- 03 Mar, 2010 17 commits
-
-
Denys Vlasenko authored
Signed-off-by:
Denys Vlasenko <vda.linux@googlemail.com> Signed-off-by:
Michal Marek <mmarek@suse.cz>
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Denys Vlasenko authored
Signed-off-by:
-
Tim Abbott authored
Signed-off-by:
Tim Abbott <tabbott@ksplice.com> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by:
-
Tim Abbott authored
Signed-off-by:
-
Tim Abbott authored
There is already an architecture-independent __page_aligned_data macro for this purpose, so removing the powerpc-specific macro should be harmless. Signed-off-by:
-
Tim Abbott authored
Signed-off-by:
-
Tim Abbott authored
Signed-off-by:
-
John Kacur authored
make ALLSOURCE_ARCHS=all tags - Document this in kbuild.txt Without this change you have to type each arch separately. Signed-off-by:
John Kacur <jkacur@redhat.com> Signed-off-by:
-
John Kacur authored
Signed-off-by:
-
- 22 Feb, 2010 1 commit
-
-
Michal Marek authored
$ make mrproper $ make tags GEN tags find: `arch/x86_64/': No such file or directory Caused by commit f81b1be4 (tags: include headers before source files) Cc: Guennadi Liakhovetski <g.liakhovetski@gmx.de> Acked-by:
WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by:
-
- 17 Feb, 2010 2 commits
-
-
Kirill Smelkov authored
Signed-off-by:
Kirill Smelkov <kirr@mns.spb.ru> Signed-off-by:
-
Guennadi Liakhovetski authored
Currently looking up a structure definition in TAGS / tags takes one to one of multiple "static struct X" definitions in arch sources, which makes it for many structs practically impossible to get to the required header. This patch changes the order of sources being tagged to first scan architecture includes, then the top-level include/ directory, and only then the rest. It also takes into account, that many architectures have more than one include directory, i.e., not only arch/$ARCH/include, but also arch/$ARCH/mach-X/include etc. Signed-off-by:
Guennadi Liakhovetski <g.liakhovetski@gmx.de> Reviewed-by:
-
- 05 Feb, 2010 3 commits
-
-
Andi Kleen authored
Better dwarf2 unwind information is a good thing, it allows better debugging with kgdb and crash and helps systemtap. Commit 00308649 ("Build with -fno-dwarf2-cfi-asm") disabled some CFI information globally to work around a module loader bug on powerpc. But this disables the better unwind tables for all architectures, not just powerpc. Move the workaround to powerpc and also add a suitable comment that's it really a workaround. This improves dwarf2 unwind tables on x86 at least. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Acked-by:
Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by:
-
Hui Zhu authored
1. Fix a little format issue. 2. Check the return of "Getopt::Long::GetOptions". Output usage and exit if it get error. 3. Change $ARGV[$#ARGV] to $ARGV[0]. 4. Change the code which get $modulefile from modinfo. Replace the pipeline with `modinfo -F filename $module`. 4. Change usage from "Specify the module directory name" to "Specify the module filename". Signed-off-by:
Hui Zhu <teawater@gmail.com> Signed-off-by:
-
Hui Zhu authored
The markup_oops.pl have 3 troubles to support cross-compiler environment: 1. It use objdump directly. 2. It use modinfo to get the message of module. 3. It use hex function that cannot support 64-bit number in 32-bit arch. This patch add 3 options to markup_oops.pl: 1. -c CROSS_COMPILE Specify the prefix used for toolchain. 2. -m MODULE_DIRNAME Specify the module directory name. 3. Change hex function to Math::BigInt->from_hex. After this patch, parse the x8664 oops in x86, we can: cat amd64m | perl ~/kernel/tmp/m.pl -c /home/teawater/kernel/bin/x8664- -m ./e.ko vmlinux Thanks, Hui Signed-off-by:
-
- 02 Feb, 2010 17 commits
-
-
git://git.pengutronix.de/git/ukl/linux-2.6Michal Marek authored
Acked-by:
Sam Ravnborg <sam@ravnborg.org> Signed-off-by:
-
Michal Marek authored
Also, add a note that "unmaintained" files below scripts/ should go via the kbuild tree (best current practice). Signed-off-by: -
John Saalwaechter authored
The mkspec script hardcodes "/var/tmp" into the generated rpm spec file's BuildRoot. The user, however, may have a custom setting for %_tmppath, which should be used in BuildRoot. This patch changes mkspec's BuildRoot output to appropriately use %_tmppath. Signed-off-by:
John Saalwaechter <saalwaechter@gmail.com> Signed-off-by:
-
Hui Zhu authored
I got a "No matching code found" when I use markup_oops.pl parse a error in a x86_64 module. cat e.c int init_module(void) { char *buf = 0; buf[0] = 3; return 0; } void cleanup_module(void) { //char *buf = 0; //buf[0] = 3; } MODULE_AUTHOR("Hui Zhu"); MODULE_LICENSE("GPL"); 0000000000000000 <init_module>: init_module(): /home/teawater/study/kernel/stack2core/example/e.c:10 0: c6 04 25 00 00 00 00 movb $0x3,0x0 7: 03 /home/teawater/study/kernel/stack2core/example/e.c:13 8: 31 c0 xor %eax,%eax a: c3 retq b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 0000000000000010 <cleanup_module>: cleanup_module(): /home/teawater/study/kernel/stack2core/example/e.c:20 10: f3 c3 repz retq 12: 90 nop 13: 90 nop Disassembly of section .modinfo: This is because the faulting instruction "movb $0x3,0x0" is the first line of the range. In the markup_oops.pl: main::(./scripts/markup_oops.pl:245): 245: if (InRange($1, $target)) { DB<2> p $line ffffffffa001b000: c6 04 25 00 00 00 00 movb $0x3,0x0 DB<3> p $counter 0 It just set $center in next loop. So it cannot get the $center. And even if $center is set to the right value 0. if ($center == 0) { print "No matching code found \n"; exit; } The first line $center will be 0, so I change the default value to -1. Signed-off-by: -
Don Zickus authored
Just a small change to a couple of scripts to go from #!/usr/bin/env python to #!/usr/bin/python This shouldn't effect anyone, unless they don't install python there. In preparation for python3, Fedora is doing a big push to change the scripts to use the system python. This allows developers to put the python3 in their path without fear of breaking existing scripts. Now I am pretty sure anyone using python3 for testing purposes will probably not run any of the scripts I changed, but Fedora has this automated tool that checks for this stuff so I thought I would try to push it upstream. Signed-off-by:
Don Zickus <dzickus@redhat.com> Acked-by:
Jarod Wilson <jarod@redhat.com> Signed-off-by:
-
Himanshu Chauhan authored
Suppress a warn_unused_result warning. fgets is called as a part of error handling. It is called just to drop a line and return immediately. read_map is reading the file in a loop and read_symbol reads line by line. So I think there is no point in using return value for useful checking. Other checks like 3 items were returned or !EOF have already been done. Signed-off-by:
Himanshu Chauhan <hschauhan@nulltrace.org> Cc: WANG Cong <xiyou.wangcong@gmail.com> Cc: Michal Marek <mmarek@suse.cz> Signed-off-by:
-
Michal Marek authored
Don't test for /bin/{dnsdomainname,domainname}, simply try to execute the command and check if it returned something. Reported-by:Glenn Sommer <glemsom@gmail.com> Acked-by:
-
Andi Kleen authored
While looking for something else I noticed that the symbol hash function used by kconfig is quite poor. It doesn't use any of the standard hash techniques but simply adds up the string and then uses power of two masking, which is both known to perform poorly. The current x86 kconfig has over 7000 symbols. When I instrumented it showed that the minimum hash chain length was 16 and a significant number of them was over 30. It didn't help that the hash table size was only 256 buckets. This patch increases the hash table size to a larger prime and switches to a FNV32 hash. I played around with a couple of hash functions, but that one seemed to perform best with reasonable hash table sizes. Increasing the hash table size even further didn't seem like a good idea, because there are a couple of global walks which walk the complete hash table. I also moved the unnamed bucket to 0. It's still the longest of all the buckets (44 entries), but hopefully it's not often hit except for the global walk which doesn't care. The result is a much nicer distribution: (first column bucket length, second number of buckets with that length) 1: 3505 2: 1236 3: 294 4: 52 5: 3 47: 1 <--- this is the unnamed symbols bucket There are still some 5+ buckets, but increasing the hash table even more would be likely not worth it. This also cleans up the code slightly by removing hard coded magic numbers. I didn't notice a big performance difference either way on my Nehalem system, but I presume it'll help somewhat on slower systems. Signed-off-by:
-
Joe Perches authored
Signed-off-by:
Joe Perches <joe@perches.com> Acked-by:
-
David Rientjes authored
The LOCALVERSION= string passed to "make" will now always be appended to the kernel version after CONFIG_LOCALVERSION, if it exists, regardless of whether CONFIG_LOCALVERSION_AUTO is set or not. This allows users to uniquely identify their kernel builds with a string. If CONFIG_LOCALVERSION_AUTO is enabled, the unique SCM tag reported by setlocalversion (or .scmversion) is appended to the kernel version, if it exists. When CONFIG_LOCALVERSION_AUTO is not enabled, a `+' is appended to the kernel version to represent that the kernel has been revised since the last release unless "make LOCALVERSION=" was used to uniquely identify the build. The end result is this: - when LOCALVERSION= is passed to "make", it is appended to the kernel version, - when CONFIG_LOCALVERSION_AUTO is enabled, a unique SCM identifier is appended if the respository has been revised beyond a tagged commit, and - when CONFIG_LOCALVERSION_AUTO is disabled, a `+' is appended if the repository has been revised beyond a tagged commit and LOCALVERSION= was not passed to "make". Examples: With CONFIG_LOCALVERSION_AUTO: "make" results in v2.6.32-rc4-00149-ga3ccf63e. If there are uncommited changes to the respository, it results in v2.6.32-rc4-00149-ga3ccf63e-dirty. If "make LOCALVERSION=kbuild" were used, it results in v2.6.32-rc4-kbuild-00149-ga3ccf63e-dirty. Without CONFIG_LOCALVERSION_AUTO, "make" results in v2.6.32-rc4+ unless the repository is at the Linux v2.6.32-rc4 commit (in which case the version would be v2.6.32-rc4). If "make LOCALVERSION=kbuild" were used, it results in v2.6.32-rc4-kbuild. Also renames variables such as localver-auto and _localver-auto to more accurately describe what they represent: localver-extra and scm-identifier, respectively. Signed-off-by:
David Rientjes <rientjes@google.com> Signed-off-by:
-
Nir Tzachar authored
This patch fixes two problems reported by Jan Engelhardt: 1) Border is now properly placed, to always be visible 2) Long menu items are properly displayed Reported-by:
Jan Engelhardt <jengelh@medozas.de> Signed-off-by:
Nir Tzachar <nir.tzachar@gmail.com> Signed-off-by:
-
Michal Marek authored
scripts/kconfig/nconf.gui.c:23: warning: no previous prototype for 'set_normal_colors' scripts/kconfig/nconf.gui.c:68: warning: no previous prototype for 'normal_color_theme' scripts/kconfig/nconf.gui.c:100: warning: no previous prototype for 'no_colors_theme' scripts/kconfig/nconf.c:455: warning: no previous prototype for 'process_special_keys' scripts/kconfig/nconf.c:487: warning: no previous prototype for 'get_next_hot' scripts/kconfig/nconf.c:506: warning: no previous prototype for 'canbhot' scripts/kconfig/nconf.c:514: warning: no previous prototype for 'is_hot' scripts/kconfig/nconf.c:522: warning: no previous prototype for 'make_hot' scripts/kconfig/nconf.c:582: warning: no previous prototype for 'item_make' scripts/kconfig/nconf.c:626: warning: no previous prototype for 'item_add_str' scripts/kconfig/nconf.c:656: warning: no previous prototype for 'item_tag' scripts/kconfig/nconf.c:668: warning: no previous prototype for 'curses_item_index' scripts/kconfig/nconf.c:673: warning: no previous prototype for 'item_data' scripts/kconfig/nconf.c:684: warning: no previous prototype for 'item_is_tag' scripts/kconfig/nconf.c:691: warning: no previous prototype for 'set_config_filename' Signed-off-by: -
nir.tzachar@gmail.com authored
This patch was inspired by the kernel projects page, where an ncurses replacement for menuconfig was mentioned (by Sam Ravnborg). Building on menuconfig, this patch implements a more modern look interface using ncurses and ncurses' satellite libraries (menu, panel, form). The implementation does not depend on lxdialog, which is currently distributed with the kernel. Signed-off-by:
-
Alexander Beregalov authored
It is the last place when the file is read, so close it. Signed-off-by:
Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by:
-
Vadim Bendebury (вб) authored
Help text for certain config options is very extensive (the text includes the names of all other options the option in question depends on). Long lines are not wrapped, making it impossible to see the list without scrolling horizontally. This patch adds some logic which wraps help screen lines at word boundaries to prevent truncating. Tested by running ARCH=powerpc make menuconfig O=/tmp/build which shows that the long lines are now wrapped, and ARCH=powerpc make xconfig O=/tmp/build to demonstrate that it still compiles and operates as expected. Signed-off-by:
Vadim Bendebury <vbendeb@google.com> Signed-off-by:
-
Rabin Vincent authored
This patch adds support for decoding ARM oopses to scripts/decodecode. The following things are handled: - ARCH and CROSS_COMPILE environment variables are respected. - The Code: in x86 oopses is in bytes, while it is in either words (4 bytes) or halfwords for ARM. - Some versions of ARM objdump refuse to disassemble instructions generated by literal constants (".word 0x..."). The workaround is to strip the object file first. - The faulting instruction is marked (liked so) in ARM, but <like so> in x86. - ARM mnemonics may include characters such as [] which need to be escaped before being passed to sed for the "<- trapping instruction" substitution. Signed-off-by:Rabin Vincent <rabin@rab.in> Signed-off-by:
-
Roland McGrath authored
This adds CROSS_COMPILE as a kconfig string so you can store it in .config. Then you can use plain "make" in the configured kernel build directory to do the right cross compilation without setting the command-line or environment variable every time. With this, you can set up different build directories for different kernel configurations, whether native or cross-builds, and then use the simple: make -C /build/dir M=module-source-dir idiom to build modules for any given target kernel, indicating which one by nothing but the build directory chosen. I tried a version that defaults the string with env="CROSS_COMPILE" so that in a "make oldconfig" with CROSS_COMPILE in the environment you can just hit return to store the way you're building it. But the kconfig prompt for strings doesn't give you any way to say you want an empty string instead of the default, so I punted that. Signed-off-by:
Roland McGrath <roland@redhat.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Anibal Monsalve Salazar <anibal@debian.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Michal Marek <mmarek@suse.cz> Signed-off-by:
-
