1 files changed, 69 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 21c8b7350b7a..6e0e52eeb87a 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -303,10 +303,7 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm,
 			__i915_gem_object_pin_pages(pt->base);
 			i915_gem_object_make_unshrinkable(pt->base);
 
-			if (lvl ||
-			    gen8_pt_count(*start, end) < I915_PDES ||
-			    intel_vgpu_active(vm->i915))
-				fill_px(pt, vm->scratch[lvl]->encode);
+			fill_px(pt, vm->scratch[lvl]->encode);
 
 			spin_lock(&pd->lock);
 			if (likely(!pd->entry[idx])) {
@@ -361,6 +358,54 @@ static void gen8_ppgtt_alloc(struct i915_address_space *vm,
 			   &start, start + length, vm->top);
 }
 
+static void __gen8_ppgtt_foreach(struct i915_address_space *vm,
+				 struct i915_page_directory *pd,
+				 u64 *start, u64 end, int lvl,
+				 void (*fn)(struct i915_address_space *vm,
+					    struct i915_page_table *pt,
+					    void *data),
+				 void *data)
+{
+	unsigned int idx, len;
+
+	len = gen8_pd_range(*start, end, lvl--, &idx);
+
+	spin_lock(&pd->lock);
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		atomic_inc(&pt->used);
+		spin_unlock(&pd->lock);
+
+		if (lvl) {
+			__gen8_ppgtt_foreach(vm, as_pd(pt), start, end, lvl,
+					     fn, data);
+		} else {
+			fn(vm, pt, data);
+			*start += gen8_pt_count(*start, end);
+		}
+
+		spin_lock(&pd->lock);
+		atomic_dec(&pt->used);
+	} while (idx++, --len);
+	spin_unlock(&pd->lock);
+}
+
+static void gen8_ppgtt_foreach(struct i915_address_space *vm,
+			       u64 start, u64 length,
+			       void (*fn)(struct i915_address_space *vm,
+					  struct i915_page_table *pt,
+					  void *data),
+			       void *data)
+{
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+
+	__gen8_ppgtt_foreach(vm, i915_vm_to_ppgtt(vm)->pd,
+			     &start, start + length, vm->top,
+			     fn, data);
+}
+
 static __always_inline u64
 gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      struct i915_page_directory *pdp,
@@ -555,6 +600,24 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 	}
 }
 
+static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
+				    dma_addr_t addr,
+				    u64 offset,
+				    enum i915_cache_level level,
+				    u32 flags)
+{
+	u64 idx = offset >> GEN8_PTE_SHIFT;
+	struct i915_page_directory * const pdp =
+		gen8_pdp_for_page_index(vm, idx);
+	struct i915_page_directory *pd =
+		i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	gen8_pte_t *vaddr;
+
+	vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
+	clflush_cache_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
+}
+
 static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	u32 pte_flags;
@@ -734,8 +797,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
 
 	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
+	ppgtt->vm.insert_page = gen8_ppgtt_insert_entry;
 	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
 	ppgtt->vm.clear_range = gen8_ppgtt_clear;
+	ppgtt->vm.foreach = gen8_ppgtt_foreach;
 
 	ppgtt->vm.pte_encode = gen8_pte_encode;