42 files changed, 3989 insertions, 2247 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 57963c6063d..43ea8c3a2bb 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -67,7 +67,7 @@ config DISCONTIGMEM
 
 config SPARSEMEM
 	def_bool y
-	depends on SPARSEMEM_MANUAL
+	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
 
 config FLATMEM
 	def_bool y
@@ -128,11 +128,8 @@ config SPARSEMEM_VMEMMAP
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
-	depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
-	depends on (IA64 || X86 || PPC64 || SUPERH || S390)
-
-comment "Memory hotplug is currently incompatible with Software Suspend"
-	depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
+	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
@@ -161,11 +158,13 @@ config PAGEFLAGS_EXTENDED
 # Default to 4 for wider testing, though 8 might be more appropriate.
 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
+# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
 #
 config SPLIT_PTLOCK_CPUS
 	int
-	default "4096" if ARM && !CPU_CACHE_VIPT
-	default "4096" if PARISC && !PA20
+	default "999999" if ARM && !CPU_CACHE_VIPT
+	default "999999" if PARISC && !PA20
+	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
 	default "4"
 
 #
@@ -203,14 +202,6 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
-config HAVE_MLOCK
-	bool
-	default y if MMU=y
-
-config HAVE_MLOCKED_PAGE_BIT
-	bool
-	default y if HAVE_MLOCK=y
-
 config MMU_NOTIFIER
 	bool
 
@@ -221,7 +212,7 @@ config KSM
 	  Enable Kernel Samepage Merging: KSM periodically scans those areas
 	  of an application's address space that an app has advised may be
 	  mergeable.  When it finds pages of identical content, it replaces
-	  the many instances by a single resident page with that content, so
+	  the many instances by a single page with that content, so
 	  saving memory until one or another app needs to modify the content.
 	  Recommended for use with KVM, or with other duplicative applications.
 	  See Documentation/vm/ksm.txt for more information: KSM is inactive
@@ -260,8 +251,9 @@ config MEMORY_FAILURE
 	  special hardware support and typically ECC memory.
 
 config HWPOISON_INJECT
-	tristate "Poison pages injector"
+	tristate "HWPoison pages injector"
 	depends on MEMORY_FAILURE && DEBUG_KERNEL
+	select PROC_PAGE_MONITOR
 
 config NOMMU_INITIAL_TRIM_EXCESS
 	int "Turn on mmap() excess space trimming before booting"
diff --git a/mm/Makefile b/mm/Makefile
index ebf849042ed..7a68d2ab556 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -22,7 +22,6 @@ obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
-obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_KSM) += ksm.o
@@ -34,11 +33,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 obj-$(CONFIG_SMP) += percpu.o
-else
-obj-$(CONFIG_SMP) += allocpercpu.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
deleted file mode 100644
index df34ceae0c6..00000000000
--- a/mm/allocpercpu.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * linux/mm/allocpercpu.c
- *
- * Separated from slab.c August 11, 2006 Christoph Lameter
- */
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/bootmem.h>
-#include <asm/sections.h>
-
-#ifndef cache_line_size
-#define cache_line_size()	L1_CACHE_BYTES
-#endif
-
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-static void percpu_depopulate(void *__pdata, int cpu)
-{
-	struct percpu_data *pdata = __percpu_disguise(__pdata);
-
-	kfree(pdata->ptrs[cpu]);
-	pdata->ptrs[cpu] = NULL;
-}
-
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
-{
-	int cpu;
-	for_each_cpu_mask_nr(cpu, *mask)
-		percpu_depopulate(__pdata, cpu);
-}
-
-#define percpu_depopulate_mask(__pdata, mask) \
-	__percpu_depopulate_mask((__pdata), &(mask))
-
-/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
- *
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
- */
-static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
-{
-	struct percpu_data *pdata = __percpu_disguise(__pdata);
-	int node = cpu_to_node(cpu);
-
-	/*
-	 * We should make sure each CPU gets private memory.
-	 */
-	size = roundup(size, cache_line_size());
-
-	BUG_ON(pdata->ptrs[cpu]);
-	if (node_online(node))
-		pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
-	else
-		pdata->ptrs[cpu] = kzalloc(size, gfp);
-	return pdata->ptrs[cpu];
-}
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
-				  cpumask_t *mask)
-{
-	cpumask_t populated;
-	int cpu;
-
-	cpus_clear(populated);
-	for_each_cpu_mask_nr(cpu, *mask)
-		if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
-			__percpu_depopulate_mask(__pdata, &populated);
-			return -ENOMEM;
-		} else
-			cpu_set(cpu, populated);
-	return 0;
-}
-
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
-	__percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-
-/**
- * alloc_percpu - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @align: alignment
- *
- * Allocate dynamic percpu area.  Percpu objects are populated with
- * zeroed buffers.
- */
-void *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * We allocate whole cache lines to avoid false sharing
-	 */
-	size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
-	void *pdata = kzalloc(sz, GFP_KERNEL);
-	void *__pdata = __percpu_disguise(pdata);
-
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-
-	if (unlikely(!pdata))
-		return NULL;
-	if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
-					   &cpu_possible_map)))
-		return __pdata;
-	kfree(pdata);
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * free_percpu - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void free_percpu(void *__pdata)
-{
-	if (unlikely(!__pdata))
-		return;
-	__percpu_depopulate_mask(__pdata, cpu_possible_mask);
-	kfree(__percpu_disguise(__pdata));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-/*
- * Generic percpu area setup.
- */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-void __init setup_per_cpu_areas(void)
-{
-	unsigned long size, i;
-	char *ptr;
-	unsigned long nr_possible_cpus = num_possible_cpus();
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
-	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
-	for_each_possible_cpu(i) {
-		__per_cpu_offset[i] = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-		ptr += size;
-	}
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 5a37e205571..0e8ca034770 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -604,15 +604,36 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 
 	/*
 	 * Finally, kill the kernel threads. We don't need to be RCU
-	 * safe anymore, since the bdi is gone from visibility.
+	 * safe anymore, since the bdi is gone from visibility. Force
+	 * unfreeze of the thread before calling kthread_stop(), otherwise
+	 * it would never exet if it is currently stuck in the refrigerator.
 	 */
-	list_for_each_entry(wb, &bdi->wb_list, list)
+	list_for_each_entry(wb, &bdi->wb_list, list) {
+		thaw_process(wb->task);
 		kthread_stop(wb->task);
+	}
+}
+
+/*
+ * This bdi is going away now, make sure that no super_blocks point to it
+ */
+static void bdi_prune_sb(struct backing_dev_info *bdi)
+{
+	struct super_block *sb;
+
+	spin_lock(&sb_lock);
+	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (sb->s_bdi == bdi)
+			sb->s_bdi = NULL;
+	}
+	spin_unlock(&sb_lock);
 }
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_prune_sb(bdi);
+
 		if (!bdi_cap_flush_forker(bdi))
 			bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 555d5d2731c..7d1486875e1 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -143,6 +143,30 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
 
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system.  Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long addr, unsigned long size)
+{
+	unsigned long cursor, end;
+
+	kmemleak_free_part(__va(addr), size);
+
+	cursor = PFN_UP(addr);
+	end = PFN_DOWN(addr + size);
+
+	for (; cursor < end; cursor++) {
+		__free_pages_bootmem(pfn_to_page(cursor), 0);
+		totalram_pages++;
+	}
+}
+
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	int aligned;
@@ -408,8 +432,8 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 	return mark_bootmem(start, end, 1, flags);
 }
 
-static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx,
-			unsigned long step)
+static unsigned long __init align_idx(struct bootmem_data *bdata,
+				      unsigned long idx, unsigned long step)
 {
 	unsigned long base = bdata->node_min_pfn;
 
@@ -421,8 +445,8 @@ static unsigned long align_idx(struct bootmem_data *bdata, unsigned long idx,
 	return ALIGN(base + idx, step) - base;
 }
 
-static unsigned long align_off(struct bootmem_data *bdata, unsigned long off,
-			unsigned long align)
+static unsigned long __init align_off(struct bootmem_data *bdata,
+				      unsigned long off, unsigned long align)
 {
 	unsigned long base = PFN_PHYS(bdata->node_min_pfn);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index ef169f37156..96ac6b0eb6c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -260,27 +260,27 @@ int filemap_flush(struct address_space *mapping)
 EXPORT_SYMBOL(filemap_flush);
 
 /**
- * wait_on_page_writeback_range - wait for writeback to complete
- * @mapping:	target address_space
- * @start:	beginning page index
- * @end:	ending page index
+ * filemap_fdatawait_range - wait for writeback to complete
+ * @mapping:		address space structure to wait for
+ * @start_byte:		offset in bytes where the range starts
+ * @end_byte:		offset in bytes where the range ends (inclusive)
  *
- * Wait for writeback to complete against pages indexed by start->end
- * inclusive
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.
  */
-int wait_on_page_writeback_range(struct address_space *mapping,
-				pgoff_t start, pgoff_t end)
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
+			    loff_t end_byte)
 {
+	pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;
+	pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
 	struct pagevec pvec;
 	int nr_pages;
 	int ret = 0;
-	pgoff_t index;
 
-	if (end < start)
+	if (end_byte < start_byte)
 		return 0;
 
 	pagevec_init(&pvec, 0);
-	index = start;
 	while ((index <= end) &&
 			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
 			PAGECACHE_TAG_WRITEBACK,
@@ -310,25 +310,6 @@ int wait_on_page_writeback_range(struct address_space *mapping,
 
 	return ret;
 }
-
-/**
- * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range
- * @mapping: address space structure to wait for
- * @start:	offset in bytes where the range starts
- * @end:	offset in bytes where the range ends (inclusive)
- *
- * Walk the list of under-writeback pages of the given address space
- * in the given range and wait for all of them.
- *
- * This is just a simple wrapper so that callers don't have to convert offsets
- * to page indexes themselves
- */
-int filemap_fdatawait_range(struct address_space *mapping, loff_t start,
-			    loff_t end)
-{
-	return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT,
-					    end >> PAGE_CACHE_SHIFT);
-}
 EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
@@ -345,8 +326,7 @@ int filemap_fdatawait(struct address_space *mapping)
 	if (i_size == 0)
 		return 0;
 
-	return wait_on_page_writeback_range(mapping, 0,
-				(i_size - 1) >> PAGE_CACHE_SHIFT);
+	return filemap_fdatawait_range(mapping, 0, i_size - 1);
 }
 EXPORT_SYMBOL(filemap_fdatawait);
 
@@ -393,9 +373,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
 		if (err != -EIO) {
-			int err2 = wait_on_page_writeback_range(mapping,
-						lstart >> PAGE_CACHE_SHIFT,
-						lend >> PAGE_CACHE_SHIFT);
+			int err2 = filemap_fdatawait_range(mapping,
+						lstart, lend);
 			if (!err)
 				err = err2;
 		}
@@ -1844,7 +1823,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 
 /*
  * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then return the number of
+ * were successfully copied.  If a fault is encountered then return the number of
  * bytes which were copied.
  */
 size_t iov_iter_copy_from_user_atomic(struct page *page,
@@ -2261,7 +2240,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 		size_t count, ssize_t written)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
 	ssize_t status;
 	struct iov_iter i;
 
@@ -2273,15 +2251,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 		*ppos = pos + status;
   	}
 	
-	/*
-	 * If we get here for O_DIRECT writes then we must have fallen through
-	 * to buffered writes (block instantiation inside i_size).  So we sync
-	 * the file data here, to try to honour O_DIRECT expectations.
-	 */
-	if (unlikely(file->f_flags & O_DIRECT) && written)
-		status = filemap_write_and_wait_range(mapping,
-					pos, pos + written - 1);
-
 	return written ? written : status;
 }
 EXPORT_SYMBOL(generic_file_buffered_write);
@@ -2380,10 +2349,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		 * semantics.
 		 */
 		endbyte = pos + written_buffered - written - 1;
-		err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
-					    SYNC_FILE_RANGE_WAIT_BEFORE|
-					    SYNC_FILE_RANGE_WRITE|
-					    SYNC_FILE_RANGE_WAIT_AFTER);
+		err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
 		if (err == 0) {
 			written = written_buffered;
 			invalidate_mapping_pages(mapping,
diff --git a/mm/highmem.c b/mm/highmem.c
index 25878cc49da..9c1e627f282 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -426,16 +426,21 @@ void __init page_address_init(void)
 
 void debug_kmap_atomic(enum km_type type)
 {
-	static unsigned warn_count = 10;
+	static int warn_count = 10;
 
-	if (unlikely(warn_count == 0))
+	if (unlikely(warn_count < 0))
 		return;
 
 	if (unlikely(in_interrupt())) {
-		if (in_irq()) {
+		if (in_nmi()) {
+			if (type != KM_NMI && type != KM_NMI_PTE) {
+				WARN_ON(1);
+				warn_count--;
+			}
+		} else if (in_irq()) {
 			if (type != KM_IRQ0 && type != KM_IRQ1 &&
 			    type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
-			    type != KM_BOUNCE_READ) {
+			    type != KM_BOUNCE_READ && type != KM_IRQ_PTE) {
 				WARN_ON(1);
 				warn_count--;
 			}
@@ -452,7 +457,9 @@ void debug_kmap_atomic(enum km_type type)
 	}
 
 	if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
-			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
+			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ ||
+			type == KM_IRQ_PTE || type == KM_NMI ||
+			type == KM_NMI_PTE ) {
 		if (!irqs_disabled()) {
 			WARN_ON(1);
 			warn_count--;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5d7601b0287..65f38c21820 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -24,6 +24,7 @@
 #include <asm/io.h>
 
 #include <linux/hugetlb.h>
+#include <linux/node.h>
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
@@ -622,42 +623,66 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 }
 
 /*
- * Use a helper variable to find the next node and then
- * copy it back to next_nid_to_alloc afterwards:
- * otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
- * But we don't need to use a spin_lock here: it really
- * doesn't matter if occasionally a racer chooses the
- * same nid as we do.  Move nid forward in the mask even
- * if we just successfully allocated a hugepage so that
- * the next caller gets hugepages on the next node.
+ * common helper functions for hstate_next_node_to_{alloc|free}.
+ * We may have allocated or freed a huge page based on a different
+ * nodes_allowed previously, so h->next_node_to_{alloc|free} might
+ * be outside of *nodes_allowed.  Ensure that we use an allowed
+ * node for alloc or free.
  */
-static int hstate_next_node_to_alloc(struct hstate *h)
+static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
 {
-	int next_nid;
-	next_nid = next_node(h->next_nid_to_alloc, node_online_map);
-	if (next_nid == MAX_NUMNODES)
-		next_nid = first_node(node_online_map);
-	h->next_nid_to_alloc = next_nid;
-	return next_nid;
+	nid = next_node(nid, *nodes_allowed);
+	if (nid == MAX_NUMNODES)
+		nid = first_node(*nodes_allowed);
+	VM_BUG_ON(nid >= MAX_NUMNODES);
+
+	return nid;
+}
+
+static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
+{
+	if (!node_isset(nid, *nodes_allowed))
+		nid = next_node_allowed(nid, nodes_allowed);
+	return nid;
+}
+
+/*
+ * returns the previously saved node ["this node"] from which to
+ * allocate a persistent huge page for the pool and advance the
+ * next node from which to allocate, handling wrap at end of node
+ * mask.
+ */
+static int hstate_next_node_to_alloc(struct hstate *h,
+					nodemask_t *nodes_allowed)
+{
+	int nid;
+
+	VM_BUG_ON(!nodes_allowed);
+
+	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
+	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);
+
+	return nid;
 }
 
-static int alloc_fresh_huge_page(struct hstate *h)
+static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 {
 	struct page *page;
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = h->next_nid_to_alloc;
+	start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
 	next_nid = start_nid;
 
 	do {
 		page = alloc_fresh_huge_page_node(h, next_nid);
-		if (page)
+		if (page) {
 			ret = 1;
-		next_nid = hstate_next_node_to_alloc(h);
-	} while (!page && next_nid != start_nid);
+			break;
+		}
+		next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
+	} while (next_nid != start_nid);
 
 	if (ret)
 		count_vm_event(HTLB_BUDDY_PGALLOC);
@@ -668,17 +693,21 @@ static int alloc_fresh_huge_page(struct hstate *h)
 }
 
 /*
- * helper for free_pool_huge_page() - find next node
- * from which to free a huge page
+ * helper for free_pool_huge_page() - return the previously saved
+ * node ["this node"] from which to free a huge page.  Advance the
+ * next node id whether or not we find a free huge page to free so
+ * that the next attempt to free addresses the next node.
  */
-static int hstate_next_node_to_free(struct hstate *h)
+static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 {
-	int next_nid;
-	next_nid = next_node(h->next_nid_to_free, node_online_map);
-	if (next_nid == MAX_NUMNODES)
-		next_nid = first_node(node_online_map);
-	h->next_nid_to_free = next_nid;
-	return next_nid;
+	int nid;
+
+	VM_BUG_ON(!nodes_allowed);
+
+	nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
+	h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
+
+	return nid;
 }
 
 /*
@@ -687,13 +716,14 @@ static int hstate_next_node_to_free(struct hstate *h)
  * balanced over allowed nodes.
  * Called with hugetlb_lock locked.
  */
-static int free_pool_huge_page(struct hstate *h, bool acct_surplus)
+static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
+							 bool acct_surplus)
 {
 	int start_nid;
 	int next_nid;
 	int ret = 0;
 
-	start_nid = h->next_nid_to_free;
+	start_nid = hstate_next_node_to_free(h, nodes_allowed);
 	next_nid = start_nid;
 
 	do {
@@ -715,9 +745,10 @@ static int free_pool_huge_page(struct hstate *h, bool acct_surplus)
 			}
 			update_and_free_page(h, page);
 			ret = 1;
+			break;
 		}
-		next_nid = hstate_next_node_to_free(h);
-	} while (!ret && next_nid != start_nid);
+		next_nid = hstate_next_node_to_free(h, nodes_allowed);
+	} while (next_nid != start_nid);
 
 	return ret;
 }
@@ -911,14 +942,14 @@ static void return_unused_surplus_pages(struct hstate *h,
 
 	/*
 	 * We want to release as many surplus pages as possible, spread
-	 * evenly across all nodes. Iterate across all nodes until we
-	 * can no longer free unreserved surplus pages. This occurs when
-	 * the nodes with surplus pages have no free pages.
-	 * free_pool_huge_page() will balance the the frees across the
-	 * on-line nodes for us and will handle the hstate accounting.
+	 * evenly across all nodes with memory. Iterate across these nodes
+	 * until we can no longer free unreserved surplus pages. This occurs
+	 * when the nodes with surplus pages have no free pages.
+	 * free_pool_huge_page() will balance the the freed pages across the
+	 * on-line nodes with memory and will handle the hstate accounting.
 	 */
 	while (nr_pages--) {
-		if (!free_pool_huge_page(h, 1))
+		if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1))
 			break;
 	}
 }
@@ -1022,16 +1053,16 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 int __weak alloc_bootmem_huge_page(struct hstate *h)
 {
 	struct huge_bootmem_page *m;
-	int nr_nodes = nodes_weight(node_online_map);
+	int nr_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);