linux/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c, branch v4.20

drm/amdgpu: Limit the max mc address to hole start

2018-10-10T19:48:02Z

For the vram_start is 0 case, the gart range will be from 0x0000FFFF00000000 to 0x0000FFFF1FFFFFFF, which will cause the engine hang. So to avoid the hole, limit the max mc address to AMDGPU_GMC_HOLE_START.:wq Signed-off-by: Emily Deng Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: fix AGP location with VRAM at 0x0

2018-10-09T22:06:58Z

That also simplifies handling quite a bit. Signed-off-by: Christian König Reviewed-by: Junwei Zhang Reviewed-by: Huang Rui Signed-off-by: Alex Deucher

drm/amdgpu: fix mask in GART location calculation

2018-09-14T15:05:34Z

We need to mask the lower bits not the upper one. Fixes: ec210e3226dc0 drm/amdgpu: put GART away from VRAM v2 Signed-off-by: Christian König Reviewed-by: Alex Deucher Acked-by: James Zhu Tested-by: James Zhu Signed-off-by: Alex Deucher

drm/amdgpu/gmc9: Adjust GART and AGP location with xgmi offset (v2)

2018-09-11T03:47:34Z

On hives with xgmi enabled, the fb_location aperture is a size which defines the total framebuffer size of all nodes in the hive. Each GPU in the hive has the same view via the fb_location aperture. GPU0 starts at offset (0 * segment size), GPU1 starts at offset (1 * segment size), etc. For access to local vram on each GPU, we need to take this offset into account. This including on setting up GPUVM page table and GART table v2: squash in "drm/amdgpu: Init correct fb region for none XGMI configuration" Acked-by: Huang Rui Acked-by: Slava Abramov Signed-off-by: Shaoyun Liu Signed-off-by: Alex Deucher Reviewed-by: Felix Kuehling Acked-by: Huang Rui

drm/amdgpu: use the AGP aperture for system memory access v2

2018-09-11T03:41:39Z

Start to use the old AGP aperture for system memory access. v2: Move that to amdgpu_ttm_alloc_gart Signed-off-by: Christian König Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: add amdgpu_gmc_agp_location v3

2018-09-11T03:41:32Z

Helper to figure out the location of the AGP BAR. v2: fix a couple of bugs v3: correctly add one to vram_end Signed-off-by: Christian König Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: put GART away from VRAM v2

2018-08-30T14:03:37Z

Always try to put the GART away from where VRAM is. v2: correctly handle the 4GB limitation Signed-off-by: Christian König Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: use the smaller hole for GART

2018-08-29T17:35:52Z

Instead of the larger one use the smaller hole in the MC address space for the GART mappings. Signed-off-by: Christian König Reviewed-by: Junwei Zhang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: fix amdgpu_gmc_gart_location a little bit

2018-08-29T17:35:24Z

Improve the VCE limitation handling. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher

drm/amdgpu: move amdgpu_device_(vram|gtt)_location

2018-08-29T17:35:18Z

Move that into amdgpu_gmc.c since we are really deadling with GMC address space here. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher