drm/amdgpu: Modify the contiguous flags behaviour

Now we have two flags for contiguous VRAM buffer allocation.
If the application request for AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS,
it would set the ttm place TTM_PL_FLAG_CONTIGUOUS flag in the
buffer's placement function.

This patch will change the default behaviour of the two flags.

When we set AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS
- This means contiguous is not mandatory.
- we will try to allocate the contiguous buffer. Say if the
  allocation fails, we fallback to allocate the individual pages.

When we setTTM_PL_FLAG_CONTIGUOUS
- This means contiguous allocation is mandatory.
- we are setting this in amdgpu_bo_pin_restricted() before bo validation
  and check this flag in the vram manager file.
- if this is set, we should allocate the buffer pages contiguously.
  the allocation fails, we return -ENOSPC.

v2:
  - keep the mem_flags and bo->flags check as is(Christian)
  - place the TTM_PL_FLAG_CONTIGUOUS flag setting into the
    amdgpu_bo_pin_restricted function placement range iteration
    loop(Christian)
  - rename find_pages with amdgpu_vram_mgr_calculate_pages_per_block
    (Christian)
  - Keep the kernel BO allocation as is(Christain)
  - If BO pin vram allocation failed, we need to return -ENOSPC as
    RDMA cannot work with scattered VRAM pages(Philip)

v3(Christian):
  - keep contiguous flag handling outside of pages_per_block
    calculation
  - remove the hacky implementation in contiguous flag error
    handling code

v4(Christian):
  - use any variable and return value for non-contiguous
    fallback

v5: rebase to amd-staging-drm-next branch

Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -153,8 +153,10 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		else
 			places[c].flags |= TTM_PL_FLAG_TOPDOWN;
 
-		if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
+		if (abo->tbo.type == ttm_bo_type_kernel &&
+		    flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
 			places[c].flags |= TTM_PL_FLAG_CONTIGUOUS;
+
 		c++;
 	}
 
@@ -967,6 +969,10 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		if (!bo->placements[i].lpfn ||
 		    (lpfn && lpfn < bo->placements[i].lpfn))
 			bo->placements[i].lpfn = lpfn;
+
+		if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS &&
+		    bo->placements[i].mem_type == TTM_PL_VRAM)
+			bo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS;
 	}
 
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);

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

@@ -450,6 +450,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = to_amdgpu_device(mgr);
+	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 	u64 vis_usage = 0, max_bytes, min_block_size;
 	struct amdgpu_vram_mgr_resource *vres;
 	u64 size, remaining_size, lpfn, fpfn;
@@ -468,7 +469,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	if (tbo->type != ttm_bo_type_kernel)
 		max_bytes -= AMDGPU_VM_RESERVED_VRAM;
 
-	if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS) {
 		pages_per_block = ~0ul;
 	} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -477,7 +478,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 		/* default to 2MB */
 		pages_per_block = 2UL << (20UL - PAGE_SHIFT);
 #endif
-		pages_per_block = max_t(uint32_t, pages_per_block,
+		pages_per_block = max_t(u32, pages_per_block,
 					tbo->page_alignment);
 	}
 
@@ -498,7 +499,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	if (place->flags & TTM_PL_FLAG_TOPDOWN)
 		vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
 
-	if (place->flags & TTM_PL_FLAG_CONTIGUOUS)
+	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
 		vres->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
 
 	if (fpfn || lpfn != mgr->mm.size)
@@ -514,21 +515,31 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 		else
 			min_block_size = mgr->default_page_size;
 
-		BUG_ON(min_block_size < mm->chunk_size);
-
 		/* Limit maximum size to 2GiB due to SG table limitations */
 		size = min(remaining_size, 2ULL << 30);
 
 		if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
-				!(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
+		    !(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
 			min_block_size = (u64)pages_per_block << PAGE_SHIFT;
 
+		BUG_ON(min_block_size < mm->chunk_size);
+
 		r = drm_buddy_alloc_blocks(mm, fpfn,
 					   lpfn,
 					   size,
 					   min_block_size,
 					   &vres->blocks,
 					   vres->flags);
+
+		if (unlikely(r == -ENOSPC) && pages_per_block == ~0ul &&
+		    !(place->flags & TTM_PL_FLAG_CONTIGUOUS)) {
+			vres->flags &= ~DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+			pages_per_block = max_t(u32, 2UL << (20UL - PAGE_SHIFT),
+						tbo->page_alignment);
+
+			continue;
+		}
+
 		if (unlikely(r))
 			goto error_free_blocks;