<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/include/uapi/drm/nouveau_drm.h, branch linux-5.2.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.</subtitle>
<id>https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-5.2.y</id>
<link rel='self' href='https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-5.2.y'/>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/'/>
<updated>2019-02-19T23:00:03Z</updated>
<entry>
<title>drm/nouveau/svm: new ioctl to migrate process memory to GPU memory</title>
<updated>2019-02-19T23:00:03Z</updated>
<author>
<name>Jérôme Glisse</name>
<email>jglisse@redhat.com</email>
</author>
<published>2018-08-07T20:13:16Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=f180bf12ac061f093abb9247505f661817973cae'/>
<id>urn:sha1:f180bf12ac061f093abb9247505f661817973cae</id>
<content type='text'>
This add an ioctl to migrate a range of process address space to the
device memory. On platform without cache coherent bus (x86, ARM, ...)
this means that CPU can not access that range directly, instead CPU
will fault which will migrate the memory back to system memory.

This is behind a staging flag so that we can evolve the API.

Signed-off-by: Jérôme Glisse &lt;jglisse@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau/svm: initial support for shared virtual memory</title>
<updated>2019-02-19T23:00:02Z</updated>
<author>
<name>Ben Skeggs</name>
<email>bskeggs@redhat.com</email>
</author>
<published>2018-07-05T02:57:12Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=eeaf06ac1a5584e41cf289f8351e446bb131374b'/>
<id>urn:sha1:eeaf06ac1a5584e41cf289f8351e446bb131374b</id>
<content type='text'>
This uses HMM to mirror a process' CPU page tables into a channel's page
tables, and keep them synchronised so that both the CPU and GPU are able
to access the same memory at the same virtual address.

While this code also supports Volta/Turing, it's only enabled for Pascal
GPUs currently due to channel recovery being unreliable right now on the
later GPUs.

Signed-off-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau: drop drm/ prefix from include</title>
<updated>2016-05-13T13:06:10Z</updated>
<author>
<name>Emil Velikov</name>
<email>emil.l.velikov@gmail.com</email>
</author>
<published>2016-04-07T18:05:47Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=c6734c689a26591fe43946ffa8911f22e7c631c6'/>
<id>urn:sha1:c6734c689a26591fe43946ffa8911f22e7c631c6</id>
<content type='text'>
Similar to the rest of the DRM UAPI - these are to be imported
unmodified into libdrm. In current form that's impossible.

Signed-off-by: Emil Velikov &lt;emil.l.velikov@gmail.com&gt;
Acked-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau: add extern C guard for the UAPI header</title>
<updated>2016-05-13T13:06:09Z</updated>
<author>
<name>Emil Velikov</name>
<email>emil.l.velikov@gmail.com</email>
</author>
<published>2016-04-07T18:05:06Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=8daf6359c48dc42979463f5cd575948b46a8143b'/>
<id>urn:sha1:8daf6359c48dc42979463f5cd575948b46a8143b</id>
<content type='text'>
Signed-off-by: Emil Velikov &lt;emil.l.velikov@gmail.com&gt;
Acked-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>nouveau_drm.h: use __u32 and __u64 from linux/types.h</title>
<updated>2015-12-10T11:33:23Z</updated>
<author>
<name>Mikko Rapeli</name>
<email>mikko.rapeli@iki.fi</email>
</author>
<published>2014-08-31T11:09:51Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=8860487ef39bef5765354ec7dd195983b49f9349'/>
<id>urn:sha1:8860487ef39bef5765354ec7dd195983b49f9349</id>
<content type='text'>
Fixes userspace compilation errors like:

drm/nouveau_drm.h:41:2: error: unknown type name ‘uint32_t’

Signed-off-by: Mikko Rapeli &lt;mikko.rapeli@iki.fi&gt;
</content>
</entry>
<entry>
<title>drm/nouveau: remove unnecessary usage of object handles</title>
<updated>2015-11-03T05:02:18Z</updated>
<author>
<name>Ben Skeggs</name>
<email>bskeggs@redhat.com</email>
</author>
<published>2015-09-04T04:40:32Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=fcf3f91c34105c3551741febbfc1066aaa7f1db7'/>
<id>urn:sha1:fcf3f91c34105c3551741febbfc1066aaa7f1db7</id>
<content type='text'>
No longer required in a lot of cases, as objects are identified over NVIF
via an alternate mechanism since the rework.

Signed-off-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau/gem: allow user-space to specify an object should be coherent</title>
<updated>2015-04-14T07:00:46Z</updated>
<author>
<name>Alexandre Courbot</name>
<email>acourbot@nvidia.com</email>
</author>
<published>2015-02-26T03:44:51Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=996f545fbb0dc9ed4a640b5ef098f51fe28cca5c'/>
<id>urn:sha1:996f545fbb0dc9ed4a640b5ef098f51fe28cca5c</id>
<content type='text'>
User-space use mappable BOs notably for fences, and expects that a
value update by the GPU will be immediatly visible through the
user-space mapping.

ARM has a property that may prevent this from happening though: memory
can be mapped multiple times only if the different mappings share the
same caching properties. However all the lowmem memory is already
identity-mapped into the kernel with cache enabled, so when user-space
requests an uncached mapping, we actually get an "undefined caching
policy" one and this has strange side-effects described on Freedesktop
bug 86690.

To prevent this from happening, allow user-space to explicitly specify
which objects should be coherent, and create such objects with the
TTM_PL_FLAG_UNCACHED flag. This will make TTM allocate memory using the
DMA API, which will fix the identify mapping and allow us to safely map
the objects to user-space uncached.

Signed-off-by: Alexandre Courbot &lt;acourbot@nvidia.com&gt;
Reviewed-by: Lucas Stach &lt;dev@lynxeye.de&gt;
Signed-off-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau: expose the full object/event interfaces to userspace</title>
<updated>2014-08-09T19:28:18Z</updated>
<author>
<name>Ben Skeggs</name>
<email>bskeggs@redhat.com</email>
</author>
<published>2014-08-09T18:10:31Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=27111a23d01c1dba3180c998629004ab4c9ac985'/>
<id>urn:sha1:27111a23d01c1dba3180c998629004ab4c9ac985</id>
<content type='text'>
Signed-off-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/nouveau: use ioctl interface for abi16 grobj alloc</title>
<updated>2014-08-09T19:13:17Z</updated>
<author>
<name>Ben Skeggs</name>
<email>bskeggs@redhat.com</email>
</author>
<published>2014-08-09T18:10:23Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=a4e610b5e655186f81f18f027d2b7a15e010cbef'/>
<id>urn:sha1:a4e610b5e655186f81f18f027d2b7a15e010cbef</id>
<content type='text'>
Signed-off-by: Ben Skeggs &lt;bskeggs@redhat.com&gt;
</content>
</entry>
<entry>
<title>UAPI: (Scripted) Disintegrate include/drm</title>
<updated>2012-10-04T17:21:50Z</updated>
<author>
<name>David Howells</name>
<email>dhowells@redhat.com</email>
</author>
<published>2012-10-04T17:21:50Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=718dcedd7e87f448a1eeeda4d1a986284c243110'/>
<id>urn:sha1:718dcedd7e87f448a1eeeda4d1a986284c243110</id>
<content type='text'>
Signed-off-by: David Howells &lt;dhowells@redhat.com&gt;
Acked-by: Arnd Bergmann &lt;arnd@arndb.de&gt;
Acked-by: Thomas Gleixner &lt;tglx@linutronix.de&gt;
Acked-by: Michael Kerrisk &lt;mtk.manpages@gmail.com&gt;
Acked-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
Acked-by: Dave Jones &lt;davej@redhat.com&gt;
</content>
</entry>
</feed>
