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
  ...

Documentation/ABI/testing/sysfs-kernel-mm-ksm

+What:		/sys/kernel/mm/ksm
+Date:		September 2009
+KernelVersion:	2.6.32
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Interface for Kernel Samepage Merging (KSM)
+
+What:		/sys/kernel/mm/ksm/full_scans
+What:		/sys/kernel/mm/ksm/pages_shared
+What:		/sys/kernel/mm/ksm/pages_sharing
+What:		/sys/kernel/mm/ksm/pages_to_scan
+What:		/sys/kernel/mm/ksm/pages_unshared
+What:		/sys/kernel/mm/ksm/pages_volatile
+What:		/sys/kernel/mm/ksm/run
+What:		/sys/kernel/mm/ksm/sleep_millisecs
+Date:		September 2009
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Kernel Samepage Merging daemon sysfs interface
+
+		full_scans: how many times all mergeable areas have been
+		scanned.
+
+		pages_shared: how many shared pages are being used.
+
+		pages_sharing: how many more sites are sharing them i.e. how
+		much saved.
+
+		pages_to_scan: how many present pages to scan before ksmd goes
+		to sleep.
+
+		pages_unshared: how many pages unique but repeatedly checked
+		for merging.
+
+		pages_volatile: how many pages changing too fast to be placed
+		in a tree.
+
+		run: write 0 to disable ksm, read 0 while ksm is disabled.
+			write 1 to run ksm, read 1 while ksm is running.
+			write 2 to disable ksm and unmerge all its pages.
+
+		sleep_millisecs: how many milliseconds ksm should sleep between
+		scans.
+
+		See Documentation/vm/ksm.txt for more information.
+
+What:		/sys/kernel/mm/ksm/merge_across_nodes
+Date:		January 2013
+KernelVersion:	3.9
+Contact:	Linux memory management mailing list <linux-mm@kvack.org>
+Description:	Control merging pages across different NUMA nodes.
+
+		When it is set to 0 only pages from the same node are merged,
+		otherwise pages from all nodes can be merged together (default).

Documentation/kernel-parameters.txt

@@ -1640,6 +1640,42 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			that the amount of memory usable for all allocations
 			is not too small.
 
+	movablemem_map=acpi
+			[KNL,X86,IA-64,PPC] This parameter is similar to
+			memmap except it specifies the memory map of
+			ZONE_MOVABLE.
+			This option inform the kernel to use Hot Pluggable bit
+			in flags from SRAT from ACPI BIOS to determine which
+			memory devices could be hotplugged. The corresponding
+			memory ranges will be set as ZONE_MOVABLE.
+			NOTE: Whatever node the kernel resides in will always
+			      be un-hotpluggable.
+
+	movablemem_map=nn[KMG]@ss[KMG]
+			[KNL,X86,IA-64,PPC] This parameter is similar to
+			memmap except it specifies the memory map of
+			ZONE_MOVABLE.
+			If user specifies memory ranges, the info in SRAT will
+			be ingored. And it works like the following:
+			- If more ranges are all within one node, then from
+			  lowest ss to the end of the node will be ZONE_MOVABLE.
+			- If a range is within a node, then from ss to the end
+			  of the node will be ZONE_MOVABLE.
+			- If a range covers two or more nodes, then from ss to
+			  the end of the 1st node will be ZONE_MOVABLE, and all
+			  the rest nodes will only have ZONE_MOVABLE.
+			If memmap is specified at the same time, the
+			movablemem_map will be limited within the memmap
+			areas. If kernelcore or movablecore is also specified,
+			movablemem_map will have higher priority to be
+			satisfied. So the administrator should be careful that
+			the amount of movablemem_map areas are not too large.
+			Otherwise kernel won't have enough memory to start.
+			NOTE: We don't stop users specifying the node the
+			      kernel resides in as hotpluggable so that this
+			      option can be used as a workaround of firmware
+                              bugs.
+
 	MTD_Partition=	[MTD]
 			Format: <name>,<region-number>,<size>,<offset>
 

Documentation/vm/ksm.txt

@@ -58,6 +58,21 @@ sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                    e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
                    Default: 20 (chosen for demonstration purposes)
 
+merge_across_nodes - specifies if pages from different numa nodes can be merged.
+                   When set to 0, ksm merges only pages which physically
+                   reside in the memory area of same NUMA node. That brings
+                   lower latency to access of shared pages. Systems with more
+                   nodes, at significant NUMA distances, are likely to benefit
+                   from the lower latency of setting 0. Smaller systems, which
+                   need to minimize memory usage, are likely to benefit from
+                   the greater sharing of setting 1 (default). You may wish to
+                   compare how your system performs under each setting, before
+                   deciding on which to use. merge_across_nodes setting can be
+                   changed only when there are no ksm shared pages in system:
+                   set run 2 to unmerge pages first, then to 1 after changing
+                   merge_across_nodes, to remerge according to the new setting.
+                   Default: 1 (merging across nodes as in earlier releases)
+
 run              - set 0 to stop ksmd from running but keep merged pages,
                    set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                    set 2 to stop ksmd and unmerge all pages currently merged,

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 */

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());
 }
 
 

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

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
 
 /*

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 */
 

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 */
 
 /*

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 */

arch/s390/mm/vmem.c

@@ -268,6 +268,10 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 	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.

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 */

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());
 }

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,

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)

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;

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;

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);

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__ */

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--;

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();
 

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
 
 /*

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) {

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();
 

arch/x86/mm/pageattr.c

@@ -529,21 +529,13 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	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;
 }

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:

block/genhd.c

@@ -18,6 +18,7 @@
 #include <linux/mutex.h>
 #include <linux/idr.h>
 #include <linux/log2.h>
+#include <linux/pm_runtime.h>
 
 #include "blk.h"
 
@@ -534,6 +535,14 @@ static void register_disk(struct gendisk *disk)
 			return;
 		}
 	}
+
+	/*
+	 * avoid probable deadlock caused by allocating memory with
+	 * GFP_KERNEL in runtime_resume callback of its all ancestor
+	 * devices
+	 */
+	pm_runtime_set_memalloc_noio(ddev, true);
+
 	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
@@ -663,6 +672,7 @@ void del_gendisk(struct gendisk *disk)
 	disk->driverfs_dev = NULL;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
+	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
 }
 EXPORT_SYMBOL(del_gendisk);

drivers/acpi/acpi_memhotplug.c

@@ -280,9 +280,11 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 
 static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
 {
-	int result = 0;
+	int result = 0, nid;
 	struct acpi_memory_info *info, *n;
 
+	nid = acpi_get_node(mem_device->device->handle);
+
 	list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
 		if (info->failed)
 			/* The kernel does not use this memory block */
@@ -295,7 +297,9 @@ static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
 			 */
 			return -EBUSY;
 
-		result = remove_memory(info->start_addr, info->length);
+		if (nid < 0)
+			nid = memory_add_physaddr_to_nid(info->start_addr);
+		result = remove_memory(nid, info->start_addr, info->length);
 		if (result)
 			return result;
 

drivers/acpi/numa.c

@@ -282,10 +282,10 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 					    handler, max_entries);
 }
 
-int __init acpi_numa_init(void)
-{
-	int cnt = 0;
+static int srat_mem_cnt;
 
+void __init early_parse_srat(void)
+{
 	/*
 	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
 	 * SRAT cpu entries could have different order with that in MADT.
@@ -295,21 +295,24 @@ int __init acpi_numa_init(void)
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-				     acpi_parse_x2apic_affinity, 0);
+				      acpi_parse_x2apic_affinity, 0);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-				     acpi_parse_processor_affinity, 0);
-		cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
-					    acpi_parse_memory_affinity,
-					    NR_NODE_MEMBLKS);
+				      acpi_parse_processor_affinity, 0);
+		srat_mem_cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
+						     acpi_parse_memory_affinity,
+						     NR_NODE_MEMBLKS);
 	}
+}
 
+int __init acpi_numa_init(void)
+{
 	/* SLIT: System Locality Information Table */
 	acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit);
 
 	acpi_numa_arch_fixup();
 
-	if (cnt < 0)
-		return cnt;
+	if (srat_mem_cnt < 0)
+		return srat_mem_cnt;
 	else if (!parsed_numa_memblks)
 		return -ENOENT;
 	return 0;

drivers/acpi/processor_driver.c

@@ -45,6 +45,7 @@
 #include <linux/cpuidle.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/io.h>
 #include <asm/cpu.h>
@@ -641,6 +642,7 @@ static int acpi_processor_remove(struct acpi_device *device)
 
 	per_cpu(processors, pr->id) = NULL;
 	per_cpu(processor_device_array, pr->id) = NULL;
+	try_offline_node(cpu_to_node(pr->id));
 
 free:
 	free_cpumask_var(pr->throttling.shared_cpu_map);

drivers/base/memory.c

@@ -693,6 +693,12 @@ int offline_memory_block(struct memory_block *mem)
 	return ret;
 }
 
+/* return true if the memory block is offlined, otherwise, return false */
+bool is_memblock_offlined(struct memory_block *mem)
+{
+	return mem->state == MEM_OFFLINE;
+}
+
 /*
  * Initialize the sysfs support for memory devices...
  */

drivers/base/power/runtime.c

@@ -124,6 +124,76 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+	return dev->power.memalloc_noio;
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path whose siblings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend callback of any one of its ancestors(or the
+ *     block device itself), the deadlock may be triggered inside the
+ *     memory allocation since it might not complete until the block
+ *     device becomes active and the involed page I/O finishes. The
+ *     situation is pointed out first by Alan Stern. Network device
+ *     are involved in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+	static DEFINE_MUTEX(dev_hotplug_mutex);
+
+	mutex_lock(&dev_hotplug_mutex);
+	for (;;) {
+		bool enabled;
+
+		/* hold power lock since bitfield is not SMP-safe. */
+		spin_lock_irq(&dev->power.lock);
+		enabled = dev->power.memalloc_noio;
+		dev->power.memalloc_noio = enable;
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * not need to enable ancestors any more if the device
+		 * has been enabled.
+		 */
+		if (enabled && enable)
+			break;
+
+		dev = dev->parent;
+
+		/*
+		 * clear flag of the parent device only if all the
+		 * children don't set the flag because ancestor's
+		 * flag was set by any one of the descendants.
+		 */
+		if (!dev || (!enable &&
+			     device_for_each_child(dev, NULL,
+						   dev_memalloc_noio)))
+			break;
+	}
+	mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
 /**
  * rpm_check_suspend_allowed - Test whether a device may be suspended.
  * @dev: Device to test.
@@ -278,7 +348,24 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 	if (!cb)
 		return -ENOSYS;
 
-	retval = __rpm_callback(cb, dev);
+	if (dev->power.memalloc_noio) {
+		unsigned int noio_flag;
+
+		/*
+		 * Deadlock might be caused if memory allocation with
+		 * GFP_KERNEL happens inside runtime_suspend and
+		 * runtime_resume callbacks of one block device's
+		 * ancestor or the block device itself. Network
+		 * device might be thought as part of iSCSI block
+		 * device, so network device and its ancestor should
+		 * be marked as memalloc_noio too.
+		 */
+		noio_flag = memalloc_noio_save();
+		retval = __rpm_callback(cb, dev);
+		memalloc_noio_restore(noio_flag);
+	} else {
+		retval = __rpm_callback(cb, dev);
+	}
 
 	dev->power.runtime_error = retval;
 	return retval != -EACCES ? retval : -EIO;

drivers/firmware/memmap.c

@@ -21,6 +21,7 @@
 #include <linux/types.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 /*
  * Data types ------------------------------------------------------------------
@@ -52,6 +53,9 @@ static ssize_t start_show(struct firmware_map_entry *entry, char *buf);
 static ssize_t end_show(struct firmware_map_entry *entry, char *buf);
 static ssize_t type_show(struct firmware_map_entry *entry, char *buf);
 
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry(u64 start, u64 end, const char *type);
+
 /*
  * Static data -----------------------------------------------------------------
  */
@@ -79,7 +83,52 @@ static const struct sysfs_ops memmap_attr_ops = {
 	.show = memmap_attr_show,
 };
 
-static struct kobj_type memmap_ktype = {
+/* Firmware memory map entries. */
+static LIST_HEAD(map_entries);
+static DEFINE_SPINLOCK(map_entries_lock);
+
+/*
+ * For memory hotplug, there is no way to free memory map entries allocated
+ * by boot mem after the system is up. So when we hot-remove memory whose
+ * map entry is allocated by bootmem, we need to remember the storage and
+ * reuse it when the memory is hot-added again.
+ */
+static LIST_HEAD(map_entries_bootmem);
+static DEFINE_SPINLOCK(map_entries_bootmem_lock);
+
+
+static inline struct firmware_map_entry *
+to_memmap_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct firmware_map_entry, kobj);
+}
+
+static void __meminit release_firmware_map_entry(struct kobject *kobj)
+{
+	struct firmware_map_entry *entry = to_memmap_entry(kobj);
+
+	if (PageReserved(virt_to_page(entry))) {
+		/*
+		 * Remember the storage allocated by bootmem, and reuse it when
+		 * the memory is hot-added again. The entry will be added to
+		 * map_entries_bootmem here, and deleted from &map_entries in
+		 * firmware_map_remove_entry().
+		 */
+		if (firmware_map_find_entry(entry->start, entry->end,
+		    entry->type)) {
+			spin_lock(&map_entries_bootmem_lock);
+			list_add(&entry->list, &map_entries_bootmem);
+			spin_unlock(&map_entries_bootmem_lock);
+		}
+
+		return;
+	}
+
+	kfree(entry);
+}
+
+static struct kobj_type __refdata memmap_ktype = {
+	.release	= release_firmware_map_entry,
 	.sysfs_ops	= &memmap_attr_ops,
 	.default_attrs	= def_attrs,
 };
@@ -88,13 +137,6 @@ static struct kobj_type memmap_ktype = {
  * Registration functions ------------------------------------------------------
  */
 
-/*
- * Firmware memory map entries. No locking is needed because the
- * firmware_map_add() and firmware_map_add_early() functions are called
- * in firmware initialisation code in one single thread of execution.
- */
-static LIST_HEAD(map_entries);
-
 /**
  * firmware_map_add_entry() - Does the real work to add a firmware memmap entry.
  * @start: Start of the memory range.
@@ -118,11 +160,25 @@ static int firmware_map_add_entry(u64 start, u64 end,
 	INIT_LIST_HEAD(&entry->list);
 	kobject_init(&entry->kobj, &memmap_ktype);
 
+	spin_lock(&map_entries_lock);
 	list_add_tail(&entry->list, &map_entries);
+	spin_unlock(&map_entries_lock);
 
 	return 0;
 }
 
+/**
+ * firmware_map_remove_entry() - Does the real work to remove a firmware
+ * memmap entry.
+ * @entry: removed entry.
+ *
+ * The caller must hold map_entries_lock, and release it properly.
+ **/
+static inline void firmware_map_remove_entry(struct firmware_map_entry *entry)
+{
+	list_del(&entry->list);
+}
+
 /*
  * Add memmap entry on sysfs
  */
@@ -144,6 +200,78 @@ static int add_sysfs_fw_map_entry(struct firmware_map_entry *entry)
 	return 0;
 }
 
+/*
+ * Remove memmap entry on sysfs
+ */
+static inline void remove_sysfs_fw_map_entry(struct firmware_map_entry *entry)
+{
+	kobject_put(&entry->kobj);
+}
+
+/*
+ * firmware_map_find_entry_in_list() - Search memmap entry in a given list.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ * @list:  In which to find the entry.
+ *
+ * This function is to find the memmap entey of a given memory range in a
+ * given list. The caller must hold map_entries_lock, and must not release
+ * the lock until the processing of the returned entry has completed.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry_in_list(u64 start, u64 end, const char *type,
+				struct list_head *list)
+{
+	struct firmware_map_entry *entry;
+
+	list_for_each_entry(entry, list, list)
+		if ((entry->start == start) && (entry->end == end) &&
+		    (!strcmp(entry->type, type))) {
+			return entry;
+		}
+
+	return NULL;
+}
+
+/*
+ * firmware_map_find_entry() - Search memmap entry in map_entries.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ *
+ * This function is to find the memmap entey of a given memory range.
+ * The caller must hold map_entries_lock, and must not release the lock
+ * until the processing of the returned entry has completed.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry(u64 start, u64 end, const char *type)
+{
+	return firmware_map_find_entry_in_list(start, end, type, &map_entries);
+}
+
+/*
+ * firmware_map_find_entry_bootmem() - Search memmap entry in map_entries_bootmem.
+ * @start: Start of the memory range.
+ * @end:   End of the memory range (exclusive).
+ * @type:  Type of the memory range.
+ *
+ * This function is similar to firmware_map_find_entry except that it find the
+ * given entry in map_entries_bootmem.
+ *
+ * Return: Pointer to the entry to be found on success, or NULL on failure.
+ */
+static struct firmware_map_entry * __meminit
+firmware_map_find_entry_bootmem(u64 start, u64 end, const char *type)
+{
+	return firmware_map_find_entry_in_list(start, end, type,
+					       &map_entries_bootmem);
+}
+
 /**
  * firmware_map_add_hotplug() - Adds a firmware mapping entry when we do
  * memory hotplug.
@@ -161,9 +289,19 @@ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type)
 {
 	struct firmware_map_entry *entry;
 
-	entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
-	if (!entry)
-		return -ENOMEM;
+	entry = firmware_map_find_entry_bootmem(start, end, type);
+	if (!entry) {
+		entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
+		if (!entry)
+			return -ENOMEM;
+	} else {
+		/* Reuse storage allocated by bootmem. */
+		spin_lock(&map_entries_bootmem_lock);
+		list_del(&entry->list);
+		spin_unlock(&map_entries_bootmem_lock);
+
+		memset(entry, 0, sizeof(*entry));
+	}
 
 	firmware_map_add_entry(start, end, type, entry);
 	/* create the memmap entry */
@@ -196,6 +334,36 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type)
 	return firmware_map_add_entry(start, end, type, entry);
 }
 
+/**
+ * firmware_map_remove() - remove a firmware mapping entry
+ * @start: Start of the memory range.
+ * @end:   End of the memory range.
+ * @type:  Type of the memory range.
+ *
+ * removes a firmware mapping entry.
+ *
+ * Returns 0 on success, or -EINVAL if no entry.
+ **/
+int __meminit firmware_map_remove(u64 start, u64 end, const char *type)
+{
+	struct firmware_map_entry *entry;
+
+	spin_lock(&map_entries_lock);
+	entry = firmware_map_find_entry(start, end - 1, type);
+	if (!entry) {
+		spin_unlock(&map_entries_lock);
+		return -EINVAL;
+	}
+
+	firmware_map_remove_entry(entry);
+	spin_unlock(&map_entries_lock);
+
+	/* remove the memmap entry */
+	remove_sysfs_fw_map_entry(entry);
+
+	return 0;
+}
+
 /*
  * Sysfs functions -------------------------------------------------------------
  */
@@ -217,8 +385,10 @@ static ssize_t type_show(struct firmware_map_entry *entry, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%s\n", entry->type);
 }
 
-#define to_memmap_attr(_attr) container_of(_attr, struct memmap_attribute, attr)
-#define to_memmap_entry(obj) container_of(obj, struct firmware_map_entry, kobj)
+static inline struct memmap_attribute *to_memmap_attr(struct attribute *attr)
+{
+	return container_of(attr, struct memmap_attribute, attr);
+}
 
 static ssize_t memmap_attr_show(struct kobject *kobj,
 				struct attribute *attr, char *buf)

drivers/md/persistent-data/dm-transaction-manager.c

@@ -25,8 +25,8 @@ struct shadow_info {
 /*
  * It would be nice if we scaled with the size of transaction.
  */
-#define HASH_SIZE 256
-#define HASH_MASK (HASH_SIZE - 1)
+#define DM_HASH_SIZE 256
+#define DM_HASH_MASK (DM_HASH_SIZE - 1)
 
 struct dm_transaction_manager {
 	int is_clone;
@@ -36,7 +36,7 @@ struct dm_transaction_manager {
 	struct dm_space_map *sm;
 
 	spinlock_t lock;
-	struct hlist_head buckets[HASH_SIZE];
+	struct hlist_head buckets[DM_HASH_SIZE];
 };
 
 /*----------------------------------------------------------------*/
@@ -44,7 +44,7 @@ struct dm_transaction_manager {
 static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 {
 	int r = 0;
-	unsigned bucket = dm_hash_block(b, HASH_MASK);
+	unsigned bucket = dm_hash_block(b, DM_HASH_MASK);
 	struct shadow_info *si;
 	struct hlist_node *n;
 
@@ -71,7 +71,7 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 	si = kmalloc(sizeof(*si), GFP_NOIO);
 	if (si) {
 		si->where = b;
-		bucket = dm_hash_block(b, HASH_MASK);
+		bucket = dm_hash_block(b, DM_HASH_MASK);
 		spin_lock(&tm->lock);
 		hlist_add_head(&si->hlist, tm->buckets + bucket);
 		spin_unlock(&tm->lock);
@@ -86,7 +86,7 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
 	int i;
 
 	spin_lock(&tm->lock);
-	for (i = 0; i < HASH_SIZE; i++) {
+	for (i = 0; i < DM_HASH_SIZE; i++) {
 		bucket = tm->buckets + i;
 		hlist_for_each_entry_safe(si, n, tmp, bucket, hlist)
 			kfree(si);
@@ -115,7 +115,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 	tm->sm = sm;
 
 	spin_lock_init(&tm->lock);
-	for (i = 0; i < HASH_SIZE; i++)
+	for (i = 0; i < DM_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(tm->buckets + i);
 
 	return tm;

drivers/staging/zcache/zbud.c

@@ -404,7 +404,7 @@ static inline struct page *zbud_unuse_zbudpage(struct zbudpage *zbudpage,
 	else
 		zbud_pers_pageframes--;
 	zbudpage_spin_unlock(zbudpage);
-	reset_page_mapcount(page);
+	page_mapcount_reset(page);
 	init_page_count(page);
 	page->index = 0;
 	return page;

drivers/staging/zsmalloc/zsmalloc-main.c

@@ -472,7 +472,7 @@ static void reset_page(struct page *page)
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	page->freelist = NULL;
-	reset_page_mapcount(page);
+	page_mapcount_reset(page);
 }
 
 static void free_zspage(struct page *first_page)

drivers/usb/core/hub.c

@@ -5177,6 +5177,7 @@ int usb_reset_device(struct usb_device *udev)
 {
 	int ret;
 	int i;
+	unsigned int noio_flag;
 	struct usb_host_config *config = udev->actconfig;
 
 	if (udev->state == USB_STATE_NOTATTACHED ||
@@ -5186,6 +5187,17 @@ int usb_reset_device(struct usb_device *udev)
 		return -EINVAL;
 	}
 
+	/*
+	 * Don't allocate memory with GFP_KERNEL in current
+	 * context to avoid possible deadlock if usb mass
+	 * storage interface or usbnet interface(iSCSI case)
+	 * is included in current configuration. The easist
+	 * approach is to do it for every device reset,
+	 * because the device 'memalloc_noio' flag may have
+	 * not been set before reseting the usb device.
+	 */
+	noio_flag = memalloc_noio_save();
+
 	/* Prevent autosuspend during the reset */
 	usb_autoresume_device(udev);
 
@@ -5230,6 +5242,7 @@ int usb_reset_device(struct usb_device *udev)
 	}
 
 	usb_autosuspend_device(udev);
+	memalloc_noio_restore(noio_flag);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_reset_device);

fs/aio.c

@@ -101,7 +101,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	struct aio_ring *ring;
 	struct aio_ring_info *info = &ctx->ring_info;
 	unsigned nr_events = ctx->max_reqs;
-	unsigned long size;
+	unsigned long size, populate;
 	int nr_pages;
 
 	/* Compensate for the ring buffer's head/tail overlap entry */
@@ -129,7 +129,8 @@ static int aio_setup_ring(struct kioctx *ctx)
 	down_write(&ctx->mm->mmap_sem);
 	info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, 
 					PROT_READ|PROT_WRITE,
-					MAP_ANONYMOUS|MAP_PRIVATE, 0);
+					MAP_ANONYMOUS|MAP_PRIVATE, 0,
+					&populate);
 	if (IS_ERR((void *)info->mmap_base)) {
 		up_write(&ctx->mm->mmap_sem);
 		info->mmap_size = 0;
@@ -147,6 +148,8 @@ static int aio_setup_ring(struct kioctx *ctx)
 		aio_free_ring(ctx);
 		return -EAGAIN;
 	}
+	if (populate)
+		mm_populate(info->mmap_base, populate);
 
 	ctx->user_id = info->mmap_base;
 

fs/buffer.c

@@ -3227,7 +3227,7 @@ static struct kmem_cache *bh_cachep __read_mostly;
  * Once the number of bh's in the machine exceeds this level, we start
  * stripping them in writeback.
  */
-static int max_buffer_heads;
+static unsigned long max_buffer_heads;
 
 int buffer_heads_over_limit;
 
@@ -3343,7 +3343,7 @@ EXPORT_SYMBOL(bh_submit_read);
 
 void __init buffer_init(void)
 {
-	int nrpages;
+	unsigned long nrpages;
 
 	bh_cachep = kmem_cache_create("buffer_head",
 			sizeof(struct buffer_head), 0,

fs/nfsd/nfs4state.c

@@ -151,7 +151,7 @@ get_nfs4_file(struct nfs4_file *fi)
 }
 
 static int num_delegations;
-unsigned int max_delegations;
+unsigned long max_delegations;
 
 /*
  * Open owner state (share locks)
@@ -700,8 +700,8 @@ static int nfsd4_get_drc_mem(int slotsize, u32 num)
 	num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION);
 
 	spin_lock(&nfsd_drc_lock);
-	avail = min_t(int, NFSD_MAX_MEM_PER_SESSION,
-			nfsd_drc_max_mem - nfsd_drc_mem_used);
+	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION,
+		    nfsd_drc_max_mem - nfsd_drc_mem_used);
 	num = min_t(int, num, avail / slotsize);
 	nfsd_drc_mem_used += num * slotsize;
 	spin_unlock(&nfsd_drc_lock);

fs/nfsd/nfsd.h

@@ -56,8 +56,8 @@ extern struct svc_version	nfsd_version2, nfsd_version3,
 extern u32			nfsd_supported_minorversion;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
-extern unsigned int		nfsd_drc_max_mem;
-extern unsigned int		nfsd_drc_mem_used;
+extern unsigned long		nfsd_drc_max_mem;
+extern unsigned long		nfsd_drc_mem_used;
 
 extern const struct seq_operations nfs_exports_op;
 
@@ -106,7 +106,7 @@ static inline int nfsd_v4client(struct svc_rqst *rq)
  * NFSv4 State
  */
 #ifdef CONFIG_NFSD_V4
-extern unsigned int max_delegations;
+extern unsigned long max_delegations;
 void nfs4_state_init(void);
 int nfsd4_init_slabs(void);
 void nfsd4_free_slabs(void);

fs/nfsd/nfssvc.c

@@ -59,8 +59,8 @@ DEFINE_MUTEX(nfsd_mutex);
  * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
  */
 spinlock_t	nfsd_drc_lock;
-unsigned int	nfsd_drc_max_mem;
-unsigned int	nfsd_drc_mem_used;
+unsigned long	nfsd_drc_max_mem;
+unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
@@ -342,7 +342,7 @@ static void set_max_drc(void)
 					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
 	nfsd_drc_mem_used = 0;
 	spin_lock_init(&nfsd_drc_lock);
-	dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
+	dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
 }
 
 static int nfsd_get_default_max_blksize(void)

fs/proc/meminfo.c

@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		* sysctl_overcommit_ratio / 100) + total_swap_pages;
 
 	cached = global_page_state(NR_FILE_PAGES) -
-			total_swapcache_pages - i.bufferram;
+			total_swapcache_pages() - i.bufferram;
 	if (cached < 0)
 		cached = 0;
 
@@ -109,7 +109,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(i.freeram),
 		K(i.bufferram),
 		K(cached),
-		K(total_swapcache_pages),
+		K(total_swapcache_pages()),
 		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
 		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
 		K(pages[LRU_ACTIVE_ANON]),
@@ -158,7 +158,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		vmi.used >> 10,
 		vmi.largest_chunk >> 10
 #ifdef CONFIG_MEMORY_FAILURE
-		,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
+		,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *

include/linux/acpi.h

@@ -485,6 +485,14 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #endif	/* !CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI_NUMA
+void __init early_parse_srat(void);
+#else
+static inline void early_parse_srat(void)
+{
+}
+#endif
+
 #ifdef CONFIG_ACPI
 void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 			       u32 pm1a_ctrl,  u32 pm1b_ctrl));

include/linux/bootmem.h

@@ -53,6 +53,7 @@ extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long size);
 extern void free_bootmem(unsigned long physaddr, unsigned long size);
 extern void free_bootmem_late(unsigned long physaddr, unsigned long size);
+extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
  * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,

include/linux/compaction.h

@@ -23,7 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			bool sync, bool *contended);
-extern int compact_pgdat(pg_data_t *pgdat, int order);
+extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
@@ -80,9 +80,8 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	return COMPACT_CONTINUE;
 }
 
-static inline int compact_pgdat(pg_data_t *pgdat, int order)
+static inline void compact_pgdat(pg_data_t *pgdat, int order)
 {
-	return COMPACT_CONTINUE;
 }
 
 static inline void reset_isolation_suitable(pg_data_t *pgdat)

include/linux/firmware-map.h

@@ -25,6 +25,7 @@
 
 int firmware_map_add_early(u64 start, u64 end, const char *type);
 int firmware_map_add_hotplug(u64 start, u64 end, const char *type);
+int firmware_map_remove(u64 start, u64 end, const char *type);
 
 #else /* CONFIG_FIRMWARE_MEMMAP */
 
@@ -38,6 +39,11 @@ static inline int firmware_map_add_hotplug(u64 start, u64 end, const char *type)
 	return 0;
 }
 
+static inline int firmware_map_remove(u64 start, u64 end, const char *type)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FIRMWARE_MEMMAP */
 
 #endif /* _LINUX_FIRMWARE_MAP_H */

include/linux/highmem.h

@@ -219,12 +219,6 @@ static inline void zero_user(struct page *page,
 	zero_user_segments(page, start, start + size, 0, 0);
 }
 
-static inline void __deprecated memclear_highpage_flush(struct page *page,
-			unsigned int offset, unsigned int size)
-{
-	zero_user(page, offset, size);
-}
-
 #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE
 
 static inline void copy_user_highpage(struct page *to, struct page *from,

include/linux/huge_mm.h

@@ -113,7 +113,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma,
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
 		anon_vma_lock_write(__anon_vma);			\
-		anon_vma_unlock(__anon_vma);				\
+		anon_vma_unlock_write(__anon_vma);			\
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
 	} while (0)

include/linux/hugetlb.h

@@ -43,9 +43,9 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
 #endif
 
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
-int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
-			struct page **, struct vm_area_struct **,
-			unsigned long *, int *, int, unsigned int flags);
+long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
+			 struct page **, struct vm_area_struct **,
+			 unsigned long *, unsigned long *, long, unsigned int);
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *);
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,

include/linux/ksm.h

@@ -16,9 +16,6 @@
 struct stable_node;
 struct mem_cgroup;
 
-struct page *ksm_does_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
-
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags);
@@ -73,15 +70,8 @@ static inline void set_page_stable_node(struct page *page,
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-static inline int ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
-{
-	struct anon_vma *anon_vma = page_anon_vma(page);
-
-	return anon_vma &&
-		(anon_vma->root != vma->anon_vma->root ||
-		 page->index != linear_page_index(vma, address));
-}
+struct page *ksm_might_need_to_copy(struct page *page,
+			struct vm_area_struct *vma, unsigned long address);
 
 int page_referenced_ksm(struct page *page,
 			struct mem_cgroup *memcg, unsigned long *vm_flags);
@@ -113,10 +103,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 	return 0;
 }
 
-static inline int ksm_might_need_to_copy(struct page *page,
+static inline struct page *ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address)
 {
-	return 0;
+	return page;
 }
 
 static inline int page_referenced_ksm(struct page *page,

include/linux/memblock.h

@@ -42,6 +42,7 @@ struct memblock {
 
 extern struct memblock memblock;
 extern int memblock_debug;
+extern struct movablemem_map movablemem_map;
 
 #define memblock_dbg(fmt, ...) \
 	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
@@ -60,6 +61,7 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			  unsigned long *out_end_pfn, int *out_nid);
 

include/linux/memcontrol.h

@@ -116,7 +116,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
  * For memory reclaim.
  */
 int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
-int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec);
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
 void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
@@ -321,12 +320,6 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return 1;
 }
 
-static inline int
-mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
-{
-	return 1;
-}
-
 static inline unsigned long
 mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {

include/linux/memory_hotplug.h

@@ -96,6 +96,7 @@ extern void __online_page_free(struct page *page);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
+extern int arch_remove_memory(u64 start, u64 size);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 /* reasonably generic interface to expand the physical pages in a zone  */
@@ -173,17 +174,16 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+#else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
-static inline void put_page_bootmem(struct page *page)
-{
-}
-#else
-extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
-extern void put_page_bootmem(struct page *page);
 #endif
+extern void put_page_bootmem(struct page *page);
+extern void get_page_bootmem(unsigned long ingo, struct page *page,
+			     unsigned long type);
 
 /*
  * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug
@@ -233,6 +233,7 @@ static inline void unlock_memory_hotplug(void) {}
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
+extern void try_offline_node(int nid);
 
 #else
 static inline int is_mem_section_removable(unsigned long pfn,
@@ -240,6 +241,8 @@ static inline int is_mem_section_removable(unsigned long pfn,
 {
 	return 0;
 }
+
+static inline void try_offline_node(int nid) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 extern int mem_online_node(int nid);
@@ -247,7 +250,8 @@ extern int add_memory(int nid, u64 start, u64 size);
 extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern int offline_memory_block(struct memory_block *mem);
-extern int remove_memory(u64 start, u64 size);
+extern bool is_memblock_offlined(struct memory_block *mem);
+extern int remove_memory(int nid, u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 								int nr_pages);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);

include/linux/migrate.h

@@ -40,11 +40,9 @@ extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
-			unsigned long private, bool offlining,
-			enum migrate_mode mode, int reason);
+		unsigned long private, enum migrate_mode mode, int reason);
 extern int migrate_huge_page(struct page *, new_page_t x,
-			unsigned long private, bool offlining,
-			enum migrate_mode mode);
+		unsigned long private, enum migrate_mode mode);
 
 extern int fail_migrate_page(struct address_space *,
 			struct page *, struct page *);
@@ -62,11 +60,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
-		unsigned long private, bool offlining,
-		enum migrate_mode mode, int reason) { return -ENOSYS; }
+		unsigned long private, enum migrate_mode mode, int reason)
+	{ return -ENOSYS; }
 static inline int migrate_huge_page(struct page *page, new_page_t x,
-		unsigned long private, bool offlining,
-		enum migrate_mode mode) { return -ENOSYS; }
+		unsigned long private, enum migrate_mode mode)
+	{ return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }

include/linux/mm.h

@@ -87,6 +87,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
 #define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
 
+#define VM_POPULATE     0x00001000
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000	/* Memory mapped I/O or similar */
 
@@ -366,7 +367,7 @@ static inline struct page *compound_head(struct page *page)
  * both from it and to it can be tracked, using atomic_inc_and_test
  * and atomic_add_negative(-1).
  */
-static inline void reset_page_mapcount(struct page *page)
+static inline void page_mapcount_reset(struct page *page)
 {
 	atomic_set(&(page)->_mapcount, -1);
 }
@@ -580,50 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
  * sets it, so none of the operations on it need to be atomic.
  */
 
-
-/*
- * page->flags layout:
- *
- * There are three possibilities for how page->flags get
- * laid out.  The first is for the normal case, without
- * sparsemem.  The second is for sparsemem when there is
- * plenty of space for node and section.  The last is when
- * we have run out of space and have to fall back to an
- * alternate (slower) way of determining the node.
- *
- * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE | ... | FLAGS |
- * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
- * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
- */
-#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
-#define SECTIONS_WIDTH		SECTIONS_SHIFT
-#else
-#define SECTIONS_WIDTH		0
-#endif
-
-#define ZONES_WIDTH		ZONES_SHIFT
-
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-#define NODES_WIDTH		NODES_SHIFT
-#else
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#error "Vmemmap: No space for nodes field in page flags"
-#endif
-#define NODES_WIDTH		0
-#endif
-
-/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */
 #define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
 #define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
 #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
-
-/*
- * We are going to use the flags for the page to node mapping if its in
- * there.  This includes the case where there is no node, so it is implicit.
- */
-#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
-#define NODE_NOT_IN_PAGE_FLAGS
-#endif
+#define LAST_NID_PGOFF		(ZONES_PGOFF - LAST_NID_WIDTH)
 
 /*
  * Define the bit shifts to access each section.  For non-existent
@@ -633,6 +595,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
 #define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
 #define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
+#define LAST_NID_PGSHIFT	(LAST_NID_PGOFF * (LAST_NID_WIDTH != 0))
 
 /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
 #ifdef NODE_NOT_IN_PAGE_FLAGS
@@ -654,6 +617,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
+#define LAST_NID_MASK		((1UL << LAST_NID_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
@@ -661,6 +625,10 @@ static inline enum zone_type page_zonenum(const struct page *page)
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
 
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+#define SECTION_IN_PAGE_FLAGS
+#endif
+
 /*
  * The identification function is only used by the buddy allocator for
  * determining if two pages could be buddies. We are not really
@@ -693,31 +661,48 @@ static inline int page_to_nid(const struct page *page)
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
-static inline int page_xchg_last_nid(struct page *page, int nid)
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+static inline int page_nid_xchg_last(struct page *page, int nid)
 {
 	return xchg(&page->_last_nid, nid);
 }
 
-static inline int page_last_nid(struct page *page)
+static inline int page_nid_last(struct page *page)
 {
 	return page->_last_nid;
 }
-static inline void reset_page_last_nid(struct page *page)
+static inline void page_nid_reset_last(struct page *page)
 {
 	page->_last_nid = -1;
 }
 #else
-static inline int page_xchg_last_nid(struct page *page, int nid)
+static inline int page_nid_last(struct page *page)
+{
+	return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+}
+
+extern int page_nid_xchg_last(struct page *page, int nid);
+
+static inline void page_nid_reset_last(struct page *page)
+{
+	int nid = (1 << LAST_NID_SHIFT) - 1;
+
+	page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
+	page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+}
+#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */
+#else
+static inline int page_nid_xchg_last(struct page *page, int nid)
 {
 	return page_to_nid(page);
 }
 
-static inline int page_last_nid(struct page *page)
+static inline int page_nid_last(struct page *page)
 {
 	return page_to_nid(page);
 }
 
-static inline void reset_page_last_nid(struct page *page)
+static inline void page_nid_reset_last(struct page *page)
 {
 }
 #endif
@@ -727,7 +712,7 @@ static inline struct zone *page_zone(const struct page *page)
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
 }
 
-#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+#ifdef SECTION_IN_PAGE_FLAGS
 static inline void set_page_section(struct page *page, unsigned long section)
 {
 	page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
@@ -757,7 +742,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 {
 	set_page_zone(page, zone);
 	set_page_node(page, node);
-#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+#ifdef SECTION_IN_PAGE_FLAGS
 	set_page_section(page, pfn_to_section_nr(pfn));
 #endif
 }
@@ -817,18 +802,7 @@ void page_address_init(void);
 #define PAGE_MAPPING_KSM	2
 #define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
 
-extern struct address_space swapper_space;
-static inline struct address_space *page_mapping(struct page *page)
-{
-	struct address_space *mapping = page->mapping;
-
-	VM_BUG_ON(PageSlab(page));
-	if (unlikely(PageSwapCache(page)))
-		mapping = &swapper_space;
-	else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
-		mapping = NULL;
-	return mapping;
-}
+extern struct address_space *page_mapping(struct page *page);
 
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 static inline void *page_rmapping(struct page *page)
@@ -1035,18 +1009,18 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 }
 #endif
 
-extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, int write);
 
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int len, unsigned int foll_flags,
-		     struct page **pages, struct vm_area_struct **vmas,
-		     int *nonblocking);
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-			unsigned long start, int nr_pages, int write, int force,
-			struct page **pages, struct vm_area_struct **vmas);
+long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		      unsigned long start, unsigned long nr_pages,
+		      unsigned int foll_flags, struct page **pages,
+		      struct vm_area_struct **vmas, int *nonblocking);
+long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		    unsigned long start, unsigned long nr_pages,
+		    int write, int force, struct page **pages,
+		    struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 struct kvec;
@@ -1359,6 +1333,24 @@ extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
 
+#define MOVABLEMEM_MAP_MAX MAX_NUMNODES
+struct movablemem_entry {
+	unsigned long start_pfn;    /* start pfn of memory segment */
+	unsigned long end_pfn;      /* end pfn of memory segment (exclusive) */
+};
+
+struct movablemem_map {
+	bool acpi;	/* true if using SRAT info */
+	int nr_map;
+	struct movablemem_entry map[MOVABLEMEM_MAP_MAX];
+	nodemask_t numa_nodes_hotplug;	/* on which nodes we specify memory */
+	nodemask_t numa_nodes_kernel;	/* on which nodes kernel resides in */
+};
+
+extern void __init insert_movablemem_map(unsigned long start_pfn,
+					 unsigned long end_pfn);
+extern int __init movablemem_map_overlap(unsigned long start_pfn,
+					 unsigned long end_pfn);
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
@@ -1395,6 +1387,9 @@ extern void setup_per_cpu_pageset(void);
 extern void zone_pcp_update(struct zone *zone);
 extern void zone_pcp_reset(struct zone *zone);
 
+/* page_alloc.c */
+extern int min_free_kbytes;
+
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
 extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
@@ -1472,13 +1467,24 @@ extern int install_special_mapping(struct mm_struct *mm,
 extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long flags,
-	vm_flags_t vm_flags, unsigned long pgoff);
-extern unsigned long do_mmap_pgoff(struct file *, unsigned long,
-        unsigned long, unsigned long,
-        unsigned long, unsigned long);
+	unsigned long len, vm_flags_t vm_flags, unsigned long pgoff);
+extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot, unsigned long flags,
+	unsigned long pgoff, unsigned long *populate);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
+#ifdef CONFIG_MMU
+extern int __mm_populate(unsigned long addr, unsigned long len,
+			 int ignore_errors);
+static inline void mm_populate(unsigned long addr, unsigned long len)
+{
+	/* Ignore errors */
+	(void) __mm_populate(addr, len, 1);
+}
+#else
+static inline void mm_populate(unsigned long addr, unsigned long len) {}
+#endif
+
 /* These take the mm semaphore themselves */
 extern unsigned long vm_brk(unsigned long, unsigned long);
 extern int vm_munmap(unsigned long, size_t);
@@ -1623,8 +1629,17 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 
-struct page *follow_page(struct vm_area_struct *, unsigned long address,
-			unsigned int foll_flags);
+struct page *follow_page_mask(struct vm_area_struct *vma,
+			      unsigned long address, unsigned int foll_flags,
+			      unsigned int *page_mask);
+
+static inline struct page *follow_page(struct vm_area_struct *vma,
+		unsigned long address, unsigned int foll_flags)
+{
+	unsigned int unused_page_mask;
+	return follow_page_mask(vma, address, foll_flags, &unused_page_mask);
+}
+
 #define FOLL_WRITE	0x01	/* check pte is writable */
 #define FOLL_TOUCH	0x02	/* mark page accessed */
 #define FOLL_GET	0x04	/* do get_page on page */
@@ -1636,6 +1651,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
+#define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
@@ -1707,7 +1723,11 @@ int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
-
+#ifdef CONFIG_MEMORY_HOTPLUG
+void vmemmap_free(struct page *memmap, unsigned long nr_pages);
+#endif
+void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
+				  unsigned long size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
@@ -1720,7 +1740,7 @@ extern int unpoison_memory(unsigned long pfn);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
-extern atomic_long_t mce_bad_pages;
+extern atomic_long_t num_poisoned_pages;
 extern int soft_offline_page(struct page *page, int flags);
 
 extern void dump_page(struct page *page);

include/linux/mm_types.h

@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/page-debug-flags.h>
 #include <linux/uprobes.h>
+#include <linux/page-flags-layout.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
@@ -173,7 +174,7 @@ struct page {
 	void *shadow;
 #endif
 
-#ifdef CONFIG_NUMA_BALANCING
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
 	int _last_nid;
 #endif
 }
@@ -414,9 +415,9 @@ struct mm_struct {
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	/*
-	 * numa_next_scan is the next time when the PTEs will me marked
-	 * pte_numa to gather statistics and migrate pages to new nodes
-	 * if necessary
+	 * numa_next_scan is the next time that the PTEs will be marked
+	 * pte_numa. NUMA hinting faults will gather statistics and migrate
+	 * pages to new nodes if necessary.
 	 */
 	unsigned long numa_next_scan;
 

include/linux/mman.h

@@ -79,6 +79,8 @@ calc_vm_flag_bits(unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
-	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    );
+	       ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) |
+	       (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ?
+							VM_POPULATE : 0);
 }
 #endif /* _LINUX_MMAN_H */

include/linux/mmzone.h

@@ -15,7 +15,7 @@
 #include <linux/seqlock.h>
 #include <linux/nodemask.h>
 #include <linux/pageblock-flags.h>
-#include <generated/bounds.h>
+#include <linux/page-flags-layout.h>
 #include <linux/atomic.h>
 #include <asm/page.h>
 
@@ -57,7 +57,9 @@ enum {
 	 */
 	MIGRATE_CMA,
 #endif
+#ifdef CONFIG_MEMORY_ISOLATION
 	MIGRATE_ISOLATE,	/* can't allocate from here */
+#endif
 	MIGRATE_TYPES
 };
 
@@ -308,24 +310,6 @@ enum zone_type {
 
 #ifndef __GENERATING_BOUNDS_H
 
-/*
- * When a memory allocation must conform to specific limitations (such
- * as being suitable for DMA) the caller will pass in hints to the
- * allocator in the gfp_mask, in the zone modifier bits.  These bits
- * are used to select a priority ordered list of memory zones which
- * match the requested limits. See gfp_zone() in include/linux/gfp.h
- */
-
-#if MAX_NR_ZONES < 2
-#define ZONES_SHIFT 0
-#elif MAX_NR_ZONES <= 2
-#define ZONES_SHIFT 1
-#elif MAX_NR_ZONES <= 4
-#define ZONES_SHIFT 2
-#else
-#error ZONES_SHIFT -- too many zones configured adjust calculation
-#endif
-
 struct zone {
 	/* Fields commonly accessed by the page allocator */
 
@@ -543,6 +527,26 @@ static inline int zone_is_oom_locked(const struct zone *zone)
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
+static inline unsigned zone_end_pfn(const struct zone *zone)
+{
+	return zone->zone_start_pfn + zone->spanned_pages;
+}
+
+static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
+{
+	return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone);
+}
+
+static inline bool zone_is_initialized(struct zone *zone)
+{
+	return !!zone->wait_table;
+}
+
+static inline bool zone_is_empty(struct zone *zone)
+{
+	return zone->spanned_pages == 0;
+}
+
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
@@ -752,11 +756,17 @@ typedef struct pglist_data {
 #define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
 
-#define node_end_pfn(nid) ({\
-	pg_data_t *__pgdat = NODE_DATA(nid);\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;\
-})
+static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
+{
+	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
+}
+
+static inline bool pgdat_is_empty(pg_data_t *pgdat)
+{
+	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
+}
 
 #include <linux/memory_hotplug.h>
 
@@ -1053,8 +1063,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
  * PA_SECTION_SHIFT		physical address to/from section number
  * PFN_SECTION_SHIFT		pfn to/from section number
  */
-#define SECTIONS_SHIFT		(MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
-
 #define PA_SECTION_SHIFT	(SECTION_SIZE_BITS)
 #define PFN_SECTION_SHIFT	(SECTION_SIZE_BITS - PAGE_SHIFT)
 

include/linux/page-flags-layout.h

+#ifndef PAGE_FLAGS_LAYOUT_H
+#define PAGE_FLAGS_LAYOUT_H
+
+#include <linux/numa.h>
+#include <generated/bounds.h>
+
+/*
+ * When a memory allocation must conform to specific limitations (such
+ * as being suitable for DMA) the caller will pass in hints to the
+ * allocator in the gfp_mask, in the zone modifier bits.  These bits
+ * are used to select a priority ordered list of memory zones which
+ * match the requested limits. See gfp_zone() in include/linux/gfp.h
+ */
+#if MAX_NR_ZONES < 2
+#define ZONES_SHIFT 0
+#elif MAX_NR_ZONES <= 2
+#define ZONES_SHIFT 1
+#elif MAX_NR_ZONES <= 4
+#define ZONES_SHIFT 2
+#else
+#error ZONES_SHIFT -- too many zones configured adjust calculation
+#endif
+
+#ifdef CONFIG_SPARSEMEM
+#include <asm/sparsemem.h>
+
+/* SECTION_SHIFT	#bits space required to store a section # */
+#define SECTIONS_SHIFT	(MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
+
+#endif /* CONFIG_SPARSEMEM */
+
+/*
+ * page->flags layout:
+ *
+ * There are five possibilities for how page->flags get laid out.  The first
+ * pair is for the normal case without sparsemem. The second pair is for
+ * sparsemem when there is plenty of space for node and section information.
+ * The last is when there is insufficient space in page->flags and a separate
+ * lookup is necessary.
+ *
+ * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |          ... | FLAGS |
+ *         " plus space for last_nid: |       NODE     | ZONE | LAST_NID ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE |          ... | FLAGS |
+ *         " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS |
+ * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
+ */
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+#define SECTIONS_WIDTH		SECTIONS_SHIFT
+#else
+#define SECTIONS_WIDTH		0
+#endif
+
+#define ZONES_WIDTH		ZONES_SHIFT
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define NODES_WIDTH		NODES_SHIFT
+#else
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#error "Vmemmap: No space for nodes field in page flags"
+#endif
+#define NODES_WIDTH		0
+#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+#define LAST_NID_SHIFT NODES_SHIFT
+#else
+#define LAST_NID_SHIFT 0
+#endif
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define LAST_NID_WIDTH LAST_NID_SHIFT
+#else
+#define LAST_NID_WIDTH 0
+#endif
+
+/*
+ * We are going to use the flags for the page to node mapping if its in
+ * there.  This includes the case where there is no node, so it is implicit.
+ */
+#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
+#define NODE_NOT_IN_PAGE_FLAGS
+#endif
+
+#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0
+#define LAST_NID_NOT_IN_PAGE_FLAGS
+#endif
+
+#endif /* _LINUX_PAGE_FLAGS_LAYOUT */

include/linux/page-isolation.h

 #ifndef __LINUX_PAGEISOLATION_H
 #define __LINUX_PAGEISOLATION_H
 
+#ifdef CONFIG_MEMORY_ISOLATION
+static inline bool is_migrate_isolate_page(struct page *page)
+{
+	return get_pageblock_migratetype(page) == MIGRATE_ISOLATE;
+}
+static inline bool is_migrate_isolate(int migratetype)
+{
+	return migratetype == MIGRATE_ISOLATE;
+}
+#else
+static inline bool is_migrate_isolate_page(struct page *page)
+{
+	return false;
+}
+static inline bool is_migrate_isolate(int migratetype)
+{
+	return false;
+}
+#endif
 
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 			 bool skip_hwpoisoned_pages);

include/linux/pm.h

@@ -537,6 +537,7 @@ struct dev_pm_info {
 	unsigned int		irq_safe:1;
 	unsigned int		use_autosuspend:1;
 	unsigned int		timer_autosuspends:1;
+	unsigned int		memalloc_noio:1;
 	enum rpm_request	request;
 	enum rpm_status		runtime_status;
 	int			runtime_error;

include/linux/pm_runtime.h

@@ -47,6 +47,7 @@ extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
 extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
 extern void pm_runtime_update_max_time_suspended(struct device *dev,
 						 s64 delta_ns);
+extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
 
 static inline bool pm_children_suspended(struct device *dev)
 {
@@ -156,6 +157,8 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev,
 						int delay) {}
 static inline unsigned long pm_runtime_autosuspend_expiration(
 				struct device *dev) { return 0; }
+static inline void pm_runtime_set_memalloc_noio(struct device *dev,
+						bool enable){}
 
 #endif /* !CONFIG_PM_RUNTIME */
 

include/linux/rmap.h

@@ -123,7 +123,7 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 	down_write(&anon_vma->root->rwsem);
 }
 
-static inline void anon_vma_unlock(struct anon_vma *anon_vma)
+static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
 {
 	up_write(&anon_vma->root->rwsem);
 }

include/linux/sched.h

@@ -51,6 +51,7 @@ struct sched_param {
 #include <linux/cred.h>
 #include <linux/llist.h>
 #include <linux/uidgid.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 
@@ -1791,6 +1792,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
 #define PF_KSWAPD	0x00040000	/* I am kswapd */
+#define PF_MEMALLOC_NOIO 0x00080000	/* Allocating memory without IO involved */
 #define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
 #define PF_KTHREAD	0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
@@ -1828,6 +1830,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+		flags &= ~__GFP_IO;
+	return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+	current->flags |= PF_MEMALLOC_NOIO;
+	return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
 /*
  * task->jobctl flags
  */

include/linux/swap.h

@@ -8,7 +8,7 @@
 #include <linux/memcontrol.h>
 #include <linux/sched.h>
 #include <linux/node.h>
-
+#include <linux/fs.h>
 #include <linux/atomic.h>
 #include <asm/page.h>
 
@@ -156,7 +156,7 @@ enum {
 	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
 };
 
-#define SWAP_CLUSTER_MAX 32
+#define SWAP_CLUSTER_MAX 32UL
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
 /*
@@ -202,6 +202,18 @@ struct swap_info_struct {
 	unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
 	atomic_t frontswap_pages;	/* frontswap pages in-use counter */
 #endif
+	spinlock_t lock;		/*
+					 * protect map scan related fields like
+					 * swap_map, lowest_bit, highest_bit,
+					 * inuse_pages, cluster_next,
+					 * cluster_nr, lowest_alloc and
+					 * highest_alloc. other fields are only
+					 * changed at swapon/swapoff, so are
+					 * protected by swap_lock. changing
+					 * flags need hold this lock and
+					 * swap_lock. If both locks need hold,
+					 * hold swap_lock first.
+					 */
 };
 
 struct swap_list_t {
@@ -209,15 +221,12 @@ struct swap_list_t {
 	int next;	/* swapfile to be used next */
 };
 
-/* Swap 50% full? Release swapcache more aggressively.. */
-#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages)
-
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
 extern unsigned long dirty_balance_reserve;
-extern unsigned int nr_free_buffer_pages(void);
-extern unsigned int nr_free_pagecache_pages(void);
+extern unsigned long nr_free_buffer_pages(void);
+extern unsigned long nr_free_pagecache_pages(void);
 
 /* Definition of global_page_state not available yet */
 #define nr_free_pages() global_page_state(NR_FREE_PAGES)
@@ -266,7 +275,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);
-extern long vm_total_pages;
+extern unsigned long vm_total_pages;
 
 #ifdef CONFIG_NUMA
 extern int zone_reclaim_mode;
@@ -330,8 +339,9 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 		sector_t *);
 
 /* linux/mm/swap_state.c */
-extern struct address_space swapper_space;
-#define total_swapcache_pages  swapper_space.nrpages
+extern struct address_space swapper_spaces[];
+#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)])
+extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *);
 extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
@@ -346,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr);
 
 /* linux/mm/swapfile.c */
-extern long nr_swap_pages;
+extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
+
+/* Swap 50% full? Release swapcache more aggressively.. */
+static inline bool vm_swap_full(void)
+{
+	return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
+}
+
+static inline long get_nr_swap_pages(void)
+{
+	return atomic_long_read(&nr_swap_pages);
+}
+
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
 extern swp_entry_t get_swap_page_of_type(int);
@@ -380,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 
 #else /* CONFIG_SWAP */
 
-#define nr_swap_pages				0L
+#define get_nr_swap_pages()			0L
 #define total_swap_pages			0L
-#define total_swapcache_pages			0UL
+#define total_swapcache_pages()			0UL
+#define vm_swap_full()				0
 
 #define si_swapinfo(val) \
 	do { (val)->freeswap = (val)->totalswap = 0; } while (0)

include/linux/vm_event_item.h

@@ -36,7 +36,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-		KSWAPD_SKIP_CONGESTION_WAIT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,

include/linux/vmstat.h

@@ -85,7 +85,7 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_numa_events(x, y) count_vm_events(x, y)
 #else
 #define count_vm_numa_event(x) do {} while (0)
-#define count_vm_numa_events(x, y) do {} while (0)
+#define count_vm_numa_events(x, y) do { (void)(y); } while (0)
 #endif /* CONFIG_NUMA_BALANCING */
 
 #define __count_zone_vm_events(item, zone, delta) \

ipc/shm.c

@@ -967,11 +967,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 	unsigned long flags;
 	unsigned long prot;
 	int acc_mode;
-	unsigned long user_addr;
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
 	struct path path;
 	fmode_t f_mode;
+	unsigned long populate = 0;
 
 	err = -EINVAL;
 	if (shmid < 0)
@@ -1070,13 +1070,15 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 			goto invalid;
 	}
 		
-	user_addr = do_mmap_pgoff(file, addr, size, prot, flags, 0);
-	*raddr = user_addr;
+	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
+	*raddr = addr;
 	err = 0;
-	if (IS_ERR_VALUE(user_addr))
-		err = (long)user_addr;
+	if (IS_ERR_VALUE(addr))
+		err = (long)addr;
 invalid:
 	up_write(&current->mm->mmap_sem);
+	if (populate)
+		mm_populate(addr, populate);
 
 out_fput:
 	fput(file);

kernel/sched/core.c

@@ -1132,18 +1132,28 @@ EXPORT_SYMBOL_GPL(kick_process);
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
-	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+	int nid = cpu_to_node(cpu);
+	const struct cpumask *nodemask = NULL;
 	enum { cpuset, possible, fail } state = cpuset;
 	int dest_cpu;
 
-	/* Look for allowed, online CPU in same node. */
-	for_each_cpu(dest_cpu, nodemask) {
-		if (!cpu_online(dest_cpu))
-			continue;
-		if (!cpu_active(dest_cpu))
-			continue;
-		if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
-			return dest_cpu;
+	/*
+	 * If the node that the cpu is on has been offlined, cpu_to_node()
+	 * will return -1. There is no cpu on the node, and we should
+	 * select the cpu on the other node.
+	 */
+	if (nid != -1) {
+		nodemask = cpumask_of_node(nid);
+
+		/* Look for allowed, online CPU in same node. */
+		for_each_cpu(dest_cpu, nodemask) {
+			if (!cpu_online(dest_cpu))
+				continue;
+			if (!cpu_active(dest_cpu))
+				continue;
+			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+				return dest_cpu;
+		}
 	}
 
 	for (;;) {

kernel/sysctl.c

@@ -105,7 +105,6 @@ extern char core_pattern[];
 extern unsigned int core_pipe_limit;
 #endif
 extern int pid_max;
-extern int min_free_kbytes;
 extern int pid_max_min, pid_max_max;
 extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;

mm/Kconfig

@@ -162,10 +162,16 @@ config MOVABLE_NODE
 	  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.
 
+#
+# Only be set on architectures that have completely implemented memory hotplug
+# feature. If you are not sure, don't touch it.
+#
+config HAVE_BOOTMEM_INFO_NODE
+	def_bool n
+
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
-	select MEMORY_ISOLATION
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
@@ -176,6 +182,8 @@ config MEMORY_HOTPLUG_SPARSE
 
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
+	select MEMORY_ISOLATION
+	select HAVE_BOOTMEM_INFO_NODE if X86_64
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 

mm/compaction.c

@@ -15,6 +15,7 @@
 #include <linux/sysctl.h>
 #include <linux/sysfs.h>
 #include <linux/balloon_compaction.h>
+#include <linux/page-isolation.h>
 #include "internal.h"
 
 #ifdef CONFIG_COMPACTION
@@ -85,7 +86,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
 static void __reset_isolation_suitable(struct zone *zone)
 {
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
 	zone->compact_cached_migrate_pfn = start_pfn;
@@ -215,7 +216,10 @@ static bool suitable_migration_target(struct page *page)
 	int migratetype = get_pageblock_migratetype(page);
 
 	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
+	if (migratetype == MIGRATE_RESERVE)
+		return false;
+
+	if (is_migrate_isolate(migratetype))
 		return false;
 
 	/* If the page is a large free page, then allow migration */
@@ -611,8 +615,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		continue;
 
 next_pageblock:
-		low_pfn += pageblock_nr_pages;
-		low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
+		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
 		last_pageblock_nr = pageblock_nr;
 	}
 
@@ -644,7 +647,7 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn;
+	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
@@ -663,7 +666,7 @@ static void isolate_freepages(struct zone *zone,
 	 */
 	high_pfn = min(low_pfn, pfn);
 
-	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	z_end_pfn = zone_end_pfn(zone);
 
 	/*
 	 * Isolate free pages until enough are available to migrate the
@@ -706,7 +709,7 @@ static void isolate_freepages(struct zone *zone,
 		 * only scans within a pageblock
 		 */
 		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, zone_end_pfn);
+		end_pfn = min(end_pfn, z_end_pfn);
 		isolated = isolate_freepages_block(cc, pfn, end_pfn,
 						   freelist, false);
 		nr_freepages += isolated;
@@ -795,7 +798,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
 
 	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);
+	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
 	/* Do not cross the free scanner or scan within a memory hole */
 	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
@@ -920,7 +923,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
-	unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	unsigned long end_pfn = zone_end_pfn(zone);
 
 	ret = compaction_suitable(zone, cc->order);
 	switch (ret) {
@@ -977,7 +980,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				(unsigned long)cc, false,
+				(unsigned long)cc,
 				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
 				MR_COMPACTION);
 		update_nr_listpages(cc);
@@ -1086,7 +1089,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 
 
 /* Compact all zones within a node */
-static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
+static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 {
 	int zoneid;
 	struct zone *zone;
@@ -1119,28 +1122,26 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 		VM_BUG_ON(!list_empty(&cc->freepages));
 		VM_BUG_ON(!list_empty(&cc->migratepages));
 	}
-
-	return 0;
 }
 
-int compact_pgdat(pg_data_t *pgdat, int order)
+void compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
 		.sync = false,
 	};
 
-	return __compact_pgdat(pgdat, &cc);
+	__compact_pgdat(pgdat, &cc);
 }
 
-static int compact_node(int nid)
+static void compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
 	};
 
-	return __compact_pgdat(NODE_DATA(nid), &cc);
+	__compact_pgdat(NODE_DATA(nid), &cc);
 }
 
 /* Compact all nodes in the system */

mm/fadvise.c

@@ -17,6 +17,7 @@
 #include <linux/fadvise.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
+#include <linux/swap.h>
 
 #include <asm/unistd.h>
 
@@ -120,9 +121,22 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index >= start_index)
-			invalidate_mapping_pages(mapping, start_index,
+		if (end_index >= start_index) {
+			unsigned long count = invalidate_mapping_pages(mapping,
+						start_index, end_index);
+
+			/*
+			 * If fewer pages were invalidated than expected then
+			 * it is possible that some of the pages were on
+			 * a per-cpu pagevec for a remote CPU. Drain all
+			 * pagevecs and try again.
+			 */
+			if (count < (end_index - start_index + 1)) {
+				lru_add_drain_all();
+				invalidate_mapping_pages(mapping, start_index,
 						end_index);
+			}
+		}
 		break;
 	default:
 		ret = -EINVAL;

mm/fremap.c

@@ -129,6 +129,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	struct vm_area_struct *vma;
 	int err = -EINVAL;
 	int has_write_lock = 0;
+	vm_flags_t vm_flags;
 
 	if (prot)
 		return err;
@@ -160,15 +161,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	/*
 	 * Make sure the vma is shared, that it supports prefaulting,
 	 * and that the remapped range is valid and fully within
-	 * the single existing vma.  vm_private_data is used as a
-	 * swapout cursor in a VM_NONLINEAR vma.
+	 * the single existing vma.
 	 */
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
-		goto out;
-
 	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
 		goto out;
 
@@ -177,6 +174,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 
 	/* Must set VM_NONLINEAR before any pages are populated. */
 	if (!(vma->vm_flags & VM_NONLINEAR)) {
+		/*
+		 * vm_private_data is used as a swapout cursor
+		 * in a VM_NONLINEAR vma.
+		 */
+		if (vma->vm_private_data)
+			goto out;
+
 		/* Don't need a nonlinear mapping, exit success */
 		if (pgoff == linear_page_index(vma, start)) {
 			err = 0;
@@ -184,6 +188,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		}
 
 		if (!has_write_lock) {
+get_write_lock:
 			up_read(&mm->mmap_sem);
 			down_write(&mm->mmap_sem);
 			has_write_lock = 1;
@@ -199,9 +204,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
 
-			flags &= MAP_NONBLOCK;
-			addr = mmap_region(file, start, size,
-					flags, vma->vm_flags, pgoff);
+			vm_flags = vma->vm_flags;
+			if (!(flags & MAP_NONBLOCK))
+				vm_flags |= VM_POPULATE;
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -220,32 +226,26 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
+	if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
+		if (!has_write_lock)
+			goto get_write_lock;
+		vma->vm_flags |= VM_POPULATE;
+	}
+
 	if (vma->vm_flags & VM_LOCKED) {
 		/*
 		 * drop PG_Mlocked flag for over-mapped range
 		 */
-		vm_flags_t saved_flags = vma->vm_flags;
+		if (!has_write_lock)
+			goto get_write_lock;
+		vm_flags = vma->vm_flags;
 		munlock_vma_pages_range(vma, start, start + size);
-		vma->vm_flags = saved_flags;
+		vma->vm_flags = vm_flags;
 	}
 
 	mmu_notifier_invalidate_range_start(mm, start, start + size);
 	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
 	mmu_notifier_invalidate_range_end(mm, start, start + size);
-	if (!err && !(flags & MAP_NONBLOCK)) {
-		if (vma->vm_flags & VM_LOCKED) {
-			/*
-			 * might be mapping previously unmapped range of file
-			 */
-			mlock_vma_pages_range(vma, start, start + size);
-		} else {
-			if (unlikely(has_write_lock)) {
-				downgrade_write(&mm->mmap_sem);
-				has_write_lock = 0;
-			}
-			make_pages_present(start, start+size);
-		}
-	}
 
 	/*
 	 * We can't clear VM_NONLINEAR because we'd have to do
@@ -254,10 +254,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	 */
 
 out:
+	vm_flags = vma->vm_flags;
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
 		up_write(&mm->mmap_sem);
+	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
+		mm_populate(start, size);
 
 	return err;
 }

mm/huge_memory.c

@@ -20,6 +20,7 @@
 #include <linux/mman.h>
 #include <linux/pagemap.h>
 #include <linux/migrate.h>
+#include <linux/hashtable.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -62,12 +63,11 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
 static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
 
 static int khugepaged(void *none);
-static int mm_slots_hash_init(void);
 static int khugepaged_slab_init(void);
-static void khugepaged_slab_free(void);
 
-#define MM_SLOTS_HASH_HEADS 1024
-static struct hlist_head *mm_slots_hash __read_mostly;
+#define MM_SLOTS_HASH_BITS 10
+static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
+
 static struct kmem_cache *mm_slot_cache __read_mostly;
 
 /**
@@ -105,7 +105,6 @@ static int set_recommended_min_free_kbytes(void)
 	struct zone *zone;
 	int nr_zones = 0;
 	unsigned long recommended_min;
-	extern int min_free_kbytes;
 
 	if (!khugepaged_enabled())
 		return 0;
@@ -634,12 +633,6 @@ static int __init hugepage_init(void)
 	if (err)
 		goto out;
 
-	err = mm_slots_hash_init();
-	if (err) {
-		khugepaged_slab_free();
-		goto out;
-	}
-
 	register_shrinker(&huge_zero_page_shrinker);
 
 	/*
@@ -1302,7 +1295,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int target_nid;
 	int current_nid = -1;
 	bool migrated;
-	bool page_locked = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1324,7 +1316,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Acquire the page lock to serialise THP migrations */
 	spin_unlock(&mm->page_table_lock);
 	lock_page(page);
-	page_locked = true;
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
@@ -1337,34 +1328,26 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Migrate the THP to the requested node */
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
-				pmdp, pmd, addr,
-				page, target_nid);
-	if (migrated)
-		current_nid = target_nid;
-	else {
-		spin_lock(&mm->page_table_lock);
-		if (unlikely(!pmd_same(pmd, *pmdp))) {
-			unlock_page(page);
-			goto out_unlock;
-		}
-		goto clear_pmdnuma;
-	}
+				pmdp, pmd, addr, page, target_nid);
+	if (!migrated)
+		goto check_same;
 
-	task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
 	return 0;
 
+check_same:
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
 clear_pmdnuma:
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
-	if (page_locked)
-		unlock_page(page);
-
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
 	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
 	return 0;
 }
 
@@ -1656,7 +1639,7 @@ static void __split_huge_page_refcount(struct page *page)
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_xchg_last_nid(page_tail, page_last_nid(page));
+		page_nid_xchg_last(page_tail, page_nid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
@@ -1846,7 +1829,7 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_write(anon_vma);
 	put_anon_vma(anon_vma);
 out:
 	return ret;
@@ -1908,12 +1891,6 @@ static int __init khugepaged_slab_init(void)
 	return 0;
 }
 
-static void __init khugepaged_slab_free(void)
-{
-	kmem_cache_destroy(mm_slot_cache);
-	mm_slot_cache = NULL;
-}
-
 static inline struct mm_slot *alloc_mm_slot(void)
 {
 	if (!mm_slot_cache)	/* initialization failed */
@@ -1926,47 +1903,23 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 	kmem_cache_free(mm_slot_cache, mm_slot);
 }
 
-static int __init mm_slots_hash_init(void)
-{
-	mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
-				GFP_KERNEL);
-	if (!mm_slots_hash)
-		return -ENOMEM;
-	return 0;
-}
-
-#if 0
-static void __init mm_slots_hash_free(void)
-{
-	kfree(mm_slots_hash);
-	mm_slots_hash = NULL;
-}
-#endif
-
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
 	struct mm_slot *mm_slot;
-	struct hlist_head *bucket;
 	struct hlist_node *node;
 
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
-	hlist_for_each_entry(mm_slot, node, bucket, hash) {
+	hash_for_each_possible(mm_slots_hash, mm_slot, node, hash, (unsigned long)mm)
 		if (mm == mm_slot->mm)
 			return mm_slot;
-	}
+
 	return NULL;
 }
 
 static void insert_to_mm_slots_hash(struct mm_struct *mm,
 				    struct mm_slot *mm_slot)
 {
-	struct hlist_head *bucket;
-
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
 	mm_slot->mm = mm;
-	hlist_add_head(&mm_slot->hash, bucket);
+	hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
 }
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
@@ -2035,7 +1988,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 	spin_lock(&khugepaged_mm_lock);
 	mm_slot = get_mm_slot(mm);
 	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 		free = 1;
 	}
@@ -2368,7 +2321,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		BUG_ON(!pmd_none(*pmd));
 		set_pmd_at(mm, address, pmd, _pmd);
 		spin_unlock(&mm->page_table_lock);
-		anon_vma_unlock(vma->anon_vma);
+		anon_vma_unlock_write(vma->anon_vma);
 		goto out;
 	}
 
@@ -2376,7 +2329,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * All pages are isolated and locked so anon_vma rmap
 	 * can't run anymore.
 	 */
-	anon_vma_unlock(vma->anon_vma);
+	anon_vma_unlock_write(vma->anon_vma);
 
 	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
 	pte_unmap(pte);
@@ -2423,7 +2376,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	struct page *page;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = -1;
+	int node = NUMA_NO_NODE;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
@@ -2453,7 +2406,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 * be more sophisticated and look at more pages,
 		 * but isn't for now.
 		 */
-		if (node == -1)
+		if (node == NUMA_NO_NODE)
 			node = page_to_nid(page);
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
@@ -2484,7 +2437,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 
 	if (khugepaged_test_exit(mm)) {
 		/* free mm_slot */
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 
 		/*

mm/hugetlb.c

@@ -1293,8 +1293,7 @@ static void __init report_hugepages(void)
 
 	for_each_hstate(h) {
 		char buf[32];
-		printk(KERN_INFO "HugeTLB registered %s page size, "
-				 "pre-allocated %ld pages\n",
+		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
 			memfmt(buf, huge_page_size(h)),
 			h->free_huge_pages);
 	}
@@ -1702,8 +1701,7 @@ static void __init hugetlb_sysfs_init(void)
 		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
 					 hstate_kobjs, &hstate_attr_group);
 		if (err)
-			printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
-								h->name);
+			pr_err("Hugetlb: Unable to add hstate %s", h->name);
 	}
 }
 
@@ -1826,9 +1824,8 @@ void hugetlb_register_node(struct node *node)
 						nhs->hstate_kobjs,
 						&per_node_hstate_attr_group);
 		if (err) {
-			printk(KERN_ERR "Hugetlb: Unable to add hstate %s"
-					" for node %d\n",
-						h->name, node->dev.id);
+			pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
+				h->name, node->dev.id);
 			hugetlb_unregister_node(node);
 			break;
 		}
@@ -1924,7 +1921,7 @@ void __init hugetlb_add_hstate(unsigned order)
 	unsigned long i;
 
 	if (size_to_hstate(PAGE_SIZE << order)) {
-		printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
+		pr_warning("hugepagesz= specified twice, ignoring\n");
 		return;
 	}
 	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
@@ -1960,8 +1957,8 @@ static int __init hugetlb_nrpages_setup(char *s)
 		mhp = &parsed_hstate->max_huge_pages;
 
 	if (mhp == last_mhp) {
-		printk(KERN_WARNING "hugepages= specified twice without "
-			"interleaving hugepagesz=, ignoring\n");
+		pr_warning("hugepages= specified twice without "
+			   "interleaving hugepagesz=, ignoring\n");
 		return 1;
 	}
 
@@ -2692,9 +2689,8 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * COW. Warn that such a situation has occurred as it may not be obvious
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
-		printk(KERN_WARNING
-			"PID %d killed due to inadequate hugepage pool\n",
-			current->pid);
+		pr_warning("PID %d killed due to inadequate hugepage pool\n",
+			   current->pid);
 		return ret;
 	}
 
@@ -2924,14 +2920,14 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
-int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			struct page **pages, struct vm_area_struct **vmas,
-			unsigned long *position, int *length, int i,
-			unsigned int flags)
+long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			 struct page **pages, struct vm_area_struct **vmas,
+			 unsigned long *position, unsigned long *nr_pages,
+			 long i, unsigned int flags)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
-	int remainder = *length;
+	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
 	spin_lock(&mm->page_table_lock);
@@ -3001,7 +2997,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	*length = remainder;
+	*nr_pages = remainder;
 	*position = vaddr;
 
 	return i ? i : -EFAULT;

mm/internal.h

@@ -162,8 +162,8 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);
 
 #ifdef CONFIG_MMU
-extern long mlock_vma_pages_range(struct vm_area_struct *vma,
-			unsigned long start, unsigned long end);
+extern long __mlock_vma_pages_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, int *nonblocking);
 extern void munlock_vma_pages_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
 static inline void munlock_vma_pages_all(struct vm_area_struct *vma)

mm/kmemleak.c

@@ -1300,9 +1300,8 @@ static void kmemleak_scan(void)
 	 */
 	lock_memory_hotplug();
 	for_each_online_node(i) {
-		pg_data_t *pgdat = NODE_DATA(i);
-		unsigned long start_pfn = pgdat->node_start_pfn;
-		unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+		unsigned long start_pfn = node_start_pfn(i);
+		unsigned long end_pfn = node_end_pfn(i);
 		unsigned long pfn;
 
 		for (pfn = start_pfn; pfn < end_pfn; pfn++) {

mm/madvise.c

@@ -16,6 +16,9 @@
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -131,6 +134,84 @@ static long madvise_behavior(struct vm_area_struct * vma,
 	return error;
 }
 
+#ifdef CONFIG_SWAP
+static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
+	unsigned long end, struct mm_walk *walk)
+{
+	pte_t *orig_pte;
+	struct vm_area_struct *vma = walk->private;
+	unsigned long index;
+
+	if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+		return 0;
+
+	for (index = start; index != end; index += PAGE_SIZE) {
+		pte_t pte;
+		swp_entry_t entry;
+		struct page *page;
+		spinlock_t *ptl;
+
+		orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
+		pte_unmap_unlock(orig_pte, ptl);
+
+		if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+			continue;
+		entry = pte_to_swp_entry(pte);
+		if (unlikely(non_swap_entry(entry)))
+			continue;
+
+		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+								vma, index);
+		if (page)
+			page_cache_release(page);
+	}
+
+	return 0;
+}
+
+static void force_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	struct mm_walk walk = {
+		.mm = vma->vm_mm,
+		.pmd_entry = swapin_walk_pmd_entry,
+		.private = vma,
+	};
+
+	walk_page_range(start, end, &walk);
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+
+static void force_shm_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct address_space *mapping)
+{
+	pgoff_t index;
+	struct page *page;
+	swp_entry_t swap;
+
+	for (; start < end; start += PAGE_SIZE) {
+		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+		page = find_get_page(mapping, index);
+		if (!radix_tree_exceptional_entry(page)) {
+			if (page)
+				page_cache_release(page);
+			continue;
+		}
+		swap = radix_to_swp_entry(page);
+		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
+								NULL, 0);
+		if (page)
+			page_cache_release(page);
+	}
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+#endif		/* CONFIG_SWAP */
+
 /*
  * Schedule all required I/O operations.  Do not wait for completion.
  */
@@ -140,6 +221,18 @@ static long madvise_willneed(struct vm_area_struct * vma,
 {
 	struct file *file = vma->vm_file;
 
+#ifdef CONFIG_SWAP
+	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+		*prev = vma;
+		if (!file)
+			force_swapin_readahead(vma, start, end);
+		else
+			force_shm_swapin_readahead(vma, start, end,
+						file->f_mapping);
+		return 0;
+	}
+#endif
+
 	if (!file)
 		return -EBADF;
 
@@ -371,6 +464,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int error = -EINVAL;
 	int write;
 	size_t len;
+	struct blk_plug plug;
 
 #ifdef CONFIG_MEMORY_FAILURE
 	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
@@ -410,18 +504,19 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
+	blk_start_plug(&plug);
 	for (;;) {
 		/* Still start < end. */
 		error = -ENOMEM;
 		if (!vma)
-			goto out;
+			goto out_plug;
 
 		/* Here start < (end|vma->vm_end). */
 		if (start < vma->vm_start) {
 			unmapped_error = -ENOMEM;
 			start = vma->vm_start;
 			if (start >= end)
-				goto out;
+				goto out_plug;
 		}
 
 		/* Here vma->vm_start <= start < (end|vma->vm_end) */
@@ -432,18 +527,20 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
 		error = madvise_vma(vma, &prev, start, tmp, behavior);
 		if (error)
-			goto out;
+			goto out_plug;
 		start = tmp;
 		if (prev && start < prev->vm_end)
 			start = prev->vm_end;
 		error = unmapped_error;
 		if (start >= end)
-			goto out;
+			goto out_plug;
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_sem */
 			vma = find_vma(current->mm, start);
 	}
+out_plug:
+	blk_finish_plug(&plug);
 out:
 	if (write)
 		up_write(&current->mm->mmap_sem);

mm/memblock.c

@@ -92,9 +92,58 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
+ * If we have CONFIG_HAVE_MEMBLOCK_NODE_MAP defined, we need to check if the
+ * memory we found if not in hotpluggable ranges.
+ *
  * RETURNS:
  * Found address on success, %0 on failure.
  */
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
+					phys_addr_t end, phys_addr_t size,
+					phys_addr_t align, int nid)
+{
+	phys_addr_t this_start, this_end, cand;
+	u64 i;
+	int curr = movablemem_map.nr_map - 1;
+
+	/* 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);
+
+	for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+restart:
+		if (this_end <= this_start || this_end < size)
+			continue;
+
+		for (; curr >= 0; curr--) {
+			if ((movablemem_map.map[curr].start_pfn << PAGE_SHIFT)
+			    < this_end)
+				break;
+		}
+
+		cand = round_down(this_end - size, align);
+		if (curr >= 0 &&
+		    cand < movablemem_map.map[curr].end_pfn << PAGE_SHIFT) {
+			this_end = movablemem_map.map[curr].start_pfn
+				   << PAGE_SHIFT;
+			goto restart;
+		}
+
+		if (cand >= this_start)
+			return cand;
+	}
+
+	return 0;
+}
+#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 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)
@@ -123,6 +172,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	}
 	return 0;
 }
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 /**
  * memblock_find_in_range - find free area in given range

mm/memory.c

@@ -69,6 +69,10 @@
 
 #include "internal.h"
 
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#endif
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
@@ -1458,10 +1462,11 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 EXPORT_SYMBOL_GPL(zap_vma_ptes);
 
 /**
- * follow_page - look up a page descriptor from a user-virtual address
+ * follow_page_mask - look up a page descriptor from a user-virtual address
  * @vma: vm_area_struct mapping @address
  * @address: virtual address to look up
  * @flags: flags modifying lookup behaviour
+ * @page_mask: on output, *page_mask is set according to the size of the page
  *
  * @flags can have FOLL_ flags set, defined in <linux/mm.h>
  *
@@ -1469,8 +1474,9 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
  * an error pointer if there is a mapping to something not represented
  * by a page descriptor (see also vm_normal_page()).
  */
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
-			unsigned int flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+			      unsigned long address, unsigned int flags,
+			      unsigned int *page_mask)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -1480,6 +1486,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 
+	*page_mask = 0;
+
 	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
 	if (!IS_ERR(page)) {
 		BUG_ON(flags & FOLL_GET);
@@ -1526,6 +1534,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 				page = follow_trans_huge_pmd(vma, address,
 							     pmd, flags);
 				spin_unlock(&mm->page_table_lock);
+				*page_mask = HPAGE_PMD_NR - 1;
 				goto out;
 			}
 		} else
@@ -1539,8 +1548,24 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 
 	pte = *ptep;
-	if (!pte_present(pte))
-		goto no_page;
+	if (!pte_present(pte)) {
+		swp_entry_t entry;
+		/*
+		 * KSM's break_ksm() relies upon recognizing a ksm page
+		 * even while it is being migrated, so for that case we
+		 * need migration_entry_wait().
+		 */
+		if (likely(!(flags & FOLL_MIGRATION)))
+			goto no_page;
+		if (pte_none(pte) || pte_file(pte))
+			goto no_page;
+		entry = pte_to_swp_entry(pte);
+		if (!is_migration_entry(entry))
+			goto no_page;
+		pte_unmap_unlock(ptep, ptl);
+		migration_entry_wait(mm, pmd, address);
+		goto split_fallthrough;
+	}
 	if ((flags & FOLL_NUMA) && pte_numa(pte))
 		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
@@ -1673,15 +1698,16 @@ static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long add
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int nr_pages, unsigned int gup_flags,
-		     struct page **pages, struct vm_area_struct **vmas,
-		     int *nonblocking)
+long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas, int *nonblocking)
 {
-	int i;
+	long i;
 	unsigned long vm_flags;
+	unsigned int page_mask;
 
-	if (nr_pages <= 0)
+	if (!nr_pages)
 		return 0;
 
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
@@ -1757,6 +1783,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				get_page(page);
 			}
 			pte_unmap(pte);
+			page_mask = 0;
 			goto next_page;
 		}
 
@@ -1774,6 +1801,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		do {
 			struct page *page;
 			unsigned int foll_flags = gup_flags;
+			unsigned int page_increm;
 
 			/*
 			 * If we have a pending SIGKILL, don't keep faulting
@@ -1783,7 +1811,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				return i ? i : -ERESTARTSYS;
 
 			cond_resched();
-			while (!(page = follow_page(vma, start, foll_flags))) {
+			while (!(page = follow_page_mask(vma, start,
+						foll_flags, &page_mask))) {
 				int ret;
 				unsigned int fault_flags = 0;
 
@@ -1857,13 +1886,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 				flush_anon_page(vma, page, start);
 				flush_dcache_page(page);
+				page_mask = 0;
 			}
 next_page:
-			if (vmas)
+			if (vmas) {
 				vmas[i] = vma;
-			i++;
-			start += PAGE_SIZE;
-			nr_pages--;
+				page_mask = 0;
+			}
+			page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+			if (page_increm > nr_pages)
+				page_increm = nr_pages;
+			i += page_increm;
+			start += page_increm * PAGE_SIZE;
+			nr_pages -= page_increm;
 		} while (nr_pages && start < vma->vm_end);
 	} while (nr_pages);
 	return i;
@@ -1977,9 +2012,9 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
  *
  * See also get_user_pages_fast, for performance critical applications.
  */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, int nr_pages, int write, int force,
-		struct page **pages, struct vm_area_struct **vmas)
+long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages, int write,
+		int force, struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = FOLL_TOUCH;
 
@@ -2919,7 +2954,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
-	struct page *page, *swapcache = NULL;
+	struct page *page, *swapcache;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
@@ -2970,9 +3005,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		ret = VM_FAULT_HWPOISON;
 		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+		swapcache = page;
 		goto out_release;
 	}
 
+	swapcache = page;
 	locked = lock_page_or_retry(page, mm, flags);
 
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
@@ -2990,16 +3027,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
 		goto out_page;
 
-	if (ksm_might_need_to_copy(page, vma, address)) {
-		swapcache = page;
-		page = ksm_does_need_to_copy(page, vma, address);
-
-		if (unlikely(!page)) {
-			ret = VM_FAULT_OOM;
-			page = swapcache;
-			swapcache = NULL;
-			goto out_page;
-		}
+	page = ksm_might_need_to_copy(page, vma, address);
+	if (unlikely(!page)) {
+		ret = VM_FAULT_OOM;
+		page = swapcache;
+		goto out_page;
 	}
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
@@ -3044,7 +3076,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
-	do_page_add_anon_rmap(page, vma, address, exclusive);
+	if (page == swapcache)
+		do_page_add_anon_rmap(page, vma, address, exclusive);
+	else /* ksm created a completely new copy */
+		page_add_new_anon_rmap(page, vma, address);
 	/* It's better to call commit-charge after rmap is established */
 	mem_cgroup_commit_charge_swapin(page, ptr);
 
@@ -3052,7 +3087,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
-	if (swapcache) {
+	if (page != swapcache) {
 		/*
 		 * Hold the lock to avoid the swap entry to be reused
 		 * until we take the PT lock for the pte_same() check
@@ -3085,7 +3120,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unlock_page(page);
 out_release:
 	page_cache_release(page);
-	if (swapcache) {
+	if (page != swapcache) {
 		unlock_page(swapcache);
 		page_cache_release(swapcache);
 	}
@@ -3821,30 +3856,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int make_pages_present(unsigned long addr, unsigned long end)
-{
-	int ret, len, write;
-	struct vm_area_struct * vma;
-
-	vma = find_vma(current->mm, addr);
-	if (!vma)
-		return -ENOMEM;
-	/*
-	 * We want to touch writable mappings with a write fault in order
-	 * to break COW, except for shared mappings because these don't COW
-	 * and we would not want to dirty them for nothing.
-	 */
-	write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
-	BUG_ON(addr >= end);
-	BUG_ON(end > vma->vm_end);
-	len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
-	ret = get_user_pages(current, current->mm, addr,
-			len, write, 0, NULL, NULL);
-	if (ret < 0)
-		return ret;
-	return ret == len ? 0 : -EFAULT;
-}
-
 #if !defined(__HAVE_ARCH_GATE_AREA)
 
 #if defined(AT_SYSINFO_EHDR)

mm/mincore.c

@@ -75,7 +75,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	/* shmem/tmpfs may return swap: account for swapcache page too. */
 	if (radix_tree_exceptional_entry(page)) {
 		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(&swapper_space, swap.val);
+		page = find_get_page(swap_address_space(swap), swap.val);
 	}
 #endif
 	if (page) {
@@ -135,7 +135,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			} else {
 #ifdef CONFIG_SWAP
 				pgoff = entry.val;
-				*vec = mincore_page(&swapper_space, pgoff);
+				*vec = mincore_page(swap_address_space(entry),
+					pgoff);
 #else
 				WARN_ON(1);
 				*vec = 1;

mm/mmzone.c

 /*
  * linux/mm/mmzone.c
  *
- * management codes for pgdats and zones.
+ * management codes for pgdats, zones and page flags
  */
 
 
@@ -96,3 +96,21 @@ void lruvec_init(struct lruvec *lruvec)
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 }
+
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS)
+int page_nid_xchg_last(struct page *page, int nid)
+{
+	unsigned long old_flags, flags;
+	int last_nid;
+
+	do {
+		old_flags = flags = page->flags;
+		last_nid = page_nid_last(page);
+
+		flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
+		flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
+
+	return last_nid;
+}
+#endif

mm/oom_kill.c

@@ -386,8 +386,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	cpuset_print_task_mems_allowed(current);
 	task_unlock(current);
 	dump_stack();
-	mem_cgroup_print_oom_info(memcg, p);
-	show_mem(SHOW_MEM_FILTER_NODES);
+	if (memcg)
+		mem_cgroup_print_oom_info(memcg, p);
+	else
+		show_mem(SHOW_MEM_FILTER_NODES);
 	if (sysctl_oom_dump_tasks)
 		dump_tasks(memcg, nodemask);
 }