1 files changed, 29 insertions, 13 deletions

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index e05e9e7282b6..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -472,7 +485,7 @@ static void emit_pte(struct xe_migrate *m,
 	/* Indirect access needs compression enabled uncached PAT index */
 	if (GRAPHICS_VERx100(xe) >= 2000)
 		pat_index = is_comp_pte ? xe->pat.idx[XE_CACHE_NONE_COMPRESSION] :
-					  xe->pat.idx[XE_CACHE_NONE];
+					  xe->pat.idx[XE_CACHE_WB];
 	else
 		pat_index = xe->pat.idx[XE_CACHE_WB];
 
@@ -760,14 +773,14 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
-				 src);
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
 			xe_res_next(&dst_it, src_L0);
 		else
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
-				 dst);
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs,
+				 &dst_it, src_L0, dst);
 
 		if (copy_system_ccs)
 			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
@@ -1009,8 +1022,8 @@ 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, true, &src_it, clear_L0,
-				 dst);
+			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_system_ccs,
+				 &src_it, clear_L0, dst);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;