<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/arch/x86/kernel/amd_nb.c, branch v4.2.7</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>x86/gart: Check for GART support before accessing GART registers</title>
<updated>2015-05-06T09:15:53+00:00</updated>
<author>
<name>Aravind Gopalakrishnan</name>
<email>Aravind.Gopalakrishnan@amd.com</email>
</author>
<published>2015-04-07T21:46:37+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=1b4574292e9d2d37b3bb437c9e778fd2bba8e170'/>
<id>1b4574292e9d2d37b3bb437c9e778fd2bba8e170</id>
<content type='text'>
GART registers are not present in newer AMD processors (Fam15h, Model
10h and later). So, avoid accessing those in PCI config space by
returning early in early_gart_iommu_check() and gart_iommu_hole_init()
if GART is not available.

Current code doesn't break on existing processors but there are some
side effects:

We get bogus AGP aperture messages which are simply noise on
GART-less processors:

  AGP: Node 0: aperture [bus addr 0x00000000-0x01ffffff] (32MB)
  AGP: Your BIOS doesn't leave aperture memory hole
  AGP: Please enable the IOMMU option in the BIOS setup
  AGP: This costs you 64MB of RAM
  AGP: Mapping aperture over RAM [mem 0xd4000000-0xd7ffffff]

We can avoid calling allocate_aperture() and would not have to
wastefully reserve 64MB of RAM with memblock_reserve(). Also, we can
avoid having to loop through all PCI buses and devices twice, searching
for a non-existent AGP bridge if we bail out early.

Refactor the family check used in amd_nb.c into an inline function so we
can use it here as well as in amd_nb.c

Fix some typos while at it.

Tested the patch on Fam10h and Fam15h Model 00h-fh and this code runs
fine. On Fam15h Model 60h-6fh and on Fam16h, we bail early as they don't
have GART.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
Reviewed-by: Suravee Suthikulpanit &lt;Suravee.Suthikulpanit@amd.com&gt;
Cc: Bjorn Helgaas &lt;bhelgaas@google.com&gt;
Cc: Borislav Petkov &lt;bp@alien8.de&gt;
Cc: H. Peter Anvin &lt;hpa@zytor.com&gt;
Cc: Joerg Rodel &lt;joro@8bytes.org&gt;
Cc: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Link: http://lkml.kernel.org/r/1428443197-3834-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
GART registers are not present in newer AMD processors (Fam15h, Model
10h and later). So, avoid accessing those in PCI config space by
returning early in early_gart_iommu_check() and gart_iommu_hole_init()
if GART is not available.

Current code doesn't break on existing processors but there are some
side effects:

We get bogus AGP aperture messages which are simply noise on
GART-less processors:

  AGP: Node 0: aperture [bus addr 0x00000000-0x01ffffff] (32MB)
  AGP: Your BIOS doesn't leave aperture memory hole
  AGP: Please enable the IOMMU option in the BIOS setup
  AGP: This costs you 64MB of RAM
  AGP: Mapping aperture over RAM [mem 0xd4000000-0xd7ffffff]

We can avoid calling allocate_aperture() and would not have to
wastefully reserve 64MB of RAM with memblock_reserve(). Also, we can
avoid having to loop through all PCI buses and devices twice, searching
for a non-existent AGP bridge if we bail out early.

Refactor the family check used in amd_nb.c into an inline function so we
can use it here as well as in amd_nb.c

Fix some typos while at it.

Tested the patch on Fam10h and Fam15h Model 00h-fh and this code runs
fine. On Fam15h Model 60h-6fh and on Fam16h, we bail early as they don't
have GART.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
Reviewed-by: Suravee Suthikulpanit &lt;Suravee.Suthikulpanit@amd.com&gt;
Cc: Bjorn Helgaas &lt;bhelgaas@google.com&gt;
Cc: Borislav Petkov &lt;bp@alien8.de&gt;
Cc: H. Peter Anvin &lt;hpa@zytor.com&gt;
Cc: Joerg Rodel &lt;joro@8bytes.org&gt;
Cc: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Link: http://lkml.kernel.org/r/1428443197-3834-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>x86, amd_nb: Add device IDs to NB tables for F15h M60h</title>
<updated>2014-10-20T12:18:45+00:00</updated>
<author>
<name>Aravind Gopalakrishnan</name>
<email>Aravind.Gopalakrishnan@amd.com</email>
</author>
<published>2014-09-18T19:56:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=15895a729e02ea55433b912cc31d5c6de16359ec'/>
<id>15895a729e02ea55433b912cc31d5c6de16359ec</id>
<content type='text'>
Add F3 and F4 PCI device IDs to amd_nb_misc_ids[] and
amd_nb_link_ids[] respectively.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Acked-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Link: http://lkml.kernel.org/r/1411070205-10217-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add F3 and F4 PCI device IDs to amd_nb_misc_ids[] and
amd_nb_link_ids[] respectively.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Acked-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Link: http://lkml.kernel.org/r/1411070205-10217-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge tag 'edac_for_3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp</title>
<updated>2014-04-01T20:54:00+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2014-04-01T20:54:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=62ff577fa2fec87edbf26f53e87210ba726d4d44'/>
<id>62ff577fa2fec87edbf26f53e87210ba726d4d44</id>
<content type='text'>
Pull EDAC updates from Borislav Petkov:
 "A bunch of EDAC updates all over the place:

   - Support for new AMD models, along with more graceful fallback for
     unsupported hw.

   - Bunch of fixes from SUSE accumulated from bug reports

   - Misc other fixes and cleanups"

* tag 'edac_for_3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
  amd64_edac: Add support for newer F16h models
  i7core_edac: Drop unused variable
  i82875p_edac: Drop redundant call to pci_get_device()
  amd8111_edac: Fix leaks in probe error paths
  e752x_edac: Drop pvt-&gt;bridge_ck
  MCE, AMD: Fix decoding module loading on unsupported hw
  i5100_edac: Remove an unneeded condition in i5100_init_csrows()
  sb_edac: Degrade log level for device registration
  amd64_edac: Fix logic to determine channel for F15 M30h processors
  edac/85xx: Remove deprecated IRQF_DISABLED
  i3200_edac: Add a missing pci_disable_device() on the exit path
  i5400_edac: Disable device when unloading module
  e752x_edac: Simplify call to pci_get_device()
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull EDAC updates from Borislav Petkov:
 "A bunch of EDAC updates all over the place:

   - Support for new AMD models, along with more graceful fallback for
     unsupported hw.

   - Bunch of fixes from SUSE accumulated from bug reports

   - Misc other fixes and cleanups"

* tag 'edac_for_3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
  amd64_edac: Add support for newer F16h models
  i7core_edac: Drop unused variable
  i82875p_edac: Drop redundant call to pci_get_device()
  amd8111_edac: Fix leaks in probe error paths
  e752x_edac: Drop pvt-&gt;bridge_ck
  MCE, AMD: Fix decoding module loading on unsupported hw
  i5100_edac: Remove an unneeded condition in i5100_init_csrows()
  sb_edac: Degrade log level for device registration
  amd64_edac: Fix logic to determine channel for F15 M30h processors
  edac/85xx: Remove deprecated IRQF_DISABLED
  i3200_edac: Add a missing pci_disable_device() on the exit path
  i5400_edac: Disable device when unloading module
  e752x_edac: Simplify call to pci_get_device()
</pre>
</div>
</content>
</entry>
<entry>
<title>amd64_edac: Add support for newer F16h models</title>
<updated>2014-02-27T17:03:16+00:00</updated>
<author>
<name>Aravind Gopalakrishnan</name>
<email>Aravind.Gopalakrishnan@amd.com</email>
</author>
<published>2014-02-20T16:28:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=85a8885bd0e00569108aa7b5e26b89c752e3cd51'/>
<id>85a8885bd0e00569108aa7b5e26b89c752e3cd51</id>
<content type='text'>
Extend ECC decoding support for F16h M30h. Tested on F16h M30h with ECC
turned on using mce_amd_inj module and the patch works fine.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Link: http://lkml.kernel.org/r/1392913726-16961-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Tested-by: Arindam Nath &lt;Arindam.Nath@amd.com&gt;
Acked-by: H. Peter Anvin &lt;hpa@zytor.com&gt;
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Extend ECC decoding support for F16h M30h. Tested on F16h M30h with ECC
turned on using mce_amd_inj module and the patch works fine.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
Link: http://lkml.kernel.org/r/1392913726-16961-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Tested-by: Arindam Nath &lt;Arindam.Nath@amd.com&gt;
Acked-by: H. Peter Anvin &lt;hpa@zytor.com&gt;
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>x86/AMD/NB: Fix amd_set_subcaches() parameter type</title>
<updated>2014-01-25T07:50:09+00:00</updated>
<author>
<name>Dan Carpenter</name>
<email>dan.carpenter@oracle.com</email>
</author>
<published>2014-01-21T07:22:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=2993ae3305ad10b41e0d0bc2662f7754ee8e30fa'/>
<id>2993ae3305ad10b41e0d0bc2662f7754ee8e30fa</id>
<content type='text'>
This is under CAP_SYS_ADMIN, but Smatch complains that mask comes
from the user and the test for "mask &gt; 0xf" can underflow.

The fix is simple: amd_set_subcaches() should hand down not an 'int'
but an 'unsigned long' like it was originally indended to do.

Signed-off-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Acked-by: Borislav Petkov &lt;bp@suse.de&gt;
Cc: Borislav Petkov &lt;bp@alien8.de&gt;
Cc: Daniel J Blueman &lt;daniel@numascale-asia.com&gt;
Link: http://lkml.kernel.org/r/20140121072209.GA22095@elgon.mountain
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is under CAP_SYS_ADMIN, but Smatch complains that mask comes
from the user and the test for "mask &gt; 0xf" can underflow.

The fix is simple: amd_set_subcaches() should hand down not an 'int'
but an 'unsigned long' like it was originally indended to do.

Signed-off-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Acked-by: Borislav Petkov &lt;bp@suse.de&gt;
Cc: Borislav Petkov &lt;bp@alien8.de&gt;
Cc: Daniel J Blueman &lt;daniel@numascale-asia.com&gt;
Link: http://lkml.kernel.org/r/20140121072209.GA22095@elgon.mountain
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>x86, amd_nb: Clarify F15h, model 30h GART and L3 support</title>
<updated>2013-08-12T13:30:08+00:00</updated>
<author>
<name>Aravind Gopalakrishnan</name>
<email>Aravind.Gopalakrishnan@amd.com</email>
</author>
<published>2013-08-02T22:43:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=7d64ac6422092adbbdaa279ab32f9d4c90a84558'/>
<id>7d64ac6422092adbbdaa279ab32f9d4c90a84558</id>
<content type='text'>
F15h, models 0x30 and later don't have a GART. Note that. Also check
CPUID leaf 0x80000006 for L3 prescence because there are models which
don't sport an L3 cache.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
[ Boris: rewrite commit message, cleanup comments. ]
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
F15h, models 0x30 and later don't have a GART. Note that. Also check
CPUID leaf 0x80000006 for L3 prescence because there are models which
don't sport an L3 cache.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
[ Boris: rewrite commit message, cleanup comments. ]
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branch 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip</title>
<updated>2013-04-30T15:42:45+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2013-04-30T15:42:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=5a5a1bf099d6942399ea0b34a62e5f0bc4c5c36e'/>
<id>5a5a1bf099d6942399ea0b34a62e5f0bc4c5c36e</id>
<content type='text'>
Pull x86 RAS changes from Ingo Molnar:

 - Add an Intel CMCI hotplug fix

 - Add AMD family 16h EDAC support

 - Make the AMD MCE banks code more flexible for virtual environments

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  amd64_edac: Add Family 16h support
  x86/mce: Rework cmci_rediscover() to play well with CPU hotplug
  x86, MCE, AMD: Use MCG_CAP MSR to find out number of banks on AMD
  x86, MCE, AMD: Replace shared_bank array with is_shared_bank() helper
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull x86 RAS changes from Ingo Molnar:

 - Add an Intel CMCI hotplug fix

 - Add AMD family 16h EDAC support

 - Make the AMD MCE banks code more flexible for virtual environments

* 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  amd64_edac: Add Family 16h support
  x86/mce: Rework cmci_rediscover() to play well with CPU hotplug
  x86, MCE, AMD: Use MCG_CAP MSR to find out number of banks on AMD
  x86, MCE, AMD: Replace shared_bank array with is_shared_bank() helper
</pre>
</div>
</content>
</entry>
<entry>
<title>amd64_edac: Add Family 16h support</title>
<updated>2013-04-19T10:46:50+00:00</updated>
<author>
<name>Aravind Gopalakrishnan</name>
<email>Aravind.Gopalakrishnan@amd.com</email>
</author>
<published>2013-04-17T19:57:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=94c1acf2c85b03a59a42d931a94a13a76c123a62'/>
<id>94c1acf2c85b03a59a42d931a94a13a76c123a62</id>
<content type='text'>
Add code to handle DRAM ECC errors decoding for Fam16h.

Tested on Fam16h with ECC turned on using the mce_amd_inj facility and
works fine.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
[ Boris: cleanups and clarifications ]
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add code to handle DRAM ECC errors decoding for Fam16h.

Tested on Fam16h with ECC turned on using the mce_amd_inj facility and
works fine.

Signed-off-by: Aravind Gopalakrishnan &lt;Aravind.Gopalakrishnan@amd.com&gt;
[ Boris: cleanups and clarifications ]
Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>x86: Constify a few items</title>
<updated>2013-03-11T14:11:03+00:00</updated>
<author>
<name>Jan Beulich</name>
<email>JBeulich@suse.com</email>
</author>
<published>2013-03-11T09:56:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=c391c7884633cdc317a60fbf152d1764282fe633'/>
<id>c391c7884633cdc317a60fbf152d1764282fe633</id>
<content type='text'>
This in particular re-does the compiler warning fix 9faec5b
("perf/x86: Fix P6 driver section warning"), tightening the
section attributes rather than relaxing them.

Signed-off-by: Jan Beulich &lt;jbeulich@suse.com&gt;
Cc: Shaun Ruffell &lt;sruffell@digium.com&gt;
Cc: yangyongqiang &lt;yangyongqiang01@baidu.com&gt;
Cc: Cyrill Gorcunov &lt;gorcunov@gmail.com&gt;
Cc: Vince Weaver &lt;vincent.weaver@maine.edu&gt;
Link: http://lkml.kernel.org/r/513DB84502000078000C4880@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This in particular re-does the compiler warning fix 9faec5b
("perf/x86: Fix P6 driver section warning"), tightening the
section attributes rather than relaxing them.

Signed-off-by: Jan Beulich &lt;jbeulich@suse.com&gt;
Cc: Shaun Ruffell &lt;sruffell@digium.com&gt;
Cc: yangyongqiang &lt;yangyongqiang01@baidu.com&gt;
Cc: Cyrill Gorcunov &lt;gorcunov@gmail.com&gt;
Cc: Vince Weaver &lt;vincent.weaver@maine.edu&gt;
Link: http://lkml.kernel.org/r/513DB84502000078000C4880@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branch 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip</title>
<updated>2012-07-22T23:07:45+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2012-07-22T23:07:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=5b160bd426946c85f32b15e5d34d62d2618a5a87'/>
<id>5b160bd426946c85f32b15e5d34d62d2618a5a87</id>
<content type='text'>
Pull x86/mce changes from Ingo Molnar:
 "This tree improves the AMD thresholding bank code and includes a
  memory fault signal handling fixlet."

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Fix siginfo_t-&gt;si_addr value for non-recoverable memory faults
  x86, MCE, AMD: Update copyrights and boilerplate
  x86, MCE, AMD: Give proper names to the thresholding banks
  x86, MCE, AMD: Make error_count read only
  x86, MCE, AMD: Cleanup reading of error_count
  x86, MCE, AMD: Print decimal thresholding values
  x86, MCE, AMD: Move shared bank to node descriptor
  x86, MCE, AMD: Remove local_allocate_... wrapper
  x86, MCE, AMD: Remove shared banks sysfs linking
  x86, amd_nb: Export model 0x10 and later PCI id
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull x86/mce changes from Ingo Molnar:
 "This tree improves the AMD thresholding bank code and includes a
  memory fault signal handling fixlet."

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Fix siginfo_t-&gt;si_addr value for non-recoverable memory faults
  x86, MCE, AMD: Update copyrights and boilerplate
  x86, MCE, AMD: Give proper names to the thresholding banks
  x86, MCE, AMD: Make error_count read only
  x86, MCE, AMD: Cleanup reading of error_count
  x86, MCE, AMD: Print decimal thresholding values
  x86, MCE, AMD: Move shared bank to node descriptor
  x86, MCE, AMD: Remove local_allocate_... wrapper
  x86, MCE, AMD: Remove shared banks sysfs linking
  x86, amd_nb: Export model 0x10 and later PCI id
</pre>
</div>
</content>
</entry>
</feed>
