1 files changed, 133 insertions, 86 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f180427e48f4..20c39d1bcef8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -34,11 +34,21 @@ static DEFINE_MUTEX(mem_sysfs_mutex);
 
 static int sections_per_block;
 
-static inline int base_memory_block_id(int section_nr)
+static inline unsigned long base_memory_block_id(unsigned long section_nr)
 {
 	return section_nr / sections_per_block;
 }
 
+static inline unsigned long pfn_to_block_id(unsigned long pfn)
+{
+	return base_memory_block_id(pfn_to_section_nr(pfn));
+}
+
+static inline unsigned long phys_to_block_id(unsigned long phys)
+{
+	return pfn_to_block_id(PFN_DOWN(phys));
+}
+
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
 
@@ -126,9 +136,9 @@ static ssize_t phys_index_show(struct device *dev,
 static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
-	unsigned long i, pfn;
-	int ret = 1;
 	struct memory_block *mem = to_memory_block(dev);
+	unsigned long pfn;
+	int ret = 1, i;
 
 	if (mem->state != MEM_ONLINE)
 		goto out;
@@ -578,23 +588,13 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
 	return 0;
 }
 
-/*
- * 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)
+/* A reference for the returned memory block device is acquired. */
+static struct memory_block *find_memory_block_by_id(unsigned long block_id)
 {
-	int block_id = base_memory_block_id(__section_nr(section));
-	struct device *hintdev = hint ? &hint->dev : NULL;
 	struct device *dev;
 
-	dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
-	if (hint)
-		put_device(&hint->dev);
-	if (!dev)
-		return NULL;
-	return to_memory_block(dev);
+	dev = subsys_find_device_by_id(&memory_subsys, block_id, NULL);
+	return dev ? to_memory_block(dev) : NULL;
 }
 
 /*
@@ -607,7 +607,9 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
  */
 struct memory_block *find_memory_block(struct mem_section *section)
 {
-	return find_memory_block_hinted(section, NULL);
+	unsigned long block_id = base_memory_block_id(__section_nr(section));
+
+	return find_memory_block_by_id(block_id);
 }
 
 static struct attribute *memory_memblk_attrs[] = {
@@ -652,20 +654,22 @@ int register_memory(struct memory_block *memory)
 }
 
 static int init_memory_block(struct memory_block **memory,
-			     struct mem_section *section, unsigned long state)
+			     unsigned long block_id, unsigned long state)
 {
 	struct memory_block *mem;
 	unsigned long start_pfn;
-	int scn_nr;
 	int ret = 0;
 
+	mem = find_memory_block_by_id(block_id);
+	if (mem) {
+		put_device(&mem->dev);
+		return -EEXIST;
+	}
 	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
 
-	scn_nr = __section_nr(section);
-	mem->start_section_nr =
-			base_memory_block_id(scn_nr) * sections_per_block;
+	mem->start_section_nr = block_id * sections_per_block;
 	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
 	mem->state = state;
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -677,97 +681,101 @@ static int init_memory_block(struct memory_block **memory,
 	return ret;
 }
 
-static int add_memory_block(int base_section_nr)
+static int add_memory_block(unsigned long base_section_nr)
 {
+	int ret, section_count = 0;
 	struct memory_block *mem;
-	int i, ret, section_count = 0, section_nr;
+	unsigned long nr;
 
-	for (i = base_section_nr;
-	     i < base_section_nr + sections_per_block;
-	     i++) {
-		if (!present_section_nr(i))
-			continue;
-		if (section_count == 0)
-			section_nr = i;
-		section_count++;
-	}
+	for (nr = base_section_nr; nr < base_section_nr + sections_per_block;
+	     nr++)
+		if (present_section_nr(nr))
+			section_count++;
 
 	if (section_count == 0)
 		return 0;
-	ret = init_memory_block(&mem, __nr_to_section(section_nr), MEM_ONLINE);
+	ret = init_memory_block(&mem, base_memory_block_id(base_section_nr),
+				MEM_ONLINE);
 	if (ret)
 		return ret;
 	mem->section_count = section_count;
 	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 ret = 0;
+	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
+	unsigned long 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 {
-		ret = init_memory_block(&mem, section, MEM_OFFLINE);
+	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);
+			mem->section_count = 0;
+			unregister_memory(mem);
+		}
 	}
-
-out:
 	mutex_unlock(&mem_sysfs_mutex);
 	return ret;
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
-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)
+/*
+ * Remove memory block devices for the given memory area. Start and size
+ * have to be aligned to memory block granularity. Memory block devices
+ * have to be offline.
+ */
+void remove_memory_block_devices(unsigned long start, unsigned long size)
 {
+	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
+	const unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
 	struct memory_block *mem;
+	unsigned long block_id;
 
-	if (WARN_ON_ONCE(!present_section(section)))
+	if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
+			 !IS_ALIGNED(size, memory_block_size_bytes())))
 		return;
 
 	mutex_lock(&mem_sysfs_mutex);
-
-	/*
-	 * Some users of the memory hotplug do not want/need memblock to
-	 * track all sections. Skip over those.
-	 */
-	mem = find_memory_block(section);
-	if (!mem)
-		goto out_unlock;
-
-	unregister_mem_sect_under_nodes(mem, __section_nr(section));
-
-	mem->section_count--;
-	if (mem->section_count == 0)
+	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
+		mem = find_memory_block_by_id(block_id);
+		if (WARN_ON_ONCE(!mem))
+			continue;
+		mem->section_count = 0;
+		unregister_memory_block_under_nodes(mem);
 		unregister_memory(mem);
-	else
-		put_device(&mem->dev);
-
-out_unlock:
+	}
 	mutex_unlock(&mem_sysfs_mutex);
 }
-#endif /* CONFIG_MEMORY_HOTREMOVE */
 
 /* return true if the memory block is offlined, otherwise, return false */
 bool is_memblock_offlined(struct memory_block *mem)
@@ -804,10 +812,9 @@ static const struct attribute_group *memory_root_attr_groups[] = {
  */
 int __init memory_dev_init(void)
 {
-	unsigned int i;
 	int ret;
 	int err;
-	unsigned long block_sz;
+	unsigned long block_sz, nr;
 
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
@@ -821,9 +828,9 @@ int __init memory_dev_init(void)
 	 * during boot and have been initialized
 	 */
 	mutex_lock(&mem_sysfs_mutex);
-	for (i = 0; i <= __highest_present_section_nr;
-		i += sections_per_block) {
-		err = add_memory_block(i);
+	for (nr = 0; nr <= __highest_present_section_nr;
+	     nr += sections_per_block) {
+		err = add_memory_block(nr);
 		if (!ret)
 			ret = err;
 	}
@@ -834,3 +841,43 @@ out:
 		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
 	return ret;
 }
+
+/**
+ * walk_memory_blocks - walk through all present memory blocks overlapped
+ *			by the range [start, start + size)
+ *
+ * @start: start address of the memory range
+ * @size: size of the memory range
+ * @arg: argument passed to func
+ * @func: callback for each memory section walked
+ *
+ * This function walks through all present memory blocks overlapped by the
+ * range [start, start + size), calling func on each memory block.
+ *
+ * In case func() returns an error, walking is aborted and the error is
+ * returned.
+ */
+int walk_memory_blocks(unsigned long start, unsigned long size,
+		       void *arg, walk_memory_blocks_func_t func)
+{
+	const unsigned long start_block_id = phys_to_block_id(start);
+	const unsigned long end_block_id = phys_to_block_id(start + size - 1);
+	struct memory_block *mem;
+	unsigned long block_id;
+	int ret = 0;
+
+	if (!size)
+		return 0;
+
+	for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
+		mem = find_memory_block_by_id(block_id);
+		if (!mem)
+			continue;
+
+		ret = func(mem, arg);
+		put_device(&mem->dev);
+		if (ret)
+			break;
+	}
+	return ret;
+}