<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c, branch v5.17</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=v5.17</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.17'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2022-01-18T23:00:58Z</updated>
<entry>
<title>drm/amd/amdgpu: fixing read wrong pf2vf data in SRIOV</title>
<updated>2022-01-18T23:00:58Z</updated>
<author>
<name>Jingwen Chen</name>
<email>Jingwen.Chen2@amd.com</email>
</author>
<published>2022-01-13T11:06:59Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=9a458402fb69bda886aa6cbe067311b6e3d9c52a'/>
<id>urn:sha1:9a458402fb69bda886aa6cbe067311b6e3d9c52a</id>
<content type='text'>
[Why]
This fixes 892deb48269c ("drm/amdgpu: Separate vf2pf work item init from virt data exchange").
we should read pf2vf data based at mman.fw_vram_usage_va after gmc
sw_init. commit 892deb48269c breaks this logic.

[How]
calling amdgpu_virt_exchange_data in amdgpu_virt_init_data_exchange to
set the right base in the right sequence.

v2:
call amdgpu_virt_init_data_exchange after gmc sw_init to make data
exchange workqueue run

v3:
clean up the code logic

v4:
add some comment and make the code more readable

Fixes: 892deb48269c ("drm/amdgpu: Separate vf2pf work item init from virt data exchange")
Signed-off-by: Jingwen Chen &lt;Jingwen.Chen2@amd.com&gt;
Reviewed-by: Horace Chen &lt;horace.chen@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: invert the logic in amdgpu_device_should_recover_gpu()</title>
<updated>2022-01-14T23:06:44Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2022-01-11T22:41:44Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=0ffb1fd1582a78649f22253d81515997fff88bc4'/>
<id>urn:sha1:0ffb1fd1582a78649f22253d81515997fff88bc4</id>
<content type='text'>
Rather than opting into GPU recovery support, default to on, and
opt out if it's not working on a particular GPU.  This avoids the
need to add new asics to this list since this is a core feature.

Reviewed-by: Evan Quan &lt;evan.quan@amd.com&gt;
Reviewed-by: Guchun Chen &lt;guchun.chen@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Enable recovery on yellow carp</title>
<updated>2022-01-14T23:06:44Z</updated>
<author>
<name>CHANDAN VURDIGERE NATARAJ</name>
<email>chandan.vurdigerenataraj@amd.com</email>
</author>
<published>2022-01-11T13:32:26Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=4175c32be5ef0ff254d6931931ec412e8029c32a'/>
<id>urn:sha1:4175c32be5ef0ff254d6931931ec412e8029c32a</id>
<content type='text'>
Add yellow carp to devices which support recovery

Signed-off-by: CHANDAN VURDIGERE NATARAJ &lt;chandan.vurdigerenataraj@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>
<entry>
<title>drm/amdgpu: not return error on the init_apu_flags</title>
<updated>2022-01-11T20:44:27Z</updated>
<author>
<name>Prike Liang</name>
<email>Prike.Liang@amd.com</email>
</author>
<published>2021-11-26T07:12:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=4eaf21b752891fffab3d51ac96e81194cda32d1c'/>
<id>urn:sha1:4eaf21b752891fffab3d51ac96e81194cda32d1c</id>
<content type='text'>
In some APU project we needn't always assign flags to identify each other,
so we may not need return an error.

Signed-off-by: Prike Liang &lt;Prike.Liang@amd.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amd/amdgpu: Add pcie indirect support to amdgpu_mm_wreg_mmio_rlc()</title>
<updated>2022-01-11T20:44:26Z</updated>
<author>
<name>Tom St Denis</name>
<email>tom.stdenis@amd.com</email>
</author>
<published>2022-01-07T11:57:41Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=4cc9f86f851847e5ebfb56212d81f1a30b9d392b'/>
<id>urn:sha1:4cc9f86f851847e5ebfb56212d81f1a30b9d392b</id>
<content type='text'>
The function amdgpu_mm_wreg_mmio_rlc() is used by debugfs to write to
MMIO registers.  It didn't support registers beyond the BAR mapped MMIO
space.  This adds pcie indirect write support.

Signed-off-by: Tom St Denis &lt;tom.stdenis@amd.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: recover gart table at resume</title>
<updated>2022-01-11T20:44:26Z</updated>
<author>
<name>Nirmoy Das</name>
<email>nirmoy.das@amd.com</email>
</author>
<published>2022-01-07T08:51:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=575e55ee4fbc2c641a29b0054b3473e9fa81ae76'/>
<id>urn:sha1:575e55ee4fbc2c641a29b0054b3473e9fa81ae76</id>
<content type='text'>
Get rid off pin/unpin of gart BO at resume/suspend and
instead pin only once and try to recover gart content
at resume time. This is much more stable in case there
is OOM situation at 2nd call to amdgpu_device_evict_resources()
while evicting GART table.

v3: remove gart recovery from other places
v2: pin gart at amdgpu_gart_table_vram_alloc()

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Nirmoy Das &lt;nirmoy.das@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: do not pass ttm_resource_manager to gtt_mgr</title>
<updated>2022-01-11T20:44:26Z</updated>
<author>
<name>Nirmoy Das</name>
<email>nirmoy.das@amd.com</email>
</author>
<published>2022-01-07T22:42:28Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=1dd8b1b987fad93b647cb0fa5289d69b4c889dc2'/>
<id>urn:sha1:1dd8b1b987fad93b647cb0fa5289d69b4c889dc2</id>
<content type='text'>
Do not allow exported amdgpu_gtt_mgr_*() to accept
any ttm_resource_manager pointer. Also there is no need
to force other module to call a ttm function just to
eventually call gtt_mgr functions.

v4: remove unused adev.
v3: upcast mgr from ttm resopurce manager instead of
getting it from adev.
v2: pass adev's gtt_mgr instead of adev.

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Nirmoy Das &lt;nirmoy.das@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Unmap MMIO mappings when device is not unplugged</title>
<updated>2022-01-11T20:44:26Z</updated>
<author>
<name>Leslie Shi</name>
<email>Yuliang.Shi@amd.com</email>
</author>
<published>2022-01-05T02:57:20Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=62d5f9f7110ad374db67ab4820f4ff2d916c3cdb'/>
<id>urn:sha1:62d5f9f7110ad374db67ab4820f4ff2d916c3cdb</id>
<content type='text'>
Patch: 3efb17ae7e92 ("drm/amdgpu: Call amdgpu_device_unmap_mmio() if device
is unplugged to prevent crash in GPU initialization failure") makes call to
amdgpu_device_unmap_mmio() conditioned on device unplugged. This patch unmaps
MMIO mappings even when device is not unplugged.

v2: Add condition of drm_dev_enter() to deleted unmaps in patch
"drm/amdgpu: Unmap all MMIO mappings"

Signed-off-by: Leslie Shi &lt;Yuliang.Shi@amd.com&gt;
Reviewed-by: Andrey Grodzovsky &lt;andrey.grodzovsky@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: explicitly check for s0ix when evicting resources</title>
<updated>2022-01-07T22:20:38Z</updated>
<author>
<name>Mario Limonciello</name>
<email>mario.limonciello@amd.com</email>
</author>
<published>2021-12-29T19:58:02Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=e53d9665ab003df0ece8f869fcd3c2bbbecf7190'/>
<id>urn:sha1:e53d9665ab003df0ece8f869fcd3c2bbbecf7190</id>
<content type='text'>
This codepath should be running in both s0ix and s3, but only does
currently because s3 and s0ix are both set in the s0ix case.

Signed-off-by: Mario Limonciello &lt;mario.limonciello@amd.com&gt;
Acked-by: Evan Quan &lt;evan.quan@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>Merge tag 'amd-drm-next-5.17-2021-12-30' of ssh://gitlab.freedesktop.org/agd5f/linux into drm-next</title>
<updated>2021-12-31T00:59:17Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2021-12-31T00:59:16Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cb6846fbb83b574c85c2a80211b402a6347b60b1'/>
<id>urn:sha1:cb6846fbb83b574c85c2a80211b402a6347b60b1</id>
<content type='text'>
amd-drm-next-5.17-2021-12-30:

amdgpu:
- Suspend/resume fixes
- Fence fix
- Misc code cleanups
- IP discovery fixes
- SRIOV fixes
- RAS fixes
- GMC 8 VRAM detection fix
- FRU fixes for Aldebaran
- Display fixes

amdkfd:
- SVM fixes
- IP discovery fixes

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
From: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20211230141032.613596-1-alexander.deucher@amd.com
</content>
</entry>
</feed>
