- 27 Feb, 2018 28 commits
-
-
Christian König authored
TTM calls the default implementation now. Signed-off-by:
Christian König <christian.koenig@amd.com> Reviewed-by:
Michel Dänzer <michel.daenzer@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Christian König authored
TTM calls the default implementation now. Signed-off-by:
-
Christian König authored
TTM calls the default implementation now. Signed-off-by:
-
Christian König authored
TTM calls the default implementation now. Signed-off-by:
-
Christian König authored
TTM calls the default implementation now. Signed-off-by:
-
Christian König authored
Use ttm_pool_populate/ttm_pool_unpopulate if the driver doesn't provide a function. Signed-off-by:
-
Rex Zhu authored
Reviewed-by:
Rex Zhu <Rex.Zhu@amd.com> Signed-off-by:
-
Rex Zhu authored
1. move display num initialize out of dpm enable tasks. 2. do not set/restore smc telemetry if dpm is runing. Reviewed-by:
-
Rex Zhu authored
Add dpm check functions on CZ/Vega10 to smu backend function table. Reviewed-by:
-
Rex Zhu authored
when smu failed, print out the error info immediately for debug. smum_send_msg_to_smu always return true, so no need to check return value. Reviewed-by:
-
Rex Zhu authored
When smu msssage failed, print out return value in dmesg. Reviewed-by:
-
Rex Zhu authored
Avoid conflicts in reading the same register mmPCIE_INDEX2 with other clients Reviewed-by:
-
Corentin Labbe authored
This patch fix the following build warnings: CC [M] drivers/gpu/drm/amd/amdgpu/amdgpu_drv.o cc1: warning: ../display/: No such file or directory [-Wmissing-include-dirs] cc1: warning: ../display/include: No such file or directory [-Wmissing-include-dirs] CC [M] drivers/gpu/drm/amd/amdgpu/amdgpu_device.o cc1: warning: ../display/: No such file or directory [-Wmissing-include-dirs] cc1: warning: ../display/include: No such file or directory [-Wmissing-include-dirs] [...] This warning is shown for each file in amdgpu directory, so it spams a lot. Acked-by:
Corentin Labbe <clabbe@baylibre.com> Signed-off-by:
-
Corentin Labbe authored
The scheduler directory was removed via commit 1b1f42d8 ("drm: move amd_gpu_scheduler into common location") Remove it from include path. Reviewed-by:
-
Ben Crocker authored
In radeon_device_init, set the need_dma32 flag for Cedar chips (e.g. FirePro 2270). This fixes, or at least works around, a bug on PowerPC exposed by last year's commits 8e3f1b1d (Russell Currey) and 253fd51e (Alistair Popple) which enabled the 64-bit DMA iommu bypass. This caused the device to freeze, in some cases unrecoverably, and is the subject of several bug reports internal to Red Hat. Signed-off-by:
Ben Crocker <bcrocker@redhat.com> Signed-off-by:
-
Thierry Reding authored
There's no need to set this before the number of DMA bits has been properly determined. Signed-off-by:
Thierry Reding <treding@nvidia.com> Signed-off-by:
-
Rex Zhu authored
Reviewed-by:
-
Rex Zhu authored
Currently all pp features are enabled by default except OVERDRIVE Reviewed-by:
-
Eric Huang authored
a bug in programming thermal interrupt register masks out interrupts and driver cannot receive interrupts. Setting 0 to mask bits will fix it. Signed-off-by:
Eric Huang <JinHuiEric.Huang@amd.com> Acked-by:
-
Rex Zhu authored
powerplay need vram width to set default mclk optimization settings(uphyst/downhyst/activity threshold) Reviewed-by:
-
Christian König authored
We have a global dummy page in TTM, use that one instead of allocating a new one. Signed-off-by:
-
Rex Zhu authored
Lock the dpm levels when we use SW method to modify the dpm tables directly to avoid a possible race with the smu. Reviewed-by:
-
Rex Zhu authored
Clamp the clock index to a valid range when reading it back Reviewed-by:
-
Roger He authored
Because ttm_bo_force_list_clean() is only called on two occasions: 1. By ttm_bo_evict_mm() during suspend. 2. By ttm_bo_clean_mm() when the driver unloads. On both cases we absolutely don't want any memory allocation failure. Signed-off-by:
Roger He <Hongbo.He@amd.com> Reviewed-by:
-
Roger He authored
set TTM_OPT_FLAG_FORCE_ALLOC when we are servicing for page fault routine. for ttm_mem_global_reserve if in page fault routine, allow the gtt pages reservation always. because page fault routing already grabbed system memory and the allowance of this exception is harmless. Otherwise, it will trigger OOM killer. will be used later. v2: set the FORCE_ALLOC always v3: minor refine Signed-off-by:
-
Roger He authored
for saving memory and more bit flag can be used in future Signed-off-by:
-
Arnd Bergmann authored
In randconfig testing, we sometimes get this warning: drivers/gpu/drm/radeon/radeon_object.c: In function 'radeon_bo_create': drivers/gpu/drm/radeon/radeon_object.c:242:2: error: #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance thanks to write-combining [-Werror=cpp] #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \ This is rather annoying since almost all other code produces no build-time output unless we have found a real bug. We already fixed this in the amdgpu driver in commit 31bb90f1 ("drm/amdgpu: shut up #warning for compile testing") by adding a CONFIG_COMPILE_TEST check last year and agreed to do the same here, but both Michel and I then forgot about it until I came across the issue again now. For stable kernels, as this is one of very few remaining randconfig warnings in 4.14. Cc: stable@vger.kernel.org Link: https://patchwork.kernel.org/patch/9550009/Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
Christian König authored
To aid debugging set the page mapping during allocation instead of during VM faults. Signed-off-by:
-
- 20 Feb, 2018 5 commits
-
-
Alex Deucher authored
This reverts commit 1c331f75. Breaks resume on some systems. Bug: https://bugs.freedesktop.org/show_bug.cgi?id=100759Signed-off-by:
-
Christian König authored
We use our own backing store and don't need the shmem file. Signed-off-by:
Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by:
-
Christian König authored
We use our own backing store and don't need the shmem file. Signed-off-by:
-
Christian König authored
To be able to use DRI_PRIME with amdgpu and i915 we add all our fences only as exclusive ones. Disable that behavior when sharing between amdgpu itself cause it hinders concurrent execution. Signed-off-by:
-
Christian König authored
Instead of the pin/unpin callback implement the attach/detach ones. Functional identical, but allows us access to the attachment. Signed-off-by:
-
- 19 Feb, 2018 7 commits
-
-
Alex Deucher authored
The logic has moved to cgs. mclk switching with DC at higher refresh rates should work. Reviewed-by:
-
Alex Deucher authored
Clamp the vblank period to 0 if the refresh rate is larger than 120 hz for non-DC. This allows us to remove the refresh rate checks from powerplay for mclk switching. Reviewed-by:
-
Alex Deucher authored
If there are no displays attached, there is no reason to disable mclk switching. Fixes mclks getting set to high when there are no displays attached. Reviewed-by:
-
Alex Deucher authored
If there are no displays attached, there is no reason to disable mclk switching. Fixes mclks getting set to high when there are no displays attached. Reviewed-by:
-
Alex Deucher authored
Rather than open coding it. Reviewed-by:
-
Corentin Labbe authored
All thoses headers are not used by any source files. Lets just remove them. Signed-off-by:
-
Gustavo A. R. Silva authored
Currently, if amdgpu_vm_bo_update() fails, the returned error is being ignored. Fix this by properly checking _r_ after calling amdgpu_vm_bo_update. Also, remove redundant code just before label _error_. Addresses-Coverity-ID: 1464280 ("Unused value") Fixes: 0abc6878 ("drm/amdgpu: update VM PDs after the PTs") Signed-off-by:Gustavo A. R. Silva <gustavo@embeddedor.com> Reviewed-by:
-
