diff options
author | Amber Lin <Amber.Lin@amd.com> | 2018-02-27 10:01:59 -0500 |
---|---|---|
committer | Alex Deucher <alexander.deucher@amd.com> | 2018-02-28 15:38:46 -0500 |
commit | f8f4b9a679e52298b14358db22c37a135e7086ec (patch) | |
tree | d832f1bc6717908756b81280b48d1c00e2b3f8b1 /drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | |
parent | 5d447f09b8d8346c64f4c952a67c61f7ce88d3c1 (diff) |
drm/amdgpu: Map all visible VRAM at startup
When using CPU to update page table, we need to kmap all the PDs/PTs after
they are allocated and that requires a TLB shot down on each CPU, which is
quite heavy.
Instead, we map the whole visible VRAM to a kernel address at once. Pages
can be obtained from the offset.
v2: move the mapping base from gmc to amdgpu_mman structure, and the
implementation in amdgpu_ttm_* functions
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index e38e6db8f760..f126a5ae41b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -621,6 +621,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_ { struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); + struct drm_mm_node *mm_node = mem->mm_node; mem->bus.addr = NULL; mem->bus.offset = 0; @@ -640,6 +641,15 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_ /* check if it's visible */ if ((mem->bus.offset + mem->bus.size) > adev->gmc.visible_vram_size) return -EINVAL; + /* Only physically contiguous buffers apply. In a contiguous + * buffer, size of the first mm_node would match the number of + * pages in ttm_mem_reg. + */ + if (adev->mman.aper_base_kaddr && + (mm_node->size == mem->num_pages)) + mem->bus.addr = (u8 *)adev->mman.aper_base_kaddr + + mem->bus.offset; + mem->bus.base = adev->gmc.aper_base; mem->bus.is_iomem = true; break; @@ -1402,6 +1412,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) /* Change the size here instead of the init above so only lpfn is affected */ amdgpu_ttm_set_active_vram_size(adev, adev->gmc.visible_vram_size); +#ifdef CONFIG_64BIT + adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base, + adev->gmc.visible_vram_size); +#endif /* *The reserved vram for firmware must be pinned to the specified @@ -1494,6 +1508,9 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev) amdgpu_ttm_debugfs_fini(adev); amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL); amdgpu_ttm_fw_reserve_vram_fini(adev); + if (adev->mman.aper_base_kaddr) + iounmap(adev->mman.aper_base_kaddr); + adev->mman.aper_base_kaddr = NULL; ttm_bo_clean_mm(&adev->mman.bdev, TTM_PL_VRAM); ttm_bo_clean_mm(&adev->mman.bdev, TTM_PL_TT); |