1. 03 3月, 2010 2 次提交
  2. 22 2月, 2010 1 次提交
  3. 17 2月, 2010 2 次提交
  4. 06 2月, 2010 3 次提交
    • A
      kbuild: move -fno-dwarf2-cfi-asm to powerpc only · d0679c73
      Andi Kleen 提交于
      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: NAndi Kleen <ak@linux.intel.com>
      Cc: Kyle McMartin <kyle@mcmartin.ca>
      Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
      Acked-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      d0679c73
    • H
      markup_oops.pl: minor fixes · 59dde385
      Hui Zhu 提交于
      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: NHui Zhu <teawater@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      59dde385
    • H
      markup_oops.pl: add options to improve cross-sompilation environments · 52e13e21
      Hui Zhu 提交于
      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: NHui Zhu <teawater@gmail.com>
      Cc: Andrew Morton <akpm@linux-foundation.org>
      Cc: Arjan van de Ven <arjan@linux.intel.com>
      Cc: Sam Ravnborg <sam@ravnborg.org>
      Cc: ozan@pardus.org.tr
      Cc: Matthew Wilcox <willy@linux.intel.com>
      Acked-by: NWANG Cong <xiyou.wangcong@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      52e13e21
  5. 02 2月, 2010 18 次提交
    • M
    • M
      MAINTAINERS: add a few more patterns to kbuild · 70fb7ba6
      Michal Marek 提交于
      Also, add a note that "unmaintained" files below scripts/ should go via
      the kbuild tree (best current practice).
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      70fb7ba6
    • J
      scripts: use %_tmppath in "make rpm-pkg" · 880df92f
      John Saalwaechter 提交于
      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: NJohn Saalwaechter <saalwaechter@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      880df92f
    • H
      markup_oops.pl: fix for faulting instruction in the first line of a range · 0139f1d9
      Hui Zhu 提交于
      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: NHui Zhu <teawater@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      0139f1d9
    • D
      scripts: change scripts to use system python instead of env · 94a47083
      Don Zickus 提交于
      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: NDon Zickus <dzickus@redhat.com>
      Acked-by: NWANG Cong <xiyou.wangcong@gmail.com>
      Acked-by: NJarod Wilson <jarod@redhat.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      94a47083
    • H
      scripts/kallsyms: suppress build warning · 71d41aed
      Himanshu Chauhan 提交于
      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: NHimanshu Chauhan <hschauhan@nulltrace.org>
      Cc: WANG Cong <xiyou.wangcong@gmail.com>
      Cc: Michal Marek <mmarek@suse.cz>
      Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      71d41aed
    • M
      scripts/mkcompile_h: don't test for hardcoded paths · d4987bd7
      Michal Marek 提交于
      Don't test for /bin/{dnsdomainname,domainname}, simply try to execute
      the command and check if it returned something.
      Reported-by: NGlenn Sommer <glemsom@gmail.com>
      Acked-by: NWANG Cong <xiyou.wangcong@gmail.com>
      Tested-by: NGlenn Sommer <glemsom@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      d4987bd7
    • A
      Improve kconfig symbol hashing · e66f25d7
      Andi Kleen 提交于
      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: NAndi Kleen <ak@linux.intel.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      e66f25d7
    • J
      62718979
    • D
      kbuild: improve version string logic · 85a256d8
      David Rientjes 提交于
      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: NDavid Rientjes <rientjes@google.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      85a256d8
    • N
      nconfig: minor fix · 68c16edd
      Nir Tzachar 提交于
      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: NJan Engelhardt <jengelh@medozas.de>
      Signed-off-by: NNir Tzachar <nir.tzachar@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      68c16edd
    • M
      nconfig: mark local functions as such · 851190c9
      Michal Marek 提交于
      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: NMichal Marek <mmarek@suse.cz>
      851190c9
    • N
      kconfig: new configuration interface (nconfig) · 692d97c3
      nir.tzachar@gmail.com 提交于
      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: NNir Tzachar <nir.tzachar@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      692d97c3
    • A
      genksyms: close ref_file after use · c64152bf
      Alexander Beregalov 提交于
      It is the last place when the file is read, so close it.
      Signed-off-by: NAlexander Beregalov <a.beregalov@gmail.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      c64152bf
    • V
      menuconfig: wrap long help lines · da60fbbc
      Vadim Bendebury (вб) 提交于
      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: NVadim Bendebury <vbendeb@google.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      da60fbbc
    • R
      scripts: add ARM support to decodecode · 5358db0b
      Rabin Vincent 提交于
      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: NRabin Vincent <rabin@rab.in>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      5358db0b
    • R
      kconfig CROSS_COMPILE option · 84336466
      Roland McGrath 提交于
      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: NRoland 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: NAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      84336466
    • J
      kbuild: Fix linking error built-in.o no such file or directory · 4b024242
      Jiafu He 提交于
      This patch fixes the link error "built-in.o: no such file or directory".
      The problem happens if "dirx/Makefile" contains only "obj-m += diry/
      dirz/" and the empty "dirx/built-in.o" is missing. Adding $(subdir-m)
      into check for builtin-target fixes this error.
      Signed-off-by: NJiafu He <jay@goldhive.com>
      Signed-off-by: NMichal Marek <mmarek@suse.cz>
      4b024242
  6. 31 1月, 2010 4 次提交
  7. 30 1月, 2010 10 次提交