<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-stable.git/drivers/gpu/drm/amd/include/kgd_kfd_interface.h, branch v4.18</title>
<subtitle>Linux kernel stable tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/'/>
<entry>
<title>drm/amdgpu: Add doorbell routing info to kgd2kfd_shared_resources</title>
<updated>2018-04-10T21:33:02+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-04-10T21:33:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=642a0e80262af8e9d5b8129e2149c670ab3bb4b8'/>
<id>642a0e80262af8e9d5b8129e2149c670ab3bb4b8</id>
<content type='text'>
This is needed for Vega10 and later ASICs to let KFD know which
doorbells can be used for SDMA and CP queues respectively.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is needed for Vega10 and later ASICs to let KFD know which
doorbells can be used for SDMA and CP queues respectively.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Remove unused interface from kfd2kgd interface</title>
<updated>2018-04-10T21:32:58+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-04-10T21:32:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=5e7086eecc32b95288bc76f2a22aadeb368e25ed'/>
<id>5e7086eecc32b95288bc76f2a22aadeb368e25ed</id>
<content type='text'>
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdkfd: Add quiesce_mm and resume_mm to kgd2kfd_calls</title>
<updated>2018-03-23T19:32:32+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-03-23T19:32:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=6b95e7973a136181e37446bd29b0b2e2f0d2d653'/>
<id>6b95e7973a136181e37446bd29b0b2e2f0d2d653</id>
<content type='text'>
These interfaces allow KGD to stop and resume all GPU user mode queue
access to a process address space. This is needed for handling MMU
notifiers of userptrs mapped for GPU access in KFD VMs.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
These interfaces allow KGD to stop and resume all GPU user mode queue
access to a process address space. This is needed for handling MMU
notifiers of userptrs mapped for GPU access in KFD VMs.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdkfd: Add ioctls for GPUVM memory management</title>
<updated>2018-03-15T21:27:51+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-03-15T21:27:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=5ec7e02854b3b9b55936c3b44b8acfb85e333f49'/>
<id>5ec7e02854b3b9b55936c3b44b8acfb85e333f49</id>
<content type='text'>
v2:
* Fix error handling after kfd_bind_process_to_device in
  kfd_ioctl_map_memory_to_gpu
v3:
* Add ioctl to acquire VM from a DRM FD
v4:
* Return number of successful map/unmap operations in failure cases
* Facilitate partial retry after failed map/unmap
* Added comments with parameter descriptions to new APIs
* Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
v2:
* Fix error handling after kfd_bind_process_to_device in
  kfd_ioctl_map_memory_to_gpu
v3:
* Add ioctl to acquire VM from a DRM FD
v4:
* Return number of successful map/unmap operations in failure cases
* Facilitate partial retry after failed map/unmap
* Added comments with parameter descriptions to new APIs
* Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add kfd2kgd interface to acquire an existing VM</title>
<updated>2018-03-15T21:27:43+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-03-15T21:27:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=ede0dd86f45adf2b7083bb161f6bc81da5fe2bad'/>
<id>ede0dd86f45adf2b7083bb161f6bc81da5fe2bad</id>
<content type='text'>
This allows acquiring an existing VM from a render node FD to use it
for a compute process.

Such VMs get destroyed when the original file descriptor is released.
Added a callback from amdgpu_vm_fini to handle KFD VM destruction
correctly in this case.

v2:
* Removed vm-&gt;vm_context check in amdgpu_amdkfd_gpuvm_destroy_cb,
  check vm-&gt;process_info earlier instead

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This allows acquiring an existing VM from a render node FD to use it
for a compute process.

Such VMs get destroyed when the original file descriptor is released.
Added a callback from amdgpu_vm_fini to handle KFD VM destruction
correctly in this case.

v2:
* Removed vm-&gt;vm_context check in amdgpu_amdkfd_gpuvm_destroy_cb,
  check vm-&gt;process_info earlier instead

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add submit IB function for KFD</title>
<updated>2018-02-07T01:32:39+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=4c660c8fbbf7b0d65a402f51e5f30a246cf3c44c'/>
<id>4c660c8fbbf7b0d65a402f51e5f30a246cf3c44c</id>
<content type='text'>
This can be used for flushing caches when not using the HWS.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This can be used for flushing caches when not using the HWS.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add GPUVM memory management functions for KFD</title>
<updated>2018-02-07T01:32:38+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=a46a2cd103a863724d668c86dca86bd0d93a19e4'/>
<id>a46a2cd103a863724d668c86dca86bd0d93a19e4</id>
<content type='text'>
v2:
* Removed unused flags from struct kgd_mem
* Updated some comments
* Added a check to unmap_memory_from_gpu whether BO was mapped

v3: add mutex_destroy in relevant places

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
v2:
* Removed unused flags from struct kgd_mem
* Updated some comments
* Added a check to unmap_memory_from_gpu whether BO was mapped

v3: add mutex_destroy in relevant places

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Update kgd2kfd_shared_resources for dGPU support</title>
<updated>2018-02-07T01:32:36+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=155494dbbbf4d6d6512b8bc2dc6bc483e47e1c71'/>
<id>155494dbbbf4d6d6512b8bc2dc6bc483e47e1c71</id>
<content type='text'>
Add GPUVM size and DRM render node. Also add function to query the
VMID mask to avoid hard-coding it in multiple places later.

v2: cut off GPUVM size at the VA hole

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add GPUVM size and DRM render node. Also add function to query the
VMID mask to avoid hard-coding it in multiple places later.

v2: cut off GPUVM size at the VA hole

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Add KFD eviction fence</title>
<updated>2018-02-07T01:32:35+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=d8d019ccffb838bb0dd98e583b5c25ccc0bc6ece'/>
<id>d8d019ccffb838bb0dd98e583b5c25ccc0bc6ece</id>
<content type='text'>
This fence is used by KFD to keep memory resident while user mode
queues are enabled. Trying to evict memory will trigger the
enable_signaling callback, which starts a KFD eviction, which
involves preempting user mode queues before signaling the fence.
There is one such fence per process.

v2:
* Grab a reference to mm_struct
* Dereference fence after NULL check
* Simplify fence release, no need to signal without anyone waiting
* Added signed-off-by Harish, who is the original author of this code

v3:
* update MAINTAINERS file
* change amd_kfd_ prefix to amdkfd_
* remove useless initialization of variable to NULL

v4:
* set amdkfd_fence_ops to be static
* Suggested by: Fengguang Wu &lt;fengguang.wu@intel.com&gt;

Signed-off-by: Harish Kasiviswanathan &lt;Harish.Kasiviswanathan@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This fence is used by KFD to keep memory resident while user mode
queues are enabled. Trying to evict memory will trigger the
enable_signaling callback, which starts a KFD eviction, which
involves preempting user mode queues before signaling the fence.
There is one such fence per process.

v2:
* Grab a reference to mm_struct
* Dereference fence after NULL check
* Simplify fence release, no need to signal without anyone waiting
* Added signed-off-by Harish, who is the original author of this code

v3:
* update MAINTAINERS file
* change amd_kfd_ prefix to amdkfd_
* remove useless initialization of variable to NULL

v4:
* set amdkfd_fence_ops to be static
* Suggested by: Fengguang Wu &lt;fengguang.wu@intel.com&gt;

Signed-off-by: Harish Kasiviswanathan &lt;Harish.Kasiviswanathan@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drm/amdgpu: Remove unused kfd2kgd interface</title>
<updated>2018-02-07T01:32:34+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-02-07T01:32:34+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=1029a3f33678afb8978285209ec5cfe153fe44ef'/>
<id>1029a3f33678afb8978285209ec5cfe153fe44ef</id>
<content type='text'>
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
