Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few hotfixes

 - various misc updates

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (108 commits)
  mm, memory_hotplug: move movable_node to the hotplug proper
  mm, memory_hotplug: drop CONFIG_MOVABLE_NODE
  mm, memory_hotplug: drop artificial restriction on online/offline
  mm: memcontrol: account slab stats per lruvec
  mm: memcontrol: per-lruvec stats infrastructure
  mm: memcontrol: use generic mod_memcg_page_state for kmem pages
  mm: memcontrol: use the node-native slab memory counters
  mm: vmstat: move slab statistics from zone to node counters
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_dstmem_prepare()
  mm/zswap.c: improve a size determination in zswap_frontswap_init()
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_pool_create()
  mm/swapfile.c: sort swap entries before free
  mm/oom_kill: count global and memory cgroup oom kills
  mm: per-cgroup memory reclaim stats
  mm: kmemleak: treat vm_struct as alternative reference to vmalloc'ed objects
  mm: kmemleak: factor object reference updating out of scan_block()
  mm: kmemleak: slightly reduce the size of some structures on 64-bit architectures
  mm, mempolicy: don't check cpuset seqlock where it doesn't matter
  mm, cpuset: always use seqlock when changing task's nodemask
  mm, mempolicy: simplify rebinding mempolicies when updating cpusets
  ...

2 files changed, 70 insertions, 85 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index cc4f1d0cbffe..c7c4e0325cdb 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -128,6 +128,9 @@ static ssize_t show_mem_removable(struct device *dev,
 	int ret = 1;
 	struct memory_block *mem = to_memory_block(dev);
 
+	if (mem->state != MEM_ONLINE)
+		goto out;
+
 	for (i = 0; i < sections_per_block; i++) {
 		if (!present_section_nr(mem->start_section_nr + i))
 			continue;
@@ -135,6 +138,7 @@ static ssize_t show_mem_removable(struct device *dev,
 		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
 	}
 
+out:
 	return sprintf(buf, "%d\n", ret);
 }
 
@@ -388,39 +392,43 @@ static ssize_t show_valid_zones(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct memory_block *mem = to_memory_block(dev);
-	unsigned long start_pfn, end_pfn;
-	unsigned long valid_start, valid_end, valid_pages;
+	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	struct zone *zone;
-	int zone_shift = 0;
+	unsigned long valid_start_pfn, valid_end_pfn;
+	bool append = false;
+	int nid;
 
-	start_pfn = section_nr_to_pfn(mem->start_section_nr);
-	end_pfn = start_pfn + nr_pages;
-
-	/* The block contains more than one zone can not be offlined. */
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
+	/*
+	 * The block contains more than one zone can not be offlined.
+	 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
+	 */
+	if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn))
 		return sprintf(buf, "none\n");
 
-	zone = page_zone(pfn_to_page(valid_start));
-	valid_pages = valid_end - valid_start;
+	start_pfn = valid_start_pfn;
+	nr_pages = valid_end_pfn - start_pfn;
 
-	/* MMOP_ONLINE_KEEP */
-	sprintf(buf, "%s", zone->name);
-
-	/* MMOP_ONLINE_KERNEL */
-	zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift);
-	if (zone_shift) {
-		strcat(buf, " ");
-		strcat(buf, (zone + zone_shift)->name);
+	/*
+	 * Check the existing zone. Make sure that we do that only on the
+	 * online nodes otherwise the page_zone is not reliable
+	 */
+	if (mem->state == MEM_ONLINE) {
+		strcat(buf, page_zone(pfn_to_page(start_pfn))->name);
+		goto out;
 	}
 
-	/* MMOP_ONLINE_MOVABLE */
-	zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift);
-	if (zone_shift) {
-		strcat(buf, " ");
-		strcat(buf, (zone + zone_shift)->name);
+	nid = pfn_to_nid(start_pfn);
+	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) {
+		strcat(buf, default_zone_for_pfn(nid, start_pfn, nr_pages)->name);
+		append = true;
 	}
 
+	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE)) {
+		if (append)
+			strcat(buf, " ");
+		strcat(buf, NODE_DATA(nid)->node_zones[ZONE_MOVABLE].name);
+	}
+out:
 	strcat(buf, "\n");
 
 	return strlen(buf);
@@ -685,14 +693,6 @@ static int add_memory_block(int base_section_nr)
 	return 0;
 }
 
-static bool is_zone_device_section(struct mem_section *ms)
-{
-	struct page *page;
-
-	page = sparse_decode_mem_map(ms->section_mem_map, __section_nr(ms));
-	return is_zone_device_page(page);
-}
-
 /*
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
@@ -702,9 +702,6 @@ int register_new_memory(int nid, struct mem_section *section)
 	int ret = 0;
 	struct memory_block *mem;
 
-	if (is_zone_device_section(section))
-		return 0;
-
 	mutex_lock(&mem_sysfs_mutex);
 
 	mem = find_memory_block(section);
@@ -741,11 +738,16 @@ static int remove_memory_section(unsigned long node_id,
 {
 	struct memory_block *mem;
 
-	if (is_zone_device_section(section))
-		return 0;
-
 	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--;
@@ -754,6 +756,7 @@ static int remove_memory_section(unsigned long node_id,
 	else
 		put_device(&mem->dev);
 
+out_unlock:
 	mutex_unlock(&mem_sysfs_mutex);
 	return 0;
 }
@@ -820,6 +823,10 @@ int __init memory_dev_init(void)
 	 */
 	mutex_lock(&mem_sysfs_mutex);
 	for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) {
+		/* Don't iterate over sections we know are !present: */
+		if (i > __highest_present_section_nr)
+			break;
+
 		err = add_memory_block(i);
 		if (!ret)
 			ret = err;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 0440d95c9b5b..73d39bc58c42 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -129,11 +129,11 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
 		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
-				sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) +
+			      node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
@@ -141,7 +141,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
 				       HPAGE_PMD_NR));
 #else
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)));
 #endif
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
@@ -368,21 +368,14 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-#define page_initialized(page)  (page->lru.next)
-
 static int __ref get_nid_for_pfn(unsigned long pfn)
 {
-	struct page *page;
-
 	if (!pfn_valid_within(pfn))
 		return -1;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	if (system_state < SYSTEM_RUNNING)
 		return early_pfn_to_nid(pfn);
 #endif
-	page = pfn_to_page(pfn);
-	if (!page_initialized(page))
-		return -1;
 	return pfn_to_nid(pfn);
 }
 
@@ -468,10 +461,9 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 	return 0;
 }
 
-static int link_mem_sections(int nid)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 {
-	unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
-	unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages;
+	unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn;
 	struct memory_block *mem_blk = NULL;
 	int err = 0;
@@ -559,10 +551,7 @@ static int node_memory_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif	/* CONFIG_HUGETLBFS */
-#else	/* !CONFIG_MEMORY_HOTPLUG_SPARSE */
-
-static int link_mem_sections(int nid) { return 0; }
-#endif	/* CONFIG_MEMORY_HOTPLUG_SPARSE */
+#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
 #if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
     !defined(CONFIG_HUGETLBFS)
@@ -576,39 +565,32 @@ static void init_node_hugetlb_work(int nid) { }
 
 #endif
 
-int register_one_node(int nid)
+int __register_one_node(int nid)
 {
-	int error = 0;
+	int p_node = parent_node(nid);
+	struct node *parent = NULL;
+	int error;
 	int cpu;
 
-	if (node_online(nid)) {
-		int p_node = parent_node(nid);
-		struct node *parent = NULL;
-
-		if (p_node != nid)
-			parent = node_devices[p_node];
-
-		node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
-		if (!node_devices[nid])
-			return -ENOMEM;
-
-		error = register_node(node_devices[nid], nid, parent);
+	if (p_node != nid)
+		parent = node_devices[p_node];
 
-		/* link cpu under this node */
-		for_each_present_cpu(cpu) {
-			if (cpu_to_node(cpu) == nid)
-				register_cpu_under_node(cpu, nid);
-		}
+	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!node_devices[nid])
+		return -ENOMEM;
 
-		/* link memory sections under this node */
-		error = link_mem_sections(nid);
+	error = register_node(node_devices[nid], nid, parent);
 
-		/* initialize work queue for memory hot plug */
-		init_node_hugetlb_work(nid);
+	/* link cpu under this node */
+	for_each_present_cpu(cpu) {
+		if (cpu_to_node(cpu) == nid)
+			register_cpu_under_node(cpu, nid);
 	}
 
-	return error;
+	/* initialize work queue for memory hot plug */
+	init_node_hugetlb_work(nid);
 
+	return error;
 }
 
 void unregister_one_node(int nid)
@@ -657,9 +639,7 @@ static struct node_attr node_state_attr[] = {
 #ifdef CONFIG_HIGHMEM
 	[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),
 };
 
@@ -670,9 +650,7 @@ static struct attribute *node_state_attrs[] = {
 #ifdef CONFIG_HIGHMEM
 	&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
 };