<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c, branch v4.19</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=v4.19</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v4.19'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2018-08-28T17:42:48Z</updated>
<entry>
<title>drm/amdgpu: Need to set moved to true when evict bo</title>
<updated>2018-08-28T17:42:48Z</updated>
<author>
<name>Emily Deng</name>
<email>Emily.Deng@amd.com</email>
</author>
<published>2018-08-28T12:52:40Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=6ddd9769db4fc11a98bd7e58be1764e47fdb8384'/>
<id>urn:sha1:6ddd9769db4fc11a98bd7e58be1764e47fdb8384</id>
<content type='text'>
Fix the VMC page fault when the running sequence is as below:
1.amdgpu_gem_create_ioctl
2.ttm_bo_swapout-&gt;amdgpu_vm_bo_invalidate, as not called
amdgpu_vm_bo_base_init, so won't called
list_add_tail(&amp;base-&gt;bo_list, &amp;bo-&gt;va). Even the bo was evicted,
it won't set the bo_base-&gt;moved.
3.drm_gem_open_ioctl-&gt;amdgpu_vm_bo_base_init, here only called
list_move_tail(&amp;base-&gt;vm_status, &amp;vm-&gt;evicted), but not set the
bo_base-&gt;moved.
4.amdgpu_vm_bo_map-&gt;amdgpu_vm_bo_insert_map, as the bo_base-&gt;moved is
not set true, the function amdgpu_vm_bo_insert_map will call
list_move(&amp;bo_va-&gt;base.vm_status, &amp;vm-&gt;moved)
5.amdgpu_cs_ioctl won't validate the swapout bo, as it is only in the
moved list, not in the evict list. So VMC page fault occurs.

Signed-off-by: Emily Deng &lt;Emily.Deng@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: Adjust the VM size based on system memory size v2</title>
<updated>2018-08-27T19:48:25Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2018-08-21T21:14:32Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=fca5d959972c18839f0306f19df2f121623447dd'/>
<id>urn:sha1:fca5d959972c18839f0306f19df2f121623447dd</id>
<content type='text'>
Set the VM size based on system memory size between the ASIC-specific
limits given by min_vm_size and max_bits. GFXv9 GPUs will keep their
default VM size of 256TB (48 bit). Only older GPUs will adjust VM size
depending on system memory size.

This makes more VM space available for ROCm applications on GFXv8 GPUs
that want to map all available VRAM and system memory in their SVM
address space.

v2:
* Clarify comment
* Round up memory size before &gt;&gt; 30
* Round up automatic vm_size to power of two

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Junwei Zhang &lt;Jerry.Zhang@amd.com&gt;
Reviewed-by: Huang Rui &lt;ray.huang@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: fix VM clearing for the root PD</title>
<updated>2018-08-22T21:04:14Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-08-16T10:01:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=8604ffcbf04f8f4f3f55a9e46e5ff948b2ed4290'/>
<id>urn:sha1:8604ffcbf04f8f4f3f55a9e46e5ff948b2ed4290</id>
<content type='text'>
We need to figure out the address after validating the BO, not before.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Junwei Zhang &lt;Jerry.Zhang@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>Merge branch 'drm-next-4.19' of git://people.freedesktop.org/~agd5f/linux into drm-next</title>
<updated>2018-08-07T20:22:23Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2018-08-07T20:09:08Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=940fbcb73fd25b517fa10c5a9cc96ca0ce1a2fc4'/>
<id>urn:sha1:940fbcb73fd25b517fa10c5a9cc96ca0ce1a2fc4</id>
<content type='text'>
Fixes for 4.19:
- Fix UVD 7.2 instance handling
- Fix UVD 7.2 harvesting
- GPU scheduler fix for when a process is killed
- TTM cleanups
- amdgpu CS bo_list fixes
- Powerplay fixes for polaris12 and CZ/ST
- DC fixes for link training certain HMDs
- DC fix for vega10 blank screen in certain cases

From: Alex Deucher &lt;alexdeucher@gmail.com&gt;
Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20180801222906.1016-1-alexander.deucher@amd.com
</content>
</entry>
<entry>
<title>drm/amdgpu: add new amdgpu_vm_bo_trace_cs() function v2</title>
<updated>2018-07-31T21:58:17Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-07-27T14:56:34Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=8ab19ea619aeed8ca4a36c124e8edfd9b9491aba'/>
<id>urn:sha1:8ab19ea619aeed8ca4a36c124e8edfd9b9491aba</id>
<content type='text'>
This allows us to trace all VM ranges which should be valid inside a CS.

v2: dump mappings without BO as well

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chunming  Zhou &lt;david1.zhou@amd.com&gt;
Reviewed-and-tested-by: Andrey Grodzovsky &lt;andrey.grodzovsky@amd.com&gt; (v1)
Reviewed-by: Huang Rui &lt;ray.huang@amd.com&gt; (v1)
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/scheduler: remove sched field from the entity</title>
<updated>2018-07-25T20:06:26Z</updated>
<author>
<name>Nayan Deshmukh</name>
<email>nayan26deshmukh@gmail.com</email>
</author>
<published>2018-07-20T12:21:06Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=068c330419ffb3422a43cb7d34351f1ef033950f'/>
<id>urn:sha1:068c330419ffb3422a43cb7d34351f1ef033950f</id>
<content type='text'>
The scheduler of the entity is decided by the run queue on which
it is queued. This patch avoids us the effort required to maintain
a sync between rq and sched field when we start shifting entites
among different rqs.

Signed-off-by: Nayan Deshmukh &lt;nayan26deshmukh@gmail.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Eric Anholt &lt;eric@anholt.net&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/scheduler: modify API to avoid redundancy</title>
<updated>2018-07-25T20:06:19Z</updated>
<author>
<name>Nayan Deshmukh</name>
<email>nayan26deshmukh@gmail.com</email>
</author>
<published>2018-07-20T12:21:05Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=cdc50176597cb44ce25eb7331c450058775b8d2a'/>
<id>urn:sha1:cdc50176597cb44ce25eb7331c450058775b8d2a</id>
<content type='text'>
entity has a scheduler field and we don't need the sched argument
in any of the functions where entity is provided.

Signed-off-by: Nayan Deshmukh &lt;nayan26deshmukh@gmail.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Eric Anholt &lt;eric@anholt.net&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: simplify the bo reference on amdgpu_bo_update</title>
<updated>2018-07-18T21:18:44Z</updated>
<author>
<name>Huang Rui</name>
<email>ray.huang@amd.com</email>
</author>
<published>2018-07-04T10:08:54Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=7eb80427746175530f03a00ad5281c4222f17238'/>
<id>urn:sha1:7eb80427746175530f03a00ad5281c4222f17238</id>
<content type='text'>
BO ptr already be initialized at definition, we needn't use the complicated
reference.

v2: fix typo at subject line

Signed-off-by: Huang Rui &lt;ray.huang@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: remove ring parameter from amdgpu_job_submit</title>
<updated>2018-07-16T21:11:52Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2018-07-13T11:54:56Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=0e28b10ff1b8e65788040b51c30c9cc984060dcd'/>
<id>urn:sha1:0e28b10ff1b8e65788040b51c30c9cc984060dcd</id>
<content type='text'>
We know the ring through the entity anyway.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Junwei Zhang &lt;Jerry.Zhang@amd.com&gt;
Acked-by: Chunming Zhou &lt;david1.zhou@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/scheduler: modify args of drm_sched_entity_init</title>
<updated>2018-07-13T19:46:05Z</updated>
<author>
<name>Nayan Deshmukh</name>
<email>nayan26deshmukh@gmail.com</email>
</author>
<published>2018-07-13T09:51:14Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=aa16b6c6b4d979234f830a48add47d02c12bb569'/>
<id>urn:sha1:aa16b6c6b4d979234f830a48add47d02c12bb569</id>
<content type='text'>
replace run queue by a list of run queues and remove the
sched arg as that is part of run queue itself

Signed-off-by: Nayan Deshmukh &lt;nayan26deshmukh@gmail.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Acked-by: Eric Anholt &lt;eric@anholt.net&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
