- 05 Aug, 2016 1 commit
-
-
Michel Dänzer authored
Fixes hangs under memory pressure, e.g. running the piglit test tex3d-maxsize concurrently with other tests. Fixes: 17d33bc9 ("drm/ttm: drop waiting for idle in ttm_bo_evict.") Reviewed-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
Michel Dänzer <michel.daenzer@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
- 02 Aug, 2016 5 commits
-
-
Huang Rui authored
Signed-off-by:
Huang Rui <ray.huang@amd.com> Reviewed-by:
Ken Wang <Qingqing.Wang@amd.com> Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
- 01 Aug, 2016 3 commits
-
-
Eric Huang authored
Reviewed-by:
Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by:
Eric Huang <JinHuiEric.Huang@amd.com> Signed-off-by:
-
Alex Deucher authored
It's already covered by the default case, but add it for consistency. Reviewed-by:
Alexandre Demers <alexandre.f.demers@gmail.com> Reviewed-by:
-
Alex Deucher authored
Looks like this got missed when we ported the code from radeon. Reviewed-by:
-
- 29 Jul, 2016 31 commits
-
-
git://git.pengutronix.de/git/pza/linuxDave Airlie authored
imx-drm ldb mode set fix - fix imx-ldb mode setting, which was broken by commit 49f98bc4 ("drm/imx: store internal bus configuration in crtc state") * tag 'imx-drm-fixes-2016-07-27' of git://git.pengutronix.de/git/pza/linux: drm/imx: imx-ldb: do not try to dereference crtc->state->state in encoder mode_set
-
git://people.freedesktop.org/~agd5f/linuxDave Airlie authored
A few more patches for amdgpu and radeon for 4.8. The big change is the additional power feature enablement for polaris that was pending the 4.7 back merge. The rest are mainly bug fixes and cleanups. * 'drm-next-4.8' of git://people.freedesktop.org/~agd5f/linux: (59 commits) drm/amd/powerplay: remove enable_clock_power_gatings_tasks from initialize and resume events drm/amd/powerplay: move clockgating to after ungating power in pp for uvd/vce drm/amdgpu: add query device id and revision id into system info entry at CGS drm/amdgpu: add new definition in bif header drm/amd/powerplay: rename smum header guards drm/amdgpu: enable UVD context buffer for older HW drm/amdgpu: fix default UVD context size drm/amdgpu: fix incorrect type of info_id drm/amdgpu: make amdgpu_cgs_call_acpi_method as static drm/amdgpu: comment out unused defaults_staturn_pro static const structure to fix the build drm/amdgpu: enable UVD VM only on polaris drm/amdgpu: increase timeout of IB test drm/amdgpu: add destroy session when generate VCE destroy msg. drm/amd: fix deadlock of job_list_lock V2 drm/amd: reset hw count when reset job drm/amdgpu: free handles after fini the context drm/ttm: partial revert "cleanup ttm_tt_(unbind|destroy)" v3 drm/amdgpu: add a fence timeout for the IB tests v2 drm/amdgpu: move UVD IB test into common code v2 drm/amdgpu: use begin/end_use for VCE power/clock gating ...
-
git://anongit.freedesktop.org/drm-intelDave Airlie authored
A few more simple fixes that Sean&I collected. There's a bunch of bigger things on dri-devel, but I think those are all too late for 4.8 really. I'll try and go collect them after -rc1 for 4.9. * tag 'topic/drm-misc-2016-07-28' of git://anongit.freedesktop.org/drm-intel: drm/arm: mali-dp: Fix error return code in malidp_bind() drm/arm: mali-dp: Remove redundant dev_err call in malidp_bind() drm/gma500: remove unnecessary stub for fb_ioctl() apple-gmux: Sphinxify docs drm/arm: mali-dp: Set crtc.port to the port instead of the endpoint drm/sti: use new Reset API drm/etnaviv: Optimize error handling in etnaviv_gem_new_userptr() drm/etnaviv: Delete unnecessary checks before two function calls drm/vmwgfx: Delete an unnecessary check before the function call "vfree" drm/qxl: Delete an unnecessary check before drm_gem_object_unreference_unlocked() drm/mgag200: Delete an unnecessary check before drm_gem_object_unreference_unlocked() drm/bridge: ps8622: Delete an unnecessary check before backlight_device_unregister() GPU-DRM-GMA500: Delete unnecessary checks before two function calls GPU-DRM-OMAP: Delete unnecessary checks before two function calls
-
Tom St Denis authored
Setting PG state this early would cause lock ups in the IP block initialized functions. Signed-off-by:
Tom St Denis <tom.stdenis@amd.com> Reviewed-by:
Rex Zhu <Rex.Zhu@amd.com> Signed-off-by:
-
Tom St Denis authored
Cannot set clockgating state before ungating power. Signed-off-by:
-
Huang Rui authored
This patch adds device id and revision into system info entry at CGS, it's able to get PCI device id and revision id from amdgpu, it might get more info in future. PCI device id will be also used on powerplay part at current. Suggested-by:
-
Huang Rui authored
This patch adds new definition in bif header, and will be used on iceland HW powertune part. Signed-off-by:
-
Huang Rui authored
This patch renames the smum header guards to align with the file name. Reported-by:
-
Christian König authored
Supported starting on certain FW versions. Signed-off-by:
Leo Liu <leo.liu@amd.com> Reviewed-by:
-
Christian König authored
Context buffers should be denied by default, not allowed. Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
Huang Rui authored
Signed-off-by:
-
Slava Grigorev authored
Signed-off-by:
Slava Grigorev <slava.grigorev@amd.com> Reviewed-by:
-
Christian König authored
Stoney support it, but doesn't has unlimited session support. Signed-off-by:
-
Chunming Zhou authored
we should give enough time to IB test. Signed-off-by:
Chunming Zhou <David1.Zhou@amd.com> Reviewed-by:
-
Rex Zhu authored
Signed-off-by:
David Mao <David.Mao@amd.com> Signed-off-by:
-
Chunming Zhou authored
run_job involves mutex, which could sleep. V2: use list_for_each_entry_safe, since the job might complete while we dropped the lock. Signed-off-by:
-
Chunming Zhou authored
Means the hw ring is empty after gpu reset. Signed-off-by:
-
Leo Liu authored
This will make sure all the submissions from different contexts gets finished, and then we close the session and free up the handles. This will fix the issue that session clean-up is not get done properly, when with the command `kill -9' Signed-off-by:
-
Christian König authored
We still need to unbind explicitly during a move. This partial reverts commit ff20caa0bcbfef9f7686f8d1868a3b990921afd6. v2: remove unnecessary check and unused variable v3: fix typo in commit message Signed-off-by:
-
Christian König authored
10ms should be enough for now. v2: fix some typos in CIK code Signed-off-by:
-
Christian König authored
Since we now raise the clocks from begin_use() we don't need a separate function for each hw generation any more. v2: remove unintentional lowering of the UVD clocks, fix typos for CIK hw. Signed-off-by:
-
Christian König authored
This fixes turning power and clock on when it is actually needed. Signed-off-by:
-
Christian König authored
This fixes turning power and clock on when it is actually needed. Signed-off-by:
-
Christian König authored
For manual UVD/VCE power and clock gating. Signed-off-by:
-
Christian König authored
Was never used as far as I can see. Signed-off-by:
-
Christian König authored
Signed-off-by:
-
Rex Zhu authored
Signed-off-by:
-
Rex Zhu authored
Signed-off-by:
-
Rex Zhu authored
This reverts commit <2ded8c7f04825bc5cde2624f6aa83f1ff62672c0> As we enabled bypass mode for uvd on polaris10 when clockgating. so no need to set uvd clock manually. Signed-off-by:
-
Rex Zhu authored
Signed-off-by:
-
