<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h, branch v5.7</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=v5.7</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.7'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2020-02-28T21:59:20Z</updated>
<entry>
<title>drm/amdkfd: Make get_tile_config() generic</title>
<updated>2020-02-28T21:59:20Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2020-02-26T17:49:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=fd7d08bad7a4f255330422a11c7da9a9b8683eff'/>
<id>urn:sha1:fd7d08bad7a4f255330422a11c7da9a9b8683eff</id>
<content type='text'>
Given we can query all the asic specific information from amdgpu_gfx_config,
we can make get_tile_config() generic.

Signed-off-by: Yong Zhao &lt;Yong.Zhao@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/amd: Extend ROCt to surface UUID for devices that have them</title>
<updated>2020-02-26T19:18:17Z</updated>
<author>
<name>Divya Shikre</name>
<email>DivyaUday.Shikre@amd.com</email>
</author>
<published>2020-02-25T22:17:37Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=0c663695a6cb9820692e7e37239c5be90c77b21d'/>
<id>urn:sha1:0c663695a6cb9820692e7e37239c5be90c77b21d</id>
<content type='text'>
Devices from Arcturus onwards will have their UUID exposed to Thunk.
Adding neccessary functions to the kernel to propagate the uuid.

Signed-off-by: Divya Shikre &lt;DivyaUday.Shikre@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Remove kfd eviction fence before release bo (v2)</title>
<updated>2020-02-26T19:17:32Z</updated>
<author>
<name>xinhui pan</name>
<email>xinhui.pan@amd.com</email>
</author>
<published>2020-02-11T03:28:34Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f4a3c42b5c52c8c603fa8433c52aa940a4ad938a'/>
<id>urn:sha1:f4a3c42b5c52c8c603fa8433c52aa940a4ad938a</id>
<content type='text'>
No need to trigger eviction as the memory mapping will not be used
anymore.

All pt/pd bos share same resv, hence the same shared eviction fence.
Everytime page table is freed, the fence will be signled and that cuases
kfd unexcepted evictions.

v2: squash in 32 bit fix

CC: Christian König &lt;christian.koenig@amd.com&gt;
CC: Felix Kuehling &lt;felix.kuehling@amd.com&gt;
CC: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: xinhui pan &lt;xinhui.pan@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: refactor runtime pm for baco</title>
<updated>2020-02-12T21:00:54Z</updated>
<author>
<name>Rajneesh Bhardwaj</name>
<email>rajneesh.bhardwaj@amd.com</email>
</author>
<published>2020-01-22T00:11:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=9593f4d6a69b0bc9577a7edb4c79be533957c161'/>
<id>urn:sha1:9593f4d6a69b0bc9577a7edb4c79be533957c161</id>
<content type='text'>
So far the kfd driver implemented same routines for runtime and system
wide suspend and resume (s2idle or mem). During system wide suspend the
kfd aquires an atomic lock that prevents any more user processes to
create queues and interact with kfd driver and amd gpu. This mechanism
created problem when amdgpu device is runtime suspended with BACO
enabled. Any application that relies on kfd driver fails to load because
the driver reports a locked kfd device since gpu is runtime suspended.

However, in an ideal case, when gpu is runtime  suspended the kfd driver
should be able to:

 - auto resume amdgpu driver whenever a client requests compute service
 - prevent runtime suspend for amdgpu  while kfd is in use

This change refactors the amdgpu and amdkfd drivers to support BACO and
runtime power management.

Reviewed-by: Oak Zeng &lt;oak.zeng@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;felix.kuehling@amd.com&gt;
Signed-off-by: Rajneesh Bhardwaj &lt;rajneesh.bhardwaj@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: GPU TLB flush API moved to amdgpu_amdkfd</title>
<updated>2020-01-16T18:34:33Z</updated>
<author>
<name>Alex Sierra</name>
<email>alex.sierra@amd.com</email>
</author>
<published>2019-12-20T05:57:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ffa022696f46fb6c13e30cad59b7271a687f96b8'/>
<id>urn:sha1:ffa022696f46fb6c13e30cad59b7271a687f96b8</id>
<content type='text'>
[Why]
TLB flush method has been deprecated using kfd2kgd interface.
This implementation is now on the amdgpu_amdkfd API.

[How]
TLB flush functions now implemented in amdgpu_amdkfd.

Signed-off-by: Alex Sierra &lt;alex.sierra@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@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: Use array to probe kfd2kgd_calls</title>
<updated>2019-10-03T14:11:05Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2019-09-28T02:03:42Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=e392c887df979112af94cfec08dd87f4dd55d085'/>
<id>urn:sha1:e392c887df979112af94cfec08dd87f4dd55d085</id>
<content type='text'>
This is the same idea as the kfd device info probe and move all the
probe control together for easy maintenance.

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/amd: Pass drm_device to kfd</title>
<updated>2019-10-03T14:11:03Z</updated>
<author>
<name>Harish Kasiviswanathan</name>
<email>Harish.Kasiviswanathan@amd.com</email>
</author>
<published>2018-09-26T20:09:37Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3a0c3423921e6a1f32ef27912c936e38bf28451b'/>
<id>urn:sha1:3a0c3423921e6a1f32ef27912c936e38bf28451b</id>
<content type='text'>
kfd needs drm_device to call into drm_cgroup functions

Signed-off-by: Harish Kasiviswanathan &lt;Harish.Kasiviswanathan@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: Query kfd device info by CHIP id instead of pci device id</title>
<updated>2019-09-13T22:49:45Z</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2019-09-03T21:55:30Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=050091ab6e832f7df0b700f1b9b596613643ada4'/>
<id>urn:sha1:050091ab6e832f7df0b700f1b9b596613643ada4</id>
<content type='text'>
This optimizes out the pci device id usage in KFD and makes the code
more maintainable.

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/amdgpu: Disable page faults while reading user wptrs</title>
<updated>2019-09-13T22:49:38Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2019-08-30T04:10:34Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cd05c865108e089c4be99c0f939c72437fba2207'/>
<id>urn:sha1:cd05c865108e089c4be99c0f939c72437fba2207</id>
<content type='text'>
These wptrs must be pinned and GPU accessible when this is called
from hqd_load functions. So they should never fault. This resolves
a circular lock dependency issue involving four locks including the
DQM lock and mmap_sem.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@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>drm/amdgpu: Determing PTE flags separately for each mapping (v3)</title>
<updated>2019-09-13T22:35:55Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2019-08-26T22:39:11Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=d0ba51b1cacd27bdc1acfe70cb55699f3329b2b1'/>
<id>urn:sha1:d0ba51b1cacd27bdc1acfe70cb55699f3329b2b1</id>
<content type='text'>
The same BO can be mapped with different PTE flags by different GPUs.
Therefore determine the PTE flags separately for each mapping instead
of storing them in the KFD buffer object.

Add a helper function to determine the PTE flags to be extended with
ASIC and memory-type-specific logic in subsequent commits.

v2: Split Arcturus-specific MTYPE changes into separate commit
v3: Fix return type of get_pte_flags to uint64_t

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Shaoyun Liu &lt;Shaoyun.Liu@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
