<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdkfd, branch v5.1</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=v5.1</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.1'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2019-04-04T15:20:34Z</updated>
<entry>
<title>drm/amdkfd: Add picasso pci id</title>
<updated>2019-04-04T15:20:34Z</updated>
<author>
<name>Alex Deucher</name>
<email>alexander.deucher@amd.com</email>
</author>
<published>2019-04-03T17:30:32Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=e7ad88553aa1d48e950ca9a4934d246c1bee4be4'/>
<id>urn:sha1:e7ad88553aa1d48e950ca9a4934d246c1bee4be4</id>
<content type='text'>
Picasso is a new raven variant.

Reviewed-by: Kent Russell &lt;kent.russell@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: use init_mqd function to allocate object for hid_mqd (CI)</title>
<updated>2019-02-28T03:19:07Z</updated>
<author>
<name>Kevin Wang</name>
<email>kevin1.wang@amd.com</email>
</author>
<published>2019-02-22T04:36:49Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cac734c2dbd2514f14c8c6a17caba1990d83bf1d'/>
<id>urn:sha1:cac734c2dbd2514f14c8c6a17caba1990d83bf1d</id>
<content type='text'>
if use the legacy method to allocate object, when mqd_hiq need to run
uninit code, it will be cause WARNING call trace.

eg: (s3 suspend test)
[   34.918944] Call Trace:
[   34.918948]  [&lt;ffffffff92961dc1&gt;] dump_stack+0x19/0x1b
[   34.918950]  [&lt;ffffffff92297648&gt;] __warn+0xd8/0x100
[   34.918951]  [&lt;ffffffff9229778d&gt;] warn_slowpath_null+0x1d/0x20
[   34.918991]  [&lt;ffffffffc03ce1fe&gt;] uninit_mqd_hiq_sdma+0x4e/0x50 [amdgpu]
[   34.919028]  [&lt;ffffffffc03d0ef7&gt;] uninitialize+0x37/0xe0 [amdgpu]
[   34.919064]  [&lt;ffffffffc03d15a6&gt;] kernel_queue_uninit+0x16/0x30 [amdgpu]
[   34.919086]  [&lt;ffffffffc03d26c2&gt;] pm_uninit+0x12/0x20 [amdgpu]
[   34.919107]  [&lt;ffffffffc03d4915&gt;] stop_nocpsch+0x15/0x20 [amdgpu]
[   34.919129]  [&lt;ffffffffc03c1dce&gt;] kgd2kfd_suspend.part.4+0x2e/0x50 [amdgpu]
[   34.919150]  [&lt;ffffffffc03c2667&gt;] kgd2kfd_suspend+0x17/0x20 [amdgpu]
[   34.919171]  [&lt;ffffffffc03c103a&gt;] amdgpu_amdkfd_suspend+0x1a/0x20 [amdgpu]
[   34.919187]  [&lt;ffffffffc02ec428&gt;] amdgpu_device_suspend+0x88/0x3a0 [amdgpu]
[   34.919189]  [&lt;ffffffff922e22cf&gt;] ? enqueue_entity+0x2ef/0xbe0
[   34.919205]  [&lt;ffffffffc02e8220&gt;] amdgpu_pmops_suspend+0x20/0x30 [amdgpu]
[   34.919207]  [&lt;ffffffff925c56ff&gt;] pci_pm_suspend+0x6f/0x150
[   34.919208]  [&lt;ffffffff925c5690&gt;] ? pci_pm_freeze+0xf0/0xf0
[   34.919210]  [&lt;ffffffff926b45c6&gt;] dpm_run_callback+0x46/0x90
[   34.919212]  [&lt;ffffffff926b49db&gt;] __device_suspend+0xfb/0x2a0
[   34.919213]  [&lt;ffffffff926b4b9f&gt;] async_suspend+0x1f/0xa0
[   34.919214]  [&lt;ffffffff922c918f&gt;] async_run_entry_fn+0x3f/0x130
[   34.919216]  [&lt;ffffffff922b9d4f&gt;] process_one_work+0x17f/0x440
[   34.919217]  [&lt;ffffffff922bade6&gt;] worker_thread+0x126/0x3c0
[   34.919218]  [&lt;ffffffff922bacc0&gt;] ? manage_workers.isra.25+0x2a0/0x2a0
[   34.919220]  [&lt;ffffffff922c1c31&gt;] kthread+0xd1/0xe0
[   34.919221]  [&lt;ffffffff922c1b60&gt;] ? insert_kthread_work+0x40/0x40
[   34.919222]  [&lt;ffffffff92974c1d&gt;] ret_from_fork_nospec_begin+0x7/0x21
[   34.919224]  [&lt;ffffffff922c1b60&gt;] ? insert_kthread_work+0x40/0x40
[   34.919224] ---[ end trace 38cd9f65c963adad ]---

Signed-off-by: Kevin Wang &lt;kevin1.wang@amd.com&gt;
Reviewed-by: Oak Zeng &lt;Oak.Zeng@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>Merge branch 'drm-next-5.1' of git://people.freedesktop.org/~agd5f/linux into drm-next</title>
<updated>2019-02-22T05:56:42Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-02-22T05:56:35Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=fbac3c48fa6b4cfa43eaae39d5a53269bff7ec5f'/>
<id>urn:sha1:fbac3c48fa6b4cfa43eaae39d5a53269bff7ec5f</id>
<content type='text'>
Fixes for 5.1:
amdgpu:
- Fix missing fw declaration after dropping old CI DPM code
- Fix debugfs access to registers beyond the MMIO bar size
- Fix context priority handling
- Add missing license on some new files
- Various cleanups and bug fixes

radeon:
- Fix missing break in CS parser for evergreen
- Various cleanups and bug fixes

sched:
- Fix entities with 0 run queues

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
From: Alex Deucher &lt;alexdeucher@gmail.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20190221214134.3308-1-alexander.deucher@amd.com
</content>
</entry>
<entry>
<title>drm/amdkfd: Optimize out sdma doorbell array in kgd2kfd_shared_resources</title>
<updated>2019-02-18T23:00:50Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2019-01-10T04:31:14Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=234441dd49bcd917d0acd23290d1c49f332a816b'/>
<id>urn:sha1:234441dd49bcd917d0acd23290d1c49f332a816b</id>
<content type='text'>
We can directly calculate sdma doorbell indexes in the process doorbell
pages through the doorbell_index structure in amdgpu_device, so no need
to cache them in kgd2kfd_shared_resources any more. This alleviates the
adaptation needs when new SDMA configurations are introduced.

Signed-off-by: Yong Zhao &lt;Yong.Zhao@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix bugs regarding CP queue doorbell mask on SOC15</title>
<updated>2019-02-18T23:00:41Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2019-02-13T18:15:05Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=1f86805adc3432e92e7d87e1ff5da9826ef56eab'/>
<id>urn:sha1:1f86805adc3432e92e7d87e1ff5da9826ef56eab</id>
<content type='text'>
Reserved doorbells for SDMA IH and VCN were not properly masked out
when allocating doorbells for CP user queues. This patch fixed that.

Signed-off-by: Yong Zhao &lt;Yong.Zhao@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Move a constant definition around</title>
<updated>2019-02-18T22:59:56Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2019-01-15T23:51:27Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=7452394310a9eac283fdbb31261b19e50fa3e546'/>
<id>urn:sha1:7452394310a9eac283fdbb31261b19e50fa3e546</id>
<content type='text'>
The similar definitions should be consecutive.

Signed-off-by: Yong Zhao &lt;Yong.Zhao@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>Merge v5.0-rc7 into drm-next</title>
<updated>2019-02-18T03:27:15Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-02-18T03:27:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c06de56121e3ac0f0f1f4a081c041654ffcacd62'/>
<id>urn:sha1:c06de56121e3ac0f0f1f4a081c041654ffcacd62</id>
<content type='text'>
Backmerging for nouveau and imx that needed some fixes for next pulls.

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix if preprocessor statement above kfd_fill_iolink_info_for_cpu</title>
<updated>2019-02-05T23:10:28Z</updated>
<author>
<name>Nathan Chancellor</name>
<email>natechancellor@gmail.com</email>
</author>
<published>2019-01-21T23:52:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=6d3d8065bb14dcd3d36b63f81fff9bc7f4388bda'/>
<id>urn:sha1:6d3d8065bb14dcd3d36b63f81fff9bc7f4388bda</id>
<content type='text'>
Clang warns:

drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_crat.c:866:5: warning:
'CONFIG_X86_64' is not defined, evaluates to 0 [-Wundef]
    ^
1 warning generated.

Fixes: d1c234e2cd10 ("drm/amdkfd: Allow building KFD on ARM64 (v2)")
Signed-off-by: Nathan Chancellor &lt;natechancellor@gmail.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Don't assign dGPUs to APU topology devices</title>
<updated>2019-01-14T20:59:50Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2019-01-02T22:47:39Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=bbdf514fe5648566b0754476cbcb92ac3422dde2'/>
<id>urn:sha1:bbdf514fe5648566b0754476cbcb92ac3422dde2</id>
<content type='text'>
dGPUs need their own topology devices. Don't assign them to APU topology
devices with CPU cores.

Bug: https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/issues/66
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Tested-by: Elias Konstantinidis &lt;ekondis@gmail.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/amdkfd: Allow building KFD on ARM64 (v2)</title>
<updated>2019-01-14T20:59:37Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2019-01-02T19:52:13Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=d1c234e2cd1091b816c990a1848d88a8697f97b4'/>
<id>urn:sha1:d1c234e2cd1091b816c990a1848d88a8697f97b4</id>
<content type='text'>
ifdef x86_64 specific code.
Allow enabling CONFIG_HSA_AMD on ARM64.

v2: Fixed a compiler warning due to an unused variable

CC: Mark Nutter &lt;Mark.Nutter@arm.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Tested-by: Mark Nutter &lt;Mark.Nutter@arm.com&gt;
Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
