- 20 Dec, 2017 5 commits
-
-
Rex Zhu authored
The smu firmware is loaded by the sbios on APUs, so query it from the smu and save the smu fw version info that is reported to userspace. Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Signed-off-by:
-
Rex Zhu authored
Set the new common smu firmware version for smu7 parts (CI and VI). Reviewed-by:
-
Rex Zhu authored
Move the smu_version to struct hwmgr, so it can be shared by other asics. Reviewed-by:
-
Alex Deucher authored
Rather than magic numbers. Reviewed-by:
Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by:
-
Alex Deucher authored
We only support SR-IOV on tonga/fiji. Don't check this register on other VI parts. Fixes: 048765ad (amdgpu: fix asic initialization for virtualized environments (v2)) Reviewed-by:
-
- 19 Dec, 2017 4 commits
-
-
Rex Zhu authored
Reviewed-by:
-
Rex Zhu authored
Reviewed-by:
-
Rex Zhu authored
mv related code out of force_dpm_level to phm_reset_power_profile_state Reviewed-by:
-
Rex Zhu authored
for sclk/mclk, can be adjusted through sysfs. for uvd/vce clk, will be adjusted case by case when requested. Reviewed-by:
-
- 18 Dec, 2017 24 commits
-
-
Andrey Grodzovsky authored
This reverts commit ba851eed895c76be0eb4260bdbeb7e26f9ccfaa2. With that change piglit max size tests (running with -t max.*size) are causing OOM and hard hang on my CZ with 1GB RAM. Signed-off-by:
Andrey Grodzovsky <andrey.grodzovsky@amd.com> Acked-by:
Christian König <christian.koenig@amd.com> Reviewed-by:
Roger He <Hongbo.He@amd.com> Signed-off-by:
-
Christian König authored
AMD is the major user of TTM, so it also makes sense that we maintain it. v2: mention Alex git tree as well Signed-off-by:
Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by:
-
Christian König authored
Instead of falling back to 2 level and very limited address space use 2+1 PD support and 128TB + 512GB of virtual address space. v2: cleanup defines, rebase on top of level enum v3: fix inverted check in hardware setup Signed-off-by:
Chunming Zhou <david1.zhou@amd.com> Signed-off-by:
-
Christian König authored
Use pr_debug instead of TTM_DEBUG, fix the lockdep assert and remove the unused constant. Signed-off-by:
-
Christian König authored
Use the reservation wrapper for this. Signed-off-by:
-
Christian König authored
We only need to wait for the contended lock when the reservation object is shared or when we want to remove everything. A trylock should be sufficient in all other cases. Signed-off-by:
-
Jim Qu authored
otherwise, uvd block will be never powered up in ring begin_use() callback. uvd ring test will be fail in resume in rumtime pm. Signed-off-by:
Jim Qu <Jim.Qu@amd.com> Reviewed-by:
-
Jim Qu authored
Signed-off-by:
-
Alex Deucher authored
add device to the name for consistency. Acked-by:
-
Alex Deucher authored
It's the only place it's used. Acked-by:
-
Alex Deucher authored
add device to the name for consistency. Acked-by:
-
Alex Deucher authored
It's the only place they are used. Acked-by:
-
Alex Deucher authored
add device to the name for consistency. Acked-by:
-
Alex Deucher authored
add device to the name for consistency. Acked-by:
-
Alex Deucher authored
It's the only place they are used. Acked-by:
-
Alex Deucher authored
add device to the name for consistency. Acked-by:
-
Alex Deucher authored
It's the only place it's used. Acked-by:
-
Alex Deucher authored
add device for consistency with other functions in this file. Acked-by:
-
Alex Deucher authored
add device for consistency with other functions in this file. Acked-by:
-
Alex Deucher authored
add device for consistency. Acked-by:
-
Alex Deucher authored
amdgpu_device.c was getting pretty cluttered. Acked-by:
-
Alex Deucher authored
for consistency with the other functions in that file. Acked-by:
-
Alex Deucher authored
Prefix the functions with device or device_ip for functions which deal with ip blocks for consistency. Acked-by:
-
Alex Deucher authored
and move them to amdgpu_atombios.c for consistency. Acked-by:
-
- 15 Dec, 2017 7 commits
-
-
Colin Ian King authored
The null check on aconnector->base.edid_blob_ptr->data is redundant since data is an array and can never be null. Remove it. Detected by CoverityScan, CID#1460369 ("Array compared against 0") Acked-by:Harry Wentland <harry.wentland@amd.com> Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
Alex Deucher authored
Same as previous asics. This was not yet set for gfx9. Acked-by:
-
Andrey Grodzovsky authored
With introduction of amdgpu_gpu_recovery we don't need any more to rely on amdgpu_lockup_timeout == 0 for disabling GPU reset. Signed-off-by:
-
Andrey Grodzovsky authored
Add new parameter to control GPU recovery procedure. v2: Add auto logic where reset is disabled for bare metal and enabled for SR-IOV. Allow forced reset from debugfs. Signed-off-by:
-
Roger He authored
include ttm_bo_move_memcpy and ttm_bo_move_ttm Signed-off-by:
-
Roger He authored
allow eviction of BOs reserved by the caller when they are not part of the current working set. Reviewed-by:
-
Roger He authored
enable eviction of other per VM BOs during allocation and allows reaping of deleted BOs during CS. Reviewed-by:
-
