drm/xe/migrate: Parameterize ccs and bo data clear in xe_migrate_clear()

Parameterize clearing ccs and bo data in xe_migrate_clear() which  higher
layers can utilize. This patch will be used later on when doing bo data
clear for igfx as well.

v2: Replace multiple params with flags in xe_migrate_clear (Matt B)
v3: s/CLEAR_BO_DATA_FLAG_*/XE_MIGRATE_CLEAR_FLAG_* and move to
    xe_migrate.h. other nits(Matt B)

Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Akshata Jahagirdar <akshata.jahagirdar@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240809220347.25330-1-nirmoy.das@intel.comSigned-off-by: Nirmoy Das <nirmoy.das@intel.com>

drivers/gpu/drm/xe/tests/xe_bo.c

@@ -36,7 +36,8 @@ static int ccs_test_migrate(struct xe_tile *tile, struct xe_bo *bo,
 
 	/* Optionally clear bo *and* CCS data in VRAM. */
 	if (clear) {
-		fence = xe_migrate_clear(tile->migrate, bo, bo->ttm.resource);
+		fence = xe_migrate_clear(tile->migrate, bo, bo->ttm.resource,
+					 XE_MIGRATE_CLEAR_FLAG_FULL);
 		if (IS_ERR(fence)) {
 			KUNIT_FAIL(test, "Failed to submit bo clear.\n");
 			return PTR_ERR(fence);

drivers/gpu/drm/xe/tests/xe_migrate.c

@@ -105,7 +105,8 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo,
 	}
 
 	xe_map_memset(xe, &remote->vmap, 0, 0xd0, remote->size);
-	fence = xe_migrate_clear(m, remote, remote->ttm.resource);
+	fence = xe_migrate_clear(m, remote, remote->ttm.resource,
+				 XE_MIGRATE_CLEAR_FLAG_FULL);
 	if (!sanity_fence_failed(xe, fence, big ? "Clearing remote big bo" :
 				 "Clearing remote small bo", test)) {
 		retval = xe_map_rd(xe, &remote->vmap, 0, u64);
@@ -279,7 +280,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
 	kunit_info(test, "Clearing small buffer object\n");
 	xe_map_memset(xe, &tiny->vmap, 0, 0x22, tiny->size);
 	expected = 0;
-	fence = xe_migrate_clear(m, tiny, tiny->ttm.resource);
+	fence = xe_migrate_clear(m, tiny, tiny->ttm.resource,
+				 XE_MIGRATE_CLEAR_FLAG_FULL);
 	if (sanity_fence_failed(xe, fence, "Clearing small bo", test))
 		goto out;
 
@@ -300,7 +302,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
 	kunit_info(test, "Clearing big buffer object\n");
 	xe_map_memset(xe, &big->vmap, 0, 0x11, big->size);
 	expected = 0;
-	fence = xe_migrate_clear(m, big, big->ttm.resource);
+	fence = xe_migrate_clear(m, big, big->ttm.resource,
+				 XE_MIGRATE_CLEAR_FLAG_FULL);
 	if (sanity_fence_failed(xe, fence, "Clearing big bo", test))
 		goto out;
 
@@ -603,7 +606,8 @@ static void test_clear(struct xe_device *xe, struct xe_tile *tile,
 
 	kunit_info(test, "Clear vram buffer object\n");
 	expected = 0x0000000000000000;
-	fence = xe_migrate_clear(tile->migrate, vram_bo, vram_bo->ttm.resource);
+	fence = xe_migrate_clear(tile->migrate, vram_bo, vram_bo->ttm.resource,
+				 XE_MIGRATE_CLEAR_FLAG_FULL);
 	if (sanity_fence_failed(xe, fence, "Clear vram_bo", test))
 		return;
 	dma_fence_put(fence);

drivers/gpu/drm/xe/xe_bo.c

@@ -793,8 +793,16 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 			}
 		}
 	} else {
-		if (move_lacks_source)
-			fence = xe_migrate_clear(migrate, bo, new_mem);
+		if (move_lacks_source) {
+			u32 flags = 0;
+
+			if (mem_type_is_vram(new_mem->mem_type))
+				flags |= XE_MIGRATE_CLEAR_FLAG_FULL;
+			else if (handle_system_ccs)
+				flags |= XE_MIGRATE_CLEAR_FLAG_CCS_DATA;
+
+			fence = xe_migrate_clear(migrate, bo, new_mem, flags);
+		}
 		else
 			fence = xe_migrate_copy(migrate, bo, bo, old_mem,
 						new_mem, handle_system_ccs);

drivers/gpu/drm/xe/xe_migrate.c

@@ -1037,9 +1037,11 @@ static void emit_clear(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs,
  * @m: The migration context.
  * @bo: The buffer object @dst is currently bound to.
  * @dst: The dst TTM resource to be cleared.
+ * @clear_flags: flags to specify which data to clear: CCS, BO, or both.
  *
- * Clear the contents of @dst to zero. On flat CCS devices,
- * the CCS metadata is cleared to zero as well on VRAM destinations.
+ * Clear the contents of @dst to zero when XE_MIGRATE_CLEAR_FLAG_BO_DATA is set.
+ * On flat CCS devices, the CCS metadata is cleared to zero with XE_MIGRATE_CLEAR_FLAG_CCS_DATA.
+ * Set XE_MIGRATE_CLEAR_FLAG_FULL to clear bo as well as CCS metadata.
  * TODO: Eliminate the @bo argument.
  *
  * Return: Pointer to a dma_fence representing the last clear batch, or
@@ -1048,18 +1050,27 @@ static void emit_clear(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs,
  */
 struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 				   struct xe_bo *bo,
-				   struct ttm_resource *dst)
+				   struct ttm_resource *dst,
+				   u32 clear_flags)
 {
 	bool clear_vram = mem_type_is_vram(dst->mem_type);
+	bool clear_bo_data = XE_MIGRATE_CLEAR_FLAG_BO_DATA & clear_flags;
+	bool clear_ccs = XE_MIGRATE_CLEAR_FLAG_CCS_DATA & clear_flags;
 	struct xe_gt *gt = m->tile->primary_gt;
 	struct xe_device *xe = gt_to_xe(gt);
-	bool clear_system_ccs = (xe_bo_needs_ccs_pages(bo) && !IS_DGFX(xe)) ? true : false;
+	bool clear_only_system_ccs = false;
 	struct dma_fence *fence = NULL;
 	u64 size = bo->size;
 	struct xe_res_cursor src_it;
 	struct ttm_resource *src = dst;
 	int err;
 
+	if (WARN_ON(!clear_bo_data && !clear_ccs))
+		return NULL;
+
+	if (!clear_bo_data && clear_ccs && !IS_DGFX(xe))
+		clear_only_system_ccs = true;
+
 	if (!clear_vram)
 		xe_res_first_sg(xe_bo_sg(bo), 0, bo->size, &src_it);
 	else
@@ -1085,7 +1096,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		batch_size = 2 +
 			pte_update_size(m, pte_flags, src, &src_it,
 					&clear_L0, &clear_L0_ofs, &clear_L0_pt,
-					clear_system_ccs ? 0 : emit_clear_cmd_len(gt), 0,
+					clear_bo_data ? emit_clear_cmd_len(gt) : 0, 0,
 					avail_pts);
 
 		if (xe_migrate_needs_ccs_emit(xe))
@@ -1107,13 +1118,13 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
 			xe_res_next(&src_it, clear_L0);
 		else
-			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_system_ccs,
+			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_only_system_ccs,
 				 &src_it, clear_L0, dst);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
 
-		if (!clear_system_ccs)
+		if (clear_bo_data)
 			emit_clear(gt, bb, clear_L0_ofs, clear_L0, XE_PAGE_SIZE, clear_vram);
 
 		if (xe_migrate_needs_ccs_emit(xe)) {
@@ -1172,7 +1183,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		return ERR_PTR(err);
 	}
 
-	if (clear_system_ccs)
+	if (clear_ccs)
 		bo->ccs_cleared = true;
 
 	return fence;

drivers/gpu/drm/xe/xe_migrate.h

@@ -102,9 +102,14 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 				  struct ttm_resource *dst,
 				  bool copy_only_ccs);
 
+#define XE_MIGRATE_CLEAR_FLAG_BO_DATA		BIT(0)
+#define XE_MIGRATE_CLEAR_FLAG_CCS_DATA		BIT(1)
+#define XE_MIGRATE_CLEAR_FLAG_FULL	(XE_MIGRATE_CLEAR_FLAG_BO_DATA | \
+					XE_MIGRATE_CLEAR_FLAG_CCS_DATA)
 struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 				   struct xe_bo *bo,
-				   struct ttm_resource *dst);
+				   struct ttm_resource *dst,
+				   u32 clear_flags);
 
 struct xe_vm *xe_migrate_get_vm(struct xe_migrate *m);