Merge branch 'akpm' (incoming from Andrew)

Merge first patch-bomb from Andrew Morton:

 - a couple of misc things

 - inotify/fsnotify work from Jan

 - ocfs2 updates (partial)

 - about half of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  mm/migrate: remove unused function, fail_migrate_page()
  mm/migrate: remove putback_lru_pages, fix comment on putback_movable_pages
  mm/migrate: correct failure handling if !hugepage_migration_support()
  mm/migrate: add comment about permanent failure path
  mm, page_alloc: warn for non-blockable __GFP_NOFAIL allocation failure
  mm: compaction: reset scanner positions immediately when they meet
  mm: compaction: do not mark unmovable pageblocks as skipped in async compaction
  mm: compaction: detect when scanners meet in isolate_freepages
  mm: compaction: reset cached scanner pfn's before reading them
  mm: compaction: encapsulate defer reset logic
  mm: compaction: trace compaction begin and end
  memcg, oom: lock mem_cgroup_print_oom_info
  sched: add tracepoints related to NUMA task migration
  mm: numa: do not automatically migrate KSM pages
  mm: numa: trace tasks that fail migration due to rate limiting
  mm: numa: limit scope of lock for NUMA migrate rate limiting
  mm: numa: make NUMA-migrate related functions static
  lib/show_mem.c: show num_poisoned_pages when oom
  mm/hwpoison: add '#' to hwpoison_inject
  mm/memblock: use WARN_ONCE when MAX_NUMNODES passed as input parameter
  ...

28 files changed, 153 insertions, 212 deletions

diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index 58b8c6a0ab1f..99084431d6ae 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -8,8 +8,8 @@
 #define MAX_DMA_ADDRESS	0xffffffffUL
 #else
 #define MAX_DMA_ADDRESS	({ \
-	extern unsigned long arm_dma_zone_size; \
-	arm_dma_zone_size ? \
+	extern phys_addr_t arm_dma_zone_size; \
+	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
 		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 34d5fd585bbb..f751714d52c1 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -33,7 +33,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
-	return alloc_bootmem_align(size, align);
+	return memblock_virt_alloc(size, align);
 }
 
 void __init arm_dt_memblock_reserve(void)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 987a7f5bce5f..8ce1cbd08dba 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -717,7 +717,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for_each_memblock(memory, region) {
-		res = alloc_bootmem_low(sizeof(*res));
+		res = memblock_virt_alloc(sizeof(*res), 0);
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 8a1b5e0bad40..f7a6fd35b1e4 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2791,9 +2791,7 @@ static int __init _alloc_links(struct omap_hwmod_link **ml,
 	sz = sizeof(struct omap_hwmod_link) * LINKS_PER_OCP_IF;
 
 	*sl = NULL;
-	*ml = alloc_bootmem(sz);
-
-	memset(*ml, 0, sz);
+	*ml = memblock_virt_alloc(sz, 0);
 
 	*sl = (void *)(*ml) + sizeof(struct omap_hwmod_link);
 
@@ -2912,9 +2910,7 @@ static int __init _alloc_linkspace(struct omap_hwmod_ocp_if **ois)
 	pr_debug("omap_hwmod: %s: allocating %d byte linkspace (%d links)\n",
 		 __func__, sz, max_ls);
 
-	linkspace = alloc_bootmem(sz);
-
-	memset(linkspace, 0, sz);
+	linkspace = memblock_virt_alloc(sz, 0);
 
 	return 0;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 3e8f106ee5fe..11eb8add7820 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -92,9 +92,6 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-
 	for_each_bank (i, mi) {
 		struct membank *bank = &mi->bank[i];
 		unsigned int pfn1, pfn2;
@@ -461,7 +458,7 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * free the section of the memmap array.
 	 */
 	if (pg < pgend)
-		free_bootmem(pg, pgend - pg);
+		memblock_free_early(pg, pgend - pg);
 }
 
 /*
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index da5237d636d6..52715a71aede 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -31,74 +31,6 @@
 static unsigned long max_gap;
 #endif
 
-/**
- * show_mem - give short summary of memory stats
- *
- * Shows a simple page count of reserved and used pages in the system.
- * For discontig machines, it does this on a per-pgdat basis.
- */
-void show_mem(unsigned int filter)
-{
-	int i, total_reserved = 0;
-	int total_shared = 0, total_cached = 0;
-	unsigned long total_present = 0;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas(filter);
-	printk(KERN_INFO "Node memory in pages:\n");
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-	for_each_online_pgdat(pgdat) {
-		unsigned long present;
-		unsigned long flags;
-		int shared = 0, cached = 0, reserved = 0;
-		int nid = pgdat->node_id;
-
-		if (skip_free_areas_node(filter, nid))
-			continue;
-		pgdat_resize_lock(pgdat, &flags);
-		present = pgdat->node_present_pages;
-		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page;
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			if (pfn_valid(pgdat->node_start_pfn + i))
-				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else {
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-				if (max_gap < LARGE_GAP)
-					continue;
-#endif
-				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
-				continue;
-			}
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page)-1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-		total_present += present;
-		total_reserved += reserved;
-		total_cached += cached;
-		total_shared += shared;
-		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", nid,
-		       present, reserved, shared, cached);
-	}
-	printk(KERN_INFO "%ld pages of RAM\n", total_present);
-	printk(KERN_INFO "%d reserved pages\n", total_reserved);
-	printk(KERN_INFO "%d pages shared\n", total_shared);
-	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 "%ld free buffer pages\n", nr_free_buffer_pages());
-}
-
-
 /* physical address where the bootmem map is located */
 unsigned long bootmap_start;
 
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 2de08f4d9930..878626805369 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -608,69 +608,6 @@ void *per_cpu_init(void)
 #endif /* CONFIG_SMP */
 
 /**
- * show_mem - give short summary of memory stats
- *
- * Shows a simple page count of reserved and used pages in the system.
- * For discontig machines, it does this on a per-pgdat basis.
- */
-void show_mem(unsigned int filter)
-{
-	int i, total_reserved = 0;
-	int total_shared = 0, total_cached = 0;
-	unsigned long total_present = 0;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas(filter);
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-	printk(KERN_INFO "Node memory in pages:\n");
-	for_each_online_pgdat(pgdat) {
-		unsigned long present;
-		unsigned long flags;
-		int shared = 0, cached = 0, reserved = 0;
-		int nid = pgdat->node_id;
-
-		if (skip_free_areas_node(filter, nid))
-			continue;
-		pgdat_resize_lock(pgdat, &flags);
-		present = pgdat->node_present_pages;
-		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page;
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			if (pfn_valid(pgdat->node_start_pfn + i))
-				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else {
-				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
-				continue;
-			}
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page)-1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-		total_present += present;
-		total_reserved += reserved;
-		total_cached += cached;
-		total_shared += shared;
-		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", nid,
-		       present, reserved, shared, cached);
-	}
-	printk(KERN_INFO "%ld pages of RAM\n", total_present);
-	printk(KERN_INFO "%d reserved pages\n", total_reserved);
-	printk(KERN_INFO "%d pages shared\n", total_shared);
-	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 "%ld free buffer pages\n", nr_free_buffer_pages());
-}
-
-/**
  * call_pernode_memory - use SRAT to call callback functions with node info
  * @start: physical start of range
  * @len: length of range
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 88504abf5704..25c350264a41 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -684,3 +684,51 @@ per_linux32_init(void)
 }
 
 __initcall(per_linux32_init);
+
+/**
+ * show_mem - give short summary of memory stats
+ *
+ * Shows a simple page count of reserved and used pages in the system.
+ * For discontig machines, it does this on a per-pgdat basis.
+ */
+void show_mem(unsigned int filter)
+{
+	int total_reserved = 0;
+	unsigned long total_present = 0;
+	pg_data_t *pgdat;
+
+	printk(KERN_INFO "Mem-info:\n");
+	show_free_areas(filter);
+	printk(KERN_INFO "Node memory in pages:\n");
+	for_each_online_pgdat(pgdat) {
+		unsigned long present;
+		unsigned long flags;
+		int reserved = 0;
+		int nid = pgdat->node_id;
+		int zoneid;
+
+		if (skip_free_areas_node(filter, nid))
+			continue;
+		pgdat_resize_lock(pgdat, &flags);
+
+		for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+			struct zone *zone = &pgdat->node_zones[zoneid];
+			if (!populated_zone(zone))
+				continue;
+
+			reserved += zone->present_pages - zone->managed_pages;
+		}
+		present = pgdat->node_present_pages;
+
+		pgdat_resize_unlock(pgdat, &flags);
+		total_present += present;
+		total_reserved += reserved;
+		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, ",
+		       nid, present, reserved);
+	}
+	printk(KERN_INFO "%ld pages of RAM\n", total_present);
+	printk(KERN_INFO "%d reserved pages\n", total_reserved);
+	printk(KERN_INFO "Total of %ld pages in page table cache\n",
+	       quicklist_total_size());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
+}
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 3cd6288f65c2..11fa51c89617 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -204,7 +204,8 @@ static void __init do_init_bootmem(void)
 		start_pfn = memblock_region_memory_base_pfn(reg);
 		end_pfn = memblock_region_memory_end_pfn(reg);
 		memblock_set_node(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn), 0);
+				  PFN_PHYS(end_pfn - start_pfn),
+				  &memblock.memory, 0);
 	}
 
 	/* All of system RAM sits in node 0 for the non-NUMA case */
diff --git a/arch/metag/mm/numa.c b/arch/metag/mm/numa.c
index b172aa45fcf8..67b46c295072 100644
--- a/arch/metag/mm/numa.c
+++ b/arch/metag/mm/numa.c
@@ -42,7 +42,8 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 	memblock_add(start, end - start);
 
 	memblock_set_node(PFN_PHYS(start_pfn),
-			  PFN_PHYS(end_pfn - start_pfn), nid);
+			  PFN_PHYS(end_pfn - start_pfn),
+			  &memblock.memory, nid);
 
 	/* Node-local pgdat */
 	pgdat_paddr = memblock_alloc_base(sizeof(struct pglist_data),
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 74c7bcc1e82d..89077d346714 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -192,7 +192,8 @@ void __init setup_memory(void)
 		start_pfn = memblock_region_memory_base_pfn(reg);
 		end_pfn = memblock_region_memory_end_pfn(reg);
 		memblock_set_node(start_pfn << PAGE_SHIFT,
-					(end_pfn - start_pfn) << PAGE_SHIFT, 0);
+				  (end_pfn - start_pfn) << PAGE_SHIFT,
+				  &memblock.memory, 0);
 	}
 
 	/* free bootmem is whole main memory */
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 96f8168cf4ec..ae085ad0fba0 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -645,55 +645,30 @@ EXPORT_SYMBOL(empty_zero_page);
 
 void show_mem(unsigned int filter)
 {
-	int i,free = 0,total = 0,reserved = 0;
-	int shared = 0, cached = 0;
+	int total = 0,reserved = 0;
+	pg_data_t *pgdat;
 
 	printk(KERN_INFO "Mem-info:\n");
 	show_free_areas(filter);
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-#ifndef CONFIG_DISCONTIGMEM
-	i = max_mapnr;
-	while (i-- > 0) {
-		total++;
-		if (PageReserved(mem_map+i))
-			reserved++;
-		else if (PageSwapCache(mem_map+i))
-			cached++;
-		else if (!page_count(&mem_map[i]))
-			free++;
-		else
-			shared += page_count(&mem_map[i]) - 1;
-	}
-#else
-	for (i = 0; i < npmem_ranges; i++) {
-		int j;
 
-		for (j = node_start_pfn(i); j < node_end_pfn(i); j++) {
-			struct page *p;
-			unsigned long flags;
-
-			pgdat_resize_lock(NODE_DATA(i), &flags);
-			p = nid_page_nr(i, j) - node_start_pfn(i);
-
-			total++;
-			if (PageReserved(p))
-				reserved++;
-			else if (PageSwapCache(p))
-				cached++;
-			else if (!page_count(p))
-				free++;
-			else
-				shared += page_count(p) - 1;
-			pgdat_resize_unlock(NODE_DATA(i), &flags);
-        	}
+	for_each_online_pgdat(pgdat) {
+		unsigned long flags;
+		int zoneid;
+
+		pgdat_resize_lock(pgdat, &flags);
+		for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+			struct zone *zone = &pgdat->node_zones[zoneid];
+			if (!populated_zone(zone))
+				continue;
+
+			total += zone->present_pages;
+			reserved = zone->present_pages - zone->managed_pages;
+		}
+		pgdat_resize_unlock(pgdat, &flags);
 	}
-#endif
+
 	printk(KERN_INFO "%d pages of RAM\n", total);
 	printk(KERN_INFO "%d reserved pages\n", reserved);
-	printk(KERN_INFO "%d pages shared\n", shared);
-	printk(KERN_INFO "%d pages swap cached\n", cached);
-
 
 #ifdef CONFIG_DISCONTIGMEM
 	{
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 3fa93dc7fe75..8c1dd23652a1 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -209,7 +209,7 @@ void __init do_init_bootmem(void)
 	/* Place all memblock_regions in the same node and merge contiguous
 	 * memblock_regions
 	 */
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 
 	/* Add all physical memory to the bootmem map, mark each area
 	 * present.
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 078d3e00a616..5a944f25e94f 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -670,7 +670,8 @@ static void __init parse_drconf_memory(struct device_node *memory)
 			node_set_online(nid);
 			sz = numa_enforce_memory_limit(base, size);
 			if (sz)
-				memblock_set_node(base, sz, nid);
+				memblock_set_node(base, sz,
+						  &memblock.memory, nid);
 		} while (--ranges);
 	}
 }
@@ -760,7 +761,7 @@ new_range:
 				continue;
 		}
 
-		memblock_set_node(start, size, nid);
+		memblock_set_node(start, size, &memblock.memory, nid);
 
 		if (--ranges)
 			goto new_range;
@@ -797,7 +798,8 @@ static void __init setup_nonnuma(void)
 
 		fake_numa_create_new_node(end_pfn, &nid);
 		memblock_set_node(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn), nid);
+				  PFN_PHYS(end_pfn - start_pfn),
+				  &memblock.memory, nid);
 		node_set_online(nid);
 	}
 }
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index 305f7ee1f382..c75d06aa27c3 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -2,7 +2,6 @@ menu "Machine selection"
 
 config SCORE
        def_bool y
-       select HAVE_GENERIC_HARDIRQS
        select GENERIC_IRQ_SHOW
        select GENERIC_IOMAP
        select GENERIC_ATOMIC64
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 38b313909ac9..adad46e41a1d 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -13,6 +13,7 @@
 #include <linux/kdebug.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/sched.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
 
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 1cf90e947dbf..de19cfa768f2 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -230,8 +230,8 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 	pmb_bolt_mapping((unsigned long)__va(start), start, end - start,
 			 PAGE_KERNEL);
 
-	memblock_set_node(PFN_PHYS(start_pfn),
-			  PFN_PHYS(end_pfn - start_pfn), nid);
+	memblock_set_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
+			  &memblock.memory, nid);
 }
 
 void __init __weak plat_early_device_setup(void)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5322e530d09c..eafbc65c9c47 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1021,7 +1021,8 @@ static void __init add_node_ranges(void)
 				"start[%lx] end[%lx]\n",
 				nid, start, this_end);
 
-			memblock_set_node(start, this_end - start, nid);
+			memblock_set_node(start, this_end - start,
+					  &memblock.memory, nid);
 			start = this_end;
 		}
 	}
@@ -1325,7 +1326,7 @@ static void __init bootmem_init_nonnuma(void)
 	       (top_of_ram - total_ram) >> 20);
 
 	init_node_masks_nonnuma();
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 	allocate_node_data(0);
 	node_set_online(0);
 }
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index ae6bc036db92..be2bde9b07cf 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -66,9 +66,6 @@ void show_mem(unsigned int filter)
 	printk(KERN_DEFAULT "Mem-info:\n");
 	show_free_areas(filter);
 
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-
 	for_each_bank(i, mi) {
 		struct membank *bank = &mi->bank[i];
 		unsigned int pfn1, pfn2;
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index f97fbe3abb67..2f59cce3b38a 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,9 +51,9 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
-static inline phys_addr_t get_max_mapped(void)
+static inline phys_addr_t get_max_low_mapped(void)
 {
-	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
+	return (phys_addr_t)max_low_pfn_mapped << PAGE_SHIFT;
 }
 
 bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index e2dbcb7dabdd..83a7995625a6 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -91,7 +91,7 @@ void __init setup_bios_corruption_check(void)
 
 	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {
 		start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
 				PAGE_SIZE, corruption_check_size);
 		end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 174da5fc5a7b..988c00a1f60d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1120,7 +1120,7 @@ void __init memblock_find_dma_reserve(void)
 		nr_pages += end_pfn - start_pfn;
 	}
 
-	for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) {
+	for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {
 		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
 		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
 		if (start_pfn < end_pfn)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..c9675594d7ca 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_real_mode();
 
-	memblock_set_current_limit(get_max_mapped());
+	memblock_set_current_limit(get_max_low_mapped());
 	dma_contiguous_reserve(0);
 
 	/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5bdc5430597c..e39504878aec 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -665,7 +665,7 @@ void __init initmem_init(void)
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 	sparse_memory_present_with_active_regions(0);
 
 #ifdef CONFIG_FLATMEM
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 104d56a9245f..f35c66c5959a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -643,7 +643,7 @@ kernel_physical_mapping_init(unsigned long start,
 #ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 }
 #endif
 
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 8dabbed409ee..1e9da795767a 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -74,7 +74,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 i;
 	phys_addr_t this_start, this_end;
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) {
 		this_start = clamp_t(phys_addr_t, this_start, start, end);
 		this_end = clamp_t(phys_addr_t, this_end, start, end);
 		if (this_start < this_end) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c85da7bb6b60..81b2750f3666 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -491,7 +491,16 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *mb = &mi->blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.memory, mb->nid);
+
+		/*
+		 * At this time, all memory regions reserved by memblock are
+		 * used by the kernel. Set the nid in memblock.reserved will
+		 * mark out all the nodes the kernel resides in.
+		 */
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
 	}
 
 	/*
@@ -553,6 +562,30 @@ static void __init numa_init_array(void)
 	}
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes;
+	unsigned long start, end;
+	struct memblock_type *type = &memblock.reserved;
+
+	/* Mark all kernel nodes. */
+	for (i = 0; i < type->cnt; i++)
+		node_set(type->regions[i].nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -565,7 +598,12 @@ static int __init numa_init(int (*init_func)(void))
 	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));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
+				  MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+				  MAX_NUMNODES));
+	/* In case that parsing SRAT failed. */
+	WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
 	numa_reset_distance();
 
 	ret = init_func();
@@ -601,6 +639,16 @@ static int __init numa_init(int (*init_func)(void))
 			numa_clear_node(i);
 	}
 	numa_init_array();
+
+	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, numa_init() won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
 	return 0;
 }
 
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 266ca912f62e..1a25187e151e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -181,6 +181,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		(unsigned long long) start, (unsigned long long) end - 1,
 		hotpluggable ? " hotplug" : "");
 
+	/* Mark hotplug range in memblock. */
+	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
+		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+			(unsigned long long)start, (unsigned long long)end - 1);
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();