<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel.git/drivers/gpu/drm/etnaviv/etnaviv_buffer.c, branch linux-5.3.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.
</subtitle>
<id>https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-5.3.y</id>
<link rel='self' href='https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-5.3.y'/>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/'/>
<updated>2018-12-18T10:55:16Z</updated>
<entry>
<title>drm/etnaviv: remove lastctx member from gpu struct</title>
<updated>2018-12-18T10:55:16Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2018-11-22T14:29:27Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=801c7a1e528623f073c4007cb04d9a817e33b3a4'/>
<id>urn:sha1:801c7a1e528623f073c4007cb04d9a817e33b3a4</id>
<content type='text'>
It only written and we don't infer any useful information from
it anymore. Remove it.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: replace license text with SPDX tags</title>
<updated>2018-05-18T13:27:56Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2018-05-08T14:20:54Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=f6ffbd4fc1a1caafe2ab840993b917fba5324598'/>
<id>urn:sha1:f6ffbd4fc1a1caafe2ab840993b917fba5324598</id>
<content type='text'>
This replaces the repetitive GPL-2.0 license text in code and header files
with the SPDX tags. Generated hardware headers aren't changed, as any changes
there need to be done in the upstream rnndb repository.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: add function to load the initial PTA state</title>
<updated>2018-03-09T11:22:38Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2018-01-22T11:28:10Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=1137bef67a11d2e5a4f44ce87b6e4dd1fb7a0163'/>
<id>urn:sha1:1137bef67a11d2e5a4f44ce87b6e4dd1fb7a0163</id>
<content type='text'>
On GPUs with the security feature the MTLB config is stored in the PTA.
Add a function to trigger the initial PTA load through the FE.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: move cmdbuf into submit object</title>
<updated>2018-01-02T16:33:36Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-11-24T15:56:37Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=2f9225dbc09abe7cacb9820ebdeef5b6c0eb9c72'/>
<id>urn:sha1:2f9225dbc09abe7cacb9820ebdeef5b6c0eb9c72</id>
<content type='text'>
Less dynamic allocations and slims down the cmdbuf object to only the
required information, as everything else is already available in the
submit object.

This also simplifies buffer and mappings lifetime management, as they
are now exlusively attached to the submit object and not additionally
to the cmdbuf.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: move exec_state to submit object</title>
<updated>2018-01-02T16:32:40Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-11-24T14:16:58Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=797b0159e6b9124c24968c9b2b4631eba7c112b9'/>
<id>urn:sha1:797b0159e6b9124c24968c9b2b4631eba7c112b9</id>
<content type='text'>
We'll need this in some places where only the submit is available. Also
this is a first step at slimming down the cmdbuf object.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: add lockdep annotations to buffer manipulation functions</title>
<updated>2018-01-02T16:25:44Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-11-17T16:51:19Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=b6d6223f5029d3c4fe466ce1711fe4cb23d06013'/>
<id>urn:sha1:b6d6223f5029d3c4fe466ce1711fe4cb23d06013</id>
<content type='text'>
When manipulating the kernel command buffer the GPU mutex must be held, as
otherwise different callers might try to replace the same part of the
buffer, wreacking havok in the GPU execution.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Philipp Zabel &lt;p.zabel@pengutronix.de&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: remove switch_context member from etnaviv_gpu</title>
<updated>2018-01-02T16:21:37Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-11-17T16:19:50Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=4375ffffbf099f14815380a3d9e5784ffc55bf31'/>
<id>urn:sha1:4375ffffbf099f14815380a3d9e5784ffc55bf31</id>
<content type='text'>
There is no need to store this in the gpu struct. MMU flushes are triggered
correctly in reaction to MMU maps and unmaps, independent of the current ctx.
Any required pipe switches can be infered from the current and the desired
GPU exec state.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Philipp Zabel &lt;p.zabel@pengutronix.de&gt;
Reviewed-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: add 'sync point' support</title>
<updated>2017-10-10T09:45:45Z</updated>
<author>
<name>Christian Gmeiner</name>
</author>
<published>2017-09-24T13:15:28Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=357713ce9bc86c1ae7ba804731d8db542944463c'/>
<id>urn:sha1:357713ce9bc86c1ae7ba804731d8db542944463c</id>
<content type='text'>
In order to support performance counters in a sane way we need to provide
a method to sync the GPU with the CPU. The GPU can process multpile command
buffers/events per irq. With the help of a 'sync point' we can trigger an event
and stop the GPU/FE immediately. When the CPU is done with is processing it
simply needs to restart the FE and the GPU will process the command stream.

Changes from v1 -&gt; v2:
- process sync point with a work item to keep irq as fast as possible

Changes from v4 -&gt; v5:
- renamed pmrs_* to sync_point_*
- call event_free(..) in sync_point_worker(..)

Signed-off-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: wire up iova handling in new cmdbuf abstraction</title>
<updated>2017-02-02T09:30:20Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-01-16T15:52:44Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=c3ef4b8c3e108397980014a4616c56f50026d547'/>
<id>urn:sha1:c3ef4b8c3e108397980014a4616c56f50026d547</id>
<content type='text'>
Don't call the IOMMU directly, but go through the new cmdbuf abstraction.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/etnaviv: move cmdbuf de-/allocation into own file</title>
<updated>2017-02-02T09:30:15Z</updated>
<author>
<name>Lucas Stach</name>
</author>
<published>2017-01-16T15:09:51Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=ea1f5729aa1bbe68f9a394e259288d6ff894b0aa'/>
<id>urn:sha1:ea1f5729aa1bbe68f9a394e259288d6ff894b0aa</id>
<content type='text'>
This will get more complex with the following changes, so move it
into its own place.

Signed-off-by: Lucas Stach &lt;l.stach@pengutronix.de&gt;
Reviewed-by: Christian Gmeiner &lt;christian.gmeiner@gmail.com&gt;
</content>
</entry>
</feed>
