drm/ttm: replace busy placement with flags v6

Instead of a list of separate busy placement add flags which indicate
that a placement should only be used when there is room or if we need to
evict.

v2: add missing TTM_PL_FLAG_IDLE for i915
v3: fix auto build test ERROR on drm-tip/drm-tip
v4: fix some typos pointed out by checkpatch
v5: cleanup some rebase problems with VMWGFX
v6: implement some missing VMWGFX functionality pointed out by Zack,
    rename the flags as suggested by Michel, rebase on drm-tip and
    adjust XE as well

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Reviewed-by: Zack Rusin <zack.rusin@broadcom.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240112125158.2748-4-christian.koenig@amd.com

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

@@ -220,9 +220,6 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 
 	placement->num_placement = c;
 	placement->placement = places;
-
-	placement->num_busy_placement = c;
-	placement->busy_placement = places;
 }
 
 /**
@@ -1406,8 +1403,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 					AMDGPU_GEM_DOMAIN_GTT);
 
 	/* Avoid costly evictions; only set GTT as a busy placement */
-	abo->placement.num_busy_placement = 1;
-	abo->placement.busy_placement = &abo->placements[1];
+	abo->placements[0].flags |= TTM_PL_FLAG_DESIRED;
 
 	r = ttm_bo_validate(bo, &abo->placement, &ctx);
 	if (unlikely(r == -EBUSY || r == -ERESTARTSYS))

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

@@ -102,23 +102,19 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	/* Don't handle scatter gather BOs */
 	if (bo->type == ttm_bo_type_sg) {
 		placement->num_placement = 0;
-		placement->num_busy_placement = 0;
 		return;
 	}
 
 	/* Object isn't an AMDGPU object so ignore */
 	if (!amdgpu_bo_is_amdgpu_bo(bo)) {
 		placement->placement = &placements;
-		placement->busy_placement = &placements;
 		placement->num_placement = 1;
-		placement->num_busy_placement = 1;
 		return;
 	}
 
 	abo = ttm_to_amdgpu_bo(bo);
 	if (abo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) {
 		placement->num_placement = 0;
-		placement->num_busy_placement = 0;
 		return;
 	}
 
@@ -128,13 +124,13 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	case AMDGPU_PL_OA:
 	case AMDGPU_PL_DOORBELL:
 		placement->num_placement = 0;
-		placement->num_busy_placement = 0;
 		return;
 
 	case TTM_PL_VRAM:
 		if (!adev->mman.buffer_funcs_enabled) {
 			/* Move to system memory */
 			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+
 		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
 			   amdgpu_bo_in_cpu_visible_vram(abo)) {
@@ -149,8 +145,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 							AMDGPU_GEM_DOMAIN_CPU);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
-			abo->placement.busy_placement = &abo->placements[1];
-			abo->placement.num_busy_placement = 1;
+			abo->placements[0].flags |= TTM_PL_FLAG_DESIRED;
 		} else {
 			/* Move to GTT memory */
 			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT |
@@ -967,8 +962,6 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 	/* allocate GART space */
 	placement.num_placement = 1;
 	placement.placement = &placements;
-	placement.num_busy_placement = 1;
-	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT;
 	placements.mem_type = TTM_PL_TT;

drivers/gpu/drm/drm_gem_vram_helper.c

@@ -147,7 +147,6 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 		invariant_flags = TTM_PL_FLAG_TOPDOWN;
 
 	gbo->placement.placement = gbo->placements;
-	gbo->placement.busy_placement = gbo->placements;
 
 	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_VRAM) {
 		gbo->placements[c].mem_type = TTM_PL_VRAM;
@@ -160,7 +159,6 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 	}
 
 	gbo->placement.num_placement = c;
-	gbo->placement.num_busy_placement = c;
 
 	for (i = 0; i < c; ++i) {
 		gbo->placements[i].fpfn = 0;

drivers/gpu/drm/i915/gem/i915_gem_ttm.c

@@ -65,8 +65,6 @@ static const struct ttm_place sys_placement_flags = {
 static struct ttm_placement i915_sys_placement = {
 	.num_placement = 1,
 	.placement = &sys_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags,
 };
 
 /**
@@ -157,32 +155,28 @@ i915_ttm_place_from_region(const struct intel_memory_region *mr,
 
 static void
 i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
-			    struct ttm_place *requested,
-			    struct ttm_place *busy,
+			    struct ttm_place *places,
 			    struct ttm_placement *placement)
 {
 	unsigned int num_allowed = obj->mm.n_placements;
 	unsigned int flags = obj->flags;
 	unsigned int i;
 
-	placement->num_placement = 1;
+	places[0].flags |= TTM_PL_FLAG_DESIRED;
 	i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
-				   obj->mm.region, requested, obj->bo_offset,
+				   obj->mm.region, &places[0], obj->bo_offset,
 				   obj->base.size, flags);
 
 	/* Cache this on object? */
-	placement->num_busy_placement = num_allowed;
-	for (i = 0; i < placement->num_busy_placement; ++i)
-		i915_ttm_place_from_region(obj->mm.placements[i], busy + i,
-					   obj->bo_offset, obj->base.size, flags);
-
-	if (num_allowed == 0) {
-		*busy = *requested;
-		placement->num_busy_placement = 1;
+	for (i = 0; i < num_allowed; ++i) {
+		i915_ttm_place_from_region(obj->mm.placements[i],
+					   &places[i + 1], obj->bo_offset,
+					   obj->base.size, flags);
+		places[i + 1].flags |= TTM_PL_FLAG_FALLBACK;
 	}
 
-	placement->placement = requested;
-	placement->busy_placement = busy;
+	placement->num_placement = num_allowed + 1;
+	placement->placement = places;
 }
 
 static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
@@ -789,7 +783,8 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 	int ret;
 
 	/* First try only the requested placement. No eviction. */
-	real_num_busy = fetch_and_zero(&placement->num_busy_placement);
+	real_num_busy = placement->num_placement;
+	placement->num_placement = 1;
 	ret = ttm_bo_validate(bo, placement, &ctx);
 	if (ret) {
 		ret = i915_ttm_err_to_gem(ret);
@@ -805,7 +800,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 		 * If the initial attempt fails, allow all accepted placements,
 		 * evicting if necessary.
 		 */
-		placement->num_busy_placement = real_num_busy;
+		placement->num_placement = real_num_busy;
 		ret = ttm_bo_validate(bo, placement, &ctx);
 		if (ret)
 			return i915_ttm_err_to_gem(ret);
@@ -839,7 +834,7 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 
 static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
 {
-	struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
+	struct ttm_place places[I915_TTM_MAX_PLACEMENTS + 1];
 	struct ttm_placement placement;
 
 	/* restricted by sg_alloc_table */
@@ -849,7 +844,7 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
 	GEM_BUG_ON(obj->mm.n_placements > I915_TTM_MAX_PLACEMENTS);
 
 	/* Move to the requested placement. */
-	i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
+	i915_ttm_placement_from_obj(obj, places, &placement);
 
 	return __i915_ttm_get_pages(obj, &placement);
 }
@@ -879,9 +874,7 @@ static int __i915_ttm_migrate(struct drm_i915_gem_object *obj,
 	i915_ttm_place_from_region(mr, &requested, obj->bo_offset,
 				   obj->base.size, flags);
 	placement.num_placement = 1;
-	placement.num_busy_placement = 1;
 	placement.placement = &requested;
-	placement.busy_placement = &requested;
 
 	ret = __i915_ttm_get_pages(obj, &placement);
 	if (ret)

drivers/gpu/drm/loongson/lsdc_ttm.c

@@ -54,7 +54,6 @@ static void lsdc_bo_set_placement(struct lsdc_bo *lbo, u32 domain)
 		pflags |= TTM_PL_FLAG_TOPDOWN;
 
 	lbo->placement.placement = lbo->placements;
-	lbo->placement.busy_placement = lbo->placements;
 
 	if (domain & LSDC_GEM_DOMAIN_VRAM) {
 		lbo->placements[c].mem_type = TTM_PL_VRAM;
@@ -77,7 +76,6 @@ static void lsdc_bo_set_placement(struct lsdc_bo *lbo, u32 domain)
 	}
 
 	lbo->placement.num_placement = c;
-	lbo->placement.num_busy_placement = c;
 
 	for (i = 0; i < c; ++i) {
 		lbo->placements[i].fpfn = 0;

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -403,27 +403,6 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 	return 0;
 }
 
-static void
-set_placement_list(struct ttm_place *pl, unsigned *n, uint32_t domain)
-{
-	*n = 0;
-
-	if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
-		pl[*n].mem_type = TTM_PL_VRAM;
-		pl[*n].flags = 0;
-		(*n)++;
-	}
-	if (domain & NOUVEAU_GEM_DOMAIN_GART) {
-		pl[*n].mem_type = TTM_PL_TT;
-		pl[*n].flags = 0;
-		(*n)++;
-	}
-	if (domain & NOUVEAU_GEM_DOMAIN_CPU) {
-		pl[*n].mem_type = TTM_PL_SYSTEM;
-		pl[(*n)++].flags = 0;
-	}
-}
-
 static void
 set_placement_range(struct nouveau_bo *nvbo, uint32_t domain)
 {
@@ -451,26 +430,39 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t domain)
 			nvbo->placements[i].fpfn = fpfn;
 			nvbo->placements[i].lpfn = lpfn;
 		}
-		for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
-			nvbo->busy_placements[i].fpfn = fpfn;
-			nvbo->busy_placements[i].lpfn = lpfn;
-		}
 	}
 }
 
 void
 nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t domain,
 			 uint32_t busy)
 {
-	struct ttm_placement *pl = &nvbo->placement;
+	unsigned int *n = &nvbo->placement.num_placement;
+	struct ttm_place *pl = nvbo->placements;
 
-	pl->placement = nvbo->placements;
-	set_placement_list(nvbo->placements, &pl->num_placement, domain);
+	domain |= busy;
 
-	pl->busy_placement = nvbo->busy_placements;
-	set_placement_list(nvbo->busy_placements, &pl->num_busy_placement,
-			   domain | busy);
+	*n = 0;
+	if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
+		pl[*n].mem_type = TTM_PL_VRAM;
+		pl[*n].flags = busy & NOUVEAU_GEM_DOMAIN_VRAM ?
+			TTM_PL_FLAG_FALLBACK : 0;
+		(*n)++;
+	}
+	if (domain & NOUVEAU_GEM_DOMAIN_GART) {
+		pl[*n].mem_type = TTM_PL_TT;
+		pl[*n].flags = busy & NOUVEAU_GEM_DOMAIN_GART ?
+			TTM_PL_FLAG_FALLBACK : 0;
+		(*n)++;
+	}
+	if (domain & NOUVEAU_GEM_DOMAIN_CPU) {
+		pl[*n].mem_type = TTM_PL_SYSTEM;
+		pl[*n].flags = busy & NOUVEAU_GEM_DOMAIN_CPU ?
+			TTM_PL_FLAG_FALLBACK : 0;
+		(*n)++;
+	}
 
+	nvbo->placement.placement = nvbo->placements;
 	set_placement_range(nvbo, domain);
 }
 
@@ -1313,11 +1305,6 @@ vm_fault_t nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 			nvbo->placements[i].lpfn = mappable;
 		}
 
-		for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
-			nvbo->busy_placements[i].fpfn = 0;
-			nvbo->busy_placements[i].lpfn = mappable;
-		}
-
 		nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, 0);
 	}
 

drivers/gpu/drm/nouveau/nouveau_bo.h

@@ -15,7 +15,6 @@ struct nouveau_bo {
 	struct ttm_placement placement;
 	u32 valid_domains;
 	struct ttm_place placements[3];
-	struct ttm_place busy_placements[3];
 	bool force_coherent;
 	struct ttm_bo_kmap_obj kmap;
 	struct list_head head;

drivers/gpu/drm/qxl/qxl_object.c

@@ -66,7 +66,6 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain)
 		pflag |= TTM_PL_FLAG_TOPDOWN;
 
 	qbo->placement.placement = qbo->placements;
-	qbo->placement.busy_placement = qbo->placements;
 	if (domain == QXL_GEM_DOMAIN_VRAM) {
 		qbo->placements[c].mem_type = TTM_PL_VRAM;
 		qbo->placements[c++].flags = pflag;
@@ -86,7 +85,6 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain)
 		qbo->placements[c++].flags = 0;
 	}
 	qbo->placement.num_placement = c;
-	qbo->placement.num_busy_placement = c;
 	for (i = 0; i < c; ++i) {
 		qbo->placements[i].fpfn = 0;
 		qbo->placements[i].lpfn = 0;

drivers/gpu/drm/qxl/qxl_ttm.c

@@ -60,9 +60,7 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 
 	if (!qxl_ttm_bo_is_qxl_bo(bo)) {
 		placement->placement = &placements;
-		placement->busy_placement = &placements;
 		placement->num_placement = 1;
-		placement->num_busy_placement = 1;
 		return;
 	}
 	qbo = to_qxl_bo(bo);

drivers/gpu/drm/radeon/radeon_object.c

@@ -78,7 +78,6 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	u32 c = 0, i;
 
 	rbo->placement.placement = rbo->placements;
-	rbo->placement.busy_placement = rbo->placements;
 	if (domain & RADEON_GEM_DOMAIN_VRAM) {
 		/* Try placing BOs which don't need CPU access outside of the
 		 * CPU accessible part of VRAM
@@ -114,7 +113,6 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	}
 
 	rbo->placement.num_placement = c;
-	rbo->placement.num_busy_placement = c;
 
 	for (i = 0; i < c; ++i) {
 		if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&

drivers/gpu/drm/radeon/radeon_ttm.c

@@ -92,9 +92,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 
 	if (!radeon_ttm_bo_is_radeon_bo(bo)) {
 		placement->placement = &placements;
-		placement->busy_placement = &placements;
 		placement->num_placement = 1;
-		placement->num_busy_placement = 1;
 		return;
 	}
 	rbo = container_of(bo, struct radeon_bo, tbo);
@@ -114,15 +112,11 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 			 */
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM |
 							 RADEON_GEM_DOMAIN_GTT);
-			rbo->placement.num_busy_placement = 0;
 			for (i = 0; i < rbo->placement.num_placement; i++) {
 				if (rbo->placements[i].mem_type == TTM_PL_VRAM) {
 					if (rbo->placements[i].fpfn < fpfn)
 						rbo->placements[i].fpfn = fpfn;
-				} else {
-					rbo->placement.busy_placement =
-						&rbo->placements[i];
-					rbo->placement.num_busy_placement = 1;
+					rbo->placements[0].flags |= TTM_PL_FLAG_DESIRED;
 				}
 			}
 		} else

drivers/gpu/drm/radeon/radeon_uvd.c

@@ -324,7 +324,6 @@ void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo,
 	rbo->placements[1].fpfn += (256 * 1024 * 1024) >> PAGE_SHIFT;
 	rbo->placements[1].lpfn += (256 * 1024 * 1024) >> PAGE_SHIFT;
 	rbo->placement.num_placement++;
-	rbo->placement.num_busy_placement++;
 }
 
 void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)