable +filesystem (Aug 2005), it already existed. It has virtual super_block, +inode, dentry and file objects and they have an array pointing lower +same kind objects. After contributing many patches for Unionfs, I +re-started my project AUFS (Jun 2006). + +In AUFS, the structure of filesystem resembles to Unionfs, but I +implemented my own ideas, approaches and enhancements and it became +totally different one. + +Comparing DM snapshot and fs based implementation +- the number of bytes to be copied between devices is much smaller. +- the type of filesystem must be one and only. +- the fs must be writable, no readonly fs, even for the lower original + device. so the compression fs will not be usable. but if we use + loopback mount, we may address this issue. + for instance, + mount /cdrom/squashfs.img /sq + losetup /sq/ext2.img + losetup /somewhere/cow + dmsetup "snapshot /dev/loop0 /dev/loop1 ..." +- it will be difficult (or needs more operations) to extract the + difference between the original device and COW. +- DM snapshot-merge may help a lot when users try merging. in the + fs-layer union, users will use rsync(1). + +You may want to read my old paper "Filesystems in LiveCD" +(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf). + + +Several characters/aspects/persona of aufs +---------------------------------------------------------------------- + +Aufs has several characters, aspects or persona. +1. a filesystem, callee of VFS helper +2. sub-VFS, caller of VFS helper for branches +3. a virtual filesystem which maintains persistent inode number +4. reader/writer of files on branches such like an application + +1. Callee of VFS Helper +As an ordinary linux filesystem, aufs is a callee of VFS. For instance, +unlink(2) from an application reaches sys_unlink() kernel function and +then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it +calls filesystem specific unlink operation. Actually aufs implements the +unlink operation but it behaves like a redirector. + +2. Caller of VFS Helper for Branches +aufs_unlink() passes the unlink request to the branch filesystem as if +it were called from VFS. So the called unlink operation of the branch +filesystem acts as usual. As a caller of VFS helper, aufs should handle +every necessary pre/post operation for the branch filesystem. +- acquire the lock for the parent dir on a branch +- lookup in a branch +- revalidate dentry on a branch +- mnt_want_write() for a branch +- vfs_unlink() for a branch +- mnt_drop_write() for a branch +- release the lock on a branch + +3. Persistent Inode Number +One of the most important issue for a filesystem is to maintain inode +numbers. This is particularly important to support exporting a +filesystem via NFS. Aufs is a virtual filesystem which doesn't have a +backend block device for its own. But some storage is necessary to +keep and maintain the inode numbers. It may be a large space and may not +suit to keep in memory. Aufs rents some space from its first writable +branch filesystem (by default) and creates file(s) on it. These files +are created by aufs internally and removed soon (currently) keeping +opened. +Note: Because these files are removed, they are totally gone after + unmounting aufs. It means the inode numbers are not persistent + across unmount or reboot. I have a plan to make them really + persistent which will be important for aufs on NFS server. + +4. Read/Write Files Internally (copy-on-write) +Because a branch can be readonly, when you write a file on it, aufs will +"copy-up" it to the upper writable branch internally. And then write the +originally requested thing to the file. Generally kernel doesn't +open/read/write file actively. In aufs, even a single write may cause a +internal "file copy". This behaviour is very similar to cp(1) command. + +Some people may think it is better to pass such work to user space +helper, instead of doing in kernel space. Actually I am still thinking +about it. But currently I have implemented it in kernel space. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/02struct.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/02struct.txt @@ -0,0 +1,258 @@ + +# Copyright (C) 2005-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Basic Aufs Internal Structure + +Superblock/Inode/Dentry/File Objects +---------------------------------------------------------------------- +As like an ordinary filesystem, aufs has its own +superblock/inode/dentry/file objects. All these objects have a +dynamically allocated array and store the same kind of pointers to the +lower filesystem, branch. +For example, when you build a union with one readwrite branch and one +readonly, mounted /au, /rw and /ro respectively. +- /au = /rw + /ro +- /ro/fileA exists but /rw/fileA + +Aufs lookup operation finds /ro/fileA and gets dentry for that. These +pointers are stored in a aufs dentry. The array in aufs dentry will be, +- [0] = NULL (because /rw/fileA doesn't exist) +- [1] = /ro/fileA + +This style of an array is essentially same to the aufs +superblock/inode/dentry/file objects. + +Because aufs supports manipulating branches, ie. add/delete/change +branches dynamically, these objects has its own generation. When +branches are changed, the generation in aufs superblock is +incremented. And a generation in other object are compared when it is +accessed. When a generation in other objects are obsoleted, aufs +refreshes the internal array. + + +Superblock +---------------------------------------------------------------------- +Additionally aufs superblock has some data for policies to select one +among multiple writable branches, XIB files, pseudo-links and kobject. +See below in detail. +About the policies which supports copy-down a directory, see +wbr_policy.txt too. + + +Branch and XINO(External Inode Number Translation Table) +---------------------------------------------------------------------- +Every branch has its own xino (external inode number translation table) +file. The xino file is created and unlinked by aufs internally. When two +members of a union exist on the same filesystem, they share the single +xino file. +The struct of a xino file is simple, just a sequence of aufs inode +numbers which is indexed by the lower inode number. +In the above sample, assume the inode number of /ro/fileA is i111 and +aufs assigns the inode number i999 for fileA. Then aufs writes 999 as +4(8) bytes at 111 * 4(8) bytes offset in the xino file. + +When the inode numbers are not contiguous, the xino file will be sparse +which has a hole in it and doesn't consume as much disk space as it +might appear. If your branch filesystem consumes disk space for such +holes, then you should specify 'xino=' option at mounting aufs. + +Aufs has a mount option to free the disk blocks for such holes in XINO +files on tmpfs or ramdisk. But it is not so effective actually. If you +meet a problem of disk shortage due to XINO files, then you should try +"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git. +The patch localizes the assignment inumbers per tmpfs-mount and avoid +the holes in XINO files. + +Also a writable branch has three kinds of "whiteout bases". All these +are existed when the branch is joined to aufs, and their names are +whiteout-ed doubly, so that users will never see their names in aufs +hierarchy. +1. a regular file which will be hardlinked to all whiteouts. +2. a directory to store a pseudo-link. +3. a directory to store an "orphan"-ed file temporary. + +1. Whiteout Base + When you remove a file on a readonly branch, aufs handles it as a + logical deletion and creates a whiteout on the upper writable branch + as a hardlink of this file in order not to consume inode on the + writable branch. +2. Pseudo-link Dir + See below, Pseudo-link. +3. Step-Parent Dir + When "fileC" exists on the lower readonly branch only and it is + opened and removed with its parent dir, and then user writes + something into it, then aufs copies-up fileC to this + directory. Because there is no other dir to store fileC. After + creating a file under this dir, the file is unlinked. + +Because aufs supports manipulating branches, ie. add/delete/change +dynamically, a branch has its own id. When the branch order changes, +aufs finds the new index by searching the branch id. + + +Pseudo-link +---------------------------------------------------------------------- +Assume "fileA" exists on the lower readonly branch only and it is +hardlinked to "fileB" on the branch. When you write something to fileA, +aufs copies-up it to the upper writable branch. Additionally aufs +creates a hardlink under the Pseudo-link Directory of the writable +branch. The inode of a pseudo-link is kept in aufs super_block as a +simple list. If fileB is read after unlinking fileA, aufs returns +filedata from the pseudo-link instead of the lower readonly +branch. Because the pseudo-link is based upon the inode, to keep the +inode number by xino (see above) is essentially necessary. + +All the hardlinks under the Pseudo-link Directory of the writable branch +should be restored in a proper location later. Aufs provides a utility +to do this. The userspace helpers executed at remounting and unmounting +aufs by default. +During this utility is running, it puts aufs into the pseudo-link +maintenance mode. In this mode, only the process which began the +maintenance mode (and its child processes) is allowed to operate in +aufs. Some other processes which are not related to the pseudo-link will +be allowed to run too, but the rest have to return an error or wait +until the maintenance mode ends. If a process already acquires an inode +mutex (in VFS), it has to return an error. + + +XIB(external inode number bitmap) +---------------------------------------------------------------------- +Addition to the xino file per a branch, aufs has an external inode number +bitmap in a superblock object. It is also an internal file such like a +xino file. +It is a simple bitmap to mark whether the aufs inode number is in-use or +not. +To reduce the file I/O, aufs prepares a single memory page to cache xib. + +As well as XINO files, aufs has a feature to truncate/refresh XIB to +reduce the number of consumed disk blocks for these files. + + +Virtual or Vertical Dir, and Readdir in Userspace +---------------------------------------------------------------------- +In order to support multiple layers (branches), aufs readdir operation +constructs a virtual dir block on memory. For readdir, aufs calls +vfs_readdir() internally for each dir on branches, merges their entries +with eliminating the whiteout-ed ones, and sets it to file (dir) +object. So the file object has its entry list until it is closed. The +entry list will be updated when the file position is zero and becomes +obsoleted. This decision is made in aufs automatically. + +The dynamically allocated memory block for the name of entries has a +unit of 512 bytes (by default) and stores the names contiguously (no +padding). Another block for each entry is handled by kmem_cache too. +During building dir blocks, aufs creates hash list and judging whether +the entry is whiteouted by its upper branch or already listed. +The merged result is cached in the corresponding inode object and +maintained by a customizable life-time option. + +Some people may call it can be a security hole or invite DoS attack +since the opened and once readdir-ed dir (file object) holds its entry +list and becomes a pressure for system memory. But I'd say it is similar +to files under /proc or /sys. The virtual files in them also holds a +memory page (generally) while they are opened. When an idea to reduce +memory for them is introduced, it will be applied to aufs too. +For those who really hate this situation, I've developed readdir(3) +library which operates this merging in userspace. You just need to set +LD_PRELOAD environment variable, and aufs will not consume no memory in +kernel space for readdir(3). + + +Workqueue +---------------------------------------------------------------------- +Aufs sometimes requires privilege access to a branch. For instance, +in copy-up/down operation. When a user process is going to make changes +to a file which exists in the lower readonly branch only, and the mode +of one of ancestor directories may not be writable by a user +process. Here aufs copy-up the file with its ancestors and they may +require privilege to set its owner/group/mode/etc. +This is a typical case of a application character of aufs (see +Introduction). + +Aufs uses workqueue synchronously for this case. It creates its own +workqueue. The workqueue is a kernel thread and has privilege. Aufs +passes the request to call mkdir or write (for example), and wait for +its completion. This approach solves a problem of a signal handler +simply. +If aufs didn't adopt the workqueue and changed the privilege of the +process, then the process may receive the unexpected SIGXFSZ or other +signals. + +Also aufs uses the system global workqueue ("events" kernel thread) too +for asynchronous tasks, such like handling inotify/fsnotify, re-creating a +whiteout base and etc. This is unrelated to a privilege. +Most of aufs operation tries acquiring a rw_semaphore for aufs +superblock at the beginning, at the same time waits for the completion +of all queued asynchronous tasks. + + +Whiteout +---------------------------------------------------------------------- +The whiteout in aufs is very similar to Unionfs's. That is represented +by its filename. UnionMount takes an approach of a file mode, but I am +afraid several utilities (find(1) or something) will have to support it. + +Basically the whiteout represents "logical deletion" which stops aufs to +lookup further, but also it represents "dir is opaque" which also stop +further lookup. + +In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively. +In order to make several functions in a single systemcall to be +revertible, aufs adopts an approach to rename a directory to a temporary +unique whiteouted name. +For example, in rename(2) dir where the target dir already existed, aufs +renames the target dir to a temporary unique whiteouted name before the +actual rename on a branch, and then handles other actions (make it opaque, +update the attributes, etc). If an error happens in these actions, aufs +simply renames the whiteouted name back and returns an error. If all are +succeeded, aufs registers a function to remove the whiteouted unique +temporary name completely and asynchronously to the system global +workqueue. + + +Copy-up +---------------------------------------------------------------------- +It is a well-known feature or concept. +When user modifies a file on a readonly branch, aufs operate "copy-up" +internally and makes change to the new file on the upper writable branch. +When the trigger systemcall does not update the timestamps of the parent +dir, aufs reverts it after copy-up. + + +Move-down (aufs3.9 and later) +---------------------------------------------------------------------- +"Copy-up" is one of the essential feature in aufs. It copies a file from +the lower readonly branch to the upper writable branch when a user +changes something about the file. +"Move-down" is an opposite action of copy-up. Basically this action is +ran manually instead of automatically and internally. +For desgin and implementation, aufs has to consider these issues. +- whiteout for the file may exist on the lower branch. +- ancestor directories may not exist on the lower branch. +- diropq for the ancestor directories may exist on the upper branch. +- free space on the lower branch will reduce. +- another access to the file may happen during moving-down, including + UDBA (see "Revalidate Dentry and UDBA"). +- the file should not be hard-linked nor pseudo-linked. they should be + handled by auplink utility later. + +Sometimes users want to move-down a file from the upper writable branch +to the lower readonly or writable branch. For instance, +- the free space of the upper writable branch is going to run out. +- create a new intermediate branch between the upper and lower branch. +- etc. + +For this purpose, use "aumvdown" command in aufs-util.git. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/03atomic_open.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/03atomic_open.txt @@ -0,0 +1,85 @@ + +# Copyright (C) 2015-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Support for a branch who has its ->atomic_open() +---------------------------------------------------------------------- +The filesystems who implement its ->atomic_open() are not majority. For +example NFSv4 does, and aufs should call NFSv4 ->atomic_open, +particularly for open(O_CREAT|O_EXCL, 0400) case. Other than +->atomic_open(), NFSv4 returns an error for this open(2). While I am not +sure whether all filesystems who have ->atomic_open() behave like this, +but NFSv4 surely returns the error. + +In order to support ->atomic_open() for aufs, there are a few +approaches. + +A. Introduce aufs_atomic_open() + - calls one of VFS:do_last(), lookup_open() or atomic_open() for + branch fs. +B. Introduce aufs_atomic_open() calling create, open and chmod. this is + an aufs user Pip Cet's approach + - calls aufs_create(), VFS finish_open() and notify_change(). + - pass fake-mode to finish_open(), and then correct the mode by + notify_change(). +C. Extend aufs_open() to call branch fs's ->atomic_open() + - no aufs_atomic_open(). + - aufs_lookup() registers the TID to an aufs internal object. + - aufs_create() does nothing when the matching TID is registered, but + registers the mode. + - aufs_open() calls branch fs's ->atomic_open() when the matching + TID is registered. +D. Extend aufs_open() to re-try branch fs's ->open() with superuser's + credential + - no aufs_atomic_open(). + - aufs_create() registers the TID to an internal object. this info + represents "this process created this file just now." + - when aufs gets EACCES from branch fs's ->open(), then confirm the + registered TID and re-try open() with superuser's credential. + +Pros and cons for each approach. + +A. + - straightforward but highly depends upon VFS internal. + - the atomic behavaiour is kept. + - some of parameters such as nameidata are hard to reproduce for + branch fs. + - large overhead. +B. + - easy to implement. + - the atomic behavaiour is lost. +C. + - the atomic behavaiour is kept. + - dirty and tricky. + - VFS checks whether the file is created correctly after calling + ->create(), which means this approach doesn't work. +D. + - easy to implement. + - the atomic behavaiour is lost. + - to open a file with superuser's credential and give it to a user + process is a bad idea, since the file object keeps the credential + in it. It may affect LSM or something. This approach doesn't work + either. + +The approach A is ideal, but it hard to implement. So here is a +variation of A, which is to be implemented. + +A-1. Introduce aufs_atomic_open() + - calls branch fs ->atomic_open() if exists. otherwise calls + vfs_create() and finish_open(). + - the demerit is that the several checks after branch fs + ->atomic_open() are lost. in the ordinary case, the checks are + done by VFS:do_last(), lookup_open() and atomic_open(). some can + be implemented in aufs, but not all I am afraid. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/03lookup.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/03lookup.txt @@ -0,0 +1,113 @@ + +# Copyright (C) 2005-2017 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 . + +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). --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/04branch.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/04branch.txt @@ -0,0 +1,74 @@ + +# Copyright (C) 2005-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Branch Manipulation + +Since aufs supports dynamic branch manipulation, ie. add/remove a branch +and changing its permission/attribute, there are a lot of works to do. + + +Add a Branch +---------------------------------------------------------------------- +o Confirm the adding dir exists outside of aufs, including loopback + mount, and its various attributes. +o Initialize the xino file and whiteout bases if necessary. + See struct.txt. + +o Check the owner/group/mode of the directory + When the owner/group/mode of the adding directory differs from the + existing branch, aufs issues a warning because it may impose a + security risk. + For example, when a upper writable branch has a world writable empty + top directory, a malicious user can create any files on the writable + branch directly, like copy-up and modify manually. If something like + /etc/{passwd,shadow} exists on the lower readonly branch but the upper + writable branch, and the writable branch is world-writable, then a + malicious guy may create /etc/passwd on the writable branch directly + and the infected file will be valid in aufs. + I am afraid it can be a security issue, but aufs can do nothing except + producing a warning. + + +Delete a Branch +---------------------------------------------------------------------- +o Confirm the deleting branch is not busy + To be general, there is one merit to adopt "remount" interface to + manipulate branches. It is to discard caches. At deleting a branch, + aufs checks the still cached (and connected) dentries and inodes. If + there are any, then they are all in-use. An inode without its + corresponding dentry can be alive alone (for example, inotify/fsnotify case). + + For the cached one, aufs checks whether the same named entry exists on + other branches. + If the cached one is a directory, because aufs provides a merged view + to users, as long as one dir is left on any branch aufs can show the + dir to users. In this case, the branch can be removed from aufs. + Otherwise aufs rejects deleting the branch. + + If any file on the deleting branch is opened by aufs, then aufs + rejects deleting. + + +Modify the Permission of a Branch +---------------------------------------------------------------------- +o Re-initialize or remove the xino file and whiteout bases if necessary. + See struct.txt. + +o rw --> ro: Confirm the modifying branch is not busy + Aufs rejects the request if any of these conditions are true. + - a file on the branch is mmap-ed. + - a regular file on the branch is opened for write and there is no + same named entry on the upper branch. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/05wbr_policy.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/05wbr_policy.txt @@ -0,0 +1,64 @@ + +# Copyright (C) 2005-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Policies to Select One among Multiple Writable Branches +---------------------------------------------------------------------- +When the number of writable branch is more than one, aufs has to decide +the target branch for file creation or copy-up. By default, the highest +writable branch which has the parent (or ancestor) dir of the target +file is chosen (top-down-parent policy). +By user's request, aufs implements some other policies to select the +writable branch, for file creation several policies, round-robin, +most-free-space, and other policies. For copy-up, top-down-parent, +bottom-up-parent, bottom-up and others. + +As expected, the round-robin policy selects the branch in circular. When +you have two writable branches and creates 10 new files, 5 files will be +created for each branch. mkdir(2) systemcall is an exception. When you +create 10 new directories, all will be created on the same branch. +And the most-free-space policy selects the one which has most free +space among the writable branches. The amount of free space will be +checked by aufs internally, and users can specify its time interval. + +The policies for copy-up is more simple, +top-down-parent is equivalent to the same named on in create policy, +bottom-up-parent selects the writable branch where the parent dir +exists and the nearest upper one from the copyup-source, +bottom-up selects the nearest upper writable branch from the +copyup-source, regardless the existence of the parent dir. + +There are some rules or exceptions to apply these policies. +- If there is a readonly branch above the policy-selected branch and + the parent dir is marked as opaque (a variation of whiteout), or the + target (creating) file is whiteout-ed on the upper readonly branch, + then the result of the policy is ignored and the target file will be + created on the nearest upper writable branch than the readonly branch. +- If there is a writable branch above the policy-selected branch and + the parent dir is marked as opaque or the target file is whiteouted + on the branch, then the result of the policy is ignored and the target + file will be created on the highest one among the upper writable + branches who has diropq or whiteout. In case of whiteout, aufs removes + it as usual. +- link(2) and rename(2) systemcalls are exceptions in every policy. + They try selecting the branch where the source exists as possible + since copyup a large file will take long time. If it can't be, + ie. the branch where the source exists is readonly, then they will + follow the copyup policy. +- There is an exception for rename(2) when the target exists. + If the rename target exists, aufs compares the index of the branches + where the source and the target exists and selects the higher + one. If the selected branch is readonly, then aufs follows the + copyup policy. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/06dirren.dot +++ linux-4.14.0/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"]; +} --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/06dirren.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/06dirren.txt @@ -0,0 +1,102 @@ + +# Copyright (C) 2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +Special handling for renaming a directory (DIRREN) +---------------------------------------------------------------------- +First, let's assume we have a simple usecase. + +- /u = /rw + /ro +- /rw/dirA exists +- /ro/dirA and /ro/dirA/file exist too +- there is no dirB on both branches +- a user issues rename("dirA", "dirB") + +Now, what should aufs behave against this rename(2)? +There are a few possible cases. + +A. returns EROFS. + since dirA exists on a readonly branch which cannot be renamed. +B. returns EXDEV. + it is possible to copy-up dirA (only the dir itself), but the child + entries ("file" in this case) should not be. it must be a bad + approach to copy-up recursively. +C. returns a success. + even the branch /ro is readonly, aufs tries renaming it. Obviously it + is a violation of aufs' policy. +D. construct an extra information which indicates that /ro/dirA should + be handled as the name of dirB. + overlayfs has a similar feature called REDIRECT. + +Until now, aufs implements the case B only which returns EXDEV, and +expects the userspace application behaves like mv(1) which tries +issueing rename(2) recursively. + +A new aufs feature called DIRREN is introduced which implements the case +D. There are several "extra information" added. + +1. detailed info per renamed directory + path: /rw/dirB/$AUFS_WH_DR_INFO_PFX. +2. the inode-number list of directories on a branch + path: /rw/dirB/$AUFS_WH_DR_BRHINO + +The filename of "detailed info per directory" represents the lower +branch, and its format is +- a type of the branch id + one of these. + + uuid (not implemented yet) + + fsid + + dev +- the inode-number of the branch root dir + +And it contains these info in a single regular file. +- magic number +- branch's inode-number of the logically renamed dir +- the name of the before-renamed dir + +The "detailed info per directory" file is created in aufs rename(2), and +loaded in any lookup. +The info is considered in lookup for the matching case only. Here +"matching" means that the root of branch (in the info filename) is same +to the current looking-up branch. After looking-up the before-renamed +name, the inode-number is compared. And the matched dentry is used. + +The "inode-number list of directories" is a regular file which contains +simply the inode-numbers on the branch. The file is created or updated +in removing the branch, and loaded in adding the branch. Its lifetime is +equal to the branch. +The list is refered in lookup, and when the current target inode is +found in the list, the aufs tries loading the "detailed info per +directory" and get the changed and valid name of the dir. + +Theoretically these "extra informaiton" may be able to be put into XATTR +in the dir inode. But aufs doesn't choose this way because +1. XATTR may not be supported by the branch (or its configuration) +2. XATTR may have its size limit. +3. XATTR may be less easy to convert than a regular file, when the + format of the info is changed in the future. +At the same time, I agree that the regular file approach is much slower +than XATTR approach. So, in the future, aufs may take the XATTR or other +better approach. + +This DIRREN feature is enabled by aufs configuration, and is activated +by a new mount option. + +For the more complicated case, there is a work with UDBA option, which +is to dected the direct access to the branches (by-passing aufs) and to +maintain the cashes in aufs. Since a single cached aufs dentry may +contains two names, before- and after-rename, the name comparision in +UDBA handler may not work correctly. In this case, the behaviour will be +equivalen to udba=reval case. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/06fhsm.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/06fhsm.txt @@ -0,0 +1,120 @@ + +# Copyright (C) 2011-2017 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. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/06mmap.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/06mmap.txt @@ -0,0 +1,72 @@ + +# Copyright (C) 2005-2017 Junjiro R. Okajima +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see . + +mmap(2) -- File Memory Mapping +---------------------------------------------------------------------- +In aufs, the file-mapped pages are handled by a branch fs directly, no +interaction with aufs. It means aufs_mmap() calls the branch fs's +->mmap(). +This approach is simple and good, but there is one problem. +Under /proc, several entries show the mmapped files by its path (with +device and inode number), and the printed path will be the path on the +branch fs's instead of virtual aufs's. +This is not a problem in most cases, but some utilities lsof(1) (and its +user) may expect the path on aufs. + +To address this issue, aufs adds a new member called vm_prfile in struct +vm_area_struct (and struct vm_region). The original vm_file points to +the file on the branch fs in order to handle everything correctly as +usual. The new vm_prfile points to a virtual file in aufs, and the +show-functions in procfs refers to vm_prfile if it is set. +Also we need to maintain several other places where touching vm_file +such like +- fork()/clone() copies vma and the reference count of vm_file is + incremented. +- merging vma maintains the ref count too. + +This is not a good approach. It just fakes the printed path. But it +leaves all behaviour around f_mapping unchanged. This is surely an +advantage. +Actually aufs had adopted another complicated approach which calls +generic_file_mmap() and handles struct vm_operations_struct. In this +approach, aufs met a hard problem and I could not solve it without +switching the approach. + +There may be one more another approach which is +- bind-mount the branch-root onto the aufs-root internally +- grab the new vfsmount (ie. struct mount) +- lazy-umount the branch-root internally +- in open(2) the aufs-file, open the branch-file with the hidden + vfsmount (instead of the original branch's vfsmount) +- ideally this "bind-mount and lazy-umount" should be done atomically, + but it may be possible from userspace by the mount helper. + +Adding the internal hidden vfsmount and using it in opening a file, the +file path under /proc will be printed correctly. This approach looks +smarter, but is not possible I am afraid. +- aufs-root may be bind-mount later. when it happens, another hidden + vfsmount will be required. +- it is hard to get the chance to bind-mount and lazy-umount + + in kernel-space, FS can have vfsmount in open(2) via + file->f_path, and aufs can know its vfsmount. But several locks are + already acquired, and if aufs tries to bind-mount and lazy-umount + here, then it may cause a deadlock. + + in user-space, bind-mount doesn't invoke the mount helper. +- since /proc shows dev and ino, aufs has to give vma these info. it + means a new member vm_prinode will be necessary. this is essentially + equivalent to vm_prfile described above. + +I have to give up this "looks-smater" approach. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/06xattr.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/06xattr.txt @@ -0,0 +1,96 @@ + +# Copyright (C) 2014-2017 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. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/07export.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/07export.txt @@ -0,0 +1,58 @@ + +# Copyright (C) 2005-2017 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 . + +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. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/08shwh.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/08shwh.txt @@ -0,0 +1,52 @@ + +# Copyright (C) 2005-2017 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 . + +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. --- linux-4.14.0.orig/Documentation/filesystems/aufs/design/10dynop.txt +++ linux-4.14.0/Documentation/filesystems/aufs/design/10dynop.txt @@ -0,0 +1,47 @@ + +# Copyright (C) 2010-2017 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 . + +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. --- linux-4.14.0.orig/Documentation/kmsg/IPVS +++ linux-4.14.0/Documentation/kmsg/IPVS @@ -0,0 +1,81 @@ +/*? Text: "%s(): NULL arg\n" */ +/*? Text: "%s(): NULL scheduler_name\n" */ +/*? Text: "%s(): [%s] pe already existed in the system\n" */ +/*? Text: "%s(): [%s] pe already linked\n" */ +/*? Text: "%s(): [%s] pe is not in the list. failed\n" */ +/*? Text: "%s(): [%s] scheduler already existed in the system\n" */ +/*? Text: "%s(): [%s] scheduler already linked\n" */ +/*? Text: "%s(): [%s] scheduler is not in the list. failed\n" */ +/*? Text: "%s(): done error\n" */ +/*? Text: "%s(): init error\n" */ +/*? Text: "%s(): lower threshold is higher than upper threshold\n" */ +/*? Text: "%s(): no memory\n" */ +/*? Text: "%s(): request for already hashed, called from %pF\n" */ +/*? Text: "%s(): request for unhash flagged, called from %pF\n" */ +/*? Text: "%s(): server weight less than zero\n" */ +/*? Text: "%s: %s %pI4:%d - %s\n" */ +/*? Text: "%s: %s [%pI6]:%d - %s\n" */ +/*? Text: "%s: %s [%pI6c]:%d - %s\n" */ +/*? Text: "%s: FWM %u 0x%08X - %s\n" */ +/*? Text: "%s: enter\n" */ +/*? Text: "%s: loaded support on port[%d] = %d\n" */ +/*? Text: "BACKUP v0, Dropping buffer bogus conn options\n" */ +/*? Text: "BACKUP v0, bogus conn\n" */ +/*? Text: "BACKUP, Dropping buffer, Err: %d in decoding\n" */ +/*? Text: "BACKUP, Dropping buffer, Unknown version %d\n" */ +/*? Text: "BACKUP, Dropping buffer, msg > buffer\n" */ +/*? Text: "BACKUP, Dropping buffer, to small\n" */ +/*? Text: "BACKUP, Invalid PE parameters\n" */ +/*? Text: "BUG control DEL with n=0 : %s:%d to %s:%d\n" */ +/*? Text: "Connection hash table configured (size=%d, memory=%ldKbytes)\n" */ +/*? Text: "Error binding address of the mcast interface\n" */ +/*? Text: "Error binding to the multicast addr\n" */ +/*? Text: "Error connecting to the multicast addr\n" */ +/*? Text: "Error during creation of socket; terminating\n" */ +/*? Text: "Error joining to the multicast group\n" */ +/*? Text: "Error setting outbound mcast interface\n" */ +/*? Text: "Failed to stop Backup Daemon\n" */ +/*? Text: "Failed to stop Master Daemon\n" */ +/*? Text: "Registered protocols (%s)\n" */ +/*? Text: "SYNC, connection pe_data invalid\n" */ +/*? Text: "Schedule: port zero only supported in persistent services, check your ipvs configuration\n" */ +/*? Text: "Scheduler module ip_vs_%s not found\n" */ +/*? Text: "There is no net ptr to find in the skb in %s() line:%d\n" */ +/*? Text: "UDP no ns data\n" */ +/*? Text: "You probably need to specify IP address on multicast interface.\n" */ +/*? Text: "[%s] pe registered.\n" */ +/*? Text: "[%s] pe unregistered.\n" */ +/*? Text: "[%s] scheduler registered.\n" */ +/*? Text: "[%s] scheduler unregistered.\n" */ +/*? Text: "can't register hooks.\n" */ +/*? Text: "can't register netlink/ioctl.\n" */ +/*? Text: "can't setup connection table.\n" */ +/*? Text: "can't setup control.\n" */ +/*? Text: "cannot register Generic Netlink interface.\n" */ +/*? Text: "cannot register sockopt.\n" */ +/*? Text: "get_ctl: len %u < %u\n" */ +/*? Text: "ip_vs_send_async error %d\n" */ +/*? Text: "ip_vs_sync_buff_create failed.\n" */ +/*? Text: "ipvs loaded.\n" */ +/*? Text: "ipvs unloaded.\n" */ +/*? Text: "length: %u != %u\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "not enough space in Netlink message\n" */ +/*? Text: "persistence engine module ip_vs_pe_%s not found\n" */ +/*? Text: "receiving message error\n" */ +/*? Text: "request control ADD for already controlled: %s:%d to %s:%d\n" */ +/*? Text: "request control DEL for uncontrolled: %s:%d to %s:%d\n" */ +/*? Text: "set_ctl: invalid protocol: %d %pI4:%d %s\n" */ +/*? Text: "set_ctl: len %u != %u\n" */ +/*? Text: "shouldn't reach here, because the box is on the half connection in the tun/dr module.\n" */ +/*? Text: "stopping backup sync thread %d ...\n" */ +/*? Text: "stopping master sync thread %d ...\n" */ +/*? Text: "sync thread started: state = BACKUP, mcast_ifn = %s, syncid = %d\n" */ +/*? Text: "sync thread started: state = MASTER, mcast_ifn = %s, syncid = %d\n" */ +/*? Text: "unknown Generic Netlink command\n" */ +/*? Text: "sync thread started: state = MASTER, mcast_ifn = %s, syncid = %d, id = %d\n" */ +/*? Text: "sync thread started: state = BACKUP, mcast_ifn = %s, syncid = %d, id = %d\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "Unknown mcast interface: %s\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/aes_s390 +++ linux-4.14.0/Documentation/kmsg/s390/aes_s390 @@ -0,0 +1,45 @@ +/*? + * Text: "Allocating XTS fallback algorithm %s failed\n" + * Severity: Error + * Parameter: + * @1: algorithm name + * Description: + * The aes_s390 module failed to allocate a software fallback for the AES + * modes that are not supported by the hardware. A possible reason for this + * problem is that the aes_generic module that provides the fallback + * algorithms is not available. + * User action: + * Ensure that the aes_generic module is available and loaded and reload + * the aes_s390 module. + */ + +/*? + * Text: "Allocating AES fallback algorithm %s failed\n" + * Severity: Error + * Parameter: + * @1: algorithm name + * Description: + * The advanced encryption standard (AES) algorithm includes three modes with + * 128-bit, 192-bit, and 256-bit keys. Your hardware system only provides + * hardware acceleration for the 128-bit mode. The aes_s390 module failed to + * allocate a software fallback for the AES modes that are not supported by the + * hardware. A possible reason for this problem is that the aes_generic module + * that provides the fallback algorithms is not available. + * User action: + * Use the 128-bit mode only or ensure that the aes_generic module is available + * and loaded and reload the aes_s390 module. + */ + +/*? + * Text: "AES hardware acceleration is only available for 128-bit keys\n" + * Severity: Informational + * Description: + * The advanced encryption standard (AES) algorithm includes three modes with + * 128-bit, 192-bit, and 256-bit keys. Your hardware system only provides + * hardware acceleration for the 128-bit key mode. The aes_s390 module + * will use the less performant software fallback algorithm for the 192-bit + * and 256-bit key modes. + * User action: + * None. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/af_iucv +++ linux-4.14.0/Documentation/kmsg/s390/af_iucv @@ -0,0 +1,23 @@ +/*? + * Text: "Application %s on z/VM guest %s exceeds message limit\n" + * Severity: Error + * Parameter: + * @1: application name + * @2: z/VM user ID + * Description: + * Messages or packets destined for the application have accumulated and + * reached the maximum value. The default for the message limit is 65535. + * You can specify a different limit as the value for MSGLIMIT within + * the IUCV statement of the z/VM virtual machine on which the application + * runs. + * User action: + * Ensure that you do not send data faster than the application retrieves + * them. Ensure that the message limit on the z/VM guest virtual machine + * on which the application runs is high enough. + */ + +/*? Text: "Attempt to release alive iucv socket %p\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/ap +++ linux-4.14.0/Documentation/kmsg/s390/ap @@ -0,0 +1,49 @@ +/*? + * Text: "%d is not a valid cryptographic domain\n" + * Severity: Warning + * Parameter: + * @1: AP domain index + * Description: + * The cryptographic domain specified for the 'domain=' module or kernel + * parameter must be an integer in the range 0 to 15. + * User action: + * Reload the cryptographic device driver with a correct module parameter. + * If the device driver has been compiled into the kernel, correct the value + * in the kernel parameter line and reboot Linux. + */ + +/*? + * Text: "The hardware system does not support AP instructions\n" + * Severity: Warning + * Description: + * The ap module addresses AP adapters through AP instructions. The hardware + * system on which the Linux instance runs does not support AP instructions. + * The ap module cannot detect any AP adapters. + * User action: + * Load the ap module only if your Linux instance runs on hardware that + * supports AP instructions. If the ap module has been compiled into the kernel, + * ignore this message. + */ + +/*? + * Text: "Registering adapter interrupts for AP device %02x.%04x failed\n" + * Severity: Error + * Parameter: + * @1: AP device ID + * @2: AP queue + * Description: + * The hardware system supports AP adapter interrupts but failed to enable + * an adapter for interrupts. Possible causes for this error are: + * i) The AP adapter firmware does not support AP interrupts. + * ii) An AP adapter firmware update to a firmware level that supports AP + * adapter interrupts failed. + * iii) The AP adapter firmware has been successfully updated to a level that + * supports AP interrupts but the new firmware has not been activated. + * User action: + * Ensure that the firmware on your AP adapters support AP interrupts and that + * any firmware updates have completed successfully. If necessary, deconfigure + * your cryptographic adapters and reconfigure them to ensure that any firmware + * updates become active, then reload the ap module. If the ap module has been + * compiled into the kernel, reboot Linux. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/appldata +++ linux-4.14.0/Documentation/kmsg/s390/appldata @@ -0,0 +1,91 @@ +/*? + * Text: "Starting the data collection for %s failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: appldata module + * @2: return code + * Description: + * The specified data collection module used the z/VM diagnose call + * DIAG 0xDC to start writing data. z/VM returned an error and the data + * collection could not start. If the return code is 5, your z/VM guest + * virtual machine is not authorized to write data records. + * User action: + * If the return code is 5, ensure that your z/VM guest virtual machine's + * entry in the z/VM directory includes the OPTION APPLMON statement. + * For other return codes see the section about DIAGNOSE Code X'DC' + * in "z/VM CP Programming Services". + */ + +/*? + * Text: "Stopping the data collection for %s failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: appldata module + * @2: return code + * Description: + * The specified data collection module used the z/VM diagnose call DIAG 0xDC + * to stop writing data. z/VM returned an error and the data collection + * continues. + * User action: + * See the section about DIAGNOSE Code X'DC' in "z/VM CP Programming Services". + */ + +/*? + * Text: "Starting a new OS data collection failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * After a CPU hotplug event, the record size for the running operating + * system data collection is no longer correct. The appldata_os module tried + * to start a new data collection with the correct record size but received + * an error from the z/VM diagnose call DIAG 0xDC. Any data collected with + * the current record size might be faulty. + * User action: + * Start a new data collection with the cappldata_os module. For information + * about starting data collections see "Device Drivers, Features, and + * Commands". For information about the return codes see the section about + * DIAGNOSE Code X'DC' in "z/VM CP Programming Services". + */ + +/*? + * Text: "Stopping a faulty OS data collection failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * After a CPU hotplug event, the record size for the running operating + * system data collection is no longer correct. The appldata_os module tried + * to stop the faulty data collection but received an error from the z/VM + * diagnose call DIAG 0xDC. Any data collected with the current record size + * might be faulty. + * User action: + * Try to restart appldata_os monitoring. For information about stopping + * and starting data collections see "Device Drivers, Features, and + * Commands". For information about the return codes see the section about + * DIAGNOSE Code X'DC' in "z/VM CP Programming Services". + */ + +/*? + * Text: "Maximum OS record size %i exceeds the maximum record size %i\n" + * Severity: Error + * Parameter: + * @1: no of bytes + * @2: no of bytes + * Description: + * The OS record size grows with the number of CPUs and is adjusted by the + * appldata_os module in response to CPU hotplug events. For more than 110 + * CPUs the record size would exceed the maximum record size of 4024 bytes + * that is supported by the z/VM hypervisor. To prevent the maximum supported + * record size from being exceeded while data collection is in progress, + * you cannot load the appldata_os module on Linux instances that are + * configured for a maximum of more than 110 CPUs. + * User action: + * If you do not want to collect operating system data, you can ignore this + * message. If you want to collect operating system data, reconfigure your + * Linux instance to support less than 110 CPUs. + */ + +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/bpf_jit +++ linux-4.14.0/Documentation/kmsg/s390/bpf_jit @@ -0,0 +1,16 @@ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ + +/*? + * Text: "Unknown opcode %02x\n" + * Severity: Error + * Parameter: + * @1: Instruction opcode + * Description: + * The BPF JIT compiler has found an unknown instruction in the BPF program + * and therefore stops the compilation. As a fallback, the interpreter is used. + * User action: + * Report this problem and the error message to your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/cio +++ linux-4.14.0/Documentation/kmsg/s390/cio @@ -0,0 +1,247 @@ +/*? + * Text: "%s is not a valid device for the cio_ignore kernel parameter\n" + * Severity: Warning + * Parameter: + * @1: device bus-ID + * Description: + * The device specification for the cio_ignore kernel parameter is + * syntactically incorrect or specifies an unknown device. This device is not + * excluded from being sensed and analyzed. + * User action: + * Correct your device specification in the kernel parameter line to have the + * device excluded when you next reboot Linux. You can write the correct + * device specification to /proc/cio_ignore to add the device to the list of + * devices to be excluded. This does not immediately make the device + * inaccessible but the device is ignored if it disappears and later reappears. + */ + +/*? + * Text: "0.%x.%04x to 0.%x.%04x is not a valid range for cio_ignore\n" + * Severity: Warning + * Parameter: + * @1: from subchannel set ID + * @2: from device number + * @3: to subchannel set ID + * @4: to device number + * Description: + * The device range specified for the cio_ignore kernel parameter is + * syntactically incorrect. No devices specified with this range are + * excluded from being sensed and analyzed. + * User action: + * Correct your range specification in the kernel parameter line to have the + * range of devices excluded when you next reboot Linux. You can write the + * correct range specification to /proc/cio_ignore to add the range of devices + * to the list of devices to be excluded. This does not immediately make the + * devices in the range inaccessible but any of these devices are ignored if + * they disappear and later reappear. + */ + +/*? + * Text: "Processing %s for channel path %x.%02x\n" + * Severity: Notice + * Parameter: + * @1: configuration change + * @2: channel subsystem ID + * @3: CHPID + * Description: + * A configuration change is in progress for the given channel path. + * User action: + * None. + */ + +/*? + * Text: "No CCW console was found\n" + * Severity: Warning + * Description: + * Linux did not find the expected CCW console and tries to use an alternative + * console. A possible reason why the console was not found is that the console + * has been specified in the cio_ignore list. + * User action: + * None, if an appropriate alternative console has been found, and you want + * to use this alternative console. If you want to use the CCW console, ensure + * that is not specified in the cio_ignore list, explicitly specify the console + * with the 'condev=' kernel parameter, and reboot Linux. + */ + +/*? + * Text: "Channel measurement facility initialized using format %s (mode %s)\n" + * Severity: Informational + * Parameter: + * @1: format + * @2: mode + * Description: + * The channel measurement facility has been initialized successfully. + * Format 'extended' should be used for z990 and later mainframe systems. + * Format 'basic' is intended for earlier mainframes. Mode 'autodetected' means + * that the format has been set automatically. Mode 'parameter' means that the + * format has been set according to the 'format=' kernel parameter. + * User action: + * None. + */ + +/*? + * Text: "The CSS device driver initialization failed with errno=%d\n" + * Severity: Alert + * Parameter: + * @1: Return code + * Description: + * The channel subsystem bus could not be established. + * User action: + * See the errno man page to find out what caused the problem. + */ + /*? Text: "%s: Got subchannel machine check but no sch_event handler provided.\n" */ + +/*? + * Text: "%s: Setting the device online failed because it is boxed\n" + * Severity: Warning + * Parameter: + * @1: Device bus-ID + * Description: + * Initialization of a device did not complete because it did not respond in + * time or it was reserved by another operating system. + * User action: + * Make sure that the device is working correctly, then try again to set it + * online. For devices that support the reserve/release mechanism (for example + * DASDs), you can try to override the reservation of the other system by + * writing 'force' to the 'online' sysfs attribute of the affected device. + */ + +/*? + * Text: "%s: Setting the device online failed because it is not operational\n" + * Severity: Warning + * Parameter: + * @1: Device bus-ID + * Description: + * Initialization of a device did not complete because it is not present or + * not operational. + * User action: + * Make sure that the device is present and working correctly, then try again + * to set it online. + */ + +/*? + * Text: "%s: The device stopped operating while being set offline\n" + * Severity: Warning + * Parameter: + * @1: Device bus-ID + * Description: + * While the device was set offline, it was not present or not operational. + * The device is now inactive, but setting it online again might fail. + * User action: + * None. + */ + +/*? + * Text: "%s: The device entered boxed state while being set offline\n" + * Severity: Warning + * Parameter: + * @1: Device bus-ID + * Description: + * While the device was set offline, it did not respond in time or it was + * reserved by another operating system. The device is now inactive, but + * setting it online again might fail. + * User action: + * None. + */ + +/*? + * Text: "Logging for subchannel 0.%x.%04x failed with errno=%d\n" + * Severity: Warning + * Parameter: + * @1: subchannel set ID + * @2: subchannel number + * @3: errno + * Description: + * Capturing model-dependent logs and traces could not be triggered for the + * specified subchannel. + * User action: + * See the errno man page to find out what caused the problem. + */ + +/*? + * Text: "Logging for subchannel 0.%x.%04x was triggered\n" + * Severity: Notice + * Parameter: + * @1: subchannel set ID + * @2: subchannel number + * Description: + * Model-dependent logs and traces may be captured for the specified + * subchannel. + * User action: + * None. + */ + +/*? + * Text: "%s: No interrupt was received within %lus (CS=%02x, DS=%02x, CHPID=%x.%02x)\n" + * Severity: Warning + * Parameter: + * @1: device number + * @2: timeout value + * @3: channel status + * @4: device status + * @5: channel subsystem ID + * @6: CHPID + * Description: + * Internal I/Os are used by the common I/O layer to ensure that devices are + * operational and accessible. + * The common I/O layer did not receive an interrupt for an internal I/O + * during the specified timeout period. + * As a result, the device might assume a state that makes the device + * unusable to Linux until the problem is resolved. + * User action: + * Make sure that the device is working correctly and try the action again. + */ + +/*? + * Text: "Link stopped: RS=%02x RSID=%04x IC=%02x IUPARAMS=%s IUNODEID=%s AUPARAMS=%s AUNODEID=%s\n" + * Severity: Error + * Parameter: + * @1: reporting source + * @2: reporting source ID + * @3: incident code + * @4: incident unit parameters + * @5: incident unit node ID + * @6: attached unit parameters + * @7: attached unit node ID + * + * Description: + * A hardware error has occurred. A unit at one end of an interface + * link has detected a failure in the link or in one of the units attached to + * the link. As a result, data transfer across the link has stopped. In the + * message text, the node IDs of involved units are represented in the + * following format: TTTTTT/MDL,MMM.PPSSSSSSSSSSSS,XXXX where TTTTTT refers to + * the machine type, MDL the model number, MMM the manufacturer, PP the + * manufacturing plant, SSSSSSSSSSSS the unit sequence number and XXXX the + * machine type-dependent physical interface number. If no data is available + * for the unit parameters or node ID field, "n/a" is used instead. + * + * User action: + * Report the problem to your support organization. + */ + +/*? + * Text: "Link degraded: RS=%02x RSID=%04x IC=%02x IUPARAMS=%s IUNODEID=%s AUPARAMS=%s AUNODEID=%s\n" + * Severity: Warning + * Parameter: + * @1: reporting source + * @2: reporting source ID + * @3: incident code + * @4: incident unit parameters + * @5: incident unit node ID + * @6: attached unit parameters + * @7: attached unit node ID + * Description: + * A hardware error has occurred. A unit at one end of an interface + * link has detected a failure in the link or in one of the units attached to + * the link. As a result, data transfer across the link is degraded. In the + * message text, the node IDs of involved units are represented in the + * following format: TTTTTT/MDL,MMM.PPSSSSSSSSSSSS,XXXX where TTTTTT refers to + * the machine type, MDL the model number, MMM the manufacturer, PP the + * manufacturing plant, SSSSSSSSSSSS the unit sequence number and XXXX the + * machine type-dependent physical interface number. If no data is available + * for the unit parameters or node ID field, "n/a" is used instead. + * + * User action: + * Report the problem to your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/cpcmd +++ linux-4.14.0/Documentation/kmsg/s390/cpcmd @@ -0,0 +1,16 @@ +/*? + * Text: "The cpcmd kernel function failed to allocate a response buffer\n" + * Severity: Warning + * Description: + * IPL code, console detection, and device drivers like vmcp or vmlogrdr use + * the cpcmd kernel function to send commands to the z/VM control program (CP). + * If a program that uses the cpcmd function does not allocate a contiguous + * response buffer below 2 GB guest real storage, cpcmd creates a bounce buffer + * to be used as the response buffer. Because of low memory or memory + * fragmentation, cpcmd could not create the bounce buffer. + * User action: + * Look for related page allocation failure messages and at the stack trace to + * find out which program or operation failed. Free some memory and retry the + * failed operation. Consider allocating more memory to your z/VM guest virtual + * machine. + */ --- linux-4.14.0.orig/Documentation/kmsg/s390/cpu +++ linux-4.14.0/Documentation/kmsg/s390/cpu @@ -0,0 +1,46 @@ +/*? + * Text: "%d configured CPUs, %d standby CPUs\n" + * Severity: Informational + * Parameter: + * @1: number of configured CPUs + * @2: number of standby CPUs + * Description: + * The kernel detected the given number of configured and standby CPUs. + * User action: + * None. + */ + +/*? + * Text: "The CPU configuration topology of the machine is:" + * Severity: Informational + * Description: + * The first six values of the topology information represent fields Mag6 to + * Mag1 of system-information block (SYSIB) 15.1.2. These fields specify the + * maximum numbers of topology-list entries (TLE) at successive topology nesting + * levels. The last value represents the MNest value of SYSIB 15.1.2 which + * specifies the maximum possible nesting that can be configured through + * dynamic changes. For details see the SYSIB 15.1.2 information in the + * "Principles of Operation." + * User action: + * None. + */ + +/*? + * Text: "CPU %i exceeds the maximum %i and is excluded from the dump\n" + * Severity: Warning + * Parameter: + * @1: CPU number + * @2: maximum CPU number + * Description: + * The Linux kernel is used as a system dumper but it runs on more CPUs than + * it has been compiled for with the CONFIG_NR_CPUS kernel configuration + * option. The system dump will be created but information on one or more + * CPUs will be missing. + * User action: + * Update the system dump kernel to a newer version that supports more + * CPUs or reduce the number of installed CPUs and reproduce the problem + * that should be analyzed. If you send the system dump that prompted this + * message to a support organization, be sure to communicate that the dump + * does not include all CPU information. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/cpum_cf +++ linux-4.14.0/Documentation/kmsg/s390/cpum_cf @@ -0,0 +1,68 @@ +/*? + * Text: "Enabling the performance measuring unit failed with rc=%x\n" + * Severity: Error + * Parameter: + * @1: error condition + * Description: + * The device driver failed to enable CPU counter sets with the + * load counter controls (lcctl) instruction. + * See the section about lcctl in "The Load-Program-Parameter and the CPU-Measurement + * Facilities", SA23-2260, for an explanation of the error conditions. + * User action: + * Stop the performance measurement programs and try again. + */ + +/*? + * Text: "Disabling the performance measuring unit failed with rc=%x\n" + * Severity: Error + * Parameter: + * @1: error condition + * Description: + * The device driver failed to disable CPU counter sets with the + * load counter controls (lcctl) instruction. + * See the section about lcctl in "The Load-Program-Parameter and the CPU-Measurement + * Facilities", SA23-2260, for an explanation of the error conditions. + * User action: + * Stop the performance measurement programs and try again. + */ + +/*? + * Text: "Registering the cpum_cf PMU failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: error code + * Description: + * The device driver could not register the Performance Measurement Unit (PMU) + * for the CPU-measurement counter facility. + * A possible cause of this problem is memory constraints. + * User action: + * If the error code is -12 (ENOMEM), consider assigning more memory + * to your Linux instance. + */ + +/*? + * Text: "CPU[%i] Counter data was lost\n" + * Severity: Error + * Parameter: + * @1: cpu number + * Description: + * CPU counter data was lost because of machine internal + * high-priority activities. + * User action: + * None. + */ + +/*? + * Text: "Registering for CPU-measurement alerts failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: error code + * Description: + * The device driver could not register to receive CPU-measurement alerts. + * Alerts make you aware of measurement errors. + * A possible cause of this problem is memory constraints. + * User action: + * If the error code is -12 (ENOMEM), consider assigning more memory + * to your Linux instance. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/cpum_sf +++ linux-4.14.0/Documentation/kmsg/s390/cpum_sf @@ -0,0 +1,104 @@ +/*? + * Text: "The sampling buffer limits have changed to: min=%lu max=%lu (diag=x%lu)\n" + * Severity: Informational + * Parameter: + * @1: minimum size in sample-data-blocks + * @2: maximum size in sample-data-blocks + * @3: size factor for buffering diagnostic-sampling data entries + * Description: + * The minimum or maximum size limit for the sampling facility buffer was + * changed. The change is effective immediately. + * User action: + * None. + */ + +/*? + * Text: "Switching off the sampling facility failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: error condition + * Description: + * The CPU-measurement sampling facility could not be switched off and continues + * to run. For details, see LOAD SAMPLING CONTROLS in + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * If this problem persists, reboot your Linux instance. + */ + +/*? + * Text: "Sample data was lost\n" + * Severity: Error + * Description: + * Sample data was lost because of machine-internal high-priority activities. + * The sampling facility is stopped. + * User action: + * End all performance measurement sessions. Discard the measurement data, + * which are likely to be flawed. Repeat your measurements. + * If the problem persists, contact your hardware administrator. + */ + +/*? + * Text: "Sampling facility support for perf is not available: reason=%04x\n" + * Severity: Error + * Parameter: + * @1: reason code + * Description: + * The device driver could not initialize the sampling facility support. + * Possible reason codes are: + * 0001: The device driver failed to query CPU-measurement sampling facility + * information. + * + * 0002: The device driver does not support the basic-sampling function that + * is available on the LPAR within which the Linux instance runs. + * + * 0003: The device driver could not register to receive CPU-measurement alerts. + * A possible cause of this problem is memory constraints. + * + * 0004: The device driver could not register the Performance Measurement Unit + * (PMU) for the CPU-measurement sampling facility. + * A possible cause of this problem is memory constraints. + * User action: + * Consider assigning more memory to your Linux instance. + */ + +/*? + * Text: "Loading sampling controls failed: op=%i err=%i\n" + * Severity: Error + * Parameter: + * @1: Type of operation + * @2: Error condition + * Description: + * The sampling facility support could not load sampling controls to enable + * (operation type 1) or disable (operation type 2) the CPU-measurement sampling + * facility. For details of the error condition, see LOAD SAMPLING CONTROLS in + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * If the problem persists, reboot your Linux instance. + */ + +/*? + * Text: "A sampling buffer entry is incorrect (alert=0x%x)\n" + * Severity: Error + * Parameter: + * @1: Alert code + * Description: + * An incorrect sampling facility buffer entry was detected. The alert code + * indicates the root cause, for example, an incorrect entry address or an + * incorrect sample-data-block-table entry. + * User action: + * End active performance measurement sessions, for example, perf processes. If + * the problem persists, reboot your Linux instance. + */ + +/*? + * Text: "Registering for s390dbf failed\n" + * Severity: Error + * Description: + * The device driver failed to register for the s390 debug feature. You will + * not receive any debug information. A possible cause of this problem is + * memory constraints. + * User action: + * Consider assigning more memory + * to your Linux instance. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/crc32-vx +++ linux-4.14.0/Documentation/kmsg/s390/crc32-vx @@ -0,0 +1 @@ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/ctcm +++ linux-4.14.0/Documentation/kmsg/s390/ctcm @@ -0,0 +1,202 @@ +/*? + * Text: "%s: An I/O-error occurred on the CTCM device\n" + * Severity: Error + * Parameter: + * @1: bus ID of the CTCM device + * Description: + * An I/O error was detected on one of the subchannels of the CTCM device. + * Depending on the error, the CTCM device driver might attempt an automatic + * recovery. + * User action: + * Check the status of the CTCM device, for example, with ifconfig. If the + * device is not operational, perform a manual recovery. See "Device Drivers, + * Features, and Commands" for details about how to recover a CTCM device. + */ + +/*? + * Text: "%s: An adapter hardware operation timed out\n" + * Severity: Error + * Parameter: + * @1: bus ID of the CTCM device + * Description: + * The CTCM device uses an adapter to physically connect to its communication + * peer. An operation on this adapter timed out. + * User action: + * Check the status of the CTCM device, for example, with ifconfig. If the + * device is not operational, perform a manual recovery. See "Device Drivers, + * Features, and Commands" for details about how to recover a CTCM device. + */ + +/*? + * Text: "%s: An error occurred on the adapter hardware\n" + * Severity: Error + * Parameter: + * @1: bus ID of the CTCM device + * Description: + * The CTCM device uses an adapter to physically connect to its communication + * peer. An operation on this adapter returned an error. + * User action: + * Check the status of the CTCM device, for example, with ifconfig. If the + * device is not operational, perform a manual recovery. See "Device Drivers, + * Features, and Commands" for details about how to recover a CTCM device. + */ + +/*? + * Text: "%s: The communication peer has disconnected\n" + * Severity: Notice + * Parameter: + * @1: channel ID + * Description: + * The remote device has disconnected. Possible reasons are that the remote + * interface has been closed or that the operating system instance with the + * communication peer has been rebooted or shut down. + * User action: + * Check the status of the peer device. Ensure that the peer operating system + * instance is running and that the peer interface is operational. + */ + +/*? + * Text: "%s: The remote operating system is not available\n" + * Severity: Notice + * Parameter: + * @1: channel ID + * Description: + * The operating system instance with the communication peer has disconnected. + * Possible reasons are that the operating system instance has been rebooted + * or shut down. + * User action: + * Ensure that the peer operating system instance is running and that the peer + * interface is operational. + */ + +/*? + * Text: "%s: The adapter received a non-specific IRQ\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the CTCM device + * Description: + * The adapter hardware used by the CTCM device received an IRQ that cannot + * be mapped to a particular device. This is a hardware problem. + * User action: + * Check the status of the CTCM device, for example, with ifconfig. Check if + * the connection to the remote device still works. If the CTCM device is not + * operational, set it offline and back online. If this does not resolve the + * problem, perform a manual recovery. See "Device Drivers, Features, and + * Commands" for details about how to recover a CTCM device. If this problem + * persists, gather Linux debug data, collect the hardware logs, and report the + * problem to your support organization. + */ + +/*? + * Text: "%s: A check occurred on the subchannel\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the CTCM device + * Description: + * A check condition has been detected on the subchannel. + * User action: + * Check if the connection to the remote device still works. If the CTCM device + * is not operational, set it offline and back online. If this does not resolve + * the problem, perform a manual recovery. See "Device Drivers, Features, and + * Commands" for details about how to recover a CTCM device. If this problem + * persists, gather Linux debug data and report the problem to your support + * organization. + */ + +/*? + * Text: "%s: The communication peer is busy\n" + * Severity: Informational + * Parameter: + * @1: channel ID + * Description: + * A busy target device was reported. This might be a temporary problem. + * User action: + * If this problem persists or is reported frequently ensure that the target + * device is working properly. + */ + +/*? + * Text: "%s: The specified target device is not valid\n" + * Severity: Error + * Parameter: + * @1: channel ID + * Description: + * A target device was called with a faulty device specification. This is an + * adapter hardware problem. + * User action: + * Gather Linux debug data, collect the hardware logs, and contact IBM support. + */ + +/*? + * Text: "An I/O operation resulted in error %04x\n" + * Severity: Error + * Parameter: + * @1: channel ID + * @2: error information + * Description: + * A hardware operation ended with an error. + * User action: + * Check the status of the CTCM device, for example, with ifconfig. If the + * device is not operational, perform a manual recovery. See "Device Drivers, + * Features, and Commands" for details about how to recover a CTCM device. + * If this problem persists, gather Linux debug data, collect the hardware logs, + * and report the problem to your support organization. + */ + +/*? + * Text: "%s: Initialization failed with RX/TX init handshake error %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the CTCM device + * @2: error information + * Description: + * A problem occurred during the initialization of the connection. If the + * connection can be established after an automatic recovery, a success message + * is issued. + * User action: + * If the problem is not resolved by the automatic recovery process, check the + * local and remote device. If this problem persists, gather Linux debug data + * and report the problem to your support organization. + */ + +/*? + * Text: "%s: The network backlog for %s is exceeded, package dropped\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the CTCM device + * @2: calling function + * Description: + * There is more network traffic than can be handled by the device. The device + * is closed and some data has not been transmitted. The device might be + * recovered automatically. + * User action: + * Investigate and resolve the congestion. If necessary, set the device + * online to make it operational. + */ + +/*? + * Text: "%s: The XID used in the MPC protocol is not valid, rc = %d\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the CTCM device + * @2: return code + * Description: + * The exchange identification (XID) used by the CTCM device driver when + * in MPC mode is not valid. + * User action: + * Note the error information provided with this message and contact your + * support organization. + */ + +/*? Text: "CTCM driver unloaded\n" */ +/*? Text: "%s: %s Internal error: net_device is NULL, ch = 0x%p\n" */ +/*? Text: "%s / Initializing the ctcm device driver failed, ret = %d\n" */ +/*? Text: "%s: %s: Internal error: Can't determine channel for interrupt device %s\n" */ +/*? Text: "CTCM driver initialized\n" */ +/*? Text: "%s: setup OK : r/w = %s/%s, protocol : %d\n" */ +/*? Text: "%s: Connected with remote side\n" */ +/*? Text: "%s: Restarting device\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/dasd +++ linux-4.14.0/Documentation/kmsg/s390/dasd @@ -0,0 +1,704 @@ +/* dasd_ioctl */ + +/*? + * Text: "%s: The DASD has been put in the quiesce state\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * No I/O operation is possible on this device. + * User action: + * Resume the DASD to enable I/O operations. + */ + +/*? + * Text: "%s: I/O operations have been resumed on the DASD\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD is no longer in state quiesce and I/O operations can be performed + * on the device. + * User action: + * None. + */ + +/*? + * Text: "%s: The DASD cannot be formatted while it is enabled\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD you try to format is enabled. Enabled devices cannot be formatted. + * User action: + * Contact the owner of the formatting tool. + */ + +/*? + * Text: "%s: The specified DASD is a partition and cannot be formatted\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD you try to format is a partition. Partitions cannot be formatted + * separately. You can only format a complete DASD including all its partitions. + * User action: + * Format the complete DASD. + * ATTENTION: Formatting irreversibly destroys all data on all partitions + * of the DASD. + */ + +/*? + * Text: "%s: The specified DASD is a partition and cannot be checked\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD you try to check is a partition. Partitions cannot be checked + * separately. You can only check a complete DASD including all its partitions. + * User action: + * Check the complete DASD. + */ + +/*? + * Text: "%s: Formatting unit %d failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: start track + * @3: return code + * Description: + * The formatting process might have been interrupted by a signal, for example, + * CTRL+C. If the process was not interrupted intentionally, an I/O error + * might have occurred. + * User action: + * Retry to format the device. If the error persists, check the log file for + * related error messages. If you cannot resolve the error, note the return + * code and contact your support organization. + */ + + +/* dasd */ + +/*? + * Text: "%s: Cancelling request %p failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to request + * @3: return code of previous function + * Description: + * In response to a user action, the DASD device driver tried but failed to + * cancel a previously started I/O operation. + * User action: + * Try the action again. + */ + +/*? + * Text: "%s: Flushing the DASD request queue failed for request %p\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to request + * Description: + * As part of the unloading process, the DASD device driver flushes the + * request queue. This failed because a previously started I/O operation + * could not be canceled. + * User action: + * Try again to unload the DASD device driver or to shut down Linux. + */ + +/*? + * Text: "The DASD device driver could not be initialized\n" + * Severity: Informational + * Description: + * The initialization of the DASD device driver failed because of previous + * errors. + * User action: + * Check for related previous error messages. + */ + +/*? + * Text: "%s: Accessing the DASD failed because it is in probeonly mode\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * The dasd= module or kernel parameter specified the probeonly attribute for + * the DASD you are trying to access. The DASD device driver cannot access + * DASDs that are in probeonly mode. + * User action: + * Change the dasd= parameter as to omit probeonly for the DASD and reload + * the DASD device driver. If the DASD device driver has been compiled into + * the kernel, reboot Linux. + */ + +/*? + * Text: "%s: cqr %p timed out (%lus), %i retries remaining\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: request + * @3: timeout value + * @4: number of retries left + * Description: + * A try of the error recovery procedure (ERP) for the channel queued request + * (cqr) timed out and failed to recover the error. ERP continues for the DASD. + * User action: + * Ignore this message if it occurs infrequently and if the recovery succeeds + * during one of the retries. If this error persists, check for related + * previous error messages and report the problem to your support organization. + * + * The timeout can be changed by writing a new value to the sysfs 'expires' attribute of the DASD. The value specifies the timeout in seconds. + */ + +/*? + * Text: "%s: cqr %p timed out (%lus) but cannot be ended, retrying in 5 s\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: request + * @3: timeout value + * Description: + * A try of the error recovery procedure (ERP) for the channel queued request + * (cqr) timed out and failed to recover the error. The I/O request submitted + * during the try could not be canceled. The ERP waits for 5 seconds before + * trying again. + * User action: + * Ignore this message if it occurs infrequently and if the recovery succeeds + * during one of the retries. If this error persists, check for related + * previous error messages and report the problem to your support organization. + * + * The timeout can be changed by writing a new value to the sysfs 'expires' attribute of the DASD. The value specifies the timeout in seconds. + */ + +/*? + * Text: "%s: The DASD cannot be set offline while it is in use\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD cannot be set offline because it is in use by an internal process. + * An action to free the DASD might not have completed yet. + * User action: + * Wait some time and set the DASD offline later. + */ + +/*? + * Text: "%s: The DASD cannot be set offline with open count %i\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: count + * Description: + * The DASD is being used by one or more processes and cannot be set offline. + * User action: + * Ensure that the DASD is not in use anymore, for example, unmount all + * partitions. Then try again to set the DASD offline. + */ + +/*? + * Text: "%s: Setting the DASD online failed with rc=%d\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * Description: + * The DASD could not be set online because of previous errors. + * User action: + * Look for previous error messages. If you cannot resolve the error, note + * the return code and contact your support organization. + */ + +/*? + * Text: "%s Setting the DASD online with discipline %s failed with rc=%i\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: discipline + * @3: return code + * Description: + * The DASD could not be set online because of previous errors. + * User action: + * Look for previous error messages. If you cannot resolve the error, note the + * return code and contact your support organization. + */ + +/*? + * Text: "%s Setting the DASD online failed because of missing DIAG discipline\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD was to be set online with discipline DIAG but this discipline of + * the DASD device driver is not available. + * User action: + * Ensure that the dasd_diag_mod module is loaded. If your Linux system does + * not include this module, you cannot set DASDs online with the DIAG + * discipline. + */ + +/*? + * Text: "%s Setting the DASD online failed because of a missing discipline\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD was to be set online with a DASD device driver discipline that + * is not available. + * User action: + * Ensure that all DASD modules are loaded correctly. + */ + +--------------------------- + +/*? + * Text: "The statistics feature has been switched off\n" + * Severity: Informational + * Description: + * The statistics feature of the DASD device driver has been switched off. + * User action: + * None. + */ + +/*? + * Text: "The statistics feature has been switched on\n" + * Severity: Informational + * Description: + * The statistics feature of the DASD device driver has been switched on. + * User action: + * None. + */ + +/*? + * Text: "The statistics have been reset\n" + * Severity: Informational + * Description: + * The DASD statistics data have been reset. + * User action: + * None. + */ + +/*? + * Text: "%s is not a supported value for /proc/dasd/statistics\n" + * Severity: Warning + * Parameter: + * @1: value + * Description: + * An incorrect value has been written to /proc/dasd/statistics. + * The supported values are: 'set on', 'set off', and 'reset'. + * User action: + * Write a supported value to /proc/dasd/statistics. + */ + +/*? + * Text: "%s is not a valid device range\n" + * Severity: Error + * Parameter: + * @1: range + * Description: + * A device range specified with the dasd= parameter is not valid. + * User action: + * Examine the dasd= parameter and correct the device range. + */ + +/*? + * Text: "The probeonly mode has been activated\n" + * Severity: Informational + * Description: + * The probeonly mode of the DASD device driver has been activated. In this + * mode the device driver rejects any 'open' syscalls with EPERM. + * User action: + * None. + */ + +/*? + * Text: "The IPL device is not a CCW device\n" + * Severity: Error + * Description: + * The value for the dasd= parameter contains the 'ipldev' keyword. During + * the boot process this keyword is replaced with the device from which the + * IPL was performed. The 'ipldev' keyword is not valid if the IPL device is + * not a CCW device. + * User action: + * Do not specify the 'ipldev' keyword when performing an IPL from a device + * other than a CCW device. + */ + +/*? + * Text: "A closing parenthesis ')' is missing in the dasd= parameter\n" + * Severity: Warning + * Description: + * The specification for the dasd= kernel or module parameter has an opening + * parenthesis '(' * without a matching closing parenthesis ')'. + * User action: + * Correct the parameter value. + */ + +/*? + * Text: "The autodetection mode has been activated\n" + * Severity: Informational + * Description: + * The autodetection mode of the DASD device driver has been activated. In + * this mode the DASD device driver sets all detected DASDs online. + * User action: + * None. + */ + +/*? + * Text: "%*s is not a supported device option\n" + * Severity: Warning + * Parameter: + * @1: length of option code + * @2: option code + * Description: + * The dasd= parameter includes an unknown option for a DASD or a device range. + * Options are specified in parenthesis and immediately follow a device or + * device range. + * User action: + * Check the dasd= syntax and remove any unsupported options from the dasd= + * parameter specification. + */ + +/*? + * Text: "PAV support has be deactivated\n" + * Severity: Informational + * Description: + * The 'nopav' keyword has been specified with the dasd= kernel or module + * parameter. The Parallel Access Volume (PAV) support of the DASD device + * driver has been deactivated. + * User action: + * None. + */ + +/*? + * Text: "'nopav' is not supported on z/VM\n" + * Severity: Informational + * Description: + * For Linux instances that run as guest operating systems of the z/VM + * hypervisor Parallel Access Volume (PAV) support is controlled by z/VM not + * by Linux. + * User action: + * Remove 'nopav' from the dasd= module or kernel parameter specification. + */ + +/*? + * Text: "High Performance FICON support has been deactivated\n" + * Severity: Informational + * Description: + * The 'nofcx' keyword has been specified with the dasd= kernel or module + * parameter. The High Performance FICON (transport mode) support of the DASD + * device driver has been deactivated. + * User action: + * None. + */ + +/*? + * Text: "The dasd= parameter value %s has an invalid ending\n" + * Severity: Warning + * Parameter: + * @1: parameter value + * Description: + * The specified value for the dasd= kernel or module parameter is not correct. + * User action: + * Check the module or the kernel parameter. + */ + +/*? + * Text: "Registering the device driver with major number %d failed\n" + * Severity: Warning + * Parameter: + * @1: DASD major + * Description: + * Major number 94 is reserved for the DASD device driver. The DASD device + * driver failed to register with this major number. Another device driver + * might have used major number 94. + * User action: + * Determine which device driver uses major number 94 instead of the DASD + * device driver and unload this device driver. Then try again to load the + * DASD device driver. + */ + +/*? + * Text: "%s: default ERP has run out of retries and failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The error recovery procedure (ERP) tried to recover an error but the number + * of retries for the I/O was exceeded before the error could be resolved. + * User action: + * Check for related previous error messages. + */ + +/*? + * Text: "%s: Unable to terminate request %p on suspend\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to request + * Description: + * As part of the suspend process, the DASD device driver terminates requests + * on the request queue. This failed because a previously started I/O operation + * could not be canceled. The suspend process will be stopped. + * User action: + * Try again to suspend the system. + */ + +/*? + * Text: "%s: ERP failed for the DASD\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * An error recovery procedure (ERP) was performed for the DASD but failed. + * User action: + * Check the message log for previous related error messages. + */ + +/*? + * Text: "%s: An error occurred in the DASD device driver, reason=%s\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: reason code + * Description: + * This problem indicates a program error in the DASD device driver. + * User action: + * Note the reason code and contact your support organization. +*/ + +/*? + * Text: "%s: No operational channel path is left for the device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * All channel paths to the device have become non-operational. The DASD + * device driver suspends I/O operations and queues I/O requests for this + * device until at least one channel path becomes operational again. + * User action: + * Ensure that each channel path to the device has been set up correctly + * and that the related physical cable connections are in place. + */ + +/*? + * Text: "%s: No verified channel paths remain for the device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * All verified channel paths to the device have become non-operational. + * Any other paths to the device have previously been identified as not usable. + * The DASD device driver suspends I/O operations and queues I/O requests + * for this device until at least one channel path becomes operational + * again. + * User action: + * Ensure that each channel path to the device has been set up correctly + * and that the related physical cable connections are in place. + * Set all paths to the device offline and online again to repeat the path + * verification. Alternatively, set the device offline and online again to + * verify all available paths for this device. + * If this problem persists, gather Linux debug data and report the problem + * to your support organization. + */ + +/*? + * Text: "%s: A channel path to the device has become operational\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * At least one channel path of this device has become operational again. + * The DASD device driver resumes I/O operations to the device and processes + * the I/O requests that were queued while there was no operational channel path. + * User action: + * None. + */ + +------------------------------------------------------------------------------------ +/* dasd_diag */ + +/*? + * Text: "%s: A 64-bit DIAG call failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * 64-bit DIAG calls require a 64-bit z/VM version. + * User action: + * Use z/VM 5.2 or later or set the sysfs 'use_diag' attribute of the DASD to 0 + * to switch off DIAG. + */ + +/*? + * Text: "%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * Description: + * The format of the DASD is not correct. + * User action: + * Check the device format. For details about the return code see the + * section about the INITIALIZE function for DIAGNOSE Code X'250' + * in "z/VM CP Programming Services". If you cannot resolve the error, note + * the return code and contact your support organization. + */ + +/*? + * Text: "%s: New DASD with %ld byte/block, total size %ld KB%s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * @2: bytes per block + * @3: size + * @4: access mode + * Description: + * A DASD with the indicated block size and total size has been set online. + * If the DASD is configured as read-only to the real or virtual hardware, + * the message includes an indication of this hardware access mode. The + * hardware access mode is independent from the 'readonly' attribute of + * the device in sysfs. + * User action: + * None. + */ + +/*? + * Text: "%s: DIAG ERP failed with rc=%d\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * Description: + * An error in the DIAG processing could not be recovered by the error + * recovery procedure (ERP) of the DIAG discipline. + * User action: + * Note the return code, check for related I/O errors, and report this problem + * to your support organization. + */ + +/*? + * Text: "%s: DIAG initialization failed with rc=%d\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * Description: + * Initializing the DASD with the DIAG discipline failed. Possible reasons for + * this problem are that the device has a device type other than FBA or ECKD, + * or has a block size other than one of the supported sizes: + * 512 byte, 1024 byte, 2048 byte, or 4096 byte. + * User action: + * Ensure that the device can be written to and has a supported device type + * and block size. For details about the return code see the section about + * the INITIALIZE function for DIAGNOSE Code X'250' in "z/VM CP Programming + * Services". If you cannot resolve the error, note the error code and contact + * your support organization. + */ + +/*? + * Text: "%s: Device type %d is not supported in DIAG mode\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: device type + * Description: + * Only DASD of type FBA and ECKD are supported in DIAG mode. + * User action: + * Set the sysfs 'use_diag' attribute of the DASD to 0 and try again to access + * the DASD. + */ + +/*? + * Text: "Discipline %s cannot be used without z/VM\n" + * Severity: Informational + * Parameter: + * @1: discipline name + * Description: + * The discipline that is specified with the dasd= kernel or module parameter + * is only available for Linux instances that run as guest operating + * systems of the z/VM hypervisor. + * User action: + * Remove the unsupported discipline from the parameter string. + */ + +/*? + * Text: "%s: The access mode of a DIAG device changed to read-only\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A device changed its access mode from writeable to + * read-only while in use. + * User action: + * Set the device offline, ensure that the device is configured correctly in + * z/VM, then set the device online again. + */ + +------------------------------------------------------------------------------------ +/* dasd_erp */ + +/*? + * Text: "%s: A timeout error occurred for cqr %p\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to request + * Description: + * A channel queued request (cqr) failed because it timed out. + * One possible reason for this error is that a request did not + * complete within the timeout interval specified for the DASD. + * The timeout interval is set as the value of the 'timeout' sysfs + * attribute of a DASD. A value of 0 disables the timeout function. + * The timeout function can be used; for example, by mirroring setups; + * to quickly process a request queue for a DASD that has become unavailable. + * User action: + * Check the message log for previous related error messages. Verify + * that the storage server and the connection from host to storage + * server are operational. If the 'timeout' sysfs attribute of the + * DASD has been set to a value other than 0, verify that this + * setting is intentional and change it if required. + */ + +/*? + * Text: "%s: A transport error occurred for cqr %p\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to request + * Description: + * A channel queued request (cqr) failed because the connection to the + * device was lost and the 'failfast' flag is set for the request. + * This flag can result from, for example: + * + * - A software layer above the DASD device driver; + * for example, in a host based mirroring setup. + * + * - Value 1 for the 'failfast' sysfs attribute of the DASD. + * This setting applies to all requests on the DASD. + * + * User action: + * Ensure that each channel path to the device has been set up + * correctly and that the related physical cable connections are in + * place. If the 'failfast' attribute of the DASD is set to 1, + * verify that this setting is intentional and change it to 0 if required. + */ + +/*? + * Text: "%s Setting the DASD online failed because the required module %s could not be loaded (rc=%d)\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: kernel module name + * @3: return code + * Description: + * The DASD was to be set online with discipline DIAG but this discipline of + * the DASD device driver is not available and an attempt to load the + * corresponding kernel module failed with the specified return code. + * + * User action: + * Ensure that the kernel module with the specified name is correctly installed + * or set the sysfs 'use_diag' attribute of the DASD to 0 to switch off DIAG. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/dasd-eckd +++ linux-4.14.0/Documentation/kmsg/s390/dasd-eckd @@ -0,0 +1,2154 @@ +/* dasd_eckd */ + +/*? + * Text: "%s: ERP failed for the DASD\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * An error recovery procedure (ERP) was performed for the DASD but failed. + * User action: + * Check the message log for previous related error messages. + */ + +/*? + * Text: "%s: An error occurred in the DASD device driver, reason=%s\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: reason code + * Description: + * This problem indicates a program error in the DASD device driver. + * User action: + * Note the reason code and contact your support organization. +*/ + +/*? + * Text: "%s: Allocating memory for private DASD data failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD device driver maintains data structures for each DASD it manages. + * There is not enough memory to allocate these data structures for one or + * more DASD. + * User action: + * Free some memory and try the operation again. + */ + +/*? + * Text: "%s: DASD with %d KB/block, %d KB total size, %d KB/track, %s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * @2: block size + * @3: DASD size + * @4: track size + * @5: disc layout + * Description: + * A DASD with the shown characteristics has been set online. + * User action: + * None. + */ + +/*? + * Text: "%s: Start track number %u used in formatting is too big\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: track number + * Description: + * The DASD format I/O control was used incorrectly by a formatting tool. + * User action: + * Contact the owner of the formatting tool. + */ + +/*? + * Text: "%s: Stop track number %u used in formatting is too big\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: track number + * Description: + * The DASD format I/O control was used incorrectly by a formatting tool. + * User action: + * Contact the owner of the formatting tool. + */ + +/*? + * Text: "%s: The DASD is not formatted\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A DASD has been set online but it has not been formatted yet. You must + * format the DASD before you can use it. + * User action: + * Format the DASD, for example, with dasdfmt. + */ + +/*? + * Text: "%s: 0x%x is not a known command\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: command + * Description: + * This problem is likely to be caused by a programming error. + * User action: + * Contact your support organization. + */ + +/*? + * Text: "%s: Track 0 has no records following the VTOC\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * Linux has identified a volume table of contents (VTOC) on the DASD but + * cannot read any data records following the VTOC. A possible cause of this + * problem is that the DASD has been used with another System z operating + * system. + * User action: + * Format the DASD for usage with Linux, for example, with dasdfmt. + * ATTENTION: Formatting irreversibly destroys all data on the DASD. + */ + +/*? + * Text: "%s: An I/O control call used incorrect flags 0x%x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: flags + * Description: + * The DASD format I/O control was used incorrectly. + * User action: + * Contact the owner of the formatting tool. + */ + +/*? + * Text: "%s: New DASD %04X/%02X (CU %04X/%02X) with %d cylinders, %d heads, %d sectors%s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * @2: device type + * @3: device model + * @4: control unit type + * @5: control unit model + * @6: number of cylinders + * @7: tracks per cylinder + * @8: sectors per track + * @9: access mode + * Description: + * A DASD with the shown characteristics has been set online. + * If the DASD is configured as read-only to the real or virtual hardware, + * the message includes an indication of this hardware access mode. The + * hardware access mode is independent from the 'readonly' attribute of + * the device in sysfs. + * User action: + * None. + */ + +/*? + * Text: "%s: The disk layout of the DASD is not supported\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD device driver only supports the following disk layouts: CDL, LDL, + * FBA, CMS, and CMS RESERVED. + * User action: + * None. + */ + +/*? + * Text: "%s: Start track %u used in formatting exceeds end track\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: track number + * Description: + * The DASD format I/O control was used incorrectly by a formatting tool. + * User action: + * Contact the owner of the formatting tool. + */ + +/*? + * Text: "%s: The DASD cache mode was set to %x (%i cylinder prestage)\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * @2: operation mode + * @3: number of cylinders + * Description: + * The DASD cache mode has been changed. See the storage system documentation + * for information about the different cache operation modes. + * User action: + * None. + */ + +/*? + * Text: "%s: The DASD cannot be formatted with block size %u\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: block size + * Description: + * The block size specified for a format instruction is not valid. The block + * size must be between 512 and 4096 byte and must be a power of 2. + * User action: + * Call the format command with a supported block size. + */ + +/*? + * Text: "%s: The UID of the DASD has changed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The Unique Identifier (UID) of a DASD that is currently in use has changed. + * This indicates that the physical disk has been replaced. + * User action: + * None if the replacement was intentional. + * If the disk change is not expected, stop using the disk to prevent possible + * data loss. +*/ + + +/* dasd_3990_erp */ + +/*? + * Text: "%s: is offline or not installed - INTERVENTION REQUIRED!!\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD to be accessed is not in an accessible state. The I/O operation + * will wait until the device is operational again. This is an operating system + * independent message that is issued by the storage system. + * User action: + * Make the DASD accessible again. For details see the storage system + * documentation. + */ + +/*? + * Text: "%s: The DASD cannot be reached on any path (lpum=%x/opm=%x)\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: last path used mask + * @3: online path mask + * Description: + * After a path to the DASD failed, the error recovery procedure of the DASD + * device driver tried but failed to reconnect the DASD through an alternative + * path. + * User action: + * Ensure that the cabling between the storage server and the mainframe + * system is securely in place. Check the file systems on the DASD when it is + * accessible again. + */ + +/*? + * Text: "%s: Unable to allocate DCTL-CQR\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an internal error. + * User action: + * Contact your support organization. + */ + +/*? + * Text: "%s: FORMAT 0 - Invalid Parameter\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A data argument of a command is not valid. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - DPS Installation Check\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This operating system independent message is issued by the storage system + * for one of the following reasons: + * - A 3380 Model D or E DASD does not have the Dynamic Path Selection (DPS) + * feature in the DASD A-unit. + * - The device type of an attached DASD is not supported by the firmware. + * - A type 3390 DASD is attached to a 3 MB channel. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 2 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Drive motor switch is off\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - CCW Count less than required\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The CCW count of a command is less than required. This is an operating + * system independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Channel requested ... %02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: reason code + * Description: + * This is an operating system independent message that is issued by the + * storage system. The possible reason codes indicate the following problems: + * 00 No Message. + * 01 The channel has requested unit check sense data. + * 02 The channel has requested retry and retry is exhausted. + * 03 A SA Check-2 error has occurred. This sense is presented with + * Equipment Check. + * 04 The channel has requested retry and retry is not possible. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Status Not As Required: reason %02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: reason code + * Description: + * This is an operating system independent message that is issued by the + * storage system. There are several potential reasons for this message; + * byte 8 contains the reason code. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Device status 1 not valid\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Storage Path Restart\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * An operation for an active channel program was queued in a Storage Control + * when a warm start was received by the path. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Reset Notification\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A system reset or its equivalent was received on an interface. The Unit + * Check that generates this sense is posted to the next channel initiated + * selection following the resetting event. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Invalid Command Sequence\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * An incorrect sequence of commands has occurred. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Missing device address bit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Subsystem Processing Error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A firmware logic error has been detected. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Seek incomplete\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Invalid Command\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A command was issued that is not in the 2107/1750 command set. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Command Invalid on Secondary Address\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A command or order not allowed on a PPRC secondary device has been received + * by the secondary device. This is an operating system independent message + * that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Invalid Defective/Alternate Track Pointer\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A defective track has been accessed. The subsystem generates an invalid + * Defective/Alternate Track Pointer as a part of RAID Recovery. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Channel Returned with Incorrect retry CCW\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A command portion of the CCW returned after a command retry sequence does + * not match the command for which retry was signaled. This is an operating + * system independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Diagnostic of Special Command Violates File Mask\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A command is not allowed under the Access Authorization specified by the + * File Mask. This is an operating system independent message that is issued + * by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Head address does not compare\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Device did not respond to selection\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Device check-2 error or Set Sector is not complete\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Device Error Source\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The device has completed soft error logging. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Data Pinned for Device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * Modified data in cache or in persistent storage exists for the DASD. The + * data cannot be destaged to the device. This track is the first track pinned + * for this device. This is an operating system independent message that is + * issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel C\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Device Status 1 not as expected\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 0 - Device Fenced - device = %02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: sense data byte 4 + * Description: + * The device shown in sense byte 4 has been fenced. This is an operating + * system independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Interruption cannot be reset\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Index missing\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - DASD Fast Write inhibited\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * DASD Fast Write is not allowed because of a nonvolatile storage battery + * check condition. This is an operating system independent message that is + * issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Invalid tag-in for an extended command sequence\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Key area error; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Count area error; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Track physical address did not compare\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 2 - 3990 check-2 error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Offset active cannot be reset\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - RCC 1 and RCC 2 sequences not successful\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in count address area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Data area error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel A\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in count address area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the key area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Caching status reset to default\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The storage director has assigned two new subsystem status devices and + * resets the status to its default value. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the data area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Device not ready\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in key area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - DASD controller failed to set or reset the long busy latch\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 1 - Cylinder address did not compare\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 3 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in data area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 2 - Support facility errors\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Key area error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - End operation with transfer count not zero\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 2 - Microcode detected error %02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: error code + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the count area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 3 - Allegiance terminated\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * Allegiance terminated because of a Reset Allegiance or an Unconditional + * Reserve command on another channel. This is an operating system independent + * message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Home address area error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Count area error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Invalid tag-in during selection sequence\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in data area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in home address area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Home address area error; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - Data area error; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in home address area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the home address area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the home address area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the count area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 4 - No sync byte in key area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Invalid DCC selection response or timeout\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the data area\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Operation Terminated\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The storage system ends an operation related to an active channel program + * when termination and redrive are required and logging is not desired. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel B\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 5 - Data Check in the key area; offset active\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Volume is suspended duplex\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The duplex pair volume has entered the suspended duplex state because of a + * failure. This is an operating system independent message that is issued by + * the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel D\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - RCC 1 sequence not successful\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel E\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - 3990 microcode time out when stopping selection\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel F\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - RCC initiated by a connection check alert\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel G\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - extra RCC required\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 6 - Overrun on channel H\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - Unexpected end operation response code\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Permanent path error (DASD controller not available)\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Missing end operation; device transfer incomplete\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Cache or nonvolatile storage equipment failure\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * An equipment failure has occurred in the cache storage or nonvolatile + * storage of the storage system. This is an operating system independent + * message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - DPS cannot be filled\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - Error correction code hardware fault\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Missing end operation; device transfer complete\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - DASD controller not available on disconnected command chain\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - No interruption from device during a command chain\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - No response to selection after a poll interruption\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 9 - Track physical address did not compare while oriented\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 9 - Head address did not compare\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Invalid tag-in for an immediate command sequence\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 9 - Cylinder address did not compare\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - DPS checks after a system reset or selective reset\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Caching reinitiated\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * Caching has been automatically reinitiated following an error. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - End operation with transfer count zero\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 7 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 9 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - Short busy time-out during device selection\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Caching terminated\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The storage system was unable to initiate caching or had to suspend caching + * for a 3990 control unit. If this problem is caused by a failure condition, + * an additional message will provide more information about the failure. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * Check for additional messages that point out possible failures. For more + * information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Subsystem status cannot be determined\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The status of a DASD Fast Write or PPRC volume cannot be determined. + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Nonvolatile storage terminated\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The storage director has stopped using nonvolatile storage or cannot + * initiate nonvolatile storage. If this problem is caused by a failure, an + * additional message will provide more information about the failure. This is + * an operating system independent message that is issued by the storage system. + * User action: + * Check for additional messages that point out possible failures. For more + * information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT 8 - Reserved\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: Write inhibited path encountered\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an informational message. + * User action: + * None. + */ + +/*? + * Text: "%s: FORMAT 9 - Device check-2 error\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * This is an operating system independent message that is issued by the + * storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Track format incorrect\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A track format error occurred while data was being written to the DASD or + * while a duplex pair was being established. This is an operating system + * independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: FORMAT F - Cache fast write access not authorized\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * A request for Cache Fast Write Data access cannot be satisfied because + * of missing access authorization for the storage system. This is an operating + * system independent message that is issued by the storage system. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: Data recovered during retry with PCI fetch mode active\n" + * Severity: Emerg + * Parameter: + * @1: bus ID of the DASD + * Description: + * A data error has been recovered on the storages system but the Linux file + * system cannot be informed about the data mismatch. To prevent Linux from + * running with incorrect data, the DASD device driver will trigger a kernel + * panic. + * User action: + * Reset your real or virtual hardware and reboot Linux. + */ + +/*? + * Text: "%s: The specified record was not found\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The record to be accessed does not exist. The DASD might be unformatted + * or defect. + * User action: + * Try to format the DASD or replace it. + * ATTENTION: Formatting irreversibly destroys all data on the DASD. + */ + +/*? + * Text: "%s: ERP %p (%02x) refers to %p\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: pointer to ERP + * @3: ERP status + * @4: cqr + * Description: + * This message provides debug information for the enhanced error recovery + * procedure (ERP). + * User action: + * If you do not need this information, you can suppress this message by + * switching off ERP logging, for example, by writing '1' to the 'erplog' + * sysfs attribute of the DASD. + */ + +/*? + * Text: "%s: ERP chain at END of ERP-ACTION\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * This message provides debug information for the enhanced error recovery + * procedure (ERP). + * User action: + * If you do not need this information, you can suppress this message by + * switching off ERP logging, for example, by writing '1' to the 'erplog' + * sysfs attribute of the DASD. + */ + +/*? + * Text: "%s: The cylinder data for accessing the DASD is inconsistent\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * An error occurred in the storage system hardware. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: Accessing the DASD failed because of a hardware error\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * An error occurred in the storage system hardware. + * User action: + * For more information see the documentation of your storage system. + */ + +/*? + * Text: "%s: ERP chain at BEGINNING of ERP-ACTION\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * This message provides debug information for the enhanced error recovery + * procedure (ERP). + * User action: + * If you do not need this information, you can suppress this message by + * switching off ERP logging, for example, by writing '1' to the 'erplog' + * sysfs attribute of the DASD. + */ + +/*? + * Text: "%s: ERP %p has run out of retries and failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: ERP pointer + * Description: + * The error recovery procedure (ERP) tried to recover an error but the number + * of retries for the I/O was exceeded before the error could be resolved. + * User action: + * Check for related previous error messages. + */ + +/*? + * Text: "%s: SIM - SRC: %02x%02x%02x%02x\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: sense byte + * @3: sense byte + * @4: sense byte + * @5: sense byte + * Description: + * This error message is a System Information Message (SIM) generated by the + * storage system. The System Reference Code (SRC) defines the error in detail. + * User action: + * Look up the SRC in the storage server documentation. + */ + +/*? + * Text: "%s: log SIM - SRC: %02x%02x%02x%02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: sense byte + * @3: sense byte + * @4: sense byte + * @5: sense byte + * Description: + * This System Information Message (SIM) is generated by the storage system. + * The System Reference Code (SRC) defines the error in detail. + * User action: + * Look up the SRC in the storage server documentation. + */ + +/*? + * Text: "%s: Reading device feature codes failed with rc=%d\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * Description: + * The device feature codes state which advanced features are supported by a + * device. + * Examples for advanced features are PAV or high performance FICON. + * Some early devices do not provide feature codes and no advanced features are + * available on these devices. + * User action: + * None, if the DASD does not provide feature codes. If the DASD provides + * feature codes, make sure that it is working correctly, then set it offline + * and back online. + */ + +/*? + * Text: "%s: A channel path group could not be established\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * Initialization of a DASD did not complete because a channel path group + * could not be established. + * User action: + * Make sure that the DASD is working correctly, then try again to set it + * online. If initialization still fails, reboot. + */ + +/*? + * Text: "%s: The DASD is not operating in multipath mode\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD channel path group could not be configured to use multipath mode. + * This might negatively affect I/O performance on this DASD. + * User action: + * Make sure that the DASD is working correctly, then try again to set it + * online. If initialization still fails, reboot. + */ + +/*? + * Text: "%s: Detecting the DASD disk layout failed because of an I/O error\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The disk layout of the DASD could not be detected because of an unexpected + * I/O error. The DASD device driver treats the device like an unformatted DASD, + * and partitions on the device are not accessible. + * User action: + * If the DASD is formatted, make sure that the DASD is working correctly, + * then set it offline and back online. If the DASD is unformatted, format the + * DASD, for example, with dasdfmt. + * ATTENTION: Formatting irreversibly destroys all data on the DASD. + */ + +/*? + * Text: "%s: An I/O request was rejected because writing is inhibited\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * An I/O request was returned with an error indication of 'command reject' + * and 'write inhibited'. The most likely reason for this error is a + * failed write request to a device that was attached as read-only in z/VM. + * User action: + * Set the device offline, ensure that the device is configured correctly in + * z/VM, then set the device online again. + */ + +/*? + * Text: "%s: An Alias device was reassigned to a new base device with UID: %s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the alias + * @2: UID of new base device + * Description: + * The alias device with the indicated bus ID has been reassigned. The UID of the new base device is shown in the message. + * User action: + * None. + */ + +/*? + * Text: "%s: Detecting the maximum supported data size for zHPF requests failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * High Performance FICON (zHPF) requests are limited to a hardware-dependent + * maximum data size. The DASD device driver failed to detect this size and zHPF + * is not available for this device. + * User action: + * Set the device offline and online again. If this problem persists, gather + * Linux debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Reading device feature codes failed (rc=%d) for new path %x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * @3: path mask + * Description: + * A new path has been made available to the a device. + * A command to read the device feature codes on this device returned an error. + * The new path will not be used for I/O. + * User action: + * Set the new path offline and online again to repeat the path verification. + * Alternatively, set the device offline and online again to + * verify all available paths for this device. + * If this problem persists, gather Linux debug data and report the problem + * to your support organization. + */ + +/*? + * Text: "%s: Detecting the maximum data size for zHPF requests failed (rc=%d) for a new path %x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: return code + * @3: path mask + * Description: + * High Performance FICON (zHPF) requests are limited to a hardware-dependent + * maximum data size. A command to detect this size for + * a new path returned an error. The new path will not be used for I/O. + * User action: + * Set the new path offline and online again to repeat the path verification. + * Alternatively, set the device offline and online again to + * verify all available paths for this device. + * If this problem persists, gather Linux debug data and report the problem + * to your support organization. + */ + +/*? + * Text: "%s: The maximum data size for zHPF requests %u on a new path %x is below the active maximum %u\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * @2: size in bytes + * @3: path mask + * @4: size in bytes + * Description: + * High Performance FICON (zHPF) requests are limited to a hardware-dependent + * maximum data size. The maximum of the new path is below + * the previously established common maximum for the + * existing paths for this device. This could cause requests on the new + * path to fail. The new path will not be used for I/O. + * User action: + * Set the device offline and online again to establish a new common maximum + * data size for the device. + */ + +/*? + * Text: "%s: The device reservation was lost\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * This Linux instance has lost its reservation of the device to another + * operating system instance. Depending on the reservation policy for the + * device, I/O might be blocked until the other operating system instance + * surrenders the reservation or all I/O requests might fail until the + * device is reset. + * User action: + * None, if this situation is handled by system automation software. + * If this situation is not handled by automation, check the + * last_known_reservation_state attribute of the device in sysfs. + * If the value is 'lost', verify that the device is no longer reserved + * by another operating system instance, then set the device offline and + * online again. For any other value of the last_known_reservation_state + * no action is required. I/O will resume when the device reservation is + * surrendered by the other operating system instance. + */ + +/*? + * Text: "%s: The storage server does not support raw-track access\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD cannot be accessed in raw-track access mode because the storage + * server does not have all required features for this access mode. + * In raw-track access mode, the DASD device driver accesses complete ECKD + * tracks. + * By default, the DASD device driver accesses only the data fields of ECKD + * devices and omits the count and key data fields. + * User action: + * Ensure that the raw_track_access sysfs attribute of the DASD has the value + * 0 to access the device in default ECKD mode. + */ + +/*? + * Text: "%s: The newly added channel path %02X will not be used because it leads to a different device %s\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: logical path mask + * @3: UID + * Description: + * The newly added channel path has a different UID than the DASD device. This indicates + * an incorrect cabling. This path is not going to be used. + * User action: + * Check the cabling of the DASD device. Disconnect and reconnect the cable. + */ + +/*? + * Text: "%s: Not all channel paths lead to the same device, path %02X leads to device %s instead of %s\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: logical path mask + * @3: UID + * @4: UID + * Description: + * Some channel paths have a different UID than others. This indicates + * an incorrect cabling. The DASD device is not enabled. + * User action: + * Check cabling of the DASD device and retry to enable the device. + */ + +/*? + * Text: "Service on the storage server caused path %x.%02x to go offline" + * Severity: Warning + * Parameter: + * @1: channel subsystem ID + * @2: CHPID + * Description: + * A channel path to the DASD has been set offline because of + * a service action on the storage server. The path will be set back + * online automatically when the service action is completed. + * User action: + * None. + */ + +/*? + * Text: "Path %x.%02x is back online after service on the storage server" + * Severity: Informational + * Parameter: + * @1: channel subsystem ID + * @2: CHPID + * Description: + * A path had been set offline temporarily because of a service + * action on the storage server. + * The service action has completed, and the channel path is available + * again. + * User action: + * None. + */ + +/*? + * Text: "%s: High Performance FICON disabled\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * Description: + * High Performance FICON (HPF) has been disabled. Either the device + * lost HPF functionality, or none of the remaining channel paths are + * HPF capable. + * User action: + * Report the problem to your support organization. + * Ensure that the cabling between the storage server and the mainframe + * system is securely in place. + * Reset the device and channel paths by writing "all" or a logical path mask + * to the path_reset sysfs attribute of the device. + */ + +/*? + * Text: "%s: Channel path %02X lost HPF functionality and is disabled\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: logical path mask + * Description: + * A channel path has lost High Performance FICON (HPF) functionality + * and was removed from regular operations. + * User action: + * Report the problem to your support organization. + * Ensure that the cabling between the storage server and the mainframe + * system is securely in place. + * Reset the device and channel paths by writing "all" or a logical path mask + * to the path_reset sysfs attribute of the device. + */ + +/*? + * Text: "%s: Path %x.%02x (pathmask %02x) is disabled - IFCC threshold exceeded\n" + * Severity: Error + * Parameter: + * @1: bus ID of the DASD + * @2: cssid + * @3: chpid + * @4: logical path mask + * Description: + * Due to numerous interface or channel control checks (IFCCs), a channel path + * was removed from regular operations to retain good I/O performance. + * User action: + * Ensure that the cabling between the storage server and the mainframe + * system is securely in place. + * Reset the device and channel paths by writing "all" or a logical path mask + * to the path_reset sysfs attribute of the device. + * If the problem persists, report it to your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/dasd-fba +++ linux-4.14.0/Documentation/kmsg/s390/dasd-fba @@ -0,0 +1,36 @@ + +/*? + * Text: "%s: New FBA DASD %04X/%02X (CU %04X/%02X) with %d MB and %d B/blk%s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the DASD + * @2: device type + * @3: device model + * @4: control unit type + * @5: control unit model + * @6: size + * @7: bytes per block + * @8: access mode + * Description: + * A DASD with the shown characteristics has been set online. + * If the DASD is configured as read-only to the real or virtual hardware, + * the message includes an indication of this hardware access mode. The + * hardware access mode is independent from the 'readonly' attribute of + * the device in sysfs. + * User action: + * None. + */ + +/*? + * Text: "%s: Allocating memory for private DASD data failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the DASD + * Description: + * The DASD device driver maintains data structures for each DASD it manages. + * There is not enough memory to allocate these data structures for one or + * more DASD. + * User action: + * Free some memory and try the operation again. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/dcssblk +++ linux-4.14.0/Documentation/kmsg/s390/dcssblk @@ -0,0 +1,206 @@ +/*? + * Text: "Adjacent DCSSs %s and %s are not contiguous\n" + * Severity: Error + * Parameter: + * @1: name 1 + * @2: name 2 + * Description: + * You can only map a set of two or more DCSSs to a single DCSS device if the + * DCSSs in the set form a contiguous memory space. The DCSS device cannot be + * created because there is a memory gap between two adjacent DCSSs. + * User action: + * Ensure that you have specified all DCSSs that belong to the set. Check the + * definitions of the DCSSs on the z/VM hypervisor to verify that they form + * a contiguous memory space. + */ + +/*? + * Text: "DCSS %s and DCSS %s have incompatible types\n" + * Severity: Error + * Parameter: + * @1: name 1 + * @2: name 2 + * Description: + * You can only map a set of two or more DCSSs to a single DCSS device if + * either all DCSSs in the set have the same type or if the set contains DCSSs + * of the two types EW and EN but no other type. The DCSS device cannot be + * created because at least two of the specified DCSSs are not compatible. + * User action: + * Check the definitions of the DCSSs on the z/VM hypervisor to verify that + * their types are compatible. + */ + +/*? + * Text: "DCSS %s is of type SC and cannot be loaded as exclusive-writable\n" + * Severity: Error + * Parameter: + * @1: device name + * Description: + * You cannot load a DCSS device in exclusive-writable access mode if the DCSS + * devise maps to one or more DCSSs of type SC. + * User action: + * Load the DCSS in shared access mode. + */ + +/*? + * Text: "DCSS device %s is removed after a failed access mode change\n" + * Severity: Error + * Parameter: + * @1: device name + * Description: + * To change the access mode of a DCSS device, all DCSSs that map to the device + * were unloaded. Reloading the DCSSs for the new access mode failed and the + * device is removed. + * User action: + * Look for related messages to find out why the DCSSs could not be reloaded. + * If necessary, add the device again. + */ + +/*? + * Text: "All DCSSs that map to device %s are saved\n" + * Severity: Informational + * Parameter: + * @1: device name + * Description: + * A save request has been submitted for the DCSS device. Changes to all DCSSs + * that map to the device are saved permanently. + * User action: + * None. + */ + +/*? + * Text: "Device %s is in use, its DCSSs will be saved when it becomes idle\n" + * Severity: Informational + * Parameter: + * @1: device name + * Description: + * A save request for the device has been deferred until the device becomes + * idle. Then changes to all DCSSs that the device maps to will be saved + * permanently. + * User action: + * None. + */ + +/*? + * Text: "A pending save request for device %s has been canceled\n" + * Severity: Informational + * Parameter: + * @1: device name + * Description: + * A save request for the DCSSs that map to a DCSS device has been pending + * while the device was in use. This save request has been canceled. Changes to + * the DCSSs will not be saved permanently. + * User action: + * None. + */ + +/*? + * Text: "Loaded %s with total size %lu bytes and capacity %lu sectors\n" + * Severity: Informational + * Parameter: + * @1: DCSS names + * @2: total size in bytes + * @3: total size in 512 byte sectors + * Description: + * The listed DCSSs have been verified as contiguous and successfully loaded. + * The displayed sizes are the sums of all DCSSs. + * User action: + * None. + */ + +/*? + * Text: "Device %s cannot be removed because it is not a known device\n" + * Severity: Warning + * Parameter: + * @1: device name + * Description: + * The DCSS device you are trying to remove is not known to the DCSS device + * driver. + * User action: + * List the entries under /sys/devices/dcssblk/ to see the names of the + * existing DCSS devices. + */ + +/*? + * Text: "Device %s cannot be removed while it is in use\n" + * Severity: Warning + * Parameter: + * @1: device name + * Description: + * You are trying to remove a device that is in use. + * User action: + * Make sure that all users of the device close the device before you try to + * remove it. + */ + +/*? + * Text: "Device %s has become idle and is being saved now\n" + * Severity: Informational + * Parameter: + * @1: device name + * Description: + * A save request for the DCSSs that map to a DCSS device has been pending + * while the device was in use. The device has become idle and all changes + * to the DCSSs are now saved permanently. + * User action: + * None. + */ + +/*? + * Text: "Writing to %s failed because it is a read-only device\n" + * Severity: Warning + * Parameter: + * @1: device name + * Description: + * The DCSS device is in shared access mode and cannot be written to. Depending + * on the type of the DCSSs that the device maps to, you might be able to + * change the access mode to exclusive-writable. + * User action: + * If the DCSSs of the device are of type SC, do not attempt to write to the + * device. If the DCSSs of the device are of type ER or SR, change the access + * mode to exclusive-writable before writing to the device. + */ + +/*? + * Text: "The address range of DCSS %s changed while the system was suspended\n" + * Severity: Error + * Parameter: + * @1: device name + * Description: + * After resuming the system, the start address or end address of a DCSS does + * not match the address when the system was suspended. DCSSs must not be + * changed after the system was suspended. + * This error cannot be recovered. The system is stopped with a kernel panic. + * User action: + * Reboot Linux. + */ + +/*? + * Text: "Suspending the system failed because DCSS device %s is writable\n" + * Severity: Error + * Parameter: + * @1: device name + * Description: + * A system cannot be suspended if one or more DCSSs are accessed in exclusive- + * writable mode. DCSS segment types EW, SW, and EN are always writable and + * must be removed before a system is suspended. + * User action: + * Remove all DCSSs of segment types EW, SW, and EN by writing the DCSS name to + * the sysfs 'remove' attribute. Set the access mode for all DCSSs of segment + * types SR and ER to read-only by writing 1 to the sysfs 'shared' attribute of + * the DCSS. Then try again to suspend the system. + */ + +/*? + * Text: "DCSS %s is of type SN or EN and cannot be saved\n" + * Severity: Warning + * Parameter: + * @1: DCSS name + * Description: + * DCSSs of type SN or EN cannot be saved. + * User action: + * If the DCSS was set up with the intention to prevent the content from being saved, + * no action is necessary. + * To be able to save the content, you must define the DCSS with a type other than SN or EN. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/diag288_wdt +++ linux-4.14.0/Documentation/kmsg/s390/diag288_wdt @@ -0,0 +1,66 @@ +/*? + * Text: "The watchdog cannot be activated\n" + * Severity: Error + * Description: + * Diagnose instruction 0x288 was called to activate the diag288 watchdog. + * The diagnose call returned an error that cannot be handled by the device driver. + * The watchdog stays inactive. + * User action: + * Contact your support organization. + */ + +/*? + * Text: "The watchdog cannot be initialized\n" + * Severity: Error + * Description: + * Diagnose instruction 0x288 was called to initialize the diag288 watchdog. + * The diagnose call returned an error that cannot be handled by the device driver. + * The watchdog stays inactive. + * A possible reason for this error is that your real or virtual hardware does not support + * the diag288 watchdog. + * User action: + * Confirm that the diag288 watchdog is supported in your environment. + * Use a watchdog that is supported in your environment. + */ + +/*? + * Text: "The watchdog cannot be deactivated\n" + * Severity: Error + * Description: + * Diagnose instruction 0x288 was called to deactivate the diag288 watchdog. + * The diagnose call returned an error that cannot be handled by the device driver. + * The watchdog stays active and a watchdog timeout will trigger the configured timeout action. + * The diag288 watchdog device driver might intentionally be configured to prevent deactivation. + * User action: + * You can configure the diag288 watchdog device driver such that it can be deactivated. + * If the diag288 device driver has been compiled as a separate module, diag288_wdt, reload the module + * without specifying the 'nowayout' module parameter. + * If the diag288 device driver has been compiled into your kernel, + * reboot Linux without specifying the 'diag288.nowayout' kernel parameter'. + */ + +/*? + * Text: "The watchdog timer cannot be started or reset\n" + * Severity: Error + * Description: + * Diagnose instruction 0x288 was called to start the diag288 watchdog or to set timer back to zero. + * The diagnose call returned an error that cannot be handled by the device driver. + * The watchdog stays inactive or becomes inactive. + * User action: + * Contact your support organization. + */ + +/*? + * Text: "Linux cannot be suspended while the watchdog is in use\n" + * Severity: Error + * Description: + * The watchdog must not time out while Linux is suspended. + * Therefore, the diag288 watchdog device driver prevents Linux from being suspended + * while the watchdog is in use. + * User action: + * i) Stop the watchdog application. ii) If the problem persists, close the watchdog + * device node by issuing 'echo V > /dev/watchdog'. + * iii) If the device driver still prevents Linux from being suspended, + * contact your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/extmem +++ linux-4.14.0/Documentation/kmsg/s390/extmem @@ -0,0 +1,293 @@ +/*? + * Text: "Querying a DCSS type failed with rc=%ld\n" + * Severity: Warning + * Parameter: + * @1: return code + * Description: + * The DCSS kernel interface used z/VM diagnose call X'64' to query the + * type of a DCSS. z/VM failed to determine the type and returned an error. + * User action: + * Look for related messages to find out which DCSS is affected. + * For details about the return codes see the section about DIAGNOSE Code + * X'64' in "z/VM CP Programming Services". + */ + +/*? + * Text: "Loading DCSS %s failed with rc=%ld\n" + * Severity: Warning + * Parameter: + * @1: DCSS name + * @2: return code + * Description: + * The DCSS kernel interface used diagnose call X'64' to load a DCSS. z/VM + * failed to load the DCSS and returned an error. + * User action: + * For details about the return codes see the section about DIAGNOSE Code + * X'64' in "z/VM CP Programming Services". + */ + +/*? + * Text: "DCSS %s of range %p to %p and type %s loaded as exclusive-writable\n" + * Severity: Informational + * Parameter: + * @1: DCSS name + * @2: starting page address + * @3: ending page address + * @4: DCSS type + * Description: + * The DCSS was loaded successfully in exclusive-writable access mode. + * User action: + * None. + */ + +/*? + * Text: "DCSS %s of range %p to %p and type %s loaded in shared access mode\n" + * Severity: Informational + * Parameter: + * @1: DCSS name + * @2: starting page address + * @3: ending page address + * @4: DCSS type + * Description: + * The DCSS was loaded successfully in shared access mode. + * User action: + * None. + */ + +/*? + * Text: "DCSS %s is already in the requested access mode\n" + * Severity: Informational + * Parameter: + * @1: DCSS name + * Description: + * A request to reload a DCSS with a new access mode has been rejected + * because the new access mode is the same as the current access mode. + * User action: + * None. + */ + +/*? + * Text: "DCSS %s is in use and cannot be reloaded\n" + * Severity: Warning + * Parameter: + * @1: DCSS name + * Description: + * Reloading a DCSS in a different access mode has failed because the DCSS is + * being used by one or more device drivers. The DCSS remains loaded with the + * current access mode. + * User action: + * Ensure that the DCSS is not used by any device driver then try again to + * load the DCSS with the new access mode. + */ + +/*? + * Text: "DCSS %s overlaps with used memory resources and cannot be reloaded\n" + * Severity: Warning + * Parameter: + * @1: DCSS name + * Description: + * The DCSS has been unloaded and cannot be reloaded because it overlaps with + * another loaded DCSS or with the memory of the z/VM guest virtual machine + * (guest storage). + * User action: + * Ensure that no DCSS is loaded that has overlapping memory resources + * with the DCSS you want to reload. If the DCSS overlaps with guest storage, + * use the DEF STORE CONFIG z/VM CP command to create a sufficient storage gap + * for the DCSS. For details, see the section about the DCSS device driver in + * "Device Drivers, Features, and Commands". + */ + +/*? + * Text: "Reloading DCSS %s failed with rc=%ld\n" + * Severity: Warning + * Parameter: + * @1: DCSS name + * @2: return code + * Description: + * The DCSS kernel interface used z/VM diagnose call X'64' to reload a DCSS + * in a different access mode. The DCSS was unloaded but z/VM failed to reload + * the DCSS. + * User action: + * For details about the return codes see the section about DIAGNOSE Code + * X'64' in "z/VM CP Programming Services". + */ + +/*? + * Text: "Unloading unknown DCSS %s failed\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * The specified DCSS cannot be unloaded. The DCSS is known to the DCSS device + * driver but not to the DCSS kernel interface. This problem indicates a + * program error in extmem.c. + * User action: + * Report this problem to your support organization. + */ + +/*? + * Text: "Saving unknown DCSS %s failed\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * The specified DCSS cannot be saved. The DCSS is known to the DCSS device + * driver but not to the DCSS kernel interface. This problem indicates a + * program error in extmem.c. + * User action: + * Report this problem to your support organization. + */ + +/*? + * Text: "Saving a DCSS failed with DEFSEG response code %i\n" + * Severity: Error + * Parameter: + * @1: response-code + * Description: + * The DEFSEG z/VM CP command failed to permanently save changes to a DCSS. + * User action: + * Ensure that the z/VM guest virtual machine is authorized to issue + * the CP DEFSEG command (typically privilege class E). + * Look for related messages to find the cause of this error. See also message + * HCPE in the DEFSEG section of the "z/VM CP Command and + * Utility Reference". + */ + +/*? + * Text: "Saving a DCSS failed with SAVESEG response code %i\n" + * Severity: Error + * Parameter: + * @1: response-code + * Description: + * The SAVESEG z/VM CP command failed to permanently save changes to a DCSS. + * User action: + * Ensure that the z/VM guest virtual machine is authorized to issue + * the CP SAVESEG command (typically privilege class E). + * Look for related messages to find the cause of this error. See also message + * HCPE in the SAVESEG section of the "z/VM CP Command and + * Utility Reference". + */ + +/*? + * Text: "DCSS %s cannot be loaded or queried\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * You cannot load or query the specified DCSS because it either is not defined + * in the z/VM hypervisor, or it is a class S DCSS, or it is above 2047 MB + * and the Linux system is a 31-bit system. + * User action: + * Use the CP command "QUERY NSS" to find out if the DCSS is a valid + * DCSS that can be loaded. + */ + +/*? + * Text: "DCSS %s cannot be loaded or queried without z/VM\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * A DCSS is a z/VM resource. Your Linux instance is not running as a z/VM + * guest operating system and, therefore, cannot load DCSSs. + * User action: + * Load DCSSs only on Linux instances that run as z/VM guest operating systems. + */ + +/*? + * Text: "Loading or querying DCSS %s resulted in a hardware error\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * Either the z/VM DIAGNOSE X'64' query or load call issued for the DCSS + * returned with an error. + * User action: + * Look for previous extmem message to find the return code from the + * DIAGNOSE X'64' query or load call. For details about the return codes see + * the section about DIAGNOSE Code X'64' in "z/VM CP Programming Services". + */ + +/*? + * Text: "DCSS %s has multiple page ranges and cannot be loaded or queried\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * You can only load or query a DCSS with multiple page ranges if: + * - The DCSS has 6 or fewer page ranges + * - The page ranges form a contiguous address space + * - The page ranges are of type EW or EN + * User action: + * Check the definition of the DCSS to make sure that the conditions for + * DCSSs with multiple page ranges are met. + */ + +/*? + * Text: "%s needs used memory resources and cannot be loaded or queried\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * You cannot load or query the DCSS because it overlaps with an already + * loaded DCSS or with the memory of the z/VM guest virtual machine + * (guest storage). + * User action: + * Ensure that no DCSS is loaded that has overlapping memory resources + * with the DCSS you want to load or query. If the DCSS overlaps with guest + * storage, use the DEF STORE CONFIG z/VM CP command to create a sufficient + * storage gap for the DCSS. For details, see the section about the DCSS + * device driver in "Device Drivers, Features, and Commands". + */ + +/*? + * Text: "DCSS %s is already loaded in a different access mode\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * The DCSS you are trying to load has already been loaded in a different + * access mode. You cannot simultaneously load the DCSS in different modes. + * User action: + * Reload the DCSS in a different mode or load it with the same mode in which + * it has already been loaded. + */ + +/*? + * Text: "There is not enough memory to load or query DCSS %s\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * The available memory is not enough to load or query the DCSS. + * User action: + * Free some memory and repeat the failed operation. + */ + +/*? + * Text: "DCSS %s overlaps with used storage and cannot be loaded\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * You cannot load the DCSS because it overlaps with an already loaded DCSS + * or with the memory of the z/VM guest virtual machine (guest storage). + * User action: + * Ensure that no DCSS is loaded that has overlapping memory resources + * with the DCSS you want to load. If the DCSS overlaps with guest storage, + * use the DEF STORE CONFIG z/VM CP command to create a sufficient storage gap + * for the DCSS. For details, see the section about the DCSS device driver in + * "Device Drivers, Features, and Commands". + */ + +/*? + * Text: "DCSS %s exceeds the kernel mapping range (%lu) and cannot be loaded\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * @2: kernel mapping range in bytes + * Description: + * You cannot load the DCSS because it exceeds the kernel mapping range limit. + * User action: + * Ensure that the DCSS range is defined below the kernel mapping range. + */ --- linux-4.14.0.orig/Documentation/kmsg/s390/hmcdrv +++ linux-4.14.0/Documentation/kmsg/s390/hmcdrv @@ -0,0 +1,22 @@ +/*? + * Text: "Allocating the requested cache size of %zu bytes failed\n" + * Severity: Error + * Parameter: + * @1: size + * Description: + * You cannot use the 'hmcdrv' module. + * Either the cache size that was specified for the 'hmcdrv' module exceeded + * the maximum of 1048576 (1 megabyte), or not enough free memory was + * available. + * If the 'hmcdrv' module was compiled into the kernel, the cache size was + * specified with the 'hmcdrv.cachesize' kernel parameter. + * For a separate 'hmcdrv' module, the cache size was specified with the + * 'cachesize=' module parameter. + * User action: + * Specify a smaller cache size and try again to load the module. + * Do not exceed the maximum specification of 1048576 (1 megabyte). + * If necessary, free some memory and try again. + * If the module is compiled into the kernel, you must reboot Linux to change + * the cache size specification. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/hugetlb +++ linux-4.14.0/Documentation/kmsg/s390/hugetlb @@ -0,0 +1,13 @@ +/*? + * Text: "hugepagesz= specifies an unsupported page size %s\n" + * Severity: Error + * Parameter: + * @1: size + * Description: + * The hugepagesz= kernel parameter specifies a huge page size + * that is not supported. + * User action: + * Specify "1M" for 1 MB huge pages. These are supported as of z10. + * Specify "2G" for 2 GB huge pages. These are supported as of zEC12 + * and zBC12 machines. + */ --- linux-4.14.0.orig/Documentation/kmsg/s390/hvc_iucv +++ linux-4.14.0/Documentation/kmsg/s390/hvc_iucv @@ -0,0 +1,123 @@ +/*? + * Text: "The z/VM IUCV HVC device driver cannot be used without z/VM\n" + * Severity: Notice + * Description: + * The z/VM IUCV hypervisor console (HVC) device driver requires the + * z/VM inter-user communication vehicle (IUCV). + * User action: + * Set "hvc_iucv=" to zero in the kernel parameter line and reboot Linux. + */ + +/*? + * Text: "%lu is not a valid value for the hvc_iucv= kernel parameter\n" + * Severity: Error + * Parameter: + * @1: hvc_iucv_devices + * Description: + * The "hvc_iucv=" kernel parameter specifies the number of z/VM IUCV + * hypervisor console (HVC) terminal devices. + * The parameter value ranges from 0 to 8. + * If zero is specified, the z/VM IUCV HVC device driver is disabled + * and no IUCV-based terminal access is available. + * User action: + * Correct the "hvc_iucv=" setting in the kernel parameter line and + * reboot Linux. + */ + +/*? + * Text: "Creating a new HVC terminal device failed with error code=%d\n" + * Severity: Error + * Parameter: + * @1: errno + * Description: + * The device driver initialization failed to allocate a new + * HVC terminal device. + * A possible cause of this problem is memory constraints. + * User action: + * If the error code is -12 (ENOMEM), consider assigning more memory + * to your z/VM guest virtual machine. + */ + +/*? + * Text: "Registering HVC terminal device as Linux console failed\n" + * Severity: Error + * Description: + * The device driver initialization failed to set up the first HVC terminal + * device for use as Linux console. + * User action: + * If the error code is -12 (ENOMEM), consider assigning more memory + * to your z/VM guest virtual machine. + */ + +/*? + * Text: "Registering IUCV handlers failed with error code=%d\n" + * Severity: Error + * Parameter: + * @1: errno + * Description: + * The device driver initialization failed to register with z/VM IUCV to + * handle IUCV connections, as well as sending and receiving of IUCV messages. + * User action: + * Check for related IUCV error messages and see the errno manual page + * to find out what caused the problem. + */ + +/*? + * Text: "Allocating memory failed with reason code=%d\n" + * Severity: Error + * Parameter: + * @1: reason + * Description: + * The z/VM IUCV hypervisor console (HVC) device driver initialization failed, + * because of a general memory allocation failure. The reason code indicates + * the memory operation that has failed: + * kmem_cache (reason code=1), + * mempool (reason code=2), or + * hvc_iucv_allow= (reason code=3) + * User action: + * Consider assigning more memory to your z/VM guest virtual machine. + */ + +/*? + * Text: "hvc_iucv_allow= does not specify a valid z/VM user ID list\n" + * Severity: Error + * Description: + * The "hvc_iucv_allow=" kernel parameter specifies a comma-separated list + * of z/VM user IDs that are permitted to connect to the z/VM IUCV hypervisor + * device driver. + * The z/VM user IDs in the list must not exceed eight characters and must + * not contain spaces. + * User action: + * Correct the "hvc_iucv_allow=" setting in the kernel parameter line and reboot + * Linux. + */ + +/*? + * Text: "hvc_iucv_allow= specifies too many z/VM user IDs\n" + * Severity: Error + * Description: + * The "hvc_iucv_allow=" kernel parameter specifies a comma-separated list + * of z/VM user IDs that are permitted to connect to the z/VM IUCV hypervisor + * device driver. + * The number of z/VM user IDs that are specified with the "hvc_iucv_allow=" + * kernel parameter exceeds the maximum of 500. + * User action: + * Correct the "hvc_iucv_allow=" setting by reducing the z/VM user IDs in + * the list and reboot Linux. + */ + +/*? + * Text: "A connection request from z/VM user ID %s was refused\n" + * Severity: Informational + * Parameter: + * @1: ID + * Description: + * An IUCV connection request from another z/VM guest virtual machine has been + * refused. The request was from a z/VM guest virtual machine that is not + * listed by the "hvc_iucv_allow=" kernel parameter. + * User action: + * Check the "hvc_iucv_allow=" kernel parameter setting. + * Consider adding the z/VM user ID to the "hvc_iucv_allow=" list in the kernel + * parameter line and reboot Linux. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/hypfs +++ linux-4.14.0/Documentation/kmsg/s390/hypfs @@ -0,0 +1,56 @@ +/*? + * Text: "The hardware system does not support hypfs\n" + * Severity: Error + * Description: + * hypfs requires DIAGNOSE Code X'204' but this diagnose code is not available + * on your hardware. You need more recent hardware to use hypfs. + * User action: + * None. + */ + +/*? + * Text: "The hardware system does not provide all functions required by hypfs\n" + * Severity: Error + * Description: + * hypfs requires DIAGNOSE Code X'224' but this diagnode code is not available + * on your hardware. You need more recent hardware to use hypfs. + * User action: + * None. + */ + +/*? + * Text: "Updating the hypfs tree failed\n" + * Severity: Error + * Description: + * There was not enough memory available to update the hypfs tree. + * User action: + * Free some memory and try again to update the hypfs tree. Consider assigning + * more memory to your LPAR or z/VM guest virtual machine. + */ + +/*? + * Text: "%s is not a valid mount option\n" + * Severity: Error + * Parameter: + * @1: mount option + * Description: + * hypfs has detected mount options that are not valid. + * User action: + * See "Device Drivers Features and Commands" for information about valid + * mount options for hypfs. + */ + +/*? + * Text: "Initialization of hypfs failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: error code + * Description: + * Initialization of hypfs failed because of resource or hardware constraints. + * Possible reasons for this problem are insufficient free memory or missing + * hardware interfaces. + * User action: + * See errno.h for information about the error codes. + */ + +/*? Text: "Hypervisor filesystem mounted\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/iucv +++ linux-4.14.0/Documentation/kmsg/s390/iucv @@ -0,0 +1,33 @@ +/*? + * Text: "Defining an interrupt buffer on CPU %i failed with 0x%02x (%s)\n" + * Severity: Warning + * Parameter: + * @1: CPU number + * @2: hexadecimal error value + * @3: short error code explanation + * Description: + * Defining an interrupt buffer for external interrupts failed. Error + * value 0x03 indicates a problem with the z/VM directory entry of the + * z/VM guest virtual machine. This problem can also be caused by a + * program error. + * User action: + * If the error value is 0x03, examine the z/VM directory entry of your + * z/VM guest virtual machine. If the directory entry is correct or if the + * error value is not 0x03, report this problem to your support organization. + */ + +/*? + * Text: "Suspending Linux did not completely close all IUCV connections\n" + * Severity: Warning + * Description: + * When resuming a suspended Linux instance, the IUCV base code found + * data structures from one or more IUCV connections that existed before the + * Linux instance was suspended. Modules that use IUCV connections must close + * these connections when a Linux instance is suspended. This problem + * indicates an error in a program that used an IUCV connection. + * User action: + * Report this problem to your support organization. + */ + +/*? Text: "iucv_external_interrupt: out of memory\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/lcs +++ linux-4.14.0/Documentation/kmsg/s390/lcs @@ -0,0 +1,169 @@ +/*? + * Text: "%s: Allocating a socket buffer to interface %s failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the LCS device + * @2: network interface + * Description: + * LAN channel station (LCS) devices require a socket buffer (SKB) structure + * for storing incoming data. The LCS device driver failed to allocate an SKB + * structure to the LCS device. A likely cause of this problem is memory + * constraints. + * User action: + * Free some memory and repeat the failed operation. + */ + +/*? + * Text: "%s: Shutting down the LCS device failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the LCS device + * Description: + * A request to shut down a LAN channel station (LCS) device resulted in an + * error. The error is logged in the LCS trace at trace level 4. + * User action: + * Try again to shut down the device. If the error persists, see the LCS trace + * to find out what causes the error. + */ + +/*? + * Text: "%s: Detecting a network adapter for LCS devices failed with rc=%d (0x%x)\n" + * Severity: Error + * Parameter: + * @1: bus ID of the LCS device + * @2: lcs_detect return code in decimal notation + * @3: lcs_detect return code in hexadecimal notation + * Description: + * The LCS device driver could not initialize a network adapter. + * User action: + * Ensure that the physical connection from the port to the network is + * in place. If the error persists, note the return code from the error + * message and contact IBM support. + */ + +/*? + * Text: "%s: A recovery process has been started for the LCS device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the LCS device + * Description: + * The LAN channel station (LCS) device is shut down and restarted. The recovery + * process might have been initiated by a user or started automatically as a + * response to a device problem. + * User action: + * Wait until a message indicates the completion of the recovery process. + */ + +/*? + * Text: "%s: An I/O-error occurred on the LCS device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the LCS device + * Description: + * The LAN channel station (LCS) device reported a problem that can be recovered + * by the LCS device driver. Repeated occurrences of this problem indicate a + * malfunctioning device. + * User action: + * If this problem occurs frequently, initiate a recovery process for the + * device, for example, by writing '1' to the 'recover' sysfs attribute of the + * device. + */ + +/*? + * Text: "%s: A command timed out on the LCS device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the LCS device + * Description: + * The LAN channel station (LCS) device reported a problem that can be recovered + * by the LCS device driver. Repeated occurrences of this problem indicate a + * malfunctioning device. + * User action: + * If this problem occurs frequently, initiate a recovery process for the + * device, for example, by writing '1' to the 'recover' sysfs attribute of the + * device. + */ + +/*? + * Text: "%s: An error occurred on the LCS device, rc=%ld\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the LCS device + * @2: return code + * Description: + * The LAN channel station (LCS) device reported a problem that can be recovered + * by the LCS device driver. Repeated occurrences of this problem indicate a + * malfunctioning device. + * User action: + * If this problem occurs frequently, initiate a recovery process for the + * device, for example, by writing '1' to the 'recover' sysfs attribute of the + * device. + */ + +/*? + * Text: "%s: The LCS device stopped because of an error, dstat=0x%X, cstat=0x%X \n" + * Severity: Warning + * Parameter: + * @1: bus ID of the LCS device + * @2: device status + * @3: subchannel status + * Description: + * The LAN channel station (LCS) device reported an error. The LCS device driver + * might start a device recovery process. + * User action: + * If the device driver does not start a recovery process, initiate a recovery + * process, for example, by writing '1' to the 'recover' sysfs attribute of the + * device. If the problem persists, note the status information provided with + * the message and contact IBM support. + */ + +/*? + * Text: "%s: Starting an LCS device resulted in an error, rc=%d!\n" + * Severity: Error + * Parameter: + * @1: bus ID of the LCS device + * @2: ccw_device_start return code in decimal notation + * Description: + * The LAN channel station (LCS) device driver failed to initialize an LCS + * device. The device is not operational. + * User action: + * Initiate a recovery process, for example, by writing '1' to the 'recover' + * sysfs attribute of the device. If the problem persists, contact IBM support. + */ + +/*? + * Text: "%s: Sending data from the LCS device to the LAN failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: bus ID of the LCS device + * @2: ccw_device_resume return code in decimal notation + * Description: + * The LAN channel station (LCS) device driver could not send data to the LAN + * using the LCS device. This might be a temporary problem. Operations continue + * on the LCS device. + * User action: + * If this problem occurs frequently, initiate a recovery process, for example, + * by writing '1' to the 'recover' sysfs attribute of the device. If the + * problem persists, contact IBM support. + */ + +/*? Text: "Query IPAssist failed. Assuming unsupported!\n" */ +/*? Text: "Stoplan for %s initiated by LGW\n" */ +/*? Text: "Not enough memory to add new multicast entry!\n" */ +/*? Text: "Not enough memory for debug facility.\n" */ +/*? Text: "Adding multicast address failed. Table possibly full!\n" */ +/*? Text: "Error in opening device!\n" */ +/*? Text: "LCS device %s %s IPv6 support\n" */ +/*? Text: "Device %s successfully recovered!\n" */ +/*? Text: "LCS device %s %s Multicast support\n" */ +/*? Text: " Initialization failed\n" */ +/*? Text: "Loading %s\n" */ +/*? Text: "Initialization failed\n" */ +/*? Text: "Terminating lcs module.\n" */ +/*? Text: "Device %s could not be recovered!\n" */ +/*? Text: "Initializing the lcs device driver failed\n" */ +/*? Text: "%s: The lcs device driver failed to recover the device\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/monreader +++ linux-4.14.0/Documentation/kmsg/s390/monreader @@ -0,0 +1,128 @@ +/*? + * Text: "Reading monitor data failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * The z/VM *MONITOR record device driver failed to read monitor data + * because the IUCV REPLY function failed. The read function against + * the monitor record device returns EIO. All monitor data that has been read + * since the last read with 0 size is incorrect. + * User action: + * Disregard all monitor data that has been read since the last read with + * 0 size. If the device driver has been compiled as a separate module, unload + * and reload the monreader module. If the device driver has been compiled + * into the kernel, reboot Linux. For more information about possible causes + * of the error see the IUCV section in "z/VM CP Programming Services" and + * the *MONITOR section in "z/VM Performance". + */ + +/*? + * Text: "z/VM *MONITOR system service disconnected with rc=%i\n" + * Severity: Error + * Parameter: + * @1: IPUSER SEVER return code + * Description: + * The z/VM *MONITOR record device driver receives monitor records through + * an IUCV connection to the z/VM *MONITOR system service. This connection + * has been severed and the read function of the z/VM *MONITOR device driver + * returns EIO. All data received since the last read with 0 size is incorrect. + * User action: + * Disregard all monitor data read since the last read with 0 size. Close and + * reopen the monitor record device. For information about the IPUSER SEVER + * return codes see "z/VM Performance". + */ + +/*? + * Text: "The read queue for monitor data is full\n" + * Severity: Warning + * Description: + * The read function of the z/VM *MONITOR device driver returns EOVERFLOW + * because not enough monitor data has been read since the monitor device + * has been opened. Monitor data already read are valid and subsequent reads + * return valid data but some intermediate data might be missing. + * User action: + * Be aware that monitor data might be missing. Assure that you regularly + * read monitor data after opening the monitor record device. + */ + +/*? + * Text: "Connecting to the z/VM *MONITOR system service failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: IUCV CONNECT return code + * Description: + * The z/VM *MONITOR record device driver receives monitor records through + * an IUCV connection to the z/VM *MONITOR system service. This connection + * could not be established when the monitor record device was opened. If + * the return code is 15, your z/VM guest virtual machine is not authorized + * to connect to the *MONITOR system service. + * User action: + * If the return code is 15, ensure that the IUCV *MONITOR statement is + * included in the z/VM directory entry for your z/VM guest virtual machine. + * For other IUCV CONNECT return codes see the IUCV section in "CP Programming + * Services" and the *MONITOR section in "z/VM Performance". + */ + +/*? + * Text: "Disconnecting the z/VM *MONITOR system service failed with rc=%i\n" + * Severity: Warning + * Parameter: + * @1: IUCV SEVER return code + * Description: + * The z/VM *MONITOR record device driver receives monitor data through an + * IUCV connection to the z/VM *MONITOR system service. This connection + * could not be closed when the monitor record device was closed. You might + * not be able to resume monitoring. + * User action: + * No immediate action is necessary. If you cannot open the monitor record + * device in the future, reboot Linux. For information about the IUCV SEVER + * return codes see the IUCV section in "CP Programming Services" and the + * *MONITOR section in "z/VM Performance". + */ + +/*? + * Text: "The z/VM *MONITOR record device driver cannot be loaded without z/VM\n" + * Severity: Error + * Description: + * The z/VM *MONITOR record device driver uses z/VM system services to provide + * monitor data about z/VM guest operating systems to applications on Linux. + * On Linux instances that run in environments other than the z/VM hypervisor, + * the z/VM *MONITOR record device driver does not provide any useful + * function and the corresponding monreader module cannot be loaded. + * User action: + * Load the z/VM *MONITOR record device driver only on Linux instances that run + * as guest operating systems of the z/VM hypervisor. If the z/VM *MONITOR + * record device driver has been compiled into the kernel, ignore this message. + */ + +/*? + * Text: "The z/VM *MONITOR record device driver failed to register with IUCV\n" + * Severity: Error + * Description: + * The z/VM *MONITOR record device driver receives monitor data through an IUCV + * connection and needs to register with the IUCV device driver. This + * registration failed and the z/VM *MONITOR record device driver was not + * loaded. A possible cause of this problem is insufficient memory. + * User action: + * Free some memory and try again to load the module. If the z/VM *MONITOR + * record device driver has been compiled into the kernel, you might have to + * configure more memory and reboot Linux. If you do not want to read monitor + * data, ignore this message. + */ + +/*? + * Text: "The specified *MONITOR DCSS %s does not have the required type SC\n" + * Severity: Error + * Parameter: + * @1: DCSS name + * Description: + * The DCSS that was specified with the monreader.mondcss kernel parameter or + * with the mondcss module parameter cannot be a *MONITOR DCSS because it is + * not of type SC. + * User action: + * Confirm that you are using the name of the DCSS that has been configured as + * the *MONITOR DCSS on the z/VM hypervisor. If the default name, MONDCSS, is + * used, omit the monreader.mondcss or mondcss parameter. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/monwriter +++ linux-4.14.0/Documentation/kmsg/s390/monwriter @@ -0,0 +1,17 @@ +/*? + * Text: "Writing monitor data failed with rc=%i\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * The monitor stream application device driver used the z/VM diagnose call + * DIAG X'DC' to start writing monitor data. z/VM returned an error and the + * monitor data cannot be written. If the return code is 5, your z/VM guest + * virtual machine is not authorized to write monitor data. + * User action: + * If the return code is 5, ensure that your z/VM guest virtual machine's + * entry in the z/VM directory includes the OPTION APPLMON statement. + * For other return codes see the section about DIAGNOSE Code X'DC' + * in "z/VM CP Programming Services". + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/netiucv +++ linux-4.14.0/Documentation/kmsg/s390/netiucv @@ -0,0 +1,156 @@ +/*? + * Text: "%s: The peer interface of the IUCV device has closed the connection\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the IUCV device + * Description: + * The peer interface on the remote z/VM guest virtual machine has closed the + * connection. Do not expect further packets on this interface. Any packets + * you send to this interface will be dropped. + * User action: + * None. + */ + +/*? + * Text: "%s: The IUCV device failed to connect to z/VM guest %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the IUCV device + * @2: z/VM user ID + * Description: + * The connection cannot be established because the z/VM guest virtual + * machine with the peer interface is not running. + * User action: + * Ensure that the z/VM guest virtual machine with the peer interface is + * running; then try again to establish the connection. + */ + +/*? + * Text: "%s: The IUCV device failed to connect to the peer on z/VM guest %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the IUCV device + * @2: z/VM user ID + * Description: + * The connection cannot be established because the z/VM guest virtual machine + * with the peer interface is not configured for IUCV connections. + * User action: + * Configure the z/VM guest virtual machine with the peer interface for IUCV + * connections; then try again to establish the connection. + */ + +/*? + * Text: "%s: Connecting the IUCV device would exceed the maximum number of IUCV connections\n" + * Severity: Error + * Parameter: + * @1: bus ID of the IUCV device + * Description: + * The connection cannot be established because the maximum number of IUCV + * connections has been reached on the local z/VM guest virtual machine. + * User action: + * Close some of the established IUCV connections on the local z/VM guest + * virtual machine; then try again to establish the connection. + */ + +/*? + * Text: "%s: z/VM guest %s has too many IUCV connections to connect with the IUCV device\n" + * Severity: Error + * Parameter: + * @1: bus ID of the IUCV device + * @2: remote z/VM user ID + * Description: + * Connecting to the remote z/VM guest virtual machine failed because the + * maximum number of IUCV connections for the remote z/VM guest virtual + * machine has been reached. + * User action: + * Close some of the established IUCV connections on the remote z/VM guest + * virtual machine; then try again to establish the connection. + */ + +/*? + * Text: "%s: The IUCV device cannot connect to a z/VM guest with no IUCV authorization\n" + * Severity: Error + * Parameter: + * @1: bus ID of the IUCV device + * Description: + * Because the remote z/VM guest virtual machine is not authorized for IUCV + * connections, the connection cannot be established. + * User action: + * Add the statements 'IUCV ALLOW' and 'IUCV ANY' to the z/VM directory + * entry of the remote z/VM guest virtual machine; then try again to + * establish the connection. See "z/VM CP Planning and Administration" + * for details about the IUCV statements. + */ + +/*? + * Text: "%s: Connecting the IUCV device failed with error %d\n" + * Severity: Error + * Parameter: + * @1: bus ID of the IUCV device + * @2: error code + * Description: + * The connection cannot be established because of an IUCV CONNECT error. + * User action: + * Report this problem to your support organization. + */ + +/*? + * Text: "%s: The IUCV device has been connected successfully to %s\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the IUCV device + * @2: remote z/VM user ID + * Description: + * The connection has been established and the interface is ready to + * transmit communication packages. + * User action: + * None. + */ + +/*? + * Text: "%s: The IUCV interface to %s has been established successfully\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the IUCV device + * @2: remote z/VM user ID + * Description: + * The IUCV interface to the remote z/VM guest virtual machine has been + * established and can be activated with "ifconfig up" or an equivalent + * command. + * User action: + * None. + */ + +/*? + * Text: "%s: The IUCV device is connected to %s and cannot be removed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the IUCV device + * @2: remote z/VM user ID + * Description: + * Removing a connection failed because the interface is active with a peer + * interface on a remote z/VM guest virtual machine. + * User action: + * Deactivate the interface with "ifconfig down" or an equivalent command; + * then try again to remove the interface. + */ + +/*? + * Text: "%s: The peer z/VM guest %s has closed the connection\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the IUCV device + * @2: remote z/VM user ID + * Description: + * The peer interface is no longer available. + * User action: + * Either deactivate and remove the interface, or wait for the peer + * z/VM guest to re-establish the interface. + */ + +/*? Text: "driver unloaded\n" */ +/*? Text: "driver initialized\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/numa +++ linux-4.14.0/Documentation/kmsg/s390/numa @@ -0,0 +1,11 @@ +/*? + * Text: "NUMA mode: %s\n" + * Severity: Informational + * Parameter: + * @1: mode + * Description: + * Linux started with the specified NUMA mode. + * User action: + * None. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/numa_emu +++ linux-4.14.0/Documentation/kmsg/s390/numa_emu @@ -0,0 +1,50 @@ +/*? + * Text: "Not enough memory for %d nodes, reducing node count\n" + * Severity: Warning + * Parameter: + * @1: requested number of nodes + * Description: + * Using the requested memory stripe size for emulating the requested number of + * NUMA nodes requires more than the available memory. The number of nodes is + * specified with the emu_nodes= kernel parameter. The memory stripe size to + * be used for distributing the available memory among the nodes is specified + * with the emu_size= kernel parameter. Fewer nodes were created than the + * requested number; each node has one memory stripe of the requested size. + * User action: + * Specify fewer nodes, reduce the memory stripe size, or make more memory + * available to your Linux instance. + */ + +/*? + * Text: "Creating %d nodes with memory stripe size %ld MB\n" + * Severity: Informational + * Parameter: + * @1: number of nodes + * @2: stripe size + * Description: + * NUMA emulation is activated with the reported number of NUMA nodes. + * The specified memory stripe size is used to distribute, in round-robin + * fashion, the available memory among the nodes. + * User action: + * None. + */ + +/*? + * Text: "Increasing memory stripe size from %ld MB to %ld MB\n" + * Severity: Warning + * Parameter: + * @1: requested memory stripe size + * @2: adjusted memory stripe size + * Description: + * NUMA emulation could not use the requested memory stripe size and + * therefore has increased it to the next possible value. + * The requested memory stripe size is a default value or it was specified + * with the emu_size= kernel parameter. + * The memory stripe size must be a multiple of the memory block size that + * can be read in hexadecimal notation from + * /sys/devices/system/memory/block_size_bytes. + * User action: + * To avoid this message in the future, specify a valid memory stripe size + * with the emu_size= kernel parameter. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/os_info +++ linux-4.14.0/Documentation/kmsg/s390/os_info @@ -0,0 +1,36 @@ +/*? + * Text: "entry %i: %s (addr=0x%lx size=%lu)\n" + * Severity: Informational + * Parameter: + * @1: entry ID + * @2: entry state + * @3: entry address + * @4: entry size + * Description: + * Linux is running in kdump mode and reports information defined by the + * previously running production kernel. Possible values for + * "entry state" are: + * + * - copied: The entry has been found, verified, and copied + * + * - not available: The entry has not been defined + * + * - checksum failed: The entry has been found, but it is not valid + * User action: + * If kdump fails, contact your service organization and include this message + * in the error report. + */ + +/*? + * Text: "crashkernel: addr=0x%lx size=%lu\n" + * Severity: Informational + * Parameter: + * @1: address + * @2: size + * Description: + * Linux is running in kdump mode and reports the address and size of + * the memory area that was reserved for kdump by the previously running + * production kernel. + * User action: + * None. + */ --- linux-4.14.0.orig/Documentation/kmsg/s390/perf +++ linux-4.14.0/Documentation/kmsg/s390/perf @@ -0,0 +1,90 @@ +/*? + * Text: "CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n" + * Severity: Informational + * Parameter: + * @1: cpu number + * @2: first version number + * @3: second version number + * @4: counter set authorization + * @5: counter set enable controls + * @6: counter set activation controls + * Description: + * This message displays information about the CPU-measurement counter facility + * (CPUM_CF) on a particular CPU. For details, see + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * None. + */ + +/*? + * Text: "CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n" + * Severity: Informational + * Parameter: + * @1: cpu number + * @2: authorization status for the basic-sampling function + * @3: authorization status for the diagnostic-sampling function + * @4: minimum sampling interval + * @5: maximum sampling interval + * @6: cpu speed + * Description: + * This message displays generic information about the CPU-measurement sampling + * facility (CPUM_SF) on a particular CPU. For details, see + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * None. + */ + +/*? + * Text: "CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i bsdes=%i tear=%016lx dear=%016lx\n" + * Severity: Informational + * Parameter: + * @1: cpu number + * @2: authorization control + * @3: enable control + * @4: activation control + * @5: basic-sampling-data-entry size + * @6: tear register contents + * @7: dear register contents + * Description: + * This message displays information about the basic-sampling function of the + * CPU-measurement sampling facility (CPUM_SF) on a particular CPU. + * For details, see + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * None. + */ + +/*? + * Text: "CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i dsdes=%i tear=%016lx dear=%016lx\n" + * Severity: Informational + * Parameter: + * @1: cpu number + * @2: authorization control + * @3: enable control + * @4: activation control + * @5: diagnostic-sampling-data-entry size + * @6: tear register contents + * @7: dear register contents + * Description: + * This message displays information about the diagnostic-sampling function of the + * CPU-measurement sampling facility (CPUM_SF) on a particular CPU. + * For details, see + * "The Load-Program-Parameter and the CPU-Measurement Facilities", SA23-2260. + * User action: + * None. + */ + +/*? + * Text: "The sampling facility is already reserved by %p\n" + * Severity: Warning + * Parameter: + * @1: address of perf sampling support owner + * Description: + * A process tried to reserve the sampling facility support, but it was already + * reserved by another process. + * User action: + * Check whether another process, for example, the perf program or OProfile is + * currently active. Retry activating the sampling facility after the other + * process has ended. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/prng +++ linux-4.14.0/Documentation/kmsg/s390/prng @@ -0,0 +1,103 @@ +/* prng */ + +/*? + * Text: "prng runs in TDES mode with chunksize=%d and reseed_limit=%u\n" + * Severity: Informational + * Parameter: + * @1: read chunk size in bytes + * @2: reseed limit + * Description: + * The pseudo-random number device driver started in triple DES mode. + * For IBM mainframes earlier than IBM zEnterprise EC12 (zEC12), + * triple DES is the only available mode. + * As of zEC12, the preferred mode is SHA-512. + * User action: + * If triple DES is the expected mode, no action is required. + * Otherwise, verify that the prng started with the mode= module or + * prng.mode= kernel parameter set to a value other than 1. + * The value 1 forces triple DES mode. Also ensure that the mainframe + * runs with the latest firmware level. + */ + +/*? + * Text: "The prng module stopped after running in triple DES mode\n" + * Severity: Informational + * Description: + * The pseudo-random number device driver was running in triple DES mode. + * The device driver module, prng, was unloaded, or it stopped + * because Linux shut down. + * User action: + * None. + */ + +/*? + * Text: "The prng module cannot start in SHA-512 mode\n" + * Severity: Error + * Description: + * The pseudo-random number device driver was loaded with the mode= module parameter + * or the prng.mode= kernel parameter set to 2. This setting forces SHA-512 mode, + * but the required support for MSA 5 is not available. This support requires an IBM + * zEnterprise EC12 (zEC12) or later mainframe. + * User action: + * If your mainframe is earlier than zEC12, set the mode= module or + * prng.mode= kernel parameter to 0 or 1 to run the + * pseudo-random number device driver in triple DES mode. + * Otherwise, ensure that MSA 5 support available. + */ + +/*? + * Text: "prng runs in SHA-512 mode with chunksize=%d and reseed_limit=%u\n" + * Severity: Informational + * Parameter: + * @1: read chunk size in bytes + * @2: reseed limit + * Description: + * The pseudo-random number device driver started in SHA-512 mode. + * As of IBM zEnterprise EC12, this is the preferred mode. + * User action: + * None. + */ + +/*? + * Text: "The prng module stopped after running in SHA-512 mode\n" + * Severity: Informational + * Description: + * The pseudo-random number device driver was running in SHA-512 mode. + * The device driver module, prng, was unloaded, or stopped + * because Linux shut down. + * User action: + * None. + */ + +/*? + * Text: "The prng self test state test for the SHA-512 mode failed\n" + * Severity: Error + * Description: + * The pseudo-random number device driver is not operational because the self test failed. + * After processing a published National Institute of Standards and Technology (NIST) test vector for the + * Deterministic Random Bit Generator (DRBG) algorithm, the device driver + * was not in the expected working state. This failure might indicate + * that the cryptographic software or hardware is not working correctly. + * The processed NIST test vector was: Hash Drbg, Sha-512, Count #0. + * User action: + * Unload and reload the prng module, or + * if prng was compiled into the kernel, restart Linux. + * If the error persists, contact your support organization. + */ + +/*? + * Text: "The prng self test data test for the SHA-512 mode failed\n" + * Severity: Error + * Description: + * The pseudo-random number device driver is not operational because the self test failed. + * After processing a published National Institute of Standards and Technology (NIST) test vector for the + * Deterministic Random Bit Generator (DRBG) algorithm, the device driver + * did not produce the expected pseudo-random data. This failure might indicate + * that the cryptographic software or hardware is not working correctly. + * The processed NIST test vector was: Hash Drbg, Sha-512, Count #0. + * User action: + * Unload and reload the prng module, or + * if prng was compiled into the kernel, restart Linux. + * If the error persists, contact your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/qeth +++ linux-4.14.0/Documentation/kmsg/s390/qeth @@ -0,0 +1,929 @@ +/*? + * Text: "%s: The LAN is offline\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A start LAN command was sent by the qeth device driver but the physical or + * virtual adapter has not started the LAN. The LAN might take a few seconds + * to become available. + * User action: + * Check the status of the qeth device, for example, with the lsqeth command. + * If the device does not become operational within a few seconds, initiate a + * recovery process, for example, by writing '1' to the 'recover' sysfs + * attribute of the device. + */ + +/*? + * Text: "%s: A recovery process has been started for the device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A recovery process was started either by the qeth device driver or through + * a user command. + * User action: + * Wait until a message indicates the completion of the recovery process. + */ + +/*? + * Text: "%s: The qeth device driver failed to recover an error on the device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth device driver performed an automatic recovery operation to recover + * an error on a qeth device. The recovery operation failed. + * User action: + * Try the following actions in the given order: i) Check the status of the + * qeth device, for example, with the lsqeth command. ii) Initiate a recovery + * process by writing '1' to the 'recover' sysfs attribute of the device. + * iii) Ungroup and regroup the subchannel triplet of the device. vi) Reboot + * Linux. v) If the problem persists, gather Linux debug data and report the + * problem to your support organization. + */ + +/*? + * Text: "%s: Device recovery failed to restore all offload features\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth device driver performed a recovery operation on a qeth device. Part + * of the recovery is to restore the offload features that were enabled before + * the recovery. At least one of those offload features could not be restored. + * User action: + * Check which offload features are enabled on the device, for example with + * the "ethtool -k" command. Try to explicitly re-enable the missing offload + * features for the device, for example with the "ethtool -K" command. + */ + +/*? + * Text: "%s: The link for interface %s on CHPID 0x%X failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * @3: CHPID + * Description: + * A network link failed. A possible reason for this error is that a physical + * network cable has been disconnected. + * User action: + * Ensure that the network cable on the adapter hardware is connected properly. + * If the connection is to a guest LAN, ensure that the device is still coupled + * to the guest LAN. + */ + +/*? + * Text: "%s: The link for %s on CHPID 0x%X has been restored\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * @3: CHPID + * Description: + * A failed network link has been re-established. A device recovery is in + * progress. + * User action: + * Wait until a message indicates the completion of the recovery process. + */ + +/*? + * Text: "%s: A hardware operation timed out on the device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A hardware operation timed out on the qeth device. + * User action: + * Check the status of the qeth device, for example, with the lsqeth command. + * If the device is not operational, initiate a recovery process, for example, + * by writing '1' to the 'recover' sysfs attribute of the device. + */ + +/*? + * Text: "%s: The adapter hardware is of an unknown type\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth device driver does not recognize the adapter hardware. The cause + * of this problem could be a hardware error or a Linux level that does not + * support your adapter hardware. + * User action: + * i) Investigate if your adapter hardware is supported by your Linux level. + * Consider using hardware that is supported by your Linux level or upgrading + * to a Linux level that supports your hardware. ii) Install the latest + * firmware on your adapter hardware. iii) If the problem persists and is not + * caused by a version mismatch, contact IBM support. + */ + +/*? + * Text: "%s: The adapter is used exclusively by another host\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth adapter is exclusively used by another host. + * User action: + * Use another qeth adapter or configure this one not exclusively to a + * particular host. + */ + +/*? + * Text: "%s: QDIO reported an error, rc=%i\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: return code + * Description: + * The QDIO subsystem reported an error. + * User action: + * Check for related QDIO errors. Check the status of the qeth device, for + * example, with the lsqeth command. If the device is not operational, initiate + * a recovery process, for example, by writing '1' to the 'recover' sysfs + * attribute of the device. + */ + +/*? + * Text: "%s: There is no kernel module to support discipline %d\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * @2: discipline + * Description: + * The qeth device driver or a user command requested a kernel module for a + * particular qeth discipline. Either the discipline is not supported by the + * qeth device driver or the requested module is not available to your Linux + * system. + * User action: + * Check if the requested discipline module has been compiled into the kernel + * or is present in /lib/modules//kernel/drivers/s390/net. + */ + +/*? + * Text: "Initializing the qeth device driver failed\n" + * Severity: Error + * Parameter: + * Description: + * The base module of the qeth device driver could not be initialized. + * User action: + * See errno.h to determine the reason for the error. + * i) Reboot Linux. ii) If the problem persists, gather Linux debug data and + * report the problem to your support organization. + */ + +/*? + * Text: "%s: Registering IP address %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: IP address + * Description: + * An IP address could not be registered with the network adapter. + * User action: + * Check if another operating system instance has already registered the + * IP address with the same network adapter or at the same logical IP subnet. + */ + +/*? + * Text: "%s: Reading the adapter MAC address failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth device driver could not read the MAC address from the network + * adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Starting ARP processing support for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not start ARP support on the network adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Starting IP fragmentation support for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not start IP fragmentation support on the + * network adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Starting VLAN support for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not start VLAN support on the network adapter. + * User action: + * None if you do not require VLAN support. If you need VLAN support, + * ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Starting multicast support for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not start multicast support on the network + * adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Activating IPv6 support for %s failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not activate IPv6 support on the network + * adapter. + * User action: + * None if you do not require IPv6 communication. If you need IPv6 support, + * ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Enabling the passthrough mode for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not enable the passthrough mode on the + * network adapter. The passthrough mode is required for all network traffic + * other than IPv4. In particular, the passthrough mode is required for IPv6 + * traffic. + * User action: + * None if all you want to support is IPv4 communication. If you want to support + * IPv6 or other network traffic apart from IPv4, ungroup and regroup the + * subchannel triplet of the device. If this does not resolve the problem, + * reboot Linux. If the problem persists, gather Linux debug data and report + * the problem to your support organization. + */ + +/*? + * Text: "%s: Enabling broadcast filtering for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not enable broadcast filtering on the network + * adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Setting up broadcast filtering for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not set up broadcast filtering on the network + * adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Setting up broadcast echo filtering for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not set up broadcast echo filtering on the + * network adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: Starting HW checksumming for %s failed, using SW checksumming\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The network adapter supports hardware checksumming for IP packages + * but the qeth device driver could not start hardware checksumming on the + * adapter. The qeth device driver continues to use software checksumming for + * IP packages. + * User action: + * None if you do not require hardware checksumming for network + * traffic. If you want to enable hardware checksumming, ungroup and regroup + * the subchannel triplet of the device. If this does not resolve the problem, + * reboot Linux. If the problem persists, gather Linux debug data and report + * the problem to your support organization. + */ + +/*? + * Text: "%s: Enabling HW checksumming for %s failed, using SW checksumming\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The network adapter supports hardware checksumming for IP packages + * but the qeth device driver could not enable hardware checksumming on the + * adapter. The qeth device driver continues to use software checksumming for + * IP packages. + * User action: + * None if you do not require hardware checksumming for network + * traffic. If you want to enable hardware checksumming, ungroup and regroup + * the subchannel triplet of the device. If this does not resolve the problem, + * reboot Linux. If the problem persists, gather Linux debug data and report + * the problem to your support organization. + */ + +/*? + * Text: "%s: Starting outbound TCP segmentation offload for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The network adapter supports TCP segmentation offload, but the qeth device + * driver could not start this support on the adapter. + * User action: + * None if you do not require TCP segmentation offload. If you want to + * enable TCP segmentation offload, ungroup and regroup the subchannel triplet + * of the device. If this does not resolve the problem, reboot Linux. If the + * problem persists, gather Linux debug data and report the problem to your + * support organization. + */ + +/*? + * Text: "%s: The network adapter failed to generate a unique ID\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * In IBM mainframe environments, network interfaces are not identified by + * a specific MAC address. Therefore, the network adapters provide the network + * interfaces with unique IDs to be used in their IPv6 link local addresses. + * Without such a unique ID, duplicate addresses might be assigned in other + * LPARs. + * User action: + * Install the latest firmware on the adapter hardware. Manually, configure + * an IPv6 link local address for this device. + */ + +/*? + * Text: "There is no IPv6 support for the layer 3 discipline\n" + * Severity: Warning + * Description: + * If you want to use IPv6 with the layer 3 discipline, you need a Linux kernel + * with IPv6 support. Because your Linux kernel has not been compiled with + * IPv6 support, you cannot use IPv6 with the layer 3 discipline, even if your + * adapter supports IPv6. + * User action: + * Use a Linux kernel that has been complied to include IPv6 support if you + * want to use IPv6 with layer 3 qeth devices. + */ + +/*? + * Text: "%s: The qeth device is not configured for the OSI layer required by z/VM\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A qeth device that connects to a virtual network on z/VM must be configured for the + * same Open Systems Interconnection (OSI) layer as the virtual network. An ETHERNET + * guest LAN or VSWITCH uses the data link layer (layer 2) while an IP guest LAN + * or VSWITCH uses the network layer (layer 3). + * User action: + * If you are connecting to an ETHERNET guest LAN or VSWITCH, set the layer2 sysfs + * attribute of the qeth device to 1. If you are connecting to an IP guest LAN or + * VSWITCH, set the layer2 sysfs attribute of the qeth device to 0. + */ + +/*? + * Text: "%s: Starting source MAC-address support for %s failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The qeth device driver could not enable source MAC-address on the network + * adapter. + * User action: + * Ungroup and regroup the subchannel triplet of the device. If this does not + * resolve the problem, reboot Linux. If the problem persists, gather Linux + * debug data and report the problem to your support organization. + */ + +/*? + * Text: "%s: MAC address %pM already exists\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: MAC-address + * Description: + * Setting the MAC address for the qeth device fails, because this + * MAC address is already defined on the OSA CHPID. + * User action: + * Use a different MAC address for this qeth device. + */ + +/*? + * Text: "%s: MAC address %pM is not authorized\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: MAC-address + * Description: + * This qeth device is a virtual network interface card (NIC), to which z/VM + * has already assigned a MAC address. z/VM MAC address verification does + * not allow you to change this predefined address. + * User action: + * None; use the MAC address that has been assigned by z/VM. + */ + +/*? + * Text: "%s: The HiperSockets network traffic analyzer is activated\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The sysfs 'sniffer' attribute of the HiperSockets device has the value '1'. + * The corresponding HiperSockets interface has been switched into promiscuous mode. + * As a result, the HiperSockets network traffic analyzer is started on the device. + * User action: + * None. + */ + + /*? + * Text: "%s: The HiperSockets network traffic analyzer is deactivated\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The sysfs 'sniffer' attribute of the HiperSockets device has the value '1'. + * Promiscuous mode has been switched off for the corresponding HiperSockets interface + * As a result, the HiperSockets network traffic analyzer is stopped on the device. + * User action: + * None. + */ + +/*? + * Text: "%s: The device is not authorized to run as a HiperSockets network traffic analyzer\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The sysfs 'sniffer' attribute of the HiperSockets device has the value '1'. + * The corresponding HiperSockets interface is switched into promiscuous mode + * but the network traffic analyzer (NTA) rules configured at the Support Element (SE) + * do not allow tracing. Possible reasons are: + * - Tracing is not authorized for all HiperSockets LANs in the mainframe system + * - Tracing is not authorized for this HiperSockets LAN + * - LPAR is not authorized to enable an NTA + * User action: + * Configure appropriate HiperSockets NTA rules at the SE. + */ + +/*? + * Text: "%s: A HiperSockets network traffic analyzer is already active in the HiperSockets LAN\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The sysfs 'sniffer' attribute of the HiperSockets device has the value '1'. + * The HiperSockets interface is switched into promiscuous mode but another + * HiperSockets device on the same HiperSockets LAN is already running as + * a network traffic analyzer. + * A HiperSockets LAN can only have one active network traffic analyzer. + * User action: + * Do not configure multiple HiperSockets devices in the same HiperSockets LAN as + * tracing devices. + */ + +/*? + * Text: "%s: Enabling HW TX checksumming for %s failed, using SW TX checksumming\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * Description: + * The network adapter supports hardware checksumming for outgoing IP packages + * but the qeth device driver could not enable hardware TX checksumming on the + * adapter. The qeth device driver continues to use software checksumming for + * outgoing IP packages. + * User action: + * None if you do not require hardware checksumming for outgoing network + * traffic. If you want to enable hardware checksumming, ungroup and regroup + * the subchannel triplet of the device. If this does not resolve the problem, + * reboot Linux. If the problem persists, gather Linux debug data and report + * the problem to your support organization. + */ + +/*? + * Text: "%s: A connection could not be established because of an OLM limit\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * z/OS has activated Optimized Latency Mode (OLM) for a connection through an OSA Express3 adapter. + * This reduces the maximum number of concurrent connections per physical port for shared adapters. + * The new connection would exceed the maximum. Linux cannot establish further connections using + * this adapter. + * User action: + * If possible, deactivate an existing connection that uses this adapter and try again to establish + * the new connection. If you cannot free an existing connection, use a different adapter for the + * new connection. + */ + +/*? + * Text: "%s: Setting the device online failed because of insufficient authorization\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The qeth device is configured with OSX CHPIDs. An OSX CHPID cannot be activated unless the LPAR is explicitly authorized to access it. + * For z/VM guest operating systems, the z/VM user ID must be explicitly authorized in addition to the LPAR. + * You grant these authorizations through the Service Element. + * User action: + * At the Service Element, authorize the LPAR and, if applicable, the z/VM user ID for using the OSX CHPIDs with which the qeth device has been configured. + * Then try again to set the device online. + */ + +/*? + * Text: "%s: portname is deprecated and is ignored\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * An OSA-Express port name was required to identify a shared OSA port. + * All operating system instances that shared the port had to use the same port name. + * This requirement no longer applies, and the specified portname attribute is ignored. + * User action: + * For future upgrades, remove OSA port name specifications from your + * network configuration. + */ + +/*? Text: "core functions removed\n" */ +/*? Text: "%s: Device is a%s card%s%s%s\nwith link type %s.\n" */ +/*? Text: "%s: issue_next_read failed: no iob available!\n" */ +/*? Text: "%s: Priority Queueing not supported\n" */ +/*? Text: "%s: sense data available. cstat 0x%X dstat 0x%X\n" */ +/*? Text: "loading core functions\n" */ +/*? Text: "%s: MAC address %pM successfully registered on device %s\n" */ +/*? Text: "%s: Device successfully recovered!\n" */ +/*? Text: "register layer 2 discipline\n" */ +/*? Text: "unregister layer 2 discipline\n" */ +/*? Text: "%s: Hardware IP fragmentation not supported on %s\n" */ +/*? Text: "%s: IPv6 not supported on %s\n" */ +/*? Text: "%s: VLAN not supported on %s\n" */ +/*? Text: "%s: Inbound source MAC-address not supported on %s\n" */ +/*? Text: "%s: IPV6 enabled\n" */ +/*? Text: "%s: ARP processing not supported on %s!\n" */ +/*? Text: "%s: Hardware IP fragmentation enabled \n" */ +/*? Text: "%s: set adapter parameters not supported.\n" */ +/*? Text: "%s: VLAN enabled\n" */ +/*? Text: "register layer 3 discipline\n" */ +/*? Text: "%s: Outbound TSO enabled\n" */ +/*? Text: "%s: Broadcast not supported on %s\n" */ +/*? Text: "%s: Outbound TSO not supported on %s\n" */ +/*? Text: "%s: Inbound HW Checksumming not supported on %s,\ncontinuing using Inbound SW Checksumming\n" */ +/*? Text: "%s: Using no checksumming on %s.\n" */ +/*? Text: "%s: Broadcast enabled\n" */ +/*? Text: "%s: Multicast not supported on %s\n" */ +/*? Text: "%s: Using SW checksumming on %s.\n" */ +/*? Text: "%s: HW Checksumming (%sbound) enabled\n" */ +/*? Text: "unregister layer 3 discipline\n" */ +/*? Text: "%s: Multicast enabled\n" */ +/*? Text: "%s: QDIO data connection isolation is deactivated\n" */ +/*? Text: "%s: QDIO data connection isolation is activated\n" */ +/*? Text: "%s: Adapter does not support QDIO data connection isolation\n" */ +/*? Text: "%s: Adapter is dedicated. QDIO data connection isolation not supported\n" */ +/*? Text: "%s: TSO does not permit QDIO data connection isolation\n" */ +/*? Text: "%s: HW TX Checksumming enabled\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "qeth_l3: ignoring TR device\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ + +/*? + * Text: "%s: Turning off reflective relay mode at the adjacent switch failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The policy for the QDIO data connection isolation was + * changed successfully, and communications are now handled according to the + * new policy. The ISOLATION_FORWARD policy is no longer used, but the qeth + * device driver could not turn off the reflective relay mode on the adjacent + * switch port. + * User action: + * Check the adjacent switch for errors and correct the problem. + */ + +/*? + * Text: "%s: The adjacent switch port does not support reflective relay mode\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The 'isolation' sysfs attribute of the qeth device could not be set to 'forward'. + * This setting selects the ISOLATION_FORWARD policy for the QDIO data connection + * isolation. The ISOLATION_FORWARD policy requires a network adapter in Virtual + * Ethernet Port Aggregator (VEPA) mode with an adjacent switch port in reflective + * relay mode. + * User action: + * Use a switch port that supports reflective relay mode if you want to use the + * ISOLATION_FORWARD policy for the qeth device. + */ + +/*? + * Text: "%s: The reflective relay mode cannot be enabled at the adjacent switch port" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The 'isolation' sysfs attribute of the qeth device could not be set to 'forward'. + * This setting selects the ISOLATION_FORWARD policy for the QDIO data connection + * isolation. The ISOLATION_FORWARD policy requires a network adapter in Virtual + * Ethernet Port Aggregator (VEPA) mode with an adjacent switch port in reflective relay + * mode. The qeth device driver failed to enable the required reflective relay mode on + * the adjacent switch port although the switch port supports this mode. + * User action: + * Enable reflective relay mode on the switch for the adjacent port and try again. + */ + +/*? + * Text: "%s: Interface %s is down because the adjacent port is no longer in reflective relay mode\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * @2: interface name + * Description: + * The ISOLATION_FORWARD policy is active for the QDIO data connection isolation + * of the qeth device. This policy requires a network adapter in Virtual Ethernet + * Port Aggregator (VEPA) mode with an adjacent switch port in reflective relay mode. + * The reflective relay mode on the adjacent switch port was disabled. The qeth device + * was set offline and the interface was deactivated to prevent any unintended network traffic. + * User action: + * Enable the reflective relay mode again on the adjacent port or use the 'isolation' + * sysfs attribute of the qeth device to set a different policy for the QDIO data connection + * isolation. You can then resume operations by setting the qeth device back + * online and activating the interface. + */ + +/*? + * Text: "%s: Failed to create completion queue\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The HiperSockets device could not be configured with a completion queue. + * A completion queue is required to operate AF_IUCV communication in an LPAR. + * User action: + * i) Investigate if you have the latest firmware level in place. + * ii) If the problem persists and is not caused by a version mismatch, contact IBM + * support. + */ + +/*? + * Text: "%s: Completion Queueing supported\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The HiperSockets device supports completion queueing. This is required to + * set up AF_IUCV communication in an LPAR. + */ + +/*? + * Text: "%s: Completion Queue support enabled" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The HiperSockets device is enabled for completion queueing. This is part of + * the process to set up AF_IUCV communication in an LPAR. + */ + +/*? + * Text: "%s: Completion Queue support disabled" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The HiperSockets device is disabled for completion queueing. This device + * cannot or no longer be used to set up AF_IUCV communication in an LPAR. + */ + +/*? + * Text: "%s: The device represents a Bridge Capable Port\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * Description: + * You can configure this device as a Bridge Port. + * User action: + * None. + */ + +/*? + * Text: "%s: The device is not configured as a Bridge Port\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The Bridge Port role cannot be withdrawn from a device + * that is not configured as a Bridge Port. + * User action: + * None. + */ + +/*? + * Text: "%s: The LAN already has a primary Bridge Port\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A LAN can have multiple secondary Bridge Ports, but only + * one primary Bridge Port. Configuring the device as a + * primary Bridge Port failed because another port on the + * LAN has been configured as the primary Bridge Port. + * User action: + * Find out which operating system instance has configured the primary + * Bridge Port. Assure that the primary role for this port is withdrawn + * before trying again to configure your device as the primary Bridge + * Port. Alternatively, consider configuring your device as a secondary + * Bridge Port. + */ + +/*? + * Text: "%s: The device is already a secondary Bridge Port\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A device cannot be configured as a primary or secondary + * Bridge Port if it is already configured as a secondary Bridge Port. + * User action: + * None, if you want the device to be a secondary Bridge Port. + * If you want to configure the device as the primary Bridge Port, + * withdraw the secondary role by writing 'none' to the 'bridgeport_role' + * sysfs attribute of the device. Then try again to configure the + * device as the primary Bridge Port. + */ + +/*? + * Text: "%s: The LAN cannot have more secondary Bridge Ports\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A LAN can have up to five secondary Bridge Ports. + * You cannot configure a further device as a secondary + * Bridge Port unless the Bridge Ports role is withdrawn from one of + * the existing secondary Bridge Ports. + * User action: + * Assure that the Bridge Port role is withdrawn from one of the + * existing secondary Bridge Ports before trying again to configure your + * device as a secondary Bridge Port. + */ + +/*? + * Text: "%s: The device is already a primary Bridge Port\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * A device cannot be configured as a primary or secondary + * Bridge Port if it is already configured as a primary Bridge Port. + * User action: + * None, if you want the device to be a primary Bridge Port. + * If you want to configure the device as a secondary Bridge Port, + * withdraw the primary role by writing 'none' to the 'bridgeport_role' + * sysfs attribute of the device. Then try again to configure the + * device as the secondary Bridge Port. + */ + +/*? + * Text: "%s: The device is not authorized to be a Bridge Port\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * The device cannot be configured as a Bridge Port because + * the required authorizations in the hardware are not in place. + * User action: + * See your hardware documentation about how to authorize + * ports for becoming a Bridge Port. + */ + +/*? + * Text: "%s: A Bridge Port is already configured by a different operating system\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * Linux instances cannot configure the target port as a Bridge Port. + * Another operating system already uses a Bridge Port on the HiperSockets + * or on the OSA adapter. For example, a z/VM instance might be using + * a port in a VSWITCH configuration. Multiple Bridge Ports on the same + * HiperSockets or OSA adapter must be configured by instances of the same + * operating system, for example, all Linux or all z/VM. + * User action: + * Reconsider your network topology. Configure Bridge Ports only for ports + * on adapters where any other Bridge Ports are configured by other Linux + * instances. + */ + +/*? + * Text: "%s: Setting address notification failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the qeth device + * Description: + * Enabling or disabling the address notification feature of a + * HiperSockets device failed. The device might not be configured as a + * Bridge Port. + * User action: + * None, unless you need address notifications for this device. + * If you need notifications, confirm that your device is attached to a + * HiperSockets LAN that supports Bridge Capable Ports and that your + * device is configured as a Bridge Port. If the 'bridgeport_role' + * sysfs attribute of the device contains, one of the values 'primary' + * or 'secondary' and you cannot set the address notification, contact + * your support organization. + */ + +/*? + * Text: "%s: Address notification from the Bridge Port stopped %s (%s)\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the qeth device + * @2: network interface name + * @3: error reported by the hardware + * Description: + * A Bridge Port no longer provides address notifications. + * Possible reasons include traffic overflow and that the device is no + * longer configured as a Bridge Port. A udev event with + * BRIDGEDHOST=abort was emitted to alert applications that rely on the + * address notifications. + * User action: + * None. + */ + +/*? + * Text: "%s: The qeth driver ran out of channel command buffers\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the qeth device + * Description: + * Command buffers can temporarily run out during periods of + * intense network configuration activities. + * The device driver recovers from this condition as outstanding + * commands are completed. + * User action: + * Wait for a short time. If the problem persists, + * initiate a recovery process by writing '1' to the 'recover' + * sysfs attribute of the device. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/s390dbf +++ linux-4.14.0/Documentation/kmsg/s390/s390dbf @@ -0,0 +1,83 @@ +/*? + * Text: "Root becomes the owner of all s390dbf files in sysfs\n" + * Severity: Warning + * Description: + * The S/390 debug feature you are using only supports uid/gid = 0. + * User action: + * None. + */ + +/*? + * Text: "Registering debug feature %s failed\n" + * Severity: Error + * Parameter: + * @1: feature name + * Description: + * The initialization of an S/390 debug feature failed. A likely cause of this + * problem is memory constraints. The system keeps running, but the debug + * data for this feature will not be available in sysfs. + * User action: + * Consider assigning more memory to your LPAR or z/VM guest virtual machine. + */ + +/*? + * Text: "Registering view %s/%s would exceed the maximum number of views %i\n" + * Severity: Error + * Parameter: + * @1: feature name + * @2: view name + * @3: maximum + * Description: + * The maximum number of allowed debug feature views has been reached. The + * view has not been registered. The system keeps running but the new view + * will not be available in sysfs. This is a program error. + * User action: + * Report this problem to your support partner. + */ + +/*? + * Text: "%s is not a valid level for a debug feature\n" + * Severity: Warning + * Parameter: + * @1: level + * Description: + * Setting a new level for a debug feature by using the 'level' sysfs attribute + * failed. Valid levels are the minus sign (-) and the integers in the + * range 0 to 6. The minus sign switches off the feature. The numbers switch + * the feature on, where higher numbers produce more debug output. + * User action: + * Write a valid value to the 'level' sysfs attribute. + */ + +/*? + * Text: "Flushing debug data failed because %c is not a valid area\n" + * Severity: Informational + * Parameter: + * @1: debug area number + * Description: + * Flushing a debug area by using the 'flush' sysfs attribute failed. Valid + * values are the minus sign (-) for flushing all areas, or the number of the + * respective area for flushing a single area. + * User action: + * Write a valid area number or the minus sign (-) to the 'flush' sysfs + * attribute. + */ + +/*? + * Text: "Allocating memory for %i pages failed\n" + * Severity: Informational + * Parameter: + * @1: number of pages + * Description: + * Setting the debug feature size by using the 'page' sysfs attribute failed. + * Linux did not have enough memory for expanding the debug feature to the + * requested size. + * User action: + * Use a smaller number of pages for the debug feature or allocate more + * memory to your LPAR or z/VM guest virtual machine. + */ + +/*? Text: "%s: set new size (%i pages)\n" */ +/*? Text: "%s: switched off\n" */ +/*? Text: "%s: level %i is out of range (%i - %i)\n" */ +/*? Text: "Registering view %s/%s failed due to out of memory\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/sclp_cmd +++ linux-4.14.0/Documentation/kmsg/s390/sclp_cmd @@ -0,0 +1,44 @@ +/*? Text: "sync request failed (cmd=0x%08x, status=0x%02x)\n" */ +/*? Text: "readcpuinfo failed (response=0x%04x)\n" */ +/*? Text: "configure cpu failed (cmd=0x%08x, response=0x%04x)\n" */ +/*? Text: "configure channel-path failed (cmd=0x%08x, response=0x%04x)\n" */ +/*? Text: "read channel-path info failed (response=0x%04x)\n" */ +/*? Text: "assign storage failed (cmd=0x%08x, response=0x%04x, rn=0x%04x)\n" */ +/*? Text: "configure PCI I/O adapter failed: cmd=0x%08x response=0x%04x\n" */ +/*? Text: "request failed (status=0x%02x)\n" */ +/*? Text: "request failed with response code 0x%x\n" */ + +/*? + * Text: "Memory hotplug state changed, suspend refused.\n" + * Severity: Error + * Description: + * Suspend is refused after a memory hotplug operation was performed. + * User action: + * The system needs to be restarted and no memory hotplug operation must be + * performed in order to allow suspend. + */ + +/*? + * Text: "Standby memory at 0x%llx (%lluM of %lluM usable)\n" + * Severity: Informational + * Parameter: + * @1: start address of standby memory + * @2: usable memory in MB + * @3: total detected memory in MB + * Description: + * Standby memory was detected. It can be used for memory hotplug only + * if it is aligned to the Linux hotplug memory block size. + * If the aligned amount of memory matches the total amount, + * all detected standby memory can be used. Otherwise, some of the detected + * memory is unaligned and cannot be used. + * User action: + * None, if the usable and the total amount of detected standby memory match. + * If the amounts of memory do not match, + * check the memory setup of your guest virtual machine and ensure that + * the standby memory start and end + * address is aligned to the Linux hotplug memory block size. + * On Linux, issue "cat /sys/devices/system/memory/block_size_bytes" + * to find the hotplug memory block size value in hexadecimal notation. + * On z/VM, query your memory setup with "vmcp q v store". + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/sclp_config +++ linux-4.14.0/Documentation/kmsg/s390/sclp_config @@ -0,0 +1,15 @@ +/*? + * Text: "CPU capability may have changed\n" + * Severity: Informational + * Description: + * The capability of the CPUs in the configuration may have been upgraded + * or downgraded. This message may also appear if the capability of the + * CPUs in the configuration did not change. + * For details see the STORE SYSTEM INFORMATION description in the + * "Principles of Operation." + * User action: + * The user can examine /proc/sysinfo for CPU capability values. + */ +/*? Text: "Open for Business request failed with response code 0x%04x\n" */ +/*? Text: "SCLP receiver did not register to receive Configuration Management Data Events.\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/sclp_cpi +++ linux-4.14.0/Documentation/kmsg/s390/sclp_cpi @@ -0,0 +1,3 @@ +/*? Text: "request failed (status=0x%02x)\n" */ +/*? Text: "request failed with response code 0x%x\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/sclp_ocf +++ linux-4.14.0/Documentation/kmsg/s390/sclp_ocf @@ -0,0 +1 @@ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/sclp_sdias +++ linux-4.14.0/Documentation/kmsg/s390/sclp_sdias @@ -0,0 +1,4 @@ +/*? Text: "sclp_send failed for get_nr_blocks\n" */ +/*? Text: "SCLP error: %x\n" */ +/*? Text: "sclp_send failed: %x\n" */ +/*? Text: "Error from SCLP while copying hsa. Event status = %x\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/scm_block +++ linux-4.14.0/Documentation/kmsg/s390/scm_block @@ -0,0 +1,51 @@ +/*? + * Text: "%lx: The capabilities of the SCM increment changed\n" + * Severity: Informational + * Parameter: + * @1: start address of the SCM increment + * Description: + * A configuration change is in progress for the storage class memory (SCM) + * increment. + * User action: + * Verify that the capability of the SCM increment is as intended; for + * example, with lsscm. + */ + +/*? + * Text: "An I/O operation to SCM failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * An error occurred during I/O to storage class memory (SCM). The operation + * was repeated, but the maximum number of retries was exceeded before the + * request could be fulfilled. + * User action: + * Contact your support organization. + */ + +/*? + * Text: "%lx: Write access to the SCM increment is suspended\n" + * Severity: Informational + * Parameter: + * @1: start address of the SCM increment + * Description: + * A concurrent firmware upgrade is in progress. For the duration of the + * upgrade, write access to the storage class memory (SCM) increment has been + * suspended. + * User action: + * None. + */ + +/*? + * Text: "%lx: Write access to the SCM increment is restored\n" + * Severity: Informational + * Parameter: + * @1: start address of the SCM increment + * Description: + * Write access to the storage class memory (SCM) increment was restored + * after a temporary suspension during a concurrent firmware upgrade. + * User action: + * None. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/setup +++ linux-4.14.0/Documentation/kmsg/s390/setup @@ -0,0 +1,165 @@ +/*? + * Text: "The initial RAM disk does not fit into the memory\n" + * Severity: Error + * Description: + * The load address and the size of the initial RAM disk specify a memory + * area that is not available. + * User action: + * Lower the load address of the initial RAM disk, reduce the size of the + * initial RAM disk, or increase the size of the system memory to make the + * initial RAM disk fit into the memory. + */ + +/*? + * Text: "The maximum memory size is %luMB\n" + * Severity: Notice + * Parameter: + * @1: size in MB + * Description: + * The system memory size cannot exceed the amount of memory that is + * provided by the real or virtual hardware. It can be further reduced + * through an upper memory address limit that is specified with the + * mem= kernel parameter. + * User action: + * None. + */ + +/*? + * Text: "Linux is running as a z/VM guest operating system in 31-bit mode\n" + * Severity: Informational + * Description: + * The 31-bit Linux kernel detected that it is running as a guest operating + * system of the z/VM hypervisor. + * User action: + * None. + */ + +/*? + * Text: "Linux is running natively in 31-bit mode\n" + * Severity: Informational + * Description: + * The 31-bit Linux kernel detected that it is running on an IBM mainframe, + * either as the sole operating system in an LPAR or as the sole operating + * system on the entire mainframe. The Linux kernel is not running as a + * guest operating system of the z/VM hypervisor. + * User action: + * None. + */ + +/*? + * Text: "The hardware system has IEEE compatible floating point units\n" + * Severity: Informational + * Description: + * The Linux kernel detected that it is running on a hardware system with + * CPUs that have IEEE compatible floating point units. + * User action: + * None. + */ + +/*? + * Text: "The hardware system has no IEEE compatible floating point units\n" + * Severity: Informational + * Description: + * The Linux kernel detected that it is running on a hardware system with + * CPUs that do not have IEEE compatible floating point units. + * User action: + * None. + */ + +/*? + * Text: "Linux is running as a z/VM guest operating system in 64-bit mode\n" + * Severity: Informational + * Description: + * The 64-bit Linux kernel detected that it is running as a guest operating + * system of the z/VM hypervisor. + * User action: + * None. + */ + +/*? + * Text: "Linux is running under KVM in 64-bit mode\n" + * Severity: Informational + * Description: + * The 64-bit Linux kernel detected that it is running as a guest operating + * system of the KVM hypervisor. + * User action: + * None. + */ + +/*? + * Text: "Linux is running natively in 64-bit mode\n" + * Severity: Informational + * Description: + * The 64-bit Linux kernel detected that it is running on an IBM mainframe, + * either as the sole operating system in an LPAR or as the sole operating + * system on the entire mainframe. The Linux kernel is not running as a + * guest operating system of the z/VM hypervisor. + * User action: + * None. + */ + +/*? + * Text: "Defining the Linux kernel NSS failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * The Linux kernel could not define the named saved system (NSS) with + * the z/VM CP DEFSYS command. The return code represents the numeric + * portion of the CP DEFSYS error message. + * User action: + * For return code 1, the z/VM guest virtual machine is not authorized + * to define named saved systems. + * Ensure that the z/VM guest virtual machine is authorized to issue + * the CP DEFSYS command (typically privilege class E). + * For other return codes, see the help and message documentation for + * the CP DEFSYS command. + */ + +/*? + * Text: "Saving the Linux kernel NSS failed with rc=%d\n" + * Severity: Error + * Parameter: + * @1: return code + * Description: + * The Linux kernel could not save the named saved system (NSS) with + * the z/VM CP SAVESYS command. The return code represents the numeric + * portion of the CP SAVESYS error message. + * User action: + * For return code 1, the z/VM guest virtual machine is not authorized + * to save named saved systems. + * Ensure that the z/VM guest virtual machine is authorized to issue + * the CP SAVESYS command (typically privilege class E). + * For other return codes, see the help and message documentation for + * the CP SAVESYS command. + */ + +/*? + * Text: "crashkernel reservation failed: %s\n" + * Severity: Informational + * Parameter: + * @1: reason string + * Description: + * The memory reservation for the kdump "crashkernel" parameter was not + * successful. The Linux kernel was either not able to find a free memory + * area or an invalid area has been defined. The reason string describes the + * cause of the failure in more detail. + * User action: + * Increase the memory footprint of your virtual machine or adjust the values + * for the "crashkernel" kernel parameter. Then boot your Linux system again. + */ + +/*? + * Text: "Reserving %lluMB of memory at %lluMB for crashkernel (System RAM: %luMB)\n" + * Severity: Informational + * Parameter: + * @1: amount of reserved memory + * @2: storage location of reserved memory + * @3: amount of system RAM + * Description: + * The memory reservation for the kdump "crashkernel" parameter was successful + * and a kdump kernel can now be loaded with the kexec tool. + * User action: + * None. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/smsgiucv +++ linux-4.14.0/Documentation/kmsg/s390/smsgiucv @@ -0,0 +1 @@ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/smsgiucv_app +++ linux-4.14.0/Documentation/kmsg/s390/smsgiucv_app @@ -0,0 +1 @@ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/tape +++ linux-4.14.0/Documentation/kmsg/s390/tape @@ -0,0 +1,63 @@ +/*? + * Text: "%s: A tape unit was detached while in use\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A tape unit has been detached from the I/O configuration while a tape + * was being accessed. This typically results in I/O error messages and + * potentially in damaged data on the tape. + * User action: + * Check the output of the application that accesses the tape device. + * If this problem occurred during a write-type operation, consider repeating + * the operation after bringing the tape device back online. + */ + +/*? + * Text: "%s: A tape cartridge has been mounted\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the tape device + * Description: + * A tape cartridge has been inserted into the tape unit. The tape in the + * tape unit is ready to be accessed. + * User action: + * None. + */ + +/*? + * Text: "%s: The tape cartridge has been successfully unloaded\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape cartridge has been unloaded from the tape unit. Insert a tape + * cartridge before accessing the tape device. + * User action: + * None. + */ + +/*? + * Text: "A cartridge is loaded in tape device %s, refusing to suspend\n" + * Severity: Error + * Parameter: + * @1: bus ID of the tape device + * Description: + * A request to suspend a tape device currently loaded with a cartridge is + * rejected. + * User action: + * Unload the tape device. Then try to suspend the system again. + */ + +/*? + * Text: "Tape device %s is busy, refusing to suspend\n" + * Severity: Error + * Parameter: + * @1: bus ID of the tape device + * Description: + * A request to suspend a tape device being currently in use is rejected. + * User action: + * Terminate applications performing tape operations + * and then try to suspend the system again. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/tape_34xx +++ linux-4.14.0/Documentation/kmsg/s390/tape_34xx @@ -0,0 +1,418 @@ +/*? + * Text: "%s: An unexpected condition %d occurred in tape error recovery\n" + * Severity: Error + * Parameter: + * @1: bus ID of the tape device + * @2: number + * Description: + * The control unit has reported an error condition that is not recognized by + * the error recovery process of the tape device driver. + * User action: + * Report this problem and the condition number from the message to your + * support organization. + */ + +/*? + * Text: "%s: A data overrun occurred between the control unit and tape unit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A data overrun error has occurred on the connection between the control + * unit and the tape unit. If this problem occurred during a write-type + * operation, the integrity of the data on the tape might be compromised. + * User action: + * Use a faster connection. If this problem occurred during a write-type + * operation, consider repositioning the tape and repeating the operation. + */ + +/*? + * Text: "%s: The block ID sequence on the tape is incorrect\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The control unit has detected an incorrect block ID sequence on the tape. + * This problem typically indicates that the data on the tape is damaged. + * User action: + * If this problem occurred during a write-type operation reposition the tape + * and repeat the operation. + */ + +/*? + * Text: "%s: A read error occurred that cannot be recovered\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A read error has occurred that cannot be recovered. The current tape might + * be damaged. + * User action: + * None. + */ + +/*? + * Text: "%s: A write error on the tape cannot be recovered\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A write error has occurred that could not be recovered by the automatic + * error recovery process. + * User action: + * Use a different tape cartridge. + */ + +/*? + * Text: "%s: Writing the ID-mark failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The ID-mark at the beginning of tape could not be written. The tape medium + * might be write-protected. + * User action: + * Try a different tape cartridge. Ensure that the write-protection on the + * cartridge is switched off. + */ + +/*? + * Text: "%s: Reading the tape beyond the end of the recorded area failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A read-type operation failed because it extended beyond the end of the + * recorded area on the tape medium. + * User action: + * None. + */ + +/*? + * Text: "%s: The tape contains an incorrect block ID sequence\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The control unit has detected an incorrect block ID sequence on the tape. + * This problem typically indicates that the data on the tape is damaged. + * User action: + * If this problem occurred during a write-type operation reposition the tape + * and repeat the operation. + */ + +/*? + * Text: "%s: A path equipment check occurred for the tape device\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A path equipment check has occurred. This check indicates problems with the + * connection between the mainframe system and the tape control unit. + * User action: + * Ensure that the cable connections between the mainframe system and the + * control unit are securely in place and not damaged. + */ + +/*? + * Text: "%s: The tape unit cannot process the tape format\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * Either the tape unit is not able to read the format ID mark, or the + * specified format is not supported by the tape unit. + * User action: + * If you do not need the data recorded on the current tape, use a different + * tape or write a new format ID mark at the beginning of the tape. Be aware + * that writing a new ID mark leads to a loss of all data that has been + * recorded on the tape. If you need the data on the current tape, use a tape + * unit that supports the tape format. + */ + +/*? + * Text: "%s: The tape medium is write-protected\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A write-type operation failed because the tape medium is write-protected. + * User action: + * Eject the tape cartridge, switch off the write protection on the cartridge, + * insert the cartridge, and try the operation again. + */ + +/*? + * Text: "%s: The tape does not have the required tape tension\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape does not have the required tape tension. + * User action: + * Rewind and reposition the tape, then repeat the operation. + */ + +/*? + * Text: "%s: The tape unit failed to load the cartridge\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * An error has occurred while loading the tape cartridge. + * User action: + * Unload the cartridge and load it again. + */ + +/*? + * Text: "%s: Automatic unloading of the tape cartridge failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit failed to unload the cartridge. + * User action: + * Unload the cartridge manually by using the eject button on the tape unit. + */ + +/*? + * Text: "%s: An equipment check has occurred on the tape unit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * Possible reasons for the check condition are a unit adapter error, a buffer + * error on the lower interface, an unusable internal path, or an error that + * has occurred while loading the cartridge. + * User action: + * Examine the tape unit and the cartridge loader. Consult the tape unit + * documentation for details. + */ + +/*? + * Text: "%s: The tape information states an incorrect length\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape is shorter than stated at the beginning of the tape data. A + * possible reason for this problem is that the tape might have been physically + * truncated. Data written to the tape might be incomplete or damaged. + * User action: + * If this problem occurred during a write-type operation, consider repeating + * the operation with a different tape cartridge. + */ + +/*? + * Text: "%s: The tape unit is not ready\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit is online but not ready. + * User action: + * Turn the ready switch on the tape unit to the ready position and try the + * operation again. + */ + +/*? + * Text: "%s: The tape medium has been rewound or unloaded manually\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit rewind button, unload button, or both have been used to + * rewind or unload the tape cartridge. A tape cartridge other than the + * intended cartridge might have been inserted or the tape medium might not + * be at the expected position. + * User action: + * Verify that the correct tape cartridge has been inserted and that the tape + * medium is at the required position before continuing to work with the tape. + */ + +/*? + * Text: "%s: The tape subsystem is running in degraded mode\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape subsystem is not operating at its maximum performance. + * User action: + * Contact your service representative for the tape unit and report this + * problem. + */ + +/*? + * Text: "%s: The tape unit is already assigned\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit is already assigned to another channel path. + * User action: + * Free the tape unit from the operating system instance to which it is + * currently assigned then try again. + */ + +/*? + * Text: "%s: The tape unit is not online\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit is not online to the tape device driver. + * User action: + * Ensure that the tape unit is operational and that the cable connections + * between the control unit and the tape unit are securely in place and not + * damaged. + */ + +/*? + * Text: "%s: The control unit has fenced access to the tape volume\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The control unit fences further access to the current tape volume. The data + * integrity on the tape volume might have been compromised. + * User action: + * Rewind and unload the tape cartridge. + */ + +/*? + * Text: "%s: A parity error occurred on the tape bus\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * A data parity check error occurred on the bus. Data that was read or written + * while the error occurred is not valid. + * User action: + * Reposition the tape and repeat the read-type or write-type operation. + */ + +/*? + * Text: "%s: I/O error recovery failed on the tape control unit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * An I/O error occurred that cannot be recovered by the automatic error + * recovery process of the tape control unit. The application that operates + * the tape unit will receive a return value of -EIO which indicates an + * I/O error. The data on the tape might be damaged. + * User action: + * If this problem occurred during a write-type operation, consider + * repositioning the tape and repeating the operation. + */ + +/*? + * Text: "%s: The tape unit requires a firmware update\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit requires firmware patches from the tape control unit but the + * required patches are not available on the control unit. + * User action: + * Make the require patches available on the control unit then reposition the + * tape and retry the operation. For details about obtaining and installing + * firmware updates see the control unit documentation. + */ + +/*? + * Text: "%s: The maximum block size for buffered mode is exceeded\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The block to be written is larger than allowed for the buffered mode. + * User action: + * Use a smaller block size. + */ + +/*? + * Text: "%s: A channel interface error cannot be recovered\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * An error has occurred on the channel interface. This error cannot + * be recovered by the control unit error recovery process. + * User action: + * See the documentation of the control unit. + */ + +/*? + * Text: "%s: A channel protocol error occurred\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * An error was detected in the channel protocol. + * User action: + * Reposition the tape and try the operation again. + */ + +/*? + * Text: "%s: The tape unit does not support the compaction algorithm\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit cannot read the current tape. The data on the tape has been + * compressed with an algorithm that is not supported by the tape unit. + * User action: + * Use a tape unit that supports the compaction algorithm used for the + * current tape. + */ + +/*? + * Text: "%s: The tape unit does not support tape format 3480-2 XF\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit does not support tapes recorded in the 3480-2 XF format. + * User action: + * If you do not need the data recorded on the current tape, rewind the tape + * and overwrite it with a supported format. If you need the data on the + * current tape, use a tape unit that supports the tape format. + */ + +/*? + * Text: "%s: The tape unit does not support format 3480 XF\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit does not support tapes recorded in the 3480 XF format. + * User action: + * If you do not need the data recorded on the current tape, rewind the tape + * and overwrite it with a supported format. If you need the data on the + * current tape, use a tape unit that supports the tape format. + */ + +/*? + * Text: "%s: The tape unit does not support the current tape length\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The length of the tape in the cartridge is incompatible with the tape unit. + * User action: + * Either use a different tape unit or use a tape with a supported length. + */ + +/*? + * Text: "%s: The tape unit does not support the tape length\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The length of the tape in the cartridge is incompatible with the tape + * unit. + * User action: + * Either use a different tape unit or use a tape with a supported length. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/tape_3590 +++ linux-4.14.0/Documentation/kmsg/s390/tape_3590 @@ -0,0 +1,183 @@ +/*? + * Text: "%s: The tape medium must be loaded into a different tape unit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape device has indicated an error condition that requires loading + * the tape cartridge into a different tape unit to recover. + * User action: + * Unload the cartridge and use a different tape unit to retry the operation. + */ + +/*? + * Text: "%s: Tape media information: exception %s, service %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: exception + * @3: service + * Description: + * This is an operating system independent tape medium information message + * that was issued by the tape unit. The information in the message is + * intended for the IBM customer engineer. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: Device subsystem information: exception %s, service %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: exception + * @3: required service action + * Description: + * This is an operating system independent device subsystem information message + * that was issued by the tape unit. The information in the message is + * intended for the IBM customer engineer. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: I/O subsystem information: exception %s, service %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: exception + * @3: required service action + * Description: + * This is an operating system independent I/O subsystem information message + * that was issued by the tape unit. The information in the message is + * intended for the IBM customer engineer. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: The tape unit has issued sense message %s\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: sense message code + * Description: + * The tape unit has issued an operating system independent sense message. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: The tape unit has issued an unknown sense message code 0x%x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: code + * Description: + * The tape device driver has received an unknown sense message from the + * tape unit. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: MIM SEV=%i, MC=%02x, ES=%x/%x, RC=%02x-%04x-%02x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: SEV + * @3: message code + * @4: exception + * @5: required service action + * @6: refcode + * @7: mid + * @8: fid + * Description: + * This is an operating system independent information message that was + * issued by the tape unit. The information in the message is intended for + * the IBM customer engineer. + * User action: + * See to the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: IOSIM SEV=%i, DEVTYPE=3590/%02x, MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: SEV + * @3: model + * @4: message code + * @5: exception + * @6: required service action + * @7: refcode1 + * @8: refcode2 + * @9: refcode3 + * Description: + * This is an operating system independent I/O subsystem information message + * that was issued by the tape unit. The information in the message is + * intended for the IBM customer engineer. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: DEVSIM SEV=%i, DEVTYPE=3590/%02x, MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: SEV + * @3: model + * @4: message code + * @5: exception + * @6: required service action + * @7: refcode1 + * @8: refcode2 + * @9: refcode3 + * Description: + * This is an operating system independent device subsystem information message + * issued by the tape unit. The information in the message is intended for + * the IBM customer engineer. + * User action: + * See the documentation for the tape unit for further information. + */ + +/*? + * Text: "%s: The tape unit has issued an unknown sense message code %x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * @2: code + * Description: + * The tape device has issued a sense message, that is unknown to the device + * driver. + * User action: + * Use the message code printed as hexadecimal value and see the documentation + * for the tape unit for further information. + */ + +/*? + * Text: "%s: The tape unit failed to obtain the encryption key from EKM\n" + * Severity: Error + * Parameter: + * @1: bus ID of the tape device + * Description: + * The tape unit was unable to retrieve the encryption key required to decode + * the data on the tape from the enterprise key manager (EKM). + * User action: + * See the EKM and tape unit documentation for information about how to enable + * the tape unit to retrieve the encryption key. + */ + +/*? + * Text: "%s: A different host has privileged access to the tape unit\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the tape device + * Description: + * You cannot access the tape unit because a different operating system + * instance has privileged access to the unit. + * User action: + * Unload the current cartridge to solve this problem. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/time +++ linux-4.14.0/Documentation/kmsg/s390/time @@ -0,0 +1,36 @@ +/*? + * Text: "The ETR interface has adjusted the clock by %li microseconds\n" + * Severity: Notice + * Parameter: + * @1: number of microseconds + * Description: + * The external time reference (ETR) interface has synchronized the system + * clock with the external reference and set it to a new value. The time + * difference between the old and new clock value has been passed to the + * network time protocol (NTP) as a single shot adjustment. + * User action: + * None. + */ + +/*? + * Text: "The real or virtual hardware system does not provide an ETR interface\n" + * Severity: Warning + * Description: + * The 'etr=' parameter has been passed on the kernel parameter line for + * a Linux instance that does not have access to the external time reference + * (ETR) facility. + * User action: + * To avoid this warning remove the 'etr=' kernel parameter. + */ + +/*? + * Text: "The real or virtual hardware system does not provide an STP interface\n" + * Severity: Warning + * Description: + * The 'stp=' parameter has been passed on the kernel parameter line for + * a Linux instance that does not have access to the server time protocol + * (STP) facility. + * User action: + * To avoid this warning remove the 'stp=' kernel parameter. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/vmlogrdr +++ linux-4.14.0/Documentation/kmsg/s390/vmlogrdr @@ -0,0 +1,19 @@ +/*? Text: "vmlogrdr: failed to start recording automatically\n" */ +/*? Text: "vmlogrdr: connection severed with reason %i\n" */ +/*? Text: "vmlogrdr: iucv connection to %s failed with rc %i \n" */ +/*? Text: "vmlogrdr: failed to stop recording automatically\n" */ +/*? Text: "not running under VM, driver not loaded.\n" */ + +/*? + * Text: "vmlogrdr: device %s is busy. Refuse to suspend.\n" + * Severity: Error + * Parameter: + * @1: device name + * Description: + * Suspending vmlogrdr devices that are in uses is not supported. + * A request to suspend such a device is refused. + * User action: + * Close all applications that use any of the vmlogrdr devices + * and then try to suspend the system again. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/vmur +++ linux-4.14.0/Documentation/kmsg/s390/vmur @@ -0,0 +1,48 @@ +/*? + * Text: "The %s cannot be loaded without z/VM\n" + * Severity: Error + * Parameter: + * @1: z/VM virtual unit record device driver + * Description: + * The z/VM virtual unit record device driver provides Linux with access to + * z/VM virtual unit record devices like punch card readers, card punches, and + * line printers. On Linux instances that run in environments other than the + * z/VM hypervisor, the device driver does not provide any useful function and + * the corresponding vmur module cannot be loaded. + * User action: + * Load the vmur module only on Linux instances that run as guest operating + * systems of the z/VM hypervisor. If the z/VM virtual unit record device + * has been compiled into the kernel, ignore this message. + */ + +/*? + * Text: "Kernel function alloc_chrdev_region failed with error code %d\n" + * Severity: Error + * Parameter: + * @1: error code according to errno definitions + * Description: + * The z/VM virtual unit record device driver (vmur) needs to register a range + * of character device minor numbers from 0x0000 to 0xffff. + * This registration failed, probably because of memory constraints. + * User action: + * Free some memory and reload the vmur module. If the z/VM virtual unit + * record device driver has been compiled into the kernel reboot Linux. + * Consider assigning more memory to your LPAR or z/VM guest virtual machine. + */ + +/*? + * Text: "Unit record device %s is busy, %s refusing to suspend.\n" + * Severity: Error + * Parameter: + * @1: bus ID of the unit record device + * @1: z/VM virtual unit record device driver + * Description: + * Linux cannot be suspended while a unit record device is in use. + * User action: + * Stop all applications that work on z/VM spool file queues, for example, the + * vmur tool. Then try again to suspend Linux. + */ + +/*? Text: "%s loaded.\n" */ +/*? Text: "%s unloaded.\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/xpram +++ linux-4.14.0/Documentation/kmsg/s390/xpram @@ -0,0 +1,74 @@ +/*? + * Text: "%d is not a valid number of XPRAM devices\n" + * Severity: Error + * Parameter: + * @1: number of partitions + * Description: + * The number of XPRAM partitions specified for the 'devs' module parameter + * or with the 'xpram.parts' kernel parameter must be an integer in the + * range 1 to 32. The XPRAM device driver created a maximum of 32 partitions + * that are probably not configured as intended. + * User action: + * If the XPRAM device driver has been compiled as a separate module, + * unload the module and load it again with a correct value for the 'devs' + * module parameter. If the XPRAM device driver has been compiled + * into the kernel, correct the 'xpram.parts' parameter in the kernel + * command line and restart Linux. + */ + +/*? + * Text: "Not enough expanded memory available\n" + * Severity: Error + * Description: + * The amount of expanded memory required to set up your XPRAM partitions + * depends on the 'sizes' parameter specified for the xpram module or on + * the specifications for the 'xpram.parts' parameter if the XPRAM device + * driver has been compiled into the kernel. Your + * current specification exceed the amount of available expanded memory. + * Your XPRAM partitions are probably not configured as intended. + * User action: + * If the XPRAM device driver has been compiled as a separate module, + * unload the xpram module and load it again with an appropriate value + * for the 'sizes' module parameter. If the XPRAM device driver has been + * compiled into the kernel, adjust the 'xpram.parts' parameter in the + * kernel command line and restart Linux. If you need more than the + * available expanded memory, increase the expanded memory allocation for + * your virtual hardware or LPAR. + */ + +/*? + * Text: "No expanded memory available\n" + * Severity: Error + * Description: + * The XPRAM device driver has been loaded in a Linux instance that runs + * in an LPAR or virtual hardware without expanded memory. + * No XPRAM partitions are created. + * User action: + * Allocate expanded memory for your LPAR or virtual hardware or do not + * load the xpram module. You can ignore this message, if you do not want + * to create XPRAM partitions. + */ + +/*? + * Text: "Resuming the system failed: %s\n" + * Severity: Error + * Parameter: + * @1: cause of the failure + * Description: + * A system cannot be resumed if the expanded memory setup changes + * after hibernation. Possible reasons for the failure are: + * - Expanded memory was removed after hibernation. + * - Size of the expanded memory changed after hibernation. + * The system is stopped with a kernel panic. + * User action: + * Reboot Linux. + */ + +/*? Text: " number of devices (partitions): %d \n" */ +/*? Text: " size of partition %d: %u kB\n" */ +/*? Text: " size of partition %d to be set automatically\n" */ +/*? Text: " memory needed (for sized partitions): %lu kB\n" */ +/*? Text: " partitions to be sized automatically: %d\n" */ +/*? Text: " automatically determined partition size: %lu kB\n" */ +/*? Text: " %u pages expanded memory found (%lu KB).\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/zcrypt +++ linux-4.14.0/Documentation/kmsg/s390/zcrypt @@ -0,0 +1,22 @@ +/*? + * Text: "Cryptographic device %02x.%04x failed and was set offline\n" + * Severity: Error + * Parameter: + * @1: AP device ID + * @2: AP queue + * Description: + * A cryptographic device failed to process a cryptographic request. + * The cryptographic device driver could not correct the error and + * set the device offline. The application that issued the + * request received an indication that the request has failed. + * User action: + * Use the lszcrypt command to confirm that the cryptographic + * hardware is still configured to your LPAR or z/VM guest virtual + * machine. If the device is available to your Linux instance the + * command output contains a line that begins with 'card', + * where is the two-digit decimal number in the message text. + * After ensuring that the device is available, use the chzcrypt command to + * set it online again. + * If the error persists, contact your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/zdump +++ linux-4.14.0/Documentation/kmsg/s390/zdump @@ -0,0 +1,27 @@ +/*? + * Text: "The 32-bit dump tool cannot be used for a 64-bit system\n" + * Severity: Alert + * Description: + * The dump process ends without creating a system dump. + * User action: + * Use a 64-bit dump tool to obtain a system dump for 64-bit Linux instance. + */ +/*? + * Text: "The 64-bit dump tool cannot be used for a 32-bit system\n" + * Severity: Alert + * Description: + * The dump process ends without creating a system dump. + * User action: + * Use a 32-bit dump tool to obtain a system dump for 32-bit Linux instance. + */ +/*? + * Text: "The dump process started for a 64-bit operating system\n" + * Severity: Alert + * Description: + * The SCSI dump process started to create a dump for a 64-bit operating + * system instance. + * User action: + * None. + */ +/*? Text: "0x%x is an unknown architecture.\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/zfcp +++ linux-4.14.0/Documentation/kmsg/s390/zfcp @@ -0,0 +1,709 @@ +/*? + * Text: "%s is not a valid SCSI device\n" + * Severity: Error + * Parameter: + * @1: device specification + * Description: + * The specification for an initial SCSI device provided with the 'zfcp.device' + * kernel parameter or with the 'device' module parameter is syntactically + * incorrect. The specified SCSI device could not be attached to the Linux + * system. + * User action: + * Correct the value for the 'zfcp.device' or 'device' parameter and reboot + * Linux. See "Device Drivers, Features, and Commands" for information about + * the syntax. + */ + +/*? + * Text: "The zfcp device driver could not register with the common I/O layer\n" + * Severity: Error + * Description: + * The device driver initialization failed. A possible cause of this problem is + * memory constraints. + * User action: + * Free some memory and try again to load the zfcp device driver. If the zfcp + * device driver has been compiled into the kernel, reboot Linux. Consider + * assigning more memory to your LPAR or z/VM guest virtual machine. If the + * problem persists, contact your support organization. + */ + +/*? + * Text: "%s: Setting up data structures for the FCP adapter failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The zfcp device driver could not allocate data structures for an FCP adapter. + * A possible reason for this problem is memory constraints. + * User action: + * Set the FCP adapter offline or detach it from the Linux system, free some + * memory and set the FCP adapter online again or attach it again. If this + * problem persists, gather Linux debug data, collect the FCP adapter + * hardware logs, and report the problem to your support organization. + */ + +/*? + * Text: "%s: The FCP device is operational again\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * An FCP device has been unavailable because it had been detached from the + * Linux system or because the corresponding CHPID was offline. The FCP device + * is now available again and the zfcp device driver resumes all operations to + * the FCP device. + * User action: + * None. + */ + +/*? + * Text: "%s: The CHPID for the FCP device is offline\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The CHPID for an FCP device has been set offline, either logically in Linux + * or on the hardware. + * User action: + * Find out which CHPID corresponds to the FCP device, for example, with the + * lscss command. Check if the CHPID has been set logically offline in sysfs. + * Write 'on' to the CHPID's status attribute to set it online. If the CHPID is + * online in sysfs, find out if it has been varied offline through a hardware + * management interface, for example the service element (SE). + */ + +/*? + * Text: "%s: The FCP device has been detached\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * An FCP device is no longer available to Linux. + * User action: + * Ensure that the FCP adapter is operational and attached to the LPAR or z/VM + * virtual machine. + */ + +/*? + * Text: "%s: The FCP device did not respond within the specified time\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The common I/O layer waited for a response from the FCP adapter but + * no response was received within the specified time limit. This might + * indicate a hardware problem. + * User action: + * Consult your hardware administrator. If this problem persists, + * gather Linux debug data, collect the FCP adapter hardware logs, and + * report the problem to your support organization. + */ + +/*? + * Text: "%s: Registering the FCP device with the SCSI stack failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter could not be registered with the Linux SCSI + * stack. A possible reason for this problem is memory constraints. + * User action: + * Set the FCP adapter offline or detach it from the Linux system, free some + * memory and set the FCP adapter online again or attach it again. If this + * problem persists, gather Linux debug data, collect the FCP adapter + * hardware logs, and report the problem to your support organization. + */ + +/*? + * Text: "%s: ERP cannot recover an error on the FCP device\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * An error occurred on an FCP device. The error recovery procedure (ERP) + * could not resolve the error. The FCP device driver cannot use the FCP device. + * User action: + * Check for previous error messages for the same FCP device to find the + * cause of the problem. + */ + +/*? + * Text: "%s: Creating an ERP thread for the FCP device failed.\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The zfcp device driver could not set up error recovery procedure (ERP) + * processing for the FCP device. The FCP device is not available for use + * in Linux. + * User action: + * Free some memory and try again to load the zfcp device driver. If the zfcp + * device driver has been compiled into the kernel, reboot Linux. Consider + * assigning more memory to your LPAR or z/VM guest virtual machine. If the + * problem persists, contact your support organization. + */ + +/*? + * Text: "%s: ERP failed for LUN 0x%016Lx on port 0x%016Lx\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: LUN + * @3: WWPN + * Description: + * An error occurred on the SCSI device at the specified LUN. The error recovery + * procedure (ERP) could not resolve the error. The SCSI device is not + * available. + * User action: + * Verify that the LUN is correct. Check the fibre channel fabric for errors + * related to the specified WWPN and LUN, the storage server, and Linux. + */ + +/*? + * Text: "%s: ERP failed for remote port 0x%016Lx\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: WWPN + * Description: + * An error occurred on a remote port. The error recovery procedure (ERP) + * could not resolve the error. The port is not available. + * User action: + * Verify that the WWPN is correct and check the fibre channel fabric for + * errors related to the WWPN. + */ + +/*? + * Text: "%s: Registering port 0x%016Lx failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: WWPN + * Description: + * The Linux kernel could not allocate enough memory to register the + * remote port with the indicated WWPN with the SCSI stack. The remote + * port is not available. + * User action: + * Free some memory and trigger the rescan for ports. + */ + +/*? + * Text: "%s: A QDIO problem occurred\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * QDIO reported a problem to the zfcp device driver. The zfcp device driver + * tries to recover this problem. + * User action: + * Check for related error messages. If this problem occurs frequently, gather + * Linux debug data and contact your support organization. + */ + +/*? + * Text: "%s: Setting up the QDIO connection to the FCP adapter failed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The zfcp device driver failed to establish a QDIO connection with the FCP + * adapter. + * User action: + * Set the FCP adapter offline or detach it from the Linux system, free some + * memory and set the FCP adapter online again or attach it again. If this + * problem persists, gather Linux debug data, collect the FCP adapter + * hardware logs, and report the problem to your support organization. + */ + +/*? + * Text: "%s: The FCP adapter reported a problem that cannot be recovered\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter has a problem that cannot be recovered by the zfcp device + * driver. The zfcp device driver stopped using the FCP device. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to your support organization. + */ + +/*? + * Text: "%s: There is a wrap plug instead of a fibre channel cable\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter is not physically connected to the fibre channel fabric. + * User action: + * Remove the wrap plug from the FCP adapter and connect the adapter with the + * fibre channel fabric. + */ + +/*? + * Text: "%s: FCP device not operational because of an unsupported FC class\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter hardware does not support the fibre channel service class + * requested by the zfcp device driver. This problem indicates a program error + * in the zfcp device driver. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to your support organization. + */ + +/*? + * Text: "%s: 0x%Lx is an ambiguous request identifier\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: request ID + * Description: + * The FCP adapter reported that it received the same request ID twice. This is + * an error. The zfcp device driver stopped using the FCP device. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to your support organization. + */ + +/*? + * Text: "%s: QTCB version 0x%x not supported by FCP adapter (0x%x to 0x%x)\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: requested version + * @3: lowest supported version + * @4: highest supported version + * Description: + * See message text. + * The queue transfer control block (QTCB) version requested by the zfcp device + * driver is not supported by the FCP adapter hardware. + * User action: + * If the requested version is higher than the highest version supported by the + * hardware, install more recent firmware on the FCP adapter. If the requested + * version is lower then the lowest version supported by the hardware, upgrade + * to a Linux level with a more recent zfcp device driver. + */ + +/*? + * Text: "%s: The FCP adapter could not log in to the fibre channel fabric\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The fibre channel switch rejected the login request from the FCP adapter. + * User action: + * Check the fibre channel fabric or switch logs for possible errors. + */ + +/*? + * Text: "%s: The FCP device is suspended because of a firmware update\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP device is not available while a firmware update is in progress. This + * problem is temporary. The FCP device will resume operations when the + * firmware update is completed. + * User action: + * Wait 10 seconds and try the operation again. + */ + +/*? + * Text: "%s: All NPIV ports on the FCP adapter have been assigned\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The number of N_Port ID Virtualization (NPIV) ports that can be assigned + * on an FCP adapter is limited. Once assigned, NPIV ports are not released + * automatically but have to be released explicitly through the support + * element (SE). + * User action: + * Identify NPIV ports that have been assigned but are no longer in use and + * release them from the SE. + */ + +/*? + * Text: "%s: The link between the FCP adapter and the FC fabric is down\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter is not usable. Specific error information is not available. + * User action: + * Check the cabling and the fibre channel fabric configuration. If this + * problem persists, gather Linux debug data, collect the FCP adapter + * hardware logs, and report the problem to your support organization. + */ + +/*? + * Text: "%s: The QTCB type is not supported by the FCP adapter\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The queue transfer control block (QTCB) type requested by the zfcp device + * driver is not supported by the FCP adapter hardware. + * User action: + * Install the latest firmware on your FCP adapter hardware. If this does not + * resolve the problem, upgrade to a Linux level with a more recent zfcp device + * driver. If the problem persists, contact your support organization. + */ + +/*? + * Text: "%s: The error threshold for checksum statistics has been exceeded\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter has reported a large number of bit errors. This might + * indicate a problem with the physical components of the fibre channel fabric. + * Details about the errors have been written to the HBA trace for the FCP + * adapter. + * User action: + * Check for problems in the fibre channel fabric and ensure that all cables + * are properly plugged. + */ + +/*? + * Text: "%s: The local link has been restored\n" + * Severity: Informational + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * A problem with the connection between the FCP adapter and the adjacent node + * on the fibre channel fabric has been resolved. The FCP adapter is now + * available again. + * User action: + * None. + */ + +/*? + * Text: "%s: The mode table on the FCP adapter has been damaged\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * This is an FCP adapter hardware problem. + * User action: + * Report this problem with FCP hardware logs to IBM support. + */ + +/*? + * Text: "%s: The adjacent fibre channel node does not support FCP\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The fibre channel switch or storage system that is connected to the FCP + * channel does not support the fibre channel protocol (FCP). The zfcp + * device driver stopped using the FCP device. + * User action: + * Check the adjacent fibre channel node. + */ + +/*? + * Text: "%s: The FCP adapter does not recognize the command 0x%x\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: command + * Description: + * A command code that was sent from the zfcp device driver to the FCP adapter + * is not valid. The zfcp device driver stopped using the FCP device. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to your support organization. + */ + +/*? + * Text: "%s: There is no light signal from the local fibre channel cable\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * There is no signal on the fibre channel cable that connects the FCP adapter + * to the fibre channel fabric. + * User action: + * Ensure that the cable is in place and connected properly to the FCP adapter + * and to the adjacent fibre channel switch or storage system. + */ + +/*? + * Text: "%s: The WWPN assignment file on the FCP adapter has been damaged\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * This is an FCP adapter hardware problem. + * User action: + * Report this problem with FCP hardware logs to IBM support. + */ + +/*? + * Text: "%s: The FCP device detected a WWPN that is duplicate or not valid\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * This condition indicates an error in the FCP adapter hardware or in the z/VM + * hypervisor. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to IBM support. + */ + +/*? + * Text: "%s: The fibre channel fabric does not support NPIV\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP adapter requires N_Port ID Virtualization (NPIV) from the adjacent + * fibre channel node. Either the FCP adapter is connected to a fibre channel + * switch that does not support NPIV or the FCP adapter tries to use NPIV in a + * point-to-point setup. The connection is not operational. + * User action: + * Verify that NPIV is correctly used for this connection. Check the FCP adapter + * configuration and the fibre channel switch configuration. If necessary, + * update the fibre channel switch firmware. + */ + +/*? + * Text: "%s: The FCP adapter cannot support more NPIV ports\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * N_Port ID Virtualization (NPIV) ports consume physical resources on the FCP + * adapter. The FCP adapter resources are exhausted. The connection is not + * operational. + * User action: + * Analyze the number of available NPIV ports and which operating system + * instances use them. If necessary, reconfigure your setup to move some + * NPIV ports to an FCP adapter with free resources. + */ + +/*? + * Text: "%s: The adjacent switch cannot support more NPIV ports\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * N_Port ID Virtualization (NPIV) ports consume physical resources. The + * resources of the fibre channel switch that is connected to the FCP adapter + * are exhausted. The connection is not operational. + * User action: + * Analyze the number of available NPIV ports on the adjacent fibre channel + * switch and how they are used. If necessary, reconfigure your fibre channel + * fabric to accommodate the required NPIV ports. + */ + +/*? + * Text: "%s: 0x%x is not a valid transfer protocol status\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: status information + * Description: + * The transfer protocol status information reported by the FCP adapter is not + * a valid status for the zfcp device driver. The zfcp device driver stopped + * using the FCP device. + * User action: + * Gather Linux debug data, collect the FCP adapter hardware logs, and report + * this problem to your support organization. + */ + +/*? + * Text: "%s: Unknown or unsupported arbitrated loop fibre channel topology detected\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The FCP device is connected to a fibre channel arbitrated loop or the FCP adapter + * reported an unknown fibre channel topology. The zfcp device driver supports + * point-to-point connections and switched fibre channel fabrics but not arbitrated + * loop topologies. The FCP device cannot be used. + * User action: + * Check the fibre channel setup and ensure that only supported topologies are + * connected to the FCP adapter. + */ + +/*? + * Text: "%s: FCP adapter maximum QTCB size (%d bytes) is too small\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: maximum supported size + * @3: requested QTCB size + * Description: + * The queue transfer control block (QTCB) size requested by the zfcp + * device driver is not supported by the FCP adapter hardware. + * User action: + * Update the firmware on your FCP adapter hardware to the latest + * available level and update the Linux kernel to the latest supported + * level. If the problem persists, contact your support organization. + */ + +/*? + * Text: "%s: The FCP adapter only supports newer control block versions\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The protocol supported by the FCP adapter is not compatible with the zfcp + * device driver. + * User action: + * Upgrade your Linux kernel to a level that includes a zfcp device driver + * with support for the control block version required by your FCP adapter. + */ + +/*? + * Text: "%s: The FCP adapter only supports older control block versions\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * Description: + * The protocol supported by the FCP adapter is not compatible with the zfcp + * device driver. + * User action: + * Install the latest firmware on your FCP adapter. + */ + +/*? + * Text: "%s: Not enough FCP adapter resources to open remote port 0x%016Lx\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: WWPN + * Description: + * Each port that is opened consumes physical resources of the FCP adapter to + * which it is attached. These resources are exhausted and the specified port + * cannot be opened. + * User action: + * Reduce the total number of remote ports that are attached to the + * FCP adapter. + */ + +/*? + * Text: "%s: LUN 0x%Lx on port 0x%Lx is already in use by CSS%d, MIF Image ID %x\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: LUN + * @3: remote port WWPN + * @4: channel subsystem ID + * @5: MIF Image ID of the LPAR + * Description: + * The SCSI device at the indicated LUN is already in use by another system. + * Only one system at a time can use the SCSI device. + * User action: + * Ensure that the other system stops using the device before trying to use it. + */ + +/*? + * Text: "%s: No handle is available for LUN 0x%016Lx on port 0x%016Lx\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: LUN + * @3: WWPN + * Description: + * The FCP adapter can only open a limited number of SCSI devices. This limit + * has been reached and the SCSI device at the indicated LUN cannot be opened. + * User action: + * For FCP subchannels running in non-NPIV mode, check all SCSI + * devices opened through the FCP adapter and close some of them. For + * FCP subchannels running in NPIV mode, verify the SAN zoning and + * host connections on the storage systems. Ensure that the zoning and + * host connections only allow access to the required LUNs. As a + * workaround, disable the automatic LUN scanning by setting the + * zfcp.allow_lun_scan kernel parameter or the allow_lun_scan module + * parameter to 0. + */ + +/*? + * Text: "%s: Incorrect direction %d, LUN 0x%016Lx on port 0x%016Lx closed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: value in direction field + * @3: LUN + * @4: WWPN + * Description: + * The direction field in a SCSI request contains an incorrect value. The zfcp + * device driver closed down the SCSI device at the indicated LUN. + * User action: + * Gather Linux debug data and report this problem to your support organization. + */ + +/*? + * Text: "%s: Incorrect CDB length %d, LUN 0x%016Lx on port 0x%016Lx closed\n" + * Severity: Error + * Parameter: + * @1: bus ID of the zfcp device + * @2: value in length field + * @3: LUN + * @4: WWPN + * Description: + * The control-data-block (CDB) length field in a SCSI request is not valid or + * too large for the FCP adapter. The zfcp device driver closed down the SCSI + * device at the indicated LUN. + * User action: + * Gather Linux debug data and report this problem to your support organization. + */ + +/*? + * Text: "%s: Opening WKA port 0x%x failed\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: destination ID of the WKA port + * Description: + * The FCP adapter rejected a request to open the specified + * well-known address (WKA) port. No retry is possible. + * User action: + * Verify the setup and check if the maximum number of remote ports + * used through this adapter is below the maximum allowed. If the + * problem persists, gather Linux debug data, collect the FCP adapter + * hardware logs, and report the problem to your support organization. + */ + +/*? + * Text: "%s: The name server reported %d words residual data\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: number of words in residual data + * Description: + * The fibre channel name server sent too much information about remote ports. + * The zfcp device driver did not receive sufficient information to attach all + * available remote ports in the SAN. + * User action: + * Verify that you are running the latest firmware level on the FCP + * adapter. Check your SAN setup and consider reducing the number of ports + * visible to the FCP adapter by using more restrictive zoning in the SAN. + */ + +/*? + * Text: "%s: A port opened with WWPN 0x%016Lx returned data that identifies it as WWPN 0x%016Lx\n" + * Severity: Warning + * Parameter: + * @1: bus ID of the zfcp device + * @2: expected WWPN + * @3: reported WWPN + * Description: + * A remote port was opened successfully, but it reported an + * unexpected WWPN in the returned port login (PLOGI) data. This + * condition might have been caused by a change applied to the SAN + * configuration while the port was being opened. + * User action: + * If this condition is only temporary and access to the remote port + * is possible, no action is required. If the condition persists, + * identify the storage system with the specified WWPN and contact the + * support organization of the storage system. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/s390/zpci +++ linux-4.14.0/Documentation/kmsg/s390/zpci @@ -0,0 +1,42 @@ +/*? + * Text: "%s: Event 0x%x reconfigured PCI function 0x%x\n" + * Severity: Informational + * Parameter: + * @1: device name of the function + * @2: PCI event code + * @3: function ID + * Description: + * The availability of a PCI function has changed. + * Possible reasons for the change include PCI configuration actions on the + * Hardware Management Console or hypervisor. + * For shared PCI functions, the function might also have been reserved or + * released by another system. + * If the device name of a function is shown as 'n/a', the device registration + * with the PCI device driver has not completed. + * The function ID identifies the function to the I/O configuration (IOCDS). + * The PCI event code can be useful diagnostic information for your support + * organization. + * User action: + * None. + */ + +/*? + * Text: "%s: Event 0x%x reports an error for PCI function 0x%x\n" + * Severity: Error + * Parameter: + * @1: device name of the function + * @2: PCI event code + * @3: function ID + * Description: + * A PCI function entered an error state from which it cannot recover + * automatically. + * User action: + * Trigger a recovery action by writing '1' to the 'recover' sysfs attribute + * of the PCI function. + * In sysfs, PCI functions are represented as /sys/bus/pci/devices/, + * where is the device name of the function. + * If the device name of a function is shown as 'n/a', the device + * registration with the PCI device driver has not completed. + * If the problem persists, contact your support organization. + */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ --- linux-4.14.0.orig/Documentation/kmsg/sbp_target +++ linux-4.14.0/Documentation/kmsg/sbp_target @@ -0,0 +1,49 @@ +/*? Text: "ABORT TASK SET not implemented\n" */ +/*? Text: "ABORT TASK not implemented\n" */ +/*? Text: "Cannot change the directory_id on an active target.\n" */ +/*? Text: "Cannot enable a target with no LUNs!\n" */ +/*? Text: "Could not update Config ROM\n" */ +/*? Text: "Ignoring ORB_POINTER write while active.\n" */ +/*? Text: "LOGICAL UNIT RESET not implemented\n" */ +/*? Text: "Node ACL not found for %s\n" */ +/*? Text: "Only one TPG per Unit is possible.\n" */ +/*? Text: "QUERY LOGINS not implemented\n" */ +/*? Text: "Reconnect timer expired for node: %016llx\n" */ +/*? Text: "SET PASSWORD not implemented\n" */ +/*? Text: "TARGET RESET not implemented\n" */ +/*? Text: "Unable to allocate struct sbp_nacl\n" */ +/*? Text: "Unable to allocate struct sbp_tpg\n" */ +/*? Text: "Unable to allocate struct sbp_tport\n" */ +/*? Text: "Waiting for reconnect from node: %016llx\n" */ +/*? Text: "cannot find login: %d\n" */ +/*? Text: "failed to allocate login descriptor\n" */ +/*? Text: "failed to allocate login response block\n" */ +/*? Text: "failed to allocate session descriptor\n" */ +/*? Text: "failed to init se_session\n" */ +/*? Text: "failed to map command block handler: %d\n" */ +/*? Text: "failed to read peer GUID: %d\n" */ +/*? Text: "ignoring management request while busy\n" */ +/*? Text: "ignoring request from foreign node (%x != %x)\n" */ +/*? Text: "ignoring request with wrong generation\n" */ +/*? Text: "initiator already logged-in\n" */ +/*? Text: "login to unknown LUN: %d\n" */ +/*? Text: "logout from different node ID\n" */ +/*? Text: "max number of logins reached\n" */ +/*? Text: "mgt_agent LOGIN to LUN %d from %016llx\n" */ +/*? Text: "mgt_agent LOGOUT from LUN %d session %d\n" */ +/*? Text: "mgt_agent RECONNECT from %016llx\n" */ +/*? Text: "mgt_agent RECONNECT login GUID doesn't match\n" */ +/*? Text: "mgt_agent RECONNECT unknown login ID\n" */ +/*? Text: "mgt_orb bad request\n" */ +/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */ +/*? Text: "refusing exclusive login with other active logins\n" */ +/*? Text: "refusing login while another exclusive login present\n" */ +/*? Text: "sbp_run_transaction: page size ignored\n" */ +/*? Text: "sbp_send_sense: unknown sense format: 0x%x\n" */ +/*? Text: "target_fabric_configfs_init() failed\n" */ +/*? Text: "target_fabric_configfs_register() failed for SBP\n" */ +/*? Text: "unknown management function 0x%x\n" */ +/*? Text: "unlink LUN: failed to update unit directory\n" */ +/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */ +/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ \ No newline at end of file --- linux-4.14.0.orig/Documentation/kmsg/zram +++ linux-4.14.0/Documentation/kmsg/zram @@ -0,0 +1,34 @@ +/*? Text: "Error allocating compressor buffer space\n" */ +/*? Text: "Error allocating memory for compressed page: %u, size=%zu\n" */ +/*? Text: "Error creating memory pool\n" */ +/*? Text: "num_devices not specified. Using default: 1\n" */ +/*? Text: "Error allocating compressor working memory!\n" */ +/*? Text: "Error allocating zram address table\n" */ +/*? Text: "Unable to get major number\n" */ +/*? Text: "Compression failed! err=%d\n" */ +/*? Text: "Decompression failed! err=%d, page=%u\n" */ +/*? Text: "There is little point creating a zram of greater than twice the size of memory since we expect a 2:1 compression ratio. Note that zram uses about 0.1%% of the size of the disk when not in use so a huge zram is wasteful.\n\tMemory Size: %zu kB\n\tSize you selected: %llu kB\nContinuing anyway ...\n" */ +/*? Text: "disk size not provided. You can use disksize_kb module param to specify size.\nUsing default: (%u%% of RAM).\n" */ +/*? Text: "Error creating sysfs group" */ +/*? Text: "Error allocating memory for incompressible page: %u\n" */ +/*? Text: "Creating %u devices ...\n" */ +/*? Text: "Initialization failed: err=%d\n" */ +/*? Text: "Error allocating disk queue for device %d\n" */ +/*? Text: "Error allocating disk structure for device %d\n" */ +/*? Text: "Invalid value for num_devices: %u\n" */ +/*? Text: "Error allocating temp memory!\n" */ +/*? Text: "Unable to allocate temp memory\n" */ +/*? Text: "Created %u device(s) ...\n" */ +/*? Text: "There is little point creating a zram of greater than twice the size of memory since we expect a 2:1 compression ratio. Note that zram uses about 0.1%% of the size of the disk when not in use so a huge zram is wasteful.\n\tMemory Size: %lu kB\n\tSize you selected: %llu kB\nContinuing anyway ...\n" */ +/*? Text: "Cannot change disksize for initialized device\n" */ +/*? Text: "Can't change algorithm for initialized device\n" */ +/*? Text: "Cannot initialise %s compressing backend\n" */ +/*? Text: "Cannot change max compression streams\n" */ +/*? Text: "Destroyed %u device(s)\n" */ +/*? Text: "Created %u device(s)\n" */ +/*? Text: "Unable to register zram-control class\n" */ +/*? Text: "Removed device: %s\n" */ +/*? Text: "Added device: %s\n" */ +/*? Text: "Error creating sysfs group for device %d\n" */ +/*? Text: "Error allocating memory for compressed page: %u, size=%u\n" */ +/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ \ No newline at end of file --- linux-4.14.0.orig/Documentation/printk-formats.txt +++ linux-4.14.0/Documentation/printk-formats.txt @@ -451,6 +451,12 @@ Passed by reference. +Kernel messages: + + %pj 123456 + + For generating the jhash of a string truncated to six digits + If you add other ``%p`` extensions, please extend lib/test_printf.c with one or more test cases, if at all feasible. --- linux-4.14.0.orig/Documentation/x86/orc-unwinder.txt +++ linux-4.14.0/Documentation/x86/orc-unwinder.txt @@ -4,7 +4,7 @@ Overview -------- -The kernel CONFIG_ORC_UNWINDER option enables the ORC unwinder, which is +The kernel CONFIG_UNWINDER_ORC option enables the ORC unwinder, which is similar in concept to a DWARF unwinder. The difference is that the format of the ORC data is much simpler than DWARF, which in turn allows the ORC unwinder to be much simpler and faster. --- linux-4.14.0.orig/Documentation/x86/x86_64/mm.txt +++ linux-4.14.0/Documentation/x86/x86_64/mm.txt @@ -1,6 +1,4 @@ - - Virtual memory map with 4 level page tables: 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm @@ -14,13 +12,16 @@ ... unused hole ... ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB) ... unused hole ... +fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space ... unused hole ... ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0 -ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable) -ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls +ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space (variable) +[fixmap start] - ffffffffff5fffff kernel-internal fixmap range +ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole Virtual memory map with 5 level page tables: @@ -29,26 +30,29 @@ hole caused by [56:63] sign extension ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory -ff90000000000000 - ff91ffffffffffff (=49 bits) hole -ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space +ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI +ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB) ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB) ... unused hole ... -ffd8000000000000 - fff7ffffffffffff (=53 bits) kasan shadow memory (8PB) +ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB) ... unused hole ... +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space ... unused hole ... ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0 -ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space -ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls +ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space +[fixmap start] - ffffffffff5fffff kernel-internal fixmap range +ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole Architecture defines a 64-bit virtual address. Implementations can support less. Currently supported are 48- and 57-bit virtual addresses. Bits 63 -through to the most-significant implemented bit are set to either all ones -or all zero. This causes hole between user space and kernel addresses. +through to the most-significant implemented bit are sign extended. +This causes hole between user space and kernel addresses if you interpret them +as unsigned. The direct mapping covers all memory in the system up to the highest memory address (this means in some cases it can also include PCI memory @@ -58,9 +62,6 @@ the processes using the page fault handler, with init_top_pgt as reference. -Current X86-64 implementations support up to 46 bits of address space (64 TB), -which is our current limit. This expands into MBZ space in the page tables. - We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual memory window (this size is arbitrary, it can be raised later if needed). The mappings are not part of any other kernel PGD and are only available @@ -72,5 +73,3 @@ Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all physical memory, vmalloc/ioremap space and virtual memory map are randomized. Their order is preserved but their base will be offset early at boot time. - --Andi Kleen, Jul 2004 --- linux-4.14.0.orig/MAINTAINERS +++ linux-4.14.0/MAINTAINERS @@ -2465,6 +2465,19 @@ F: include/uapi/linux/audit.h F: kernel/audit* +AUFS (advanced multi layered unification filesystem) FILESYSTEM +M: "J. R. Okajima" +L: linux-unionfs@vger.kernel.org +L: aufs-users@lists.sourceforge.net (members only) +W: http://aufs.sourceforge.net +T: git://github.com/sfjro/aufs4-linux.git +S: Supported +F: Documentation/filesystems/aufs/ +F: Documentation/ABI/testing/debugfs-aufs +F: Documentation/ABI/testing/sysfs-aufs +F: fs/aufs/ +F: include/uapi/linux/aufs_type.h + AUXILIARY DISPLAY DRIVERS M: Miguel Ojeda Sandonis W: http://miguelojeda.es/auxdisplay.htm --- linux-4.14.0.orig/Makefile +++ linux-4.14.0/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 0 +SUBLEVEL = 12 EXTRAVERSION = -NAME = Fearless Coyote +NAME = Petit Gorille # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -176,6 +176,20 @@ KBUILD_CHECKSRC = 0 endif +# Call message checker as part of the C compilation +# +# Use 'make D=1' to enable checking +# Use 'make D=2' to create the message catalog + +ifdef D + ifeq ("$(origin D)", "command line") + KBUILD_KMSG_CHECK = $(D) + endif +endif +ifndef KBUILD_KMSG_CHECK + KBUILD_KMSG_CHECK = 0 +endif + # Use make M=dir to specify directory of external module to build # Old syntax make ... SUBDIRS=$PWD is still supported # Setting the environment variable KBUILD_EXTMOD take precedence @@ -366,6 +380,7 @@ CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void $(CF) +KMSG_CHECK = $(srctree)/scripts/kmsg-doc NOSTDINC_FLAGS = CFLAGS_MODULE = AFLAGS_MODULE = @@ -373,9 +388,13 @@ CFLAGS_KERNEL = AFLAGS_KERNEL = LDFLAGS_vmlinux = -CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,) -CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) +# Prefer linux-backports-modules +ifneq ($(KBUILD_SRC),) +ifneq ($(shell if test -e $(KBUILD_OUTPUT)/ubuntu-build; then echo yes; fi),yes) +UBUNTUINCLUDE := -I/usr/src/linux-headers-lbm-$(KERNELRELEASE) +endif +endif # Use USERINCLUDE when you must reference the UAPI directories only. USERINCLUDE := \ @@ -388,27 +407,29 @@ # Use LINUXINCLUDE when you must reference the include/ directory. # Needed to be compatible with the O= option LINUXINCLUDE := \ + $(UBUNTUINCLUDE) \ -I$(srctree)/arch/$(hdr-arch)/include \ -I$(objtree)/arch/$(hdr-arch)/include/generated \ $(if $(KBUILD_SRC), -I$(srctree)/include) \ -I$(objtree)/include \ $(USERINCLUDE) -KBUILD_CPPFLAGS := -D__KERNEL__ +# UBUNTU: Include our third party driver stuff too +LINUXINCLUDE += -Iubuntu/include $(if $(KBUILD_SRC),-I$(srctree)/ubuntu/include) +KBUILD_AFLAGS := -D__ASSEMBLY__ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common -fshort-wchar \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -std=gnu89 $(call cc-option,-fno-PIE) - - + -std=gnu89 +KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := -KBUILD_AFLAGS := -D__ASSEMBLY__ $(call cc-option,-fno-PIE) KBUILD_AFLAGS_MODULE := -DMODULE KBUILD_CFLAGS_MODULE := -DMODULE KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds +GCC_PLUGINS_CFLAGS := # Read KERNELRELEASE from include/config/kernel.release (if it exists) KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) @@ -421,8 +442,9 @@ export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS -export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV CFLAGS_KCOV CFLAGS_KASAN CFLAGS_UBSAN +export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_KASAN CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE +export KBUILD_KMSG_CHECK KMSG_CHECK export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL export KBUILD_ARFLAGS @@ -563,7 +585,7 @@ # Objects we will link into vmlinux / subdirs we need to visit init-y := init/ -drivers-y := drivers/ sound/ firmware/ +drivers-y := drivers/ sound/ firmware/ ubuntu/ net-y := net/ libs-y := lib/ core-y := usr/ @@ -622,6 +644,18 @@ # Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux +# force no-pie for distro compilers that enable pie by default +KBUILD_CFLAGS += $(call cc-option, -fno-pie) +KBUILD_CFLAGS += $(call cc-option, -no-pie) +KBUILD_AFLAGS += $(call cc-option, -fno-pie) +KBUILD_CPPFLAGS += $(call cc-option, -fno-pie) + +KBUILD_CFLAGS += $(call cc-option,-fno-PIE) +KBUILD_AFLAGS += $(call cc-option,-fno-PIE) +CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,) +CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) +export CFLAGS_GCOV CFLAGS_KCOV + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS := @@ -801,6 +835,9 @@ # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) +# Make sure -fstack-check isn't enabled (like gentoo apparently did) +KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,) + # conserve stack if available KBUILD_CFLAGS += $(call cc-option,-fconserve-stack) @@ -934,8 +971,8 @@ ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - ifdef CONFIG_ORC_UNWINDER - $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + ifdef CONFIG_UNWINDER_ORC + $(error "Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") else $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") endif @@ -1162,6 +1199,7 @@ $(error Headers not exportable for the $(SRCARCH) architecture)) $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) + $(Q)$(MAKE) $(hdr-inst)=ubuntu/include dst=include oldheaders= PHONY += headers_check_all headers_check_all: headers_install_all @@ -1171,6 +1209,7 @@ headers_check: headers_install $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include HDRCHECK=1 $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1 + $(Q)$(MAKE) $(hdr-inst)=ubuntu/include dst=include oldheaders= HDRCHECK=1 # --------------------------------------------------------------------------- # Kernel selftest --- linux-4.14.0.orig/arch/Kconfig +++ linux-4.14.0/arch/Kconfig @@ -91,7 +91,7 @@ config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES - depends on !PREEMPT + select TASKS_RCU if PREEMPT config KPROBES_ON_FTRACE def_bool y --- linux-4.14.0.orig/arch/arm/Kconfig +++ linux-4.14.0/arch/arm/Kconfig @@ -2201,6 +2201,7 @@ source "drivers/Kconfig" source "drivers/firmware/Kconfig" +source "ubuntu/Kconfig" source "fs/Kconfig" --- linux-4.14.0.orig/arch/arm/boot/dts/imx53.dtsi +++ linux-4.14.0/arch/arm/boot/dts/imx53.dtsi @@ -433,15 +433,6 @@ clock-names = "ipg", "per"; }; - srtc: srtc@53fa4000 { - compatible = "fsl,imx53-rtc", "fsl,imx25-rtc"; - reg = <0x53fa4000 0x4000>; - interrupts = <24>; - interrupt-parent = <&tzic>; - clocks = <&clks IMX5_CLK_SRTC_GATE>; - clock-names = "ipg"; - }; - iomuxc: iomuxc@53fa8000 { compatible = "fsl,imx53-iomuxc"; reg = <0x53fa8000 0x4000>; --- linux-4.14.0.orig/arch/arm/configs/exynos_defconfig +++ linux-4.14.0/arch/arm/configs/exynos_defconfig @@ -244,7 +244,7 @@ CONFIG_USB_STORAGE_KARMA=m CONFIG_USB_STORAGE_CYPRESS_ATACB=m CONFIG_USB_STORAGE_ENE_UB6250=m -CONFIG_USB_UAS=m +CONFIG_USB_UAS=y CONFIG_USB_DWC3=y CONFIG_USB_DWC2=y CONFIG_USB_HSIC_USB3503=y --- linux-4.14.0.orig/arch/arm/include/asm/assembler.h +++ linux-4.14.0/arch/arm/include/asm/assembler.h @@ -518,4 +518,22 @@ #endif .endm + .macro bug, msg, line +#ifdef CONFIG_THUMB2_KERNEL +1: .inst 0xde02 +#else +1: .inst 0xe7f001f2 +#endif +#ifdef CONFIG_DEBUG_BUGVERBOSE + .pushsection .rodata.str, "aMS", %progbits, 1 +2: .asciz "\msg" + .popsection + .pushsection __bug_table, "aw" + .align 2 + .word 1b, 2b + .hword \line + .popsection +#endif + .endm + #endif /* __ASM_ASSEMBLER_H__ */ --- linux-4.14.0.orig/arch/arm/include/asm/kvm_arm.h +++ linux-4.14.0/arch/arm/include/asm/kvm_arm.h @@ -161,8 +161,7 @@ #else #define VTTBR_X (5 - KVM_T0SZ) #endif -#define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X) #define VTTBR_VMID_SHIFT _AC(48, ULL) #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) --- linux-4.14.0.orig/arch/arm/include/asm/ptrace.h +++ linux-4.14.0/arch/arm/include/asm/ptrace.h @@ -126,8 +126,7 @@ /* * kprobe-based event tracer support */ -#include -#include +#include #define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0)) extern int regs_query_register_offset(const char *name); --- linux-4.14.0.orig/arch/arm/kernel/entry-header.S +++ linux-4.14.0/arch/arm/kernel/entry-header.S @@ -300,6 +300,8 @@ mov r2, sp ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr ldr lr, [r2, #\offset + S_PC]! @ get pc + tst r1, #PSR_I_BIT | 0x0f + bne 1f msr spsr_cxsf, r1 @ save in spsr_svc #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) @ We must avoid clrex due to Cortex-A15 erratum #830321 @@ -314,6 +316,7 @@ @ after ldm {}^ add sp, sp, #\offset + PT_REGS_SIZE movs pc, lr @ return & move spsr_svc into cpsr +1: bug "Returning to usermode but unexpected PSR bits set?", \@ #elif defined(CONFIG_CPU_V7M) @ V7M restore. @ Note that we don't need to do clrex here as clearing the local @@ -329,6 +332,8 @@ ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr ldr lr, [sp, #\offset + S_PC] @ get pc add sp, sp, #\offset + S_SP + tst r1, #PSR_I_BIT | 0x0f + bne 1f msr spsr_cxsf, r1 @ save in spsr_svc @ We must avoid clrex due to Cortex-A15 erratum #830321 @@ -341,6 +346,7 @@ .endif add sp, sp, #PT_REGS_SIZE - S_SP movs pc, lr @ return & move spsr_svc into cpsr +1: bug "Returning to usermode but unexpected PSR bits set?", \@ #endif /* !CONFIG_THUMB2_KERNEL */ .endm --- linux-4.14.0.orig/arch/arm/mach-highbank/Makefile +++ linux-4.14.0/arch/arm/mach-highbank/Makefile @@ -1,3 +1,5 @@ +KBUILD_CFLAGS += -I$(srctree)/arch/arm/mach-highbank/include + obj-y := highbank.o system.o smc.o plus_sec := $(call as-instr,.arch_extension sec,+sec) --- linux-4.14.0.orig/arch/arm/mm/dump.c +++ linux-4.14.0/arch/arm/mm/dump.c @@ -129,8 +129,8 @@ .val = PMD_SECT_USER, .set = "USR", }, { - .mask = L_PMD_SECT_RDONLY, - .val = L_PMD_SECT_RDONLY, + .mask = L_PMD_SECT_RDONLY | PMD_SECT_AP2, + .val = L_PMD_SECT_RDONLY | PMD_SECT_AP2, .set = "ro", .clear = "RW", #elif __LINUX_ARM_ARCH__ >= 6 --- linux-4.14.0.orig/arch/arm/mm/init.c +++ linux-4.14.0/arch/arm/mm/init.c @@ -639,8 +639,8 @@ .start = (unsigned long)_stext, .end = (unsigned long)__init_begin, #ifdef CONFIG_ARM_LPAE - .mask = ~L_PMD_SECT_RDONLY, - .prot = L_PMD_SECT_RDONLY, + .mask = ~(L_PMD_SECT_RDONLY | PMD_SECT_AP2), + .prot = L_PMD_SECT_RDONLY | PMD_SECT_AP2, #else .mask = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE), .prot = PMD_SECT_APX | PMD_SECT_AP_WRITE, --- linux-4.14.0.orig/arch/arm64/Kconfig +++ linux-4.14.0/arch/arm64/Kconfig @@ -539,6 +539,16 @@ If unsure, say Y. +config QCOM_FALKOR_ERRATUM_E1041 + bool "Falkor E1041: Speculative instruction fetches might cause errant memory access" + default y + help + Falkor CPU may speculatively fetch instructions from an improper + memory location when MMU translation is changed from SCTLR_ELn[M]=1 + to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem. + + If unsure, say Y. + endmenu @@ -783,6 +793,7 @@ config FORCE_MAX_ZONEORDER int default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE) + default "13" if (ARCH_THUNDER && ARM64_4K_PAGES) default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE) default "11" help @@ -1148,6 +1159,8 @@ source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "drivers/firmware/Kconfig" source "drivers/acpi/Kconfig" --- linux-4.14.0.orig/arch/arm64/Makefile +++ linux-4.14.0/arch/arm64/Makefile @@ -14,8 +14,12 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) GZFLAGS :=-9 -ifneq ($(CONFIG_RELOCATABLE),) -LDFLAGS_vmlinux += -pie -shared -Bsymbolic +ifeq ($(CONFIG_RELOCATABLE), y) +# Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour +# for relative relocs, since this leads to better Image compression +# with the relocation offsets always being zero. +LDFLAGS_vmlinux += -pie -shared -Bsymbolic \ + $(call ld-option, --no-apply-dynamic-relocs) endif ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) @@ -77,9 +81,6 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds -ifeq ($(CONFIG_DYNAMIC_FTRACE),y) -KBUILD_LDFLAGS_MODULE += $(objtree)/arch/arm64/kernel/ftrace-mod.o -endif endif # Default value --- linux-4.14.0.orig/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ linux-4.14.0/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -301,6 +301,7 @@ &usb1_phy { status = "okay"; + phy-supply = <&usb_otg_pwr>; }; &usb0 { --- linux-4.14.0.orig/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ linux-4.14.0/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -49,6 +49,14 @@ / { compatible = "amlogic,meson-gxl"; + + reserved-memory { + /* Alternate 3 MiB reserved for ARM Trusted Firmware (BL31) */ + secmon_reserved_alt: secmon@05000000 { + reg = <0x0 0x05000000 0x0 0x300000>; + no-map; + }; + }; }; ðmac { --- linux-4.14.0.orig/arch/arm64/include/asm/assembler.h +++ linux-4.14.0/arch/arm64/include/asm/assembler.h @@ -499,4 +499,14 @@ #endif .endm +/** + * Errata workaround prior to disable MMU. Insert an ISB immediately prior + * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. + */ + .macro pre_disable_mmu_workaround +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041 + isb +#endif + .endm + #endif /* __ASM_ASSEMBLER_H */ --- linux-4.14.0.orig/arch/arm64/include/asm/compat.h +++ linux-4.14.0/arch/arm64/include/asm/compat.h @@ -215,7 +215,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL /* * A pointer passed in from user mode. This should not --- linux-4.14.0.orig/arch/arm64/include/asm/cputype.h +++ linux-4.14.0/arch/arm64/include/asm/cputype.h @@ -91,6 +91,7 @@ #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 +#define QCOM_CPU_PART_FALKOR 0xC00 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -99,6 +100,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) +#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #ifndef __ASSEMBLY__ --- linux-4.14.0.orig/arch/arm64/include/asm/efi.h +++ linux-4.14.0/arch/arm64/include/asm/efi.h @@ -132,11 +132,9 @@ * Defer the switch to the current thread's TTBR0_EL1 * until uaccess_enable(). Restore the current * thread's saved ttbr0 corresponding to its active_mm - * (if different from init_mm). */ cpu_set_reserved_ttbr0(); - if (current->active_mm != &init_mm) - update_saved_ttbr0(current, current->active_mm); + update_saved_ttbr0(current, current->active_mm); } } } --- linux-4.14.0.orig/arch/arm64/include/asm/fixmap.h +++ linux-4.14.0/arch/arm64/include/asm/fixmap.h @@ -51,6 +51,13 @@ FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif /* CONFIG_ACPI_APEI_GHES */ + __end_of_permanent_fixed_addresses, /* --- linux-4.14.0.orig/arch/arm64/include/asm/kvm_arm.h +++ linux-4.14.0/arch/arm64/include/asm/kvm_arm.h @@ -170,8 +170,7 @@ #define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS) #define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA) -#define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X) #define VTTBR_VMID_SHIFT (UL(48)) #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) --- linux-4.14.0.orig/arch/arm64/include/asm/mmu_context.h +++ linux-4.14.0/arch/arm64/include/asm/mmu_context.h @@ -156,29 +156,21 @@ #define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) -/* - * This is called when "tsk" is about to enter lazy TLB mode. - * - * mm: describes the currently active mm context - * tsk: task which is entering lazy tlb - * cpu: cpu number which is entering lazy tlb - * - * tsk->mm will be NULL - */ -static inline void -enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -} - #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { - if (system_uses_ttbr0_pan()) { - BUG_ON(mm->pgd == swapper_pg_dir); - task_thread_info(tsk)->ttbr0 = - virt_to_phys(mm->pgd) | ASID(mm) << 48; - } + u64 ttbr; + + if (!system_uses_ttbr0_pan()) + return; + + if (mm == &init_mm) + ttbr = __pa_symbol(empty_zero_page); + else + ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48; + + task_thread_info(tsk)->ttbr0 = ttbr; } #else static inline void update_saved_ttbr0(struct task_struct *tsk, @@ -187,6 +179,16 @@ } #endif +static inline void +enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + /* + * We don't actually care about the ttbr0 mapping, so point it at the + * zero page. + */ + update_saved_ttbr0(tsk, &init_mm); +} + static inline void __switch_mm(struct mm_struct *next) { unsigned int cpu = smp_processor_id(); @@ -214,11 +216,9 @@ * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch - * of another thread of the same process). Avoid setting the reserved - * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit). + * of another thread of the same process). */ - if (next != &init_mm) - update_saved_ttbr0(tsk, next); + update_saved_ttbr0(tsk, next); } #define deactivate_mm(tsk,mm) do { } while (0) --- linux-4.14.0.orig/arch/arm64/include/asm/module.h +++ linux-4.14.0/arch/arm64/include/asm/module.h @@ -32,7 +32,7 @@ struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - void *ftrace_trampoline; + struct plt_entry *ftrace_trampoline; }; #endif @@ -45,4 +45,48 @@ #define module_alloc_base ((u64)_etext - MODULES_VSIZE) #endif +struct plt_entry { + /* + * A program that conforms to the AArch64 Procedure Call Standard + * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or + * IP1 (x17) may be inserted at any branch instruction that is + * exposed to a relocation that supports long branches. Since that + * is exactly what we are dealing with here, we are free to use x16 + * as a scratch register in the PLT veneers. + */ + __le32 mov0; /* movn x16, #0x.... */ + __le32 mov1; /* movk x16, #0x...., lsl #16 */ + __le32 mov2; /* movk x16, #0x...., lsl #32 */ + __le32 br; /* br x16 */ +}; + +static inline struct plt_entry get_plt_entry(u64 val) +{ + /* + * MOVK/MOVN/MOVZ opcode: + * +--------+------------+--------+-----------+-------------+---------+ + * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] | + * +--------+------------+--------+-----------+-------------+---------+ + * + * Rd := 0x10 (x16) + * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32) + * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ) + * sf := 1 (64-bit variant) + */ + return (struct plt_entry){ + cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5), + cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5), + cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5), + cpu_to_le32(0xd61f0200) + }; +} + +static inline bool plt_entries_equal(const struct plt_entry *a, + const struct plt_entry *b) +{ + return a->mov0 == b->mov0 && + a->mov1 == b->mov1 && + a->mov2 == b->mov2; +} + #endif /* __ASM_MODULE_H */ --- linux-4.14.0.orig/arch/arm64/include/asm/pgtable.h +++ linux-4.14.0/arch/arm64/include/asm/pgtable.h @@ -98,6 +98,8 @@ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) #define pte_valid_young(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) +#define pte_valid_user(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) /* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending @@ -107,6 +109,18 @@ #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) +/* + * p??_access_permitted() is true for valid user mappings (subject to the + * write permission check) other than user execute-only which do not have the + * PTE_USER bit set. PROT_NONE mappings do not have the PTE_VALID bit set. + */ +#define pte_access_permitted(pte, write) \ + (pte_valid_user(pte) && (!(write) || pte_write(pte))) +#define pmd_access_permitted(pmd, write) \ + (pte_access_permitted(pmd_pte(pmd), (write))) +#define pud_access_permitted(pud, write) \ + (pte_access_permitted(pud_pte(pud), (write))) + static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) &= ~pgprot_val(prot); @@ -135,12 +149,20 @@ static inline pte_t pte_mkclean(pte_t pte) { - return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkdirty(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); + + if (pte_write(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + + return pte; } static inline pte_t pte_mkold(pte_t pte) @@ -628,28 +650,23 @@ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * ptep_set_wrprotect - mark read-only while preserving the hardware update of - * the Access Flag. + * ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; - /* - * ptep_set_wrprotect() is only called on CoW mappings which are - * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE && - * PTE_RDONLY) or writable and software-dirty (PTE_WRITE && - * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and - * protection_map[]. There is no race with the hardware update of the - * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM) - * is set. - */ - VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep), - "%s: potential race with hardware DBM", __func__); pte = READ_ONCE(*ptep); do { old_pte = pte; + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); --- linux-4.14.0.orig/arch/arm64/kernel/Makefile +++ linux-4.14.0/arch/arm64/kernel/Makefile @@ -63,6 +63,3 @@ ifeq ($(CONFIG_DEBUG_EFI),y) AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\"" endif - -# will be included by each individual module but not by the core kernel itself -extra-$(CONFIG_DYNAMIC_FTRACE) += ftrace-mod.o --- linux-4.14.0.orig/arch/arm64/kernel/cpu-reset.S +++ linux-4.14.0/arch/arm64/kernel/cpu-reset.S @@ -37,6 +37,7 @@ mrs x12, sctlr_el1 ldr x13, =SCTLR_ELx_FLAGS bic x12, x12, x13 + pre_disable_mmu_workaround msr sctlr_el1, x12 isb --- linux-4.14.0.orig/arch/arm64/kernel/efi-entry.S +++ linux-4.14.0/arch/arm64/kernel/efi-entry.S @@ -96,6 +96,7 @@ mrs x0, sctlr_el2 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el2, x0 isb b 2f @@ -103,6 +104,7 @@ mrs x0, sctlr_el1 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el1, x0 isb 2: --- linux-4.14.0.orig/arch/arm64/kernel/ftrace.c +++ linux-4.14.0/arch/arm64/kernel/ftrace.c @@ -76,7 +76,7 @@ if (offset < -SZ_128M || offset >= SZ_128M) { #ifdef CONFIG_ARM64_MODULE_PLTS - unsigned long *trampoline; + struct plt_entry trampoline; struct module *mod; /* @@ -104,22 +104,24 @@ * is added in the future, but for now, the pr_err() below * deals with a theoretical issue only. */ - trampoline = (unsigned long *)mod->arch.ftrace_trampoline; - if (trampoline[0] != addr) { - if (trampoline[0] != 0) { + trampoline = get_plt_entry(addr); + if (!plt_entries_equal(mod->arch.ftrace_trampoline, + &trampoline)) { + if (!plt_entries_equal(mod->arch.ftrace_trampoline, + &(struct plt_entry){})) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; } /* point the trampoline to our ftrace entry point */ module_disable_ro(mod); - trampoline[0] = addr; + *mod->arch.ftrace_trampoline = trampoline; module_enable_ro(mod, true); /* update trampoline before patching in the branch */ smp_wmb(); } - addr = (unsigned long)&trampoline[1]; + addr = (unsigned long)(void *)mod->arch.ftrace_trampoline; #else /* CONFIG_ARM64_MODULE_PLTS */ return -EINVAL; #endif /* CONFIG_ARM64_MODULE_PLTS */ --- linux-4.14.0.orig/arch/arm64/kernel/head.S +++ linux-4.14.0/arch/arm64/kernel/head.S @@ -732,6 +732,7 @@ * to take into account by discarding the current kernel mapping and * creating a new one. */ + pre_disable_mmu_workaround msr sctlr_el1, x20 // disable the MMU isb bl __create_page_tables // recreate kernel mapping --- linux-4.14.0.orig/arch/arm64/kernel/module-plts.c +++ linux-4.14.0/arch/arm64/kernel/module-plts.c @@ -11,21 +11,6 @@ #include #include -struct plt_entry { - /* - * A program that conforms to the AArch64 Procedure Call Standard - * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or - * IP1 (x17) may be inserted at any branch instruction that is - * exposed to a relocation that supports long branches. Since that - * is exactly what we are dealing with here, we are free to use x16 - * as a scratch register in the PLT veneers. - */ - __le32 mov0; /* movn x16, #0x.... */ - __le32 mov1; /* movk x16, #0x...., lsl #16 */ - __le32 mov2; /* movk x16, #0x...., lsl #32 */ - __le32 br; /* br x16 */ -}; - static bool in_init(const struct module *mod, void *loc) { return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size; @@ -40,33 +25,14 @@ int i = pltsec->plt_num_entries; u64 val = sym->st_value + rela->r_addend; - /* - * MOVK/MOVN/MOVZ opcode: - * +--------+------------+--------+-----------+-------------+---------+ - * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] | - * +--------+------------+--------+-----------+-------------+---------+ - * - * Rd := 0x10 (x16) - * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32) - * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ) - * sf := 1 (64-bit variant) - */ - plt[i] = (struct plt_entry){ - cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5), - cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5), - cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5), - cpu_to_le32(0xd61f0200) - }; + plt[i] = get_plt_entry(val); /* * Check if the entry we just created is a duplicate. Given that the * relocations are sorted, this will be the last entry we allocated. * (if one exists). */ - if (i > 0 && - plt[i].mov0 == plt[i - 1].mov0 && - plt[i].mov1 == plt[i - 1].mov1 && - plt[i].mov2 == plt[i - 1].mov2) + if (i > 0 && plt_entries_equal(plt + i, plt + i - 1)) return (u64)&plt[i - 1]; pltsec->plt_num_entries++; @@ -154,6 +120,7 @@ unsigned long core_plts = 0; unsigned long init_plts = 0; Elf64_Sym *syms = NULL; + Elf_Shdr *tramp = NULL; int i; /* @@ -165,6 +132,10 @@ mod->arch.core.plt = sechdrs + i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt")) mod->arch.init.plt = sechdrs + i; + else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && + !strcmp(secstrings + sechdrs[i].sh_name, + ".text.ftrace_trampoline")) + tramp = sechdrs + i; else if (sechdrs[i].sh_type == SHT_SYMTAB) syms = (Elf64_Sym *)sechdrs[i].sh_addr; } @@ -215,5 +186,12 @@ mod->arch.init.plt_num_entries = 0; mod->arch.init.plt_max_entries = init_plts; + if (tramp) { + tramp->sh_type = SHT_NOBITS; + tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + tramp->sh_addralign = __alignof__(struct plt_entry); + tramp->sh_size = sizeof(struct plt_entry); + } + return 0; } --- linux-4.14.0.orig/arch/arm64/kernel/module.lds +++ linux-4.14.0/arch/arm64/kernel/module.lds @@ -1,4 +1,5 @@ SECTIONS { .plt (NOLOAD) : { BYTE(0) } .init.plt (NOLOAD) : { BYTE(0) } + .text.ftrace_trampoline (NOLOAD) : { BYTE(0) } } --- linux-4.14.0.orig/arch/arm64/kernel/process.c +++ linux-4.14.0/arch/arm64/kernel/process.c @@ -258,6 +258,15 @@ memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); + /* + * In case p was allocated the same task_struct pointer as some + * other recently-exited task, make sure p is disassociated from + * any cpu that may have run that now-exited task recently. + * Otherwise we could erroneously skip reloading the FPSIMD + * registers for p. + */ + fpsimd_flush_task_state(p); + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; --- linux-4.14.0.orig/arch/arm64/kernel/relocate_kernel.S +++ linux-4.14.0/arch/arm64/kernel/relocate_kernel.S @@ -45,6 +45,7 @@ mrs x0, sctlr_el2 ldr x1, =SCTLR_ELx_FLAGS bic x0, x0, x1 + pre_disable_mmu_workaround msr sctlr_el2, x0 isb 1: --- linux-4.14.0.orig/arch/arm64/kvm/hyp-init.S +++ linux-4.14.0/arch/arm64/kvm/hyp-init.S @@ -151,6 +151,7 @@ mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc + pre_disable_mmu_workaround msr sctlr_el2, x5 isb --- linux-4.14.0.orig/arch/arm64/kvm/hyp/debug-sr.c +++ linux-4.14.0/arch/arm64/kvm/hyp/debug-sr.c @@ -84,6 +84,9 @@ { u64 reg; + /* Clear pmscr in case of early return */ + *pmscr_el1 = 0; + /* SPE present on this CPU? */ if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1), ID_AA64DFR0_PMSVER_SHIFT)) --- linux-4.14.0.orig/arch/arm64/mm/dump.c +++ linux-4.14.0/arch/arm64/mm/dump.c @@ -389,7 +389,7 @@ .check_wx = true, }; - walk_pgd(&st, &init_mm, 0); + walk_pgd(&st, &init_mm, VA_START); note_page(&st, 0, 0, 0); if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", --- linux-4.14.0.orig/arch/arm64/mm/init.c +++ linux-4.14.0/arch/arm64/mm/init.c @@ -476,6 +476,8 @@ reserve_elfcorehdr(); + high_memory = __va(memblock_end_of_DRAM() - 1) + 1; + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); @@ -502,7 +504,6 @@ sparse_init(); zone_sizes_init(min, max); - high_memory = __va((max << PAGE_SHIFT) - 1) + 1; memblock_dump_all(); } --- linux-4.14.0.orig/arch/blackfin/Kconfig +++ linux-4.14.0/arch/blackfin/Kconfig @@ -321,11 +321,14 @@ config GPIO_ADI def_bool y + depends on !PINCTRL depends on (BF51x || BF52x || BF53x || BF538 || BF539 || BF561) -config PINCTRL +config PINCTRL_BLACKFIN_ADI2 def_bool y - depends on BF54x || BF60x + depends on (BF54x || BF60x) + select PINCTRL + select PINCTRL_ADI2 config MEM_MT48LC64M4A2FB_7E bool --- linux-4.14.0.orig/arch/blackfin/Kconfig.debug +++ linux-4.14.0/arch/blackfin/Kconfig.debug @@ -18,6 +18,7 @@ config DEBUG_MMRS tristate "Generate Blackfin MMR tree" + depends on !PINCTRL select DEBUG_FS help Create a tree of Blackfin MMRs via the debugfs tree. If --- linux-4.14.0.orig/arch/m68k/mm/mcfmmu.c +++ linux-4.14.0/arch/m68k/mm/mcfmmu.c @@ -170,7 +170,7 @@ max_pfn = max_low_pfn = PFN_DOWN(_ramend); high_memory = (void *)_ramend; - m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6; + m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); /* setup bootmem data */ --- linux-4.14.0.orig/arch/mips/Kconfig +++ linux-4.14.0/arch/mips/Kconfig @@ -65,7 +65,7 @@ select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS - select HAVE_VIRT_CPU_ACCOUNTING_GEN + select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES && 64BIT select MODULES_USE_ELF_REL if MODULES --- linux-4.14.0.orig/arch/mips/bcm47xx/leds.c +++ linux-4.14.0/arch/mips/bcm47xx/leds.c @@ -331,7 +331,7 @@ /* Verified on: WRT54GS V1.0 */ static const struct gpio_led bcm47xx_leds_linksys_wrt54g_type_0101[] __initconst = { - BCM47XX_GPIO_LED(0, "green", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF), + BCM47XX_GPIO_LED(0, "green", "wlan", 1, LEDS_GPIO_DEFSTATE_OFF), BCM47XX_GPIO_LED(1, "green", "power", 0, LEDS_GPIO_DEFSTATE_ON), BCM47XX_GPIO_LED(7, "green", "dmz", 1, LEDS_GPIO_DEFSTATE_OFF), }; --- linux-4.14.0.orig/arch/mips/boot/dts/brcm/Makefile +++ linux-4.14.0/arch/mips/boot/dts/brcm/Makefile @@ -23,7 +23,6 @@ bcm63268-comtrend-vr-3032u.dtb \ bcm93384wvg.dtb \ bcm93384wvg_viper.dtb \ - bcm96358nb4ser.dtb \ bcm96368mvwg.dtb \ bcm9ejtagprb.dtb \ bcm97125cbmb.dtb \ --- linux-4.14.0.orig/arch/mips/include/asm/Kbuild +++ linux-4.14.0/arch/mips/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += qspinlock.h generic-y += sections.h generic-y += segment.h -generic-y += serial.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += user.h --- linux-4.14.0.orig/arch/mips/include/asm/asmmacro.h +++ linux-4.14.0/arch/mips/include/asm/asmmacro.h @@ -19,6 +19,9 @@ #include #endif +/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */ +#undef fp + /* * Helper macros for generating raw instruction encodings. */ @@ -105,6 +108,7 @@ .macro fpu_save_16odd thread .set push .set mips64r2 + .set fp=64 SET_HARDFLOAT sdc1 $f1, THREAD_FPR1(\thread) sdc1 $f3, THREAD_FPR3(\thread) @@ -126,8 +130,8 @@ .endm .macro fpu_save_double thread status tmp -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) sll \tmp, \status, 5 bgez \tmp, 10f fpu_save_16odd \thread @@ -163,6 +167,7 @@ .macro fpu_restore_16odd thread .set push .set mips64r2 + .set fp=64 SET_HARDFLOAT ldc1 $f1, THREAD_FPR1(\thread) ldc1 $f3, THREAD_FPR3(\thread) @@ -184,8 +189,8 @@ .endm .macro fpu_restore_double thread status tmp -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) sll \tmp, \status, 5 bgez \tmp, 10f # 16 register mode? @@ -234,9 +239,6 @@ .endm #ifdef TOOLCHAIN_SUPPORTS_MSA -/* preprocessor replaces the fp in ".set fp=64" with $30 otherwise */ -#undef fp - .macro _cfcmsa rd, cs .set push .set mips32r2 --- linux-4.14.0.orig/arch/mips/include/asm/cmpxchg.h +++ linux-4.14.0/arch/mips/include/asm/cmpxchg.h @@ -204,8 +204,10 @@ #else #include #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) +#ifndef CONFIG_SMP #define cmpxchg64(ptr, o, n) cmpxchg64_local((ptr), (o), (n)) #endif +#endif #undef __scbeqz --- linux-4.14.0.orig/arch/mips/include/asm/compat.h +++ linux-4.14.0/arch/mips/include/asm/compat.h @@ -200,7 +200,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL /* * A pointer passed in from user mode. This should not --- linux-4.14.0.orig/arch/mips/include/asm/serial.h +++ linux-4.14.0/arch/mips/include/asm/serial.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2017 MIPS Tech, LLC + * + * 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. + */ +#ifndef __ASM__SERIAL_H +#define __ASM__SERIAL_H + +#ifdef CONFIG_MIPS_GENERIC +/* + * Generic kernels cannot know a correct value for all platforms at + * compile time. Set it to 0 to prevent 8250_early using it + */ +#define BASE_BAUD 0 +#else +#include +#endif + +#endif /* __ASM__SERIAL_H */ --- linux-4.14.0.orig/arch/mips/kernel/ptrace.c +++ linux-4.14.0/arch/mips/kernel/ptrace.c @@ -618,6 +618,19 @@ .n = ARRAY_SIZE(mips64_regsets), }; +#ifdef CONFIG_MIPS32_N32 + +static const struct user_regset_view user_mipsn32_view = { + .name = "mipsn32", + .e_flags = EF_MIPS_ABI2, + .e_machine = ELF_ARCH, + .ei_osabi = ELF_OSABI, + .regsets = mips64_regsets, + .n = ARRAY_SIZE(mips64_regsets), +}; + +#endif /* CONFIG_MIPS32_N32 */ + #endif /* CONFIG_64BIT */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) @@ -629,6 +642,10 @@ if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) return &user_mips_view; #endif +#ifdef CONFIG_MIPS32_N32 + if (test_tsk_thread_flag(task, TIF_32BIT_ADDR)) + return &user_mipsn32_view; +#endif return &user_mips64_view; #endif } --- linux-4.14.0.orig/arch/mips/kernel/r4k_fpu.S +++ linux-4.14.0/arch/mips/kernel/r4k_fpu.S @@ -40,8 +40,8 @@ */ LEAF(_save_fp) EXPORT_SYMBOL(_save_fp) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) mfc0 t0, CP0_STATUS #endif fpu_save_double a0 t0 t1 # clobbers t1 @@ -52,8 +52,8 @@ * Restore a thread's fp context. */ LEAF(_restore_fp) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) mfc0 t0, CP0_STATUS #endif fpu_restore_double a0 t0 t1 # clobbers t1 @@ -246,11 +246,11 @@ cfc1 t1, fcr31 .set pop -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) .set push SET_HARDFLOAT -#ifdef CONFIG_CPU_MIPS32_R2 +#ifdef CONFIG_CPU_MIPSR2 .set mips32r2 .set fp=64 mfc0 t0, CP0_STATUS @@ -314,11 +314,11 @@ LEAF(_restore_fp_context) EX lw t1, 0(a1) -#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2) || \ - defined(CONFIG_CPU_MIPS32_R6) +#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPSR2) || \ + defined(CONFIG_CPU_MIPSR6) .set push SET_HARDFLOAT -#ifdef CONFIG_CPU_MIPS32_R2 +#ifdef CONFIG_CPU_MIPSR2 .set mips32r2 .set fp=64 mfc0 t0, CP0_STATUS --- linux-4.14.0.orig/arch/mips/math-emu/cp1emu.c +++ linux-4.14.0/arch/mips/math-emu/cp1emu.c @@ -1795,7 +1795,7 @@ SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(fd, MIPSInst_FD(ir)); rv.s = ieee754sp_maddf(fd, fs, ft); - break; + goto copcsr; } case fmsubf_op: { @@ -1809,7 +1809,7 @@ SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(fd, MIPSInst_FD(ir)); rv.s = ieee754sp_msubf(fd, fs, ft); - break; + goto copcsr; } case frint_op: { @@ -1834,7 +1834,7 @@ SPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754sp_2008class(fs); rfmt = w_fmt; - break; + goto copcsr; } case fmin_op: { @@ -1847,7 +1847,7 @@ SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmin(fs, ft); - break; + goto copcsr; } case fmina_op: { @@ -1860,7 +1860,7 @@ SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmina(fs, ft); - break; + goto copcsr; } case fmax_op: { @@ -1873,7 +1873,7 @@ SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmax(fs, ft); - break; + goto copcsr; } case fmaxa_op: { @@ -1886,7 +1886,7 @@ SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmaxa(fs, ft); - break; + goto copcsr; } case fabs_op: @@ -2165,7 +2165,7 @@ DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(fd, MIPSInst_FD(ir)); rv.d = ieee754dp_maddf(fd, fs, ft); - break; + goto copcsr; } case fmsubf_op: { @@ -2179,7 +2179,7 @@ DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(fd, MIPSInst_FD(ir)); rv.d = ieee754dp_msubf(fd, fs, ft); - break; + goto copcsr; } case frint_op: { @@ -2204,7 +2204,7 @@ DPFROMREG(fs, MIPSInst_FS(ir)); rv.l = ieee754dp_2008class(fs); rfmt = l_fmt; - break; + goto copcsr; } case fmin_op: { @@ -2217,7 +2217,7 @@ DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmin(fs, ft); - break; + goto copcsr; } case fmina_op: { @@ -2230,7 +2230,7 @@ DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmina(fs, ft); - break; + goto copcsr; } case fmax_op: { @@ -2243,7 +2243,7 @@ DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmax(fs, ft); - break; + goto copcsr; } case fmaxa_op: { @@ -2256,7 +2256,7 @@ DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmaxa(fs, ft); - break; + goto copcsr; } case fabs_op: --- linux-4.14.0.orig/arch/mips/pci/pci-mt7620.c +++ linux-4.14.0/arch/mips/pci/pci-mt7620.c @@ -121,7 +121,7 @@ else break; if (retry++ > WAITRETRY_MAX) { - printk(KERN_WARN "PCIE-PHY retry failed.\n"); + pr_warn("PCIE-PHY retry failed.\n"); return -1; } } --- linux-4.14.0.orig/arch/mips/ralink/mt7620.c +++ linux-4.14.0/arch/mips/ralink/mt7620.c @@ -145,8 +145,8 @@ FUNC("i2c", 0, 4, 2), }; -static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) }; -static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) }; +static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("refclk", 0, 37, 1) }; +static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 36, 1) }; static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) }; static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) }; --- linux-4.14.0.orig/arch/parisc/boot/compressed/misc.c +++ linux-4.14.0/arch/parisc/boot/compressed/misc.c @@ -123,8 +123,8 @@ while ((nuline = strchr(s, '\n')) != NULL) { if (nuline != s) pdc_iodc_print(s, nuline - s); - pdc_iodc_print("\r\n", 2); - s = nuline + 1; + pdc_iodc_print("\r\n", 2); + s = nuline + 1; } if (*s != '\0') pdc_iodc_print(s, strlen(s)); --- linux-4.14.0.orig/arch/parisc/include/asm/compat.h +++ linux-4.14.0/arch/parisc/include/asm/compat.h @@ -195,7 +195,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL struct compat_ipc64_perm { compat_key_t key; --- linux-4.14.0.orig/arch/parisc/kernel/entry.S +++ linux-4.14.0/arch/parisc/kernel/entry.S @@ -878,9 +878,6 @@ STREG %r19,PT_SR7(%r16) intr_return: - /* NOTE: Need to enable interrupts incase we schedule. */ - ssm PSW_SM_I, %r0 - /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -907,6 +904,11 @@ LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ + /* NOTE: We need to enable interrupts if we have to deliver + * signals. We used to do this earlier but it caused kernel + * stack overflows. */ + ssm PSW_SM_I, %r0 + copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -958,6 +960,10 @@ cmpib,COND(=) 0, %r20, intr_do_preempt nop + /* NOTE: We need to enable interrupts if we schedule. We used + * to do this earlier but it caused kernel stack overflows. */ + ssm PSW_SM_I, %r0 + #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif --- linux-4.14.0.orig/arch/parisc/kernel/hpmc.S +++ linux-4.14.0/arch/parisc/kernel/hpmc.S @@ -305,6 +305,7 @@ __INITRODATA + .align 4 .export os_hpmc_size os_hpmc_size: .word .os_hpmc_end-.os_hpmc --- linux-4.14.0.orig/arch/parisc/kernel/syscall.S +++ linux-4.14.0/arch/parisc/kernel/syscall.S @@ -690,15 +690,15 @@ /* ELF32 Process entry path */ lws_compare_and_swap_2: #ifdef CONFIG_64BIT - /* Clip the input registers */ + /* Clip the input registers. We don't need to clip %r23 as we + only use it for word operations */ depdi 0, 31, 32, %r26 depdi 0, 31, 32, %r25 depdi 0, 31, 32, %r24 - depdi 0, 31, 32, %r23 #endif /* Check the validity of the size pointer */ - subi,>>= 4, %r23, %r0 + subi,>>= 3, %r23, %r0 b,n lws_exit_nosys /* Jump to the functions which will load the old and new values into --- linux-4.14.0.orig/arch/powerpc/Kconfig +++ linux-4.14.0/arch/powerpc/Kconfig @@ -1212,6 +1212,8 @@ source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "fs/Kconfig" source "lib/Kconfig" --- linux-4.14.0.orig/arch/powerpc/Makefile +++ linux-4.14.0/arch/powerpc/Makefile @@ -279,7 +279,7 @@ all: zImage # With make 3.82 we cannot mix normal and wildcard targets -BOOT_TARGETS1 := zImage zImage.initrd uImage +BOOT_TARGETS1 := zImage zImage.initrd uImage vmlinux.strip BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% uImage.% PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2) --- linux-4.14.0.orig/arch/powerpc/include/asm/compat.h +++ linux-4.14.0/arch/powerpc/include/asm/compat.h @@ -185,7 +185,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL /* * A pointer passed in from user mode. This should not --- linux-4.14.0.orig/arch/powerpc/include/asm/cputhreads.h +++ linux-4.14.0/arch/powerpc/include/asm/cputhreads.h @@ -3,6 +3,7 @@ #define _ASM_POWERPC_CPUTHREADS_H #ifndef __ASSEMBLY__ +#include #include #include --- linux-4.14.0.orig/arch/powerpc/include/asm/emulated_ops.h +++ linux-4.14.0/arch/powerpc/include/asm/emulated_ops.h @@ -55,6 +55,10 @@ struct ppc_emulated_entry mfdscr; struct ppc_emulated_entry mtdscr; struct ppc_emulated_entry lq_stq; + struct ppc_emulated_entry lxvw4x; + struct ppc_emulated_entry lxvh8x; + struct ppc_emulated_entry lxvd2x; + struct ppc_emulated_entry lxvb16x; #endif } ppc_emulated; --- linux-4.14.0.orig/arch/powerpc/include/asm/epapr_hcalls.h +++ linux-4.14.0/arch/powerpc/include/asm/epapr_hcalls.h @@ -508,7 +508,7 @@ static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; unsigned long r; @@ -520,7 +520,7 @@ static inline long epapr_hypercall0(unsigned int nr) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; return epapr_hypercall(in, out, nr); @@ -528,7 +528,7 @@ static inline long epapr_hypercall1(unsigned int nr, unsigned long p1) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; in[0] = p1; @@ -538,7 +538,7 @@ static inline long epapr_hypercall2(unsigned int nr, unsigned long p1, unsigned long p2) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; in[0] = p1; @@ -549,7 +549,7 @@ static inline long epapr_hypercall3(unsigned int nr, unsigned long p1, unsigned long p2, unsigned long p3) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; in[0] = p1; @@ -562,7 +562,7 @@ unsigned long p2, unsigned long p3, unsigned long p4) { - unsigned long in[8]; + unsigned long in[8] = {0}; unsigned long out[8]; in[0] = p1; --- linux-4.14.0.orig/arch/powerpc/include/asm/machdep.h +++ linux-4.14.0/arch/powerpc/include/asm/machdep.h @@ -76,6 +76,7 @@ void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); + void (*panic)(char *str); void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ --- linux-4.14.0.orig/arch/powerpc/include/asm/mmu_context.h +++ linux-4.14.0/arch/powerpc/include/asm/mmu_context.h @@ -114,9 +114,10 @@ #endif } -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) { + return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) --- linux-4.14.0.orig/arch/powerpc/include/asm/paca.h +++ linux-4.14.0/arch/powerpc/include/asm/paca.h @@ -49,6 +49,9 @@ #define get_lppaca() (get_paca()->lppaca_ptr) #define get_slb_shadow() (get_paca()->slb_shadow_ptr) +/* Maximum number of threads per core. */ +#define MAX_SMT 8 + struct task_struct; /* @@ -210,6 +213,7 @@ */ u16 in_mce; u8 hmi_event_available; /* HMI event is available */ + u8 hmi_p9_special_emu; /* HMI P9 special emulation */ #endif /* Stuff for accurate time accounting */ --- linux-4.14.0.orig/arch/powerpc/include/asm/setup.h +++ linux-4.14.0/arch/powerpc/include/asm/setup.h @@ -24,6 +24,7 @@ void check_for_initrd(void); void initmem_init(void); +void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES --- linux-4.14.0.orig/arch/powerpc/include/asm/smp.h +++ linux-4.14.0/arch/powerpc/include/asm/smp.h @@ -30,6 +30,7 @@ #include extern int boot_cpuid; +extern int boot_hw_cpuid; extern int spinning_secondaries; extern void cpu_die(void); --- linux-4.14.0.orig/arch/powerpc/include/asm/uaccess.h +++ linux-4.14.0/arch/powerpc/include/asm/uaccess.h @@ -174,6 +174,23 @@ extern long __get_user_bad(void); +/* + * This does an atomic 128 byte aligned load from userspace. + * Upto caller to do enable_kernel_vmx() before calling! + */ +#define __get_user_atomic_128_aligned(kaddr, uaddr, err) \ + __asm__ __volatile__( \ + "1: lvx 0,0,%1 # get user\n" \ + " stvx 0,0,%2 # put kernel\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: li %0,%3\n" \ + " b 2b\n" \ + ".previous\n" \ + EX_TABLE(1b, 3b) \ + : "=r" (err) \ + : "b" (uaddr), "b" (kaddr), "i" (-EFAULT), "0" (err)) + #define __get_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ "1: "op" %1,0(%2) # get_user\n" \ --- linux-4.14.0.orig/arch/powerpc/kernel/cpu_setup_power.S +++ linux-4.14.0/arch/powerpc/kernel/cpu_setup_power.S @@ -102,6 +102,7 @@ li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 @@ -126,6 +127,7 @@ li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 --- linux-4.14.0.orig/arch/powerpc/kernel/exceptions-64s.S +++ linux-4.14.0/arch/powerpc/kernel/exceptions-64s.S @@ -542,7 +542,7 @@ RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,_NIP(r1) - andis. r4,r12,DSISR_BAD_FAULT_64S@h + andis. r4,r12,DSISR_SRR1_MATCH_64S@h li r5,0x400 std r3,_DAR(r1) std r4,_DSISR(r1) @@ -1033,6 +1033,8 @@ EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */ + cmpdi cr0,r3,0 + /* Windup the stack. */ /* Move original HSRR0 and HSRR1 into the respective regs */ ld r9,_MSR(r1) @@ -1049,10 +1051,15 @@ REST_8GPRS(2, r1) REST_GPR(10, r1) ld r11,_CCR(r1) + REST_2GPRS(12, r1) + bne 1f mtcr r11 REST_GPR(11, r1) - REST_2GPRS(12, r1) - /* restore original r1. */ + ld r1,GPR1(r1) + hrfid + +1: mtcr r11 + REST_GPR(11, r1) ld r1,GPR1(r1) /* @@ -1065,8 +1072,9 @@ EXCEPTION_PROLOG_0(PACA_EXGEN) b tramp_real_hmi_exception -EXC_COMMON_ASYNC(hmi_exception_common, 0xe60, handle_hmi_exception) - +EXC_COMMON_BEGIN(hmi_exception_common) +EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception, + ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON) EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20) EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80) --- linux-4.14.0.orig/arch/powerpc/kernel/fadump.c +++ linux-4.14.0/arch/powerpc/kernel/fadump.c @@ -1453,25 +1453,6 @@ return; } -static int fadump_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - /* - * If firmware-assisted dump has been registered then trigger - * firmware-assisted dump and let firmware handle everything - * else. If this returns, then fadump was not registered, so - * go through the rest of the panic path. - */ - crash_fadump(NULL, ptr); - - return NOTIFY_DONE; -} - -static struct notifier_block fadump_panic_block = { - .notifier_call = fadump_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - /* * Prepare for firmware-assisted dump. */ @@ -1504,9 +1485,6 @@ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); fadump_init_files(); - atomic_notifier_chain_register(&panic_notifier_list, - &fadump_panic_block); - return 1; } subsys_initcall(setup_fadump); --- linux-4.14.0.orig/arch/powerpc/kernel/kprobes-ftrace.c +++ linux-4.14.0/arch/powerpc/kernel/kprobes-ftrace.c @@ -65,6 +65,7 @@ /* Disable irq for emulating a breakpoint and avoiding preempt */ local_irq_save(flags); hard_irq_disable(); + preempt_disable(); p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) @@ -86,12 +87,18 @@ kcb->kprobe_status = KPROBE_HIT_ACTIVE; if (!p->pre_handler || !p->pre_handler(p, regs)) __skip_singlestep(p, regs, kcb, orig_nip); - /* - * If pre_handler returns !0, it sets regs->nip and - * resets current kprobe. - */ + else { + /* + * If pre_handler returns !0, it sets regs->nip and + * resets current kprobe. In this case, we still need + * to restore irq, but not preemption. + */ + local_irq_restore(flags); + return; + } } end: + preempt_enable_no_resched(); local_irq_restore(flags); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); --- linux-4.14.0.orig/arch/powerpc/kernel/mce.c +++ linux-4.14.0/arch/powerpc/kernel/mce.c @@ -470,6 +470,34 @@ { __this_cpu_inc(irq_stat.hmi_exceptions); +#ifdef CONFIG_PPC_BOOK3S_64 + /* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */ + if (pvr_version_is(PVR_POWER9)) { + unsigned long hmer = mfspr(SPRN_HMER); + + /* Do we have the debug bit set */ + if (hmer & PPC_BIT(17)) { + hmer &= ~PPC_BIT(17); + mtspr(SPRN_HMER, hmer); + + /* + * Now to avoid problems with soft-disable we + * only do the emulation if we are coming from + * user space + */ + if (user_mode(regs)) + local_paca->hmi_p9_special_emu = 1; + + /* + * Don't bother going to OPAL if that's the + * only relevant bit. + */ + if (!(hmer & mfspr(SPRN_HMEER))) + return local_paca->hmi_p9_special_emu; + } + } +#endif /* CONFIG_PPC_BOOK3S_64 */ + wait_for_subcore_guest_exit(); if (ppc_md.hmi_exception_early) @@ -477,5 +505,5 @@ wait_for_tb_resync(); - return 0; + return 1; } --- linux-4.14.0.orig/arch/powerpc/kernel/misc_64.S +++ linux-4.14.0/arch/powerpc/kernel/misc_64.S @@ -623,7 +623,9 @@ * NOTE, we rely on r0 being 0 from above. */ mtspr SPRN_IAMR,r0 +BEGIN_FTR_SECTION_NESTED(42) mtspr SPRN_AMOR,r0 +END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) /* save regs for local vars on new stack. --- linux-4.14.0.orig/arch/powerpc/kernel/optprobes.c +++ linux-4.14.0/arch/powerpc/kernel/optprobes.c @@ -115,7 +115,6 @@ static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long flags; /* This is possible if op is under delayed unoptimizing */ @@ -124,13 +123,14 @@ local_irq_save(flags); hard_irq_disable(); + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); } else { __this_cpu_write(current_kprobe, &op->kp); regs->nip = (unsigned long)op->kp.addr; - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } @@ -140,6 +140,7 @@ * local_irq_restore() will re-enable interrupts, * if they were hard disabled. */ + preempt_enable_no_resched(); local_irq_restore(flags); } NOKPROBE_SYMBOL(optimized_callback); --- linux-4.14.0.orig/arch/powerpc/kernel/paca.c +++ linux-4.14.0/arch/powerpc/kernel/paca.c @@ -207,6 +207,7 @@ { u64 limit; int cpu; + unsigned int nr_cpus; limit = ppc64_rma_size; @@ -219,20 +220,32 @@ limit = min(0x10000000ULL, limit); #endif - paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); + /* + * Always align up the nr_cpu_ids to SMT threads and allocate + * the paca. This will help us to prepare for a situation where + * boot cpu id > nr_cpus_id. We will use the last nthreads + * slots (nthreads == threads per core) to accommodate a core + * that contains boot cpu thread. + * + * Do not change nr_cpu_ids value here. Let us do that in + * early_init_dt_scan_cpus() where we know exact value + * of threads per core. + */ + nr_cpus = _ALIGN_UP(nr_cpu_ids, MAX_SMT); + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); memset(paca, 0, paca_size); printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n", - paca_size, nr_cpu_ids, paca); + paca_size, nr_cpus, paca); - allocate_lppacas(nr_cpu_ids, limit); + allocate_lppacas(nr_cpus, limit); - allocate_slb_shadows(nr_cpu_ids, limit); + allocate_slb_shadows(nr_cpus, limit); /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < nr_cpu_ids; cpu++) + for (cpu = 0; cpu < nr_cpus; cpu++) initialise_paca(&paca[cpu], cpu); } --- linux-4.14.0.orig/arch/powerpc/kernel/pci-common.c +++ linux-4.14.0/arch/powerpc/kernel/pci-common.c @@ -331,6 +331,7 @@ } return NULL; } +EXPORT_SYMBOL(pci_find_hose_for_OF_device); /* * Reads the interrupt pin to determine if interrupt is use by card. @@ -1648,6 +1649,7 @@ { return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); } +EXPORT_SYMBOL_GPL(early_find_capability); struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) { --- linux-4.14.0.orig/arch/powerpc/kernel/prom.c +++ linux-4.14.0/arch/powerpc/kernel/prom.c @@ -302,6 +302,29 @@ } } +/* + * Adjust the logical id of a boot cpu to fall under nr_cpu_ids. Map it to + * last core slot in the allocated paca array. + * + * e.g. on SMT=8 system, kernel booted with nr_cpus=1 and boot cpu = 33, + * align nr_cpu_ids to MAX_SMT value 8. Allocate paca array to hold up-to + * MAX_SMT=8 cpus. Since boot cpu 33 is greater than nr_cpus (8), adjust + * its logical id so that new id becomes less than nr_cpu_ids. Make sure + * that boot cpu's new logical id is aligned to its thread id and falls + * under last nthreads slots available in paca array. In this case the + * boot cpu 33 is adjusted to new boot cpu id 1. + * + */ +static inline void adjust_boot_cpuid(int nthreads, int phys_id) +{ + boot_hw_cpuid = phys_id; + if (boot_cpuid >= nr_cpu_ids) { + boot_cpuid = (boot_cpuid % nthreads) + (nr_cpu_ids - nthreads); + pr_info("Adjusted logical boot cpu id: logical %d physical %d\n", + boot_cpuid, phys_id); + } +} + static int __init early_init_dt_scan_cpus(unsigned long node, const char *uname, int depth, void *data) @@ -325,6 +348,18 @@ nthreads = len / sizeof(int); +#ifdef CONFIG_SMP + /* + * Now that we know threads per core lets align nr_cpu_ids to + * correct SMT value. + */ + if (nr_cpu_ids % nthreads) { + nr_cpu_ids = _ALIGN_UP(nr_cpu_ids, nthreads); + pr_info("Aligned nr_cpus to SMT=%d, nr_cpu_ids = %d\n", + nthreads, nr_cpu_ids); + } +#endif + /* * Now see if any of these threads match our boot cpu. * NOTE: This must match the parsing done in smp_setup_cpu_maps. @@ -363,7 +398,9 @@ DBG("boot cpu: logical %d physical %d\n", found, be32_to_cpu(intserv[found_thread])); boot_cpuid = found; - set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); + adjust_boot_cpuid(nthreads, be32_to_cpu(intserv[found_thread])); + set_hard_smp_processor_id(boot_cpuid, + be32_to_cpu(intserv[found_thread])); /* * PAPR defines "logical" PVR values for cpus that --- linux-4.14.0.orig/arch/powerpc/kernel/setup-common.c +++ linux-4.14.0/arch/powerpc/kernel/setup-common.c @@ -85,6 +85,7 @@ EXPORT_SYMBOL(machine_id); int boot_cpuid = -1; +int boot_hw_cpuid = -1; EXPORT_SYMBOL_GPL(boot_cpuid); /* @@ -473,6 +474,7 @@ struct device_node *dn = NULL; int cpu = 0; int nthreads = 1; + bool boot_cpu_added = false; DBG("smp_setup_cpu_maps()\n"); @@ -499,6 +501,24 @@ } nthreads = len / sizeof(int); + /* + * If boot cpu hasn't been added to paca and there are only + * last nthreads slots available in paca array then wait + * for boot cpu to show up. + */ + if (!boot_cpu_added && (cpu + nthreads) >= nr_cpu_ids) { + int found = 0; + + DBG("Holding last nthreads paca slots for boot cpu\n"); + for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { + if (boot_hw_cpuid == be32_to_cpu(intserv[j])) { + found = 1; + break; + } + } + if (!found) + continue; + } for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { bool avail; @@ -514,6 +534,11 @@ set_cpu_present(cpu, avail); set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); + if (boot_hw_cpuid == be32_to_cpu(intserv[j])) { + DBG("Boot cpu %d (hard id %d) added to paca\n", + cpu, be32_to_cpu(intserv[j])); + boot_cpu_added = true; + } cpu++; } } @@ -704,6 +729,30 @@ } EXPORT_SYMBOL(check_legacy_ioport); +static int ppc_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + /* + * If firmware-assisted dump has been registered then trigger + * firmware-assisted dump and let firmware handle everything else. + */ + crash_fadump(NULL, ptr); + ppc_md.panic(ptr); /* May not return */ + return NOTIFY_DONE; +} + +static struct notifier_block ppc_panic_block = { + .notifier_call = ppc_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + +void __init setup_panic(void) +{ + if (!ppc_md.panic) + return; + atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); +} + #ifdef CONFIG_CHECK_CACHE_COHERENCY /* * For platforms that have configurable cache-coherency. This function @@ -848,6 +897,9 @@ /* Probe the machine type, establish ppc_md. */ probe_machine(); + /* Setup panic notifier if requested by the platform. */ + setup_panic(); + /* * Configure ppc_md.power_save (ppc32 only, 64-bit machines do * it from their respective probe() function. --- linux-4.14.0.orig/arch/powerpc/kernel/signal.c +++ linux-4.14.0/arch/powerpc/kernel/signal.c @@ -103,7 +103,7 @@ static void do_signal(struct task_struct *tsk) { sigset_t *oldset = sigmask_to_save(); - struct ksignal ksig; + struct ksignal ksig = { .sig = 0 }; int ret; int is32 = is_32bit_task(); --- linux-4.14.0.orig/arch/powerpc/kernel/traps.c +++ linux-4.14.0/arch/powerpc/kernel/traps.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -699,6 +700,187 @@ die("System Management Interrupt", regs, SIGABRT); } +#ifdef CONFIG_VSX +static void p9_hmi_special_emu(struct pt_regs *regs) +{ + unsigned int ra, rb, t, i, sel, instr, rc; + const void __user *addr; + u8 vbuf[16], *vdst; + unsigned long ea, msr, msr_mask; + bool swap; + + if (__get_user_inatomic(instr, (unsigned int __user *)regs->nip)) + return; + + /* + * lxvb16x opcode: 0x7c0006d8 + * lxvd2x opcode: 0x7c000698 + * lxvh8x opcode: 0x7c000658 + * lxvw4x opcode: 0x7c000618 + */ + if ((instr & 0xfc00073e) != 0x7c000618) { + pr_devel("HMI vec emu: not vector CI %i:%s[%d] nip=%016lx" + " instr=%08x\n", + smp_processor_id(), current->comm, current->pid, + regs->nip, instr); + return; + } + + /* Grab vector registers into the task struct */ + msr = regs->msr; /* Grab msr before we flush the bits */ + flush_vsx_to_thread(current); + enable_kernel_altivec(); + + /* + * Is userspace running with a different endian (this is rare but + * not impossible) + */ + swap = (msr & MSR_LE) != (MSR_KERNEL & MSR_LE); + + /* Decode the instruction */ + ra = (instr >> 16) & 0x1f; + rb = (instr >> 11) & 0x1f; + t = (instr >> 21) & 0x1f; + if (instr & 1) + vdst = (u8 *)¤t->thread.vr_state.vr[t]; + else + vdst = (u8 *)¤t->thread.fp_state.fpr[t][0]; + + /* Grab the vector address */ + ea = regs->gpr[rb] + (ra ? regs->gpr[ra] : 0); + if (is_32bit_task()) + ea &= 0xfffffffful; + addr = (__force const void __user *)ea; + + /* Check it */ + if (!access_ok(VERIFY_READ, addr, 16)) { + pr_devel("HMI vec emu: bad access %i:%s[%d] nip=%016lx" + " instr=%08x addr=%016lx\n", + smp_processor_id(), current->comm, current->pid, + regs->nip, instr, (unsigned long)addr); + return; + } + + /* Read the vector */ + rc = 0; + if ((unsigned long)addr & 0xfUL) + /* unaligned case */ + rc = __copy_from_user_inatomic(vbuf, addr, 16); + else + __get_user_atomic_128_aligned(vbuf, addr, rc); + if (rc) { + pr_devel("HMI vec emu: page fault %i:%s[%d] nip=%016lx" + " instr=%08x addr=%016lx\n", + smp_processor_id(), current->comm, current->pid, + regs->nip, instr, (unsigned long)addr); + return; + } + + pr_devel("HMI vec emu: emulated vector CI %i:%s[%d] nip=%016lx" + " instr=%08x addr=%016lx\n", + smp_processor_id(), current->comm, current->pid, regs->nip, + instr, (unsigned long) addr); + + /* Grab instruction "selector" */ + sel = (instr >> 6) & 3; + + /* + * Check to make sure the facility is actually enabled. This + * could happen if we get a false positive hit. + * + * lxvd2x/lxvw4x always check MSR VSX sel = 0,2 + * lxvh8x/lxvb16x check MSR VSX or VEC depending on VSR used sel = 1,3 + */ + msr_mask = MSR_VSX; + if ((sel & 1) && (instr & 1)) /* lxvh8x & lxvb16x + VSR >= 32 */ + msr_mask = MSR_VEC; + if (!(msr & msr_mask)) { + pr_devel("HMI vec emu: MSR fac clear %i:%s[%d] nip=%016lx" + " instr=%08x msr:%016lx\n", + smp_processor_id(), current->comm, current->pid, + regs->nip, instr, msr); + return; + } + + /* Do logging here before we modify sel based on endian */ + switch (sel) { + case 0: /* lxvw4x */ + PPC_WARN_EMULATED(lxvw4x, regs); + break; + case 1: /* lxvh8x */ + PPC_WARN_EMULATED(lxvh8x, regs); + break; + case 2: /* lxvd2x */ + PPC_WARN_EMULATED(lxvd2x, regs); + break; + case 3: /* lxvb16x */ + PPC_WARN_EMULATED(lxvb16x, regs); + break; + } + +#ifdef __LITTLE_ENDIAN__ + /* + * An LE kernel stores the vector in the task struct as an LE + * byte array (effectively swapping both the components and + * the content of the components). Those instructions expect + * the components to remain in ascending address order, so we + * swap them back. + * + * If we are running a BE user space, the expectation is that + * of a simple memcpy, so forcing the emulation to look like + * a lxvb16x should do the trick. + */ + if (swap) + sel = 3; + + switch (sel) { + case 0: /* lxvw4x */ + for (i = 0; i < 4; i++) + ((u32 *)vdst)[i] = ((u32 *)vbuf)[3-i]; + break; + case 1: /* lxvh8x */ + for (i = 0; i < 8; i++) + ((u16 *)vdst)[i] = ((u16 *)vbuf)[7-i]; + break; + case 2: /* lxvd2x */ + for (i = 0; i < 2; i++) + ((u64 *)vdst)[i] = ((u64 *)vbuf)[1-i]; + break; + case 3: /* lxvb16x */ + for (i = 0; i < 16; i++) + vdst[i] = vbuf[15-i]; + break; + } +#else /* __LITTLE_ENDIAN__ */ + /* On a big endian kernel, a BE userspace only needs a memcpy */ + if (!swap) + sel = 3; + + /* Otherwise, we need to swap the content of the components */ + switch (sel) { + case 0: /* lxvw4x */ + for (i = 0; i < 4; i++) + ((u32 *)vdst)[i] = cpu_to_le32(((u32 *)vbuf)[i]); + break; + case 1: /* lxvh8x */ + for (i = 0; i < 8; i++) + ((u16 *)vdst)[i] = cpu_to_le16(((u16 *)vbuf)[i]); + break; + case 2: /* lxvd2x */ + for (i = 0; i < 2; i++) + ((u64 *)vdst)[i] = cpu_to_le64(((u64 *)vbuf)[i]); + break; + case 3: /* lxvb16x */ + memcpy(vdst, vbuf, 16); + break; + } +#endif /* !__LITTLE_ENDIAN__ */ + + /* Go to next instruction */ + regs->nip += 4; +} +#endif /* CONFIG_VSX */ + void handle_hmi_exception(struct pt_regs *regs) { struct pt_regs *old_regs; @@ -706,6 +888,21 @@ old_regs = set_irq_regs(regs); irq_enter(); +#ifdef CONFIG_VSX + /* Real mode flagged P9 special emu is needed */ + if (local_paca->hmi_p9_special_emu) { + local_paca->hmi_p9_special_emu = 0; + + /* + * We don't want to take page faults while doing the + * emulation, we just replay the instruction if necessary. + */ + pagefault_disable(); + p9_hmi_special_emu(regs); + pagefault_enable(); + } +#endif /* CONFIG_VSX */ + if (ppc_md.handle_hmi_exception) ppc_md.handle_hmi_exception(regs); @@ -1924,6 +2121,10 @@ WARN_EMULATED_SETUP(mfdscr), WARN_EMULATED_SETUP(mtdscr), WARN_EMULATED_SETUP(lq_stq), + WARN_EMULATED_SETUP(lxvw4x), + WARN_EMULATED_SETUP(lxvh8x), + WARN_EMULATED_SETUP(lxvd2x), + WARN_EMULATED_SETUP(lxvb16x), #endif }; --- linux-4.14.0.orig/arch/powerpc/kernel/watchdog.c +++ linux-4.14.0/arch/powerpc/kernel/watchdog.c @@ -276,9 +276,12 @@ { unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000; int cpu = smp_processor_id(); + u64 tb = get_tb(); - if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks) - watchdog_timer_interrupt(cpu); + if (tb - per_cpu(wd_timer_tb, cpu) >= ticks) { + per_cpu(wd_timer_tb, cpu) = tb; + wd_smp_clear_cpu_pending(cpu, tb); + } } EXPORT_SYMBOL(arch_touch_nmi_watchdog); --- linux-4.14.0.orig/arch/powerpc/kvm/book3s_hv_builtin.c +++ linux-4.14.0/arch/powerpc/kvm/book3s_hv_builtin.c @@ -529,6 +529,8 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; if (xive_enabled()) { if (is_rm()) return xive_rm_h_xirr(vcpu); @@ -541,6 +543,8 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; vcpu->arch.gpr[5] = get_tb(); if (xive_enabled()) { if (is_rm()) @@ -554,6 +558,8 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; if (xive_enabled()) { if (is_rm()) return xive_rm_h_ipoll(vcpu, server); @@ -567,6 +573,8 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, unsigned long mfrr) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; if (xive_enabled()) { if (is_rm()) return xive_rm_h_ipi(vcpu, server, mfrr); @@ -579,6 +587,8 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; if (xive_enabled()) { if (is_rm()) return xive_rm_h_cppr(vcpu, cppr); @@ -591,6 +601,8 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) { + if (!kvmppc_xics_enabled(vcpu)) + return H_TOO_HARD; if (xive_enabled()) { if (is_rm()) return xive_rm_h_eoi(vcpu, xirr); --- linux-4.14.0.orig/arch/powerpc/kvm/book3s_xive.c +++ linux-4.14.0/arch/powerpc/kvm/book3s_xive.c @@ -725,7 +725,8 @@ /* Return the per-cpu state for state saving/migration */ return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT | - (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT; + (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT | + (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT; } int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) @@ -1558,7 +1559,7 @@ /* * Restore P and Q. If the interrupt was pending, we - * force both P and Q, which will trigger a resend. + * force Q and !P, which will trigger a resend. * * That means that a guest that had both an interrupt * pending (queued) and Q set will restore with only @@ -1566,7 +1567,7 @@ * is perfectly fine as coalescing interrupts that haven't * been presented yet is always allowed. */ - if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING) + if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING)) state->old_p = true; if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING) state->old_q = true; --- linux-4.14.0.orig/arch/powerpc/lib/code-patching.c +++ linux-4.14.0/arch/powerpc/lib/code-patching.c @@ -21,6 +21,7 @@ #include #include #include +#include static int __patch_instruction(unsigned int *addr, unsigned int instr) { @@ -146,11 +147,8 @@ * During early early boot patch_instruction is called * when text_poke_area is not ready, but we still need * to allow patching. We just do the plain old patching - * We use slab_is_available and per cpu read * via this_cpu_read - * of text_poke_area. Per-CPU areas might not be up early - * this can create problems with just using this_cpu_read() */ - if (!slab_is_available() || !this_cpu_read(text_poke_area)) + if (!this_cpu_read(*PTRRELOC(&text_poke_area))) return __patch_instruction(addr, instr); local_irq_save(flags); --- linux-4.14.0.orig/arch/powerpc/lib/sstep.c +++ linux-4.14.0/arch/powerpc/lib/sstep.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include --- linux-4.14.0.orig/arch/powerpc/mm/hash_native_64.c +++ linux-4.14.0/arch/powerpc/mm/hash_native_64.c @@ -47,7 +47,8 @@ DEFINE_RAW_SPINLOCK(native_tlbie_lock); -static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) +static inline unsigned long ___tlbie(unsigned long vpn, int psize, + int apsize, int ssize) { unsigned long va; unsigned int penc; @@ -100,7 +101,15 @@ : "memory"); break; } - trace_tlbie(0, 0, va, 0, 0, 0, 0); + return va; +} + +static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) +{ + unsigned long rb; + + rb = ___tlbie(vpn, psize, apsize, ssize); + trace_tlbie(0, 0, rb, 0, 0, 0, 0); } static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) @@ -652,7 +661,7 @@ if (hpte_v & HPTE_V_VALID) { hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn); hptep->v = 0; - __tlbie(vpn, psize, apsize, ssize); + ___tlbie(vpn, psize, apsize, ssize); } } --- linux-4.14.0.orig/arch/powerpc/mm/hugetlbpage-radix.c +++ linux-4.14.0/arch/powerpc/mm/hugetlbpage-radix.c @@ -49,17 +49,28 @@ struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + int fixed = (flags & MAP_FIXED); + unsigned long high_limit; struct vm_unmapped_area_info info; - if (unlikely(addr > mm->context.addr_limit && addr < TASK_SIZE)) - mm->context.addr_limit = TASK_SIZE; + high_limit = DEFAULT_MAP_WINDOW; + if (addr >= high_limit || (fixed && (addr + len > high_limit))) + high_limit = TASK_SIZE; if (len & ~huge_page_mask(h)) return -EINVAL; - if (len > mm->task_size) + if (len > high_limit) return -ENOMEM; + if (fixed) { + if (addr > high_limit - len) + return -ENOMEM; + } - if (flags & MAP_FIXED) { + if (unlikely(addr > mm->context.addr_limit && + mm->context.addr_limit != TASK_SIZE)) + mm->context.addr_limit = TASK_SIZE; + + if (fixed) { if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; @@ -68,7 +79,7 @@ if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (mm->task_size - len >= addr && + if (high_limit - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -79,12 +90,9 @@ info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; - info.high_limit = current->mm->mmap_base; + info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; - if (addr > DEFAULT_MAP_WINDOW) - info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW; - return vm_unmapped_area(&info); } --- linux-4.14.0.orig/arch/powerpc/mm/mmap.c +++ linux-4.14.0/arch/powerpc/mm/mmap.c @@ -106,22 +106,32 @@ { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; + int fixed = (flags & MAP_FIXED); + unsigned long high_limit; struct vm_unmapped_area_info info; + high_limit = DEFAULT_MAP_WINDOW; + if (addr >= high_limit || (fixed && (addr + len > high_limit))) + high_limit = TASK_SIZE; + + if (len > high_limit) + return -ENOMEM; + if (fixed) { + if (addr > high_limit - len) + return -ENOMEM; + } + if (unlikely(addr > mm->context.addr_limit && mm->context.addr_limit != TASK_SIZE)) mm->context.addr_limit = TASK_SIZE; - if (len > mm->task_size - mmap_min_addr) - return -ENOMEM; - - if (flags & MAP_FIXED) + if (fixed) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (mm->task_size - len >= addr && addr >= mmap_min_addr && + if (high_limit - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -129,13 +139,9 @@ info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; + info.high_limit = high_limit; info.align_mask = 0; - if (unlikely(addr > DEFAULT_MAP_WINDOW)) - info.high_limit = mm->context.addr_limit; - else - info.high_limit = DEFAULT_MAP_WINDOW; - return vm_unmapped_area(&info); } @@ -149,37 +155,42 @@ struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; + int fixed = (flags & MAP_FIXED); + unsigned long high_limit; struct vm_unmapped_area_info info; + high_limit = DEFAULT_MAP_WINDOW; + if (addr >= high_limit || (fixed && (addr + len > high_limit))) + high_limit = TASK_SIZE; + + if (len > high_limit) + return -ENOMEM; + if (fixed) { + if (addr > high_limit - len) + return -ENOMEM; + } + if (unlikely(addr > mm->context.addr_limit && mm->context.addr_limit != TASK_SIZE)) mm->context.addr_limit = TASK_SIZE; - /* requested length too big for entire address space */ - if (len > mm->task_size - mmap_min_addr) - return -ENOMEM; - - if (flags & MAP_FIXED) + if (fixed) return addr; - /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); - if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vm_start_gap(vma))) + if (high_limit - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = mm->mmap_base; + info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW); info.align_mask = 0; - if (addr > DEFAULT_MAP_WINDOW) - info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW; - addr = vm_unmapped_area(&info); if (!(addr & ~PAGE_MASK)) return addr; --- linux-4.14.0.orig/arch/powerpc/mm/mmu_context_book3s64.c +++ linux-4.14.0/arch/powerpc/mm/mmu_context_book3s64.c @@ -93,11 +93,11 @@ return index; /* - * We do switch_slb() early in fork, even before we setup the - * mm->context.addr_limit. Default to max task size so that we copy the - * default values to paca which will help us to handle slb miss early. + * In the case of exec, use the default limit, + * otherwise inherit it from the mm we are duplicating. */ - mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64; + if (!mm->context.addr_limit) + mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64; /* * The old code would re-promote on fork, we don't do that when using --- linux-4.14.0.orig/arch/powerpc/mm/pgtable-radix.c +++ linux-4.14.0/arch/powerpc/mm/pgtable-radix.c @@ -169,6 +169,16 @@ { unsigned long start, end; + /* + * mark_rodata_ro() will mark itself as !writable at some point. + * Due to DD1 workaround in radix__pte_update(), we'll end up with + * an invalid pte and the system will crash quite severly. + */ + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { + pr_warn("Warning: Unable to mark rodata read only on P9 DD1\n"); + return; + } + start = (unsigned long)_stext; end = (unsigned long)__init_begin; --- linux-4.14.0.orig/arch/powerpc/mm/slice.c +++ linux-4.14.0/arch/powerpc/mm/slice.c @@ -96,7 +96,7 @@ { struct vm_area_struct *vma; - if ((mm->task_size - len) < addr) + if ((mm->context.addr_limit - len) < addr) return 0; vma = find_vma(mm, addr); return (!vma || (addr + len) <= vm_start_gap(vma)); @@ -133,7 +133,7 @@ if (!slice_low_has_vma(mm, i)) ret->low_slices |= 1u << i; - if (mm->task_size <= SLICE_LOW_TOP) + if (mm->context.addr_limit <= SLICE_LOW_TOP) return; for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.addr_limit); i++) @@ -412,25 +412,31 @@ struct slice_mask compat_mask; int fixed = (flags & MAP_FIXED); int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); + unsigned long page_size = 1UL << pshift; struct mm_struct *mm = current->mm; unsigned long newaddr; unsigned long high_limit; - /* - * Check if we need to expland slice area. - */ - if (unlikely(addr > mm->context.addr_limit && - mm->context.addr_limit != TASK_SIZE)) { - mm->context.addr_limit = TASK_SIZE; + high_limit = DEFAULT_MAP_WINDOW; + if (addr >= high_limit || (fixed && (addr + len > high_limit))) + high_limit = TASK_SIZE; + + if (len > high_limit) + return -ENOMEM; + if (len & (page_size - 1)) + return -EINVAL; + if (fixed) { + if (addr & (page_size - 1)) + return -EINVAL; + if (addr > high_limit - len) + return -ENOMEM; + } + + if (high_limit > mm->context.addr_limit) { + mm->context.addr_limit = high_limit; on_each_cpu(slice_flush_segments, mm, 1); } - /* - * This mmap request can allocate upt to 512TB - */ - if (addr > DEFAULT_MAP_WINDOW) - high_limit = mm->context.addr_limit; - else - high_limit = DEFAULT_MAP_WINDOW; + /* * init different masks */ @@ -446,27 +452,19 @@ /* Sanity checks */ BUG_ON(mm->task_size == 0); + BUG_ON(mm->context.addr_limit == 0); VM_BUG_ON(radix_enabled()); slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize); slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n", addr, len, flags, topdown); - if (len > mm->task_size) - return -ENOMEM; - if (len & ((1ul << pshift) - 1)) - return -EINVAL; - if (fixed && (addr & ((1ul << pshift) - 1))) - return -EINVAL; - if (fixed && addr > (mm->task_size - len)) - return -ENOMEM; - /* If hint, make sure it matches our alignment restrictions */ if (!fixed && addr) { - addr = _ALIGN_UP(addr, 1ul << pshift); + addr = _ALIGN_UP(addr, page_size); slice_dbg(" aligned addr=%lx\n", addr); /* Ignore hint if it's too large or overlaps a VMA */ - if (addr > mm->task_size - len || + if (addr > high_limit - len || !slice_area_is_free(mm, addr, len)) addr = 0; } --- linux-4.14.0.orig/arch/powerpc/net/bpf_jit_comp64.c +++ linux-4.14.0/arch/powerpc/net/bpf_jit_comp64.c @@ -762,7 +762,8 @@ func = (u8 *) __bpf_call_base + imm; /* Save skb pointer if we need to re-cache skb data */ - if (bpf_helper_changes_pkt_data(func)) + if ((ctx->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data(func)) PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_func_call(image, ctx, (u64)func); @@ -771,7 +772,8 @@ PPC_MR(b2p[BPF_REG_0], 3); /* refresh skb cache */ - if (bpf_helper_changes_pkt_data(func)) { + if ((ctx->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data(func)) { /* reload skb pointer to r3 */ PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_skb_loads(image, ctx); --- linux-4.14.0.orig/arch/powerpc/perf/core-book3s.c +++ linux-4.14.0/arch/powerpc/perf/core-book3s.c @@ -410,8 +410,12 @@ int ret; __u64 target; - if (is_kernel_addr(addr)) - return branch_target((unsigned int *)addr); + if (is_kernel_addr(addr)) { + if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + return 0; + + return branch_target(&instr); + } /* Userspace: need copy instruction here then translate it */ pagefault_disable(); --- linux-4.14.0.orig/arch/powerpc/perf/hv-24x7.c +++ linux-4.14.0/arch/powerpc/perf/hv-24x7.c @@ -540,7 +540,7 @@ { if (s1 < s2) return 1; - if (s2 > s1) + if (s1 > s2) return -1; return memcmp(d1, d2, s1); --- linux-4.14.0.orig/arch/powerpc/perf/imc-pmu.c +++ linux-4.14.0/arch/powerpc/perf/imc-pmu.c @@ -467,7 +467,7 @@ * Nest HW counter memory resides in a per-chip reserve-memory (HOMER). * Get the base memory addresss for this cpu. */ - chip_id = topology_physical_package_id(event->cpu); + chip_id = cpu_to_chip_id(event->cpu); pcni = pmu->mem_info; do { if (pcni->id == chip_id) { @@ -524,19 +524,19 @@ */ static int core_imc_mem_init(int cpu, int size) { - int phys_id, rc = 0, core_id = (cpu / threads_per_core); + int nid, rc = 0, core_id = (cpu / threads_per_core); struct imc_mem_info *mem_info; /* * alloc_pages_node() will allocate memory for core in the * local node only. */ - phys_id = topology_physical_package_id(cpu); + nid = cpu_to_node(cpu); mem_info = &core_imc_pmu->mem_info[core_id]; mem_info->id = core_id; /* We need only vbase for core counters */ - mem_info->vbase = page_address(alloc_pages_node(phys_id, + mem_info->vbase = page_address(alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | __GFP_NOWARN, get_order(size))); if (!mem_info->vbase) @@ -797,14 +797,14 @@ static int thread_imc_mem_alloc(int cpu_id, int size) { u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id); - int phys_id = topology_physical_package_id(cpu_id); + int nid = cpu_to_node(cpu_id); if (!local_mem) { /* * This case could happen only once at start, since we dont * free the memory in cpu offline path. */ - local_mem = page_address(alloc_pages_node(phys_id, + local_mem = page_address(alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | __GFP_NOWARN, get_order(size))); if (!local_mem) --- linux-4.14.0.orig/arch/powerpc/platforms/powernv/opal-async.c +++ linux-4.14.0/arch/powerpc/platforms/powernv/opal-async.c @@ -39,18 +39,18 @@ int token; spin_lock_irqsave(&opal_async_comp_lock, flags); - token = find_first_bit(opal_async_complete_map, opal_max_async_tokens); + token = find_first_zero_bit(opal_async_token_map, opal_max_async_tokens); if (token >= opal_max_async_tokens) { token = -EBUSY; goto out; } - if (__test_and_set_bit(token, opal_async_token_map)) { + if (!__test_and_clear_bit(token, opal_async_complete_map)) { token = -EBUSY; goto out; } - __clear_bit(token, opal_async_complete_map); + __set_bit(token, opal_async_token_map); out: spin_unlock_irqrestore(&opal_async_comp_lock, flags); --- linux-4.14.0.orig/arch/powerpc/platforms/powernv/opal-imc.c +++ linux-4.14.0/arch/powerpc/platforms/powernv/opal-imc.c @@ -191,8 +191,10 @@ break; } - if (!imc_pmu_create(imc_dev, pmu_count, domain)) - pmu_count++; + if (!imc_pmu_create(imc_dev, pmu_count, domain)) { + if (domain == IMC_DOMAIN_NEST) + pmu_count++; + } } return 0; --- linux-4.14.0.orig/arch/powerpc/platforms/powernv/setup.c +++ linux-4.14.0/arch/powerpc/platforms/powernv/setup.c @@ -319,7 +319,7 @@ { unsigned long ret_freq; - ret_freq = cpufreq_quick_get(cpu) * 1000ul; + ret_freq = cpufreq_get(cpu) * 1000ul; /* * If the backend cpufreq driver does not exist, --- linux-4.14.0.orig/arch/powerpc/platforms/powernv/smp.c +++ linux-4.14.0/arch/powerpc/platforms/powernv/smp.c @@ -49,6 +49,13 @@ static void pnv_smp_setup_cpu(int cpu) { + /* + * P9 workaround for CI vector load (see traps.c), + * enable the corresponding HMI interrupt + */ + if (pvr_version_is(PVR_POWER9)) + mtspr(SPRN_HMEER, mfspr(SPRN_HMEER) | PPC_BIT(17)); + if (xive_enabled()) xive_smp_setup_cpu(); else if (cpu != boot_cpuid) --- linux-4.14.0.orig/arch/powerpc/platforms/ps3/setup.c +++ linux-4.14.0/arch/powerpc/platforms/ps3/setup.c @@ -104,6 +104,20 @@ ps3_sys_manager_halt(); /* never returns */ } +static void ps3_panic(char *str) +{ + DBG("%s:%d %s\n", __func__, __LINE__, str); + + smp_send_stop(); + printk("\n"); + printk(" System does not reboot automatically.\n"); + printk(" Please press POWER button.\n"); + printk("\n"); + + while(1) + lv1_pause(1); +} + #if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \ defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE) static void __init prealloc(struct ps3_prealloc *p) @@ -255,6 +269,7 @@ .probe = ps3_probe, .setup_arch = ps3_setup_arch, .init_IRQ = ps3_init_IRQ, + .panic = ps3_panic, .get_boot_time = ps3_get_boot_time, .set_dabr = ps3_set_dabr, .calibrate_decr = ps3_calibrate_decr, --- linux-4.14.0.orig/arch/powerpc/platforms/pseries/setup.c +++ linux-4.14.0/arch/powerpc/platforms/pseries/setup.c @@ -726,6 +726,7 @@ .pcibios_fixup = pSeries_final_fixup, .restart = rtas_restart, .halt = rtas_halt, + .panic = rtas_os_term, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, --- linux-4.14.0.orig/arch/powerpc/platforms/pseries/vio.c +++ linux-4.14.0/arch/powerpc/platforms/pseries/vio.c @@ -1592,6 +1592,8 @@ void vio_unregister_device(struct vio_dev *viodev) { device_unregister(&viodev->dev); + if (viodev->family == VDEVICE) + irq_dispose_mapping(viodev->irq); } EXPORT_SYMBOL(vio_unregister_device); --- linux-4.14.0.orig/arch/powerpc/sysdev/ipic.c +++ linux-4.14.0/arch/powerpc/sysdev/ipic.c @@ -846,12 +846,12 @@ u32 ipic_get_mcp_status(void) { - return ipic_read(primary_ipic->regs, IPIC_SERMR); + return ipic_read(primary_ipic->regs, IPIC_SERSR); } void ipic_clear_mcp_status(u32 mask) { - ipic_write(primary_ipic->regs, IPIC_SERMR, mask); + ipic_write(primary_ipic->regs, IPIC_SERSR, mask); } /* Return an interrupt vector or 0 if no interrupt is pending. */ --- linux-4.14.0.orig/arch/powerpc/xmon/xmon.c +++ linux-4.14.0/arch/powerpc/xmon/xmon.c @@ -530,14 +530,19 @@ waiting: secondary = 1; + spin_begin(); while (secondary && !xmon_gate) { if (in_xmon == 0) { - if (fromipi) + if (fromipi) { + spin_end(); goto leave; + } secondary = test_and_set_bit(0, &in_xmon); } - barrier(); + spin_cpu_relax(); + touch_nmi_watchdog(); } + spin_end(); if (!secondary && !xmon_gate) { /* we are the first cpu to come in */ @@ -568,21 +573,25 @@ mb(); xmon_gate = 1; barrier(); + touch_nmi_watchdog(); } cmdloop: while (in_xmon) { if (secondary) { + spin_begin(); if (cpu == xmon_owner) { if (!test_and_set_bit(0, &xmon_taken)) { secondary = 0; + spin_end(); continue; } /* missed it */ while (cpu == xmon_owner) - barrier(); + spin_cpu_relax(); } - barrier(); + spin_cpu_relax(); + touch_nmi_watchdog(); } else { cmd = cmds(regs); if (cmd != 0) { @@ -2475,6 +2484,11 @@ unsigned long num; int c; + if (!xive_enabled()) { + printf("Xive disabled on this system\n"); + return; + } + c = inchar(); if (c == 'a') { dump_all_xives(); --- linux-4.14.0.orig/arch/s390/Kconfig +++ linux-4.14.0/arch/s390/Kconfig @@ -944,3 +944,11 @@ need this. endmenu + +config KMSG_IDS + def_bool y + prompt "Kernel message numbers" + help + Select this option if you want to include a message number to the + prefix for kernel messages issued by the s390 architecture and + driver code. See "Documentation/s390/kmsg.txt" for more details. --- linux-4.14.0.orig/arch/s390/include/asm/compat.h +++ linux-4.14.0/arch/s390/include/asm/compat.h @@ -263,7 +263,6 @@ #define si_overrun _sifields._timer._overrun #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL /* * A pointer passed in from user mode. This should not --- linux-4.14.0.orig/arch/s390/include/asm/elf.h +++ linux-4.14.0/arch/s390/include/asm/elf.h @@ -194,13 +194,14 @@ #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE PAGE_SIZE -/* - * This is the base location for PIE (ET_DYN with INTERP) loads. On - * 64-bit, this is raised to 4GB to leave the entire 32-bit address - * space open for things that want to use the area for 32-bit pointers. - */ -#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \ - 0x100000000UL) +/* This is the location that an ET_DYN program is loaded if exec'ed. Typical + use of this is to invoke "./ld.so someprog" to test out a new version of + the loader. We need to make sure that it is out of the way of the program + that it will "exec", and that there is sufficient room for the brk. 64-bit + tasks are aligned to 4GB. */ +#define ELF_ET_DYN_BASE (is_compat_task() ? \ + (STACK_TOP / 3 * 2) : \ + (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. */ --- linux-4.14.0.orig/arch/s390/include/asm/pci_insn.h +++ linux-4.14.0/arch/s390/include/asm/pci_insn.h @@ -82,6 +82,6 @@ int zpci_load(u64 *data, u64 req, u64 offset); int zpci_store(u64 data, u64 req, u64 offset); int zpci_store_block(const u64 *data, u64 req, u64 offset); -void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc); +int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc); #endif --- linux-4.14.0.orig/arch/s390/include/asm/runtime_instr.h +++ linux-4.14.0/arch/s390/include/asm/runtime_instr.h @@ -86,6 +86,8 @@ load_runtime_instr_cb(&runtime_instr_empty_cb); } -void exit_thread_runtime_instr(void); +struct task_struct; + +void runtime_instr_release(struct task_struct *tsk); #endif /* _RUNTIME_INSTR_H */ --- linux-4.14.0.orig/arch/s390/include/asm/switch_to.h +++ linux-4.14.0/arch/s390/include/asm/switch_to.h @@ -30,21 +30,20 @@ asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs)); } -#define switch_to(prev,next,last) do { \ - if (prev->mm) { \ - save_fpu_regs(); \ - save_access_regs(&prev->thread.acrs[0]); \ - save_ri_cb(prev->thread.ri_cb); \ - save_gs_cb(prev->thread.gs_cb); \ - } \ - if (next->mm) { \ - update_cr_regs(next); \ - set_cpu_flag(CIF_FPU); \ - restore_access_regs(&next->thread.acrs[0]); \ - restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ - restore_gs_cb(next->thread.gs_cb); \ - } \ - prev = __switch_to(prev,next); \ +#define switch_to(prev, next, last) do { \ + /* save_fpu_regs() sets the CIF_FPU flag, which enforces \ + * a restore of the floating point / vector registers as \ + * soon as the next task returns to user space \ + */ \ + save_fpu_regs(); \ + save_access_regs(&prev->thread.acrs[0]); \ + save_ri_cb(prev->thread.ri_cb); \ + save_gs_cb(prev->thread.gs_cb); \ + update_cr_regs(next); \ + restore_access_regs(&next->thread.acrs[0]); \ + restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ + restore_gs_cb(next->thread.gs_cb); \ + prev = __switch_to(prev, next); \ } while (0) #endif /* __ASM_SWITCH_TO_H */ --- linux-4.14.0.orig/arch/s390/include/asm/topology.h +++ linux-4.14.0/arch/s390/include/asm/topology.h @@ -65,11 +65,8 @@ #ifdef CONFIG_NUMA -#define cpu_to_node cpu_to_node -static inline int cpu_to_node(int cpu) -{ - return cpu_topology[cpu].node_id; -} +extern int __cpu_to_node(int cpu); +#define cpu_to_node __cpu_to_node /* Returns a pointer to the cpumask of CPUs on node 'node'. */ #define cpumask_of_node cpumask_of_node --- linux-4.14.0.orig/arch/s390/kernel/Makefile +++ linux-4.14.0/arch/s390/kernel/Makefile @@ -84,3 +84,6 @@ # vdso obj-y += vdso64/ obj-$(CONFIG_COMPAT) += vdso32/ + +# kernel message catalog +obj-$(CONFIG_KMSG_IDS) += kmsg.o --- linux-4.14.0.orig/arch/s390/kernel/compat_linux.c +++ linux-4.14.0/arch/s390/kernel/compat_linux.c @@ -263,6 +263,7 @@ return retval; } + groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); --- linux-4.14.0.orig/arch/s390/kernel/dis.c +++ linux-4.14.0/arch/s390/kernel/dis.c @@ -1548,6 +1548,7 @@ { "vfsq", 0xce, INSTR_VRR_VV000MM }, { "vfs", 0xe2, INSTR_VRR_VVV00MM }, { "vftci", 0x4a, INSTR_VRI_VVIMM }, + { "", 0, INSTR_INVALID } }; static struct s390_insn opcode_eb[] = { @@ -1953,7 +1954,7 @@ { char *mode = user_mode(regs) ? "User" : "Krnl"; unsigned char code[64]; - char buffer[64], *ptr; + char buffer[128], *ptr; mm_segment_t old_fs; unsigned long addr; int start, end, opsize, hops, i; @@ -2016,7 +2017,7 @@ start += opsize; pr_cont("%s", buffer); ptr = buffer; - ptr += sprintf(ptr, "\n "); + ptr += sprintf(ptr, "\n\t "); hops++; } pr_cont("\n"); --- linux-4.14.0.orig/arch/s390/kernel/early.c +++ linux-4.14.0/arch/s390/kernel/early.c @@ -375,8 +375,10 @@ S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; if (test_facility(40)) S390_lowcore.machine_flags |= MACHINE_FLAG_LPP; - if (test_facility(50) && test_facility(73)) + if (test_facility(50) && test_facility(73)) { S390_lowcore.machine_flags |= MACHINE_FLAG_TE; + __ctl_set_bit(0, 55); + } if (test_facility(51)) S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC; if (test_facility(129)) { --- linux-4.14.0.orig/arch/s390/kernel/guarded_storage.c +++ linux-4.14.0/arch/s390/kernel/guarded_storage.c @@ -14,9 +14,11 @@ void exit_thread_gs(void) { + preempt_disable(); kfree(current->thread.gs_cb); kfree(current->thread.gs_bc_cb); current->thread.gs_cb = current->thread.gs_bc_cb = NULL; + preempt_enable(); } static int gs_enable(void) --- linux-4.14.0.orig/arch/s390/kernel/kmsg.c +++ linux-4.14.0/arch/s390/kernel/kmsg.c @@ -0,0 +1,114 @@ +/* + * Message printing with message catalog prefixes. + * + * Copyright IBM Corp. 2012 + */ + +#include +#include +#include +#include +#include + +static inline u32 __printk_jhash(const void *key, u32 length) +{ + u32 a, b, c, len; + const u8 *k; + u8 zk[12]; + + a = b = 0x9e3779b9; + c = 0; + for (len = length + 12, k = key; len >= 12; len -= 12, k += 12) { + if (len >= 24) { + a += k[0] | k[1] << 8 | k[2] << 16 | k[3] << 24; + b += k[4] | k[5] << 8 | k[6] << 16 | k[7] << 24; + c += k[8] | k[9] << 8 | k[10] << 16 | k[11] << 24; + } else { + memset(zk, 0, 12); + memcpy(zk, k, len - 12); + a += zk[0] | zk[1] << 8 | zk[2] << 16 | zk[3] << 24; + b += zk[4] | zk[5] << 8 | zk[6] << 16 | zk[7] << 24; + c += (u32) zk[8] << 8; + c += (u32) zk[9] << 16; + c += (u32) zk[10] << 24; + c += length; + } + a -= b + c; a ^= (c>>13); + b -= a + c; b ^= (a<<8); + c -= a + b; c ^= (b>>13); + a -= b + c; a ^= (c>>12); + b -= a + c; b ^= (a<<16); + c -= a + b; c ^= (b>>5); + a -= b + c; a ^= (c>>3); + b -= a + c; b ^= (a<<10); + c -= a + b; c ^= (b>>15); + } + return c; +} + +/** + * __jhash_string - calculate the six digit jhash of a string + * @str: string to calculate the jhash + */ +unsigned long long __jhash_string(const char *str) +{ + return __printk_jhash(str, strlen(str)) & 0xffffff; +} +EXPORT_SYMBOL(__jhash_string); + +static int __dev_printk_hash(const char *level, const struct device *dev, + struct va_format *vaf) +{ + if (!dev) + return printk("%s(NULL device *): %pV", level, vaf); + + return printk("%s%s.%06x: %pV", level, dev_driver_string(dev), + __printk_jhash(vaf->fmt, strlen(vaf->fmt)) & 0xffffff, + vaf); +} + +int dev_printk_hash(const char *level, const struct device *dev, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + r = __dev_printk_hash(level, dev, &vaf); + va_end(args); + + return r; +} +EXPORT_SYMBOL(dev_printk_hash); + +#define define_dev_printk_hash_level(func, kern_level) \ +int func(const struct device *dev, const char *fmt, ...) \ +{ \ + struct va_format vaf; \ + va_list args; \ + int r; \ + \ + va_start(args, fmt); \ + \ + vaf.fmt = fmt; \ + vaf.va = &args; \ + \ + r = __dev_printk_hash(kern_level, dev, &vaf); \ + va_end(args); \ + \ + return r; \ +} \ +EXPORT_SYMBOL(func); + +define_dev_printk_hash_level(dev_emerg_hash, KERN_EMERG); +define_dev_printk_hash_level(dev_alert_hash, KERN_ALERT); +define_dev_printk_hash_level(dev_crit_hash, KERN_CRIT); +define_dev_printk_hash_level(dev_err_hash, KERN_ERR); +define_dev_printk_hash_level(dev_warn_hash, KERN_WARNING); +define_dev_printk_hash_level(dev_notice_hash, KERN_NOTICE); +define_dev_printk_hash_level(_dev_info_hash, KERN_INFO); --- linux-4.14.0.orig/arch/s390/kernel/machine_kexec.c +++ linux-4.14.0/arch/s390/kernel/machine_kexec.c @@ -269,6 +269,7 @@ s390_reset_system(); data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); + __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ /* Call the moving routine */ (*data_mover)(&image->head, image->start); --- linux-4.14.0.orig/arch/s390/kernel/process.c +++ linux-4.14.0/arch/s390/kernel/process.c @@ -49,10 +49,8 @@ */ void exit_thread(struct task_struct *tsk) { - if (tsk == current) { - exit_thread_runtime_instr(); + if (tsk == current) exit_thread_gs(); - } } void flush_thread(void) @@ -65,6 +63,7 @@ void arch_release_task_struct(struct task_struct *tsk) { + runtime_instr_release(tsk); } int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) @@ -100,6 +99,7 @@ memset(&p->thread.per_user, 0, sizeof(p->thread.per_user)); memset(&p->thread.per_event, 0, sizeof(p->thread.per_event)); clear_tsk_thread_flag(p, TIF_SINGLE_STEP); + p->thread.per_flags = 0; /* Initialize per thread user and system timer values */ p->thread.user_timer = 0; p->thread.guest_timer = 0; --- linux-4.14.0.orig/arch/s390/kernel/ptrace.c +++ linux-4.14.0/arch/s390/kernel/ptrace.c @@ -1172,26 +1172,37 @@ unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct gs_cb *data = target->thread.gs_cb; + struct gs_cb gs_cb = { }, *data = NULL; int rc; if (!MACHINE_HAS_GS) return -ENODEV; - if (!data) { + if (!target->thread.gs_cb) { data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->gsd = 25; - target->thread.gs_cb = data; - if (target == current) - __ctl_set_bit(2, 4); - } else if (target == current) { - save_gs_cb(data); } + if (!target->thread.gs_cb) + gs_cb.gsd = 25; + else if (target == current) + save_gs_cb(&gs_cb); + else + gs_cb = *target->thread.gs_cb; rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - data, 0, sizeof(struct gs_cb)); - if (target == current) - restore_gs_cb(data); + &gs_cb, 0, sizeof(gs_cb)); + if (rc) { + kfree(data); + return -EFAULT; + } + preempt_disable(); + if (!target->thread.gs_cb) + target->thread.gs_cb = data; + *target->thread.gs_cb = gs_cb; + if (target == current) { + __ctl_set_bit(2, 4); + restore_gs_cb(target->thread.gs_cb); + } + preempt_enable(); return rc; } --- linux-4.14.0.orig/arch/s390/kernel/relocate_kernel.S +++ linux-4.14.0/arch/s390/kernel/relocate_kernel.S @@ -29,7 +29,6 @@ ENTRY(relocate_kernel) basr %r13,0 # base address .base: - stnsm sys_msk-.base(%r13),0xfb # disable DAT stctg %c0,%c15,ctlregs-.base(%r13) stmg %r0,%r15,gprregs-.base(%r13) lghi %r0,3 @@ -103,8 +102,6 @@ .align 8 load_psw: .long 0x00080000,0x80000000 - sys_msk: - .quad 0 ctlregs: .rept 16 .quad 0 --- linux-4.14.0.orig/arch/s390/kernel/runtime_instr.c +++ linux-4.14.0/arch/s390/kernel/runtime_instr.c @@ -21,11 +21,24 @@ /* empty control block to disable RI by loading it */ struct runtime_instr_cb runtime_instr_empty_cb; +void runtime_instr_release(struct task_struct *tsk) +{ + kfree(tsk->thread.ri_cb); +} + static void disable_runtime_instr(void) { - struct pt_regs *regs = task_pt_regs(current); + struct task_struct *task = current; + struct pt_regs *regs; + if (!task->thread.ri_cb) + return; + regs = task_pt_regs(task); + preempt_disable(); load_runtime_instr_cb(&runtime_instr_empty_cb); + kfree(task->thread.ri_cb); + task->thread.ri_cb = NULL; + preempt_enable(); /* * Make sure the RI bit is deleted from the PSW. If the user did not @@ -46,17 +59,6 @@ cb->valid = 1; } -void exit_thread_runtime_instr(void) -{ - struct task_struct *task = current; - - if (!task->thread.ri_cb) - return; - disable_runtime_instr(); - kfree(task->thread.ri_cb); - task->thread.ri_cb = NULL; -} - SYSCALL_DEFINE1(s390_runtime_instr, int, command) { struct runtime_instr_cb *cb; @@ -65,9 +67,7 @@ return -EOPNOTSUPP; if (command == S390_RUNTIME_INSTR_STOP) { - preempt_disable(); - exit_thread_runtime_instr(); - preempt_enable(); + disable_runtime_instr(); return 0; } --- linux-4.14.0.orig/arch/s390/kernel/syscalls.S +++ linux-4.14.0/arch/s390/kernel/syscalls.S @@ -370,10 +370,10 @@ SYSCALL(sys_sendmmsg,compat_sys_sendmmsg) SYSCALL(sys_socket,sys_socket) SYSCALL(sys_socketpair,compat_sys_socketpair) /* 360 */ -SYSCALL(sys_bind,sys_bind) -SYSCALL(sys_connect,sys_connect) +SYSCALL(sys_bind,compat_sys_bind) +SYSCALL(sys_connect,compat_sys_connect) SYSCALL(sys_listen,sys_listen) -SYSCALL(sys_accept4,sys_accept4) +SYSCALL(sys_accept4,compat_sys_accept4) SYSCALL(sys_getsockopt,compat_sys_getsockopt) /* 365 */ SYSCALL(sys_setsockopt,compat_sys_setsockopt) SYSCALL(sys_getsockname,compat_sys_getsockname) --- linux-4.14.0.orig/arch/s390/kernel/topology.c +++ linux-4.14.0/arch/s390/kernel/topology.c @@ -64,6 +64,13 @@ cpumask_t cpus_with_topology; +int __cpu_to_node(int cpu) +{ + return cpu_topology[cpu].node_id; +} + +EXPORT_SYMBOL(__cpu_to_node); + static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) { cpumask_t mask; --- linux-4.14.0.orig/arch/s390/kvm/priv.c +++ linux-4.14.0/arch/s390/kvm/priv.c @@ -235,8 +235,6 @@ VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return -EAGAIN; } - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); return 0; } @@ -247,6 +245,9 @@ int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; @@ -276,6 +277,9 @@ int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; @@ -311,6 +315,9 @@ int reg1, reg2; int rc; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + rc = try_handle_skey(vcpu); if (rc) return rc != -EAGAIN ? rc : 0; --- linux-4.14.0.orig/arch/s390/mm/pgalloc.c +++ linux-4.14.0/arch/s390/mm/pgalloc.c @@ -85,8 +85,6 @@ /* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */ VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE); - if (end >= TASK_SIZE_MAX) - return -ENOMEM; rc = 0; notify = 0; while (mm->context.asce_limit < end) { --- linux-4.14.0.orig/arch/s390/net/bpf_jit_comp.c +++ linux-4.14.0/arch/s390/net/bpf_jit_comp.c @@ -55,8 +55,7 @@ #define SEEN_LITERAL 8 /* code uses literals */ #define SEEN_FUNC 16 /* calls C functions */ #define SEEN_TAIL_CALL 32 /* code uses tail calls */ -#define SEEN_SKB_CHANGE 64 /* code changes skb data */ -#define SEEN_REG_AX 128 /* code uses constant blinding */ +#define SEEN_REG_AX 64 /* code uses constant blinding */ #define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB) /* @@ -448,12 +447,12 @@ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, 152); } - if (jit->seen & SEEN_SKB) + if (jit->seen & SEEN_SKB) { emit_load_skb_data_hlen(jit); - if (jit->seen & SEEN_SKB_CHANGE) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); + } } /* @@ -983,8 +982,8 @@ EMIT2(0x0d00, REG_14, REG_W1); /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); - if (bpf_helper_changes_pkt_data((void *)func)) { - jit->seen |= SEEN_SKB_CHANGE; + if ((jit->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data((void *)func)) { /* lg %b1,ST_OFF_SKBP(%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); --- linux-4.14.0.orig/arch/s390/pci/pci.c +++ linux-4.14.0/arch/s390/pci/pci.c @@ -368,7 +368,8 @@ /* End of second scan with interrupts on. */ break; /* First scan complete, reenable interrupts. */ - zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC)) + break; si = 0; continue; } @@ -956,7 +957,7 @@ if (!s390_pci_probe) return 0; - if (!test_facility(69) || !test_facility(71) || !test_facility(72)) + if (!test_facility(69) || !test_facility(71)) return 0; rc = zpci_debug_init(); --- linux-4.14.0.orig/arch/s390/pci/pci_insn.c +++ linux-4.14.0/arch/s390/pci/pci_insn.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -91,11 +92,14 @@ } /* Set Interruption Controls */ -void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc) +int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc) { + if (!test_facility(72)) + return -EIO; asm volatile ( " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" : : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused)); + return 0; } /* PCI Load */ --- linux-4.14.0.orig/arch/sparc/include/asm/cmpxchg_32.h +++ linux-4.14.0/arch/sparc/include/asm/cmpxchg_32.h @@ -63,6 +63,9 @@ (unsigned long)_n_, sizeof(*(ptr))); \ }) +u64 __cmpxchg_u64(u64 *ptr, u64 old, u64 new); +#define cmpxchg64(ptr, old, new) __cmpxchg_u64(ptr, old, new) + #include /* --- linux-4.14.0.orig/arch/sparc/include/asm/compat.h +++ linux-4.14.0/arch/sparc/include/asm/compat.h @@ -209,7 +209,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL /* * A pointer passed in from user mode. This should not --- linux-4.14.0.orig/arch/sparc/include/asm/mmu_context_64.h +++ linux-4.14.0/arch/sparc/include/asm/mmu_context_64.h @@ -8,9 +8,11 @@ #include #include +#include #include #include +#include static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { --- linux-4.14.0.orig/arch/sparc/include/asm/ptrace.h +++ linux-4.14.0/arch/sparc/include/asm/ptrace.h @@ -7,6 +7,7 @@ #if defined(__sparc__) && defined(__arch64__) #ifndef __ASSEMBLY__ +#include #include #include --- linux-4.14.0.orig/arch/sparc/include/asm/tsb.h +++ linux-4.14.0/arch/sparc/include/asm/tsb.h @@ -217,7 +217,7 @@ sllx REG2, 32, REG2; \ andcc REG1, REG2, %g0; \ be,pt %xcc, 700f; \ - sethi %hi(0x1ffc0000), REG2; \ + sethi %hi(0xffe00000), REG2; \ sllx REG2, 1, REG2; \ brgez,pn REG1, FAIL_LABEL; \ andn REG1, REG2, REG1; \ --- linux-4.14.0.orig/arch/sparc/lib/atomic32.c +++ linux-4.14.0/arch/sparc/lib/atomic32.c @@ -173,6 +173,20 @@ } EXPORT_SYMBOL(__cmpxchg_u32); +u64 __cmpxchg_u64(u64 *ptr, u64 old, u64 new) +{ + unsigned long flags; + u64 prev; + + spin_lock_irqsave(ATOMIC_HASH(ptr), flags); + if ((prev = *ptr) == old) + *ptr = new; + spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags); + + return prev; +} +EXPORT_SYMBOL(__cmpxchg_u64); + unsigned long __xchg_u32(volatile u32 *ptr, u32 new) { unsigned long flags; --- linux-4.14.0.orig/arch/sparc/lib/hweight.S +++ linux-4.14.0/arch/sparc/lib/hweight.S @@ -44,8 +44,8 @@ .previous ENTRY(__arch_hweight64) - sethi %hi(__sw_hweight16), %g1 - jmpl %g1 + %lo(__sw_hweight16), %g0 + sethi %hi(__sw_hweight64), %g1 + jmpl %g1 + %lo(__sw_hweight64), %g0 nop ENDPROC(__arch_hweight64) EXPORT_SYMBOL(__arch_hweight64) --- linux-4.14.0.orig/arch/sparc/mm/init_64.c +++ linux-4.14.0/arch/sparc/mm/init_64.c @@ -2540,10 +2540,17 @@ { high_memory = __va(last_valid_pfn << PAGE_SHIFT); - register_page_bootmem_info(); free_all_bootmem(); /* + * Must be done after boot memory is put on freelist, because here we + * might set fields in deferred struct pages that have not yet been + * initialized, and free_all_bootmem() initializes all the reserved + * deferred pages for us. + */ + register_page_bootmem_info(); + + /* * Set up the zero page, mark it reserved, so that page count * is not manipulated when freeing the page from user ptes. */ --- linux-4.14.0.orig/arch/sparc/net/bpf_jit_comp_64.c +++ linux-4.14.0/arch/sparc/net/bpf_jit_comp_64.c @@ -1245,14 +1245,16 @@ u8 *func = ((u8 *)__bpf_call_base) + imm; ctx->saw_call = true; + if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) + emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx); emit_call((u32 *)func, ctx); emit_nop(ctx); emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); - if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind) - load_skb_regs(ctx, bpf2sparc[BPF_REG_6]); + if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) + load_skb_regs(ctx, L7); break; } --- linux-4.14.0.orig/arch/tile/include/asm/compat.h +++ linux-4.14.0/arch/tile/include/asm/compat.h @@ -173,7 +173,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL struct compat_ipc64_perm { compat_key_t key; --- linux-4.14.0.orig/arch/um/include/asm/Kbuild +++ linux-4.14.0/arch/um/include/asm/Kbuild @@ -1,4 +1,5 @@ generic-y += barrier.h +generic-y += bpf_perf_event.h generic-y += bug.h generic-y += clkdev.h generic-y += current.h --- linux-4.14.0.orig/arch/um/include/asm/mmu_context.h +++ linux-4.14.0/arch/um/include/asm/mmu_context.h @@ -15,9 +15,10 @@ /* * Needed since we do not use the asm-generic/mm_hooks.h: */ -static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { uml_setup_stubs(mm); + return 0; } extern void arch_exit_mmap(struct mm_struct *mm); static inline void arch_unmap(struct mm_struct *mm, --- linux-4.14.0.orig/arch/um/include/shared/init.h +++ linux-4.14.0/arch/um/include/shared/init.h @@ -41,7 +41,7 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -#include +#include /* These are for everybody (although not all archs will actually discard it in modules) */ --- linux-4.14.0.orig/arch/unicore32/include/asm/mmu_context.h +++ linux-4.14.0/arch/unicore32/include/asm/mmu_context.h @@ -81,9 +81,10 @@ } \ } while (0) -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) { + return 0; } static inline void arch_unmap(struct mm_struct *mm, --- linux-4.14.0.orig/arch/x86/Kconfig +++ linux-4.14.0/arch/x86/Kconfig @@ -56,7 +56,7 @@ select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 # Causing hangs/crashes, see the commit that added this change for details. - select ARCH_HAS_REFCOUNT if BROKEN + select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN @@ -108,7 +108,7 @@ select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KGDB select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_MMAP_RND_BITS if MMU @@ -171,7 +171,7 @@ select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK @@ -303,7 +303,6 @@ config KASAN_SHADOW_OFFSET hex depends on KASAN - default 0xdff8000000000000 if X86_5LEVEL default 0xdffffc0000000000 config HAVE_INTEL_TXT @@ -926,7 +925,8 @@ config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK + range 2 64 if SMP && X86_32 && X86_BIGSMP + range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 default "1" if !SMP default "8192" if MAXSMP @@ -1887,6 +1887,28 @@ If unsure, say N. +config EFI_SECURE_BOOT_LOCK_DOWN + def_bool n + depends on EFI + prompt "Lock down the kernel when UEFI Secure Boot is enabled" + ---help--- + UEFI Secure Boot provides a mechanism for ensuring that the firmware + will only load signed bootloaders and kernels. Certain use cases may + also require that all kernel modules also be signed and that + userspace is prevented from directly changing the running kernel + image. Say Y here to automatically lock down the kernel when a + system boots with UEFI Secure Boot enabled. + +config EFI_ALLOW_SECURE_BOOT_EXIT + def_bool n + depends on EFI_SECURE_BOOT_LOCK_DOWN && MAGIC_SYSRQ + select ALLOW_LOCKDOWN_LIFT + prompt "Allow secure boot mode to be exited with SysRq+x on a keyboard" + ---help--- + Allow secure boot mode to be exited and the kernel lockdown lifted by + typing SysRq+x on a keyboard attached to the system (not permitted + through procfs). + config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" @@ -2868,6 +2890,8 @@ source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "drivers/firmware/Kconfig" source "fs/Kconfig" --- linux-4.14.0.orig/arch/x86/Kconfig.debug +++ linux-4.14.0/arch/x86/Kconfig.debug @@ -359,28 +359,14 @@ choice prompt "Choose kernel unwinder" - default FRAME_POINTER_UNWINDER + default UNWINDER_ORC if X86_64 + default UNWINDER_FRAME_POINTER if X86_32 ---help--- This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc//stack, livepatch, lockdep, and more. -config FRAME_POINTER_UNWINDER - bool "Frame pointer unwinder" - select FRAME_POINTER - ---help--- - This option enables the frame pointer unwinder for unwinding kernel - stack traces. - - The unwinder itself is fast and it uses less RAM than the ORC - unwinder, but the kernel text size will grow by ~3% and the kernel's - overall performance will degrade by roughly 5-10%. - - This option is recommended if you want to use the livepatch - consistency model, as this is currently the only way to get a - reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). - -config ORC_UNWINDER +config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 select STACK_VALIDATION @@ -396,7 +382,22 @@ Enabling this option will increase the kernel's runtime memory usage by roughly 2-4MB, depending on your kernel config. -config GUESS_UNWINDER +config UNWINDER_FRAME_POINTER + bool "Frame pointer unwinder" + select FRAME_POINTER + ---help--- + This option enables the frame pointer unwinder for unwinding kernel + stack traces. + + The unwinder itself is fast and it uses less RAM than the ORC + unwinder, but the kernel text size will grow by ~3% and the kernel's + overall performance will degrade by roughly 5-10%. + + This option is recommended if you want to use the livepatch + consistency model, as this is currently the only way to get a + reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). + +config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT ---help--- @@ -411,7 +412,7 @@ endchoice config FRAME_POINTER - depends on !ORC_UNWINDER && !GUESS_UNWINDER + depends on !UNWINDER_ORC && !UNWINDER_GUESS bool endmenu --- linux-4.14.0.orig/arch/x86/boot/compressed/Makefile +++ linux-4.14.0/arch/x86/boot/compressed/Makefile @@ -78,6 +78,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o + vmlinux-objs-y += $(obj)/pgtable_64.o endif $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone --- linux-4.14.0.orig/arch/x86/boot/compressed/eboot.c +++ linux-4.14.0/arch/x86/boot/compressed/eboot.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "../string.h" #include "eboot.h" @@ -606,6 +607,31 @@ } } +#define MEMORY_ONLY_RESET_CONTROL_GUID \ + EFI_GUID (0xe20939be, 0x32d4, 0x41be, 0xa1, 0x50, 0x89, 0x7f, 0x85, 0xd4, 0x98, 0x29) + +static void enable_reset_attack_mitigation(void) +{ + static const efi_guid_t var_guid = MEMORY_ONLY_RESET_CONTROL_GUID; + static const efi_char16_t MemoryOverwriteRequestControl_name[] = { + 'M', 'e', 'm', 'o', 'r', 'y', + 'O', 'v', 'e', 'r', 'w', 'r', 'i', 't', 'e', + 'R', 'e', 'q', 'u', 'e', 's', 't', + 'C', 'o', 'n', 't', 'r', 'o', 'l', + 0 + }; + u8 val = 1; + + /* Ignore the return value here - there's not really a lot we can do */ + efi_call_runtime(set_variable, + (efi_char16_t *)MemoryOverwriteRequestControl_name, + (efi_guid_t *)&var_guid, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + sizeof(val), val); +} + /* * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create @@ -990,6 +1016,11 @@ else setup_boot_services32(efi_early); + /* Ask the firmware to clear memory if we don't have a clean shutdown */ + enable_reset_attack_mitigation(); + + sanitize_boot_params(boot_params); + /* * If the boot loader gave us a value for secure_boot then we use that, * otherwise we ask the BIOS. --- linux-4.14.0.orig/arch/x86/boot/compressed/head_64.S +++ linux-4.14.0/arch/x86/boot/compressed/head_64.S @@ -289,10 +289,18 @@ leaq boot_stack_end(%rbx), %rsp #ifdef CONFIG_X86_5LEVEL - /* Check if 5-level paging has already enabled */ - movq %cr4, %rax - testl $X86_CR4_LA57, %eax - jnz lvl5 + /* + * Check if we need to enable 5-level paging. + * RSI holds real mode data and need to be preserved across + * a function call. + */ + pushq %rsi + call l5_paging_required + popq %rsi + + /* If l5_paging_required() returned zero, we're done here. */ + cmpq $0, %rax + je lvl5 /* * At this point we are in long mode with 4-level paging enabled, --- linux-4.14.0.orig/arch/x86/boot/compressed/misc.c +++ linux-4.14.0/arch/x86/boot/compressed/misc.c @@ -169,6 +169,16 @@ } } +static bool l5_supported(void) +{ + /* Check if leaf 7 is supported. */ + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)); +} + #if CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) @@ -362,6 +372,12 @@ console_init(); debug_putstr("early console in extract_kernel\n"); + if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) { + error("This linux kernel as configured requires 5-level paging\n" + "This CPU does not support the required 'cr4.la57' feature\n" + "Unable to boot - please use a kernel appropriate for your CPU\n"); + } + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; --- linux-4.14.0.orig/arch/x86/boot/compressed/pagetable.c +++ linux-4.14.0/arch/x86/boot/compressed/pagetable.c @@ -23,6 +23,9 @@ */ #undef CONFIG_AMD_MEM_ENCRYPT +/* No PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_PAGE_TABLE_ISOLATION + #include "misc.h" /* These actually do the work of building the kernel identity maps. */ --- linux-4.14.0.orig/arch/x86/boot/compressed/pgtable_64.c +++ linux-4.14.0/arch/x86/boot/compressed/pgtable_64.c @@ -0,0 +1,28 @@ +#include + +/* + * __force_order is used by special_insns.h asm code to force instruction + * serialization. + * + * 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. + */ +unsigned long __force_order; + +int l5_paging_required(void) +{ + /* Check if leaf 7 is supported. */ + + if (native_cpuid_eax(0) < 7) + return 0; + + /* Check if la57 is supported. */ + if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return 0; + + /* Check if 5-level paging has already been enabled. */ + if (native_read_cr4() & X86_CR4_LA57) + return 0; + + return 1; +} --- linux-4.14.0.orig/arch/x86/configs/tiny.config +++ linux-4.14.0/arch/x86/configs/tiny.config @@ -1,5 +1,5 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set -CONFIG_GUESS_UNWINDER=y -# CONFIG_FRAME_POINTER_UNWINDER is not set +CONFIG_UNWINDER_GUESS=y +# CONFIG_UNWINDER_FRAME_POINTER is not set --- linux-4.14.0.orig/arch/x86/configs/x86_64_defconfig +++ linux-4.14.0/arch/x86/configs/x86_64_defconfig @@ -299,6 +299,7 @@ # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y +CONFIG_UNWINDER_ORC=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y --- linux-4.14.0.orig/arch/x86/crypto/salsa20_glue.c +++ linux-4.14.0/arch/x86/crypto/salsa20_glue.c @@ -59,13 +59,6 @@ salsa20_ivsetup(ctx, walk.iv); - if (likely(walk.nbytes == nbytes)) - { - salsa20_encrypt_bytes(ctx, walk.src.virt.addr, - walk.dst.virt.addr, nbytes); - return blkcipher_walk_done(desc, &walk, 0); - } - while (walk.nbytes >= 64) { salsa20_encrypt_bytes(ctx, walk.src.virt.addr, walk.dst.virt.addr, --- linux-4.14.0.orig/arch/x86/entry/calling.h +++ linux-4.14.0/arch/x86/entry/calling.h @@ -1,6 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include #include +#include +#include +#include +#include +#include /* @@ -142,56 +147,25 @@ UNWIND_HINT_REGS offset=\offset .endm - .macro RESTORE_EXTRA_REGS offset=0 - movq 0*8+\offset(%rsp), %r15 - movq 1*8+\offset(%rsp), %r14 - movq 2*8+\offset(%rsp), %r13 - movq 3*8+\offset(%rsp), %r12 - movq 4*8+\offset(%rsp), %rbp - movq 5*8+\offset(%rsp), %rbx - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - - .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 - .if \rstor_r11 - movq 6*8(%rsp), %r11 - .endif - .if \rstor_r8910 - movq 7*8(%rsp), %r10 - movq 8*8(%rsp), %r9 - movq 9*8(%rsp), %r8 - .endif - .if \rstor_rax - movq 10*8(%rsp), %rax - .endif - .if \rstor_rcx - movq 11*8(%rsp), %rcx - .endif - .if \rstor_rdx - movq 12*8(%rsp), %rdx - .endif - movq 13*8(%rsp), %rsi - movq 14*8(%rsp), %rdi - UNWIND_HINT_IRET_REGS offset=16*8 - .endm - .macro RESTORE_C_REGS - RESTORE_C_REGS_HELPER 1,1,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RAX - RESTORE_C_REGS_HELPER 0,1,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RCX - RESTORE_C_REGS_HELPER 1,0,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_R11 - RESTORE_C_REGS_HELPER 1,1,0,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RCX_R11 - RESTORE_C_REGS_HELPER 1,0,0,1,1 - .endm - - .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 - subq $-(15*8+\addskip), %rsp + .macro POP_EXTRA_REGS + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + .endm + + .macro POP_C_REGS + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi .endm .macro icebp @@ -218,6 +192,146 @@ #endif .endm +#ifdef CONFIG_PAGE_TABLE_ISOLATION + +/* + * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two + * halves: + */ +#define PTI_SWITCH_PGTABLES_MASK (1< #include #include -#include "calling.h" #include #include #include @@ -40,6 +39,8 @@ #include #include +#include "calling.h" + .code64 .section .entry.text, "ax" @@ -136,6 +137,67 @@ * with them due to bugs in both AMD and Intel CPUs. */ + .pushsection .entry_trampoline, "ax" + +/* + * The code in here gets remapped into cpu_entry_area's trampoline. This means + * that the assembler and linker have the wrong idea as to where this code + * lives (and, in fact, it's mapped more than once, so it's not even at a + * fixed address). So we can't reference any symbols outside the entry + * trampoline and expect it to work. + * + * Instead, we carefully abuse %rip-relative addressing. + * _entry_trampoline(%rip) refers to the start of the remapped) entry + * trampoline. We can thus find cpu_entry_area with this macro: + */ + +#define CPU_ENTRY_AREA \ + _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) + +/* The top word of the SYSENTER stack is hot and is usable as scratch space. */ +#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \ + SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA + +ENTRY(entry_SYSCALL_64_trampoline) + UNWIND_HINT_EMPTY + swapgs + + /* Stash the user RSP. */ + movq %rsp, RSP_SCRATCH + + /* Note: using %rsp as a scratch reg. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + + /* Load the top of the task stack into RSP */ + movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp + + /* Start building the simulated IRET frame. */ + pushq $__USER_DS /* pt_regs->ss */ + pushq RSP_SCRATCH /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + + /* + * x86 lacks a near absolute jump, and we can't jump to the real + * entry text with a relative jump. We could push the target + * address and then use retq, but this destroys the pipeline on + * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead, + * spill RDI and restore it in a second-stage trampoline. + */ + pushq %rdi + movq $entry_SYSCALL_64_stage2, %rdi + jmp *%rdi +END(entry_SYSCALL_64_trampoline) + + .popsection + +ENTRY(entry_SYSCALL_64_stage2) + UNWIND_HINT_EMPTY + popq %rdi + jmp entry_SYSCALL_64_after_hwframe +END(entry_SYSCALL_64_stage2) + ENTRY(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* @@ -145,11 +207,13 @@ */ swapgs + /* + * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * is not required to switch CR3. + */ movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - TRACE_IRQS_OFF - /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ @@ -170,6 +234,8 @@ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ UNWIND_HINT_REGS extra=0 + TRACE_IRQS_OFF + /* * If we need to do entry work or if we guess we'll need to do * exit work, go straight to the slow path. @@ -221,10 +287,9 @@ TRACE_IRQS_ON /* user mode is traced as IRQs on */ movq RIP(%rsp), %rcx movq EFLAGS(%rsp), %r11 - RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RSP(%rsp), %rsp + addq $6*8, %rsp /* skip extra regs -- they were preserved */ UNWIND_HINT_EMPTY - USERGS_SYSRET64 + jmp .Lpop_c_regs_except_rcx_r11_and_sysret 1: /* @@ -246,17 +311,18 @@ call do_syscall_64 /* returns with IRQs disabled */ return_from_SYSCALL_64: - RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ /* * Try to use SYSRET instead of IRET if we're returning to - * a completely clean 64-bit userspace context. + * a completely clean 64-bit userspace context. If we're not, + * go to the slow exit path. */ movq RCX(%rsp), %rcx movq RIP(%rsp), %r11 - cmpq %rcx, %r11 /* RCX == RIP */ - jne opportunistic_sysret_failed + + cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */ + jne swapgs_restore_regs_and_return_to_usermode /* * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP @@ -274,14 +340,14 @@ /* If this changed %rcx, it was not canonical */ cmpq %rcx, %r11 - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode movq R11(%rsp), %r11 cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode /* * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot @@ -302,12 +368,12 @@ * would never get past 'stuck_here'. */ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed + jnz swapgs_restore_regs_and_return_to_usermode /* nothing to check for RSP */ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode /* * We win! This label is here just for ease of understanding @@ -315,14 +381,37 @@ */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RSP(%rsp), %rsp UNWIND_HINT_EMPTY - USERGS_SYSRET64 + POP_EXTRA_REGS +.Lpop_c_regs_except_rcx_r11_and_sysret: + popq %rsi /* skip r11 */ + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rsi /* skip rcx */ + popq %rdx + popq %rsi -opportunistic_sysret_failed: - SWAPGS - jmp restore_c_regs_and_iret + /* + * Now all regs are restored except RSP and RDI. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + pushq RSP-RDI(%rdi) /* RSP */ + pushq (%rdi) /* RDI */ + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + + popq %rdi + popq %rsp + USERGS_SYSRET64 END(entry_SYSCALL_64) ENTRY(stub_ptregs_64) @@ -423,8 +512,7 @@ movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode 1: /* kernel thread */ @@ -457,12 +545,13 @@ .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY - pushfq - testl $X86_EFLAGS_IF, (%rsp) + pushq %rax + SAVE_FLAGS(CLBR_RAX) + testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 .Lokay_\@: - addq $8, %rsp + popq %rax #endif .endm @@ -554,6 +643,13 @@ /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS @@ -563,12 +659,8 @@ jz 1f /* - * IRQ from user mode. Switch to kernel gsbase and inform context - * tracking that we're in kernel mode. - */ - SWAPGS - - /* + * IRQ from user mode. + * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode * (which can take locks). Since TRACE_IRQS_OFF idempotent, @@ -612,8 +704,54 @@ mov %rsp,%rdi call prepare_exit_to_usermode TRACE_IRQS_IRETQ + +GLOBAL(swapgs_restore_regs_and_return_to_usermode) +#ifdef CONFIG_DEBUG_ENTRY + /* Assert that pt_regs indicates user mode. */ + testb $3, CS(%rsp) + jnz 1f + ud2 +1: +#endif + POP_EXTRA_REGS + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + + /* + * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + /* Copy the IRET frame to the trampoline stack. */ + pushq 6*8(%rdi) /* SS */ + pushq 5*8(%rdi) /* RSP */ + pushq 4*8(%rdi) /* EFLAGS */ + pushq 3*8(%rdi) /* CS */ + pushq 2*8(%rdi) /* RIP */ + + /* Push user RDI on the trampoline stack. */ + pushq (%rdi) + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + + /* Restore RDI. */ + popq %rdi SWAPGS - jmp restore_regs_and_iret + INTERRUPT_RETURN + /* Returning to kernel space */ retint_kernel: @@ -633,15 +771,17 @@ */ TRACE_IRQS_IRETQ -/* - * At this label, code paths which return to kernel and to user, - * which come from interrupts/exception and from syscalls, merge. - */ -GLOBAL(restore_regs_and_iret) - RESTORE_EXTRA_REGS -restore_c_regs_and_iret: - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 +GLOBAL(restore_regs_and_return_to_kernel) +#ifdef CONFIG_DEBUG_ENTRY + /* Assert that pt_regs indicates kernel mode. */ + testb $3, CS(%rsp) + jz 1f + ud2 +1: +#endif + POP_EXTRA_REGS + POP_C_REGS + addq $8, %rsp /* skip regs->orig_ax */ INTERRUPT_RETURN ENTRY(native_iret) @@ -689,7 +829,9 @@ */ pushq %rdi /* Stash user RDI */ - SWAPGS + SWAPGS /* to kernel GS */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */ + movq PER_CPU_VAR(espfix_waddr), %rdi movq %rax, (0*8)(%rdi) /* user RAX */ movq (1*8)(%rsp), %rax /* user RIP */ @@ -705,7 +847,6 @@ /* Now RAX == RSP. */ andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */ - popq %rdi /* Restore user RDI */ /* * espfix_stack[31:16] == 0. The page tables are set up such that @@ -716,7 +857,11 @@ * still points to an RO alias of the ESPFIX stack. */ orq PER_CPU_VAR(espfix_stack), %rax - SWAPGS + + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + SWAPGS /* to user GS */ + popq %rdi /* Restore user RDI */ + movq %rax, %rsp UNWIND_HINT_IRET_REGS offset=8 @@ -805,7 +950,35 @@ /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) + +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +ENTRY(switch_to_thread_stack) + UNWIND_HINT_FUNC + + pushq %rdi + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi + ret +END(switch_to_thread_stack) .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) @@ -818,17 +991,18 @@ ASM_CLAC - .ifeq \has_error_code + .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif ALLOC_PT_GPREGS_ON_STACK - .if \paranoid - .if \paranoid == 1 + .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ - jnz 1f + jnz .Lfrom_usermode_switch_stack_\@ .endif + + .if \paranoid call paranoid_entry .else call error_entry @@ -870,20 +1044,15 @@ jmp error_exit .endif - .if \paranoid == 1 + .if \paranoid < 2 /* - * Paranoid entry from userspace. Switch stacks and treat it + * Entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ -1: +.Lfrom_usermode_switch_stack_\@: call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - call sync_regs - movq %rax, %rsp /* switch stack */ - movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code @@ -1059,6 +1228,7 @@ idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN +idtentry xennmi do_nmi has_error_code=0 idtentry xendebug do_debug has_error_code=0 idtentry xenint3 do_int3 has_error_code=0 #endif @@ -1092,7 +1262,11 @@ js 1f /* negative -> in kernel */ SWAPGS xorl %ebx, %ebx -1: ret + +1: + SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + + ret END(paranoid_entry) /* @@ -1112,17 +1286,15 @@ DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF_DEBUG testl %ebx, %ebx /* swapgs needed? */ - jnz paranoid_exit_no_swapgs + jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore -paranoid_exit_no_swapgs: + jmp .Lparanoid_exit_restore +.Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 - INTERRUPT_RETURN +.Lparanoid_exit_restore: + jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* @@ -1144,8 +1316,18 @@ * from user mode due to an IRET fault. */ SWAPGS + /* We have user CR3. Change to kernel CR3. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ + popq %r12 /* save return addr in %12 */ + movq %rsp, %rdi /* arg0 = pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ + ENCODE_FRAME_POINTER + pushq %r12 + /* * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode @@ -1182,6 +1364,7 @@ * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done .Lbstep_iret: @@ -1191,10 +1374,11 @@ .Lerror_bad_iret: /* - * We came from an IRET to user mode, so we have user gsbase. - * Switch to kernel gsbase: + * We came from an IRET to user mode, so we have user + * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* * Pretend that the exception came from user mode: set up pt_regs @@ -1223,10 +1407,17 @@ jmp retint_user END(error_exit) -/* Runs on exception stack */ -/* XXX: broken on Xen PV */ +/* + * Runs on exception stack. Xen PV does not go through this path at all, + * so we can use real assembly here. + * + * Registers: + * %r14: Used to save/restore the CR3 of the interrupted context + * when PAGE_TABLE_ISOLATION is in use. Do not clobber. + */ ENTRY(nmi) UNWIND_HINT_IRET_REGS + /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1284,8 +1475,9 @@ * stacks lest we corrupt the "NMI executing" variable. */ - SWAPGS_UNSAFE_STACK + swapgs cld + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp UNWIND_HINT_IRET_REGS base=%rdx offset=8 @@ -1328,8 +1520,7 @@ * Return back to user mode. We must *not* do the normal exit * work, because we don't want to enable interrupts. */ - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode .Lnmi_from_kernel: /* @@ -1450,7 +1641,7 @@ popq %rdx /* We are returning to kernel mode, so this cannot result in a fault. */ - INTERRUPT_RETURN + iretq first_nmi: /* Restore rdx. */ @@ -1481,7 +1672,7 @@ pushfq /* RFLAGS */ pushq $__KERNEL_CS /* CS */ pushq $1f /* RIP */ - INTERRUPT_RETURN /* continues at repeat_nmi below */ + iretq /* continues at repeat_nmi below */ UNWIND_HINT_IRET_REGS 1: #endif @@ -1539,34 +1730,41 @@ movq $-1, %rsi call do_nmi + RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 + testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS + POP_EXTRA_REGS + POP_C_REGS - /* Point RSP at the "iret" frame. */ - REMOVE_PT_GPREGS_FROM_STACK 6*8 + /* + * Skip orig_ax and the "outermost" frame to point RSP at the "iret" + * at the "iret" frame. + */ + addq $6*8, %rsp /* * Clear "NMI executing". Set DF first so that we can easily * distinguish the remaining code between here and IRET from - * the SYSCALL entry and exit paths. On a native kernel, we - * could just inspect RIP, but, on paravirt kernels, - * INTERRUPT_RETURN can translate into a jump into a - * hypercall page. + * the SYSCALL entry and exit paths. + * + * We arguably should just inspect RIP instead, but I (Andy) wrote + * this code when I had the misapprehension that Xen PV supported + * NMIs, and Xen PV would break that approach. */ std movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* - * INTERRUPT_RETURN reads the "iret" frame and exits the NMI - * stack in a single instruction. We are returning to kernel - * mode, so this cannot result in a fault. + * iretq reads the "iret" frame and exits the NMI stack in a + * single instruction. We are returning to kernel mode, so this + * cannot result in a fault. Similarly, we don't need to worry + * about espfix64 on the way back to kernel mode. */ - INTERRUPT_RETURN + iretq END(nmi) ENTRY(ignore_sysret) --- linux-4.14.0.orig/arch/x86/entry/entry_64_compat.S +++ linux-4.14.0/arch/x86/entry/entry_64_compat.S @@ -48,7 +48,11 @@ */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + SWAPGS + + /* We are about to clobber %rsp anyway, clobbering here is OK */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -186,8 +190,13 @@ /* Interrupts are off on entry. */ swapgs - /* Stash user ESP and switch to the kernel stack. */ + /* Stash user ESP */ movl %esp, %r8d + + /* Use %rsp as scratch reg. User ESP is stashed in r8 */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + + /* Switch to the kernel stack */ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* Construct struct pt_regs on stack */ @@ -256,10 +265,22 @@ * when the system call started, which is already known to user * code. We zero R8-R10 to avoid info leaks. */ + movq RSP-ORIG_RAX(%rsp), %rsp + + /* + * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored + * on the process stack which is not mapped to userspace and + * not readable after we SWITCH_TO_USER_CR3. Delay the CR3 + * switch until after after the last reference to the process + * stack. + * + * %r8/%r9 are zeroed before the sysret, thus safe to clobber. + */ + SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 + xorq %r8, %r8 xorq %r9, %r9 xorq %r10, %r10 - movq RSP-ORIG_RAX(%rsp), %rsp swapgs sysretl END(entry_SYSCALL_compat) @@ -306,8 +327,11 @@ */ movl %eax, %eax - /* Construct struct pt_regs on stack (iret frame is already on stack) */ pushq %rax /* pt_regs->orig_ax */ + + /* switch to thread stack expects orig_ax to be pushed */ + call switch_to_thread_stack + pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ @@ -337,8 +361,7 @@ /* Go back to user mode. */ TRACE_IRQS_ON - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) ENTRY(stub32_clone) --- linux-4.14.0.orig/arch/x86/entry/syscalls/Makefile +++ linux-4.14.0/arch/x86/entry/syscalls/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -out := $(obj)/../../include/generated/asm -uapi := $(obj)/../../include/generated/uapi/asm +out := arch/$(SRCARCH)/include/generated/asm +uapi := arch/$(SRCARCH)/include/generated/uapi/asm # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ --- linux-4.14.0.orig/arch/x86/entry/vsyscall/vsyscall_64.c +++ linux-4.14.0/arch/x86/entry/vsyscall/vsyscall_64.c @@ -37,6 +37,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" @@ -138,6 +139,10 @@ WARN_ON_ONCE(address != regs->ip); + /* This should be unreachable in NATIVE mode. */ + if (WARN_ON(vsyscall_mode == NATIVE)) + return false; + if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -329,16 +334,47 @@ return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } +/* + * The VSYSCALL page is the only user-accessible page in the kernel address + * range. Normally, the kernel page tables can have _PAGE_USER clear, but + * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls + * are enabled. + * + * Some day we may create a "minimal" vsyscall mode in which we emulate + * vsyscalls but leave the page not present. If so, we skip calling + * this. + */ +void __init set_vsyscall_pgtable_user_bits(pgd_t *root) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); + set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); + p4d = p4d_offset(pgd, VSYSCALL_ADDR); +#if CONFIG_PGTABLE_LEVELS >= 5 + p4d->p4d |= _PAGE_USER; +#endif + pud = pud_offset(p4d, VSYSCALL_ADDR); + set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); + pmd = pmd_offset(pud, VSYSCALL_ADDR); + set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); +} + void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - if (vsyscall_mode != NONE) + if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, vsyscall_mode == NATIVE ? PAGE_KERNEL_VSYSCALL : PAGE_KERNEL_VVAR); + set_vsyscall_pgtable_user_bits(swapper_pg_dir); + } BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); --- linux-4.14.0.orig/arch/x86/events/core.c +++ linux-4.14.0/arch/x86/events/core.c @@ -2371,7 +2371,7 @@ struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ - ldt = lockless_dereference(current->active_mm->context.ldt); + ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; --- linux-4.14.0.orig/arch/x86/events/intel/core.c +++ linux-4.14.0/arch/x86/events/intel/core.c @@ -2958,6 +2958,10 @@ if (event->attr.use_clockid) flags &= ~PERF_SAMPLE_TIME; + if (!event->attr.exclude_kernel) + flags &= ~PERF_SAMPLE_REGS_USER; + if (event->attr.sample_regs_user & ~PEBS_REGS) + flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } @@ -3730,6 +3734,19 @@ EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1"); static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + EVENT_PTR(td_slots_issued), + EVENT_PTR(td_slots_retired), + EVENT_PTR(td_fetch_bubbles), + EVENT_PTR(td_total_slots), + EVENT_PTR(td_total_slots_scale), + EVENT_PTR(td_recovery_bubbles), + EVENT_PTR(td_recovery_bubbles_scale), + NULL +}; + +static struct attribute *hsw_tsx_events_attrs[] = { EVENT_PTR(tx_start), EVENT_PTR(tx_commit), EVENT_PTR(tx_abort), @@ -3742,18 +3759,16 @@ EVENT_PTR(el_conflict), EVENT_PTR(cycles_t), EVENT_PTR(cycles_ct), - EVENT_PTR(mem_ld_hsw), - EVENT_PTR(mem_st_hsw), - EVENT_PTR(td_slots_issued), - EVENT_PTR(td_slots_retired), - EVENT_PTR(td_fetch_bubbles), - EVENT_PTR(td_total_slots), - EVENT_PTR(td_total_slots_scale), - EVENT_PTR(td_recovery_bubbles), - EVENT_PTR(td_recovery_bubbles_scale), NULL }; +static __init struct attribute **get_hsw_events_attrs(void) +{ + return boot_cpu_has(X86_FEATURE_RTM) ? + merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) : + hsw_events_attrs; +} + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4182,7 +4197,7 @@ x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); x86_pmu.lbr_double_abort = true; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; @@ -4221,7 +4236,7 @@ x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); x86_pmu.limit_period = bdw_limit_period; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; @@ -4279,7 +4294,7 @@ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; extra_attr = merge_attr(extra_attr, skl_format_attr); - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); pr_cont("Skylake events, "); --- linux-4.14.0.orig/arch/x86/events/intel/ds.c +++ linux-4.14.0/arch/x86/events/intel/ds.c @@ -3,16 +3,18 @@ #include #include +#include #include #include #include "../perf_event.h" +/* Waste a full page so it can be mapped into the cpu_entry_area */ +DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 -#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -279,17 +281,52 @@ static DEFINE_PER_CPU(void *, insn_buffer); -static int alloc_pebs_buffer(int cpu) +static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + phys_addr_t pa; + size_t msz = 0; + + pa = virt_to_phys(addr); + for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE) + cea_set_pte(cea, pa, prot); +} + +static void ds_clear_cea(void *cea, size_t size) +{ + size_t msz = 0; + + for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE) + cea_set_pte(cea, 0, PAGE_NONE); +} + +static void *dsalloc_pages(size_t size, gfp_t flags, int cpu) +{ + unsigned int order = get_order(size); int node = cpu_to_node(cpu); - int max; - void *buffer, *ibuffer; + struct page *page; + + page = __alloc_pages_node(node, flags | __GFP_ZERO, order); + return page ? page_address(page) : NULL; +} + +static void dsfree_pages(const void *buffer, size_t size) +{ + if (buffer) + free_pages((unsigned long)buffer, get_order(size)); +} + +static int alloc_pebs_buffer(int cpu) +{ + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + size_t bsiz = x86_pmu.pebs_buffer_size; + int max, node = cpu_to_node(cpu); + void *buffer, *ibuffer, *cea; if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); + buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu); if (unlikely(!buffer)) return -ENOMEM; @@ -300,25 +337,27 @@ if (x86_pmu.intel_cap.pebs_format < 2) { ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); if (!ibuffer) { - kfree(buffer); + dsfree_pages(buffer, bsiz); return -ENOMEM; } per_cpu(insn_buffer, cpu) = ibuffer; } - - max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; - - ds->pebs_buffer_base = (u64)(unsigned long)buffer; + hwev->ds_pebs_vaddr = buffer; + /* Update the cpu entry area mapping */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; + ds->pebs_buffer_base = (unsigned long) cea; + ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL); ds->pebs_index = ds->pebs_buffer_base; - ds->pebs_absolute_maximum = ds->pebs_buffer_base + - max * x86_pmu.pebs_record_size; - + max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size); + ds->pebs_absolute_maximum = ds->pebs_buffer_base + max; return 0; } static void release_pebs_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *cea; if (!ds || !x86_pmu.pebs) return; @@ -326,73 +365,70 @@ kfree(per_cpu(insn_buffer, cpu)); per_cpu(insn_buffer, cpu) = NULL; - kfree((void *)(unsigned long)ds->pebs_buffer_base); + /* Clear the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; + ds_clear_cea(cea, x86_pmu.pebs_buffer_size); ds->pebs_buffer_base = 0; + dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size); + hwev->ds_pebs_vaddr = NULL; } static int alloc_bts_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - int node = cpu_to_node(cpu); - int max, thresh; - void *buffer; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *buffer, *cea; + int max; if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu); if (unlikely(!buffer)) { WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; } - - max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; - thresh = max / 16; - - ds->bts_buffer_base = (u64)(unsigned long)buffer; + hwev->ds_bts_vaddr = buffer; + /* Update the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; + ds->bts_buffer_base = (unsigned long) cea; + ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - ds->bts_absolute_maximum = ds->bts_buffer_base + - max * BTS_RECORD_SIZE; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - - thresh * BTS_RECORD_SIZE; - + max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); + ds->bts_absolute_maximum = ds->bts_buffer_base + max; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); return 0; } static void release_bts_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *cea; if (!ds || !x86_pmu.bts) return; - kfree((void *)(unsigned long)ds->bts_buffer_base); + /* Clear the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; + ds_clear_cea(cea, BTS_BUFFER_SIZE); ds->bts_buffer_base = 0; + dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE); + hwev->ds_bts_vaddr = NULL; } static int alloc_ds_buffer(int cpu) { - int node = cpu_to_node(cpu); - struct debug_store *ds; - - ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); - if (unlikely(!ds)) - return -ENOMEM; + struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store; + memset(ds, 0, sizeof(*ds)); per_cpu(cpu_hw_events, cpu).ds = ds; - return 0; } static void release_ds_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - return; - per_cpu(cpu_hw_events, cpu).ds = NULL; - kfree(ds); } void release_ds_buffers(void) --- linux-4.14.0.orig/arch/x86/events/perf_event.h +++ linux-4.14.0/arch/x86/events/perf_event.h @@ -14,6 +14,8 @@ #include +#include + /* To enable MSR tracing please use the generic trace points. */ /* @@ -77,38 +79,41 @@ struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 8 #define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1) /* * Flags PEBS can handle without an PMI. * * TID can only be handled by flushing at context switch. + * REGS_USER can be handled for events limited to ring 3. * */ #define PEBS_FREERUNNING_FLAGS \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ - PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR) + PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ + PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; +#define PEBS_REGS \ + (PERF_REG_X86_AX | \ + PERF_REG_X86_BX | \ + PERF_REG_X86_CX | \ + PERF_REG_X86_DX | \ + PERF_REG_X86_DI | \ + PERF_REG_X86_SI | \ + PERF_REG_X86_SP | \ + PERF_REG_X86_BP | \ + PERF_REG_X86_IP | \ + PERF_REG_X86_FLAGS | \ + PERF_REG_X86_R8 | \ + PERF_REG_X86_R9 | \ + PERF_REG_X86_R10 | \ + PERF_REG_X86_R11 | \ + PERF_REG_X86_R12 | \ + PERF_REG_X86_R13 | \ + PERF_REG_X86_R14 | \ + PERF_REG_X86_R15) /* * Per register state. @@ -194,6 +199,8 @@ * Intel DebugStore bits */ struct debug_store *ds; + void *ds_pebs_vaddr; + void *ds_bts_vaddr; u64 pebs_enabled; int n_pebs; int n_large_pebs; --- linux-4.14.0.orig/arch/x86/hyperv/hv_init.c +++ linux-4.14.0/arch/x86/hyperv/hv_init.c @@ -29,6 +29,14 @@ #include #include +#ifndef PKG_ABI +/* + * Preserve the ability to 'make deb-pkg' since PKG_ABI is provided + * by the Ubuntu build rules. + */ +#define PKG_ABI 0 +#endif + #ifdef CONFIG_HYPERV_TSCPAGE static struct ms_hyperv_tsc_page *tsc_pg; @@ -113,7 +121,7 @@ u64 guest_id; union hv_x64_msr_hypercall_contents hypercall_msr; - if (x86_hyper != &x86_hyper_ms_hyperv) + if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; /* Allocate percpu VP index */ @@ -131,7 +139,7 @@ * 1. Register the guest ID * 2. Enable the hypercall and register the hypercall page */ - guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); + guest_id = generate_guest_id(0x80 /*Canonical*/, LINUX_VERSION_CODE, PKG_ABI); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); hv_hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); --- linux-4.14.0.orig/arch/x86/include/asm/archrandom.h +++ linux-4.14.0/arch/x86/include/asm/archrandom.h @@ -45,7 +45,7 @@ bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_LONG "\n\t" + asm volatile(RDRAND_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -59,7 +59,7 @@ bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_INT "\n\t" + asm volatile(RDRAND_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -71,7 +71,7 @@ static inline bool rdseed_long(unsigned long *v) { bool ok; - asm volatile(RDSEED_LONG "\n\t" + asm volatile(RDSEED_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; @@ -80,7 +80,7 @@ static inline bool rdseed_int(unsigned int *v) { bool ok; - asm volatile(RDSEED_INT "\n\t" + asm volatile(RDSEED_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; --- linux-4.14.0.orig/arch/x86/include/asm/bitops.h +++ linux-4.14.0/arch/x86/include/asm/bitops.h @@ -143,7 +143,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; - asm volatile(LOCK_PREFIX "andb %2,%1\n\t" + asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), ADDR : "ir" ((char) ~(1 << nr)) : "memory"); @@ -246,7 +246,7 @@ { bool oldbit; - asm("bts %2,%1\n\t" + asm("bts %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -286,7 +286,7 @@ { bool oldbit; - asm volatile("btr %2,%1\n\t" + asm volatile("btr %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -298,7 +298,7 @@ { bool oldbit; - asm volatile("btc %2,%1\n\t" + asm volatile("btc %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -329,7 +329,7 @@ { bool oldbit; - asm volatile("bt %2,%1\n\t" + asm volatile("bt %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); --- linux-4.14.0.orig/arch/x86/include/asm/compat.h +++ linux-4.14.0/arch/x86/include/asm/compat.h @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include @@ -209,7 +210,6 @@ } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL struct compat_ipc64_perm { compat_key_t key; --- linux-4.14.0.orig/arch/x86/include/asm/cpu_entry_area.h +++ linux-4.14.0/arch/x86/include/asm/cpu_entry_area.h @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _ASM_X86_CPU_ENTRY_AREA_H +#define _ASM_X86_CPU_ENTRY_AREA_H + +#include +#include +#include + +/* + * cpu_entry_area is a percpu region that contains things needed by the CPU + * and early entry/exit code. Real types aren't used for all fields here + * to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below entry_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct entry_stack_page entry_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries. + * + * In the future, this should have a separate slot for each stack + * with guard pages between them. + */ + char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; +#endif +#ifdef CONFIG_CPU_SUP_INTEL + /* + * Per CPU debug store for Intel performance monitoring. Wastes a + * full page at the moment. + */ + struct debug_store cpu_debug_store; + /* + * The actual PEBS/BTS buffers must be mapped to user space + * Reserve enough fixmap PTEs. + */ + struct debug_store_buffers cpu_debug_buffers; +#endif +}; + +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) + +DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); + +extern void setup_cpu_entry_areas(void); +extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); + +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#define CPU_ENTRY_AREA_MAP_SIZE \ + (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) + +extern struct cpu_entry_area *get_cpu_entry_area(int cpu); + +static inline struct entry_stack *cpu_entry_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->entry_stack_page.stack; +} + +#endif --- linux-4.14.0.orig/arch/x86/include/asm/cpufeature.h +++ linux-4.14.0/arch/x86/include/asm/cpufeature.h @@ -126,16 +126,17 @@ #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) -#define clear_cpu_cap(c, bit) clear_bit(bit, (unsigned long *)((c)->x86_capability)) -#define setup_clear_cpu_cap(bit) do { \ - clear_cpu_cap(&boot_cpu_data, bit); \ - set_bit(bit, (unsigned long *)cpu_caps_cleared); \ -} while (0) + +extern void setup_clear_cpu_cap(unsigned int bit); +extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); + #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). --- linux-4.14.0.orig/arch/x86/include/asm/cpufeatures.h +++ linux-4.14.0/arch/x86/include/asm/cpufeatures.h @@ -13,173 +13,176 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used * in /proc/cpuinfo instead of the macro name. If the string is "", * this feature bit is not displayed in /proc/cpuinfo at all. + * + * When adding new features here that depend on other features, + * please update the table in kernel/cpu/cpuid-deps.c as well. */ -/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ - /* (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ -#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ -#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ -#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ -#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ -#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ -#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -/* cpu types for specific tunings: */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ -#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ - -/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ -#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ -#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ -#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ -#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ -#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ + +/* CPU types for specific tunings: */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" MFENCE synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ -#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ -#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ -#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ -#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ - -/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ + +/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -187,146 +190,157 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ - -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ - -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ + +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ - -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ - - -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ - -/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ - -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ -#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ - -/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ -#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ - -/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ - -/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ -#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ -#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ - -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ - -/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ + +#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ + + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ + +/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ + +/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ + +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ + +/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ /* * BUG word(s) */ -#define X86_BUG(x) (NCAPINTS*32 + (x)) +#define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ -#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ -#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */ + #endif /* _ASM_X86_CPUFEATURES_H */ --- linux-4.14.0.orig/arch/x86/include/asm/desc.h +++ linux-4.14.0/arch/x86/include/asm/desc.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -20,6 +21,8 @@ desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; + /* Set the ACCESS bit so it can be mapped RO */ + desc->type |= 1; desc->s = 1; desc->dpl = 0x3; @@ -60,17 +63,10 @@ return this_cpu_ptr(&gdt_page)->gdt; } -/* Get the fixmap index for a specific processor */ -static inline unsigned int get_cpu_gdt_ro_index(int cpu) -{ - return FIX_GDT_REMAP_BEGIN + cpu; -} - /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { - unsigned int idx = get_cpu_gdt_ro_index(cpu); - return (struct desc_struct *)__fix_to_virt(idx); + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ @@ -185,7 +181,7 @@ #endif } -static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; --- linux-4.14.0.orig/arch/x86/include/asm/disabled-features.h +++ linux-4.14.0/arch/x86/include/asm/disabled-features.h @@ -44,6 +44,12 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define DISABLE_PTI 0 +#else +# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -54,7 +60,7 @@ #define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 -#define DISABLED_MASK7 0 +#define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 #define DISABLED_MASK9 (DISABLE_MPX) #define DISABLED_MASK10 0 --- linux-4.14.0.orig/arch/x86/include/asm/espfix.h +++ linux-4.14.0/arch/x86/include/asm/espfix.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_ESPFIX_H #define _ASM_X86_ESPFIX_H -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_ESPFIX64 #include @@ -11,7 +11,8 @@ extern void init_espfix_bsp(void); extern void init_espfix_ap(int cpu); - -#endif /* CONFIG_X86_64 */ +#else +static inline void init_espfix_ap(int cpu) { } +#endif #endif /* _ASM_X86_ESPFIX_H */ --- linux-4.14.0.orig/arch/x86/include/asm/fixmap.h +++ linux-4.14.0/arch/x86/include/asm/fixmap.h @@ -44,7 +44,6 @@ PAGE_SIZE) #endif - /* * Here we define all the compile-time 'special' virtual * addresses. The point is to have a constant address at @@ -84,7 +83,6 @@ FIX_IO_APIC_BASE_0, FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, #endif - FIX_RO_IDT, /* Virtual mapping for read-only IDT */ #ifdef CONFIG_X86_32 FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, @@ -100,9 +98,12 @@ #ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif - /* Fixmap entries to remap the GDTs, one per processor. */ - FIX_GDT_REMAP_BEGIN, - FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif __end_of_permanent_fixed_addresses, @@ -137,7 +138,7 @@ extern void reserve_top_address(unsigned long reserve); #define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) extern int fixmaps_set; --- linux-4.14.0.orig/arch/x86/include/asm/hypervisor.h +++ linux-4.14.0/arch/x86/include/asm/hypervisor.h @@ -20,14 +20,22 @@ #ifndef _ASM_X86_HYPERVISOR_H #define _ASM_X86_HYPERVISOR_H +/* x86 hypervisor types */ +enum x86_hypervisor_type { + X86_HYPER_NATIVE = 0, + X86_HYPER_VMWARE, + X86_HYPER_MS_HYPERV, + X86_HYPER_XEN_PV, + X86_HYPER_XEN_HVM, + X86_HYPER_KVM, +}; + #ifdef CONFIG_HYPERVISOR_GUEST #include +#include #include -/* - * x86 hypervisor information - */ struct hypervisor_x86 { /* Hypervisor name */ const char *name; @@ -35,40 +43,27 @@ /* Detection routine */ uint32_t (*detect)(void); - /* Platform setup (run once per boot) */ - void (*init_platform)(void); + /* Hypervisor type */ + enum x86_hypervisor_type type; - /* X2APIC detection (run once per boot) */ - bool (*x2apic_available)(void); + /* init time callbacks */ + struct x86_hyper_init init; - /* pin current vcpu to specified physical cpu (run rarely) */ - void (*pin_vcpu)(int); - - /* called during init_mem_mapping() to setup early mappings. */ - void (*init_mem_mapping)(void); + /* runtime callbacks */ + struct x86_hyper_runtime runtime; }; -extern const struct hypervisor_x86 *x86_hyper; - -/* Recognized hypervisors */ -extern const struct hypervisor_x86 x86_hyper_vmware; -extern const struct hypervisor_x86 x86_hyper_ms_hyperv; -extern const struct hypervisor_x86 x86_hyper_xen_pv; -extern const struct hypervisor_x86 x86_hyper_xen_hvm; -extern const struct hypervisor_x86 x86_hyper_kvm; - +extern enum x86_hypervisor_type x86_hyper_type; extern void init_hypervisor_platform(void); -extern bool hypervisor_x2apic_available(void); -extern void hypervisor_pin_vcpu(int cpu); - -static inline void hypervisor_init_mem_mapping(void) +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) { - if (x86_hyper && x86_hyper->init_mem_mapping) - x86_hyper->init_mem_mapping(); + return x86_hyper_type == type; } #else static inline void init_hypervisor_platform(void) { } -static inline bool hypervisor_x2apic_available(void) { return false; } -static inline void hypervisor_init_mem_mapping(void) { } +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return type == X86_HYPER_NATIVE; +} #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ --- linux-4.14.0.orig/arch/x86/include/asm/inat.h +++ linux-4.14.0/arch/x86/include/asm/inat.h @@ -97,6 +97,16 @@ #define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) #define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 + /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); extern int inat_get_last_prefix_id(insn_byte_t last_pfx); --- linux-4.14.0.orig/arch/x86/include/asm/intel_ds.h +++ linux-4.14.0/arch/x86/include/asm/intel_ds.h @@ -0,0 +1,36 @@ +#ifndef _ASM_INTEL_DS_H +#define _ASM_INTEL_DS_H + +#include + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 8 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +} __aligned(PAGE_SIZE); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + +struct debug_store_buffers { + char bts_buffer[BTS_BUFFER_SIZE]; + char pebs_buffer[PEBS_BUFFER_SIZE]; +}; + +#endif --- linux-4.14.0.orig/arch/x86/include/asm/invpcid.h +++ linux-4.14.0/arch/x86/include/asm/invpcid.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INVPCID +#define _ASM_X86_INVPCID + +static inline void __invpcid(unsigned long pcid, unsigned long addr, + unsigned long type) +{ + struct { u64 d[2]; } desc = { { pcid, addr } }; + + /* + * The memory clobber is because the whole point is to invalidate + * stale TLB entries and, especially if we're flushing global + * mappings, we don't want the compiler to reorder any subsequent + * memory accesses before the TLB flush. + * + * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and + * invpcid (%rcx), %rax in long mode. + */ + asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01" + : : "m" (desc), "a" (type), "c" (&desc) : "memory"); +} + +#define INVPCID_TYPE_INDIV_ADDR 0 +#define INVPCID_TYPE_SINGLE_CTXT 1 +#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 +#define INVPCID_TYPE_ALL_NON_GLOBAL 3 + +/* Flush all mappings for a given pcid and addr, not including globals. */ +static inline void invpcid_flush_one(unsigned long pcid, + unsigned long addr) +{ + __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); +} + +/* Flush all mappings for a given PCID, not including globals. */ +static inline void invpcid_flush_single_context(unsigned long pcid) +{ + __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); +} + +/* Flush all mappings, including globals, for all PCIDs. */ +static inline void invpcid_flush_all(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL); +} + +/* Flush all mappings for all PCIDs except globals. */ +static inline void invpcid_flush_all_nonglobals(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); +} + +#endif /* _ASM_X86_INVPCID */ --- linux-4.14.0.orig/arch/x86/include/asm/irqflags.h +++ linux-4.14.0/arch/x86/include/asm/irqflags.h @@ -142,6 +142,9 @@ swapgs; \ sysretl +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(x) pushfq; popq %rax +#endif #else #define INTERRUPT_RETURN iret #define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit --- linux-4.14.0.orig/arch/x86/include/asm/kdebug.h +++ linux-4.14.0/arch/x86/include/asm/kdebug.h @@ -26,6 +26,7 @@ extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); +extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); --- linux-4.14.0.orig/arch/x86/include/asm/kvm_host.h +++ linux-4.14.0/arch/x86/include/asm/kvm_host.h @@ -1426,4 +1426,7 @@ #endif } +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + #endif /* _ASM_X86_KVM_HOST_H */ --- linux-4.14.0.orig/arch/x86/include/asm/mmu.h +++ linux-4.14.0/arch/x86/include/asm/mmu.h @@ -3,6 +3,7 @@ #define _ASM_X86_MMU_H #include +#include #include #include @@ -27,7 +28,8 @@ atomic64_t tlb_gen; #ifdef CONFIG_MODIFY_LDT_SYSCALL - struct ldt_struct *ldt; + struct rw_semaphore ldt_usr_sem; + struct ldt_struct *ldt; #endif #ifdef CONFIG_X86_64 --- linux-4.14.0.orig/arch/x86/include/asm/mmu_context.h +++ linux-4.14.0/arch/x86/include/asm/mmu_context.h @@ -50,22 +50,53 @@ * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ - struct desc_struct *entries; - unsigned int nr_entries; + struct desc_struct *entries; + unsigned int nr_entries; + + /* + * If PTI is in use, then the entries array is not mapped while we're + * in user mode. The whole array will be aliased at the addressed + * given by ldt_slot_va(slot). We use two slots so that we can allocate + * and map, and enable a new LDT without invalidating the mapping + * of an older, still-in-use LDT. + * + * slot will be -1 if this LDT doesn't have an alias mapping. + */ + int slot; }; +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ +#ifdef CONFIG_X86_64 + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +#else + BUG(); +#endif +} + /* * Used for LDT copy/destruction. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm); +static inline void init_new_context_ldt(struct mm_struct *mm) +{ + mm->context.ldt = NULL; + init_rwsem(&mm->context.ldt_usr_sem); +} +int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); +void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ -static inline int init_new_context_ldt(struct task_struct *tsk, - struct mm_struct *mm) +static inline void init_new_context_ldt(struct mm_struct *mm) { } +static inline int ldt_dup_context(struct mm_struct *oldmm, + struct mm_struct *mm) { return 0; } -static inline void destroy_context_ldt(struct mm_struct *mm) {} +static inline void destroy_context_ldt(struct mm_struct *mm) { } +static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif static inline void load_mm_ldt(struct mm_struct *mm) @@ -73,8 +104,8 @@ #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - /* lockless_dereference synchronizes with smp_store_release */ - ldt = lockless_dereference(mm->context.ldt); + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all @@ -90,10 +121,31 @@ * that we can see. */ - if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->nr_entries); - else + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { clear_LDT(); + } #else clear_LDT(); #endif @@ -132,18 +184,21 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + mutex_init(&mm->context.lock); + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } - #endif - return init_new_context_ldt(tsk, mm); +#endif + init_new_context_ldt(mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) { @@ -176,15 +231,16 @@ } while (0) #endif -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { paravirt_arch_dup_mmap(oldmm, mm); + return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); + ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 @@ -282,33 +338,6 @@ } /* - * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID - * bits. This serves two purposes. It prevents a nasty situation in - * which PCID-unaware code saves CR3, loads some other value (with PCID - * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if - * the saved ASID was nonzero. It also means that any bugs involving - * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger - * deterministically. - */ - -static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) -{ - if (static_cpu_has(X86_FEATURE_PCID)) { - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1); - } else { - VM_WARN_ON_ONCE(asid != 0); - return __sme_pa(mm->pgd); - } -} - -static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) -{ - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; -} - -/* * This can be used from process context to figure out what the value of * CR3 is without needing to do a (slow) __read_cr3(). * @@ -317,7 +346,7 @@ */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd, this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ --- linux-4.14.0.orig/arch/x86/include/asm/module.h +++ linux-4.14.0/arch/x86/include/asm/module.h @@ -6,7 +6,7 @@ #include struct mod_arch_specific { -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; --- linux-4.14.0.orig/arch/x86/include/asm/paravirt.h +++ linux-4.14.0/arch/x86/include/asm/paravirt.h @@ -16,10 +16,9 @@ #include #include -static inline void load_sp0(struct tss_struct *tss, - struct thread_struct *thread) +static inline void load_sp0(unsigned long sp0) { - PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread); + PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0); } /* The paravirtualized CPUID instruction. */ @@ -928,6 +927,15 @@ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(clobbers) \ + PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +#endif + #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ --- linux-4.14.0.orig/arch/x86/include/asm/paravirt_types.h +++ linux-4.14.0/arch/x86/include/asm/paravirt_types.h @@ -134,7 +134,7 @@ void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries); void (*free_ldt)(struct desc_struct *ldt, unsigned entries); - void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t); + void (*load_sp0)(unsigned long sp0); void (*set_iopl_mask)(unsigned mask); --- linux-4.14.0.orig/arch/x86/include/asm/percpu.h +++ linux-4.14.0/arch/x86/include/asm/percpu.h @@ -526,7 +526,7 @@ { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1\n\t" + asm volatile("bt "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); --- linux-4.14.0.orig/arch/x86/include/asm/pgalloc.h +++ linux-4.14.0/arch/x86/include/asm/pgalloc.h @@ -30,6 +30,17 @@ */ extern gfp_t __userpte_alloc_gfp; +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Instead of one PGD, we acquire two PGDs. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ +#define PGD_ALLOCATION_ORDER 1 +#else +#define PGD_ALLOCATION_ORDER 0 +#endif + /* * Allocate and free page tables. */ --- linux-4.14.0.orig/arch/x86/include/asm/pgtable.h +++ linux-4.14.0/arch/x86/include/asm/pgtable.h @@ -28,6 +28,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); void ptdump_walk_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX @@ -846,7 +847,12 @@ static inline int p4d_bad(p4d_t p4d) { - return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; + unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; + + if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ @@ -880,7 +886,12 @@ static inline int pgd_bad(pgd_t pgd) { - return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE; + unsigned long ignore_flags = _PAGE_USER; + + if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) @@ -909,7 +920,11 @@ * pgd_offset() returns a (pgd_t *) * pgd_index() is used get the offset into the pgd page's array of pgd_t's; */ -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address))) +#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address))) +/* + * a shortcut to get a pgd_t in a given mm + */ +#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's @@ -1093,6 +1108,12 @@ clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); } +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return pud_flags(pud) & _PAGE_RW; +} + /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * @@ -1105,7 +1126,14 @@ */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { - memcpy(dst, src, count * sizeof(pgd_t)); + memcpy(dst, src, count * sizeof(pgd_t)); +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + /* Clone the user space pgd as well */ + memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), + count * sizeof(pgd_t)); +#endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) --- linux-4.14.0.orig/arch/x86/include/asm/pgtable_32_types.h +++ linux-4.14.0/arch/x86/include/asm/pgtable_32_types.h @@ -38,13 +38,22 @@ #define LAST_PKMAP 1024 #endif -#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \ - & PMD_MASK) +/* + * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c + * to avoid include recursion hell + */ +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) + +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) + +#define PKMAP_BASE \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) #else -# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE) +# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE) #endif #define MODULES_VADDR VMALLOC_START --- linux-4.14.0.orig/arch/x86/include/asm/pgtable_64.h +++ linux-4.14.0/arch/x86/include/asm/pgtable_64.h @@ -131,9 +131,97 @@ #endif } +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and + * the user one is in the last 4k. To switch between them, you + * just need to flip the 12th bit in their addresses. + */ +#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT + +/* + * This generates better code than the inline assembly in + * __set_bit(). + */ +static inline void *ptr_set_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr |= BIT(bit); + return (void *)__ptr; +} +static inline void *ptr_clear_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr &= ~BIT(bit); + return (void *)__ptr; +} + +static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) +{ + return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) +{ + return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) +{ + return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) +{ + return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * + * Returns true for parts of the PGD that map userspace and + * false for the parts that map the kernel. + */ +static inline bool pgdp_maps_userspace(void *__ptr) +{ + unsigned long ptr = (unsigned long)__ptr; + + return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2); +} + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd); + +/* + * Take a PGD location (pgdp) and a pgd value that needs to be set there. + * Populates the user and returns the resulting PGD that must be set in + * the kernel copy of the page tables. + */ +static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return pgd; + return __pti_set_user_pgd(pgdp, pgd); +} +#else +static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +#endif + static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { +#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL) + p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd); +#else *p4dp = p4d; +#endif } static inline void native_p4d_clear(p4d_t *p4d) @@ -147,7 +235,11 @@ static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + *pgdp = pti_set_user_pgd(pgdp, pgd); +#else *pgdp = pgd; +#endif } static inline void native_pgd_clear(pgd_t *pgd) --- linux-4.14.0.orig/arch/x86/include/asm/pgtable_64_types.h +++ linux-4.14.0/arch/x86/include/asm/pgtable_64_types.h @@ -76,32 +76,45 @@ #define PGDIR_MASK (~(PGDIR_SIZE - 1)) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ -#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) + #ifdef CONFIG_X86_5LEVEL -#define VMALLOC_SIZE_TB _AC(16384, UL) -#define __VMALLOC_BASE _AC(0xff92000000000000, UL) -#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +# define VMALLOC_SIZE_TB _AC(12800, UL) +# define __VMALLOC_BASE _AC(0xffa0000000000000, UL) +# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +# define LDT_PGD_ENTRY _AC(-112, UL) +# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #else -#define VMALLOC_SIZE_TB _AC(32, UL) -#define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +# define VMALLOC_SIZE_TB _AC(32, UL) +# define __VMALLOC_BASE _AC(0xffffc90000000000, UL) +# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +# define LDT_PGD_ENTRY _AC(-4, UL) +# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #endif + #ifdef CONFIG_RANDOMIZE_MEMORY -#define VMALLOC_START vmalloc_base -#define VMEMMAP_START vmemmap_base +# define VMALLOC_START vmalloc_base +# define VMEMMAP_START vmemmap_base #else -#define VMALLOC_START __VMALLOC_BASE -#define VMEMMAP_START __VMEMMAP_BASE +# define VMALLOC_START __VMALLOC_BASE +# define VMEMMAP_START __VMEMMAP_BASE #endif /* CONFIG_RANDOMIZE_MEMORY */ -#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) -#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) + +#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) + +#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) /* The module sections ends with the start of the fixmap */ -#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) -#define MODULES_LEN (MODULES_END - MODULES_VADDR) -#define ESPFIX_PGD_ENTRY _AC(-2, UL) -#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) -#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) -#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) +#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) +#define MODULES_LEN (MODULES_END - MODULES_VADDR) + +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) + +#define CPU_ENTRY_AREA_PGD _AC(-3, UL) +#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT) + +#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) +#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) #define EARLY_DYNAMIC_PAGE_TABLES 64 --- linux-4.14.0.orig/arch/x86/include/asm/pgtable_types.h +++ linux-4.14.0/arch/x86/include/asm/pgtable_types.h @@ -200,10 +200,9 @@ #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ _PAGE_DIRTY | _PAGE_ENC) +#define _PAGE_TABLE (_KERNPG_TABLE | _PAGE_USER) #define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) #define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) --- linux-4.14.0.orig/arch/x86/include/asm/processor-flags.h +++ linux-4.14.0/arch/x86/include/asm/processor-flags.h @@ -38,6 +38,11 @@ #define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull) #define CR3_PCID_MASK 0xFFFull #define CR3_NOFLUSH BIT_ULL(63) + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_SWITCH_BIT 11 +#endif + #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save --- linux-4.14.0.orig/arch/x86/include/asm/processor.h +++ linux-4.14.0/arch/x86/include/asm/processor.h @@ -162,9 +162,9 @@ extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; -extern struct tss_struct doublefault_tss; -extern __u32 cpu_caps_cleared[NCAPINTS]; -extern __u32 cpu_caps_set[NCAPINTS]; +extern struct x86_hw_tss doublefault_tss; +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); @@ -252,6 +252,11 @@ write_cr3(__sme_pa(pgdir)); } +/* + * Note that while the legacy 'TSS' name comes from 'Task State Segment', + * on modern x86 CPUs the TSS also holds information important to 64-bit mode, + * unrelated to the task-switch mechanism: + */ #ifdef CONFIG_X86_32 /* This is the TSS defined by the hardware. */ struct x86_hw_tss { @@ -304,7 +309,13 @@ struct x86_hw_tss { u32 reserved1; u64 sp0; + + /* + * We store cpu_current_top_of_stack in sp1 so it's always accessible. + * Linux does not use ring 1, so sp1 is not otherwise needed. + */ u64 sp1; + u64 sp2; u64 reserved2; u64 ist[7]; @@ -322,12 +333,22 @@ #define IO_BITMAP_BITS 65536 #define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) +#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 +struct entry_stack { + unsigned long words[64]; +}; + +struct entry_stack_page { + struct entry_stack stack; +} __aligned(PAGE_SIZE); + struct tss_struct { /* - * The hardware state: + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. */ struct x86_hw_tss x86_tss; @@ -338,18 +359,9 @@ * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __aligned(PAGE_SIZE); -#ifdef CONFIG_X86_32 - /* - * Space for the temporary SYSENTER stack. - */ - unsigned long SYSENTER_stack_canary; - unsigned long SYSENTER_stack[64]; -#endif - -} ____cacheline_aligned; - -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* * sizeof(unsigned long) coming from an extra "long" at the end @@ -363,6 +375,9 @@ #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#else +/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ +#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif /* @@ -431,7 +446,9 @@ struct thread_struct { /* Cached TLS descriptors: */ struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; +#ifdef CONFIG_X86_32 unsigned long sp0; +#endif unsigned long sp; #ifdef CONFIG_X86_32 unsigned long sysenter_cs; @@ -518,16 +535,9 @@ } static inline void -native_load_sp0(struct tss_struct *tss, struct thread_struct *thread) +native_load_sp0(unsigned long sp0) { - tss->x86_tss.sp0 = thread->sp0; -#ifdef CONFIG_X86_32 - /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) { - tss->x86_tss.ss1 = thread->sysenter_cs; - wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); - } -#endif + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static inline void native_swapgs(void) @@ -539,12 +549,18 @@ static inline unsigned long current_top_of_stack(void) { -#ifdef CONFIG_X86_64 - return this_cpu_read_stable(cpu_tss.x86_tss.sp0); -#else - /* sp0 on x86_32 is special in and around vm86 mode. */ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ return this_cpu_read_stable(cpu_current_top_of_stack); -#endif +} + +static inline bool on_thread_stack(void) +{ + return (unsigned long)(current_top_of_stack() - + current_stack_pointer) < THREAD_SIZE; } #ifdef CONFIG_PARAVIRT @@ -552,10 +568,9 @@ #else #define __cpuid native_cpuid -static inline void load_sp0(struct tss_struct *tss, - struct thread_struct *thread) +static inline void load_sp0(unsigned long sp0) { - native_load_sp0(tss, thread); + native_load_sp0(sp0); } #define set_iopl_mask native_set_iopl_mask @@ -804,6 +819,15 @@ #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ TOP_OF_KERNEL_STACK_PADDING) +#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1)) + +#define task_pt_regs(task) \ +({ \ + unsigned long __ptr = (unsigned long)task_stack_page(task); \ + __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ + ((struct pt_regs *)__ptr) - 1; \ +}) + #ifdef CONFIG_X86_32 /* * User space process size: 3GB (default). @@ -823,34 +847,26 @@ .addr_limit = KERNEL_DS, \ } -/* - * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. - * This is necessary to guarantee that the entire "struct pt_regs" - * is accessible even if the CPU haven't stored the SS/ESP registers - * on the stack (interrupt gate does not save these registers - * when switching to the same priv ring). - * Therefore beware: accessing the ss/esp fields of the - * "struct pt_regs" is possible, but they may contain the - * completely wrong values. - */ -#define task_pt_regs(task) \ -({ \ - unsigned long __ptr = (unsigned long)task_stack_page(task); \ - __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ - ((struct pt_regs *)__ptr) - 1; \ -}) - #define KSTK_ESP(task) (task_pt_regs(task)->sp) #else /* - * User space process size. 47bits minus one guard page. The guard - * page is necessary on Intel CPUs: if a SYSCALL instruction is at - * the highest possible canonical userspace address, then that - * syscall will enter the kernel with a non-canonical return - * address, and SYSRET will explode dangerously. We avoid this - * particular problem by preventing anything from being mapped - * at the maximum canonical address. + * User space process size. This is the first address outside the user range. + * There are a few constraints that determine this: + * + * On Intel CPUs, if a SYSCALL instruction is at the highest canonical + * address, then that syscall will enter the kernel with a + * non-canonical return address, and SYSRET will explode dangerously. + * We avoid this particular problem by preventing anything executable + * from being mapped at the maximum canonical address. + * + * On AMD CPUs in the Ryzen family, there's a nasty bug in which the + * CPUs malfunction if they execute code from the highest canonical page. + * They'll speculate right off the end of the canonical space, and + * bad things happen. This is worked around in the same way as the + * Intel problem. + * + * With page table isolation enabled, we map the LDT in ... [stay tuned] */ #define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) @@ -873,11 +889,9 @@ #define STACK_TOP_MAX TASK_SIZE_MAX #define INIT_THREAD { \ - .sp0 = TOP_OF_INIT_STACK, \ .addr_limit = KERNEL_DS, \ } -#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ --- linux-4.14.0.orig/arch/x86/include/asm/pti.h +++ linux-4.14.0/arch/x86/include/asm/pti.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _ASM_X86_PTI_H +#define _ASM_X86_PTI_H +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +extern void pti_init(void); +extern void pti_check_boottime_disable(void); +#else +static inline void pti_check_boottime_disable(void) { } +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_X86_PTI_H */ --- linux-4.14.0.orig/arch/x86/include/asm/ptrace.h +++ linux-4.14.0/arch/x86/include/asm/ptrace.h @@ -136,9 +136,9 @@ #endif } -#ifdef CONFIG_X86_64 static inline bool user_64bit_mode(struct pt_regs *regs) { +#ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT /* * On non-paravirt systems, this is the only long mode CPL 3 @@ -149,8 +149,12 @@ /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif +#else /* !CONFIG_X86_64 */ + return false; +#endif } +#ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp #endif --- linux-4.14.0.orig/arch/x86/include/asm/refcount.h +++ linux-4.14.0/arch/x86/include/asm/refcount.h @@ -15,7 +15,7 @@ * back to the regular execution flow in .text. */ #define _REFCOUNT_EXCEPTION \ - ".pushsection .text.unlikely\n" \ + ".pushsection .text..refcount\n" \ "111:\tlea %[counter], %%" _ASM_CX "\n" \ "112:\t" ASM_UD0 "\n" \ ASM_UNREACHABLE \ --- linux-4.14.0.orig/arch/x86/include/asm/rmwcc.h +++ linux-4.14.0/arch/x86/include/asm/rmwcc.h @@ -29,7 +29,7 @@ #define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ bool c; \ - asm volatile (fullop ";" CC_SET(cc) \ + asm volatile (fullop CC_SET(cc) \ : [counter] "+m" (var), CC_OUT(cc) (c) \ : __VA_ARGS__ : clobbers); \ return c; \ --- linux-4.14.0.orig/arch/x86/include/asm/stacktrace.h +++ linux-4.14.0/arch/x86/include/asm/stacktrace.h @@ -16,6 +16,7 @@ STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, + STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -28,6 +29,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); +bool in_entry_stack(unsigned long *stack, struct stack_info *info); + int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); --- linux-4.14.0.orig/arch/x86/include/asm/switch_to.h +++ linux-4.14.0/arch/x86/include/asm/switch_to.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_SWITCH_TO_H #define _ASM_X86_SWITCH_TO_H +#include + struct task_struct; /* one of the stranger aspects of C forward declarations */ struct task_struct *__switch_to_asm(struct task_struct *prev, @@ -73,4 +75,28 @@ ((last) = __switch_to_asm((prev), (next))); \ } while (0) +#ifdef CONFIG_X86_32 +static inline void refresh_sysenter_cs(struct thread_struct *thread) +{ + /* Only happens when SEP is enabled, no need to test "SEP"arately: */ + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) + return; + + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); + wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); +} +#endif + +/* This is used when switching tasks or entering/exiting vm86 mode. */ +static inline void update_sp0(struct task_struct *task) +{ + /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ +#ifdef CONFIG_X86_32 + load_sp0(task->thread.sp0); +#else + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task_top_of_stack(task)); +#endif +} + #endif /* _ASM_X86_SWITCH_TO_H */ --- linux-4.14.0.orig/arch/x86/include/asm/syscalls.h +++ linux-4.14.0/arch/x86/include/asm/syscalls.h @@ -21,7 +21,7 @@ asmlinkage long sys_iopl(unsigned int); /* kernel/ldt.c */ -asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); +asmlinkage long sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ asmlinkage long sys_rt_sigreturn(void); --- linux-4.14.0.orig/arch/x86/include/asm/thread_info.h +++ linux-4.14.0/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) #endif #endif --- linux-4.14.0.orig/arch/x86/include/asm/tlbflush.h +++ linux-4.14.0/arch/x86/include/asm/tlbflush.h @@ -9,70 +9,130 @@ #include #include #include +#include +#include +#include -static inline void __invpcid(unsigned long pcid, unsigned long addr, - unsigned long type) -{ - struct { u64 d[2]; } desc = { { pcid, addr } }; +/* + * The x86 feature is called PCID (Process Context IDentifier). It is similar + * to what is traditionally called ASID on the RISC processors. + * + * We don't use the traditional ASID implementation, where each process/mm gets + * its own ASID and flush/restart when we run out of ASID space. + * + * Instead we have a small per-cpu array of ASIDs and cache the last few mm's + * that came by on this CPU, allowing cheaper switch_mm between processes on + * this CPU. + * + * We end up with different spaces for different things. To avoid confusion we + * use different names for each of them: + * + * ASID - [0, TLB_NR_DYN_ASIDS-1] + * the canonical identifier for an mm + * + * kPCID - [1, TLB_NR_DYN_ASIDS] + * the value we write into the PCID part of CR3; corresponds to the + * ASID+1, because PCID 0 is special. + * + * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS] + * for KPTI each mm has two address spaces and thus needs two + * PCID values, but we can still do with a single ASID denomination + * for each mm. Corresponds to kPCID + 2048. + * + */ - /* - * The memory clobber is because the whole point is to invalidate - * stale TLB entries and, especially if we're flushing global - * mappings, we don't want the compiler to reorder any subsequent - * memory accesses before the TLB flush. - * - * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and - * invpcid (%rcx), %rax in long mode. - */ - asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01" - : : "m" (desc), "a" (type), "c" (&desc) : "memory"); -} +/* There are 12 bits of space for ASIDS in CR3 */ +#define CR3_HW_ASID_BITS 12 + +/* + * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for + * user/kernel switches + */ +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define PTI_CONSUMED_PCID_BITS 1 +#else +# define PTI_CONSUMED_PCID_BITS 0 +#endif -#define INVPCID_TYPE_INDIV_ADDR 0 -#define INVPCID_TYPE_SINGLE_CTXT 1 -#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 -#define INVPCID_TYPE_ALL_NON_GLOBAL 3 +#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS) -/* Flush all mappings for a given pcid and addr, not including globals. */ -static inline void invpcid_flush_one(unsigned long pcid, - unsigned long addr) -{ - __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); -} +/* + * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account + * for them being zero-based. Another -1 is because PCID 0 is reserved for + * use by non-PCID-aware users. + */ +#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2) + +/* + * 6 because 6 should be plenty and struct tlb_state will fit in two cache + * lines. + */ +#define TLB_NR_DYN_ASIDS 6 -/* Flush all mappings for a given PCID, not including globals. */ -static inline void invpcid_flush_single_context(unsigned long pcid) +/* + * Given @asid, compute kPCID + */ +static inline u16 kern_pcid(u16 asid) { - __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); + VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * Make sure that the dynamic ASID space does not confict with the + * bit we are using to switch between user and kernel ASIDs. + */ + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT)); + + /* + * The ASID being passed in here should have respected the + * MAX_ASID_AVAILABLE and thus never have the switch bit set. + */ + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT)); +#endif + /* + * The dynamically-assigned ASIDs that get passed in are small + * (context.tlb_gen); - smp_mb__after_atomic(); - - return new_tlb_gen; + VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID)); + return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH; } #ifdef CONFIG_PARAVIRT @@ -99,12 +159,6 @@ return !static_cpu_has(X86_FEATURE_PCID); } -/* - * 6 because 6 should be plenty and struct tlb_state will fit in - * two cache lines. - */ -#define TLB_NR_DYN_ASIDS 6 - struct tlb_context { u64 ctx_id; u64 tlb_gen; @@ -139,6 +193,24 @@ bool is_lazy; /* + * If set we changed the page tables in such a way that we + * needed an invalidation of all contexts (aka. PCIDs / ASIDs). + * This tells us to go invalidate all the non-loaded ctxs[] + * on the next context switch. + * + * The current ctx was kept up-to-date as it ran and does not + * need to be invalidated. + */ + bool invalidate_other; + + /* + * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate + * the corresponding user PCID needs a flush next time we + * switch to it; see SWITCH_TO_USER_CR3. + */ + unsigned short user_pcid_flush_mask; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ @@ -216,6 +288,14 @@ } /* + * Mark all other ASIDs as invalid, preserves the current. + */ +static inline void invalidate_other_asid(void) +{ + this_cpu_write(cpu_tlbstate.invalidate_other, true); +} + +/* * Save some of cr4 feature set we're using (e.g. Pentium 4MB * enable and PPro Global page enable), so that any CPU's that boot * up after us can get the correct flags. This should only be used @@ -234,37 +314,63 @@ extern void initialize_tlbstate_and_flush(void); -static inline void __native_flush_tlb(void) +/* + * Given an ASID, flush the corresponding user ASID. We can delay this + * until the next time we switch to it. + * + * See SWITCH_TO_USER_CR3. + */ +static inline void invalidate_user_asid(u16 asid) { + /* There is no user ASID if address space separation is off */ + if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + return; + /* - * If current->mm == NULL then we borrow a mm which may change during a - * task switch and therefore we must not be preempted while we write CR3 - * back: + * We only have a single ASID if PCID is off and the CR3 + * write will have flushed it. */ - preempt_disable(); - native_write_cr3(__native_read_cr3()); - preempt_enable(); + if (!cpu_feature_enabled(X86_FEATURE_PCID)) + return; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + __set_bit(kern_pcid(asid), + (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask)); } -static inline void __native_flush_tlb_global_irq_disabled(void) +/* + * flush the entire current user mapping + */ +static inline void __native_flush_tlb(void) { - unsigned long cr4; + /* + * Preemption or interrupts must be disabled to protect the access + * to the per CPU variable and to prevent being preempted between + * read_cr3() and write_cr3(). + */ + WARN_ON_ONCE(preemptible()); - cr4 = this_cpu_read(cpu_tlbstate.cr4); - /* clear PGE */ - native_write_cr4(cr4 & ~X86_CR4_PGE); - /* write old PGE again and flush TLBs */ - native_write_cr4(cr4); + invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid)); + + /* If current->mm == NULL then the read_cr3() "borrows" an mm */ + native_write_cr3(__native_read_cr3()); } +/* + * flush everything + */ static inline void __native_flush_tlb_global(void) { - unsigned long flags; + unsigned long cr4, flags; if (static_cpu_has(X86_FEATURE_INVPCID)) { /* * Using INVPCID is considerably faster than a pair of writes * to CR4 sandwiched inside an IRQ flag save/restore. + * + * Note, this works with CR4.PCIDE=0 or 1. */ invpcid_flush_all(); return; @@ -277,36 +383,69 @@ */ raw_local_irq_save(flags); - __native_flush_tlb_global_irq_disabled(); + cr4 = this_cpu_read(cpu_tlbstate.cr4); + /* toggle PGE */ + native_write_cr4(cr4 ^ X86_CR4_PGE); + /* write old PGE again and flush TLBs */ + native_write_cr4(cr4); raw_local_irq_restore(flags); } +/* + * flush one page in the user mapping + */ static inline void __native_flush_tlb_single(unsigned long addr) { + u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + /* + * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1. + * Just use invalidate_user_asid() in case we are called early. + */ + if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) + invalidate_user_asid(loaded_mm_asid); + else + invpcid_flush_one(user_pcid(loaded_mm_asid), addr); } +/* + * flush everything + */ static inline void __flush_tlb_all(void) { - if (boot_cpu_has(X86_FEATURE_PGE)) + if (boot_cpu_has(X86_FEATURE_PGE)) { __flush_tlb_global(); - else + } else { + /* + * !PGE -> !PCID (setup_pcid()), thus every flush is total. + */ __flush_tlb(); - - /* - * Note: if we somehow had PCID but not PGE, then this wouldn't work -- - * we'd end up flushing kernel translations for the current ASID but - * we might fail to flush kernel translations for other cached ASIDs. - * - * To avoid this issue, we force PCID off if PGE is off. - */ + } } +/* + * flush one page in the kernel mapping + */ static inline void __flush_tlb_one(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + /* + * __flush_tlb_single() will have cleared the TLB entry for this ASID, + * but since kernel space is replicated across all, we must also + * invalidate all others. + */ + invalidate_other_asid(); } #define TLB_FLUSH_ALL -1UL @@ -367,6 +506,17 @@ void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info); +static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +{ + /* + * Bump the generation count. This also serves as a full barrier + * that synchronizes with switch_mm(): callers are required to order + * their read of mm_cpumask after their writes to the paging + * structures. + */ + return atomic64_inc_return(&mm->context.tlb_gen); +} + static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm) { --- linux-4.14.0.orig/arch/x86/include/asm/trace/fpu.h +++ linux-4.14.0/arch/x86/include/asm/trace/fpu.h @@ -34,11 +34,6 @@ ) ); -DEFINE_EVENT(x86_fpu, x86_fpu_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) @@ -73,11 +68,6 @@ TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); - -DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), --- linux-4.14.0.orig/arch/x86/include/asm/traps.h +++ linux-4.14.0/arch/x86/include/asm/traps.h @@ -38,9 +38,9 @@ #if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) asmlinkage void xen_divide_error(void); +asmlinkage void xen_xennmi(void); asmlinkage void xen_xendebug(void); asmlinkage void xen_xenint3(void); -asmlinkage void xen_nmi(void); asmlinkage void xen_overflow(void); asmlinkage void xen_bounds(void); asmlinkage void xen_invalid_op(void); @@ -75,7 +75,6 @@ dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); @@ -145,4 +144,22 @@ X86_TRAP_IRET = 32, /* 32, IRET Exception */ }; +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE = 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR = 1 << 4, + X86_PF_PK = 1 << 5, +}; #endif /* _ASM_X86_TRAPS_H */ --- linux-4.14.0.orig/arch/x86/include/asm/unwind.h +++ linux-4.14.0/arch/x86/include/asm/unwind.h @@ -7,17 +7,20 @@ #include #include +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) + struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; struct task_struct *task; int graph_idx; bool error; -#if defined(CONFIG_ORC_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs; -#elif defined(CONFIG_FRAME_POINTER_UNWINDER) +#elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; struct pt_regs *regs; @@ -51,22 +54,35 @@ __unwind_start(state, task, regs, first_frame); } -#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER) -static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) +/* + * If 'partial' returns true, only the iret frame registers are valid. + */ +static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, + bool *partial) { if (unwind_done(state)) return NULL; + if (partial) { +#ifdef CONFIG_UNWINDER_ORC + *partial = !state->full_regs; +#else + *partial = false; +#endif + } + return state->regs; } #else -static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) +static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, + bool *partial) { return NULL; } #endif -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); --- linux-4.14.0.orig/arch/x86/include/asm/vsyscall.h +++ linux-4.14.0/arch/x86/include/asm/vsyscall.h @@ -7,6 +7,7 @@ #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); +extern void set_vsyscall_pgtable_user_bits(pgd_t *root); /* * Called on instruction fetch fault in vsyscall page. --- linux-4.14.0.orig/arch/x86/include/asm/x86_init.h +++ linux-4.14.0/arch/x86/include/asm/x86_init.h @@ -115,6 +115,18 @@ }; /** + * struct x86_hyper_init - x86 hypervisor init functions + * @init_platform: platform setup + * @x2apic_available: X2APIC detection + * @init_mem_mapping: setup early mappings during init_mem_mapping() + */ +struct x86_hyper_init { + void (*init_platform)(void); + bool (*x2apic_available)(void); + void (*init_mem_mapping)(void); +}; + +/** * struct x86_init_ops - functions for platform specific setup * */ @@ -127,6 +139,7 @@ struct x86_init_timers timers; struct x86_init_iommu iommu; struct x86_init_pci pci; + struct x86_hyper_init hyper; }; /** @@ -200,6 +213,15 @@ }; /** + * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks + * + * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + */ +struct x86_hyper_runtime { + void (*pin_vcpu)(int cpu); +}; + +/** * struct x86_platform_ops - platform specific runtime functions * @calibrate_cpu: calibrate CPU * @calibrate_tsc: calibrate TSC, if different from CPU @@ -218,6 +240,7 @@ * possible in x86_early_init_platform_quirks() by * only using the current x86_hardware_subarch * semantics. + * @hyper: x86 hypervisor specific runtime callbacks */ struct x86_platform_ops { unsigned long (*calibrate_cpu)(void); @@ -233,6 +256,7 @@ void (*apic_post_init)(void); struct x86_legacy_features legacy; void (*set_legacy_features)(void); + struct x86_hyper_runtime hyper; }; struct pci_dev; --- linux-4.14.0.orig/arch/x86/include/uapi/asm/processor-flags.h +++ linux-4.14.0/arch/x86/include/uapi/asm/processor-flags.h @@ -78,7 +78,12 @@ #define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) #define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ #define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) -#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ + +#define X86_CR3_PCID_BITS 12 +#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL)) + +#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ +#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) /* * Intel CPU features in CR4 @@ -152,5 +157,8 @@ #define CX86_ARR_BASE 0xc4 #define CX86_RCR_BASE 0xdc +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) #endif /* _UAPI_ASM_X86_PROCESSOR_FLAGS_H */ --- linux-4.14.0.orig/arch/x86/kernel/Makefile +++ linux-4.14.0/arch/x86/kernel/Makefile @@ -25,9 +25,9 @@ KASAN_SANITIZE_head$(BITS).o := n KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n -KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_paravirt.o := n -OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y @@ -128,9 +128,9 @@ obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o -obj-$(CONFIG_ORC_UNWINDER) += unwind_orc.o -obj-$(CONFIG_FRAME_POINTER_UNWINDER) += unwind_frame.o -obj-$(CONFIG_GUESS_UNWINDER) += unwind_guess.o +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o +obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o +obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o ### # 64 bit specific files --- linux-4.14.0.orig/arch/x86/kernel/apic/apic.c +++ linux-4.14.0/arch/x86/kernel/apic/apic.c @@ -1645,7 +1645,7 @@ * under KVM */ if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) { + !x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; --- linux-4.14.0.orig/arch/x86/kernel/apic/x2apic_uv_x.c +++ linux-4.14.0/arch/x86/kernel/apic/x2apic_uv_x.c @@ -920,9 +920,8 @@ /* * percpu heartbeat timer */ -static void uv_heartbeat(unsigned long ignored) +static void uv_heartbeat(struct timer_list *timer) { - struct timer_list *timer = &uv_scir_info->timer; unsigned char bits = uv_scir_info->state; /* Flip heartbeat bit: */ @@ -947,7 +946,7 @@ struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer; uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY); - setup_pinned_timer(timer, uv_heartbeat, cpu); + timer_setup(timer, uv_heartbeat, TIMER_PINNED); timer->expires = jiffies + SCIR_CPU_HB_INTERVAL; add_timer_on(timer, cpu); uv_cpu_scir_info(cpu)->enabled = 1; --- linux-4.14.0.orig/arch/x86/kernel/asm-offsets.c +++ linux-4.14.0/arch/x86/kernel/asm-offsets.c @@ -17,6 +17,7 @@ #include #include #include +#include #ifdef CONFIG_XEN #include @@ -93,4 +94,13 @@ BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + + /* TLB state for the entry code */ + OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); + + /* Layout info for cpu_entry_area */ + OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); + OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); + OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page); + DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); } --- linux-4.14.0.orig/arch/x86/kernel/asm-offsets_32.c +++ linux-4.14.0/arch/x86/kernel/asm-offsets_32.c @@ -47,13 +47,8 @@ BLANK(); /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - offsetofend(struct tss_struct, SYSENTER_stack)); - - /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + offsetofend(struct cpu_entry_area, entry_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); --- linux-4.14.0.orig/arch/x86/kernel/asm-offsets_64.c +++ linux-4.14.0/arch/x86/kernel/asm-offsets_64.c @@ -23,6 +23,9 @@ #ifdef CONFIG_PARAVIRT OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); +#ifdef CONFIG_DEBUG_ENTRY + OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl); +#endif BLANK(); #endif @@ -63,6 +66,7 @@ OFFSET(TSS_ist, tss_struct, x86_tss.ist); OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_CC_STACKPROTECTOR --- linux-4.14.0.orig/arch/x86/kernel/cpu/Makefile +++ linux-4.14.0/arch/x86/kernel/cpu/Makefile @@ -23,6 +23,7 @@ obj-y += match.o obj-y += bugs.o obj-$(CONFIG_CPU_FREQ) += aperfmperf.o +obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o --- linux-4.14.0.orig/arch/x86/kernel/cpu/amd.c +++ linux-4.14.0/arch/x86/kernel/cpu/amd.c @@ -804,8 +804,11 @@ case 0x17: init_amd_zn(c); break; } - /* Enable workaround for FXSAVE leak */ - if (c->x86 >= 6) + /* + * Enable workaround for FXSAVE leak on CPUs + * without a XSaveErPtr feature + */ + if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR))) set_cpu_bug(c, X86_BUG_FXSAVE_LEAK); cpu_detect_cache_sizes(c); --- linux-4.14.0.orig/arch/x86/kernel/cpu/common.c +++ linux-4.14.0/arch/x86/kernel/cpu/common.c @@ -452,8 +452,8 @@ return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -466,28 +466,23 @@ load_stack_canary_segment(); } -/* Setup the fixmap mapping only once per-processor */ -static inline void setup_fixmap_gdt(int cpu) -{ -#ifdef CONFIG_X86_64 - /* On 64-bit systems, we use a read-only fixmap GDT. */ - pgprot_t prot = PAGE_KERNEL_RO; -#else - /* - * On native 32-bit systems, the GDT cannot be read-only because - * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. - * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. - */ - pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? - PAGE_KERNEL_RO : PAGE_KERNEL; +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); #endif - __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); -} +#ifdef CONFIG_X86_64 +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; +#endif /* Load the original GDT from the per-cpu structure */ void load_direct_gdt(int cpu) @@ -723,7 +718,7 @@ { int i; - for (i = 0; i < NCAPINTS; i++) { + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; } @@ -903,6 +898,10 @@ } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + if (c->x86_vendor != X86_VENDOR_AMD) + setup_force_cpu_bug(X86_BUG_CPU_INSECURE); + fpu__init_system(c); #ifdef CONFIG_X86_32 @@ -1225,7 +1224,7 @@ return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1234,11 +1233,7 @@ tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1301,18 +1296,16 @@ pr_cont(")\n"); } -static __init int setup_disablecpuid(char *arg) +/* + * clearcpuid= was already parsed in fpu__init_parse_early_param. + * But we need to keep a dummy __setup around otherwise it would + * show up as an environment variable for init. + */ +static __init int setup_clearcpuid(char *arg) { - int bit; - - if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); - else - return 0; - return 1; } -__setup("clearcpuid=", setup_disablecpuid); +__setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, @@ -1334,25 +1327,22 @@ DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -/* - * Special IST stacks which the CPU switches to when it calls - * an IST-marked descriptor entry. Up to 7 stacks (hardware - * limit), all of them are 4K, except the debug stack which - * is 8K. - */ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ -}; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + if (static_cpu_has(X86_FEATURE_PTI)) + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); + else + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1363,7 +1353,7 @@ * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1507,7 +1497,7 @@ if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1546,7 +1536,7 @@ * set up and load the per-CPU TSS */ if (!oist->ist[0]) { - char *estacks = per_cpu(exception_stacks, cpu); + char *estacks = get_cpu_entry_area(cpu)->exception_stacks; for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; @@ -1557,7 +1547,7 @@ } } - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; /* * <= is required because the CPU will access up to @@ -1572,9 +1562,14 @@ initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, me); - load_sp0(t, ¤t->thread); - set_tss_desc(cpu, t); + /* + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. + */ + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); + load_mm_ldt(&init_mm); clear_all_debug_regs(); @@ -1585,7 +1580,6 @@ if (is_uv_system()) uv_cpu_init(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } @@ -1595,8 +1589,7 @@ { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); - struct thread_struct *thread = &curr->thread; + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); @@ -1627,12 +1620,16 @@ initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, curr); - load_sp0(t, thread); - set_tss_desc(cpu, t); + /* + * Initialize the TSS. Don't bother initializing sp0, as the initial + * task never enters user mode. + */ + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_mm_ldt(&init_mm); - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ @@ -1644,7 +1641,6 @@ fpu__init_cpu(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } #endif --- linux-4.14.0.orig/arch/x86/kernel/cpu/cpuid-deps.c +++ linux-4.14.0/arch/x86/kernel/cpu/cpuid-deps.c @@ -0,0 +1,121 @@ +/* Declare dependencies between CPUIDs */ +#include +#include +#include +#include + +struct cpuid_dep { + unsigned int feature; + unsigned int depends; +}; + +/* + * Table of CPUID features that depend on others. + * + * This only includes dependencies that can be usefully disabled, not + * features part of the base set (like FPU). + * + * Note this all is not __init / __initdata because it can be + * called from cpu hotplug. It shouldn't do anything in this case, + * but it's difficult to tell that to the init reference checker. + */ +const static struct cpuid_dep cpuid_deps[] = { + { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, + { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, + { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, + { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, + { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, + { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM2, X86_FEATURE_XMM }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, + { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, + { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, + { X86_FEATURE_AES, X86_FEATURE_XMM2 }, + { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, + { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + {} +}; + +static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature) +{ + /* + * Note: This could use the non atomic __*_bit() variants, but the + * rest of the cpufeature code uses atomics as well, so keep it for + * consistency. Cleanup all of it separately. + */ + if (!c) { + clear_cpu_cap(&boot_cpu_data, feature); + set_bit(feature, (unsigned long *)cpu_caps_cleared); + } else { + clear_bit(feature, (unsigned long *)c->x86_capability); + } +} + +/* Take the capabilities and the BUG bits into account */ +#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8) + +static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + DECLARE_BITMAP(disable, MAX_FEATURE_BITS); + const struct cpuid_dep *d; + bool changed; + + if (WARN_ON(feature >= MAX_FEATURE_BITS)) + return; + + clear_feature(c, feature); + + /* Collect all features to disable, handling dependencies */ + memset(disable, 0, sizeof(disable)); + __set_bit(feature, disable); + + /* Loop until we get a stable state. */ + do { + changed = false; + for (d = cpuid_deps; d->feature; d++) { + if (!test_bit(d->depends, disable)) + continue; + if (__test_and_set_bit(d->feature, disable)) + continue; + + changed = true; + clear_feature(c, d->feature); + } + } while (changed); +} + +void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + do_clear_cpu_cap(c, feature); +} + +void setup_clear_cpu_cap(unsigned int feature) +{ + do_clear_cpu_cap(NULL, feature); +} --- linux-4.14.0.orig/arch/x86/kernel/cpu/hypervisor.c +++ linux-4.14.0/arch/x86/kernel/cpu/hypervisor.c @@ -26,6 +26,12 @@ #include #include +extern const struct hypervisor_x86 x86_hyper_vmware; +extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_pv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; +extern const struct hypervisor_x86 x86_hyper_kvm; + static const __initconst struct hypervisor_x86 * const hypervisors[] = { #ifdef CONFIG_XEN_PV @@ -41,54 +47,52 @@ #endif }; -const struct hypervisor_x86 *x86_hyper; -EXPORT_SYMBOL(x86_hyper); +enum x86_hypervisor_type x86_hyper_type; +EXPORT_SYMBOL(x86_hyper_type); -static inline void __init +static inline const struct hypervisor_x86 * __init detect_hypervisor_vendor(void) { - const struct hypervisor_x86 *h, * const *p; + const struct hypervisor_x86 *h = NULL, * const *p; uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { - h = *p; - pri = h->detect(); - if (pri != 0 && pri > max_pri) { + pri = (*p)->detect(); + if (pri > max_pri) { max_pri = pri; - x86_hyper = h; + h = *p; } } - if (max_pri) - pr_info("Hypervisor detected: %s\n", x86_hyper->name); -} - -void __init init_hypervisor_platform(void) -{ - - detect_hypervisor_vendor(); + if (h) + pr_info("Hypervisor detected: %s\n", h->name); - if (!x86_hyper) - return; - - if (x86_hyper->init_platform) - x86_hyper->init_platform(); + return h; } -bool __init hypervisor_x2apic_available(void) +static void __init copy_array(const void *src, void *target, unsigned int size) { - return x86_hyper && - x86_hyper->x2apic_available && - x86_hyper->x2apic_available(); + unsigned int i, n = size / sizeof(void *); + const void * const *from = (const void * const *)src; + const void **to = (const void **)target; + + for (i = 0; i < n; i++) + if (from[i]) + to[i] = from[i]; } -void hypervisor_pin_vcpu(int cpu) +void __init init_hypervisor_platform(void) { - if (!x86_hyper) + const struct hypervisor_x86 *h; + + h = detect_hypervisor_vendor(); + + if (!h) return; - if (x86_hyper->pin_vcpu) - x86_hyper->pin_vcpu(cpu); - else - WARN_ONCE(1, "vcpu pinning requested but not supported!\n"); + copy_array(&h->init, &x86_init.hyper, sizeof(h->init)); + copy_array(&h->runtime, &x86_platform.hyper, sizeof(h->runtime)); + + x86_hyper_type = h->type; + x86_init.hyper.init_platform(); } --- linux-4.14.0.orig/arch/x86/kernel/cpu/intel_rdt.c +++ linux-4.14.0/arch/x86/kernel/cpu/intel_rdt.c @@ -267,6 +267,7 @@ r->num_closid = r_l3->num_closid / 2; r->cache.cbm_len = r_l3->cache.cbm_len; r->default_ctrl = r_l3->default_ctrl; + r->cache.shareable_bits = r_l3->cache.shareable_bits; r->data_width = (r->cache.cbm_len + 3) / 4; r->alloc_capable = true; /* --- linux-4.14.0.orig/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ linux-4.14.0/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1081,6 +1081,7 @@ struct dentry *dentry; int ret; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* * resctrl file system can only be mounted once. @@ -1130,12 +1131,12 @@ goto out_mondata; if (rdt_alloc_capable) - static_branch_enable(&rdt_alloc_enable_key); + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); if (rdt_mon_capable) - static_branch_enable(&rdt_mon_enable_key); + static_branch_enable_cpuslocked(&rdt_mon_enable_key); if (rdt_alloc_capable || rdt_mon_capable) - static_branch_enable(&rdt_enable_key); + static_branch_enable_cpuslocked(&rdt_enable_key); if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3]; @@ -1157,6 +1158,7 @@ cdp_disable(); out: mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return dentry; } @@ -1295,9 +1297,7 @@ kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ - get_online_cpus(); update_closid_rmid(cpu_online_mask, &rdtgroup_default); - put_online_cpus(); kernfs_remove(kn_info); kernfs_remove(kn_mongrp); @@ -1308,6 +1308,7 @@ { struct rdt_resource *r; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /*Put everything back to default values. */ @@ -1315,11 +1316,12 @@ reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); - static_branch_disable(&rdt_alloc_enable_key); - static_branch_disable(&rdt_mon_enable_key); - static_branch_disable(&rdt_enable_key); + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_disable_cpuslocked(&rdt_enable_key); kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } static struct file_system_type rdt_fs_type = { --- linux-4.14.0.orig/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ linux-4.14.0/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -245,6 +245,9 @@ if (m->status & MCI_STATUS_UC) { + if (ctx == IN_KERNEL) + return MCE_PANIC_SEVERITY; + /* * On older systems where overflow_recov flag is not present, we * should simply panic if an error overflow occurs. If @@ -255,10 +258,6 @@ if (mce_flags.smca) return mce_severity_amd_smca(m, ctx); - /* software can try to contain */ - if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - /* kill current process */ return MCE_AR_SEVERITY; } else { --- linux-4.14.0.orig/arch/x86/kernel/cpu/microcode/intel.c +++ linux-4.14.0/arch/x86/kernel/cpu/microcode/intel.c @@ -565,15 +565,6 @@ } #else -/* - * Flush global tlb. We only do this in x86_64 where paging has been enabled - * already and PGE should be enabled as well. - */ -static inline void flush_tlb_early(void) -{ - __native_flush_tlb_global_irq_disabled(); -} - static inline void print_ucode(struct ucode_cpu_info *uci) { struct microcode_intel *mc; @@ -602,10 +593,6 @@ if (rev != mc->hdr.rev) return -1; -#ifdef CONFIG_X86_64 - /* Flush global tlb. This is precaution. */ - flush_tlb_early(); -#endif uci->cpu_sig.rev = rev; if (early) --- linux-4.14.0.orig/arch/x86/kernel/cpu/mshyperv.c +++ linux-4.14.0/arch/x86/kernel/cpu/mshyperv.c @@ -254,9 +254,9 @@ #endif } -const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { +const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, - .init_platform = ms_hyperv_init_platform, + .type = X86_HYPER_MS_HYPERV, + .init.init_platform = ms_hyperv_init_platform, }; -EXPORT_SYMBOL(x86_hyper_ms_hyperv); --- linux-4.14.0.orig/arch/x86/kernel/cpu/vmware.c +++ linux-4.14.0/arch/x86/kernel/cpu/vmware.c @@ -205,10 +205,10 @@ (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; } -const __refconst struct hypervisor_x86 x86_hyper_vmware = { +const __initconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, - .init_platform = vmware_platform_setup, - .x2apic_available = vmware_legacy_x2apic_available, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, }; -EXPORT_SYMBOL(x86_hyper_vmware); --- linux-4.14.0.orig/arch/x86/kernel/doublefault.c +++ linux-4.14.0/arch/x86/kernel/doublefault.c @@ -50,25 +50,23 @@ cpu_relax(); } -struct tss_struct doublefault_tss __cacheline_aligned = { - .x86_tss = { - .sp0 = STACK_START, - .ss0 = __KERNEL_DS, - .ldt = 0, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, +struct x86_hw_tss doublefault_tss __cacheline_aligned = { + .sp0 = STACK_START, + .ss0 = __KERNEL_DS, + .ldt = 0, + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, - .ip = (unsigned long) doublefault_fn, - /* 0x2 bit is always set */ - .flags = X86_EFLAGS_SF | 0x2, - .sp = STACK_START, - .es = __USER_DS, - .cs = __KERNEL_CS, - .ss = __KERNEL_DS, - .ds = __USER_DS, - .fs = __KERNEL_PERCPU, + .ip = (unsigned long) doublefault_fn, + /* 0x2 bit is always set */ + .flags = X86_EFLAGS_SF | 0x2, + .sp = STACK_START, + .es = __USER_DS, + .cs = __KERNEL_CS, + .ss = __KERNEL_DS, + .ds = __USER_DS, + .fs = __KERNEL_PERCPU, - .__cr3 = __pa_nodebug(swapper_pg_dir), - } + .__cr3 = __pa_nodebug(swapper_pg_dir), }; /* dummy for do_double_fault() call */ --- linux-4.14.0.orig/arch/x86/kernel/dumpstack.c +++ linux-4.14.0/arch/x86/kernel/dumpstack.c @@ -18,6 +18,7 @@ #include #include +#include #include #include @@ -43,6 +44,24 @@ return true; } +bool in_entry_stack(unsigned long *stack, struct stack_info *info) +{ + struct entry_stack *ss = cpu_entry_stack(smp_processor_id()); + + void *begin = ss; + void *end = ss + 1; + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_ENTRY; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, char *log_lvl) { @@ -50,6 +69,39 @@ printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +void show_iret_regs(struct pt_regs *regs) +{ + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, + regs->sp, regs->flags); +} + +static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, + bool partial) +{ + /* + * These on_stack() checks aren't strictly necessary: the unwind code + * has already validated the 'regs' pointer. The checks are done for + * ordering reasons: if the registers are on the next stack, we don't + * want to print them out yet. Otherwise they'll be shown as part of + * the wrong stack. Later, when show_trace_log_lvl() switches to the + * next stack, this function will be called again with the same regs so + * they can be printed in the right context. + */ + if (!partial && on_stack(info, regs, sizeof(*regs))) { + __show_regs(regs, 0); + + } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, + IRET_FRAME_SIZE)) { + /* + * When an interrupt or exception occurs in entry code, the + * full pt_regs might not have been saved yet. In that case + * just print the iret frame. + */ + show_iret_regs(regs); + } +} + void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl) { @@ -57,11 +109,13 @@ struct stack_info stack_info = {0}; unsigned long visit_mask = 0; int graph_idx = 0; + bool partial; printk("%sCall Trace:\n", log_lvl); unwind_start(&state, task, regs, stack); stack = stack ? : get_stack_pointer(task, regs); + regs = unwind_get_entry_regs(&state, &partial); /* * Iterate through the stacks, starting with the current stack pointer. @@ -71,31 +125,35 @@ * - task stack * - interrupt stack * - HW exception stacks (double fault, nmi, debug, mce) + * - entry stack * - * x86-32 can have up to three stacks: + * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack + * - entry stack */ - for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; - /* - * If we overflowed the task stack into a guard page, jump back - * to the bottom of the usable stack. - */ - if (task_stack_page(task) - (void *)stack < PAGE_SIZE) - stack = task_stack_page(task); - - if (get_stack_info(stack, task, &stack_info, &visit_mask)) - break; + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) + break; + } stack_name = stack_type_name(stack_info.type); if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_if_on_stack(&stack_info, regs, partial); /* * Scan the stack, printing any text addresses we find. At the @@ -119,7 +177,7 @@ /* * Don't print regs->ip again if it was already printed - * by __show_regs() below. + * by show_regs_if_on_stack(). */ if (regs && stack == ®s->ip) goto next; @@ -154,9 +212,9 @@ unwind_next_frame(&state); /* if the frame has entry regs, print them */ - regs = unwind_get_entry_regs(&state); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + regs = unwind_get_entry_regs(&state, &partial); + if (regs) + show_regs_if_on_stack(&stack_info, regs, partial); } if (stack_name) @@ -252,11 +310,13 @@ unsigned long sp; #endif printk(KERN_DEFAULT - "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter, + "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter, IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", - IS_ENABLED(CONFIG_KASAN) ? " KASAN" : ""); + IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", + IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) --- linux-4.14.0.orig/arch/x86/kernel/dumpstack_32.c +++ linux-4.14.0/arch/x86/kernel/dumpstack_32.c @@ -26,6 +26,9 @@ if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; + if (type == STACK_TYPE_ENTRY) + return "ENTRY_TRAMPOLINE"; + return NULL; } @@ -93,6 +96,9 @@ if (task != current) goto unknown; + if (in_entry_stack(stack, info)) + goto recursion_check; + if (in_hardirq_stack(stack, info)) goto recursion_check; --- linux-4.14.0.orig/arch/x86/kernel/dumpstack_64.c +++ linux-4.14.0/arch/x86/kernel/dumpstack_64.c @@ -37,6 +37,15 @@ if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_ENTRY) { + /* + * On 64-bit, we have a generic entry stack that we + * use for all the kernel entry points, including + * SYSENTER. + */ + return "ENTRY_TRAMPOLINE"; + } + if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -115,6 +124,9 @@ if (in_irq_stack(stack, info)) goto recursion_check; + if (in_entry_stack(stack, info)) + goto recursion_check; + goto unknown; recursion_check: --- linux-4.14.0.orig/arch/x86/kernel/fpu/init.c +++ linux-4.14.0/arch/x86/kernel/fpu/init.c @@ -249,6 +249,10 @@ */ static void __init fpu__init_parse_early_param(void) { + char arg[32]; + char *argptr = arg; + int bit; + if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); @@ -266,6 +270,13 @@ if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + if (cmdline_find_option(boot_command_line, "clearcpuid", arg, + sizeof(arg)) && + get_option(&argptr, &bit) && + bit >= 0 && + bit < NCAPINTS * 32) + setup_clear_cpu_cap(bit); } /* --- linux-4.14.0.orig/arch/x86/kernel/fpu/xstate.c +++ linux-4.14.0/arch/x86/kernel/fpu/xstate.c @@ -15,6 +15,7 @@ #include #include +#include /* * Although we spell it out in here, the Processor Trace @@ -36,6 +37,19 @@ "unknown xstate feature" , }; +static short xsave_cpuid_features[] __initdata = { + X86_FEATURE_FPU, + X86_FEATURE_XMM, + X86_FEATURE_AVX, + X86_FEATURE_MPX, + X86_FEATURE_MPX, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_INTEL_PT, + X86_FEATURE_PKU, +}; + /* * Mask of xstate features supported by the CPU and the kernel: */ @@ -59,26 +73,6 @@ void fpu__xstate_clear_all_cpu_caps(void) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVEC); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512IFMA); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); - setup_clear_cpu_cap(X86_FEATURE_AVX512DQ); - setup_clear_cpu_cap(X86_FEATURE_AVX512BW); - setup_clear_cpu_cap(X86_FEATURE_AVX512VL); - setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_XGETBV1); - setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI); - setup_clear_cpu_cap(X86_FEATURE_PKU); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); - setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* @@ -726,6 +720,7 @@ unsigned int eax, ebx, ecx, edx; static int on_boot_cpu __initdata = 1; int err; + int i; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -759,6 +754,14 @@ goto out_disable; } + /* + * Clear XSAVE features that are disabled in the normal CPUID. + */ + for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { + if (!boot_cpu_has(xsave_cpuid_features[i])) + xfeatures_mask &= ~BIT(i); + } + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ --- linux-4.14.0.orig/arch/x86/kernel/head_32.S +++ linux-4.14.0/arch/x86/kernel/head_32.S @@ -212,9 +212,6 @@ #endif .Ldefault_entry: -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 @@ -402,7 +399,7 @@ # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number --- linux-4.14.0.orig/arch/x86/kernel/head_64.S +++ linux-4.14.0/arch/x86/kernel/head_64.S @@ -38,11 +38,12 @@ * */ -#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) PGD_START_KERNEL = pgd_index(__START_KERNEL_map) +#endif L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -50,6 +51,7 @@ .code64 .globl startup_64 startup_64: + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -89,6 +91,7 @@ addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -133,6 +136,7 @@ movq $1f, %rax jmp *%rax 1: + UNWIND_HINT_EMPTY /* Check if nx is implemented */ movl $0x80000001, %eax @@ -150,9 +154,6 @@ 1: wrmsr /* Make changes effective */ /* Setup cr0 */ -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $CR0_STATE, %eax /* Make changes effective */ movq %rax, %cr0 @@ -235,7 +236,7 @@ pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(secondary_startup_64) +END(secondary_startup_64) #include "verify_cpu.S" @@ -247,6 +248,7 @@ */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp + UNWIND_HINT_EMPTY jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif @@ -266,26 +268,24 @@ .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS __FINITDATA -bad_address: - jmp bad_address - __INIT ENTRY(early_idt_handler_array) - # 104(%rsp) %rflags - # 96(%rsp) %cs - # 88(%rsp) %rip - # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 - pushq $0 # Dummy error code, to make stack frame uniform + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 + UNWIND_HINT_IRET_REGS + pushq $0 # Dummy error code, to make stack frame uniform + .else + UNWIND_HINT_IRET_REGS offset=8 .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common + UNWIND_HINT_IRET_REGS i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) + UNWIND_HINT_IRET_REGS offset=16 +END(early_idt_handler_array) early_idt_handler_common: /* @@ -313,6 +313,7 @@ pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS cmpq $14,%rsi /* Page fault? */ jnz 10f @@ -327,8 +328,8 @@ 20: decl early_recursion_flag(%rip) - jmp restore_regs_and_iret -ENDPROC(early_idt_handler_common) + jmp restore_regs_and_return_to_kernel +END(early_idt_handler_common) __INITDATA @@ -340,6 +341,27 @@ .balign PAGE_SIZE; \ GLOBAL(name) +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Each PGD needs to be 8k long and 8k aligned. We do not + * ever go out to userspace with these, so we do not + * strictly *need* the second page, but this allows us to + * have a single set_pgd() implementation that does not + * need to worry about whether it has 4k or 8k to work + * with. + * + * This ensures PGDs are 8k long: + */ +#define PTI_USER_PGD_FILL 512 +/* This ensures they are 8k-aligned: */ +#define NEXT_PGD_PAGE(name) \ + .balign 2 * PAGE_SIZE; \ +GLOBAL(name) +#else +#define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define PTI_USER_PGD_FILL 0 +#endif + /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ @@ -349,30 +371,29 @@ .endr __INITDATA -NEXT_PAGE(early_top_pgt) +NEXT_PGD_PAGE(early_top_pgt) .fill 511,8,0 #ifdef CONFIG_X86_5LEVEL .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif + .fill PTI_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 .data -#ifndef CONFIG_XEN -NEXT_PAGE(init_top_pgt) - .fill 512,8,0 -#else -NEXT_PAGE(init_top_pgt) +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) +NEXT_PGD_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC + .fill PTI_USER_PGD_FILL,8,0 NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC @@ -382,6 +403,10 @@ * Don't set NX because code runs from these pages. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +#else +NEXT_PGD_PAGE(init_top_pgt) + .fill 512,8,0 + .fill PTI_USER_PGD_FILL,8,0 #endif #ifdef CONFIG_X86_5LEVEL @@ -435,7 +460,7 @@ EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" - + __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE --- linux-4.14.0.orig/arch/x86/kernel/ioport.c +++ linux-4.14.0/arch/x86/kernel/ioport.c @@ -31,7 +31,7 @@ if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) return -EINVAL; - if (turn_on && !capable(CAP_SYS_RAWIO)) + if (turn_on && (!capable(CAP_SYS_RAWIO) || kernel_is_locked_down())) return -EPERM; /* @@ -67,7 +67,7 @@ * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(cpu_tss, get_cpu()); + tss = &per_cpu(cpu_tss_rw, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); @@ -121,7 +121,7 @@ return -EINVAL; /* Trying to gain more privileges? */ if (level > old) { - if (!capable(CAP_SYS_RAWIO)) + if (!capable(CAP_SYS_RAWIO) || kernel_is_locked_down()) return -EPERM; } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | --- linux-4.14.0.orig/arch/x86/kernel/irq.c +++ linux-4.14.0/arch/x86/kernel/irq.c @@ -219,18 +219,6 @@ /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - /* - * NB: Unlike exception entries, IRQ entries do not reliably - * handle context tracking in the low-level entry code. This is - * because syscall entries execute briefly with IRQs on before - * updating context tracking state, so we can take an IRQ from - * kernel mode with CONTEXT_USER. The low-level entry code only - * updates the context if we came from user mode, so we won't - * switch to CONTEXT_KERNEL. We'll fix that once the syscall - * code is cleaned up enough that we can cleanly defer enabling - * IRQs. - */ - entering_irq(); /* entering_irq() tells RCU that we're not quiescent. Check it. */ --- linux-4.14.0.orig/arch/x86/kernel/irq_64.c +++ linux-4.14.0/arch/x86/kernel/irq_64.c @@ -57,10 +57,10 @@ if (regs->sp >= estack_top && regs->sp <= estack_bottom) return; - WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n", + WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n", current->comm, curbase, regs->sp, irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom); + estack_top, estack_bottom, (void *)regs->ip); if (sysctl_panic_on_stackoverflow) panic("low stack detected by irq handler - check messages\n"); --- linux-4.14.0.orig/arch/x86/kernel/kexec-bzimage64.c +++ linux-4.14.0/arch/x86/kernel/kexec-bzimage64.c @@ -179,6 +179,7 @@ if (efi_enabled(EFI_OLD_MEMMAP)) return 0; + params->secure_boot = boot_params.secure_boot; ei->efi_loader_signature = current_ei->efi_loader_signature; ei->efi_systab = current_ei->efi_systab; ei->efi_systab_hi = current_ei->efi_systab_hi; --- linux-4.14.0.orig/arch/x86/kernel/kprobes/ftrace.c +++ linux-4.14.0/arch/x86/kernel/kprobes/ftrace.c @@ -26,7 +26,7 @@ #include "common.h" static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, +void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, unsigned long orig_ip) { /* @@ -41,20 +41,21 @@ __this_cpu_write(current_kprobe, NULL); if (orig_ip) regs->ip = orig_ip; - return 1; } int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; + if (kprobe_ftrace(p)) { + __skip_singlestep(p, regs, kcb, 0); + preempt_enable_no_resched(); + return 1; + } + return 0; } NOKPROBE_SYMBOL(skip_singlestep); -/* Ftrace callback handler for kprobes */ +/* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) { @@ -77,13 +78,17 @@ /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); + /* To emulate trap based kprobes, preempt_disable here */ + preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) + if (!p->pre_handler || !p->pre_handler(p, regs)) { __skip_singlestep(p, regs, kcb, orig_ip); + preempt_enable_no_resched(); + } /* * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. + * resets current kprobe, and keep preempt count +1. */ } end: --- linux-4.14.0.orig/arch/x86/kernel/kvm.c +++ linux-4.14.0/arch/x86/kernel/kvm.c @@ -544,12 +544,12 @@ return kvm_cpuid_base(); } -const struct hypervisor_x86 x86_hyper_kvm __refconst = { +const __initconst struct hypervisor_x86 x86_hyper_kvm = { .name = "KVM", .detect = kvm_detect, - .x2apic_available = kvm_para_available, + .type = X86_HYPER_KVM, + .init.x2apic_available = kvm_para_available, }; -EXPORT_SYMBOL_GPL(x86_hyper_kvm); static __init int activate_jump_labels(void) { --- linux-4.14.0.orig/arch/x86/kernel/ldt.c +++ linux-4.14.0/arch/x86/kernel/ldt.c @@ -5,6 +5,11 @@ * Copyright (C) 2002 Andi Kleen * * This handles calls from both 32bit and 64bit mode. + * + * Lock order: + * contex.ldt_usr_sem + * mmap_sem + * context.lock */ #include @@ -13,11 +18,13 @@ #include #include #include +#include #include #include #include #include +#include #include #include #include @@ -41,17 +48,15 @@ #endif } -/* context.lock is held for us, so we don't need any locking. */ +/* context.lock is held by the task which issued the smp function call */ static void flush_ldt(void *__mm) { struct mm_struct *mm = __mm; - mm_context_t *pc; if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = &mm->context; - set_ldt(pc->ldt->entries, pc->ldt->nr_entries); + load_mm_ldt(mm); refresh_ldt_segments(); } @@ -88,25 +93,143 @@ return NULL; } + /* The new LDT isn't aliased for PTI yet. */ + new_ldt->slot = -1; + new_ldt->nr_entries = num_entries; return new_ldt; } +/* + * If PTI is enabled, this maps the LDT into the kernelmode and + * usermode tables for the given mm. + * + * There is no corresponding unmap function. Even if the LDT is freed, we + * leave the PTEs around until the slot is reused or the mm is destroyed. + * This is harmless: the LDT is always in ordinary memory, and no one will + * access the freed slot. + * + * If we wanted to unmap freed LDTs, we'd also need to do a flush to make + * it useful, and the flush would slow down modify_ldt(). + */ +static int +map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + bool is_vmalloc, had_top_level_entry; + unsigned long va; + spinlock_t *ptl; + pgd_t *pgd; + int i; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return 0; + + /* + * Any given ldt_struct should have map_ldt_struct() called at most + * once. + */ + WARN_ON(ldt->slot != -1); + + /* + * Did we already have the top level entry allocated? We can't + * use pgd_none() for this because it doens't do anything on + * 4-level page table kernels. + */ + pgd = pgd_offset(mm, LDT_BASE_ADDR); + had_top_level_entry = (pgd->pgd != 0); + + is_vmalloc = is_vmalloc_addr(ldt->entries); + + for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + unsigned long offset = i << PAGE_SHIFT; + const void *src = (char *)ldt->entries + offset; + unsigned long pfn; + pte_t pte, *ptep; + + va = (unsigned long)ldt_slot_va(slot) + offset; + pfn = is_vmalloc ? vmalloc_to_pfn(src) : + page_to_pfn(virt_to_page(src)); + /* + * Treat the PTI LDT range as a *userspace* range. + * get_locked_pte() will allocate all needed pagetables + * and account for them in this mm. + */ + ptep = get_locked_pte(mm, va, &ptl); + if (!ptep) + return -ENOMEM; + /* + * Map it RO so the easy to find address is not a primary + * target via some kernel interface which misses a + * permission check. + */ + pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL)); + set_pte_at(mm, va, ptep, pte); + pte_unmap_unlock(ptep, ptl); + } + + if (mm->context.ldt) { + /* + * We already had an LDT. The top-level entry should already + * have been allocated and synchronized with the usermode + * tables. + */ + WARN_ON(!had_top_level_entry); + if (static_cpu_has(X86_FEATURE_PTI)) + WARN_ON(!kernel_to_user_pgdp(pgd)->pgd); + } else { + /* + * This is the first time we're mapping an LDT for this process. + * Sync the pgd to the usermode tables. + */ + WARN_ON(had_top_level_entry); + if (static_cpu_has(X86_FEATURE_PTI)) { + WARN_ON(kernel_to_user_pgdp(pgd)->pgd); + set_pgd(kernel_to_user_pgdp(pgd), *pgd); + } + } + + va = (unsigned long)ldt_slot_va(slot); + flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0); + + ldt->slot = slot; +#endif + return 0; +} + +static void free_ldt_pgtables(struct mm_struct *mm) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + struct mmu_gather tlb; + unsigned long start = LDT_BASE_ADDR; + unsigned long end = start + (1UL << PGDIR_SHIFT); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + tlb_gather_mmu(&tlb, mm, start, end); + free_pgd_range(&tlb, start, end, start, end); + tlb_finish_mmu(&tlb, start, end); +#endif +} + /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } -/* context.lock is held */ -static void install_ldt(struct mm_struct *current_mm, - struct ldt_struct *ldt) +static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt) { - /* Synchronizes with lockless_dereference in load_mm_ldt. */ - smp_store_release(¤t_mm->context.ldt, ldt); + mutex_lock(&mm->context.lock); - /* Activate the LDT for all CPUs using current_mm. */ - on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); + /* Synchronizes with READ_ONCE in load_mm_ldt. */ + smp_store_release(&mm->context.ldt, ldt); + + /* Activate the LDT for all CPUs using currents mm. */ + on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true); + + mutex_unlock(&mm->context.lock); } static void free_ldt_struct(struct ldt_struct *ldt) @@ -123,27 +246,20 @@ } /* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. + * Called on fork from arch_dup_mmap(). Just copy the current LDT state, + * the new task is not running, so nothing can be installed. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) +int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm) { struct ldt_struct *new_ldt; - struct mm_struct *old_mm; int retval = 0; - mutex_init(&mm->context.lock); - old_mm = current->mm; - if (!old_mm) { - mm->context.ldt = NULL; + if (!old_mm) return 0; - } mutex_lock(&old_mm->context.lock); - if (!old_mm->context.ldt) { - mm->context.ldt = NULL; + if (!old_mm->context.ldt) goto out_unlock; - } new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { @@ -155,6 +271,12 @@ new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); + retval = map_ldt_struct(mm, new_ldt, 0); + if (retval) { + free_ldt_pgtables(mm); + free_ldt_struct(new_ldt); + goto out_unlock; + } mm->context.ldt = new_ldt; out_unlock: @@ -173,13 +295,18 @@ mm->context.ldt = NULL; } +void ldt_arch_exit_mmap(struct mm_struct *mm) +{ + free_ldt_pgtables(mm); +} + static int read_ldt(void __user *ptr, unsigned long bytecount) { struct mm_struct *mm = current->mm; unsigned long entries_size; int retval; - mutex_lock(&mm->context.lock); + down_read(&mm->context.ldt_usr_sem); if (!mm->context.ldt) { retval = 0; @@ -208,7 +335,7 @@ retval = bytecount; out_unlock: - mutex_unlock(&mm->context.lock); + up_read(&mm->context.ldt_usr_sem); return retval; } @@ -268,7 +395,8 @@ ldt.avl = 0; } - mutex_lock(&mm->context.lock); + if (down_write_killable(&mm->context.ldt_usr_sem)) + return -EINTR; old_ldt = mm->context.ldt; old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; @@ -285,18 +413,37 @@ new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); + /* + * If we are using PTI, map the new LDT into the userspace pagetables. + * If there is already an LDT, use the other slot so that other CPUs + * will continue to use the old LDT until install_ldt() switches + * them over to the new LDT. + */ + error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0); + if (error) { + /* + * This only can fail for the first LDT setup. If an LDT is + * already installed then the PTE page is already + * populated. Mop up a half populated page table. + */ + if (!WARN_ON_ONCE(old_ldt)) + free_ldt_pgtables(mm); + free_ldt_struct(new_ldt); + goto out_unlock; + } + install_ldt(mm, new_ldt); free_ldt_struct(old_ldt); error = 0; out_unlock: - mutex_unlock(&mm->context.lock); + up_write(&mm->context.ldt_usr_sem); out: return error; } -asmlinkage int sys_modify_ldt(int func, void __user *ptr, - unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { int ret = -ENOSYS; @@ -314,5 +461,14 @@ ret = write_ldt(ptr, bytecount, 0); break; } - return ret; + /* + * The SYSCALL_DEFINE() macros give us an 'unsigned long' + * return type, but tht ABI for sys_modify_ldt() expects + * 'int'. This cast gives us an int-sized value in %rax + * for the return code. The 'unsigned' is necessary so + * the compiler does not try to sign-extend the negative + * return codes into the high half of the register when + * taking the value from int->long. + */ + return (unsigned int)ret; } --- linux-4.14.0.orig/arch/x86/kernel/machine_kexec_32.c +++ linux-4.14.0/arch/x86/kernel/machine_kexec_32.c @@ -48,8 +48,6 @@ "\tmovl $"STR(__KERNEL_DS)",%%eax\n" "\tmovl %%eax,%%ds\n" "\tmovl %%eax,%%es\n" - "\tmovl %%eax,%%fs\n" - "\tmovl %%eax,%%gs\n" "\tmovl %%eax,%%ss\n" : : : "eax", "memory"); #undef STR @@ -232,8 +230,8 @@ * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0), 0); idt_invalidate(phys_to_virt(0)); + set_gdt(phys_to_virt(0), 0); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, --- linux-4.14.0.orig/arch/x86/kernel/mpparse.c +++ linux-4.14.0/arch/x86/kernel/mpparse.c @@ -431,6 +431,7 @@ } static unsigned long mpf_base; +static bool mpf_found; static unsigned long __init get_mpc_size(unsigned long physptr) { @@ -504,7 +505,7 @@ if (!smp_found_config) return; - if (!mpf_base) + if (!mpf_found) return; if (acpi_lapic && early) @@ -593,6 +594,7 @@ smp_found_config = 1; #endif mpf_base = base; + mpf_found = true; pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", base, base + sizeof(*mpf) - 1, mpf); @@ -858,7 +860,7 @@ if (!enable_update_mptable) return 0; - if (!mpf_base) + if (!mpf_found) return 0; mpf = early_memremap(mpf_base, sizeof(*mpf)); --- linux-4.14.0.orig/arch/x86/kernel/msr.c +++ linux-4.14.0/arch/x86/kernel/msr.c @@ -84,6 +84,9 @@ int err = 0; ssize_t bytes = 0; + if (kernel_is_locked_down()) + return -EPERM; + if (count % 8) return -EINVAL; /* Invalid chunk size */ @@ -131,6 +134,10 @@ err = -EBADF; break; } + if (kernel_is_locked_down()) { + err = -EPERM; + break; + } if (copy_from_user(®s, uregs, sizeof regs)) { err = -EFAULT; break; --- linux-4.14.0.orig/arch/x86/kernel/paravirt_patch_64.c +++ linux-4.14.0/arch/x86/kernel/paravirt_patch_64.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); @@ -60,7 +59,6 @@ PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): --- linux-4.14.0.orig/arch/x86/kernel/process.c +++ linux-4.14.0/arch/x86/kernel/process.c @@ -47,9 +47,25 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { .x86_tss = { - .sp0 = TOP_OF_INIT_STACK, + /* + * .sp0 is only used when entering ring 0 from a lower + * privilege level. Since the init task never runs anything + * but ring 0 code, there is no need for a valid value here. + * Poison it. + */ + .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, + +#ifdef CONFIG_X86_64 + /* + * .sp1 is cpu_current_top_of_stack. The init task never + * runs user code, but cpu_current_top_of_stack should still + * be well defined before the first context switch. + */ + .sp1 = TOP_OF_INIT_STACK, +#endif + #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, @@ -65,11 +81,8 @@ */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif -#ifdef CONFIG_X86_32 - .SYSENTER_stack_canary = STACK_END_MAGIC, -#endif }; -EXPORT_PER_CPU_SYMBOL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); DEFINE_PER_CPU(bool, __tss_limit_invalid); EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); @@ -98,7 +111,7 @@ struct fpu *fpu = &t->fpu; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); --- linux-4.14.0.orig/arch/x86/kernel/process_32.c +++ linux-4.14.0/arch/x86/kernel/process_32.c @@ -234,7 +234,7 @@ struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ @@ -284,9 +284,11 @@ /* * Reload esp0 and cpu_current_top_of_stack. This changes - * current_thread_info(). + * current_thread_info(). Refresh the SYSENTER configuration in + * case prev or next is vm86. */ - load_sp0(tss, next); + update_sp0(next_p); + refresh_sysenter_cs(next); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); --- linux-4.14.0.orig/arch/x86/kernel/process_64.c +++ linux-4.14.0/arch/x86/kernel/process_64.c @@ -69,9 +69,8 @@ unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); - printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, - regs->sp, regs->flags); + show_iret_regs(regs); + if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else @@ -88,6 +87,9 @@ printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); + if (!all) + return; + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); @@ -98,9 +100,6 @@ rdmsrl(MSR_GS_BASE, gs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - if (!all) - return; - cr0 = read_cr0(); cr2 = read_cr2(); cr3 = __read_cr3(); @@ -274,7 +273,6 @@ struct inactive_task_frame *frame; struct task_struct *me = current; - p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; @@ -401,7 +399,7 @@ struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); @@ -463,9 +461,10 @@ * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); + this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); - /* Reload esp0 and ss1. This changes current_thread_info(). */ - load_sp0(tss, next); + /* Reload sp0. */ + update_sp0(next_p); /* * Now maybe reload the debug registers and handle I/O bitmaps --- linux-4.14.0.orig/arch/x86/kernel/reboot.c +++ linux-4.14.0/arch/x86/kernel/reboot.c @@ -457,7 +457,46 @@ DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), }, }, - + { /* Handle problems with rebooting on the Latitude E6520. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6520"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 790. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 790", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 790"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 990. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + }, + }, + { /* Handle problems with rebooting on the Latitude E6220. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6220", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6220"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 390. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 390", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 390"), + }, + }, { } }; --- linux-4.14.0.orig/arch/x86/kernel/setup.c +++ linux-4.14.0/arch/x86/kernel/setup.c @@ -70,6 +70,12 @@ #include #include #include +#include + +#include +#include +#include +#include #include #include