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>

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

@@ -158,6 +158,14 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
+	if (domain & AMDGPU_GEM_DOMAIN_DOORBELL) {
+		places[c].fpfn = 0;
+		places[c].lpfn = 0;
+		places[c].mem_type = AMDGPU_PL_DOORBELL;
+		places[c].flags = 0;
+		c++;
+	}
+
 	if (domain & AMDGPU_GEM_DOMAIN_GTT) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
@@ -477,7 +485,7 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
 		goto fail;
 	}
 
-	/* TODO add more domains checks, such as AMDGPU_GEM_DOMAIN_CPU */
+	/* TODO add more domains checks, such as AMDGPU_GEM_DOMAIN_CPU, _DOMAIN_DOORBELL */
 	return true;
 
 fail:
@@ -1029,6 +1037,7 @@ void amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	} else if (bo->tbo.resource->mem_type == TTM_PL_TT) {
 		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
 	}
+
 }
 
 static const char * const amdgpu_vram_names[] = {

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

@@ -182,6 +182,8 @@ static inline unsigned amdgpu_mem_type_to_domain(u32 mem_type)
 		return AMDGPU_GEM_DOMAIN_GWS;
 	case AMDGPU_PL_OA:
 		return AMDGPU_GEM_DOMAIN_OA;
+	case AMDGPU_PL_DOORBELL:
+		return AMDGPU_GEM_DOMAIN_DOORBELL;
 	default:
 		break;
 	}

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;

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

@@ -127,6 +127,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	case AMDGPU_PL_GDS:
 	case AMDGPU_PL_GWS:
 	case AMDGPU_PL_OA:
+	case AMDGPU_PL_DOORBELL:
 		placement->num_placement = 0;
 		placement->num_busy_placement = 0;
 		return;
@@ -496,9 +497,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	if (old_mem->mem_type == AMDGPU_PL_GDS ||
 	    old_mem->mem_type == AMDGPU_PL_GWS ||
 	    old_mem->mem_type == AMDGPU_PL_OA ||
+	    old_mem->mem_type == AMDGPU_PL_DOORBELL ||
 	    new_mem->mem_type == AMDGPU_PL_GDS ||
 	    new_mem->mem_type == AMDGPU_PL_GWS ||
-	    new_mem->mem_type == AMDGPU_PL_OA) {
+	    new_mem->mem_type == AMDGPU_PL_OA ||
+	    new_mem->mem_type == AMDGPU_PL_DOORBELL) {
 		/* Nothing to save here */
 		ttm_bo_move_null(bo, new_mem);
 		goto out;
@@ -582,6 +585,12 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev,
 		mem->bus.offset += adev->gmc.aper_base;
 		mem->bus.is_iomem = true;
 		break;
+	case AMDGPU_PL_DOORBELL:
+		mem->bus.offset = mem->start << PAGE_SHIFT;
+		mem->bus.offset += adev->doorbell.base;
+		mem->bus.is_iomem = true;
+		mem->bus.caching = ttm_uncached;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -596,6 +605,10 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
 
 	amdgpu_res_first(bo->resource, (u64)page_offset << PAGE_SHIFT, 0,
 			 &cursor);
+
+	if (bo->resource->mem_type == AMDGPU_PL_DOORBELL)
+		return ((uint64_t)(adev->doorbell.base + cursor.start)) >> PAGE_SHIFT;
+
 	return (adev->gmc.aper_base + cursor.start) >> PAGE_SHIFT;
 }
 
@@ -1305,6 +1318,7 @@ uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem)
 		flags |= AMDGPU_PTE_VALID;
 
 	if (mem && (mem->mem_type == TTM_PL_TT ||
+		    mem->mem_type == AMDGPU_PL_DOORBELL ||
 		    mem->mem_type == AMDGPU_PL_PREEMPT)) {
 		flags |= AMDGPU_PTE_SYSTEM;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h

@@ -33,6 +33,7 @@
 #define AMDGPU_PL_GWS		(TTM_PL_PRIV + 1)
 #define AMDGPU_PL_OA		(TTM_PL_PRIV + 2)
 #define AMDGPU_PL_PREEMPT	(TTM_PL_PRIV + 3)
+#define AMDGPU_PL_DOORBELL	(TTM_PL_PRIV + 4)
 
 #define AMDGPU_GTT_MAX_TRANSFER_SIZE	512
 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS	2