pax_global_header00006660000000000000000000000064127041365170014520gustar00rootroot0000000000000052 comment=113198d8918272e41a58aa09a7ac7dd1e0435417 rasdaemon-0.5.8/000077500000000000000000000000001270413651700135035ustar00rootroot00000000000000rasdaemon-0.5.8/.gitignore000066400000000000000000000005151270413651700154740ustar00rootroot00000000000000.deps/ autom4te.cache/ misc/rasdaemon.spec misc/ras-mc-ctl.service misc/rasdaemon.service Makefile Makefile.in config.h config.h.in config.h.in~ stamp-h1 aclocal.m4 config.guess config.log config.status config.sub configure depcomp install-sh libtool ltmain.sh missing rasdaemon *.o *.c~ *.h~ rasdaemon-*.tar.bz2 rasdaemon-*.src.rpm rasdaemon-0.5.8/AUTHORS000066400000000000000000000000541270413651700145520ustar00rootroot00000000000000Mauro Carvalho Chehab rasdaemon-0.5.8/COPYING000066400000000000000000000403551270413651700145450ustar00rootroot00000000000000 GNU GENERAL PUBLIC LICENSE Version 2, June 1991 Copyright (C) 1989, 1991 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This General Public License applies to most of the Free Software Foundation's software and to any other program whose authors commit to using it. (Some other Free Software Foundation software is covered by the GNU Lesser General Public License instead.) You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. Finally, any free program is threatened constantly by software patents. We wish to avoid the danger that redistributors of a free program will individually obtain patent licenses, in effect making the program proprietary. To prevent this, we have made it clear that any patent must be licensed for everyone's free use or not licensed at all. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any derivative work under copyright law: that is to say, a work containing the Program or a portion of it, either verbatim or with modifications and/or translated into another language. (Hereinafter, translation is included without limitation in the term "modification".) Each licensee is addressed as "you". Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running the Program is not restricted, and the output from the Program is covered only if its contents constitute a work based on the Program (independent of having been made by running the Program). Whether that is true depends on what the Program does. 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and give any other recipients of the Program a copy of this License along with the Program. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Program or any portion of it, thus forming a work based on the Program, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) You must cause the modified files to carry prominent notices stating that you changed the files and the date of any change. b) You must cause any work that you distribute or publish, that in whole or in part contains or is derived from the Program or any part thereof, to be licensed as a whole at no charge to all third parties under the terms of this License. c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the most ordinary way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this License. (Exception: if the Program itself is interactive but does not normally print such an announcement, your work based on the Program is not required to print an announcement.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Program, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Program, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Program. In addition, mere aggregation of another work not based on the Program with the Program (or with a work based on the Program) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may copy and distribute the Program (or a work based on it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you also do one of the following: a) Accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, b) Accompany it with a written offer, valid for at least three years, to give any third party, for a charge no more than your cost of physically performing source distribution, a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, c) Accompany it with the information you received as to the offer to distribute corresponding source code. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form with such an offer, in accord with Subsection b above.) The source code for a work means the preferred form of the work for making modifications to it. For an executable work, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the executable. However, as a special exception, the source code distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. If distribution of executable or object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place counts as distribution of the source code, even though third parties are not compelled to copy the source along with the object code. 4. You may not copy, modify, sublicense, or distribute the Program except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense or distribute the Program is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 5. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Program or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Program (or any work based on the Program), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Program or works based on it. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties to this License. 7. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Program at all. For example, if a patent license would not permit royalty-free redistribution of the Program by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Program. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system, which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 8. If the distribution and/or use of the Program is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Program under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 9. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of this License, you may choose any version ever published by the Free Software Foundation. 10. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) 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 Street, Fifth Floor, Boston, MA 02110-1301 USA. rasdaemon-0.5.8/ChangeLog000066400000000000000000000054111270413651700152560ustar00rootroot000000000000002013-03-12 Mauro Carvalho Chehab * Version 0.1.0 * Initial version 2013-05-08 Mauro Carvalho Chehab * Version 0.2.0 * Add support to log via syslog * Add ras-mc-ctl script to handle dimm labels * Add a rpm spec file * Make sqlite3 code experimental * Add manpages and systemd services * Update to take advantage of tracing features on Kernel 3.10 2013-05-20 Mauro Carvalho Chehab * Version 0.3.0 * Several fixes * Add support for MCE traces * Add support for PCI AER traces * Add a target to build it on rpm-based distros 2013-05-28 Mauro Carvalho Chehab * Version 0.4.0 * Several fixes * Get rid of pthreads, to avoid troubles with sqllite3 (requires Kernel 3.10 or upper) * Add memory error decoding on MCE traces 2013-05-29 Mauro Carvalho Chehab * Version 0.4.1 * Some fixes, mostly at sqlite3 code * Add support at ras-mc-ctl to query database 2013-09-10 Mauro Carvalho Chehab * Version 0.4.2 * Fixes ras-mc-ctl layout 2014-02-16 Mauro Carvalho Chehab * Version 0.5.0 * Initial ABRT support 2014-03-25 Mauro Carvalho Chehab * Version 0.5.1 * Fix patches at *.service files * Some fixes and documentation for --record option 2014-04-03 Mauro Carvalho Chehab - Version 0.5.2 * Some fixes for ABRT report support 2014-08-10 Mauro Carvalho Chehab - Version 0.5.3 * Add support for extlog trace events * Some fixes affecting sqlite handling * Handle failures of snprintf() * Fix mce numfield decoded error 2014-08-15 Mauro Carvalho Chehab - Version 0.5.4 * Fix a bug while parsing dimm labels on amd64 * Enable database recording by default on systemd service file * Correct range while parsing top, middle and lower layers 2015-06-03 Mauro Carvalho Chehab - Version 0.5.5 * Improve INSTALL summary instructions * Add support to match the machine by system's product name * Add support for Haswell/Broadwell/Knights Landing * Some bug fixes on some MCE handlers 2015-07-03 Mauro Carvalho Chehab - Version 0.5.6 * Add internal errors of IA32_MC4_STATUS for Haswell * Use MCA error msg as error_msg * Unnecessary comma for empty mc_location string * Remove a space from mcgstatus_msg * Add support to log Local Machine Check Exception (LMCE) 2016-02-05 Mauro Carvalho Chehab - Version 0.5.7 * Add model numbers for Broadwell-EP/EX and -DE * Add support for Knights Landing processor 2016-04-15 Mauro Carvalho Chehab - Version 0.5.8 * Add Broadwell EP/EX MSCOD and Broadwell DE MSCOD values rasdaemon-0.5.8/INSTALL000066400000000000000000000366101270413651700145420ustar00rootroot00000000000000Installation Instructions ************************* Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation, Inc. Copying and distribution of this file, with or without modification, are permitted in any medium without royalty provided the copyright notice and this notice are preserved. This file is offered as-is, without warranty of any kind. Basic Installation ================== Briefly, the shell command `./configure && make && make install' should configure, build, and install this package. The following more-detailed instructions are generic; see the `README' file for instructions specific to this package. Some packages provide this `INSTALL' file but do not implement all of the features documented below. The lack of an optional feature in a given package is not necessarily a bug. More recommendations for GNU packages can be found in *note Makefile Conventions: (standards)Makefile Conventions. The `configure' shell script attempts to guess correct values for various system-dependent variables used during compilation. It uses those values to create a `Makefile' in each directory of the package. It may also create one or more `.h' files containing system-dependent definitions. Finally, it creates a shell script `config.status' that you can run in the future to recreate the current configuration, and a file `config.log' containing compiler output (useful mainly for debugging `configure'). It can also use an optional file (typically called `config.cache' and enabled with `--cache-file=config.cache' or simply `-C') that saves the results of its tests to speed up reconfiguring. Caching is disabled by default to prevent problems with accidental use of stale cache files. If you need to do unusual things to compile the package, please try to figure out how `configure' could check whether to do them, and mail diffs or instructions to the address given in the `README' so they can be considered for the next release. If you are using the cache, and at some point `config.cache' contains results you don't want to keep, you may remove or edit it. The file `configure.ac' (or `configure.in') is used to create `configure' by a program called `autoconf'. You need `configure.ac' if you want to change it or regenerate `configure' using a newer version of `autoconf'. The simplest way to compile this package is: 1. `cd' to the directory containing the package's source code and type `./configure' to configure the package for your system. Running `configure' might take a while. While running, it prints some messages telling which features it is checking for. 2. Type `make' to compile the package. 3. Optionally, type `make check' to run any self-tests that come with the package, generally using the just-built uninstalled binaries. 4. Type `make install' to install the programs and any data files and documentation. When installing into a prefix owned by root, it is recommended that the package be configured and built as a regular user, and only the `make install' phase executed with root privileges. 5. Optionally, type `make installcheck' to repeat any self-tests, but this time using the binaries in their final installed location. This target does not install anything. Running this target as a regular user, particularly if the prior `make install' required root privileges, verifies that the installation completed correctly. 6. You can remove the program binaries and object files from the source code directory by typing `make clean'. To also remove the files that `configure' created (so you can compile the package for a different kind of computer), type `make distclean'. There is also a `make maintainer-clean' target, but that is intended mainly for the package's developers. If you use it, you may have to get all sorts of other programs in order to regenerate files that came with the distribution. 7. Often, you can also type `make uninstall' to remove the installed files again. In practice, not all packages have tested that uninstallation works correctly, even though it is required by the GNU Coding Standards. 8. Some packages, particularly those that use Automake, provide `make distcheck', which can by used by developers to test that all other targets like `make install' and `make uninstall' work correctly. This target is generally not run by end users. Compilers and Options ===================== Some systems require unusual options for compilation or linking that the `configure' script does not know about. Run `./configure --help' for details on some of the pertinent environment variables. You can give `configure' initial values for configuration parameters by setting variables in the command line or in the environment. Here is an example: ./configure CC=c99 CFLAGS=-g LIBS=-lposix *Note Defining Variables::, for more details. Compiling For Multiple Architectures ==================================== You can compile the package for more than one kind of computer at the same time, by placing the object files for each architecture in their own directory. To do this, you can use GNU `make'. `cd' to the directory where you want the object files and executables to go and run the `configure' script. `configure' automatically checks for the source code in the directory that `configure' is in and in `..'. This is known as a "VPATH" build. With a non-GNU `make', it is safer to compile the package for one architecture at a time in the source code directory. After you have installed the package for one architecture, use `make distclean' before reconfiguring for another architecture. On MacOS X 10.5 and later systems, you can create libraries and executables that work on multiple system types--known as "fat" or "universal" binaries--by specifying multiple `-arch' options to the compiler but only a single `-arch' option to the preprocessor. Like this: ./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ CPP="gcc -E" CXXCPP="g++ -E" This is not guaranteed to produce working output in all cases, you may have to build one architecture at a time and combine the results using the `lipo' tool if you have problems. Installation Names ================== By default, `make install' installs the package's commands under `/usr/local/bin', include files under `/usr/local/include', etc. You can specify an installation prefix other than `/usr/local' by giving `configure' the option `--prefix=PREFIX', where PREFIX must be an absolute file name. You can specify separate installation prefixes for architecture-specific files and architecture-independent files. If you pass the option `--exec-prefix=PREFIX' to `configure', the package uses PREFIX as the prefix for installing programs and libraries. Documentation and other data files still use the regular prefix. In addition, if you use an unusual directory layout you can give options like `--bindir=DIR' to specify different values for particular kinds of files. Run `configure --help' for a list of the directories you can set and what kinds of files go in them. In general, the default for these options is expressed in terms of `${prefix}', so that specifying just `--prefix' will affect all of the other directory specifications that were not explicitly provided. The most portable way to affect installation locations is to pass the correct locations to `configure'; however, many packages provide one or both of the following shortcuts of passing variable assignments to the `make install' command line to change installation locations without having to reconfigure or recompile. The first method involves providing an override variable for each affected directory. For example, `make install prefix=/alternate/directory' will choose an alternate location for all directory configuration variables that were expressed in terms of `${prefix}'. Any directories that were specified during `configure', but not in terms of `${prefix}', must each be overridden at install time for the entire installation to be relocated. The approach of makefile variable overrides for each directory variable is required by the GNU Coding Standards, and ideally causes no recompilation. However, some platforms have known limitations with the semantics of shared libraries that end up requiring recompilation when using this method, particularly noticeable in packages that use GNU Libtool. The second method involves providing the `DESTDIR' variable. For example, `make install DESTDIR=/alternate/directory' will prepend `/alternate/directory' before all installation names. The approach of `DESTDIR' overrides is not required by the GNU Coding Standards, and does not work on platforms that have drive letters. On the other hand, it does better at avoiding recompilation issues, and works well even when some directory options were not specified in terms of `${prefix}' at `configure' time. Optional Features ================= If the package supports it, you can cause programs to be installed with an extra prefix or suffix on their names by giving `configure' the option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. Some packages pay attention to `--enable-FEATURE' options to `configure', where FEATURE indicates an optional part of the package. They may also pay attention to `--with-PACKAGE' options, where PACKAGE is something like `gnu-as' or `x' (for the X Window System). The `README' should mention any `--enable-' and `--with-' options that the package recognizes. For packages that use the X Window System, `configure' can usually find the X include and library files automatically, but if it doesn't, you can use the `configure' options `--x-includes=DIR' and `--x-libraries=DIR' to specify their locations. Some packages offer the ability to configure how verbose the execution of `make' will be. For these packages, running `./configure --enable-silent-rules' sets the default to minimal output, which can be overridden with `make V=1'; while running `./configure --disable-silent-rules' sets the default to verbose, which can be overridden with `make V=0'. Particular systems ================== On HP-UX, the default C compiler is not ANSI C compatible. If GNU CC is not installed, it is recommended to use the following options in order to use an ANSI C compiler: ./configure CC="cc -Ae -D_XOPEN_SOURCE=500" and if that doesn't work, install pre-built binaries of GCC for HP-UX. HP-UX `make' updates targets which have the same time stamps as their prerequisites, which makes it generally unusable when shipped generated files such as `configure' are involved. Use GNU `make' instead. On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot parse its `' header file. The option `-nodtk' can be used as a workaround. If GNU CC is not installed, it is therefore recommended to try ./configure CC="cc" and if that doesn't work, try ./configure CC="cc -nodtk" On Solaris, don't put `/usr/ucb' early in your `PATH'. This directory contains several dysfunctional programs; working variants of these programs are available in `/usr/bin'. So, if you need `/usr/ucb' in your `PATH', put it _after_ `/usr/bin'. On Haiku, software installed for all users goes in `/boot/common', not `/usr/local'. It is recommended to use the following options: ./configure --prefix=/boot/common Specifying the System Type ========================== There may be some features `configure' cannot figure out automatically, but needs to determine by the type of machine the package will run on. Usually, assuming the package is built to be run on the _same_ architectures, `configure' can figure that out, but if it prints a message saying it cannot guess the machine type, give it the `--build=TYPE' option. TYPE can either be a short name for the system type, such as `sun4', or a canonical name which has the form: CPU-COMPANY-SYSTEM where SYSTEM can have one of these forms: OS KERNEL-OS See the file `config.sub' for the possible values of each field. If `config.sub' isn't included in this package, then this package doesn't need to know the machine type. If you are _building_ compiler tools for cross-compiling, you should use the option `--target=TYPE' to select the type of system they will produce code for. If you want to _use_ a cross compiler, that generates code for a platform different from the build platform, you should specify the "host" platform (i.e., that on which the generated programs will eventually be run) with `--host=TYPE'. Sharing Defaults ================ If you want to set default values for `configure' scripts to share, you can create a site shell script called `config.site' that gives default values for variables like `CC', `cache_file', and `prefix'. `configure' looks for `PREFIX/share/config.site' if it exists, then `PREFIX/etc/config.site' if it exists. Or, you can set the `CONFIG_SITE' environment variable to the location of the site script. A warning: not all `configure' scripts look for a site script. Defining Variables ================== Variables not defined in a site shell script can be set in the environment passed to `configure'. However, some packages may run configure again during the build, and the customized values of these variables may be lost. In order to avoid this problem, you should set them in the `configure' command line, using `VAR=value'. For example: ./configure CC=/usr/local2/bin/gcc causes the specified `gcc' to be used as the C compiler (unless it is overridden in the site shell script). Unfortunately, this technique does not work for `CONFIG_SHELL' due to an Autoconf limitation. Until the limitation is lifted, you can use this workaround: CONFIG_SHELL=/bin/bash ./configure CONFIG_SHELL=/bin/bash `configure' Invocation ====================== `configure' recognizes the following options to control how it operates. `--help' `-h' Print a summary of all of the options to `configure', and exit. `--help=short' `--help=recursive' Print a summary of the options unique to this package's `configure', and exit. The `short' variant lists options used only in the top level, while the `recursive' variant lists options also present in any nested packages. `--version' `-V' Print the version of Autoconf used to generate the `configure' script, and exit. `--cache-file=FILE' Enable the cache: use and save the results of the tests in FILE, traditionally `config.cache'. FILE defaults to `/dev/null' to disable caching. `--config-cache' `-C' Alias for `--cache-file=config.cache'. `--quiet' `--silent' `-q' Do not print messages saying which checks are being made. To suppress all normal output, redirect it to `/dev/null' (any error messages will still be shown). `--srcdir=DIR' Look for the package's source code in directory DIR. Usually `configure' can determine that directory automatically. `--prefix=DIR' Use DIR as the installation prefix. *note Installation Names:: for more details, including other options available for fine-tuning the installation locations. `--no-create' `-n' Run the configure checks, but stop before creating any output files. `configure' also accepts some other, not widely useful, options. Run `configure --help' for more details. rasdaemon-0.5.8/Makefile.am000066400000000000000000000053231270413651700155420ustar00rootroot00000000000000ACLOCAL_AMFLAGS=-I m4 SUBDIRS = libtrace util man SYSTEMD_SERVICES_IN = misc/rasdaemon.service.in misc/ras-mc-ctl.service.in SYSTEMD_SERVICES = $(SYSTEMD_SERVICES_IN:.service.in=.service) EXTRA_DIST = $(SYSTEMD_SERVICES_IN) # This rule is needed because \@sbindir\@ is expanded to \${exec_prefix\}/sbin # during ./configure phase, therefore it is not possible to add .service.in # files to AC_CONFIG_FILES in configure.ac SUFFIXES = .service.in .service .service.in.service: sed -e s,\@sbindir\@,$(sbindir),g $< > $@ # This rule is needed because the service files must be generated on target # system after ./configure phase all-local: $(SYSTEMD_SERVICES) sbin_PROGRAMS = rasdaemon rasdaemon_SOURCES = rasdaemon.c ras-events.c ras-mc-handler.c \ bitfield.c if WITH_SQLITE3 rasdaemon_SOURCES += ras-record.c endif if WITH_AER rasdaemon_SOURCES += ras-aer-handler.c endif if WITH_MCE rasdaemon_SOURCES += ras-mce-handler.c mce-intel.c mce-amd-k8.c \ mce-intel-p4-p6.c mce-intel-nehalem.c \ mce-intel-dunnington.c mce-intel-tulsa.c \ mce-intel-sb.c mce-intel-ivb.c mce-intel-haswell.c \ mce-intel-knl.c mce-intel-broadwell-de.c \ mce-intel-broadwell-epex.c endif if WITH_EXTLOG rasdaemon_SOURCES += ras-extlog-handler.c endif if WITH_ABRT_REPORT rasdaemon_SOURCES += ras-report.c endif rasdaemon_LDADD = -lpthread $(SQLITE3_LIBS) libtrace/libtrace.a include_HEADERS = config.h ras-events.h ras-logger.h ras-mc-handler.h \ ras-aer-handler.h ras-mce-handler.h ras-record.h bitfield.h ras-report.h \ ras-extlog-handler.h # This rule can't be called with more than one Makefile job (like make -j8) # I can't figure out a way to fix that dist-rpm: dist-bzip2 if [ ! -d "`rpm --eval %{_topdir}`/SOURCES/" ]; then mkdir "`rpm --eval %{_topdir}`/SOURCES/"; fi cp @PACKAGE@-@PACKAGE_VERSION@.tar.bz2 `rpm --eval %{_topdir}`/SOURCES/ rpmbuild -ba misc/@PACKAGE@.spec cp `rpm --eval %{_topdir}`/SRPMS/@PACKAGE@-@PACKAGE_VERSION@*.src.rpm . srpm: dist-bzip2 if [ ! -d "`rpm --eval %{_topdir}`/SOURCES/" ]; then mkdir "`rpm --eval %{_topdir}`/SOURCES/"; fi cp @PACKAGE@-@PACKAGE_VERSION@.tar.bz2 `rpm --eval %{_topdir}`/SOURCES/ rpmbuild -bs misc/@PACKAGE@.spec mock: srpm mock `rpm --eval %{_topdir}`/SRPMS/@PACKAGE@-@PACKAGE_VERSION@*.src.rpm rpmlint: rpmlint misc/@PACKAGE@.spec `rpm --eval %{_topdir}`/SRPMS/@PACKAGE@-@PACKAGE_VERSION@*.src.rpm `rpm --eval %{_topdir}`/RPMS/*/@PACKAGE@-@PACKAGE_VERSION@*.rpm upload: scp `rpm --eval %{_topdir}`/SRPMS/@PACKAGE@-@PACKAGE_VERSION@*.src.rpm @PACKAGE@-@PACKAGE_VERSION@.tar.bz2 misc/rasdaemon.spec fedorapeople.org:public_html # custom target install-data-local: $(install_sh) -d "$(DESTDIR)@RASSTATEDIR@" $(install_sh) -d "$(DESTDIR)@sysconfdir@/ras/dimm_labels.d" rasdaemon-0.5.8/NEWS000066400000000000000000000054731270413651700142130ustar00rootroot00000000000000RAS DAEMON ========== In Kernel 3.5 we've started to address the long-discussed need of having a better way to handle platform Reliability, Availability and Serviceability (RAS). Basically, a tracepoint event that handles memory errors called ras:mc_event was added there, together with HERM/EDAC version 3.0 patches. In Kernel 3.8, a new event was added, to handle PCIe AER events (ras:aer_event) [1]. On kernel 3.9, a new driver was added to report hardware memory errors that comes from the BIOS via ras:mc_event (the new ghes_edac driver). It is still on my TODO list to add a RAS trace event for non-memory related errors that come via the MCA machine check handler (mcelog). While progress made was made at Kernel infrastructure, the needed userspace tools were still lacking. So, I decided to start materializing the userspace counterpart for what it was informally named as rasdaemon on some discussions. The rasdaemon tool is available at: http://git.infradead.org/users/mchehab/rasdaemon.git The current version is on very early stages, and it has a copy on it of the library that Steven Rostedt's is writing for trace-cmd tool. The plan is to use the trace-cmd library, when it starts to packaged as a separate library. I'd like to thanks Steven for the help he gave me to write this initial version. The current version of the tool enables the ras:mc_event log, and reads it via the raw trace debugfs node: /sys/kernel/debug/tracing/per_cpu/cpu*/trace_pipe_raw It also has a code that allows recording the errors via an sqlite3 database. The long term plan is to provide a tool that will catch and handle all ras:* error events that comes from the Kernel tracing infrastructure, logging them and providing tools to report it, being able to detect burst errors (like the ones caused by a solar storm at memories) or sparsed errors, in a way that would provide a glue to the users about the root cause of the error. Of course, there are much to do there. It is a natural evolution of the tool to add support there for the ras:aer_event traces that can come from PCIe AER. While it currently works with current Kernels since kernel 3.5, there are a number of interesting changes at tracing that are planned to be merged for Kernel 3.10: - poll() support for per_cpu trace_pipe_raw; - a timestamp that could more easily associated with machine's uptime; - support for a separate ringbuffer for RAS. So, it is planned the minimal requirement for the final version (v1.0) would be kernel 3.10. This is currently on very early staging. Help is needed ;) So, please send us suggestions, patches etc to the EDAC mailing list: linux-edac@vger.kernel.org Thanks, Mauro Carvalho Chehab 2013-03-14 - [1] Currently, ras:mc_event is at include/ras/. It is on my todo list to move it to be together with ras:aer_event, at include/trace/events/ras.h. rasdaemon-0.5.8/README000066400000000000000000000212511270413651700143640ustar00rootroot00000000000000RAS Daemon ========== Those tools provide a way to get Platform Reliability, Availability and Serviceability (RAS) reports made via the Kernel tracing events. The main repository for the rasdaemon is at Fedora hosted: https://git.fedorahosted.org/cgit/rasdaemon.git/ I have a secondary repository at Infradead: http://git.infradead.org/users/mchehab/rasdaemon.git Where I use when I'm working on experimental patches, not ready yet for upstream. GOALS ===== Its initial goal is to replace the edac-tools that got bitroted after the addition of the HERM (Hardware Events Report Method )patches[1] at the EDAC Kernel drivers. [1] http://lkml.indiana.edu/hypermail/linux/kernel/1205.1/02075.html Its long term goal is to be the userspace tool that will collect all hardware error events reported by the Linux Kernel from several sources (EDAC, MCE, PCI, ...) into one common framework. It is not meant to provide tools for doing error injection, as there are other tools already covering it, like: git://git.kernel.org/pub/scm/linux/kernel/git/gong.chen/mce-test.git Yet, a few set of testing scripts are provided under /contrib dir. When the final version of the HERM patches was merged upstream, it was decided to not expose the memory error counters to userspace. This is one of the differences from what it was provided by edac-utils, as EDAC 2.0.0 exports errors via a set of sysfs nodes that sums the amount of errors per DIMM, per memory channel and per memory controller. However, those counters are monotonically increased, and there's no way to detect if they're very sparsed in time, if the occurrence is increasing over time, or if they're due to some burst, perhaps due to a Solar Storm hitting the ionosphere. In other words, the rationale for not exposing such the information is that: 1) can be easily accounted on userspace; 2) they're not really meaningful. E. g. one system with, let's say 10 corrected errors can be fine, while another one with the same amount of errors can have problems, as the error counters don't take into account things like system uptime, memory error bursts (that could be caused by a solar storm, for example), etc. So, the idea since them was to make the kernel-userspace interface simpler and move the policy to the userspace daemon. It is up to the userspace daemon to correlate the data about the RAS events and provide the system administrator a comprehensive report, presenting him a better hint if he needs to contact the hardware vendor to replace a component that is working degraded, or to simply discard the error. So, the approach taken here is to allow storing those errors on a SQLite database, in order to allow those data to be latter mining. It is currently not part of the scope to do sophiscicated data mininy analysis, as that would require enough statistitical data about hardware MTBF. In other words, an abnormal component that needs to be replaced shoud be statistically compared with a similar component that operates under a normal condition. To do such checks, the analysis tool would need to know the probability density function(p. d. f.) of that component, and its rellevant parameters (like mean and standard derivation, if the p. d. f. funcion is a Normal distribution). While this tool works since Kernel 3.5 (where HERM patches got added), in order to get the full benefit of this tool, Kernel 3.10 or upper is needed. COMPILING AND INSTALLING ======================== sqlite3 and autoconf needs to be installed. On Fedora, this is done by installing the following packages: make gcc autoconf automake libtool tar sqlite-devel (if sqlite3 will be used) perl-DBD-SQLite (if sqlite3 will be used) To install then on Fedora, run: yum install -y make gcc autoconf automake libtool tar perl-dbd-sqlite Or, if sqlite3 database will be used to store data: yum install -y make gcc autoconf automake libtool tar sqlite-devel There are currently 3 features that are enabled optionally, via ./configure parameters: --enable-sqlite3 enable storing data at SQL lite database (currently experimental) --enable-aer enable PCIe AER events (currently experimental) --enable-mce enable MCE events (currently experimental) In order to compile it, run: $ autoreconf -vfi $ ./configure [parameters] $ make So, for example, to enable everything but sqlite3: $ autoreconf -vfi && ./configure --enable-aer --enable-mce && make After compiling, run, as root: # make install COMPILING AND INSTALLING ======================== If the distribution is rpm-based, an alternative method would be to do: $ autoreconf -vfi && ./configure The above procedure will generate a file at misc/rasdaemon.spec. You may edit it, in order to add/remove the --enable-[option] parameters. To generate the rpm files, do: $ make dist-rpm To install the rpm files, run, as root: # rpm -i `rpm --eval %{_topdir}`/RPMS/x86_64/rasdaemon-0.*.fc18.x86_64.rpm RUNNING ======= The daemon generally requires root permission, in order to read the needed debugfs trace nodes, with needs to be previously mounted. The rasdaemon will check at /proc/mounts where the debugfs partition is mounted and use it while running. To run the rasdaemon in background, just call it without any parameters: # rasdaemon The output will be available via syslog. Or, to run it in foreground and see the logs in console, run it as: # rasdaemon -f or, if you also want to record errors at the database (--enable-sqlite3 is required): # rasdaemon -f -r You may also start it via systemd: # systemctl start rasdaemon The rasdaemon will then output the messages to journald. TESTING ======= A script is provided under /contrib, in order to test the daemon EDAC handler. While the daemon is running, just run: # contrib/edac-fake-inject The script requires a Kernel compiled with CONFIG_EDAC_DEBUG and a running EDAC driver. MCE error handling can use the MCE inject: http://git.kernel.org/cgit/utils/cpu/mce/mce-inject.git For it to work, Kernel mce-inject module should be compiled and loaded. APEI error injection can use this tool: https://git.kernel.org/cgit/linux/kernel/git/gong.chen/mce-test.git/ AER error injection can use this tool: https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/ SUBMITTING PATCHES ================== If you want to help improving this tool, be my guest! We try to follow the Kernel's CodingStyle and submission rules as a reference. Please send patches enclosed in an email, in plain text, to: Mauro Carvalho Chehab or Mauro Carvalho Chehab Sending a copy also to linux-edac@vger.kernel.org. Don't foget to add a description of the patch in the body of the email, adding a Signed-off-by: at the end of the patch description (before the unified diff with the patch). We use Signed-off-by the same way as in kernel, so I'm transcribing bellow the same text as found under Kernel's Documentation/SubmittingPatches: "To improve tracking of who did what, especially with patches that can percolate to their final resting place in the kernel through several layers of maintainers, we've introduced a "sign-off" procedure on patches that are being emailed around. The sign-off is a simple line at the end of the explanation for the patch, which certifies that you wrote it or otherwise have the right to pass it on as an open-source patch. The rules are pretty simple: if you can certify the below: Developer's Certificate of Origin 1.1 By making a contribution to this project, I certify that: (a) The contribution was created in whole or in part by me and I have the right to submit it under the open source license indicated in the file; or (b) The contribution is based upon previous work that, to the best of my knowledge, is covered under an appropriate open source license and I have the right under that license to submit that work with modifications, whether created in whole or in part by me, under the same open source license (unless I am permitted to submit under a different license), as indicated in the file; or (c) The contribution was provided directly to me by some other person who certified (a), (b) or (c) and I have not modified it. (d) I understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information I submit with it, including my sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open source license(s) involved. then you just add a line saying Signed-off-by: Random J Developer using your real name (sorry, no pseudonyms or anonymous contributions.)" rasdaemon-0.5.8/TODO000066400000000000000000000003631270413651700141750ustar00rootroot000000000000001) Handle signals. 2) Better handle error conditions to be sure that events won't be lost. 3) Test support for PCIe AER trace records. 4) Better parse mce trace records. 5) Make it work fine with offline CPUs. 6) Handle CPU hotplugs. rasdaemon-0.5.8/bitfield.c000066400000000000000000000051201270413651700154270ustar00rootroot00000000000000/* * Copyright (C) 2013 Mauro Carvalho Chehab * * The code below were adapted from Andi Kleen/Intel/SuSe mcelog code, * released under GNU Public General License, v.2 * * 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 Street, Fifth Floor, Boston, MA 02110-1301 USA */ #include #include #include "ras-mce-handler.h" #include "bitfield.h" unsigned bitfield_msg(char *buf, size_t len, const char **bitarray, unsigned array_len, unsigned bit_offset, unsigned ignore_bits, uint64_t status) { int i, n; char *p = buf; len--; for (i = 0; i < array_len; i++) { if (status & ignore_bits) continue; if (status & (1 << (i + bit_offset))) { if (p != buf) { n = snprintf(p, len, ", "); if (n < 0) break; len -= n; p += n; } if (!bitarray[i]) n = snprintf(p, len, "BIT%d", i + bit_offset); else n = snprintf(p, len, "%s", bitarray[i]); if (n < 0) break; len -= n; p += n; } } *p = 0; return p - buf; } static uint64_t bitmask(uint64_t i) { uint64_t mask = 1; while (mask < i) mask = (mask << 1) | 1; return mask; } void decode_bitfield(struct mce_event *e, uint64_t status, struct field *fields) { struct field *f; for (f = fields; f->str; f++) { uint64_t v = (status >> f->start_bit) & bitmask(f->stringlen - 1); char *s = NULL; if (v < f->stringlen) s = f->str[v]; if (!s) { if (v == 0) continue; mce_snprintf(e->error_msg, "<%u:%llx>", f->start_bit, (long long)v); } else mce_snprintf(e->error_msg, "%s", s); } } void decode_numfield(struct mce_event *e, uint64_t status, struct numfield *fields) { struct numfield *f; for (f = fields; f->name; f++) { uint64_t mask = (1ULL << (f->end - f->start + 1)) - 1; uint64_t v = (status >> f->start) & mask; if (v > 0 || f->force) { char fmt[32] = {0}; snprintf(fmt, 32, "%%s: %s\n", f->fmt ? f->fmt : "%Lu"); mce_snprintf(e->error_msg, fmt, f->name, v); } } } rasdaemon-0.5.8/bitfield.h000066400000000000000000000040211270413651700154330ustar00rootroot00000000000000/* * The code below came from Andi Kleen/Intel/SuSe mcelog code, * released under GNU Public General License, v.2 * * 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 Street, Fifth Floor, Boston, MA 02110-1301 USA */ #include /* Generic bitfield decoder */ struct field { unsigned start_bit; char **str; unsigned stringlen; }; struct numfield { unsigned start, end; char *name; char *fmt; int force; }; #define FIELD(start_bit, name) { start_bit, name, ARRAY_SIZE(name) } #define SBITFIELD(start_bit, string) { start_bit, ((char * [2]) { NULL, string }), 2 } #define NUMBER(start, end, name) { start, end, name, "%Lu", 0 } #define NUMBERFORCE(start, end, name) { start, end, name, "%Lu", 1 } #define HEXNUMBER(start, end, name) { start, end, name, "%Lx", 0 } #define HEXNUMBERFORCE(start, end, name) { start, end, name, "%Lx", 1 } struct mce_event; void decode_bitfield(struct mce_event *e, uint64_t status, struct field *fields); void decode_numfield(struct mce_event *e, uint64_t status, struct numfield *fields); #define MASK(x) ((1ULL << (1 + (x))) - 1) #define EXTRACT(v, a, b) (((v) >> (a)) & MASK((b)-(a))) static inline int test_prefix(int nr, uint32_t value) { return ((value >> nr) == 1); } /* Ancillary routines */ unsigned bitfield_msg(char *buf, size_t len, const char **bitarray, unsigned array_len, unsigned bit_offset, unsigned ignore_bits, uint64_t status); rasdaemon-0.5.8/configure.ac000066400000000000000000000046321270413651700157760ustar00rootroot00000000000000AC_INIT([RASdaemon], 0.5.8) AM_SILENT_RULES([yes]) AC_CANONICAL_SYSTEM AC_CONFIG_MACRO_DIR([m4]) AC_CONFIG_HEADERS([config.h]) AM_INIT_AUTOMAKE AC_PROG_CC AC_PROG_INSTALL AC_PROG_LIBTOOL X_AC_META AC_CONFIG_FILES([ Makefile libtrace/Makefile man/Makefile man/ras-mc-ctl.8 man/rasdaemon.1 misc/rasdaemon.spec util/Makefile util/ras-mc-ctl ]) AC_ARG_ENABLE([sqlite3], AS_HELP_STRING([--enable-sqlite3], [enable storing data at SQL lite database (currently experimental)])) AS_IF([test "x$enable_sqlite3" = "xyes"], [ AC_CHECK_LIB(sqlite3, sqlite3_open,[echo "found sqlite3"] , AC_MSG_ERROR([*** Unable to find sqlite3 library]), ) SQLITE3_LIBS="-lsqlite3" AC_DEFINE(HAVE_SQLITE3,1,"have sqlite3") AC_SUBST([WITH_SQLITE3]) ]) AM_CONDITIONAL([WITH_SQLITE3], [test x$enable_sqlite3 = xyes]) AC_SUBST([SQLITE3_LIBS]) AC_ARG_ENABLE([aer], AS_HELP_STRING([--enable-aer], [enable PCIe AER events (currently experimental)])) AS_IF([test "x$enable_aer" = "xyes"], [ AC_DEFINE(HAVE_AER,1,"have PCIe AER events collect") AC_SUBST([WITH_AER]) ]) AM_CONDITIONAL([WITH_AER], [test x$enable_aer = xyes]) AC_ARG_ENABLE([mce], AS_HELP_STRING([--enable-mce], [enable MCE events (currently experimental)])) AS_IF([test "x$enable_mce" = "xyes"], [ AC_DEFINE(HAVE_MCE,1,"have PCIe MCE events collect") AC_SUBST([WITH_MCE]) ]) AM_CONDITIONAL([WITH_MCE], [test x$enable_mce = xyes]) AC_ARG_ENABLE([extlog], AS_HELP_STRING([--enable-extlog], [enable EXTLOG events (currently experimental)])) AS_IF([test "x$enable_extlog" = "xyes"], [ AC_DEFINE(HAVE_EXTLOG,1,"have EXTLOG events collect") AC_SUBST([WITH_EXTLOG]) ]) AM_CONDITIONAL([WITH_EXTLOG], [test x$enable_extlog = xyes]) AC_ARG_ENABLE([abrt_report], AS_HELP_STRING([--enable-abrt-report], [enable report event to ABRT (currently experimental)])) AS_IF([test "x$enable_abrt_report" = "xyes"], [ AC_DEFINE(HAVE_ABRT_REPORT,1,"have report event to ABRT") AC_SUBST([WITH_ABRT_REPORT]) ]) AM_CONDITIONAL([WITH_ABRT_REPORT], [test x$enable_abrt_report = xyes]) test "$sysconfdir" = '${prefix}/etc' && sysconfdir=/etc CFLAGS="$CFLAGS -Wall -Wmissing-prototypes -Wstrict-prototypes" AC_SUBST([rasstatedir], [$localstatedir/lib/rasdaemon]) AC_DEFINE_DIR([RASSTATEDIR], [rasstatedir], [rasdaemon db store state dir]) AC_SUBST([RASSTATEDIR]) AC_DEFINE([RAS_DB_FNAME], ["ras-mc_event.db"], [ras events database]) AC_SUBST([RAS_DB_FNAME], ["ras-mc_event.db"]) AC_OUTPUT rasdaemon-0.5.8/contrib/000077500000000000000000000000001270413651700151435ustar00rootroot00000000000000rasdaemon-0.5.8/contrib/edac-fake-inject000077500000000000000000000025211270413651700201430ustar00rootroot00000000000000#!/bin/bash MC="$(ls -d /sys/devices/system/edac/mc/mc? |sed -e s,.*/mc,,)" SYSFS="$(cat /proc/mounts|grep debugfs|cut -d' ' -f 2)" if [ ! -e $SYSFS/edac/ ]; then echo "$SYSFS/edac not found." echo " It seems that your Kernel was not compiled with CONFIG_EDAC_DEBUG."; exit -1; fi for i in $MC; do LAYER1=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 1) LAYER2=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 3) LAYER3=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 5) DEBUGFS=$SYSFS/edac/mc$i/ MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 2) for j in `seq 0 $MAX`; do echo $j > $DEBUGFS/fake_inject_$LAYER1 if [ "$LAYER2" == "" ]; then echo "Injecting errors at mc#$i $j" echo > $DEBUGFS/fake_inject else MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 4) for k in `seq 0 $MAX`; do echo $k > $DEBUGFS/fake_inject_$LAYER2 if [ "$LAYER3" == "" ]; then echo "Injecting errors at mc#$i $j:$k" echo > $DEBUGFS/fake_inject else MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 6) for l in `seq 0 $MAX`; do echo $l > $DEBUGFS/fake_inject_$LAYER3 echo "Injecting errors at mc#$i $j:$k:$l" echo > $DEBUGFS/fake_inject done fi done fi done done rasdaemon-0.5.8/contrib/edac-tests000077500000000000000000000045231270413651700171310ustar00rootroot00000000000000#!/bin/bash FILE=new-$(hostname)-$(date +"%Y-%m-%d-%H-%M-%S").txt run() { echo "# $@" >> $FILE $@ 2>> $FILE >> $FILE if [ "$?" != "0" ]; then ERR=$? echo "Error on $0# $@" echo "Error $ERR" >> $FILE tail -f $FILE exit -1 fi } run_noerror() { echo "# $@" >> $FILE $@ 2>> $FILE >> $FILE } DRIVER=$(lsmod|grep edac_core|cut -b 33-) echo "RUNNING driver $DRIVER on kernel `uname -r`, hostname `hostname`, at `date`" >$FILE mount -t debugfs debugfs /sys/kernel/debug/ run ras-mc-ctl --layout run ras-mc-ctl --guess-labels run free -l run dmidecode run_noerror tree /sys/devices/system/edac/ run_noerror grep . /sys/devices/system/edac/mc/mc?/dimm*/* /sys/devices/system/edac/mc/mc?/rank*/* run_noerror grep . /sys/devices/system/edac/mc/mc?/csrow*/* run_noerror dmesg for i in /sys/devices/system/edac/mc/mc?/reset_counters; do echo 1 >$i done echo "ras:*" >/sys/kernel/debug/tracing/set_event run echo "Enabled events: " run cat /sys/kernel/debug/tracing/set_event MC="$(ls -d /sys/devices/system/edac/mc/mc? |sed -e s,.*/mc,,)" for i in $MC; do LAYER1=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 1) LAYER2=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 3) LAYER3=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d ' ' -f 5) DEBUGFS=/sys/kernel/debug/edac/mc$i/ MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 2) for j in `seq 0 $MAX`; do MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 4) for k in `seq 0 $MAX`; do MAX=$(cat /sys/devices/system/edac/mc/mc$i/max_location |cut -d' ' -f 6) echo $j > $DEBUGFS/fake_inject_$LAYER1 echo $k > $DEBUGFS/fake_inject_$LAYER2 if [ "$MAX" == "" ]; then echo "Injecting errors at mc#$i $j:$k" echo "Injecting errors at mc#$i $j:$k" >> $FILE echo > $DEBUGFS/fake_inject dmesg |tail -3 >> $FILE else for l in `seq 0 $MAX`; do echo "Injecting errors at mc#$i $j:$k:$l" echo "Injecting errors at mc#$i $j:$k:$l" >> $FILE echo $l > $DEBUGFS/fake_inject_$LAYER3 echo > $DEBUGFS/fake_inject dmesg |tail -3 >> $FILE done fi done done done run grep . /sys/devices/system/edac/mc/mc?/*e_* run cat /sys/kernel/debug/tracing/trace # FIXME: need to add some logic there to check if the proper error # counts are incremented, without producing a very long log rasdaemon-0.5.8/labels/000077500000000000000000000000001270413651700147455ustar00rootroot00000000000000rasdaemon-0.5.8/labels/dell000066400000000000000000000013361270413651700156130ustar00rootroot00000000000000# RASDAEMON Motherboard DIMM labels Database file. # # Vendor-name and model-name are found from the program 'dmidecode' # labels are found from the silk screen on the motherboard. # #Vendor: # Model: #