summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
diff options
context:
space:
mode:
authorAlex Deucher <alexander.deucher@amd.com>2023-07-14 16:11:26 +0300
committerAlex Deucher <alexander.deucher@amd.com>2023-08-08 00:14:06 +0300
commitdc3499c71d3618130d9c6675e4de1e3562c17125 (patch)
treee640d64e12963c4734daf0f62941f48a4d609ed3 /drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
parent05c899eacc0412bae0581add19c4062db8bdffda (diff)
downloadlinux-dc3499c71d3618130d9c6675e4de1e3562c17125.tar.xz
drm/amdgpu: accommodate DOMAIN/PL_DOORBELL
This patch adds changes: - to accommodate the new GEM domain for DOORBELLs - to accommodate the new TTM PL for DOORBELLs in order to manage doorbell pages as GEM object. V2: Addressed reviwe comments from Christian - drop the doorbell changes for pinning/unpinning - drop the doorbell changes for dma-buf map - drop the doorbell changes for sgt - no need to handle TTM_PL_FLAG_CONTIGUOUS for doorbell - add caching type for doorbell V3: - Removed unrelated empty line (Christian) - Add PL_DOORBELL in mem_type_to_domain() as well (Alex) Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian Koenig <christian.koenig@amd.com> Reviewed-by: Christian Koenig <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h2
1 files changed, 2 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index 5c4f93ee0c57..3c988cc406e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -90,6 +90,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
cur->node = block;
break;
case TTM_PL_TT:
+ case AMDGPU_PL_DOORBELL:
node = to_ttm_range_mgr_node(res)->mm_nodes;
while (start >= node->size << PAGE_SHIFT)
start -= node++->size << PAGE_SHIFT;
@@ -152,6 +153,7 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
cur->size = min(amdgpu_vram_mgr_block_size(block), cur->remaining);
break;
case TTM_PL_TT:
+ case AMDGPU_PL_DOORBELL:
node = cur->node;
cur->node = ++node;