<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c, branch v5.12</title>
<subtitle>Mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
</subtitle>
<id>https://git.shady.money/linux/atom?h=v5.12</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.12'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2021-01-25T22:46:48Z</updated>
<entry>
<title>drm/amd/amdgpu: add error handling to amdgpu_virt_read_pf2vf_data</title>
<updated>2021-01-25T22:46:48Z</updated>
<author>
<name>Jingwen Chen</name>
<email>Jingwen.Chen2@amd.com</email>
</author>
<published>2021-01-19T08:54:50Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=64dcf2f01d59cf9fad19b1a387bd39736a8f4d69'/>
<id>urn:sha1:64dcf2f01d59cf9fad19b1a387bd39736a8f4d69</id>
<content type='text'>
[Why]
when vram lost happened in guest, try to write vram can lead to
kernel stuck.

[How]
When the readback data is invalid, don't do write work, directly
reschedule a new work.

Signed-off-by: Jingwen Chen &lt;Jingwen.Chen2@amd.com&gt;
Reviewed-by: Monk Liu&lt;monk.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amd/amdgpu: remove redundant flush_delayed_work</title>
<updated>2021-01-20T21:38:17Z</updated>
<author>
<name>Jingwen Chen</name>
<email>Jingwen.Chen2@amd.com</email>
</author>
<published>2021-01-18T02:30:36Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=b43ae488ac3191feb119ffdda22d28f72a99c1e3'/>
<id>urn:sha1:b43ae488ac3191feb119ffdda22d28f72a99c1e3</id>
<content type='text'>
When using cancel_delayed_work_sync, there's no need
to flush_delayed_work first. This sequence can lead to
a redundant loop of work executing.

Signed-off-by: Jingwen Chen &lt;Jingwen.Chen2@amd.com&gt;
Reviewed-by: Monk Liu &lt;monk.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/sriov Stop data exchange for wholegpu reset</title>
<updated>2021-01-14T04:47:39Z</updated>
<author>
<name>Jack Zhang</name>
<email>Jack.Zhang1@amd.com</email>
</author>
<published>2021-01-07T10:38:29Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3c2a01cb0fc567c18b802f25d619e31c196294ce'/>
<id>urn:sha1:3c2a01cb0fc567c18b802f25d619e31c196294ce</id>
<content type='text'>
[Why]
When host trigger a whole gpu reset, guest will keep
waiting till host finish reset. But there's a work
queue in guest exchanging data between vf&amp;pf which need
to access frame buffer. During whole gpu reset, frame
buffer is not accessable, and this causes the call trace.

[How]
After vf get reset notification from pf, stop data exchange.

Signed-off-by: Jingwen Chen &lt;Jingwen.Chen2@amd.com&gt;
Signed-off-by: Jack Zhang &lt;Jack.Zhang1@amd.com&gt;
Reviewed-by: Monk Liu &lt;monk.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>Merge tag 'amd-drm-next-5.11-2020-12-09' of git://people.freedesktop.org/~agd5f/linux into drm-next</title>
<updated>2020-12-10T06:55:53Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2020-12-10T06:55:41Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=b10733527bfd864605c33ab2e9a886eec317ec39'/>
<id>urn:sha1:b10733527bfd864605c33ab2e9a886eec317ec39</id>
<content type='text'>
amd-drm-next-5.11-2020-12-09:

amdgpu:
- SR-IOV fixes
- Navy Flounder updates
- Sienna Cichlid updates
- Dimgrey Cavefish updates
- Vangogh updates
- Misc SMU fixes
- Misc display fixes
- Last big hunk of W=1 warning fixes
- Cursor validation fixes
- CI BACO updates

From: Alex Deucher &lt;alexdeucher@gmail.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20201210045344.21566-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/amd/amdgpu/amdgpu_virt: Correct possible copy/paste or doc-rot misnaming issue</title>
<updated>2020-11-24T17:09:52Z</updated>
<author>
<name>Lee Jones</name>
<email>lee.jones@linaro.org</email>
</author>
<published>2020-11-23T11:18:43Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f59bf24e4b85f1d79dfe3d136513e3645a99e43e'/>
<id>urn:sha1:f59bf24e4b85f1d79dfe3d136513e3645a99e43e</id>
<content type='text'>
Fixes the following W=1 kernel build warning(s):

 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:115: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_request_full_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:115: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_request_full_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:138: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_release_full_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:138: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_release_full_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:159: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_reset_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:159: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_reset_gpu'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:194: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_wait_reset'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:194: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_wait_reset'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:210: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_alloc_mm_table'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:210: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_alloc_mm_table'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:239: warning: Function parameter or member 'adev' not described in 'amdgpu_virt_free_mm_table'
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:239: warning: Excess function parameter 'amdgpu' description in 'amdgpu_virt_free_mm_table'

Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: "Christian König" &lt;christian.koenig@amd.com&gt;
Cc: David Airlie &lt;airlied@linux.ie&gt;
Cc: Daniel Vetter &lt;daniel@ffwll.ch&gt;
Cc: amd-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Lee Jones &lt;lee.jones@linaro.org&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>amd/amdgpu: use kmalloc_array to replace kmalloc with multiply</title>
<updated>2020-11-24T17:04:39Z</updated>
<author>
<name>Bernard Zhao</name>
<email>bernard@vivo.com</email>
</author>
<published>2020-11-18T02:55:01Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=95666c6cfe9247610efbd68c228f0831d4c18a51'/>
<id>urn:sha1:95666c6cfe9247610efbd68c228f0831d4c18a51</id>
<content type='text'>
Fix check_patch.pl warning:
WARNING: Prefer kmalloc_array over kmalloc with multiply
+bps = kmalloc(align_space * sizeof((*data)-&gt;bps), GFP_KERNEL);
WARNING: Prefer kmalloc_array over kmalloc with multiply
+bps_bo = kmalloc(align_space * sizeof((*data)-&gt;bps_bo),
GFP_KERNEL);
kmalloc_array has multiply overflow check, which will be safer.

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Bernard Zhao &lt;bernard@vivo.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amd/amdgpu/amdgpu_virt: Make local function 'amdgpu_virt_update_vf2pf_work_item()' static</title>
<updated>2020-11-13T22:29:46Z</updated>
<author>
<name>Lee Jones</name>
<email>lee.jones@linaro.org</email>
</author>
<published>2020-11-13T13:49:19Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=05ed830e49a8cb8a20e9e6044376beb6c2dd7d72'/>
<id>urn:sha1:05ed830e49a8cb8a20e9e6044376beb6c2dd7d72</id>
<content type='text'>
Fixes the following W=1 kernel build warning(s):

 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:560:6: warning: no previous prototype for ‘amdgpu_virt_update_vf2pf_work_item’ [-Wmissing-prototypes]

Cc: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Cc: "Christian König" &lt;christian.koenig@amd.com&gt;
Cc: David Airlie &lt;airlied@linux.ie&gt;
Cc: Daniel Vetter &lt;daniel@ffwll.ch&gt;
Cc: amd-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Lee Jones &lt;lee.jones@linaro.org&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu/virt: fix handling of the atomic flag</title>
<updated>2020-11-06T09:31:26Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexdeucher@gmail.com</email>
</author>
<published>2020-11-04T10:04:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=e431eb8089eef1477082d6ae072ac252699b231f'/>
<id>urn:sha1:e431eb8089eef1477082d6ae072ac252699b231f</id>
<content type='text'>
Use the per device drm driver feature flags rather than the
global one.  This way we can make the drm driver struct const.

Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Reviewed-by: Luben Tuikov &lt;luben.tuikov@amd.com&gt;
Signed-off-by: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20201104100425.1922351-3-daniel.vetter@ffwll.ch
</content>
</entry>
<entry>
<title>drm/amdgpu: Implement new guest side VF2PF message transaction (v2)</title>
<updated>2020-09-25T21:03:22Z</updated>
<author>
<name>Bokun Zhang</name>
<email>Bokun.Zhang@amd.com</email>
</author>
<published>2020-07-28T19:29:12Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=519b8b76f0b62a0be0d9fcee39819d2461fc3cb0'/>
<id>urn:sha1:519b8b76f0b62a0be0d9fcee39819d2461fc3cb0</id>
<content type='text'>
- Refactor the driver code to use amdgpu_virt_read_pf2vf_data
  and amdgpu_virt_write_vf2pf_data instead of writing all code in
  one function (which is the old amdgpu_virt_init_data_exchange)

- Adding a new transaction method for VF2PF message between host
  and guest driver. Guest side will periodically update VF2PF
  message in the framebuffer.

  In the new header, we include guest ucode information, guest
  framebuffer usage, and engine usage

- Clean up the old macros since they will cause compile error if
  the new transaction method is used

v2: squash in build fix

Signed-off-by: Bokun Zhang &lt;Bokun.Zhang@amd.com&gt;
Reviewed-by: Monk Liu &lt;monk.liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Get DRM dev from adev by inline-f</title>
<updated>2020-08-24T17:06:06Z</updated>
<author>
<name>Luben Tuikov</name>
<email>luben.tuikov@amd.com</email>
</author>
<published>2020-08-24T16:29:45Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=4a580877bdcb837e7a3754ae20798dcfccb44e80'/>
<id>urn:sha1:4a580877bdcb837e7a3754ae20798dcfccb44e80</id>
<content type='text'>
Add a static inline adev_to_drm() to obtain
the DRM device pointer from an amdgpu_device pointer.

Signed-off-by: Luben Tuikov &lt;luben.tuikov@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
