Merge branch 'akpm' (more incoming from Andrew)

Merge second patch-bomb from Andrew Morton:

 - A little DM fix

 - the MM queue

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (154 commits)
  ksm: allocate roots when needed
  mm: cleanup "swapcache" in do_swap_page
  mm,ksm: swapoff might need to copy
  mm,ksm: FOLL_MIGRATION do migration_entry_wait
  ksm: shrink 32-bit rmap_item back to 32 bytes
  ksm: treat unstable nid like in stable tree
  ksm: add some comments
  tmpfs: fix mempolicy object leaks
  tmpfs: fix use-after-free of mempolicy object
  mm/fadvise.c: drain all pagevecs if POSIX_FADV_DONTNEED fails to discard all pages
  mm: export mmu notifier invalidates
  mm: accelerate mm_populate() treatment of THP pages
  mm: use long type for page counts in mm_populate() and get_user_pages()
  mm: accurately document nr_free_*_pages functions with code comments
  HWPOISON: change order of error_states[]'s elements
  HWPOISON: fix misjudgement of page_action() for errors on mlocked pages
  memcg: stop warning on memcg_propagate_kmem
  net: change type of virtio_chan->p9_max_pages
  vmscan: change type of vm_total_pages to unsigned long
  fs/nfsd: change type of max_delegations, nfsd_drc_max_mem and nfsd_drc_mem_used
  ...

23 files changed, 673 insertions, 44 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f4dd585898c5..224b44ab534e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -434,4 +434,7 @@ int __meminit vmemmap_populate(struct page *start_page,
 	return 0;
 }
 #endif	/* CONFIG_ARM64_64K_PAGES */
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
 #endif	/* CONFIG_SPARSEMEM_VMEMMAP */
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 1516d1dc11fd..80dab509dfb0 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -93,7 +93,7 @@ void show_mem(unsigned int filter)
 	printk(KERN_INFO "%d pages swap cached\n", total_cached);
 	printk(KERN_INFO "Total of %ld pages in page table cache\n",
 	       quicklist_total_size());
-	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
 }
 
 
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index c641333cd997..c2e955ee79a8 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -666,7 +666,7 @@ void show_mem(unsigned int filter)
 	printk(KERN_INFO "%d pages swap cached\n", total_cached);
 	printk(KERN_INFO "Total of %ld pages in page table cache\n",
 	       quicklist_total_size());
-	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
 }
 
 /**
@@ -822,4 +822,8 @@ int __meminit vmemmap_populate(struct page *start_page,
 {
 	return vmemmap_populate_basepages(start_page, size, node);
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index b755ea92aea7..20bc967c7209 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -688,6 +688,24 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return ret;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	ret = __remove_pages(zone, start_pfn, nr_pages);
+	if (ret)
+		pr_warn("%s: Problem encountered in __remove_pages() as"
+			" ret=%d\n", __func__,  ret);
+
+	return ret;
+}
+#endif
 #endif
 
 /*
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 95a45293e5ac..7e2246fb2f31 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -297,5 +297,10 @@ int __meminit vmemmap_populate(struct page *start_page,
 
 	return 0;
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 40df7c8f2096..f1f7409a4183 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -133,6 +133,18 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	return __remove_pages(zone, start_pfn, nr_pages);
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 /*
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ae672f41c464..49ce6bb2c641 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -228,4 +228,16 @@ int arch_add_memory(int nid, u64 start, u64 size)
 		vmem_remove_mapping(start, size);
 	return rc;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/*
+	 * There is no hardware or firmware interface which could trigger a
+	 * hot memory remove on s390. So there is nothing that needs to be
+	 * implemented.
+	 */
+	return -EBUSY;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 79699f46a443..e21aaf4f5cb6 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -268,6 +268,10 @@ out:
 	return ret;
 }
 
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 /*
  * Add memory segment to the segment list if it doesn't overlap with
  * an already present segment.
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 82cc576fab15..105794037143 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -558,4 +558,21 @@ int memory_add_physaddr_to_nid(u64 addr)
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	ret = __remove_pages(zone, start_pfn, nr_pages);
+	if (unlikely(ret))
+		pr_warn("%s: Failed, __remove_pages() == %d\n", __func__,
+			ret);
+
+	return ret;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index dde85ef1c56d..48e0c030e8f5 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -57,7 +57,7 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 	printk("Free swap:       %6ldkB\n",
-	       nr_swap_pages << (PAGE_SHIFT-10));
+	       get_nr_swap_pages() << (PAGE_SHIFT-10));
 	printk("%ld pages of RAM\n", totalram_pages);
 	printk("%ld free pages\n", nr_free_pages());
 }
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5c2c6e61facb..1588d33d5492 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2235,6 +2235,11 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 3cfa98bf9125..743c951c61b0 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -130,7 +130,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (!retval) {
 		unsigned long addr = MEM_USER_INTRPT;
 		addr = mmap_region(NULL, addr, INTRPT_SIZE,
-				   MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE,
 				   VM_READ|VM_EXEC|
 				   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0);
 		if (addr > (unsigned long) -PAGE_SIZE)
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index ef29d6c5e10e..2749515a0547 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -935,6 +935,14 @@ int remove_memory(u64 start, u64 size)
 {
 	return -EINVAL;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/* TODO */
+	return -EBUSY;
+}
+#endif
 #endif
 
 struct kmem_cache *pgd_cache;
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index de0de0c0e8a1..b3b4972c2451 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -61,7 +61,7 @@ void show_mem(unsigned int filter)
 	       global_page_state(NR_PAGETABLE),
 	       global_page_state(NR_BOUNCE),
 	       global_page_state(NR_FILE_PAGES),
-	       nr_swap_pages);
+	       get_nr_swap_pages());
 
 	for_each_zone(zone) {
 		unsigned long flags, order, total = 0, largest_order = -1;
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 52560a2038e1..1b99ee5c9f00 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -57,8 +57,8 @@ static inline int numa_cpu_node(int cpu)
 #endif
 
 #ifdef CONFIG_NUMA
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
+extern void numa_set_node(int cpu, int node);
+extern void numa_clear_node(int cpu);
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index e6423002c10b..567b5d0632b2 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -351,6 +351,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index cfc755dc1607..230c8ea878e5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -696,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic);
 
 int acpi_unmap_lsapic(int cpu)
 {
+#ifdef CONFIG_ACPI_NUMA
+	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
+#endif
+
 	per_cpu(x86_cpu_to_apicid, cpu) = -1;
 	set_cpu_present(cpu, false);
 	num_processors--;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 915f5efefcf5..9c857f05cef0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1056,6 +1056,15 @@ void __init setup_arch(char **cmdline_p)
 	setup_bios_corruption_check();
 #endif
 
+	/*
+	 * In the memory hotplug case, the kernel needs info from SRAT to
+	 * determine which memory is hotpluggable before allocating memory
+	 * using memblock.
+	 */
+	acpi_boot_table_init();
+	early_acpi_boot_init();
+	early_parse_srat();
+
 #ifdef CONFIG_X86_32
 	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
 			(max_pfn_mapped<<PAGE_SHIFT) - 1);
@@ -1101,10 +1110,6 @@ void __init setup_arch(char **cmdline_p)
 	/*
 	 * Parse the ACPI tables for possible boot-time SMP configuration.
 	 */
-	acpi_boot_table_init();
-
-	early_acpi_boot_init();
-
 	initmem_init();
 	memblock_find_dma_reserve();
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index b299724f6e34..2d19001151d5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -862,6 +862,18 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	return __remove_pages(zone, start_pfn, nr_pages);
+}
+#endif
 #endif
 
 /*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3eba7f429880..474e28f10815 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -707,6 +707,343 @@ int arch_add_memory(int nid, u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
+#define PAGE_INUSE 0xFD
+
+static void __meminit free_pagetable(struct page *page, int order)
+{
+	struct zone *zone;
+	bool bootmem = false;
+	unsigned long magic;
+	unsigned int nr_pages = 1 << order;
+
+	/* bootmem page has reserved flag */
+	if (PageReserved(page)) {
+		__ClearPageReserved(page);
+		bootmem = true;
+
+		magic = (unsigned long)page->lru.next;
+		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
+			while (nr_pages--)
+				put_page_bootmem(page++);
+		} else
+			__free_pages_bootmem(page, order);
+	} else
+		free_pages((unsigned long)page_address(page), order);
+
+	/*
+	 * SECTION_INFO pages and MIX_SECTION_INFO pages
+	 * are all allocated by bootmem.
+	 */
+	if (bootmem) {
+		zone = page_zone(page);
+		zone_span_writelock(zone);
+		zone->present_pages += nr_pages;
+		zone_span_writeunlock(zone);
+		totalram_pages += nr_pages;
+	}
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+	pte_t *pte;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte = pte_start + i;
+		if (pte_val(*pte))
+			return;
+	}
+
+	/* free a pte talbe */
+	free_pagetable(pmd_page(*pmd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pmd_clear(pmd);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+	pmd_t *pmd;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd = pmd_start + i;
+		if (pmd_val(*pmd))
+			return;
+	}
+
+	/* free a pmd talbe */
+	free_pagetable(pud_page(*pud), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pud_clear(pud);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+/* Return true if pgd is changed, otherwise return false. */
+static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
+{
+	pud_t *pud;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (pud_val(*pud))
+			return false;
+	}
+
+	/* free a pud table */
+	free_pagetable(pgd_page(*pgd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pgd_clear(pgd);
+	spin_unlock(&init_mm.page_table_lock);
+
+	return true;
+}
+
+static void __meminit
+remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pte_t *pte;
+	void *page_addr;
+	phys_addr_t phys_addr;
+
+	pte = pte_start + pte_index(addr);
+	for (; addr < end; addr = next, pte++) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		if (next > end)
+			next = end;
+
+		if (!pte_present(*pte))
+			continue;
+
+		/*
+		 * We mapped [0,1G) memory as identity mapping when
+		 * initializing, in arch/x86/kernel/head_64.S. These
+		 * pagetables cannot be removed.
+		 */
+		phys_addr = pte_val(*pte) + (addr & PAGE_MASK);
+		if (phys_addr < (phys_addr_t)0x40000000)
+			return;
+
+		if (IS_ALIGNED(addr, PAGE_SIZE) &&
+		    IS_ALIGNED(next, PAGE_SIZE)) {
+			/*
+			 * Do not free direct mapping pages since they were
+			 * freed when offlining, or simplely not in use.
+			 */
+			if (!direct)
+				free_pagetable(pte_page(*pte), 0);
+
+			spin_lock(&init_mm.page_table_lock);
+			pte_clear(&init_mm, addr, pte);
+			spin_unlock(&init_mm.page_table_lock);
+
+			/* For non-direct mapping, pages means nothing. */
+			pages++;
+		} else {
+			/*
+			 * If we are here, we are freeing vmemmap pages since
+			 * direct mapped memory ranges to be freed are aligned.
+			 *
+			 * If we are not removing the whole page, it means
+			 * other page structs in this page are being used and
+			 * we canot remove them. So fill the unused page_structs
+			 * with 0xFD, and remove the page when it is wholly
+			 * filled with 0xFD.
+			 */
+			memset((void *)addr, PAGE_INUSE, next - addr);
+
+			page_addr = page_address(pte_page(*pte));
+			if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
+				free_pagetable(pte_page(*pte), 0);
+
+				spin_lock(&init_mm.page_table_lock);
+				pte_clear(&init_mm, addr, pte);
+				spin_unlock(&init_mm.page_table_lock);
+			}
+		}
+	}
+
+	/* Call free_pte_table() in remove_pmd_table(). */
+	flush_tlb_all();
+	if (direct)
+		update_page_count(PG_LEVEL_4K, -pages);
+}
+
+static void __meminit
+remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pte_t *pte_base;
+	pmd_t *pmd;
+	void *page_addr;
+
+	pmd = pmd_start + pmd_index(addr);
+	for (; addr < end; addr = next, pmd++) {
+		next = pmd_addr_end(addr, end);
+
+		if (!pmd_present(*pmd))
+			continue;
+
+		if (pmd_large(*pmd)) {
+			if (IS_ALIGNED(addr, PMD_SIZE) &&
+			    IS_ALIGNED(next, PMD_SIZE)) {
+				if (!direct)
+					free_pagetable(pmd_page(*pmd),
+						       get_order(PMD_SIZE));
+
+				spin_lock(&init_mm.page_table_lock);
+				pmd_clear(pmd);
+				spin_unlock(&init_mm.page_table_lock);
+				pages++;
+			} else {
+				/* If here, we are freeing vmemmap pages. */
+				memset((void *)addr, PAGE_INUSE, next - addr);
+
+				page_addr = page_address(pmd_page(*pmd));
+				if (!memchr_inv(page_addr, PAGE_INUSE,
+						PMD_SIZE)) {
+					free_pagetable(pmd_page(*pmd),
+						       get_order(PMD_SIZE));
+
+					spin_lock(&init_mm.page_table_lock);
+					pmd_clear(pmd);
+					spin_unlock(&init_mm.page_table_lock);
+				}
+			}
+
+			continue;
+		}
+
+		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
+		remove_pte_table(pte_base, addr, next, direct);
+		free_pte_table(pte_base, pmd);
+	}
+
+	/* Call free_pmd_table() in remove_pud_table(). */
+	if (direct)
+		update_page_count(PG_LEVEL_2M, -pages);
+}
+
+static void __meminit
+remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pmd_t *pmd_base;
+	pud_t *pud;
+	void *page_addr;
+
+	pud = pud_start + pud_index(addr);
+	for (; addr < end; addr = next, pud++) {
+		next = pud_addr_end(addr, end);
+
+		if (!pud_present(*pud))
+			continue;
+
+		if (pud_large(*pud)) {
+			if (IS_ALIGNED(addr, PUD_SIZE) &&
+			    IS_ALIGNED(next, PUD_SIZE)) {
+				if (!direct)
+					free_pagetable(pud_page(*pud),
+						       get_order(PUD_SIZE));
+
+				spin_lock(&init_mm.page_table_lock);
+				pud_clear(pud);
+				spin_unlock(&init_mm.page_table_lock);
+				pages++;
+			} else {
+				/* If here, we are freeing vmemmap pages. */
+				memset((void *)addr, PAGE_INUSE, next - addr);
+
+				page_addr = page_address(pud_page(*pud));
+				if (!memchr_inv(page_addr, PAGE_INUSE,
+						PUD_SIZE)) {
+					free_pagetable(pud_page(*pud),
+						       get_order(PUD_SIZE));
+
+					spin_lock(&init_mm.page_table_lock);
+					pud_clear(pud);
+					spin_unlock(&init_mm.page_table_lock);
+				}
+			}
+
+			continue;
+		}
+
+		pmd_base = (pmd_t *)pud_page_vaddr(*pud);
+		remove_pmd_table(pmd_base, addr, next, direct);
+		free_pmd_table(pmd_base, pud);
+	}
+
+	if (direct)
+		update_page_count(PG_LEVEL_1G, -pages);
+}
+
+/* start and end are both virtual address. */
+static void __meminit
+remove_pagetable(unsigned long start, unsigned long end, bool direct)
+{
+	unsigned long next;
+	pgd_t *pgd;
+	pud_t *pud;
+	bool pgd_changed = false;
+
+	for (; start < end; start = next) {
+		next = pgd_addr_end(start, end);
+
+		pgd = pgd_offset_k(start);
+		if (!pgd_present(*pgd))
+			continue;
+
+		pud = (pud_t *)pgd_page_vaddr(*pgd);
+		remove_pud_table(pud, start, next, direct);
+		if (free_pud_table(pud, pgd))
+			pgd_changed = true;
+	}
+
+	if (pgd_changed)
+		sync_global_pgds(start, end - 1);
+
+	flush_tlb_all();
+}
+
+void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+	unsigned long start = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + nr_pages);
+
+	remove_pagetable(start, end, false);
+}
+
+static void __meminit
+kernel_physical_mapping_remove(unsigned long start, unsigned long end)
+{
+	start = (unsigned long)__va(start);
+	end = (unsigned long)__va(end);
+
+	remove_pagetable(start, end, true);
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int __ref arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	kernel_physical_mapping_remove(start, start + size);
+	ret = __remove_pages(zone, start_pfn, nr_pages);
+	WARN_ON_ONCE(ret);
+
+	return ret;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_vsyscall;
@@ -1019,6 +1356,66 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 	return 0;
 }
 
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+	unsigned long addr = (unsigned long)start_page;
+	unsigned long end = (unsigned long)(start_page + size);
+	unsigned long next;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned int nr_pages;
+	struct page *page;
+
+	for (; addr < end; addr = next) {
+		pte_t *pte = NULL;
+
+		pgd = pgd_offset_k(addr);
+		if (pgd_none(*pgd)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO);
+
+		pud = pud_offset(pgd, addr);
+		if (pud_none(*pud)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
+
+		if (!cpu_has_pse) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+			get_page_bootmem(section_nr, pmd_page(*pmd),
+					 MIX_SECTION_INFO);
+
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte))
+				continue;
+			get_page_bootmem(section_nr, pte_page(*pte),
+					 SECTION_INFO);
+		} else {
+			next = pmd_addr_end(addr, end);
+
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd))
+				continue;
+
+			nr_pages = 1 << (get_order(PMD_SIZE));
+			page = pmd_page(*pmd);
+			while (nr_pages--)
+				get_page_bootmem(section_nr, page++,
+						 SECTION_INFO);
+		}
+	}
+}
+#endif
+
 void __meminit vmemmap_populate_print_last(void)
 {
 	if (p_start) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 8504f3698753..dfd30259eb89 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -56,7 +56,7 @@ early_param("numa", numa_setup);
 /*
  * apicid, cpu, node mappings
  */
-s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+s16 __apicid_to_node[MAX_LOCAL_APIC] = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(node_to_cpumask_map);
 DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
 
-void __cpuinit numa_set_node(int cpu, int node)
+void numa_set_node(int cpu, int node)
 {
 	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
 
@@ -101,7 +101,7 @@ void __cpuinit numa_set_node(int cpu, int node)
 		set_cpu_numa_node(cpu, node);
 }
 
-void __cpuinit numa_clear_node(int cpu)
+void numa_clear_node(int cpu)
 {
 	numa_set_node(cpu, NUMA_NO_NODE);
 }
@@ -213,10 +213,9 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	 * Allocate node data.  Try node-local memory and then any node.
 	 * Never allocate in DMA zone.
 	 */
-	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
 	if (!nd_pa) {
-		pr_err("Cannot find %zu bytes in node %d\n",
-		       nd_size, nid);
+		pr_err("Cannot find %zu bytes in any node\n", nd_size);
 		return;
 	}
 	nd = __va(nd_pa);
@@ -561,10 +560,12 @@ static int __init numa_init(int (*init_func)(void))
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
 		set_apicid_to_node(i, NUMA_NO_NODE);
 
-	nodes_clear(numa_nodes_parsed);
+	/*
+	 * Do not clear numa_nodes_parsed or zero numa_meminfo here, because
+	 * SRAT was parsed earlier in early_parse_srat().
+	 */
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
-	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
 	WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
 	numa_reset_distance();
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a1b1c88f9caf..ca1f1c2bb7be 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -529,21 +529,13 @@ out_unlock:
 	return do_split;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
 {
 	unsigned long pfn, pfninc = 1;
 	unsigned int i, level;
-	pte_t *pbase, *tmp;
+	pte_t *tmp;
 	pgprot_t ref_prot;
-	struct page *base;
-
-	if (!debug_pagealloc)
-		spin_unlock(&cpa_lock);
-	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
-	if (!debug_pagealloc)
-		spin_lock(&cpa_lock);
-	if (!base)
-		return -ENOMEM;
+	struct page *base = virt_to_page(pbase);
 
 	spin_lock(&pgd_lock);
 	/*
@@ -551,10 +543,11 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	 * up for us already:
 	 */
 	tmp = lookup_address(address, &level);
-	if (tmp != kpte)
-		goto out_unlock;
+	if (tmp != kpte) {
+		spin_unlock(&pgd_lock);
+		return 1;
+	}
 
-	pbase = (pte_t *)page_address(base);
 	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
 	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
 	/*
@@ -601,17 +594,27 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	 * going on.
 	 */
 	__flush_tlb_all();
+	spin_unlock(&pgd_lock);
 
-	base = NULL;
+	return 0;
+}
 
-out_unlock:
-	/*
-	 * If we dropped out via the lookup_address check under
-	 * pgd_lock then stick the page back into the pool:
-	 */
-	if (base)
+static int split_large_page(pte_t *kpte, unsigned long address)
+{
+	pte_t *pbase;
+	struct page *base;
+
+	if (!debug_pagealloc)
+		spin_unlock(&cpa_lock);
+	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
+	if (!debug_pagealloc)
+		spin_lock(&cpa_lock);
+	if (!base)
+		return -ENOMEM;
+
+	pbase = (pte_t *)page_address(base);
+	if (__split_large_page(kpte, address, pbase))
 		__free_page(base);
-	spin_unlock(&pgd_lock);
 
 	return 0;
 }
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9dd530..79836d01f789 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -141,11 +141,126 @@ static inline int save_add_info(void) {return 1;}
 static inline int save_add_info(void) {return 0;}
 #endif
 
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+static void __init
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+	int overlap, i;
+	unsigned long start_pfn, end_pfn;
+
+	start_pfn = PFN_DOWN(start);
+	end_pfn = PFN_UP(end);
+
+	/*
+	 * For movablemem_map=acpi:
+	 *
+	 * SRAT:		|_____| |_____| |_________| |_________| ......
+	 * node id:                0       1         1           2
+	 * hotpluggable:	   n       y         y           n
+	 * movablemem_map:	        |_____| |_________|
+	 *
+	 * Using movablemem_map, we can prevent memblock from allocating memory
+	 * on ZONE_MOVABLE at boot time.
+	 *
+	 * Before parsing SRAT, memblock has already reserve some memory ranges
+	 * for other purposes, such as for kernel image. We cannot prevent
+	 * kernel from using these memory, so we need to exclude these memory
+	 * even if it is hotpluggable.
+	 * Furthermore, to ensure the kernel has enough memory to boot, we make
+	 * all the memory on the node which the kernel resides in
+	 * un-hotpluggable.
+	 */
+	if (hotpluggable && movablemem_map.acpi) {
+		/* Exclude ranges reserved by memblock. */
+		struct memblock_type *rgn = &memblock.reserved;
+
+		for (i = 0; i < rgn->cnt; i++) {
+			if (end <= rgn->regions[i].base ||
+			    start >= rgn->regions[i].base +
+			    rgn->regions[i].size)
+				continue;
+
+			/*
+			 * If the memory range overlaps the memory reserved by
+			 * memblock, then the kernel resides in this node.
+			 */
+			node_set(node, movablemem_map.numa_nodes_kernel);
+
+			goto out;
+		}
+
+		/*
+		 * If the kernel resides in this node, then the whole node
+		 * should not be hotpluggable.
+		 */
+		if (node_isset(node, movablemem_map.numa_nodes_kernel))
+			goto out;
+
+		insert_movablemem_map(start_pfn, end_pfn);
+
+		/*
+		 * numa_nodes_hotplug nodemask represents which nodes are put
+		 * into movablemem_map.map[].
+		 */
+		node_set(node, movablemem_map.numa_nodes_hotplug);
+		goto out;
+	}
+
+	/*
+	 * For movablemem_map=nn[KMG]@ss[KMG]:
+	 *
+	 * SRAT:		|_____| |_____| |_________| |_________| ......
+	 * node id:		   0       1         1           2
+	 * user specified:	          |__|                 |___|
+	 * movablemem_map:		  |___| |_________|    |______| ......
+	 *
+	 * Using movablemem_map, we can prevent memblock from allocating memory
+	 * on ZONE_MOVABLE at boot time.
+	 *
+	 * NOTE: In this case, SRAT info will be ingored.
+	 */
+	overlap = movablemem_map_overlap(start_pfn, end_pfn);
+	if (overlap >= 0) {
+		/*
+		 * If part of this range is in movablemem_map, we need to
+		 * add the range after it to extend the range to the end
+		 * of the node, because from the min address specified to
+		 * the end of the node will be ZONE_MOVABLE.
+		 */
+		start_pfn = max(start_pfn,
+			    movablemem_map.map[overlap].start_pfn);
+		insert_movablemem_map(start_pfn, end_pfn);
+
+		/*
+		 * Set the nodemask, so that if the address range on one node
+		 * is not continuse, we can add the subsequent ranges on the
+		 * same node into movablemem_map.
+		 */
+		node_set(node, movablemem_map.numa_nodes_hotplug);
+	} else {
+		if (node_isset(node, movablemem_map.numa_nodes_hotplug))
+			/*
+			 * Insert the range if we already have movable ranges
+			 * on the same node.
+			 */
+			insert_movablemem_map(start_pfn, end_pfn);
+	}
+out:
+	return;
+}
+#else		/* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+static inline void
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+}
+#endif		/* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
 int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
 	u64 start, end;
+	u32 hotpluggable;
 	int node, pxm;
 
 	if (srat_disabled())
@@ -154,7 +269,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		goto out_err_bad_srat;
 	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
 		goto out_err;
-	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
+	hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+	if (hotpluggable && !save_add_info())
 		goto out_err;
 
 	start = ma->base_address;
@@ -174,9 +290,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 	node_set(node, numa_nodes_parsed);
 
-	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n",
 	       node, pxm,
-	       (unsigned long long) start, (unsigned long long) end - 1);
+	       (unsigned long long) start, (unsigned long long) end - 1,
+	       hotpluggable ? "Hot Pluggable": "");
+
+	handle_movablemem(node, start, end, hotpluggable);
 
 	return 0;
 out_err_bad_srat: