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()
  ...

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.

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) {

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,

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;
 }

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);

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;

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,
 };
 
@@ -82,33 +85,57 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return (i < type->cnt) ? i : -1;
 }
 
-/**
- * memblock_find_in_range_node - find free area in given range and node
+/*
+ * __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
  *
- * Find @size free area aligned to @align in the specified range and node.
+ * Utility called from memblock_find_in_range_node(), find free area bottom-up.
  *
  * 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)
+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;
 
-	/* pump up @end */
-	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
-		end = memblock.current_limit;
+	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);
 
-	/* avoid allocating the first page */
-	start = max_t(phys_addr_t, start, PAGE_SIZE);
-	end = max(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);
@@ -121,9 +148,80 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 		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
+ * @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
+ *
+ * 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.
+ */
+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)
+{
+	int ret;
+	phys_addr_t kernel_end;
+
+	/* pump up @end */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* avoid allocating the first page */
+	start = max_t(phys_addr_t, start, PAGE_SIZE);
+	end = max(start, end);
+	kernel_end = __pa_symbol(_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;
+
+		/* make sure we will allocate above the kernel */
+		bottom_up_start = max(start, kernel_end);
+
+		/* 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 __memblock_find_range_top_down(start, end, size, align, nid);
+}
+
 /**
  * memblock_find_in_range - find free area in given range
  * @start: start of candidate range
@@ -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,

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);
+	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');
 	}
-	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');
+	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
+		struct mem_cgroup *iter;
 
-	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);
+		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 */

mm/memory-failure.c

@@ -1422,19 +1422,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 	if (flags & MF_COUNT_INCREASED)
 		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;
 }

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,

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_warn("movable_node option not supported\n");
+#endif
+	return 0;
+}
+early_param("movable_node", cmdline_parse_movable_node);
+
 /* check which state of node_states will be changed when offline memory */
 static void node_states_check_changes_offline(unsigned long nr_pages,
 		struct zone *zone, struct memory_notify *arg)
@@ -1702,7 +1743,7 @@ int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
+static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
 {
 	int ret = !is_memblock_offlined(mem);
 
@@ -1854,7 +1895,7 @@ void __ref remove_memory(int nid, u64 start, u64 size)
 	 * if this is not the case.
 	 */
 	ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
-				is_memblock_offlined_cb);
+				check_memblock_offlined_cb);
 	if (ret) {
 		unlock_memory_hotplug();
 		BUG();

mm/mempolicy.c

@@ -1125,7 +1125,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
-		int source = -1;
+		int source = NUMA_NO_NODE;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
@@ -1160,7 +1160,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 			if (!node_isset(dest, tmp))
 				break;
 		}
-		if (source == -1)
+		if (source == NUMA_NO_NODE)
 			break;
 
 		node_clear(source, tmp);
@@ -1835,7 +1835,7 @@ static unsigned offset_il_node(struct mempolicy *pol,
 	unsigned nnodes = nodes_weight(pol->v.nodes);
 	unsigned target;
 	int c;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	if (!nnodes)
 		return numa_node_id();
@@ -1872,11 +1872,11 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 
 /*
  * Return the bit number of a random bit set in the nodemask.
- * (returns -1 if nodemask is empty)
+ * (returns NUMA_NO_NODE if nodemask is empty)
  */
 int node_random(const nodemask_t *maskp)
 {
-	int w, bit = -1;
+	int w, bit = NUMA_NO_NODE;
 
 	w = nodes_weight(*maskp);
 	if (w)
@@ -2914,62 +2914,45 @@ out:
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
  *
- * Convert a mempolicy into a string.
- * Returns the number of characters in buffer (if positive)
- * or an error (negative)
+ * Convert @pol into a string.  If @buffer is too short, truncate the string.
+ * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
+ * longest flag, "relative", and to display at least a few node ids.
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
-	int l;
-	nodemask_t nodes;
-	unsigned short mode;
-	unsigned short flags = pol ? pol->flags : 0;
+	nodemask_t nodes = NODE_MASK_NONE;
+	unsigned short mode = MPOL_DEFAULT;
+	unsigned short flags = 0;
 
-	/*
-	 * Sanity check:  room for longest mode, flag and some nodes
-	 */
-	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
-
-	if (!pol || pol == &default_policy)
-		mode = MPOL_DEFAULT;
-	else
+	if (pol && pol != &default_policy) {
 		mode = pol->mode;
+		flags = pol->flags;
+	}
 
 	switch (mode) {
 	case MPOL_DEFAULT:
-		nodes_clear(nodes);
 		break;
-
 	case MPOL_PREFERRED:
-		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
 			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
-
 	case MPOL_BIND:
-		/* Fall through */
 	case MPOL_INTERLEAVE:
 		nodes = pol->v.nodes;
 		break;
-
 	default:
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		snprintf(p, maxlen, "unknown");
+		return;
 	}
 
-	l = strlen(policy_modes[mode]);
-	if (buffer + maxlen < p + l + 1)
-		return -ENOSPC;
-
-	strcpy(p, policy_modes[mode]);
-	p += l;
+	p += snprintf(p, maxlen, policy_modes[mode]);
 
 	if (flags & MPOL_MODE_FLAGS) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = '=';
+		p += snprintf(p, buffer + maxlen - p, "=");
 
 		/*
 		 * Currently, the only defined flags are mutually exclusive
@@ -2981,10 +2964,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	}
 
 	if (!nodes_empty(nodes)) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = ':';
+		p += snprintf(p, buffer + maxlen - p, ":");
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
-	return p - buffer;
 }

mm/mmap.c

@@ -179,14 +179,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = (totalram_pages - hugetlb_total_pages())
-	       	* sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
@@ -1856,7 +1854,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
 
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1865,14 +1863,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = 0;
 	return vm_unmapped_area(&info);
@@ -1895,7 +1893,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
-	if (len > TASK_SIZE)
+	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED)
@@ -1905,14 +1903,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
 				(!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
 	addr = vm_unmapped_area(&info);

mm/mprotect.c

@@ -112,6 +112,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
+	unsigned long nr_huge_updates = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -126,9 +127,10 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 						newprot, prot_numa);
 
 				if (nr_ptes) {
-					if (nr_ptes == HPAGE_PMD_NR)
-						pages++;
-
+					if (nr_ptes == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
 					continue;
 				}
 			}
@@ -141,6 +143,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
 }
 

mm/nobootmem.c

@@ -82,27 +82,18 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static void __init __free_pages_memory(unsigned long start, unsigned long end)
 {
-	unsigned long i, start_aligned, end_aligned;
-	int order = ilog2(BITS_PER_LONG);
+	int order;
 
-	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
-	end_aligned = end & ~(BITS_PER_LONG - 1);
+	while (start < end) {
+		order = min(MAX_ORDER - 1UL, __ffs(start));
 
-	if (end_aligned <= start_aligned) {
-		for (i = start; i < end; i++)
-			__free_pages_bootmem(pfn_to_page(i), 0);
+		while (start + (1UL << order) > end)
+			order--;
 
-		return;
+		__free_pages_bootmem(pfn_to_page(start), order);
+
+		start += (1UL << order);
 	}
-
-	for (i = start; i < start_aligned; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
-
-	for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
-		__free_pages_bootmem(pfn_to_page(i), order);
-
-	for (i = end_aligned; i < end; i++)
-		__free_pages_bootmem(pfn_to_page(i), 0);
 }
 
 static unsigned long __init __free_memory_core(phys_addr_t start,

mm/nommu.c

@@ -1948,13 +1948,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some 3% for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover

mm/page_alloc.c

@@ -234,8 +234,8 @@ int page_group_by_mobility_disabled __read_mostly;
 
 void set_pageblock_migratetype(struct page *page, int migratetype)
 {
-
-	if (unlikely(page_group_by_mobility_disabled))
+	if (unlikely(page_group_by_mobility_disabled &&
+		     migratetype < MIGRATE_PCPTYPES))
 		migratetype = MIGRATE_UNMOVABLE;
 
 	set_pageblock_flags_group(page, (unsigned long)migratetype,
@@ -1027,6 +1027,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 {
 	int current_order = page_order(page);
 
+	/*
+	 * When borrowing from MIGRATE_CMA, we need to release the excess
+	 * buddy pages to CMA itself.
+	 */
 	if (is_migrate_cma(fallback_type))
 		return fallback_type;
 
@@ -1091,21 +1095,11 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			list_del(&page->lru);
 			rmv_page_order(page);
 
-			/*
-			 * Borrow the excess buddy pages as well, irrespective
-			 * of whether we stole freepages, or took ownership of
-			 * the pageblock or not.
-			 *
-			 * Exception: When borrowing from MIGRATE_CMA, release
-			 * the excess buddy pages to CMA itself.
-			 */
 			expand(zone, page, order, current_order, area,
-			       is_migrate_cma(migratetype)
-			     ? migratetype : start_migratetype);
+			       new_type);
 
-			trace_mm_page_alloc_extfrag(page, order,
-				current_order, start_migratetype, migratetype,
-				new_type == start_migratetype);
+			trace_mm_page_alloc_extfrag(page, order, current_order,
+				start_migratetype, migratetype, new_type);
 
 			return page;
 		}
@@ -1711,7 +1705,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
  * comments in mmzone.h.  Reduces cache footprint of zonelist scans
  * that have to skip over a lot of full or unallowed zones.
  *
- * If the zonelist cache is present in the passed in zonelist, then
+ * If the zonelist cache is present in the passed zonelist, then
  * returns a pointer to the allowed node mask (either the current
  * tasks mems_allowed, or node_states[N_MEMORY].)
  *
@@ -2593,7 +2587,7 @@ rebalance:
 	 * running out of options and have to consider going OOM
 	 */
 	if (!did_some_progress) {
-		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+		if (oom_gfp_allowed(gfp_mask)) {
 			if (oom_killer_disabled)
 				goto nopage;
 			/* Coredumps can quickly deplete all memory reserves */
@@ -3881,8 +3875,6 @@ static inline unsigned long wait_table_bits(unsigned long size)
 	return ffz(~size);
 }
 
-#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
-
 /*
  * Check if a pageblock contains reserved pages
  */
@@ -4266,7 +4258,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
 	 */
 	zone->pageset = &boot_pageset;
 
-	if (zone->present_pages)
+	if (populated_zone(zone))
 		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
 			zone->name, zone->present_pages,
 					 zone_batchsize(zone));
@@ -5160,7 +5152,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
 
 	for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
-		if (zone->present_pages) {
+		if (populated_zone(zone)) {
 			node_set_state(nid, N_HIGH_MEMORY);
 			if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
 			    zone_type <= ZONE_NORMAL)

mm/readahead.c

@@ -401,6 +401,7 @@ ondemand_readahead(struct address_space *mapping,
 		   unsigned long req_size)
 {
 	unsigned long max = max_sane_readahead(ra->ra_pages);
+	pgoff_t prev_offset;
 
 	/*
 	 * start of file
@@ -452,8 +453,11 @@ ondemand_readahead(struct address_space *mapping,
 
 	/*
 	 * sequential cache miss
+	 * trivial case: (offset - prev_offset) == 1
+	 * unaligned reads: (offset - prev_offset) == 0
 	 */
-	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+	prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT;
+	if (offset - prev_offset <= 1UL)
 		goto initial_readahead;
 
 	/*
@@ -569,7 +573,7 @@ static ssize_t
 do_readahead(struct address_space *mapping, struct file *filp,
 	     pgoff_t index, unsigned long nr)
 {
-	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
+	if (!mapping || !mapping->a_ops)
 		return -EINVAL;
 
 	force_page_cache_readahead(mapping, filp, index, nr);

mm/slab.c

@@ -3982,7 +3982,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 
 	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
 	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(cachep, i);
+		c = cache_from_memcg_idx(cachep, i);
 		if (c)
 			/* return value determined by the parent cache only */
 			__do_tune_cpucache(c, limit, batchcount, shared, gfp);

mm/slab.h

@@ -160,7 +160,8 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	if (!s->memcg_params)
 		return NULL;
@@ -204,7 +205,8 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+static inline struct kmem_cache *
+cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	return NULL;
 }

mm/slab_common.c

@@ -571,7 +571,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 		return;
 
 	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(s, i);
+		c = cache_from_memcg_idx(s, i);
 		if (!c)
 			continue;
 

mm/slub.c

@@ -4983,7 +4983,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		 * through the descendants with best-effort propagation.
 		 */
 		for_each_memcg_cache_index(i) {
-			struct kmem_cache *c = cache_from_memcg(s, i);
+			struct kmem_cache *c = cache_from_memcg_idx(s, i);
 			if (c)
 				attribute->store(c, buf, len);
 		}

mm/sparse.c

@@ -590,33 +590,32 @@ void __init sparse_init(void)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						 unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
 	/* This will make the necessary allocations eventually. */
 	return sparse_mem_map_populate(pnum, nid);
 }
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
 
 	vmemmap_free(start, end);
 }
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
 
 	vmemmap_free(start, end);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #else
-static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+static struct page *__kmalloc_section_memmap(void)
 {
 	struct page *page, *ret;
-	unsigned long memmap_size = sizeof(struct page) * nr_pages;
+	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
 
 	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
 	if (page)
@@ -634,28 +633,30 @@ got_map_ptr:
 	return ret;
 }
 
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						  unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
-	return __kmalloc_section_memmap(nr_pages);
+	return __kmalloc_section_memmap();
 }
 
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	if (is_vmalloc_addr(memmap))
 		vfree(memmap);
 	else
 		free_pages((unsigned long)memmap,
-			   get_order(sizeof(struct page) * nr_pages));
+			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
-	unsigned long magic;
+	unsigned long magic, nr_pages;
 	struct page *page = virt_to_page(memmap);
 
+	nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
+		>> PAGE_SHIFT;
+
 	for (i = 0; i < nr_pages; i++, page++) {
 		magic = (unsigned long) page->lru.next;
 
@@ -684,8 +685,7 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
  * set.  If this is <=0, then that means that the passed-in
  * map was not consumed and must be freed.
  */
-int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
-			   int nr_pages)
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct pglist_data *pgdat = zone->zone_pgdat;
@@ -702,12 +702,12 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	ret = sparse_index_init(section_nr, pgdat->node_id);
 	if (ret < 0 && ret != -EEXIST)
 		return ret;
-	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
 	if (!memmap)
 		return -ENOMEM;
 	usemap = __kmalloc_section_usemap();
 	if (!usemap) {
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 		return -ENOMEM;
 	}
 
@@ -719,7 +719,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
-	memset(memmap, 0, sizeof(struct page) * nr_pages);
+	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
 
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
@@ -729,7 +729,7 @@ out:
 	pgdat_resize_unlock(pgdat, &flags);
 	if (ret <= 0) {
 		kfree(usemap);
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 	}
 	return ret;
 }
@@ -759,7 +759,6 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 {
 	struct page *usemap_page;
-	unsigned long nr_pages;
 
 	if (!usemap)
 		return;
@@ -771,7 +770,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
 		kfree(usemap);
 		if (memmap)
-			__kfree_section_memmap(memmap, PAGES_PER_SECTION);
+			__kfree_section_memmap(memmap);
 		return;
 	}
 
@@ -780,12 +779,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	 * on the section which has pgdat at boot time. Just keep it as is now.
 	 */
 
-	if (memmap) {
-		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
-			>> PAGE_SHIFT;
-
-		free_map_bootmem(memmap, nr_pages);
-	}
+	if (memmap)
+		free_map_bootmem(memmap);
 }
 
 void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)

mm/swapfile.c

@@ -707,7 +707,7 @@ noswap:
 	return (swp_entry_t) {0};
 }
 
-/* The only caller of this function is now susupend routine */
+/* The only caller of this function is now suspend routine */
 swp_entry_t get_swap_page_of_type(int type)
 {
 	struct swap_info_struct *si;
@@ -845,7 +845,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 }
 
 /*
- * Caller has made sure that the swapdevice corresponding to entry
+ * Caller has made sure that the swap device corresponding to entry
  * is still around or has not been recycled.
  */
 void swap_free(swp_entry_t entry)
@@ -947,7 +947,7 @@ int try_to_free_swap(struct page *page)
 	 * original page might be freed under memory pressure, then
 	 * later read back in from swap, now with the wrong data.
 	 *
-	 * Hibration suspends storage while it is writing the image
+	 * Hibernation suspends storage while it is writing the image
 	 * to disk so check that here.
 	 */
 	if (pm_suspended_storage())
@@ -1179,7 +1179,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	 * some architectures (e.g. x86_32 with PAE) we might catch a glimpse
 	 * of unmatched parts which look like swp_pte, so unuse_pte must
 	 * recheck under pte lock.  Scanning without pte lock lets it be
-	 * preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
+	 * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
 	 */
 	pte = pte_offset_map(pmd, addr);
 	do {
@@ -1924,17 +1924,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->cluster_info = NULL;
 	p->flags = 0;
 	frontswap_map = frontswap_map_get(p);
-	frontswap_map_set(p, NULL);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 	frontswap_invalidate_area(type);
+	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
 	free_percpu(p->percpu_cluster);
 	p->percpu_cluster = NULL;
 	vfree(swap_map);
 	vfree(cluster_info);
 	vfree(frontswap_map);
-	/* Destroy swap account informatin */
+	/* Destroy swap account information */
 	swap_cgroup_swapoff(type);
 
 	inode = mapping->host;
@@ -2786,8 +2786,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 
 	/*
 	 * We are fortunate that although vmalloc_to_page uses pte_offset_map,
-	 * no architecture is using highmem pages for kernel pagetables: so it
-	 * will not corrupt the GFP_ATOMIC caller's atomic pagetable kmaps.
+	 * no architecture is using highmem pages for kernel page tables: so it
+	 * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps.
 	 */
 	head = vmalloc_to_page(si->swap_map + offset);
 	offset &= ~PAGE_MASK;

mm/util.c

@@ -7,6 +7,9 @@
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mman.h>
+#include <linux/hugetlb.h>
+
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -398,6 +401,16 @@ struct address_space *page_mapping(struct page *page)
 	return mapping;
 }
 
+/*
+ * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
+ */
+unsigned long vm_commit_limit(void)
+{
+	return ((totalram_pages - hugetlb_total_pages())
+		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+}
+
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);

mm/vmalloc.c

@@ -359,6 +359,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	if (unlikely(!va))
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Only scan the relevant parts containing pointers to other objects
+	 * to avoid false negatives.
+	 */
+	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
+
 retry:
 	spin_lock(&vmap_area_lock);
 	/*
@@ -1546,7 +1552,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node, const void *caller)
+				 pgprot_t prot, int node)
 {
 	const int order = 0;
 	struct page **pages;
@@ -1560,13 +1566,12 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
 		pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM,
-				PAGE_KERNEL, node, caller);
+				PAGE_KERNEL, node, area->caller);
 		area->flags |= VM_VPAGES;
 	} else {
 		pages = kmalloc_node(array_size, nested_gfp, node);
 	}
 	area->pages = pages;
-	area->caller = caller;
 	if (!area->pages) {
 		remove_vm_area(area->addr);
 		kfree(area);
@@ -1577,7 +1582,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		struct page *page;
 		gfp_t tmp_mask = gfp_mask | __GFP_NOWARN;
 
-		if (node < 0)
+		if (node == NUMA_NO_NODE)
 			page = alloc_page(tmp_mask);
 		else
 			page = alloc_pages_node(node, tmp_mask, order);
@@ -1634,9 +1639,9 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!area)
 		goto fail;
 
-	addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
 	if (!addr)
-		goto fail;
+		return NULL;
 
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -1646,11 +1651,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	clear_vm_uninitialized_flag(area);
 
 	/*
-	 * A ref_count = 3 is needed because the vm_struct and vmap_area
-	 * structures allocated in the __get_vm_area_node() function contain
-	 * references to the virtual address of the vmalloc'ed block.
+	 * A ref_count = 2 is needed because vm_struct allocated in
+	 * __get_vm_area_node() contains a reference to the virtual address of
+	 * the vmalloc'ed block.
 	 */
-	kmemleak_alloc(addr, real_size, 3, gfp_mask);
+	kmemleak_alloc(addr, real_size, 2, gfp_mask);
 
 	return addr;
 
@@ -2563,6 +2568,11 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 		if (!counters)
 			return;
 
+		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
+		smp_rmb();
+		if (v->flags & VM_UNINITIALIZED)
+			return;
+
 		memset(counters, 0, nr_node_ids * sizeof(unsigned int));
 
 		for (nr = 0; nr < v->nr_pages; nr++)
@@ -2579,23 +2589,15 @@ static int s_show(struct seq_file *m, void *p)
 	struct vmap_area *va = p;
 	struct vm_struct *v;
 
-	if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
+	/*
+	 * s_show can encounter race with remove_vm_area, !VM_VM_AREA on
+	 * behalf of vmap area is being tear down or vm_map_ram allocation.
+	 */
+	if (!(va->flags & VM_VM_AREA))
 		return 0;
 
-	if (!(va->flags & VM_VM_AREA)) {
-		seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
-			(void *)va->va_start, (void *)va->va_end,
-					va->va_end - va->va_start);
-		return 0;
-	}
-
 	v = va->vm;
 
-	/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
-	smp_rmb();
-	if (v->flags & VM_UNINITIALIZED)
-		return 0;
-
 	seq_printf(m, "0x%pK-0x%pK %7ld",
 		v->addr, v->addr + v->size, v->size);
 

mm/vmstat.c

@@ -812,6 +812,7 @@ const char * const vmstat_text[] = {
 
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
+	"numa_huge_pte_updates",
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
@@ -1229,6 +1230,20 @@ static void start_cpu_timer(int cpu)
 	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
 }
 
+static void vmstat_cpu_dead(int node)
+{
+	int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu)
+		if (cpu_to_node(cpu) == node)
+			goto end;
+
+	node_clear_state(node, N_CPU);
+end:
+	put_online_cpus();
+}
+
 /*
  * Use the cpu notifier to insure that the thresholds are recalculated
  * when necessary.
@@ -1258,6 +1273,7 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		refresh_zone_stat_thresholds();
+		vmstat_cpu_dead(cpu_to_node(cpu));
 		break;
 	default:
 		break;
@@ -1276,8 +1292,12 @@ static int __init setup_vmstat(void)
 
 	register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu)
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
 		start_cpu_timer(cpu);
+		node_set_state(cpu_to_node(cpu), N_CPU);
+	}
+	put_online_cpus();
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);

mm/zswap.c

@@ -217,6 +217,7 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
+	RB_CLEAR_NODE(&entry->rbnode);
 	return entry;
 }
 
@@ -225,19 +226,6 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
-/* caller must hold the tree lock */
-static void zswap_entry_get(struct zswap_entry *entry)
-{
-	entry->refcount++;
-}
-
-/* caller must hold the tree lock */
-static int zswap_entry_put(struct zswap_entry *entry)
-{
-	entry->refcount--;
-	return entry->refcount;
-}
-
 /*********************************
 * rbtree functions
 **********************************/
@@ -285,6 +273,61 @@ static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
 	return 0;
 }
 
+static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
+{
+	if (!RB_EMPTY_NODE(&entry->rbnode)) {
+		rb_erase(&entry->rbnode, root);
+		RB_CLEAR_NODE(&entry->rbnode);
+	}
+}
+
+/*
+ * Carries out the common pattern of freeing and entry's zsmalloc allocation,
+ * freeing the entry itself, and decrementing the number of stored pages.
+ */
+static void zswap_free_entry(struct zswap_tree *tree,
+			struct zswap_entry *entry)
+{
+	zbud_free(tree->pool, entry->handle);
+	zswap_entry_cache_free(entry);
+	atomic_dec(&zswap_stored_pages);
+	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+}
+
+/* caller must hold the tree lock */
+static void zswap_entry_get(struct zswap_entry *entry)
+{
+	entry->refcount++;
+}
+
+/* caller must hold the tree lock
+* remove from the tree and free it, if nobody reference the entry
+*/
+static void zswap_entry_put(struct zswap_tree *tree,
+			struct zswap_entry *entry)
+{
+	int refcount = --entry->refcount;
+
+	BUG_ON(refcount < 0);
+	if (refcount == 0) {
+		zswap_rb_erase(&tree->rbroot, entry);
+		zswap_free_entry(tree, entry);
+	}
+}
+
+/* caller must hold the tree lock */
+static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
+				pgoff_t offset)
+{
+	struct zswap_entry *entry = NULL;
+
+	entry = zswap_rb_search(root, offset);
+	if (entry)
+		zswap_entry_get(entry);
+
+	return entry;
+}
+
 /*********************************
 * per-cpu code
 **********************************/
@@ -368,18 +411,6 @@ static bool zswap_is_full(void)
 		zswap_pool_pages);
 }
 
-/*
- * Carries out the common pattern of freeing and entry's zsmalloc allocation,
- * freeing the entry itself, and decrementing the number of stored pages.
- */
-static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
-{
-	zbud_free(tree->pool, entry->handle);
-	zswap_entry_cache_free(entry);
-	atomic_dec(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
-}
-
 /*********************************
 * writeback code
 **********************************/
@@ -387,7 +418,7 @@ static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
 enum zswap_get_swap_ret {
 	ZSWAP_SWAPCACHE_NEW,
 	ZSWAP_SWAPCACHE_EXIST,
-	ZSWAP_SWAPCACHE_NOMEM
+	ZSWAP_SWAPCACHE_FAIL,
 };
 
 /*
@@ -401,9 +432,10 @@ enum zswap_get_swap_ret {
  * added to the swap cache, and returned in retpage.
  *
  * If success, the swap cache page is returned in retpage
- * Returns 0 if page was already in the swap cache, page is not locked
- * Returns 1 if the new page needs to be populated, page is locked
- * Returns <0 on error
+ * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
+ * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
+ *     the new page is added to swapcache and locked
+ * Returns ZSWAP_SWAPCACHE_FAIL on error
  */
 static int zswap_get_swap_cache_page(swp_entry_t entry,
 				struct page **retpage)
@@ -475,7 +507,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 	if (new_page)
 		page_cache_release(new_page);
 	if (!found_page)
-		return ZSWAP_SWAPCACHE_NOMEM;
+		return ZSWAP_SWAPCACHE_FAIL;
 	*retpage = found_page;
 	return ZSWAP_SWAPCACHE_EXIST;
 }
@@ -502,7 +534,7 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	struct page *page;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int ret, refcount;
+	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
@@ -517,23 +549,22 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 
 	/* find and ref zswap entry */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
 		return 0;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 	BUG_ON(offset != entry->offset);
 
 	/* try to allocate swap cache page */
 	switch (zswap_get_swap_cache_page(swpentry, &page)) {
-	case ZSWAP_SWAPCACHE_NOMEM: /* no memory */
+	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
 		ret = -ENOMEM;
 		goto fail;
 
-	case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */
+	case ZSWAP_SWAPCACHE_EXIST:
 		/* page is already in the swap cache, ignore for now */
 		page_cache_release(page);
 		ret = -EEXIST;
@@ -556,43 +587,44 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 		SetPageUptodate(page);
 	}
 
+	/* move it to the tail of the inactive list after end_writeback */
+	SetPageReclaim(page);
+
 	/* start writeback */
 	__swap_writepage(page, &wbc, end_swap_bio_write);
 	page_cache_release(page);
 	zswap_written_back_pages++;
 
 	spin_lock(&tree->lock);
-
 	/* drop local reference */
-	zswap_entry_put(entry);
-	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	/*
-	 * There are three possible values for refcount here:
-	 * (1) refcount is 1, load is in progress, unlink from rbtree,
-	 *     load will free
-	 * (2) refcount is 0, (normal case) entry is valid,
-	 *     remove from rbtree and free entry
-	 * (3) refcount is -1, invalidate happened during writeback,
-	 *     free entry
-	 */
-	if (refcount >= 0) {
-		/* no invalidate yet, remove from rbtree */
-		rb_erase(&entry->rbnode, &tree->rbroot);
-	}
+	* There are two possible situations for entry here:
+	* (1) refcount is 1(normal case),  entry is valid and on the tree
+	* (2) refcount is 0, entry is freed and not on the tree
+	*     because invalidate happened during writeback
+	*  search the tree and free the entry if find entry
+	*/
+	if (entry == zswap_rb_search(&tree->rbroot, offset))
+		zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
-	if (refcount <= 0) {
-		/* free the entry */
-		zswap_free_entry(tree, entry);
-		return 0;
-	}
-	return -EAGAIN;
 
+	goto end;
+
+	/*
+	* if we get here due to ZSWAP_SWAPCACHE_EXIST
+	* a load may happening concurrently
+	* it is safe and okay to not free the entry
+	* if we free the entry in the following put
+	* it it either okay to return !0
+	*/
 fail:
 	spin_lock(&tree->lock);
-	zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
+
+end:
 	return ret;
 }
 
@@ -676,11 +708,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		if (ret == -EEXIST) {
 			zswap_duplicate_entry++;
 			/* remove from rbtree */
-			rb_erase(&dupentry->rbnode, &tree->rbroot);
-			if (!zswap_entry_put(dupentry)) {
-				/* free */
-				zswap_free_entry(tree, dupentry);
-			}
+			zswap_rb_erase(&tree->rbroot, dupentry);
+			zswap_entry_put(tree, dupentry);
 		}
 	} while (ret == -EEXIST);
 	spin_unlock(&tree->lock);
@@ -709,17 +738,16 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	struct zswap_entry *entry;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int refcount, ret;
+	int ret;
 
 	/* find */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was written back */
 		spin_unlock(&tree->lock);
 		return -1;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
 	/* decompress */
@@ -734,22 +762,9 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	BUG_ON(ret);
 
 	spin_lock(&tree->lock);
-	refcount = zswap_entry_put(entry);
-	if (likely(refcount)) {
-		spin_unlock(&tree->lock);
-		return 0;
-	}
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	/*
-	 * We don't have to unlink from the rbtree because
-	 * zswap_writeback_entry() or zswap_frontswap_invalidate page()
-	 * has already done this for us if we are the last reference.
-	 */
-	/* free */
-
-	zswap_free_entry(tree, entry);
-
 	return 0;
 }
 
@@ -758,7 +773,6 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	int refcount;
 
 	/* find */
 	spin_lock(&tree->lock);
@@ -770,20 +784,12 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 	}
 
 	/* remove from rbtree */
-	rb_erase(&entry->rbnode, &tree->rbroot);
+	zswap_rb_erase(&tree->rbroot, entry);
 
 	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	spin_unlock(&tree->lock);
-
-	if (refcount) {
-		/* writeback in progress, writeback will free */
-		return;
-	}
-
-	/* free */
-	zswap_free_entry(tree, entry);
 }
 
 /* frees all zswap entries for the given swap type */
@@ -797,11 +803,8 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 
 	/* walk the tree and free everything */
 	spin_lock(&tree->lock);
-	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) {
-		zbud_free(tree->pool, entry->handle);
-		zswap_entry_cache_free(entry);
-		atomic_dec(&zswap_stored_pages);
-	}
+	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
+		zswap_free_entry(tree, entry);
 	tree->rbroot = RB_ROOT;
 	spin_unlock(&tree->lock);