1 files changed, 165 insertions, 111 deletions

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 36b43052001..8f7ed9933a7 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -1,12 +1,13 @@
 /*
- * drivers/base/node.c - basic Node class support
+ * Basic Node interface support
  */
 
-#include <linux/sysdev.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/memory.h>
+#include <linux/vmstat.h>
+#include <linux/notifier.h>
 #include <linux/node.h>
 #include <linux/hugetlb.h>
 #include <linux/compaction.h>
@@ -18,18 +19,16 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 
-static struct sysdev_class_attribute *node_state_attrs[];
-
-static struct sysdev_class node_class = {
+static struct bus_type node_subsys = {
 	.name = "node",
-	.attrs = node_state_attrs,
+	.dev_name = "node",
 };
 
 
-static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
+static ssize_t node_read_cpumap(struct device *dev, int type, char *buf)
 {
 	struct node *node_dev = to_node(dev);
-	const struct cpumask *mask = cpumask_of_node(node_dev->sysdev.id);
+	const struct cpumask *mask = cpumask_of_node(node_dev->dev.id);
 	int len;
 
 	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
@@ -43,23 +42,23 @@ static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
 	return len;
 }
 
-static inline ssize_t node_read_cpumask(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static inline ssize_t node_read_cpumask(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	return node_read_cpumap(dev, 0, buf);
 }
-static inline ssize_t node_read_cpulist(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static inline ssize_t node_read_cpulist(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	return node_read_cpumap(dev, 1, buf);
 }
 
-static SYSDEV_ATTR(cpumap,  S_IRUGO, node_read_cpumask, NULL);
-static SYSDEV_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL);
+static DEVICE_ATTR(cpumap,  S_IRUGO, node_read_cpumask, NULL);
+static DEVICE_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
-static ssize_t node_read_meminfo(struct sys_device * dev,
-			struct sysdev_attribute *attr, char * buf)
+static ssize_t node_read_meminfo(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
 	int n;
 	int nid = dev->id;
@@ -126,12 +125,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_WRITEBACK)),
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-		       nid, K(node_page_state(nid, NR_ANON_PAGES)
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR
-#endif
-		       ),
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
 		       nid, K(node_page_state(nid, NR_SHMEM)),
 		       nid, node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
@@ -142,22 +136,23 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
 				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 			, nid,
 			K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR)
+			HPAGE_PMD_NR));
+#else
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
 #endif
-		       );
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
 }
 
 #undef K
-static SYSDEV_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL);
+static DEVICE_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL);
 
-static ssize_t node_read_numastat(struct sys_device * dev,
-				struct sysdev_attribute *attr, char * buf)
+static ssize_t node_read_numastat(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf,
 		       "numa_hit %lu\n"
@@ -173,22 +168,25 @@ static ssize_t node_read_numastat(struct sys_device * dev,
 		       node_page_state(dev->id, NUMA_LOCAL),
 		       node_page_state(dev->id, NUMA_OTHER));
 }
-static SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
+static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
 
-static ssize_t node_read_vmstat(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t node_read_vmstat(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	int nid = dev->id;
-	return sprintf(buf,
-		"nr_written %lu\n"
-		"nr_dirtied %lu\n",
-		node_page_state(nid, NR_WRITTEN),
-		node_page_state(nid, NR_DIRTIED));
+	int i;
+	int n = 0;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
+			     node_page_state(nid, i));
+
+	return n;
 }
-static SYSDEV_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL);
+static DEVICE_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL);
 
-static ssize_t node_read_distance(struct sys_device * dev,
-			struct sysdev_attribute *attr, char * buf)
+static ssize_t node_read_distance(struct device *dev,
+			struct device_attribute *attr, char * buf)
 {
 	int nid = dev->id;
 	int len = 0;
@@ -206,7 +204,7 @@ static ssize_t node_read_distance(struct sys_device * dev,
 	len += sprintf(buf + len, "\n");
 	return len;
 }
-static SYSDEV_ATTR(distance, S_IRUGO, node_read_distance, NULL);
+static DEVICE_ATTR(distance, S_IRUGO, node_read_distance, NULL);
 
 #ifdef CONFIG_HUGETLBFS
 /*
@@ -224,7 +222,7 @@ static node_registration_func_t __hugetlb_unregister_node;
 static inline bool hugetlb_register_node(struct node *node)
 {
 	if (__hugetlb_register_node &&
-			node_state(node->sysdev.id, N_HIGH_MEMORY)) {
+			node_state(node->dev.id, N_MEMORY)) {
 		__hugetlb_register_node(node);
 		return true;
 	}
@@ -249,6 +247,24 @@ static inline void hugetlb_register_node(struct node *node) {}
 static inline void hugetlb_unregister_node(struct node *node) {}
 #endif
 
+static void node_device_release(struct device *dev)
+{
+	struct node *node = to_node(dev);
+
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
+	/*
+	 * We schedule the work only when a memory section is
+	 * onlined/offlined on this node. When we come here,
+	 * all the memory on this node has been offlined,
+	 * so we won't enqueue new work to this work.
+	 *
+	 * The work is using node->node_work, so we should
+	 * flush work before freeing the memory.
+	 */
+	flush_work(&node->node_work);
+#endif
+	kfree(node);
+}
 
 /*
  * register_node - Setup a sysfs device for a node.
@@ -256,21 +272,22 @@ static inline void hugetlb_unregister_node(struct node *node) {}
  *
  * Initialize and register the node device.
  */
-int register_node(struct node *node, int num, struct node *parent)
+static int register_node(struct node *node, int num, struct node *parent)
 {
 	int error;
 
-	node->sysdev.id = num;
-	node->sysdev.cls = &node_class;
-	error = sysdev_register(&node->sysdev);
+	node->dev.id = num;
+	node->dev.bus = &node_subsys;
+	node->dev.release = node_device_release;
+	error = device_register(&node->dev);
 
 	if (!error){
-		sysdev_create_file(&node->sysdev, &attr_cpumap);
-		sysdev_create_file(&node->sysdev, &attr_cpulist);
-		sysdev_create_file(&node->sysdev, &attr_meminfo);
-		sysdev_create_file(&node->sysdev, &attr_numastat);
-		sysdev_create_file(&node->sysdev, &attr_distance);
-		sysdev_create_file(&node->sysdev, &attr_vmstat);
+		device_create_file(&node->dev, &dev_attr_cpumap);
+		device_create_file(&node->dev, &dev_attr_cpulist);
+		device_create_file(&node->dev, &dev_attr_meminfo);
+		device_create_file(&node->dev, &dev_attr_numastat);
+		device_create_file(&node->dev, &dev_attr_distance);
+		device_create_file(&node->dev, &dev_attr_vmstat);
 
 		scan_unevictable_register_node(node);
 
@@ -290,20 +307,20 @@ int register_node(struct node *node, int num, struct node *parent)
  */
 void unregister_node(struct node *node)
 {
-	sysdev_remove_file(&node->sysdev, &attr_cpumap);
-	sysdev_remove_file(&node->sysdev, &attr_cpulist);
-	sysdev_remove_file(&node->sysdev, &attr_meminfo);
-	sysdev_remove_file(&node->sysdev, &attr_numastat);
-	sysdev_remove_file(&node->sysdev, &attr_distance);
-	sysdev_remove_file(&node->sysdev, &attr_vmstat);
+	device_remove_file(&node->dev, &dev_attr_cpumap);
+	device_remove_file(&node->dev, &dev_attr_cpulist);
+	device_remove_file(&node->dev, &dev_attr_meminfo);
+	device_remove_file(&node->dev, &dev_attr_numastat);
+	device_remove_file(&node->dev, &dev_attr_distance);
+	device_remove_file(&node->dev, &dev_attr_vmstat);
 
 	scan_unevictable_unregister_node(node);
 	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
 
-	sysdev_unregister(&node->sysdev);
+	device_unregister(&node->dev);
 }
 
-struct node node_devices[MAX_NUMNODES];
+struct node *node_devices[MAX_NUMNODES];
 
 /*
  * register cpu under node
@@ -311,41 +328,41 @@ struct node node_devices[MAX_NUMNODES];
 int register_cpu_under_node(unsigned int cpu, unsigned int nid)
 {
 	int ret;
-	struct sys_device *obj;
+	struct device *obj;
 
 	if (!node_online(nid))
 		return 0;
 
-	obj = get_cpu_sysdev(cpu);
+	obj = get_cpu_device(cpu);
 	if (!obj)
 		return 0;
 
-	ret = sysfs_create_link(&node_devices[nid].sysdev.kobj,
+	ret = sysfs_create_link(&node_devices[nid]->dev.kobj,
 				&obj->kobj,
 				kobject_name(&obj->kobj));
 	if (ret)
 		return ret;
 
 	return sysfs_create_link(&obj->kobj,
-				 &node_devices[nid].sysdev.kobj,
-				 kobject_name(&node_devices[nid].sysdev.kobj));
+				 &node_devices[nid]->dev.kobj,
+				 kobject_name(&node_devices[nid]->dev.kobj));
 }
 
 int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 {
-	struct sys_device *obj;
+	struct device *obj;
 
 	if (!node_online(nid))
 		return 0;
 
-	obj = get_cpu_sysdev(cpu);
+	obj = get_cpu_device(cpu);
 	if (!obj)
 		return 0;
 
-	sysfs_remove_link(&node_devices[nid].sysdev.kobj,
+	sysfs_remove_link(&node_devices[nid]->dev.kobj,
 			  kobject_name(&obj->kobj));
 	sysfs_remove_link(&obj->kobj,
-			  kobject_name(&node_devices[nid].sysdev.kobj));
+			  kobject_name(&node_devices[nid]->dev.kobj));
 
 	return 0;
 }
@@ -375,8 +392,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 		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_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
 	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
 		int page_nid;
 
@@ -385,22 +404,23 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 			continue;
 		if (page_nid != nid)
 			continue;
-		ret = sysfs_create_link_nowarn(&node_devices[nid].sysdev.kobj,
-					&mem_blk->sysdev.kobj,
-					kobject_name(&mem_blk->sysdev.kobj));
+		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+					&mem_blk->dev.kobj,
+					kobject_name(&mem_blk->dev.kobj));
 		if (ret)
 			return ret;
 
-		return sysfs_create_link_nowarn(&mem_blk->sysdev.kobj,
-				&node_devices[nid].sysdev.kobj,
-				kobject_name(&node_devices[nid].sysdev.kobj));
+		return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+				&node_devices[nid]->dev.kobj,
+				kobject_name(&node_devices[nid]->dev.kobj));
 	}
 	/* mem section does not span the specified node */
 	return 0;
 }
 
 /* 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;
@@ -412,7 +432,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 	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;
@@ -424,10 +445,10 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk)
 			continue;
 		if (node_test_and_set(nid, *unlinked_nodes))
 			continue;
-		sysfs_remove_link(&node_devices[nid].sysdev.kobj,
-			 kobject_name(&mem_blk->sysdev.kobj));
-		sysfs_remove_link(&mem_blk->sysdev.kobj,
-			 kobject_name(&node_devices[nid].sysdev.kobj));
+		sysfs_remove_link(&node_devices[nid]->dev.kobj,
+			 kobject_name(&mem_blk->dev.kobj));
+		sysfs_remove_link(&mem_blk->dev.kobj,
+			 kobject_name(&node_devices[nid]->dev.kobj));
 	}
 	NODEMASK_FREE(unlinked_nodes);
 	return 0;
@@ -449,7 +470,15 @@ static int link_mem_sections(int nid)
 		if (!present_section_nr(section_nr))
 			continue;
 		mem_sect = __nr_to_section(section_nr);
+
+		/* same memblock ? */
+		if (mem_blk)
+			if ((section_nr >= mem_blk->start_section_nr) &&
+			    (section_nr <= mem_blk->end_section_nr))
+				continue;
+
 		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
+
 		ret = register_mem_sect_under_node(mem_blk, nid);
 		if (!err)
 			err = ret;
@@ -458,7 +487,7 @@ static int link_mem_sections(int nid)
 	}
 
 	if (mem_blk)
-		kobject_put(&mem_blk->sysdev.kobj);
+		kobject_put(&mem_blk->dev.kobj);
 	return err;
 }
 
@@ -485,7 +514,7 @@ static void node_hugetlb_work(struct work_struct *work)
 
 static void init_node_hugetlb_work(int nid)
 {
-	INIT_WORK(&node_devices[nid].node_work, node_hugetlb_work);
+	INIT_WORK(&node_devices[nid]->node_work, node_hugetlb_work);
 }
 
 static int node_memory_callback(struct notifier_block *self,
@@ -502,7 +531,7 @@ static int node_memory_callback(struct notifier_block *self,
 		 * when transitioning to/from memoryless state.
 		 */
 		if (nid != NUMA_NO_NODE)
-			schedule_work(&node_devices[nid].node_work);
+			schedule_work(&node_devices[nid]->node_work);
 		break;
 
 	case MEM_GOING_ONLINE:
@@ -543,9 +572,13 @@ int register_one_node(int nid)
 		struct node *parent = NULL;
 
 		if (p_node != nid)
-			parent = &node_devices[p_node];
+			parent = node_devices[p_node];
 
-		error = register_node(&node_devices[nid], nid, parent);
+		node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
+		if (!node_devices[nid])
+			return -ENOMEM;
+
+		error = register_node(node_devices[nid], nid, parent);
 
 		/* link cpu under this node */
 		for_each_present_cpu(cpu) {
@@ -566,7 +599,12 @@ int register_one_node(int nid)
 
 void unregister_one_node(int nid)
 {
-	unregister_node(&node_devices[nid]);
+	if (!node_devices[nid])
+		return;
+
+	unregister_node(node_devices[nid]);
+	kfree(node_devices[nid]);
+	node_devices[nid] = NULL;
 }
 
 /*
@@ -577,50 +615,63 @@ static ssize_t print_nodes_state(enum node_states state, char *buf)
 {
 	int n;
 
-	n = nodelist_scnprintf(buf, PAGE_SIZE, node_states[state]);
-	if (n > 0 && PAGE_SIZE > n + 1) {
-		*(buf + n++) = '\n';
-		*(buf + n++) = '\0';
-	}
+	n = nodelist_scnprintf(buf, PAGE_SIZE-2, node_states[state]);
+	buf[n++] = '\n';
+	buf[n] = '\0';
 	return n;
 }
 
 struct node_attr {
-	struct sysdev_class_attribute attr;
+	struct device_attribute attr;
 	enum node_states state;
 };
 
-static ssize_t show_node_state(struct sysdev_class *class,
-			       struct sysdev_class_attribute *attr, char *buf)
+static ssize_t show_node_state(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct node_attr *na = container_of(attr, struct node_attr, attr);
 	return print_nodes_state(na->state, buf);
 }
 
 #define _NODE_ATTR(name, state) \
-	{ _SYSDEV_CLASS_ATTR(name, 0444, show_node_state, NULL), state }
+	{ __ATTR(name, 0444, show_node_state, NULL), state }
 
 static struct node_attr node_state_attr[] = {
-	_NODE_ATTR(possible, N_POSSIBLE),
-	_NODE_ATTR(online, N_ONLINE),
-	_NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
-	_NODE_ATTR(has_cpu, N_CPU),
+	[N_POSSIBLE] = _NODE_ATTR(possible, N_POSSIBLE),
+	[N_ONLINE] = _NODE_ATTR(online, N_ONLINE),
+	[N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
 #ifdef CONFIG_HIGHMEM
-	_NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+	[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
 #endif
+	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
 };
 
-static struct sysdev_class_attribute *node_state_attrs[] = {
-	&node_state_attr[0].attr,
-	&node_state_attr[1].attr,
-	&node_state_attr[2].attr,
-	&node_state_attr[3].attr,
+static struct attribute *node_state_attrs[] = {
+	&node_state_attr[N_POSSIBLE].attr.attr,
+	&node_state_attr[N_ONLINE].attr.attr,
+	&node_state_attr[N_NORMAL_MEMORY].attr.attr,
 #ifdef CONFIG_HIGHMEM
-	&node_state_attr[4].attr,
+	&node_state_attr[N_HIGH_MEMORY].attr.attr,
 #endif
+#ifdef CONFIG_MOVABLE_NODE
+	&node_state_attr[N_MEMORY].attr.attr,
+#endif
+	&node_state_attr[N_CPU].attr.attr,
 	NULL
 };
 
+static struct attribute_group memory_root_attr_group = {
+	.attrs = node_state_attrs,
+};
+
+static const struct attribute_group *cpu_root_attr_groups[] = {
+	&memory_root_attr_group,
+	NULL,
+};
+
 #define NODE_CALLBACK_PRI	2	/* lower than SLAB */
 static int __init register_node_type(void)
 {
@@ -629,10 +680,13 @@ static int __init register_node_type(void)
  	BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
  	BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);
 
-	ret = sysdev_class_register(&node_class);
+	ret = subsys_system_register(&node_subsys, cpu_root_attr_groups);
 	if (!ret) {
-		hotplug_memory_notifier(node_memory_callback,
-					NODE_CALLBACK_PRI);
+		static struct notifier_block node_memory_callback_nb = {
+			.notifier_call = node_memory_callback,
+			.priority = NODE_CALLBACK_PRI,
+		};
+		register_hotmemory_notifier(&node_memory_callback_nb);
 	}
 
 	/*