v4 De-couple sysfs memory directories from memory sections

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -435,6 +435,37 @@ int __weak arch_get_memory_phys_device(u
 	return 0;
 }
 
+/*
+ * For now, we have a linear search to go find the appropriate
+ * memory_block corresponding to a particular phys_index. If
+ * this gets to be a real problem, we can always use a radix
+ * tree or something here.
+ *
+ * This could be made generic for all sysdev classes.
+ */
+struct memory_block *find_memory_block(struct mem_section *section)
+{
+	struct kobject *kobj;
+	struct sys_device *sysdev;
+	struct memory_block *mem;
+	char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+
+	/*
+	 * This only works because we know that section == sysdev->id
+	 * slightly redundant with sysdev_register()
+	 */
+	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+
+	kobj = kset_find_obj(&memory_sysdev_class.kset, name);
+	if (!kobj)
+		return NULL;
+
+	sysdev = container_of(kobj, struct sys_device, kobj);
+	mem = container_of(sysdev, struct memory_block, sysdev);
+
+	return mem;
+}
+
 static int add_memory_block(int nid, struct mem_section *section,
 			unsigned long state, enum mem_add_context context)
 {

@@ -468,37 +499,6 @@ static int add_memory_block(int nid, str
 	return ret;
 }
 
-/*
- * For now, we have a linear search to go find the appropriate
- * memory_block corresponding to a particular phys_index. If
- * this gets to be a real problem, we can always use a radix
- * tree or something here.
- *
- * This could be made generic for all sysdev classes.
- */
-struct memory_block *find_memory_block(struct mem_section *section)
-{
-	struct kobject *kobj;
-	struct sys_device *sysdev;
-	struct memory_block *mem;
-	char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
-
-	/*
-	 * This only works because we know that section == sysdev->id
-	 * slightly redundant with sysdev_register()
-	 */
-	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
-
-	kobj = kset_find_obj(&memory_sysdev_class.kset, name);
-	if (!kobj)
-		return NULL;
-
-	sysdev = container_of(kobj, struct sys_device, kobj);
-	mem = container_of(sysdev, struct memory_block, sysdev);
-
-	return mem;
-}
-
 int remove_memory_block(unsigned long node_id, struct mem_section *section,
 		int phys_device)
 {

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -109,12 +109,20 @@ unregister_memory(struct memory_block *m
  * uses.
  */
 
-static ssize_t show_mem_phys_index(struct sys_device *dev,
+static ssize_t show_mem_start_phys_index(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
-	return sprintf(buf, "%08lx\n", mem->phys_index);
+	return sprintf(buf, "%08lx\n", mem->start_phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, sysdev);
+	return sprintf(buf, "%08lx\n", mem->end_phys_index);
 }
 
 /*

@@ -128,7 +136,7 @@ static ssize_t show_mem_removable(struct
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
 
-	start_pfn = section_nr_to_pfn(mem->phys_index);
+	start_pfn = section_nr_to_pfn(mem->start_phys_index);
 	ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
 	return sprintf(buf, "%d\n", ret);
 }

@@ -191,7 +199,7 @@ memory_block_action(struct memory_block
 	int ret;
 	int old_state = mem->state;
 
-	psection = mem->phys_index;
+	psection = mem->start_phys_index;
 	first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
 
 	/*

@@ -264,7 +272,7 @@ store_mem_state(struct sys_device *dev,
 	int ret = -EINVAL;
 
 	mem = container_of(dev, struct memory_block, sysdev);
-	phys_section_nr = mem->phys_index;
+	phys_section_nr = mem->start_phys_index;
 
 	if (!present_section_nr(phys_section_nr))
 		goto out;

@@ -296,7 +304,8 @@ static ssize_t show_phys_device(struct s
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
-static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
 static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
 static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
 static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);

@@ -476,16 +485,18 @@ static int add_memory_block(int nid, str
 	if (!mem)
 		return -ENOMEM;
 
-	mem->phys_index = __section_nr(section);
+	mem->start_phys_index = __section_nr(section);
 	mem->state = state;
 	mutex_init(&mem->state_mutex);
-	start_pfn = section_nr_to_pfn(mem->phys_index);
+	start_pfn = section_nr_to_pfn(mem->start_phys_index);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
 	ret = register_memory(mem, section);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_index);
 	if (!ret)
+		ret = mem_create_simple_file(mem, end_phys_index);
+	if (!ret)
 		ret = mem_create_simple_file(mem, state);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_device);

@@ -507,6 +518,7 @@ int remove_memory_block(unsigned long no
 	mem = find_memory_block(section);
 	unregister_mem_sect_under_nodes(mem);
 	mem_remove_simple_file(mem, phys_index);
+	mem_remove_simple_file(mem, end_phys_index);
 	mem_remove_simple_file(mem, state);
 	mem_remove_simple_file(mem, phys_device);
 	mem_remove_simple_file(mem, removable);

Index: linux-2.6/include/linux/memory.h
===================================================================
@@ -21,7 +21,8 @@
 #include <linux/mutex.h>
 
 struct memory_block {
-	unsigned long phys_index;
+	unsigned long start_phys_index;
+	unsigned long end_phys_index;
 	unsigned long state;
 	/*
 	 * This serializes all state change requests.  It isn't

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -487,6 +487,7 @@ static int add_memory_block(int nid, str
 
 	mem->start_phys_index = __section_nr(section);
 	mem->state = state;
+	atomic_inc(&mem->section_count);
 	mutex_init(&mem->state_mutex);
 	start_pfn = section_nr_to_pfn(mem->start_phys_index);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);

@@ -516,13 +517,16 @@ int remove_memory_block(unsigned long no
 	struct memory_block *mem;
 
 	mem = find_memory_block(section);
-	unregister_mem_sect_under_nodes(mem);
-	mem_remove_simple_file(mem, phys_index);
-	mem_remove_simple_file(mem, end_phys_index);
-	mem_remove_simple_file(mem, state);
-	mem_remove_simple_file(mem, phys_device);
-	mem_remove_simple_file(mem, removable);
-	unregister_memory(mem, section);
+
+	if (atomic_dec_and_test(&mem->section_count)) {
+		unregister_mem_sect_under_nodes(mem);
+		mem_remove_simple_file(mem, phys_index);
+		mem_remove_simple_file(mem, end_phys_index);
+		mem_remove_simple_file(mem, state);
+		mem_remove_simple_file(mem, phys_device);
+		mem_remove_simple_file(mem, removable);
+		unregister_memory(mem, section);
+	}
 
 	return 0;
 }

Index: linux-2.6/include/linux/memory.h
===================================================================
@@ -19,11 +19,13 @@
 #include <linux/node.h>
 #include <linux/compiler.h>
 #include <linux/mutex.h>
+#include <asm/atomic.h>
 
 struct memory_block {
 	unsigned long start_phys_index;
 	unsigned long end_phys_index;
 	unsigned long state;
+	atomic_t section_count;
 	/*
 	 * This serializes all state change requests.  It isn't
 	 * held during creation because the control files are

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -27,6 +27,8 @@
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
 
+static struct mutex mem_sysfs_mutex;
+
 #define MEMORY_CLASS_NAME	"memory"
 
 static struct sysdev_class memory_sysdev_class = {

@@ -485,6 +487,8 @@ static int add_memory_block(int nid, str
 	if (!mem)
 		return -ENOMEM;
 
+	mutex_lock(&mem_sysfs_mutex);
+
 	mem->start_phys_index = __section_nr(section);
 	mem->state = state;
 	atomic_inc(&mem->section_count);

@@ -508,6 +512,7 @@ static int add_memory_block(int nid, str
 			ret = register_mem_sect_under_node(mem, nid);
 	}
 
+	mutex_unlock(&mem_sysfs_mutex);
 	return ret;
 }
 

@@ -516,6 +521,7 @@ int remove_memory_block(unsigned long no
 {
 	struct memory_block *mem;
 
+	mutex_lock(&mem_sysfs_mutex);
 	mem = find_memory_block(section);
 
 	if (atomic_dec_and_test(&mem->section_count)) {

@@ -528,6 +534,7 @@ int remove_memory_block(unsigned long no
 		unregister_memory(mem, section);
 	}
 
+	mutex_unlock(&mem_sysfs_mutex);
 	return 0;
 }
 

@@ -562,6 +569,8 @@ int __init memory_dev_init(void)
 	if (ret)
 		goto out;
 
+	mutex_init(&mem_sysfs_mutex);
+
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -30,6 +30,14 @@
 static struct mutex mem_sysfs_mutex;
 
 #define MEMORY_CLASS_NAME	"memory"
+#define MIN_MEMORY_BLOCK_SIZE	(1 << SECTION_SIZE_BITS)
+
+static int sections_per_block;
+
+static inline int base_memory_block_id(int section_nr)
+{
+	return (section_nr / sections_per_block) * sections_per_block;
+}
 
 static struct sysdev_class memory_sysdev_class = {
 	.name = MEMORY_CLASS_NAME,

@@ -84,22 +92,21 @@ EXPORT_SYMBOL(unregister_memory_isolate_
  * register_memory - Setup a sysfs device for a memory block
  */
 static
-int register_memory(struct memory_block *memory, struct mem_section *section)
+int register_memory(struct memory_block *memory)
 {
 	int error;
 
 	memory->sysdev.cls = &memory_sysdev_class;
-	memory->sysdev.id = __section_nr(section);
+	memory->sysdev.id = memory->start_phys_index;
 
 	error = sysdev_register(&memory->sysdev);
 	return error;
 }
 
 static void
-unregister_memory(struct memory_block *memory, struct mem_section *section)
+unregister_memory(struct memory_block *memory)
 {
 	BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
-	BUG_ON(memory->sysdev.id != __section_nr(section));
 
 	/* drop the ref. we got in remove_memory_block() */
 	kobject_put(&memory->sysdev.kobj);

@@ -133,13 +140,16 @@ static ssize_t show_mem_end_phys_index(s
 static ssize_t show_mem_removable(struct sys_device *dev,
 			struct sysdev_attribute *attr, char *buf)
 {
-	unsigned long start_pfn;
-	int ret;
+	unsigned long i, pfn;
+	int ret = 1;
 	struct memory_block *mem =
 		container_of(dev, struct memory_block, sysdev);
 
-	start_pfn = section_nr_to_pfn(mem->start_phys_index);
-	ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
+	for (i = mem->start_phys_index; i <= mem->end_phys_index; i++) {
+		pfn = section_nr_to_pfn(i);
+		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+	}
+
 	return sprintf(buf, "%d\n", ret);
 }
 

@@ -192,17 +202,14 @@ int memory_isolate_notify(unsigned long
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(struct memory_block *mem, unsigned long action)
+memory_section_action(unsigned long phys_index, unsigned long action)
 {
 	int i;
-	unsigned long psection;
 	unsigned long start_pfn, start_paddr;
 	struct page *first_page;
 	int ret;
-	int old_state = mem->state;
 
-	psection = mem->start_phys_index;
-	first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
+	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
 
 	/*
 	 * The probe routines leave the pages reserved, just

@@ -215,8 +222,8 @@ memory_block_action(struct memory_block
 				continue;
 
 			printk(KERN_WARNING "section number %ld page number %d "
-				"not reserved, was it already online? \n",
-				psection, i);
+				"not reserved, was it already online?\n",
+				phys_index, i);
 			return -EBUSY;
 		}
 	}

@@ -227,18 +234,13 @@ memory_block_action(struct memory_block
 			ret = online_pages(start_pfn, PAGES_PER_SECTION);
 			break;
 		case MEM_OFFLINE:
-			mem->state = MEM_GOING_OFFLINE;
 			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
 			ret = remove_memory(start_paddr,
 					    PAGES_PER_SECTION << PAGE_SHIFT);
-			if (ret) {
-				mem->state = old_state;
-				break;
-			}
 			break;
 		default:
-			WARN(1, KERN_WARNING "%s(%p, %ld) unknown action: %ld\n",
-					__func__, mem, action, action);
+			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
+			     "%ld\n", __func__, phys_index, action, action);
 			ret = -EINVAL;
 	}
 

@@ -248,7 +250,7 @@ memory_block_action(struct memory_block
 static int memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
-	int ret = 0;
+	int i, ret = 0;
 	mutex_lock(&mem->state_mutex);
 
 	if (mem->state != from_state_req) {

@@ -256,8 +258,21 @@ static int memory_block_change_state(str
 		goto out;
 	}
 
-	ret = memory_block_action(mem, to_state);
-	if (!ret)
+	if (to_state == MEM_OFFLINE)
+		mem->state = MEM_GOING_OFFLINE;
+
+	for (i = mem->start_phys_index; i <= mem->end_phys_index; i++) {
+		ret = memory_section_action(i, to_state);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		for (i = mem->start_phys_index; i <= mem->end_phys_index; i++)
+			memory_section_action(i, from_state_req);
+
+		mem->state = from_state_req;
+	} else
 		mem->state = to_state;
 
 out:

@@ -270,20 +285,15 @@ store_mem_state(struct sys_device *dev,
 		struct sysdev_attribute *attr, const char *buf, size_t count)
 {
 	struct memory_block *mem;
-	unsigned int phys_section_nr;
 	int ret = -EINVAL;
 
 	mem = container_of(dev, struct memory_block, sysdev);
-	phys_section_nr = mem->start_phys_index;
-
-	if (!present_section_nr(phys_section_nr))
-		goto out;
 
 	if (!strncmp(buf, "online", min((int)count, 6)))
 		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 	else if(!strncmp(buf, "offline", min((int)count, 7)))
 		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
-out:
+
 	if (ret)
 		return ret;
 	return count;

@@ -460,12 +470,13 @@ struct memory_block *find_memory_block(s
 	struct sys_device *sysdev;
 	struct memory_block *mem;
 	char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+	int block_id = base_memory_block_id(__section_nr(section));
 
 	/*
 	 * This only works because we know that section == sysdev->id
 	 * slightly redundant with sysdev_register()
 	 */
-	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+	sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id);
 
 	kobj = kset_find_obj(&memory_sysdev_class.kset, name);
 	if (!kobj)

@@ -477,26 +488,26 @@ struct memory_block *find_memory_block(s
 	return mem;
 }
 
-static int add_memory_block(int nid, struct mem_section *section,
-			unsigned long state, enum mem_add_context context)
+static int init_memory_block(struct memory_block **memory,
+			     struct mem_section *section, unsigned long state)
 {
-	struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	struct memory_block *mem;
 	unsigned long start_pfn;
 	int ret = 0;
 
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
 
-	mutex_lock(&mem_sysfs_mutex);
-
-	mem->start_phys_index = __section_nr(section);
+	mem->start_phys_index = base_memory_block_id(__section_nr(section));
+	mem->end_phys_index = mem->start_phys_index + sections_per_block - 1;
 	mem->state = state;
 	atomic_inc(&mem->section_count);
 	mutex_init(&mem->state_mutex);
 	start_pfn = section_nr_to_pfn(mem->start_phys_index);
 	mem->phys_device = arch_get_memory_phys_device(start_pfn);
 
-	ret = register_memory(mem, section);
+	ret = register_memory(mem);
 	if (!ret)
 		ret = mem_create_simple_file(mem, phys_index);
 	if (!ret)

@@ -507,8 +518,29 @@ static int add_memory_block(int nid, str
 		ret = mem_create_simple_file(mem, phys_device);
 	if (!ret)
 		ret = mem_create_simple_file(mem, removable);
+
+	*memory = mem;
+	return ret;
+}
+
+static int add_memory_section(int nid, struct mem_section *section,
+			unsigned long state, enum mem_add_context context)
+{
+	struct memory_block *mem;
+	int ret = 0;
+
+	mutex_lock(&mem_sysfs_mutex);
+
+	mem = find_memory_block(section);
+	if (mem) {
+		atomic_inc(&mem->section_count);
+		kobject_put(&mem->sysdev.kobj);
+	} else
+		ret = init_memory_block(&mem, section, state);
+
 	if (!ret) {
-		if (context == HOTPLUG)
+		if (context == HOTPLUG &&
+		    atomic_read(&mem->section_count) == sections_per_block)
 			ret = register_mem_sect_under_node(mem, nid);
 	}
 

@@ -531,8 +563,10 @@ int remove_memory_block(unsigned long no
 		mem_remove_simple_file(mem, state);
 		mem_remove_simple_file(mem, phys_device);
 		mem_remove_simple_file(mem, removable);
-		unregister_memory(mem, section);
-	}
+		unregister_memory(mem);
+		kfree(mem);
+	} else
+		kobject_put(&mem->sysdev.kobj);
 
 	mutex_unlock(&mem_sysfs_mutex);
 	return 0;

@@ -544,7 +578,7 @@ int remove_memory_block(unsigned long no
  */
 int register_new_memory(int nid, struct mem_section *section)
 {
-	return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG);
+	return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG);
 }
 
 int unregister_memory_section(struct mem_section *section)

@@ -555,6 +589,26 @@ int unregister_memory_section(struct mem
 	return remove_memory_block(0, section, 0);
 }
 
+u32 __weak memory_block_size_bytes(void)
+{
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+
+static u32 get_memory_block_size(void)
+{
+	u32 block_sz;
+
+	block_sz = memory_block_size_bytes();
+
+	/* Validate blk_sz is a power of 2 and not less than section size */
+	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
+		WARN_ON(1);
+		block_sz = MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return block_sz;
+}
+
 /*
  * Initialize the sysfs support for memory devices...
  */

@@ -563,6 +617,7 @@ int __init memory_dev_init(void)
 	unsigned int i;
 	int ret;
 	int err;
+	int block_sz;
 
 	memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops;
 	ret = sysdev_class_register(&memory_sysdev_class);

@@ -571,6 +626,9 @@ int __init memory_dev_init(void)
 
 	mutex_init(&mem_sysfs_mutex);
 
+	block_sz = get_memory_block_size();
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized

@@ -578,8 +636,8 @@ int __init memory_dev_init(void)
 	for (i = 0; i < NR_MEM_SECTIONS; i++) {
 		if (!present_section_nr(i))
 			continue;
-		err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE,
-				       BOOT);
+		err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE,
+					 BOOT);
 		if (!ret)
 			ret = err;
 	}

Index: linux-2.6/include/linux/memory.h
===================================================================
@@ -116,7 +116,7 @@ extern int memory_dev_init(void);
 extern int remove_memory_block(unsigned long, struct mem_section *, int);
 extern int memory_notify(unsigned long val, void *v);
 extern int memory_isolate_notify(unsigned long val, void *v);
-extern struct memory_block *find_memory_block(unsigned long);
+extern struct memory_block *find_memory_block(struct mem_section *);
 extern int memory_is_hidden(struct mem_section *);
 #define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
 enum mem_add_context { BOOT, HOTPLUG };

Index: linux-2.6/drivers/base/node.c
===================================================================
@@ -346,8 +346,10 @@ int register_mem_sect_under_node(struct
 		return -EFAULT;
 	if (!node_online(nid))
 		return 0;
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
-	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_phys_index);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_phys_index);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 

@@ -371,7 +373,8 @@ int register_mem_sect_under_node(struct
 }
 
 /* unregister memory section under all nodes that it spans */
-int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+				    unsigned long phys_index)
 {
 	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;

@@ -383,7 +386,8 @@ int unregister_mem_sect_under_nodes(stru
 	if (!unlinked_nodes)
 		return -ENOMEM;
 	nodes_clear(*unlinked_nodes);
-	sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index);
+
+	sect_start_pfn = section_nr_to_pfn(phys_index);
 	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int nid;

Index: linux-2.6/drivers/base/memory.c
===================================================================
@@ -555,9 +555,9 @@ int remove_memory_block(unsigned long no
 
 	mutex_lock(&mem_sysfs_mutex);
 	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem, __section_nr(section));
 
 	if (atomic_dec_and_test(&mem->section_count)) {
-		unregister_mem_sect_under_nodes(mem);
 		mem_remove_simple_file(mem, phys_index);
 		mem_remove_simple_file(mem, end_phys_index);
 		mem_remove_simple_file(mem, state);

Index: linux-2.6/include/linux/node.h
===================================================================
@@ -44,7 +44,8 @@ extern int register_cpu_under_node(unsig
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
 						int nid);
-extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk);
+extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+					   unsigned long phys_index);
 
 #ifdef CONFIG_HUGETLBFS
 extern void register_hugetlbfs_with_node(node_registration_func_t doregister,

@@ -72,7 +73,8 @@ static inline int register_mem_sect_unde
 {
 	return 0;
 }
-static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
+static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+						  unsigned long phys_index)
 {
 	return 0;
 }

Index: linux-2.6/arch/powerpc/platforms/pseries/hotplug-memory.c
===================================================================
@@ -17,6 +17,54 @@
 #include <asm/pSeries_reconfig.h>
 #include <asm/sparsemem.h>
 
+static u32 get_memblock_size(void)
+{
+	struct device_node *np;
+	unsigned int memblock_size = 0;
+
+	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (np) {
+		const unsigned long *size;
+
+		size = of_get_property(np, "ibm,lmb-size", NULL);
+		memblock_size = size ? *size : 0;
+
+		of_node_put(np);
+	} else {
+		unsigned int memzero_size = 0;
+		const unsigned int *regs;
+
+		np = of_find_node_by_path("/memory@0");
+		if (np) {
+			regs = of_get_property(np, "reg", NULL);
+			memzero_size = regs ? regs[3] : 0;
+			of_node_put(np);
+		}
+
+		if (memzero_size) {
+			/* We now know the size of memory@0, use this to find
+			 * the first memoryblock and get its size.
+			 */
+			char buf[64];
+
+			sprintf(buf, "/memory@%x", memzero_size);
+			np = of_find_node_by_path(buf);
+			if (np) {
+				regs = of_get_property(np, "reg", NULL);
+				memblock_size = regs ? regs[3] : 0;
+				of_node_put(np);
+			}
+		}
+	}
+
+	return memblock_size;
+}
+
+u32 memory_block_size_bytes(void)
+{
+	return get_memblock_size();
+}
+
 static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
 {
 	unsigned long start, start_pfn;

@@ -127,30 +175,22 @@ static int pseries_add_memory(struct dev
 
 static int pseries_drconf_memory(unsigned long *base, unsigned int action)
 {
-	struct device_node *np;
-	const unsigned long *lmb_size;
+	unsigned long memblock_size;
 	int rc;
 
-	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (!np)
+	memblock_size = get_memblock_size();
+	if (!memblock_size)
 		return -EINVAL;
 
-	lmb_size = of_get_property(np, "ibm,lmb-size", NULL);
-	if (!lmb_size) {
-		of_node_put(np);
-		return -EINVAL;
-	}
-
 	if (action == PSERIES_DRCONF_MEM_ADD) {
-		rc = memblock_add(*base, *lmb_size);
+		rc = memblock_add(*base, memblock_size);
 		rc = (rc < 0) ? -EINVAL : 0;
 	} else if (action == PSERIES_DRCONF_MEM_REMOVE) {
-		rc = pseries_remove_memblock(*base, *lmb_size);
+		rc = pseries_remove_memblock(*base, memblock_size);
 	} else {
 		rc = -EINVAL;
 	}
 
-	of_node_put(np);
 	return rc;
 }