Skip to content

L
linux

xiphi1978 / linux

通知 2
Star 0
Fork 0
L
linux

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 03 3月, 2010 17 次提交
  3. 22 2月, 2010 1 次提交
  5. 17 2月, 2010 2 次提交
  7. 06 2月, 2010 3 次提交
    • A
      kbuild: move -fno-dwarf2-cfi-asm to powerpc only · d0679c73
      由 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
      由 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
      由 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
  9. 02 2月, 2010 17 次提交
    • M
      Merge branch 'modpost' of git://git.pengutronix.de/git/ukl/linux-2.6 into kbuild/for-next · d224a94a
      由 Michal Marek 提交于 
      Acked-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NMichal Marek <mmarek@suse.cz>
      d224a94a
    • M
      MAINTAINERS: add a few more patterns to kbuild · 70fb7ba6
      由 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
      由 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
      由 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
      由 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
      由 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
      由 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
      由 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
      Makefile: Document ability to make file.lst and file.S · 62718979
      由 Joe Perches 提交于 
      Signed-off-by: NJoe Perches <joe@perches.com>
Acked-by: NWANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: NMichal Marek <mmarek@suse.cz>
      62718979
    • D
      kbuild: improve version string logic · 85a256d8
      由 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
      由 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
      由 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
      由 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
      由 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
      由 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
      由 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
      由 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