<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel.git/arch/x86/kernel/cpu/centaur.c, branch linux-3.1.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.
</subtitle>
<id>https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-3.1.y</id>
<link rel='self' href='https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-3.1.y'/>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/'/>
<updated>2009-11-23T19:59:53Z</updated>
<entry>
<title>x86, cpu: mv display_cacheinfo -&gt; cpu_detect_cache_sizes</title>
<updated>2009-11-23T19:59:53Z</updated>
<author>
<name>Borislav Petkov</name>
</author>
<published>2009-11-21T13:01:45Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=27c13ecec4d8856687b50b959e1146845b478f95'/>
<id>urn:sha1:27c13ecec4d8856687b50b959e1146845b478f95</id>
<content type='text'>
display_cacheinfo() doesn't display anything anymore and it is used to
detect CPU cache sizes. Rename it accordingly.

Signed-off-by: Borislav Petkov &lt;petkovbb@gmail.com&gt;
LKML-Reference: &lt;20091121130145.GA31357@liondog.tnic&gt;
Signed-off-by: H. Peter Anvin &lt;hpa@zytor.com&gt;
</content>
</entry>
<entry>
<title>x86/centaur: merge 32 &amp; 64 bit version</title>
<updated>2009-03-14T15:27:29Z</updated>
<author>
<name>Sebastian Andrzej Siewior</name>
</author>
<published>2009-03-14T11:24:02Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=48f4c485c275e9550fa1a1191768689cc3ae0037'/>
<id>urn:sha1:48f4c485c275e9550fa1a1191768689cc3ae0037</id>
<content type='text'>
there should be no difference, except:

 * the 64bit variant now also initializes the padlock unit.
 * -&gt;c_early_init() is executed again from -&gt;c_init()
 * the 64bit fixups made into 32bit path.

Signed-off-by: Sebastian Andrzej Siewior &lt;sebastian@breakpoint.cc&gt;
Cc: herbert@gondor.apana.org.au
LKML-Reference: &lt;1237029843-28076-2-git-send-email-sebastian@breakpoint.cc&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: move various CPU initialization objects into .cpuinit.rodata</title>
<updated>2009-03-12T12:13:07Z</updated>
<author>
<name>Jan Beulich</name>
</author>
<published>2009-03-12T12:08:49Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=02dde8b45c5460794b9052d7c12939fe3eb63c2c'/>
<id>urn:sha1:02dde8b45c5460794b9052d7c12939fe3eb63c2c</id>
<content type='text'>
Impact: debuggability and micro-optimization

Putting whatever is possible into the (final) .rodata section increases
the likelihood of catching memory corruption bugs early, and reduces
false cache line sharing.

Signed-off-by: Jan Beulich &lt;jbeulich@novell.com&gt;
LKML-Reference: &lt;49B90961.76E4.0078.0@novell.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: remove duplicated get_model_name() calling</title>
<updated>2008-09-06T12:09:12Z</updated>
<author>
<name>Yinghai Lu</name>
</author>
<published>2008-09-06T08:52:27Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=1b05d60d60e81c6594da8298107a05b506f01797'/>
<id>urn:sha1:1b05d60d60e81c6594da8298107a05b506f01797</id>
<content type='text'>
Signed-off-by: Yinghai Lu &lt;yhlu.kernel@gmail.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: remove cpu_vendor_dev</title>
<updated>2008-09-04T19:09:45Z</updated>
<author>
<name>Yinghai Lu</name>
</author>
<published>2008-09-04T19:09:45Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=10a434fcb23a57c385177a0086955fae01003f64'/>
<id>urn:sha1:10a434fcb23a57c385177a0086955fae01003f64</id>
<content type='text'>
1. add c_x86_vendor into cpu_dev
2. change cpu_devs to static
3. check c_x86_vendor before put that cpu_dev into array
4. remove alignment for 64bit
5. order the sequence in cpu_devs according to link sequence...
   so could put intel at first, then amd...

Signed-off-by: Yinghai Lu &lt;yhlu.kernel@gmail.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: move mtrr cpu cap setting early in early_init_xxxx</title>
<updated>2008-09-04T19:09:43Z</updated>
<author>
<name>Yinghai Lu</name>
</author>
<published>2008-09-04T19:09:43Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=5fef55fddb7317585cabc1eae38dbd57f1c59729'/>
<id>urn:sha1:5fef55fddb7317585cabc1eae38dbd57f1c59729</id>
<content type='text'>
Krzysztof Helt found MTRR is not detected on k6-2

root cause:
	we moved mtrr_bp_init() early for mtrr trimming,
and in early_detect we only read the CPU capability from cpuid,
so some cpu doesn't have that bit in cpuid.

So we need to add early_init_xxxx to preset those bit before mtrr_bp_init
for those earlier cpus.

this patch is for v2.6.27

Reported-by: Krzysztof Helt &lt;krzysztof.h1@wp.pl&gt;
Signed-off-by: Yinghai Lu &lt;yhlu.kernel@gmail.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: clean up cpu capabilities accesses, centaur.c</title>
<updated>2008-04-17T15:40:51Z</updated>
<author>
<name>Ingo Molnar</name>
</author>
<published>2008-02-26T07:51:22Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=e1a94a974c2aa3c0a7c1a915c805211fb6773de1'/>
<id>urn:sha1:e1a94a974c2aa3c0a7c1a915c805211fb6773de1</id>
<content type='text'>
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
</content>
</entry>
<entry>
<title>x86: more coding style fixes in centaur.c</title>
<updated>2008-04-17T15:40:47Z</updated>
<author>
<name>Ingo Molnar</name>
</author>
<published>2008-02-18T02:30:47Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=edc05e6de3e2fd203da21ba984b19d92e5398b62'/>
<id>urn:sha1:edc05e6de3e2fd203da21ba984b19d92e5398b62</id>
<content type='text'>
no code changed:

 arch/x86/kernel/cpu/centaur.o:
    text    data     bss     dec     hex filename
    1031     324       0    1355     54b centaur.o.before
    1031     324       0    1355     54b centaur.o.after

 md5:
  4f306a7f980b58eb69c4bdcfcde565f1  centaur.o.before.asm
  4f306a7f980b58eb69c4bdcfcde565f1  centaur.o.after.asm

Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
Signed-off-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
</content>
</entry>
<entry>
<title>x86: coding style fixes for arch/x86/kernel/cpu/centaur.c</title>
<updated>2008-04-17T15:40:47Z</updated>
<author>
<name>Paolo Ciarrocchi</name>
</author>
<published>2008-02-17T22:30:23Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=29a9994bd8dbafc17f43d31651d31ea7b0add6a4'/>
<id>urn:sha1:29a9994bd8dbafc17f43d31651d31ea7b0add6a4</id>
<content type='text'>
Kills more than 150 errors/warnings

Signed-off-by: Paolo Ciarrocchi &lt;paolo.ciarrocchi@gmail.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
Signed-off-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
</content>
</entry>
<entry>
<title>x86: use ELF section to list CPU vendor specific code</title>
<updated>2008-04-17T15:40:47Z</updated>
<author>
<name>Thomas Petazzoni</name>
</author>
<published>2008-02-15T11:00:23Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=03ae5768b6110ebaa97dc3e7abf1c3d8bec5f874'/>
<id>urn:sha1:03ae5768b6110ebaa97dc3e7abf1c3d8bec5f874</id>
<content type='text'>
Replace the hardcoded list of initialization functions for each CPU
vendor by a list in an ELF section, which is read at initialization in
arch/x86/kernel/cpu/cpu.c to fill the cpu_devs[] array. The ELF
section, named .x86cpuvendor.init, is reclaimed after boot, and
contains entries of type "struct cpu_vendor_dev" which associates a
vendor number with a pointer to a "struct cpu_dev" structure.

This first modification allows to remove all the VENDOR_init_cpu()
functions.

This patch also removes the hardcoded calls to early_init_amd() and
early_init_intel(). Instead, we add a "c_early_init" member to the
cpu_dev structure, which is then called if not NULL by the generic CPU
initialization code. Unfortunately, in early_cpu_detect(), this_cpu is
not yet set, so we have to use the cpu_devs[] array directly.

This patch is part of the Linux Tiny project, and is needed for
further patch that will allow to disable compilation of unused CPU
support code.

Signed-off-by: Thomas Petazzoni &lt;thomas.petazzoni@free-electrons.com&gt;
Signed-off-by: Ingo Molnar &lt;mingo@elte.hu&gt;
Signed-off-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
</content>
</entry>
</feed>
