GC optimization for primitive arrays

PoC for GH-19608

Author: iluuu1994

Zend/zend_gc.c

@@ -983,6 +983,9 @@ static void gc_scan_black(zend_refcounted *ref, gc_stack *stack)
 handle_ht:
 		n = ht->nNumUsed;
 		zv = ht->arPacked;
+		if (GC_FLAGS(ht) & GC_NOT_COLLECTABLE) {
+			goto next;
+		}
 		if (HT_IS_PACKED(ht)) {
 			goto handle_zvals;
 		}
@@ -1041,7 +1044,7 @@ static void gc_scan_black(zend_refcounted *ref, gc_stack *stack)
  * counts and mark visited nodes grey. See MarkGray() in Bacon & Rajan. */
 static void gc_mark_grey(zend_refcounted *ref, gc_stack *stack)
 {
-	HashTable *ht;
+	HashTable *ht, *zvals_ht = NULL;
 	Bucket *p;
 	zval *zv;
 	uint32_t n;
@@ -1129,9 +1132,11 @@ static void gc_mark_grey(zend_refcounted *ref, gc_stack *stack)
 					goto handle_ht;
 				}
 			}
-handle_zvals:
+handle_zvals:;
+			bool is_primitive = true;
 			for (; n != 0; n--) {
 				if (Z_COLLECTABLE_P(zv)) {
+					is_primitive = false;
 					ref = Z_COUNTED_P(zv);
 					GC_DELREF(ref);
 					if (!GC_REF_CHECK_COLOR(ref, GC_GREY)) {
@@ -1148,29 +1153,40 @@ static void gc_mark_grey(zend_refcounted *ref, gc_stack *stack)
 							}
 							zv++;
 						}
+						zvals_ht = NULL;
 						goto tail_call;
 					}
 				}
 				zv++;
 			}
+			if (is_primitive && zvals_ht) {
+				GC_ADD_FLAGS(zvals_ht, GC_NOT_COLLECTABLE);
+			}
+			zvals_ht = NULL;
 		}
 	} else if (GC_TYPE(ref) == IS_ARRAY) {
 		ZEND_ASSERT(((zend_array*)ref) != &EG(symbol_table));
 		ht = (zend_array*)ref;
 handle_ht:
 		n = ht->nNumUsed;
+		if (GC_FLAGS(ht) & GC_NOT_COLLECTABLE) {
+			goto next;
+		}
 		if (HT_IS_PACKED(ht)) {
             zv = ht->arPacked;
+            zvals_ht = ht;
             goto handle_zvals;
 		}
 
+		bool is_primitive = true;
 		p = ht->arData;
 		for (; n != 0; n--) {
 			zv = &p->val;
 			if (Z_TYPE_P(zv) == IS_INDIRECT) {
 				zv = Z_INDIRECT_P(zv);
 			}
 			if (Z_COLLECTABLE_P(zv)) {
+				is_primitive = false;
 				ref = Z_COUNTED_P(zv);
 				GC_DELREF(ref);
 				if (!GC_REF_CHECK_COLOR(ref, GC_GREY)) {
@@ -1196,6 +1212,9 @@ static void gc_mark_grey(zend_refcounted *ref, gc_stack *stack)
 			}
 			p++;
 		}
+		if (is_primitive) {
+			GC_ADD_FLAGS(ht, GC_NOT_COLLECTABLE);
+		}
 	} else if (GC_TYPE(ref) == IS_REFERENCE) {
 		if (Z_COLLECTABLE(((zend_reference*)ref)->val)) {
 			ref = Z_COUNTED(((zend_reference*)ref)->val);
@@ -1378,6 +1397,9 @@ static void gc_scan(zend_refcounted *ref, gc_stack *stack)
 
 handle_ht:
 		n = ht->nNumUsed;
+		if (GC_FLAGS(ht) & GC_NOT_COLLECTABLE) {
+			goto next;
+		}
 		if (HT_IS_PACKED(ht)) {
             zv = ht->arPacked;
             goto handle_zvals;
@@ -1623,6 +1645,9 @@ static int gc_collect_white(zend_refcounted *ref, uint32_t *flags, gc_stack *sta
 
 handle_ht:
 		n = ht->nNumUsed;
+		if (GC_FLAGS(ht) & GC_NOT_COLLECTABLE) {
+			goto next;
+		}
 		if (HT_IS_PACKED(ht)) {
 			zv = ht->arPacked;
 			goto handle_zvals;
@@ -1811,6 +1836,9 @@ static int gc_remove_nested_data_from_buffer(zend_refcounted *ref, gc_root_buffe
 
 handle_ht:
 		n = ht->nNumUsed;
+		if (GC_FLAGS(ht) & GC_NOT_COLLECTABLE) {
+			goto next;
+		}
 		if (HT_IS_PACKED(ht)) {
 			zv = ht->arPacked;
 			goto handle_zvals;

Zend/zend_hash.c

@@ -885,6 +885,7 @@ static zend_always_inline zval *_zend_hash_add_or_update_i(HashTable *ht, zend_s
 	nIndex = h | ht->nTableMask;
 	Z_NEXT(p->val) = HT_HASH_EX(arData, nIndex);
 	HT_HASH_EX(arData, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 	if (flag & HASH_LOOKUP) {
 		ZVAL_NULL(&p->val);
 	} else {
@@ -970,6 +971,7 @@ static zend_always_inline zval *_zend_hash_str_add_or_update_i(HashTable *ht, co
 	nIndex = h | ht->nTableMask;
 	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
 	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 
 	return &p->val;
 }
@@ -1172,6 +1174,7 @@ static zend_always_inline zval *_zend_hash_index_add_or_update_i(HashTable *ht,
 	p = ht->arData + idx;
 	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
 	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 	if ((zend_long)h >= ht->nNextFreeElement) {
 		ht->nNextFreeElement = (zend_long)h < ZEND_LONG_MAX ? h + 1 : ZEND_LONG_MAX;
 	}

Zend/zend_hash.h

@@ -1638,6 +1638,7 @@ static zend_always_inline zval *_zend_hash_append_ex(HashTable *ht, zend_string
 	nIndex = (uint32_t)p->h | ht->nTableMask;
 	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
 	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 	ht->nNumOfElements++;
 	return &p->val;
 }
@@ -1664,6 +1665,7 @@ static zend_always_inline zval *_zend_hash_append_ptr_ex(HashTable *ht, zend_str
 	nIndex = (uint32_t)p->h | ht->nTableMask;
 	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
 	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 	ht->nNumOfElements++;
 	return &p->val;
 }
@@ -1690,6 +1692,7 @@ static zend_always_inline void _zend_hash_append_ind(HashTable *ht, zend_string
 	nIndex = (uint32_t)p->h | ht->nTableMask;
 	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
 	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
+	GC_DEL_FLAGS(ht, GC_NOT_COLLECTABLE);
 	ht->nNumOfElements++;
 }