tjh.dev / kernel
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
1
fork

Configure Feed

Select the types of activity you want to include in your feed.

drm/amdgpu/ttm: Initialize AMDGPU_PL_MMIO_REMAP Heap

Add a one-page TTM range manager for AMDGPU_PL_MMIO_REMAP via
amdgpu_ttm_init_on_chip(). This only registers the placement with TTM;
no BO is allocated in this patch.

The singleton 4K remap BO is created and freed in the following patch.

This split follows to separate heap bring-up from BO allocation.

Cc: Christian König <christian.koenig@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

authored by

Srinivasan Shanmugam and committed by
Alex Deucher a3ac30ff fb5a52db

+9
+9
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
··· 2021 2021 return r; 2022 2022 } 2023 2023 2024 + /* Initialize MMIO-remap pool (single page 4K) */ 2025 + r = amdgpu_ttm_init_on_chip(adev, AMDGPU_PL_MMIO_REMAP, 1); 2026 + if (r) { 2027 + dev_err(adev->dev, "Failed initializing MMIO-remap heap.\n"); 2028 + return r; 2029 + } 2030 + 2024 2031 /* Initialize preemptible memory pool */ 2025 2032 r = amdgpu_preempt_mgr_init(adev); 2026 2033 if (r) { ··· 2090 2083 } 2091 2084 amdgpu_bo_free_kernel(&adev->mman.sdma_access_bo, NULL, 2092 2085 &adev->mman.sdma_access_ptr); 2086 + 2093 2087 amdgpu_ttm_fw_reserve_vram_fini(adev); 2094 2088 amdgpu_ttm_drv_reserve_vram_fini(adev); 2095 2089 ··· 2112 2104 ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GWS); 2113 2105 ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_OA); 2114 2106 ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_DOORBELL); 2107 + ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_MMIO_REMAP); 2115 2108 ttm_device_fini(&adev->mman.bdev); 2116 2109 adev->mman.initialized = false; 2117 2110 dev_info(adev->dev, "amdgpu: ttm finalized\n");