[for,4.19-stable,v3,16/24] mm/memory_hotplug: create memory block devices after arch_add_memory()

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f9818d75ac43..b89b9c3efa59 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -39,6 +39,11 @@  static inline int base_memory_block_id(int section_nr)
 	return section_nr / sections_per_block;
 }
 
+static inline int pfn_to_block_id(unsigned long pfn)
+{
+	return base_memory_block_id(pfn_to_section_nr(pfn));
+}
+
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
 
@@ -591,10 +596,9 @@  int __weak arch_get_memory_phys_device(unsigned long start_pfn)
  * A reference for the returned object is held and the reference for the
  * hinted object is released.
  */
-struct memory_block *find_memory_block_hinted(struct mem_section *section,
-					      struct memory_block *hint)
+static struct memory_block *find_memory_block_by_id(int block_id,
+						    struct memory_block *hint)
 {
-	int block_id = base_memory_block_id(__section_nr(section));
 	struct device *hintdev = hint ? &hint->dev : NULL;
 	struct device *dev;
 
@@ -606,6 +610,14 @@  struct memory_block *find_memory_block_hinted(struct mem_section *section,
 	return to_memory_block(dev);
 }
 
+struct memory_block *find_memory_block_hinted(struct mem_section *section,
+					      struct memory_block *hint)
+{
+	int block_id = base_memory_block_id(__section_nr(section));
+
+	return find_memory_block_by_id(block_id, hint);
+}
+
 /*
  * For now, we have a linear search to go find the appropriate
  * memory_block corresponding to a particular phys_index. If
@@ -667,6 +679,11 @@  static int init_memory_block(struct memory_block **memory, int block_id,
 	unsigned long start_pfn;
 	int ret = 0;
 
+	mem = find_memory_block_by_id(block_id, NULL);
+	if (mem) {
+		put_device(&mem->dev);
+		return -EEXIST;
+	}
 	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
@@ -704,44 +721,53 @@  static int add_memory_block(int base_section_nr)
 	return 0;
 }
 
+static void unregister_memory(struct memory_block *memory)
+{
+	if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
+		return;
+
+	/* drop the ref. we got via find_memory_block() */
+	put_device(&memory->dev);
+	device_unregister(&memory->dev);
+}
+
 /*
- * need an interface for the VM to add new memory regions,
- * but without onlining it.
+ * Create memory block devices for the given memory area. Start and size
+ * have to be aligned to memory block granularity. Memory block devices
+ * will be initialized as offline.
  */
-int hotplug_memory_register(int nid, struct mem_section *section)
+int create_memory_block_devices(unsigned long start, unsigned long size)
 {
-	int block_id = base_memory_block_id(__section_nr(section));
-	int ret = 0;
+	const int start_block_id = pfn_to_block_id(PFN_DOWN(start));
+	int end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
 	struct memory_block *mem;
+	unsigned long block_id;
+	int ret = 0;
 
-	mutex_lock(&mem_sysfs_mutex);
+	if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
+			 !IS_ALIGNED(size, memory_block_size_bytes())))
+		return -EINVAL;
 
-	mem = find_memory_block(section);
-	if (mem) {
-		mem->section_count++;
-		put_device(&mem->dev);
-	} else {
+	mutex_lock(&mem_sysfs_mutex);
+	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
 		ret = init_memory_block(&mem, block_id, MEM_OFFLINE);
 		if (ret)
-			goto out;
-		mem->section_count++;
+			break;
+		mem->section_count = sections_per_block;
+	}
+	if (ret) {
+		end_block_id = block_id;
+		for (block_id = start_block_id; block_id != end_block_id;
+		     block_id++) {
+			mem = find_memory_block_by_id(block_id, NULL);
+			mem->section_count = 0;
+			unregister_memory(mem);
+		}
 	}
-
-out:
 	mutex_unlock(&mem_sysfs_mutex);
 	return ret;
 }
 
-static void
-unregister_memory(struct memory_block *memory)
-{
-	BUG_ON(memory->dev.bus != &memory_subsys);
-
-	/* drop the ref. we got via find_memory_block() */
-	put_device(&memory->dev);
-	device_unregister(&memory->dev);
-}
-
 void unregister_memory_section(struct mem_section *section)
 {
 	struct memory_block *mem;
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 474c7c60c8f2..db3e8567f900 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -111,7 +111,7 @@  extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
-int hotplug_memory_register(int nid, struct mem_section *section);
+int create_memory_block_devices(unsigned long start, unsigned long size);
 extern void unregister_memory_section(struct mem_section *);
 extern int memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6b5ce0bd907f..414771114685 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -256,13 +256,7 @@  static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
 		return -EEXIST;
 
 	ret = sparse_add_one_section(nid, phys_start_pfn, altmap);
-	if (ret < 0)
-		return ret;
-
-	if (!want_memblock)
-		return 0;
-
-	return hotplug_memory_register(nid, __pfn_to_section(phys_start_pfn));
+	return ret < 0 ? ret : 0;
 }
 
 /*
@@ -1096,6 +1090,13 @@  int __ref add_memory_resource(int nid, struct resource *res, bool online)
 	if (ret < 0)
 		goto error;
 
+	/* create memory block devices after memory was added */
+	ret = create_memory_block_devices(start, size);
+	if (ret) {
+		arch_remove_memory(nid, start, size, NULL);
+		goto error;
+	}
+
 	if (new_node) {
 		/* If sysfs file of new node can't be created, cpu on the node
 		 * can't be hot-added. There is no rollback way now.