Merge branch 'akpm' (patches from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 "Quite a lot of other stuff is banked up awaiting further
  next->mainline merging, but this batch contains:

   - Lots of random misc patches
   - OCFS2
   - Most of MM
   - backlight updates
   - lib/ updates
   - printk updates
   - checkpatch updates
   - epoll tweaking
   - rtc updates
   - hfs
   - hfsplus
   - documentation
   - procfs
   - update gcov to gcc-4.7 format
   - IPC"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (269 commits)
  ipc, msg: fix message length check for negative values
  ipc/util.c: remove unnecessary work pending test
  devpts: plug the memory leak in kill_sb
  ./Makefile: export initial ramdisk compression config option
  init/Kconfig: add option to disable kernel compression
  drivers: w1: make w1_slave::flags long to avoid memory corruption
  drivers/w1/masters/ds1wm.cuse dev_get_platdata()
  drivers/memstick/core/ms_block.c: fix unreachable state in h_msb_read_page()
  drivers/memstick/core/mspro_block.c: fix attributes array allocation
  drivers/pps/clients/pps-gpio.c: remove redundant of_match_ptr
  kernel/panic.c: reduce 1 byte usage for print tainted buffer
  gcov: reuse kbasename helper
  kernel/gcov/fs.c: use pr_warn()
  kernel/module.c: use pr_foo()
  gcov: compile specific gcov implementation based on gcc version
  gcov: add support for gcc 4.7 gcov format
  gcov: move gcov structs definitions to a gcc version specific file
  kernel/taskstats.c: return -ENOMEM when alloc memory fails in add_del_listener()
  kernel/taskstats.c: add nla_nest_cancel() for failure processing between nla_nest_start() and nla_nest_end()
  kernel/sysctl_binary.c: use scnprintf() instead of snprintf()
  ...

28 files changed, 569 insertions, 390 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 394838f489eb..3f4ffda152bb 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -153,11 +153,18 @@ config MOVABLE_NODE
 	help
 	  Allow a node to have only movable memory.  Pages used by the kernel,
 	  such as direct mapping pages cannot be migrated.  So the corresponding
-	  memory device cannot be hotplugged.  This option allows users to
-	  online all the memory of a node as movable memory so that the whole
-	  node can be hotplugged.  Users who don't use the memory hotplug
-	  feature are fine with this option on since they don't online memory
-	  as movable.
+	  memory device cannot be hotplugged.  This option allows the following
+	  two things:
+	  - When the system is booting, node full of hotpluggable memory can
+	  be arranged to have only movable memory so that the whole node can
+	  be hot-removed. (need movable_node boot option specified).
+	  - After the system is up, the option allows users to online all the
+	  memory of a node as movable memory so that the whole node can be
+	  hot-removed.
+
+	  Users who don't use the memory hotplug feature are fine with this
+	  option on since they don't specify movable_node boot option or they
+	  don't online memory as movable.
 
 	  Say Y here if you want to hotplug a whole node.
 	  Say N here if you want kernel to use memory on all nodes evenly.
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 6ab7744e692e..90bd3507b413 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -172,11 +172,12 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	struct page *page;
-	unsigned long start, end, pages, count = 0;
+	unsigned long *map, start, end, pages, count = 0;
 
 	if (!bdata->node_bootmem_map)
 		return 0;
 
+	map = bdata->node_bootmem_map;
 	start = bdata->node_min_pfn;
 	end = bdata->node_low_pfn;
 
@@ -184,10 +185,9 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 		bdata - bootmem_node_data, start, end);
 
 	while (start < end) {
-		unsigned long *map, idx, vec;
+		unsigned long idx, vec;
 		unsigned shift;
 
-		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
 		shift = idx & (BITS_PER_LONG - 1);
 		/*
@@ -784,7 +784,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
 	/* update goal according ...MAX_DMA32_PFN */
-	end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	end_pfn = pgdat_end_pfn(pgdat);
 
 	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
 	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
diff --git a/mm/compaction.c b/mm/compaction.c
index b5326b141a25..805165bcd3dd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -235,10 +235,9 @@ static bool suitable_migration_target(struct page *page)
 }
 
 /*
- * Isolate free pages onto a private freelist. Caller must hold zone->lock.
- * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
- * pages inside of the pageblock (even though it may still end up isolating
- * some pages).
+ * Isolate free pages onto a private freelist. If @strict is true, will abort
+ * returning 0 on any invalid PFNs or non-free pages inside of the pageblock
+ * (even though it may still end up isolating some pages).
  */
 static unsigned long isolate_freepages_block(struct compact_control *cc,
 				unsigned long blockpfn,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2612f60f53ee..0556c6a44959 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -27,11 +27,12 @@
 #include "internal.h"
 
 /*
- * By default transparent hugepage support is enabled for all mappings
- * and khugepaged scans all mappings. Defrag is only invoked by
- * khugepaged hugepage allocations and by page faults inside
- * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
- * allocations.
+ * By default transparent hugepage support is disabled in order that avoid
+ * to risk increase the memory footprint of applications without a guaranteed
+ * benefit. When transparent hugepage support is enabled, is for all mappings,
+ * and khugepaged scans all mappings.
+ * Defrag is invoked by khugepaged hugepage allocations and by page faults
+ * for all hugepage allocations.
  */
 unsigned long transparent_hugepage_flags __read_mostly =
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
@@ -758,14 +759,6 @@ static inline struct page *alloc_hugepage_vma(int defrag,
 			       HPAGE_PMD_ORDER, vma, haddr, nd);
 }
 
-#ifndef CONFIG_NUMA
-static inline struct page *alloc_hugepage(int defrag)
-{
-	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
-			   HPAGE_PMD_ORDER);
-}
-#endif
-
 static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
@@ -2198,7 +2191,34 @@ static void khugepaged_alloc_sleep(void)
 			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
+static int khugepaged_node_load[MAX_NUMNODES];
+
 #ifdef CONFIG_NUMA
+static int khugepaged_find_target_node(void)
+{
+	static int last_khugepaged_target_node = NUMA_NO_NODE;
+	int nid, target_node = 0, max_value = 0;
+
+	/* find first node with max normal pages hit */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (khugepaged_node_load[nid] > max_value) {
+			max_value = khugepaged_node_load[nid];
+			target_node = nid;
+		}
+
+	/* do some balance if several nodes have the same hit record */
+	if (target_node <= last_khugepaged_target_node)
+		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
+				nid++)
+			if (max_value == khugepaged_node_load[nid]) {
+				target_node = nid;
+				break;
+			}
+
+	last_khugepaged_target_node = target_node;
+	return target_node;
+}
+
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
 	if (IS_ERR(*hpage)) {
@@ -2232,9 +2252,8 @@ static struct page
 	 * mmap_sem in read mode is good idea also to allow greater
 	 * scalability.
 	 */
-	*hpage  = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
-				      node, __GFP_OTHER_NODE);
-
+	*hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask(
+		khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER);
 	/*
 	 * After allocating the hugepage, release the mmap_sem read lock in
 	 * preparation for taking it in write mode.
@@ -2250,6 +2269,17 @@ static struct page
 	return *hpage;
 }
 #else
+static int khugepaged_find_target_node(void)
+{
+	return 0;
+}
+
+static inline struct page *alloc_hugepage(int defrag)
+{
+	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
+			   HPAGE_PMD_ORDER);
+}
+
 static struct page *khugepaged_alloc_hugepage(bool *wait)
 {
 	struct page *hpage;
@@ -2456,6 +2486,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (pmd_trans_huge(*pmd))
 		goto out;
 
+	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -2472,12 +2503,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		if (unlikely(!page))
 			goto out_unmap;
 		/*
-		 * Chose the node of the first page. This could
-		 * be more sophisticated and look at more pages,
-		 * but isn't for now.
+		 * Record which node the original page is from and save this
+		 * information to khugepaged_node_load[].
+		 * Khupaged will allocate hugepage from the node has the max
+		 * hit record.
 		 */
-		if (node == NUMA_NO_NODE)
-			node = page_to_nid(page);
+		node = page_to_nid(page);
+		khugepaged_node_load[node]++;
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
 			goto out_unmap;
@@ -2492,9 +2524,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		ret = 1;
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
-	if (ret)
+	if (ret) {
+		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
 		collapse_huge_page(mm, address, hpage, vma, node);
+	}
 out:
 	return ret;
 }
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e126b0ef9ad2..31f01c5011e5 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -753,7 +753,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 	}
 
 	spin_lock_irqsave(&object->lock, flags);
-	if (ptr + size > object->pointer + object->size) {
+	if (size == SIZE_MAX) {
+		size = object->pointer + object->size - ptr;
+	} else if (ptr + size > object->pointer + object->size) {
 		kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
 		dump_object_info(object);
 		kmem_cache_free(scan_area_cache, area);
diff --git a/mm/ksm.c b/mm/ksm.c
index 0bea2b262a47..175fff79dc95 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2309,8 +2309,8 @@ static ssize_t merge_across_nodes_store(struct kobject *kobj,
 			 * Allocate stable and unstable together:
 			 * MAXSMP NODES_SHIFT 10 will use 16kB.
 			 */
-			buf = kcalloc(nr_node_ids + nr_node_ids,
-				sizeof(*buf), GFP_KERNEL | __GFP_ZERO);
+			buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf),
+				      GFP_KERNEL);
 			/* Let us assume that RB_ROOT is NULL is zero */
 			if (!buf)
 				err = -ENOMEM;
diff --git a/mm/memblock.c b/mm/memblock.c
index 0ac412a0a7ee..53e477bb5558 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,6 +20,8 @@
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
+#include <asm-generic/sections.h>
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 
@@ -32,6 +34,7 @@ struct memblock memblock __initdata_memblock = {
 	.reserved.cnt		= 1,	/* empty dummy entry */
 	.reserved.max		= INIT_MEMBLOCK_REGIONS,
 
+	.bottom_up		= false,
 	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
 };
 
@@ -82,6 +85,73 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return (i < type->cnt) ? i : -1;
 }
 
+/*
+ * __memblock_find_range_bottom_up - find free area utility in bottom-up
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @size: size of free area to find
+ * @align: alignment of free area to find
+ * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ *
+ * Utility called from memblock_find_in_range_node(), find free area bottom-up.
+ *
+ * RETURNS:
+ * Found address on success, 0 on failure.
+ */
+static phys_addr_t __init_memblock
+__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
+				phys_addr_t size, phys_addr_t align, int nid)
+{
+	phys_addr_t this_start, this_end, cand;
+	u64 i;
+
+	for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+		cand = round_up(this_start, align);
+		if (cand < this_end && this_end - cand >= size)
+			return cand;
+	}
+
+	return 0;
+}
+
+/**
+ * __memblock_find_range_top_down - find free area utility, in top-down
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @size: size of free area to find
+ * @align: alignment of free area to find
+ * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ *
+ * Utility called from memblock_find_in_range_node(), find free area top-down.
+ *
+ * RETURNS:
+ * Found address on success, 0 on failure.
+ */
+static phys_addr_t __init_memblock
+__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
+			       phys_addr_t size, phys_addr_t align, int nid)
+{
+	phys_addr_t this_start, this_end, cand;
+	u64 i;
+
+	for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+		if (this_end < size)
+			continue;
+
+		cand = round_down(this_end - size, align);
+		if (cand >= this_start)
+			return cand;
+	}
+
+	return 0;
+}
+
 /**
  * memblock_find_in_range_node - find free area in given range and node
  * @start: start of candidate range
@@ -92,15 +162,23 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
+ * When allocation direction is bottom-up, the @start should be greater
+ * than the end of the kernel image. Otherwise, it will be trimmed. The
+ * reason is that we want the bottom-up allocation just near the kernel
+ * image so it is highly likely that the allocated memory and the kernel
+ * will reside in the same node.
+ *
+ * If bottom-up allocation failed, will try to allocate memory top-down.
+ *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align, int nid)
 {
-	phys_addr_t this_start, this_end, cand;
-	u64 i;
+	int ret;
+	phys_addr_t kernel_end;
 
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
@@ -109,19 +187,39 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	/* avoid allocating the first page */
 	start = max_t(phys_addr_t, start, PAGE_SIZE);
 	end = max(start, end);
+	kernel_end = __pa_symbol(_end);
 
-	for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
-		this_start = clamp(this_start, start, end);
-		this_end = clamp(this_end, start, end);
+	/*
+	 * try bottom-up allocation only when bottom-up mode
+	 * is set and @end is above the kernel image.
+	 */
+	if (memblock_bottom_up() && end > kernel_end) {
+		phys_addr_t bottom_up_start;
 
-		if (this_end < size)
-			continue;
+		/* make sure we will allocate above the kernel */
+		bottom_up_start = max(start, kernel_end);
 
-		cand = round_down(this_end - size, align);
-		if (cand >= this_start)
-			return cand;
+		/* ok, try bottom-up allocation first */
+		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
+						      size, align, nid);
+		if (ret)
+			return ret;
+
+		/*
+		 * we always limit bottom-up allocation above the kernel,
+		 * but top-down allocation doesn't have the limit, so
+		 * retrying top-down allocation may succeed when bottom-up
+		 * allocation failed.
+		 *
+		 * bottom-up allocation is expected to be fail very rarely,
+		 * so we use WARN_ONCE() here to see the stack trace if
+		 * fail happens.
+		 */
+		WARN_ONCE(1, "memblock: bottom-up allocation failed, "
+			     "memory hotunplug may be affected\n");
 	}
-	return 0;
+
+	return __memblock_find_range_top_down(start, end, size, align, nid);
 }
 
 /**
@@ -134,7 +232,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
  * Find @size free area aligned to @align in the specified range.
  *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 796820925de0..f20a57b7faf2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -59,6 +59,7 @@
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/tcp_memcontrol.h>
+#include "slab.h"
 
 #include <asm/uaccess.h>
 
@@ -2968,7 +2969,7 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 
 	VM_BUG_ON(p->is_root_cache);
 	cachep = p->root_cache;
-	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
+	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
 }
 
 #ifdef CONFIG_SLABINFO
@@ -2997,21 +2998,14 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	struct res_counter *fail_res;
 	struct mem_cgroup *_memcg;
 	int ret = 0;
-	bool may_oom;
 
 	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
 	if (ret)
 		return ret;
 
-	/*
-	 * Conditions under which we can wait for the oom_killer. Those are
-	 * the same conditions tested by the core page allocator
-	 */
-	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
-
 	_memcg = memcg;
 	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
-				      &_memcg, may_oom);
+				      &_memcg, oom_gfp_allowed(gfp));
 
 	if (ret == -EINTR)  {
 		/*
@@ -3151,7 +3145,7 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 {
 	struct memcg_cache_params *cur_params = s->memcg_params;
 
-	VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);
+	VM_BUG_ON(!is_root_cache(s));
 
 	if (num_groups > memcg_limited_groups_array_size) {
 		int i;
@@ -3412,7 +3406,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	idx = memcg_cache_id(memcg);
 
 	mutex_lock(&memcg_cache_mutex);
-	new_cachep = cachep->memcg_params->memcg_caches[idx];
+	new_cachep = cache_from_memcg_idx(cachep, idx);
 	if (new_cachep) {
 		css_put(&memcg->css);
 		goto out;
@@ -3458,8 +3452,8 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 	 * we'll take the set_limit_mutex to protect ourselves against this.
 	 */
 	mutex_lock(&set_limit_mutex);
-	for (i = 0; i < memcg_limited_groups_array_size; i++) {
-		c = s->memcg_params->memcg_caches[i];
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg_idx(s, i);
 		if (!c)
 			continue;
 
@@ -3592,8 +3586,8 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	 * code updating memcg_caches will issue a write barrier to match this.
 	 */
 	read_barrier_depends();
-	if (likely(cachep->memcg_params->memcg_caches[idx])) {
-		cachep = cachep->memcg_params->memcg_caches[idx];
+	if (likely(cache_from_memcg_idx(cachep, idx))) {
+		cachep = cache_from_memcg_idx(cachep, idx);
 		goto out;
 	}
 
@@ -5389,45 +5383,50 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
 static int memcg_numa_stat_show(struct cgroup_subsys_state *css,
 				struct cftype *cft, struct seq_file *m)
 {
+	struct numa_stat {
+		const char *name;
+		unsigned int lru_mask;
+	};
+
+	static const struct numa_stat stats[] = {
+		{ "total", LRU_ALL },
+		{ "file", LRU_ALL_FILE },
+		{ "anon", LRU_ALL_ANON },
+		{ "unevictable", BIT(LRU_UNEVICTABLE) },
+	};
+	const struct numa_stat *stat;
 	int nid;
-	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
-	unsigned long node_nr;
+	unsigned long nr;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
-	seq_printf(m, "total=%lu", total_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
-	}
-	seq_putc(m, '\n');
-
-	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
-	seq_printf(m, "file=%lu", file_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				LRU_ALL_FILE);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
-	}
-	seq_putc(m, '\n');
-
-	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
-	seq_printf(m, "anon=%lu", anon_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				LRU_ALL_ANON);
-		seq_printf(m, " N%d=%lu", nid, node_nr);
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask);
+		seq_printf(m, "%s=%lu", stat->name, nr);
+		for_each_node_state(nid, N_MEMORY) {
+			nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
+							  stat->lru_mask);
+			seq_printf(m, " N%d=%lu", nid, nr);
+		}
+		seq_putc(m, '\n');
+	}
+
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		struct mem_cgroup *iter;
+
+		nr = 0;
+		for_each_mem_cgroup_tree(iter, memcg)
+			nr += mem_cgroup_nr_lru_pages(iter, stat->lru_mask);
+		seq_printf(m, "hierarchical_%s=%lu", stat->name, nr);
+		for_each_node_state(nid, N_MEMORY) {
+			nr = 0;
+			for_each_mem_cgroup_tree(iter, memcg)
+				nr += mem_cgroup_node_nr_lru_pages(
+					iter, nid, stat->lru_mask);
+			seq_printf(m, " N%d=%lu", nid, nr);
+		}
+		seq_putc(m, '\n');
 	}
-	seq_putc(m, '\n');
 
-	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
-	seq_printf(m, "unevictable=%lu", unevictable_nr);
-	for_each_node_state(nid, N_MEMORY) {
-		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
-				BIT(LRU_UNEVICTABLE));
-		seq_printf(m, " N%d=%lu", nid, node_nr);
-	}
-	seq_putc(m, '\n');
 	return 0;
 }
 #endif /* CONFIG_NUMA */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index bf3351b5115e..f9d78ec7831f 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1423,19 +1423,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		return 1;
 
 	/*
-	 * The lock_memory_hotplug prevents a race with memory hotplug.
-	 * This is a big hammer, a better would be nicer.
-	 */
-	lock_memory_hotplug();
-
-	/*
-	 * Isolate the page, so that it doesn't get reallocated if it
-	 * was free. This flag should be kept set until the source page
-	 * is freed and PG_hwpoison on it is set.
-	 */
-	if (get_pageblock_migratetype(p) != MIGRATE_ISOLATE)
-		set_migratetype_isolate(p, true);
-	/*
 	 * When the target page is a free hugepage, just remove it
 	 * from free hugepage list.
 	 */
@@ -1455,7 +1442,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		/* Not a free page */
 		ret = 1;
 	}
-	unlock_memory_hotplug();
 	return ret;
 }
 
@@ -1654,15 +1640,28 @@ int soft_offline_page(struct page *page, int flags)
 		}
 	}
 
+	/*
+	 * The lock_memory_hotplug prevents a race with memory hotplug.
+	 * This is a big hammer, a better would be nicer.
+	 */
+	lock_memory_hotplug();
+
+	/*
+	 * Isolate the page, so that it doesn't get reallocated if it
+	 * was free. This flag should be kept set until the source page
+	 * is freed and PG_hwpoison on it is set.
+	 */
+	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+		set_migratetype_isolate(page, true);
+
 	ret = get_any_page(page, pfn, flags);
-	if (ret < 0)
-		goto unset;
-	if (ret) { /* for in-use pages */
+	unlock_memory_hotplug();
+	if (ret > 0) { /* for in-use pages */
 		if (PageHuge(page))
 			ret = soft_offline_huge_page(page, flags);
 		else
 			ret = __soft_offline_page(page, flags);
-	} else { /* for free pages */
+	} else if (ret == 0) { /* for free pages */
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
 			dequeue_hwpoisoned_huge_page(hpage);
@@ -1673,7 +1672,6 @@ int soft_offline_page(struct page *page, int flags)
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	}
-unset:
 	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 33a3dbec3cc8..bf8665849a5f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -453,8 +453,6 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 
 /*
  * This function frees user-level page tables of a process.
- *
- * Must be called with pagetable lock held.
  */
 void free_pgd_range(struct mmu_gather *tlb,
 			unsigned long addr, unsigned long end,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ed85fe3870e2..489f235502db 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -31,6 +31,7 @@
 #include <linux/firmware-map.h>
 #include <linux/stop_machine.h>
 #include <linux/hugetlb.h>
+#include <linux/memblock.h>
 
 #include <asm/tlbflush.h>
 
@@ -365,8 +366,7 @@ out_fail:
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 			    unsigned long end_pfn)
 {
-	unsigned long old_pgdat_end_pfn =
-		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat);
 
 	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
 		pgdat->node_start_pfn = start_pfn;
@@ -402,13 +402,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 static int __meminit __add_section(int nid, struct zone *zone,
 					unsigned long phys_start_pfn)
 {
-	int nr_pages = PAGES_PER_SECTION;
 	int ret;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
 
-	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
+	ret = sparse_add_one_section(zone, phys_start_pfn);
 
 	if (ret < 0)
 		return ret;
@@ -579,9 +578,9 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 static void shrink_pgdat_span(struct pglist_data *pgdat,
 			      unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pgdat_start_pfn =  pgdat->node_start_pfn;
-	unsigned long pgdat_end_pfn =
-		pgdat->node_start_pfn + pgdat->node_spanned_pages;
+	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
+	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
+	unsigned long pgdat_end_pfn = p;
 	unsigned long pfn;
 	struct mem_section *ms;
 	int nid = pgdat->node_id;
@@ -935,7 +934,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	arg.nr_pages = nr_pages;
 	node_states_check_changes_online(nr_pages, zone, &arg);
 
-	nid = page_to_nid(pfn_to_page(pfn));
+	nid = pfn_to_nid(pfn);
 
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -1044,17 +1043,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-/*
+/**
+ * try_online_node - online a node if offlined
+ *
  * called by cpu_up() to online a node without onlined memory.
  */
-int mem_online_node(int nid)
+int try_online_node(int nid)
 {
 	pg_data_t	*pgdat;
 	int	ret;
 
+	if (node_online(nid))
+		return 0;
+
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
 	if (!pgdat) {
+		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1062,6 +1067,12 @@ int mem_online_node(int nid)
 	ret = register_one_node(nid);
 	BUG_ON(ret);
 
+	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
+		mutex_lock(&zonelists_mutex);
+		build_all_zonelists(NULL, NULL);
+		mutex_unlock(&zonelists_mutex);
+	}
+
 out:
 	unlock_memory_hotplug();
 	return ret;
@@ -1412,6 +1423,36 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
 }
 #endif /* CONFIG_MOVABLE_NODE */
 
+static int __init cmdline_parse_movable_node(char *p)
+{
+#ifdef CONFIG_MOVABLE_NODE
+	/*
+	 * Memory used by the kernel cannot be hot-removed because Linux
+	 * cannot migrate the kernel pages. When memory hotplug is
+	 * enabled, we should prevent memblock from allocating memory
+	 * for the kernel.
+	 *
+	 * ACPI SRAT records all hotpluggable memory ranges. But before
+	 * SRAT is parsed, we don't know about it.
+	 *
+	 * The kernel image is loaded into memory at very early time. We
+	 * cannot prevent this anyway. So on NUMA system, we set any
+	 * node the kernel resides in as un-hotpluggable.
+	 *
+	 * Since on modern servers, one node could have double-digit
+	 * gigabytes memory, we can assume the memory around the kernel
+	 * image is also un-hotpluggable. So before SRAT is parsed, just
+	 * allocate memory near the kernel image to try the best to keep
+	 * the kernel away from hotpluggable memory.
+	 */
+	memblock_set_bottom_up(true);
+#else
+	pr_