<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/drivers/ntb, branch v4.2-rc3</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>NTB: Add split BAR output for debugfs stats</title>
<updated>2015-07-04T18:09:32+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-06-18T09:17:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=bf44fe4671f97ee17d178e08c2d3b346188d062b'/>
<id>bf44fe4671f97ee17d178e08c2d3b346188d062b</id>
<content type='text'>
When split BAR is enabled, the driver needs to dump out the split BAR
registers rather than the original 64bit BAR registers.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When split BAR is enabled, the driver needs to dump out the split BAR
registers rather than the original 64bit BAR registers.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Change WARN_ON_ONCE to pr_warn_once on unsafe</title>
<updated>2015-07-04T18:09:30+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-06-15T12:22:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=fd839bf88485878ec602dbb3146fd44769eb3784'/>
<id>fd839bf88485878ec602dbb3146fd44769eb3784</id>
<content type='text'>
The unsafe doorbell and scratchpad access should display reason when
WARN is called.  Otherwise we get a stack dump without any explanation.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The unsafe doorbell and scratchpad access should display reason when
WARN is called.  Otherwise we get a stack dump without any explanation.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Print driver name and version in module init</title>
<updated>2015-07-04T18:09:28+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-06-15T12:21:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=7eb387813db6730a5793cd53077b4039d948d17f'/>
<id>7eb387813db6730a5793cd53077b4039d948d17f</id>
<content type='text'>
Printouts driver name and version to indicate what is being loaded.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Printouts driver name and version to indicate what is being loaded.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Increase transport MTU to 64k from 16k</title>
<updated>2015-07-04T18:09:27+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-06-03T15:29:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=9891417de8a816de60faea8a2ff7a04c4b3cf3a1'/>
<id>9891417de8a816de60faea8a2ff7a04c4b3cf3a1</id>
<content type='text'>
Benchmarking showed a significant performance increase with the MTU size
to 64k instead of 16k.  Change the driver default to 64k.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Benchmarking showed a significant performance increase with the MTU size
to 64k instead of 16k.  Change the driver default to 64k.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Rename Intel code names to platform names</title>
<updated>2015-07-04T18:09:25+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-05-20T16:55:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=2f887b9a44015a8146d52e40bef9e2b7bc6cd275'/>
<id>2f887b9a44015a8146d52e40bef9e2b7bc6cd275</id>
<content type='text'>
Instead of using the platform code names, use the correct platform names
to identify the respective Intel NTB hardware.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Instead of using the platform code names, use the correct platform names
to identify the respective Intel NTB hardware.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Default to CPU memcpy for performance</title>
<updated>2015-07-04T18:09:24+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-05-19T20:52:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=a41ef053f700618f5f55a1dd658908a71163400b'/>
<id>a41ef053f700618f5f55a1dd658908a71163400b</id>
<content type='text'>
Disable DMA usage by default, since the CPU provides much better
performance with write combining.  Provide a module parameter to enable
DMA usage when offloading the memcpy is preferred.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Disable DMA usage by default, since the CPU provides much better
performance with write combining.  Provide a module parameter to enable
DMA usage when offloading the memcpy is preferred.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Improve performance with write combining</title>
<updated>2015-07-04T18:09:21+00:00</updated>
<author>
<name>Dave Jiang</name>
<email>dave.jiang@intel.com</email>
</author>
<published>2015-05-19T20:45:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=06917f753547e6bba8a5d17f79971d1c071a70dd'/>
<id>06917f753547e6bba8a5d17f79971d1c071a70dd</id>
<content type='text'>
Changing the memory window BAR mappings to write combining significantly
boosts the performance.  We will also use memcpy that uses non-temporal
store, which showed performance improvement when doing non-cached
memcpys.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Changing the memory window BAR mappings to write combining significantly
boosts the performance.  We will also use memcpy that uses non-temporal
store, which showed performance improvement when doing non-cached
memcpys.

Signed-off-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Use NUMA memory in Intel driver</title>
<updated>2015-07-04T18:09:19+00:00</updated>
<author>
<name>Allen Hubbe</name>
<email>Allen.Hubbe@emc.com</email>
</author>
<published>2015-05-19T16:04:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=0e041fb5369975c183d22ffeb156ea0dae760088'/>
<id>0e041fb5369975c183d22ffeb156ea0dae760088</id>
<content type='text'>
Allocate memory for the NUMA node of the NTB device.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Allocate memory for the NUMA node of the NTB device.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Use NUMA memory and DMA chan in transport</title>
<updated>2015-07-04T18:08:33+00:00</updated>
<author>
<name>Allen Hubbe</name>
<email>Allen.Hubbe@emc.com</email>
</author>
<published>2015-05-18T10:20:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=1199aa61264a74717bc747e7031673242bad5119'/>
<id>1199aa61264a74717bc747e7031673242bad5119</id>
<content type='text'>
Allocate memory and request the DMA channel for the same NUMA node as
the NTB device.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Allocate memory and request the DMA channel for the same NUMA node as
the NTB device.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>NTB: Rate limit ntb_qp_link_work</title>
<updated>2015-07-04T18:08:30+00:00</updated>
<author>
<name>Allen Hubbe</name>
<email>Allen.Hubbe@emc.com</email>
</author>
<published>2015-05-11T14:08:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=2876228941ac5dcab12854aa5a3462b3f2274b09'/>
<id>2876228941ac5dcab12854aa5a3462b3f2274b09</id>
<content type='text'>
When the ntb transport is connecting and waiting for the peer, the debug
console receives lots of debug level messages about the remote qp link
status being down.  Rate limit those messages.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When the ntb transport is connecting and waiting for the peer, the debug
console receives lots of debug level messages about the remote qp link
status being down.  Rate limit those messages.

Signed-off-by: Allen Hubbe &lt;Allen.Hubbe@emc.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</pre>
</div>
</content>
</entry>
</feed>
