18 files changed, 580 insertions, 355 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index a4c768397baa..55543397a8a7 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -26,4 +26,6 @@ obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
+obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
+
 obj-$(CONFIG_MEMTEST)		+= memtest.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f62777940dfb..79b0b372d2d0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -229,7 +229,16 @@ void vmalloc_sync_all(void)
 
 		spin_lock_irqsave(&pgd_lock, flags);
 		list_for_each_entry(page, &pgd_list, lru) {
-			if (!vmalloc_sync_one(page_address(page), address))
+			spinlock_t *pgt_lock;
+			pmd_t *ret;
+
+			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+
+			spin_lock(pgt_lock);
+			ret = vmalloc_sync_one(page_address(page), address);
+			spin_unlock(pgt_lock);
+
+			if (!ret)
 				break;
 		}
 		spin_unlock_irqrestore(&pgd_lock, flags);
@@ -251,6 +260,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
@@ -326,29 +337,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-	unsigned long address;
-
-	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
-	     address += PGDIR_SIZE) {
-
-		const pgd_t *pgd_ref = pgd_offset_k(address);
-		unsigned long flags;
-		struct page *page;
-
-		if (pgd_none(*pgd_ref))
-			continue;
-
-		spin_lock_irqsave(&pgd_lock, flags);
-		list_for_each_entry(page, &pgd_list, lru) {
-			pgd_t *pgd;
-			pgd = (pgd_t *)page_address(page) + pgd_index(address);
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
-				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
-	}
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
 /*
@@ -369,6 +358,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later
@@ -802,8 +793,10 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	up_read(&mm->mmap_sem);
 
 	/* Kernel mode? Handle exceptions or die: */
-	if (!(error_code & PF_USER))
+	if (!(error_code & PF_USER)) {
 		no_context(regs, error_code, address);
+		return;
+	}
 
 	/* User-space => ok to do another page fault: */
 	if (is_prefetch(regs, error_code, address))
@@ -892,8 +885,14 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	if (pmd_large(*pmd))
 		return spurious_fault_check(error_code, (pte_t *) pmd);
 
+	/*
+	 * Note: don't use pte_present() here, since it returns true
+	 * if the _PAGE_PROTNONE bit is set.  However, this aliases the
+	 * _PAGE_GLOBAL bit, which for kernel pages give false positives
+	 * when CONFIG_DEBUG_PAGEALLOC is used.
+	 */
 	pte = pte_offset_kernel(pmd, address);
-	if (!pte_present(*pte))
+	if (!(pte_flags(*pte) & _PAGE_PRESENT))
 		return 0;
 
 	ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b278535b14aa..c0e28a13de7d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -2,6 +2,7 @@
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -33,6 +34,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
 	unsigned long puds, pmds, ptes, tables, start;
+	phys_addr_t base;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
 	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
@@ -75,12 +77,12 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #else
 	start = 0x8000;
 #endif
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+	base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
-	if (e820_table_start == -1UL)
+	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
 
-	e820_table_start >>= PAGE_SHIFT;
+	e820_table_start = base >> PAGE_SHIFT;
 	e820_table_end = e820_table_start;
 	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
 
@@ -299,7 +301,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
-		reserve_early(e820_table_start << PAGE_SHIFT,
+		memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT,
 				 e820_table_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bca79091b9d6..0e969f9f401b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,6 +25,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
@@ -67,7 +68,7 @@ static __init void *alloc_low_page(void)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	return adr;
 }
 
@@ -422,49 +423,28 @@ static void __init add_one_highpage_init(struct page *page)
 	totalhigh_pages++;
 }
 
-struct add_highpages_data {
-	unsigned long start_pfn;
-	unsigned long end_pfn;
-};
-
-static int __init add_highpages_work_fn(unsigned long start_pfn,
-					 unsigned long end_pfn, void *datax)
+void __init add_highpages_with_active_regions(int nid,
+			 unsigned long start_pfn, unsigned long end_pfn)
 {
-	int node_pfn;
-	struct page *page;
-	unsigned long final_start_pfn, final_end_pfn;
-	struct add_highpages_data *data;
+	struct range *range;
+	int nr_range;
+	int i;
 
-	data = (struct add_highpages_data *)datax;
+	nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn);
 
-	final_start_pfn = max(start_pfn, data->start_pfn);
-	final_end_pfn = min(end_pfn, data->end_pfn);
-	if (final_start_pfn >= final_end_pfn)
-		return 0;
+	for (i = 0; i < nr_range; i++) {
+		struct page *page;
+		int node_pfn;
 
-	for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
-	     node_pfn++) {
-		if (!pfn_valid(node_pfn))
-			continue;
-		page = pfn_to_page(node_pfn);
-		add_one_highpage_init(page);
+		for (node_pfn = range[i].start; node_pfn < range[i].end;
+		     node_pfn++) {
+			if (!pfn_valid(node_pfn))
+				continue;
+			page = pfn_to_page(node_pfn);
+			add_one_highpage_init(page);
+		}
 	}
-
-	return 0;
-
 }
-
-void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
-					      unsigned long end_pfn)
-{
-	struct add_highpages_data data;
-
-	data.start_pfn = start_pfn;
-	data.end_pfn = end_pfn;
-
-	work_with_active_regions(nid, add_highpages_work_fn, &data);
-}
-
 #else
 static inline void permanent_kmaps_init(pgd_t *pgd_base)
 {
@@ -548,48 +528,6 @@ static void __init pagetable_init(void)
 	permanent_kmaps_init(pgd_base);
 }
 
-#ifdef CONFIG_ACPI_SLEEP
-/*
- * ACPI suspend needs this for resume, because things like the intel-agp
- * driver might have split up a kernel 4MB mapping.
- */
-char swsusp_pg_dir[PAGE_SIZE]
-	__attribute__ ((aligned(PAGE_SIZE)));
-
-static inline void save_pg_dir(void)
-{
-	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
-}
-#else /* !CONFIG_ACPI_SLEEP */
-static inline void save_pg_dir(void)
-{
-}
-#endif /* !CONFIG_ACPI_SLEEP */
-
-void zap_low_mappings(bool early)
-{
-	int i;
-
-	/*
-	 * Zap initial low-memory mappings.
-	 *
-	 * Note that "pgd_clear()" doesn't do it for
-	 * us, because pgd_clear() is a no-op on i386.
-	 */
-	for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
-#ifdef CONFIG_X86_PAE
-		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
-#else
-		set_pgd(swapper_pg_dir+i, __pgd(0));
-#endif
-	}
-
-	if (early)
-		__flush_tlb();
-	else
-		flush_tlb_all();
-}
-
 pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
@@ -712,14 +650,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	e820_register_active_regions(0, 0, highend_pfn);
+	memblock_x86_register_active_regions(0, 0, highend_pfn);
 	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	e820_register_active_regions(0, 0, max_low_pfn);
+	memblock_x86_register_active_regions(0, 0, max_low_pfn);
 	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
@@ -750,68 +688,12 @@ static void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-#ifndef CONFIG_NO_BOOTMEM
-static unsigned long __init setup_node_bootmem(int nodeid,
-				 unsigned long start_pfn,
-				 unsigned long end_pfn,
-				 unsigned long bootmap)
-{
-	unsigned long bootmap_size;
-
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap >> PAGE_SHIFT,
-					 start_pfn, end_pfn);
-	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
-		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
-	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
-		 nodeid, bootmap, bootmap + bootmap_size);
-	free_bootmem_with_active_regions(nodeid, end_pfn);
-
-	return bootmap + bootmap_size;
-}
-#endif
-
 void __init setup_bootmem_allocator(void)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	int nodeid;
-	unsigned long bootmap_size, bootmap;
-	/*
-	 * Initialize the boot-time allocator (with low memory only):
-	 */
-	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-#endif
-
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
-#ifndef CONFIG_NO_BOOTMEM
-	for_each_online_node(nodeid) {
-		 unsigned long start_pfn, end_pfn;
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-		start_pfn = node_start_pfn[nodeid];
-		end_pfn = node_end_pfn[nodeid];
-		if (start_pfn > max_low_pfn)
-			continue;
-		if (end_pfn > max_low_pfn)
-			end_pfn = max_low_pfn;
-#else
-		start_pfn = 0;
-		end_pfn = max_low_pfn;
-#endif
-		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
-						 bootmap);
-	}
-#endif
-
 	after_bootmem = 1;
 }
 
@@ -958,9 +840,6 @@ void __init mem_init(void)
 
 	if (boot_cpu_data.wp_works_ok < 0)
 		test_wp_bit();
-
-	save_pg_dir();
-	zap_low_mappings(true);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -1070,8 +949,3 @@ void mark_rodata_ro(void)
 }
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-	return reserve_bootmem(phys, len, flags);
-}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a6674689a20..84346200e783 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
@@ -52,8 +53,6 @@
 #include <asm/init.h>
 #include <linux/bootmem.h>
 
-static unsigned long dma_reserve __initdata;
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -98,6 +97,43 @@ static int __init nonx32_setup(char *str)
 __setup("noexec32=", nonx32_setup);
 
 /*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+	unsigned long address;
+
+	for (address = start; address <= end; address += PGDIR_SIZE) {
+		const pgd_t *pgd_ref = pgd_offset_k(address);
+		unsigned long flags;
+		struct page *page;
+
+		if (pgd_none(*pgd_ref))
+			continue;
+
+		spin_lock_irqsave(&pgd_lock, flags);
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd;
+			spinlock_t *pgt_lock;
+
+			pgd = (pgd_t *)page_address(page) + pgd_index(address);
+			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+			spin_lock(pgt_lock);
+
+			if (pgd_none(*pgd))
+				set_pgd(pgd, *pgd_ref);
+			else
+				BUG_ON(pgd_page_vaddr(*pgd)
+				       != pgd_page_vaddr(*pgd_ref));
+
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock_irqrestore(&pgd_lock, flags);
+	}
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -293,7 +329,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
@@ -534,11 +570,13 @@ kernel_physical_mapping_init(unsigned long start,
 			     unsigned long end,
 			     unsigned long page_size_mask)
 {
-
+	bool pgd_changed = false;
 	unsigned long next, last_map_addr = end;
+	unsigned long addr;
 
 	start = (unsigned long)__va(start);
 	end = (unsigned long)__va(end);
+	addr = start;
 
 	for (; start < end; start = next) {
 		pgd_t *pgd = pgd_offset_k(start);
@@ -563,7 +601,12 @@ kernel_physical_mapping_init(unsigned long start,
 		spin_lock(&init_mm.page_table_lock);
 		pgd_populate(&init_mm, pgd, __va(pud_phys));
 		spin_unlock(&init_mm.page_table_lock);
+		pgd_changed = true;
 	}
+
+	if (pgd_changed)
+		sync_global_pgds(addr, end);
+
 	__flush_tlb_all();
 
 	return last_map_addr;
@@ -573,23 +616,7 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_size, bootmap;
-
-	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
-					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
-	free_bootmem_with_active_regions(0, end_pfn);
-#else
-	e820_register_active_regions(0, start_pfn, end_pfn);
-#endif
+	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
 }
 #endif
 
@@ -799,52 +826,6 @@ void mark_rodata_ro(void)
 
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-#ifdef CONFIG_NUMA
-	int nid, next_nid;
-	int ret;
-#endif
-	unsigned long pfn = phys >> PAGE_SHIFT;
-
-	if (pfn >= max_pfn) {
-		/*
-		 * This can happen with kdump kernels when accessing
-		 * firmware tables:
-		 */
-		if (pfn < max_pfn_mapped)
-			return -EFAULT;
-
-		printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
-				phys, len);
-		return -EFAULT;
-	}
-
-	/* Should check here against the e820 map to avoid double free */
-#ifdef CONFIG_NUMA
-	nid = phys_to_nid(phys);
-	next_nid = phys_to_nid(phys + len - 1);
-	if (nid == next_nid)
-		ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
-	else
-		ret = reserve_bootmem(phys, len, flags);
-
-	if (ret != 0)
-		return ret;
-
-#else
-	reserve_bootmem(phys, len, flags);
-#endif
-
-	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
-		dma_reserve += len / PAGE_SIZE;
-		set_dma_reserve(dma_reserve);
-	}
-
-	return 0;
-}
-
 int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
@@ -1003,6 +984,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 		}
 
 	}
+	sync_global_pgds((unsigned long)start_page, end);
 	return 0;
 }
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 84e236ce76ba..72fc70cf6184 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -74,7 +74,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 /*
  * Map 'pfn' using fixed map 'type' and protections 'prot'
  */
-void *
+void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 {
 	/*
@@ -86,12 +86,12 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
 		prot = PAGE_KERNEL_UC_MINUS;
 
-	return kmap_atomic_prot_pfn(pfn, type, prot);
+	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot);
 }
 EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
 
 void
-iounmap_atomic(void *kvaddr, enum km_type type)
+iounmap_atomic(void __iomem *kvaddr, enum km_type type)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 3ba6e0608c55..0369843511dc 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -362,6 +362,11 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr)
 	return &bm_pte[pte_index(addr)];
 }
 
+bool __init is_early_ioremap_ptep(pte_t *ptep)
+{
+	return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)];
+}
+
 static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
 
 void __init early_ioremap_init(void)
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed579d4e4..804a3b6c6e14 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/nodemask.h>
+#include <linux/memblock.h>
+
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <linux/acpi.h>
@@ -22,7 +24,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
@@ -54,8 +56,8 @@ static __init int find_northbridge(void)
 static __init void early_get_boot_cpu_id(void)
 {
 	/*
-	 * need to get boot_cpu_id so can use that to create apicid_to_node
-	 * in k8_scan_nodes()
+	 * need to get the APIC ID of the BSP so can use that to
+	 * create apicid_to_node in k8_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -212,7 +214,7 @@ int __init k8_scan_nodes(void)
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = (1<<bits);
 	apicid_base = 0;
-	/* need to get boot_cpu_id early for system with apicid lifting */
+	/* get the APIC ID of the BSP early for systems with apicid lifting */
 	early_get_boot_cpu_id();
 	if (boot_cpu_physical_apicid > 0) {
 		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
@@ -222,7 +224,7 @@ int __init k8_scan_nodes(void)
 	for_each_node_mask(i, node_possible_map) {
 		int j;
 
-		e820_register_active_regions(i,
+		memblock_x86_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index b3b531a4f8e5..d87dd6d042d6 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -631,6 +631,8 @@ bool kmemcheck_fault(struct pt_regs *regs, unsigned long address,
 	if (!pte)
 		return false;
 
+	WARN_ON_ONCE(in_nmi());
+
 	if (error_code & 2)
 		kmemcheck_access(regs, address, KMEMCHECK_WRITE);
 	else
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index 63c19e27aa6f..324aa3f07237 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -9,7 +9,7 @@ static bool opcode_is_prefix(uint8_t b)
 		b == 0xf0 || b == 0xf2 || b == 0xf3
 		/* Group 2 */
 		|| b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
-		|| b == 0x64 || b == 0x65 || b == 0x2e || b == 0x3e
+		|| b == 0x64 || b == 0x65
 		/* Group 3 */
 		|| b == 0x66
 		/* Group 4 */
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
new file mode 100644
index 000000000000..aa1169392b83
--- /dev/null
+++ b/arch/x86/mm/memblock.c
@@ -0,0 +1,348 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/range.h>
+
+/* Check for already reserved areas */
+static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	bool changed = false;
+
+again:
+	last = addr + size;
+	for_each_memblock(reserved, r) {
+		if (last > r->base && addr < r->base) {
+			size = r->base - addr;
+			changed = true;
+			goto again;
+		}
+		if (last > (r->base + r->size) && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
+			size = last - addr;
+			changed = true;
+			goto again;
+		}
+		if (last <= (r->base + r->size) && addr >= r->base) {
+			*sizep = 0;
+			return false;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find next free range after start, and size is returned in *sizep
+ */
+u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r) {
+		u64 ei_start = r->base;
+		u64 ei_last = ei_start + r->size;
+		u64 addr;
+
+		addr = round_up(ei_start, align);
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		*sizep = ei_last - addr;
+		while (check_with_memblock_reserved_size(&addr, sizep, align))
+			;
+
+		if (*sizep)
+			return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+static __init struct range *find_range_array(int count)
+{
+	u64 end, size, mem;
+	struct range *range;
+
+	size = sizeof(struct range) * count;
+	end = memblock.current_limit;
+
+	mem = memblock_find_in_range(0, end, size, sizeof(struct range));
+	if (mem == MEMBLOCK_ERROR)
+		panic("can not find more space for range array");
+
+	/*
+	 * This range is tempoaray, so don't reserve it, it will not be
+	 * overlapped because We will not alloccate new buffer before
+	 * We discard this one
+	 */
+	range = __va(mem);
+	memset(range, 0, size);
+
+	return range;
+}
+
+static void __init memblock_x86_subtract_reserved(struct range *range, int az)
+{
+	u64 final_start, final_end;
+	struct memblock_region *r;
+
+	/* Take out region array itself at first*/
+	memblock_free_reserved_regions();
+
+	memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt);
+
+	for_each_memblock(reserved, r) {
+		memblock_dbg("  [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1);
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+	/* Put region array back ? */
+	memblock_reserve_reserved_regions();
+}
+
+struct count_data {
+	int nr;
+};
+
+static int __init count_work_fn(unsigned long start_pfn,
+				unsigned long end_pfn, void *datax)
+{
+	struct count_data *data = datax;
+
+	data->nr++;
+
+	return 0;
+}
+
+static int __init count_early_node_map(int nodeid)
+{
+	struct count_data data;
+
+	data.nr = 0;
+	work_with_active_regions(nodeid, count_work_fn, &data);
+
+	return data.nr;
+}
+
+int __init __get_free_all_memory_range(struct range **rangep, int nodeid,
+			 unsigned long start_pfn, unsigned long end_pfn)
+{
+	int count;
+	struct range *range;
+	int nr_range;
+
+	count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	/*
+	 * Use early_node_map[] and memblock.reserved.region to get range array
+	 * at first
+	 */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+	subtract_range(range, count, 0, start_pfn);
+	subtract_range(range, count, end_pfn, -1ULL);
+
+	memblock_x86_subtract_reserved(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	*rangep = range;
+	return nr_range;
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	unsigned long end_pfn = -1UL;
+
+#ifdef CONFIG_X86_32
+	end_pfn = max_low_pfn;
+#endif
+	return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn);
+}
+
+static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free)
+{
+	int i, count;
+	struct range *range;
+	int nr_range;
+	u64 final_start, final_end;
+	u64 free_size;
+	struct memblock_region *r;
+
+	count = (memblock.reserved.cnt + memblock.memory.cnt) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	addr = PFN_UP(addr);
+	limit = PFN_DOWN(limit);
+
+	for_each_memblock(memory, r) {
+		final_start = PFN_UP(r->base);
+		final_end = PFN_DOWN(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		nr_range = add_range(range, count, nr_range, final_start, final_end);
+	}
+	subtract_range(range, count, 0, addr);
+	subtract_range(range, count, limit, -1ULL);
+
+	/* Subtract memblock.reserved.region in range ? */
+	if (!get_free)
+		goto sort_and_count_them;
+	for_each_memblock(reserved, r) {
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		subtract_range(range, count, final_start, final_end);
+	}
+
+sort_and_count_them:
+	nr_range = clean_sort_range(range, count);
+
+	free_size = 0;
+	for (i = 0; i < nr_range; i++)
+		free_size += range[i].end - range[i].start;
+
+	return free_size << PAGE_SHIFT;
+}
+
+u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, true);
+}
+
+u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, false);
+}
+
+void __init memblock_x86_reserve_range(u64 start, u64 end, char *name)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("    memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name);
+
+	memblock_reserve(start, end - start);
+}
+
+void __init memblock_x86_free_range(u64 start, u64 end)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("       memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1);
+
+	memblock_free(start, end - start);
+}
+
+/*
+ * Need to call this function after memblock_x86_register_active_regions,
+ * so early_node_map[] is filled already.
+ */
+u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != MEMBLOCK_ERROR)
+		return addr;
+
+	/* Fallback, should already have start end within node range */
+	return memblock_find_in_range(start, end, size, align);
+}
+
+/*
+ * Finds an active region in the address range from start_pfn to last_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the memblock entry.
+ */
+static int __init memblock_x86_find_active_region(const struct memblock_region *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn)
+{
+	u64 align = PAGE_SIZE;
+
+	*ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
+	*ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
+
+	/* Skip map entries smaller than a page */
+	if (*ei_startpfn >= *ei_endpfn)
+		return 0;
+
+	/* Skip if map is outside the node */
+	if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
+		return 0;
+
+	/* Check for overlaps */
+	if (*ei_startpfn < start_pfn)
+		*ei_startpfn = start_pfn;
+	if (*ei_endpfn > last_pfn)
+		*ei_endpfn = last_pfn;
+
+	return 1;
+}
+
+/* Walk the memblock.memory map and register active regions within a node */
+void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn)
+{
+	unsigned long ei_startpfn;
+	unsigned long ei_endpfn;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			add_active_range(nid, ei_startpfn, ei_endpfn);
+}
+
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+u64 __init memblock_x86_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long last_pfn = end >> PAGE_SHIFT;
+	unsigned long ei_startpfn, ei_endpfn, ram = 0;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			ram += ei_endpfn - ei_startpfn;
+
+	return end - start - ((u64)ram << PAGE_SHIFT);
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 18d244f70205..92faf3a1c53e 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -6,8 +6,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/pfn.h>
-
-#include <asm/e820.h>
+#include <linux/memblock.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -35,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 	       (unsigned long long) pattern,
 	       (unsigned long long) start_bad,
 	       (unsigned long long) end_bad);
-	reserve_early(start_bad, end_bad, "BAD RAM");
+	memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
 }
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -74,7 +73,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 size = 0;
 
 	while (start < end) {
-		start = find_e820_area_size(start, &size, 1);
+		start = memblock_x86_find_in_range_size(start, &size, 1);
 
 		/* done ? */
 		if (start >= end)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 809baaaf48b1..84a3e4c9f277 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
@@ -120,7 +121,7 @@ int __init get_memcfg_numa_flat(void)
 
 	node_start_pfn[0] = 0;
 	node_end_pfn[0] = max_pfn;
-	e820_register_active_regions(0, 0, max_pfn);
+	memblock_x86_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
 	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
@@ -161,14 +162,14 @@ static void __init allocate_pgdat(int nid)
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		unsigned long pgdat_phys;
-		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
 				 sizeof(pg_data_t),
 				 PAGE_SIZE);
 		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
 		memset(buf, 0, sizeof(buf));
 		sprintf(buf, "NODE_DATA %d",  nid);
-		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
+		memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
 	}
 	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
 		nid, (unsigned long)NODE_DATA(nid));
@@ -291,15 +292,15 @@ static __init unsigned long calculate_numa_remap_pages(void)
 						 PTRS_PER_PTE);
 		node_kva_target <<= PAGE_SHIFT;
 		do {
-			node_kva_final = find_e820_area(node_kva_target,
+			node_kva_final = memblock_find_in_range(node_kva_target,
 					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
 						((u64)size)<<PAGE_SHIFT,
 						LARGE_PAGE_BYTES);
 			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == -1ULL &&
+		} while (node_kva_final == MEMBLOCK_ERROR &&
 			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
 
-		if (node_kva_final == -1ULL)
+		if (node_kva_final == MEMBLOCK_ERROR)
 			panic("Can not get kva ram\n");
 
 		node_remap_size[nid] = size;
@@ -318,15 +319,13 @@ static __init unsigned long calculate_numa_remap_pages(void)
 		 *  but we could have some hole in high memory, and it will only
 		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
 		 *  to use it as free.
-		 *  So reserve_early here, hope we don't run out of that array
+		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
 		 */
-		reserve_early(node_kva_final,
+		memblock_x86_reserve_range(node_kva_final,
 			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
 			      "KVA RAM");
 
 		node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT;
-		remove_active_range(nid, node_remap_start_pfn[nid],
-					 node_remap_start_pfn[nid] + size);
 	}
 	printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",
 			reserve_pages);
@@ -367,14 +366,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
-		kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT,
+		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
 					max_low_pfn<<PAGE_SHIFT,
 					kva_pages<<PAGE_SHIFT,
 					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
 		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn);
+	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
 
-	if (kva_start_pfn == -1UL)
+	if (kva_start_pfn == MEMBLOCK_ERROR)
 		panic("Can not get kva space\n");
 
 	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
@@ -382,7 +381,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
 
 	/* avoid clash with initrd */
-	reserve_early(kva_start_pfn<<PAGE_SHIFT,
+	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
 		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
 		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
@@ -419,9 +418,6 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 	for_each_online_node(nid) {
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 		NODE_DATA(nid)->node_id = nid;
-#ifndef CONFIG_NO_BOOTMEM
-		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-#endif
 	}
 
 	setup_bootmem_allocator();
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a7bcc23ef96c..60f498511dd6 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -18,7 +19,7 @@
 #include <asm/dma.h>
 #include <asm/numa.h>
 #include <asm/acpi.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -86,16 +87,16 @@ static int __init allocate_cachealigned_memnodemap(void)
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == -1UL) {
+	if (nodemap_addr == MEMBLOCK_ERROR) {
 		printk(KERN_ERR
 		       "NUMA: Unable to allocate Memory to Node hash map\n");
 		nodemap_addr = nodemap_size = 0;
 		return -1;
 	}
 	memnodemap = phys_to_virt(nodemap_addr);
-	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
+	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
 	       nodemap_addr, nodemap_addr + nodemap_size);
@@ -171,8 +172,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
 	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	/* extend the search scope */
@@ -181,8 +182,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
 	else
 		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
@@ -198,10 +199,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	unsigned long start_pfn, last_pfn, nodedata_phys;
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_start, bootmap_pages, bootmap_size;
-	void *bootmap;
-#endif
 
 	if (!end)
 		return;
@@ -226,7 +223,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
-	reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
+	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
 	nid = phys_to_nid(nodedata_phys);
@@ -238,47 +235,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
-#ifndef CONFIG_NO_BOOTMEM
-	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
-
-	/*
-	 * Find a place for the bootmem map
-	 * nodedata_phys could be on other nodes by alloc_bootmem,
-	 * so need to sure bootmap_start not to be small, otherwise
-	 * early_node_mem will get that with find_e820_area instead
-	 * of alloc_bootmem, that could clash with reserved range
-	 */
-	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
-	bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
-	/*
-	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
-	 * to use that to align to PAGE_SIZE
-	 */
-	bootmap = early_node_mem(nodeid, bootmap_start, end,
-				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
-	if (bootmap == NULL)  {
-		free_early(nodedata_phys, nodedata_phys + pgdat_size);
-		node_data[nodeid] = NULL;
-		return;
-	}
-	bootmap_start = __pa(bootmap);
-	reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
-			"BOOTMAP");
-
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap_start >> PAGE_SHIFT,
-					 start_pfn, last_pfn);
-
-	printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
-		 bootmap_start, bootmap_start + bootmap_size - 1,
-		 bootmap_pages);
-	nid = phys_to_nid(bootmap_start);
-	if (nid != nodeid)
-		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
-
-	free_bootmem_with_active_regions(nodeid, end);
-#endif
-
 	node_set_online(nodeid);
 }
 
@@ -416,7 +372,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes;
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -452,7 +408,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * non-reserved memory is less than the per-node size.
 			 */
 			while (end - physnodes[i].start -
-				e820_hole_size(physnodes[i].start, end) < size) {
+				memblock_x86_hole_size(physnodes[i].start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > physnodes[i].end) {
 					end = physnodes[i].end;
@@ -466,7 +422,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -475,7 +431,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr,
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -503,7 +459,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
 	u64 end = start + size;
 
-	while (end - start - e820_hole_size(start, end) < size) {
+	while (end - start - memblock_x86_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -532,7 +488,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
 						MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
@@ -565,7 +521,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -574,7 +530,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -638,7 +594,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 	 */
 	remove_all_active_ranges();
 	for_each_node_mask(i, node_possible_map) {
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
@@ -691,7 +647,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	node_set(0, node_possible_map);
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
-	e820_register_active_regions(0, start_pfn, last_pfn);
+	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
@@ -703,9 +659,7 @@ unsigned long __init numa_free_all_bootmem(void)
 	for_each_online_node(i)
 		pages += free_all_bootmem_node(NODE_DATA(i));
 
-#ifdef CONFIG_NO_BOOTMEM
 	pages += free_all_memory_core_early(MAX_NUMNODES);
-#endif
 
 	return pages;
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5c4ee422590e..8be8c7d7bc89 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -87,7 +87,19 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(pgd_t *pgd)
+
+static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	BUILD_BUG_ON(sizeof(virt_to_page(pgd)->index) < sizeof(mm));
+	virt_to_page(pgd)->index = (pgoff_t)mm;
+}
+
+struct mm_struct *pgd_page_get_mm(struct page *page)
+{
+	return (struct mm_struct *)page->index;
+}
+
+static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 {
 	/* If the pgd points to a shared pagetable level (either the
 	   ptes in non-PAE, or shared PMD in PAE), then just copy the
@@ -98,15 +110,13 @@ static void pgd_ctor(pgd_t *pgd)
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
-		paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
-					 __pa(swapper_pg_dir) >> PAGE_SHIFT,
-					 KERNEL_PGD_BOUNDARY,
-					 KERNEL_PGD_PTRS);
 	}
 
 	/* list required to sync kernel mapping updates */
-	if (!SHARED_KERNEL_PMD)
+	if (!SHARED_KERNEL_PMD) {
+		pgd_set_mm(pgd, mm);
 		pgd_list_add(pgd);
+	}
 }
 
 static void pgd_dtor(pgd_t *pgd)
@@ -272,7 +282,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	 */
 	spin_lock_irqsave(&pgd_lock, flags);
 
-	pgd_ctor(pgd);
+	pgd_ctor(mm, pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
 
 	spin_unlock_irqrestore(&pgd_lock, flags);
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 9324f13492d5..a17dffd136c1 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -25,6 +25,7 @@
  */
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
@@ -264,7 +265,7 @@ int __init get_memcfg_from_srat(void)
 		if (node_read_chunk(chunk->nid, chunk))
 			continue;
 
-		e820_register_active_regions(chunk->nid, chunk->start_pfn,
+		memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
 	/* for out of order entries in SRAT */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index f9897f7a9ef1..a35cb9d8b060 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -98,15 +99,15 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 	unsigned long phys;
 
 	length = slit->header.length;
-	phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+	phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length,
 		 PAGE_SIZE);
 
-	if (phys == -1L)
+	if (phys == MEMBLOCK_ERROR)
 		panic(" Can not save slit!\n");
 
 	acpi_slit = __va(phys);
 	memcpy(acpi_slit, slit, length);
-	reserve_early(phys, phys + length, "ACPI SLIT");
+	memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -324,7 +325,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
 	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
 	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
@@ -420,9 +421,11 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 	}
 
-	for_each_node_mask(i, nodes_parsed)
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
-						nodes[i].end >> PAGE_SHIFT);
+	for (i = 0; i < num_node_memblks; i++)
+		memblock_x86_register_active_regions(memblk_nodeid[i],
+				node_memblk_range[i].start >> PAGE_SHIFT,
+				node_memblk_range[i].end >> PAGE_SHIFT);
+
 	/* for out of order entries in SRAT */
 	sort_node_map();
 	if (!nodes_cover_memory(nodes)) {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c03f14ab6667..49358481c733 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -5,6 +5,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/cpu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -52,6 +53,8 @@ union smp_flush_state {
    want false sharing in the per cpu data segment. */
 static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
 
+static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -173,7 +176,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 	union smp_flush_state *f;
 
 	/* Caller has disabled preemption */
-	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
+	sender = this_cpu_read(tlb_vector_offset);
 	f = &flush_state[sender];
 
 	/*
@@ -218,6 +221,47 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	flush_tlb_others_ipi(cpumask, mm, va);
 }
 
+static void __cpuinit calculate_tlb_offset(void)
+{
+	int cpu, node, nr_node_vecs;
+	/*
+	 * we are changing tlb_vector_offset for each CPU in runtime, but this
+	 * will not cause inconsistency, as the write is atomic under X86. we
+	 * might see more lock contentions in a short time, but after all CPU's
+	 * tlb_vector_offset are changed, everything should go normal
+	 *
+	 * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might
+	 * waste some vectors.
+	 **/
+	if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS)
+		nr_node_vecs = 1;
+	else
+		nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
+
+	for_each_online_node(node) {
+		int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+			nr_node_vecs;
+		int cpu_offset = 0;
+		for_each_cpu(cpu, cpumask_of_node(node)) {
+			per_cpu(tlb_vector_offset, cpu) = node_offset +
+				cpu_offset;
+			cpu_offset++;
+			cpu_offset = cpu_offset % nr_node_vecs;
+		}
+	}
+}
+
+static int tlb_cpuhp_notify(struct notifier_block *n,
+		unsigned long action, void *hcpu)
+{
+	switch (action & 0xf) {
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		calculate_tlb_offset();
+	}
+	return NOTIFY_OK;
+}
+
 static int __cpuinit init_smp_flush(void)
 {
 	int i;
@@ -225,6 +269,8 @@ static int __cpuinit init_smp_flush(void)
 	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
 		raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
+	calculate_tlb_offset();
+	hotcpu_notifier(tlb_cpuhp_notify, 0);
 	return 0;
 }
 core_initcall(init_smp_flush);