Merge branch 'x86/mm' into x86/core

6 files changed, 418 insertions, 481 deletions

diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 00f127c80b0..d11745334a6 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -158,7 +158,6 @@ EXPORT_SYMBOL(kunmap);
 EXPORT_SYMBOL(kmap_atomic);
 EXPORT_SYMBOL(kunmap_atomic);
 
-#ifdef CONFIG_NUMA
 void __init set_highmem_pages_init(void)
 {
 	struct zone *zone;
@@ -182,11 +181,3 @@ void __init set_highmem_pages_init(void)
 	}
 	totalram_pages += totalhigh_pages;
 }
-#else
-void __init set_highmem_pages_init(void)
-{
-	add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
-
-	totalram_pages += totalhigh_pages;
-}
-#endif /* CONFIG_NUMA */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ce6a722587d..6d63e3d1253 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,8 +1,345 @@
+#include <linux/ioport.h>
 #include <linux/swap.h>
+
 #include <asm/cacheflush.h>
+#include <asm/e820.h>
+#include <asm/init.h>
 #include <asm/page.h>
+#include <asm/page_types.h>
 #include <asm/sections.h>
 #include <asm/system.h>
+#include <asm/tlbflush.h>
+
+unsigned long __initdata e820_table_start;
+unsigned long __meminitdata e820_table_end;
+unsigned long __meminitdata e820_table_top;
+
+int after_bootmem;
+
+int direct_gbpages
+#ifdef CONFIG_DIRECT_GBPAGES
+				= 1
+#endif
+;
+
+static void __init find_early_table_space(unsigned long end, int use_pse,
+					  int use_gbpages)
+{
+	unsigned long puds, pmds, ptes, tables, start;
+
+	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+
+	if (use_gbpages) {
+		unsigned long extra;
+
+		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
+		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+	} else
+		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
+
+	if (use_pse) {
+		unsigned long extra;
+
+		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+#ifdef CONFIG_X86_32
+		extra += PMD_SIZE;
+#endif
+		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	} else
+		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
+
+#ifdef CONFIG_X86_32
+	/* for fixmap */
+	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
+#endif
+
+	/*
+	 * RED-PEN putting page tables only on node 0 could
+	 * cause a hotspot and fill up ZONE_DMA. The page tables
+	 * need roughly 0.5KB per GB.
+	 */
+#ifdef CONFIG_X86_32
+	start = 0x7000;
+	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+					tables, PAGE_SIZE);
+#else /* CONFIG_X86_64 */
+	start = 0x8000;
+	e820_table_start = find_e820_area(start, end, tables, PAGE_SIZE);
+#endif
+	if (e820_table_start == -1UL)
+		panic("Cannot find space for the kernel page tables");
+
+	e820_table_start >>= PAGE_SHIFT;
+	e820_table_end = e820_table_start;
+	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
+
+	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
+		end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT);
+}
+
+struct map_range {
+	unsigned long start;
+	unsigned long end;
+	unsigned page_size_mask;
+};
+
+#ifdef CONFIG_X86_32
+#define NR_RANGE_MR 3
+#else /* CONFIG_X86_64 */
+#define NR_RANGE_MR 5
+#endif
+
+static int save_mr(struct map_range *mr, int nr_range,
+		   unsigned long start_pfn, unsigned long end_pfn,
+		   unsigned long page_size_mask)
+{
+	if (start_pfn < end_pfn) {
+		if (nr_range >= NR_RANGE_MR)
+			panic("run out of range for init_memory_mapping\n");
+		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
+		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
+		mr[nr_range].page_size_mask = page_size_mask;
+		nr_range++;
+	}
+
+	return nr_range;
+}
+
+#ifdef CONFIG_X86_64
+static void __init init_gbpages(void)
+{
+	if (direct_gbpages && cpu_has_gbpages)
+		printk(KERN_INFO "Using GB pages for direct mapping\n");
+	else
+		direct_gbpages = 0;
+}
+#else
+static inline void init_gbpages(void)
+{
+}
+#endif
+
+/*
+ * Setup the direct mapping of the physical memory at PAGE_OFFSET.
+ * This runs before bootmem is initialized and gets pages directly from
+ * the physical memory. To access them they are temporarily mapped.
+ */
+unsigned long __init_refok init_memory_mapping(unsigned long start,
+					       unsigned long end)
+{
+	unsigned long page_size_mask = 0;
+	unsigned long start_pfn, end_pfn;
+	unsigned long pos;
+	unsigned long ret;
+
+	struct map_range mr[NR_RANGE_MR];
+	int nr_range, i;
+	int use_pse, use_gbpages;
+
+	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
+
+	if (!after_bootmem)
+		init_gbpages();
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	/*
+	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+	 * This will simplify cpa(), which otherwise needs to support splitting
+	 * large pages into small in interrupt context, etc.
+	 */
+	use_pse = use_gbpages = 0;
+#else
+	use_pse = cpu_has_pse;
+	use_gbpages = direct_gbpages;
+#endif
+
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_PAE
+	set_nx();
+	if (nx_enabled)
+		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
+#endif
+
+	/* Enable PSE if available */
+	if (cpu_has_pse)
+		set_in_cr4(X86_CR4_PSE);
+
+	/* Enable PGE if available */
+	if (cpu_has_pge) {
+		set_in_cr4(X86_CR4_PGE);
+		__supported_pte_mask |= _PAGE_GLOBAL;
+	}
+#endif
+
+	if (use_gbpages)
+		page_size_mask |= 1 << PG_LEVEL_1G;
+	if (use_pse)
+		page_size_mask |= 1 << PG_LEVEL_2M;
+
+	memset(mr, 0, sizeof(mr));
+	nr_range = 0;
+
+	/* head if not big page alignment ? */
+	start_pfn = start >> PAGE_SHIFT;
+	pos = start_pfn << PAGE_SHIFT;
+#ifdef CONFIG_X86_32
+	/*
+	 * Don't use a large page for the first 2/4MB of memory
+	 * because there are often fixed size MTRRs in there
+	 * and overlapping MTRRs into large pages can cause
+	 * slowdowns.
+	 */
+	if (pos == 0)
+		end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
+	else
+		end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+				 << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
+			<< (PMD_SHIFT - PAGE_SHIFT);
+#endif
+	if (end_pfn > (end >> PAGE_SHIFT))
+		end_pfn = end >> PAGE_SHIFT;
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+		pos = end_pfn << PAGE_SHIFT;
+	}
+
+	/* big page (2M) range */
+	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+			 << (PMD_SHIFT - PAGE_SHIFT);
+#ifdef CONFIG_X86_32
+	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+#else /* CONFIG_X86_64 */
+	end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+			 << (PUD_SHIFT - PAGE_SHIFT);
+	if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+		end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+#endif
+
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pos = end_pfn << PAGE_SHIFT;
+	}
+
+#ifdef CONFIG_X86_64
+	/* big page (1G) range */
+	start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+			 << (PUD_SHIFT - PAGE_SHIFT);
+	end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask &
+				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+		pos = end_pfn << PAGE_SHIFT;
+	}
+
+	/* tail is not big page (1G) alignment */
+	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+			 << (PMD_SHIFT - PAGE_SHIFT);
+	end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pos = end_pfn << PAGE_SHIFT;
+	}
+#endif
+
+	/* tail is not big page (2M) alignment */
+	start_pfn = pos>>PAGE_SHIFT;
+	end_pfn = end>>PAGE_SHIFT;
+	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+
+	/* try to merge same page size and continuous */
+	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
+		unsigned long old_start;
+		if (mr[i].end != mr[i+1].start ||
+		    mr[i].page_size_mask != mr[i+1].page_size_mask)
+			continue;
+		/* move it */
+		old_start = mr[i].start;
+		memmove(&mr[i], &mr[i+1],
+			(nr_range - 1 - i) * sizeof(struct map_range));
+		mr[i--].start = old_start;
+		nr_range--;
+	}
+
+	for (i = 0; i < nr_range; i++)
+		printk(KERN_DEBUG " %010lx - %010lx page %s\n",
+				mr[i].start, mr[i].end,
+			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
+			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
+
+	/*
+	 * Find space for the kernel direct mapping tables.
+	 *
+	 * Later we should allocate these tables in the local node of the
+	 * memory mapped. Unfortunately this is done currently before the
+	 * nodes are discovered.
+	 */
+	if (!after_bootmem)
+		find_early_table_space(end, use_pse, use_gbpages);
+
+#ifdef CONFIG_X86_32
+	for (i = 0; i < nr_range; i++)
+		kernel_physical_mapping_init(mr[i].start, mr[i].end,
+					     mr[i].page_size_mask);
+	ret = end;
+#else /* CONFIG_X86_64 */
+	for (i = 0; i < nr_range; i++)
+		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
+						   mr[i].page_size_mask);
+#endif
+
+#ifdef CONFIG_X86_32
+	early_ioremap_page_table_range_init();
+
+	load_cr3(swapper_pg_dir);
+#endif
+
+#ifdef CONFIG_X86_64
+	if (!after_bootmem)
+		mmu_cr4_features = read_cr4();
+#endif
+	__flush_tlb_all();
+
+	if (!after_bootmem && e820_table_end > e820_table_start)
+		reserve_early(e820_table_start << PAGE_SHIFT,
+				 e820_table_end << PAGE_SHIFT, "PGTABLE");
+
+	if (!after_bootmem)
+		early_memtest(start, end);
+
+	return ret >> PAGE_SHIFT;
+}
+
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number.
+ *
+ *
+ * On x86, access has to be given to the first megabyte of ram because that area
+ * contains bios code and data regions used by X and dosemu and similar apps.
+ * Access has to be given to non-kernel-ram areas as well, these contain the PCI
+ * mmio resources as well as potential bios/acpi data regions.
+ */
+int devmem_is_allowed(unsigned long pagenr)
+{
+	if (pagenr <= 256)
+		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
+	if (!page_is_ram(pagenr))
+		return 1;
+	return 0;
+}
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
@@ -47,3 +384,10 @@ void free_initmem(void)
 			(unsigned long)(&__init_begin),
 			(unsigned long)(&__init_end));
 }
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+	free_init_pages("initrd memory", start, end);
+}
+#endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 47df0e1bbeb..2966c6b8d30 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,6 +49,7 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/init.h>
 
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
@@ -58,19 +59,14 @@ unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
 
-
-static unsigned long __initdata table_start;
-static unsigned long __meminitdata table_end;
-static unsigned long __meminitdata table_top;
-
-static int __initdata after_init_bootmem;
+bool __read_mostly __vmalloc_start_set = false;
 
 static __init void *alloc_low_page(void)
 {
-	unsigned long pfn = table_end++;
+	unsigned long pfn = e820_table_end++;
 	void *adr;
 
-	if (pfn >= table_top)
+	if (pfn >= e820_table_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
@@ -90,7 +86,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
-		if (after_init_bootmem)
+		if (after_bootmem)
 			pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 		else
 			pmd_table = (pmd_t *)alloc_low_page();
@@ -117,7 +113,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
 		pte_t *page_table = NULL;
 
-		if (after_init_bootmem) {
+		if (after_bootmem) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
 			page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
 #endif
@@ -168,12 +164,12 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
 	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
 	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
 	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
-	    && ((__pa(pte) >> PAGE_SHIFT) < table_start
-		|| (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
+	    && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start
+		|| (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) {
 		pte_t *newpte;
 		int i;
 
-		BUG_ON(after_init_bootmem);
+		BUG_ON(after_bootmem);
 		newpte = alloc_low_page();
 		for (i = 0; i < PTRS_PER_PTE; i++)
 			set_pte(newpte + i, pte[i]);
@@ -242,11 +238,14 @@ static inline int is_kernel_text(unsigned long addr)
  * of max_low_pfn pages, by creating page tables starting from address
  * PAGE_OFFSET:
  */
-static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
-						unsigned long start_pfn,
-						unsigned long end_pfn,
-						int use_pse)
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+			     unsigned long end,
+			     unsigned long page_size_mask)
 {
+	int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+	unsigned long start_pfn, end_pfn;
+	pgd_t *pgd_base = swapper_pg_dir;
 	int pgd_idx, pmd_idx, pte_ofs;
 	unsigned long pfn;
 	pgd_t *pgd;
@@ -255,6 +254,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 	unsigned pages_2m, pages_4k;
 	int mapping_iter;
 
+	start_pfn = start >> PAGE_SHIFT;
+	end_pfn = end >> PAGE_SHIFT;
+
 	/*
 	 * First iteration will setup identity mapping using large/small pages
 	 * based on use_pse, with other attributes same as set by
@@ -369,26 +371,6 @@ repeat:
 		mapping_iter = 2;
 		goto repeat;
 	}
-}
-
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain address
- * is valid. The argument is a physical page number.
- *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
- */
-int devmem_is_allowed(unsigned long pagenr)
-{
-	if (pagenr <= 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
-		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
 	return 0;
 }
 
@@ -545,8 +527,9 @@ void __init native_pagetable_setup_done(pgd_t *base)
  * be partially populated, and so it avoids stomping on any existing
  * mappings.
  */
-static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
+void __init early_ioremap_page_table_range_init(void)
 {
+	pgd_t *pgd_base = swapper_pg_dir;
 	unsigned long vaddr, end;
 
 	/*
@@ -641,7 +624,7 @@ static int __init noexec_setup(char *str)
 }
 early_param("noexec", noexec_setup);
 
-static void __init set_nx(void)
+void __init set_nx(void)
 {
 	unsigned int v[4], l, h;
 
@@ -793,6 +776,8 @@ void __init initmem_init(unsigned long start_pfn,
 #ifdef CONFIG_FLATMEM
 	max_mapnr = num_physpages;
 #endif
+	__vmalloc_start_set = true;
+
 	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
 			pages_to_mb(max_low_pfn));
 
@@ -814,176 +799,61 @@ static void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+static unsigned long __init setup_node_bootmem(int nodeid,
+				 unsigned long start_pfn,
+				 unsigned long end_pfn,
+				 unsigned long bootmap)
+{
+	unsigned long bootmap_size;
+
+	if (start_pfn > max_low_pfn)
+		return bootmap;
+	if (end_pfn > max_low_pfn)
+		end_pfn = max_low_pfn;
+
+	/* 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);
+	early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+
+	return bootmap + bootmap_size;
+}
+
 void __init setup_bootmem_allocator(void)
 {
-	int i;
+	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(min_low_pfn<<PAGE_SHIFT,
-				 max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+	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");
 
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
-					 min_low_pfn, max_low_pfn);
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
-	printk(KERN_INFO "  low ram: %08lx - %08lx\n",
-		 min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT);
-	printk(KERN_INFO "  bootmap %08lx - %08lx\n",
-		 bootmap, bootmap + bootmap_size);
-	for_each_online_node(i)
-		free_bootmem_with_active_regions(i, max_low_pfn);
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-
-	after_init_bootmem = 1;
-}
-
-static void __init find_early_table_space(unsigned long end, int use_pse)
-{
-	unsigned long puds, pmds, ptes, tables, start;
-
-	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
-
-	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
-
-	if (use_pse) {
-		unsigned long extra;
-
-		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
-		extra += PMD_SIZE;
-		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	} else
-		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
-	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
-
-	/* for fixmap */
-	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-
-	/*
-	 * RED-PEN putting page tables only on node 0 could
-	 * cause a hotspot and fill up ZONE_DMA. The page tables
-	 * need roughly 0.5KB per GB.
-	 */
-	start = 0x7000;
-	table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
-					tables, PAGE_SIZE);
-	if (table_start == -1UL)
-		panic("Cannot find space for the kernel page tables");
-
-	table_start >>= PAGE_SHIFT;
-	table_end = table_start;
-	table_top = table_start + (tables>>PAGE_SHIFT);
-
-	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT,
-		(table_start << PAGE_SHIFT) + tables);
-}
-
-unsigned long __init_refok init_memory_mapping(unsigned long start,
-						unsigned long end)
-{
-	pgd_t *pgd_base = swapper_pg_dir;
-	unsigned long start_pfn, end_pfn;
-	unsigned long big_page_start;
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
-	 * This will simplify cpa(), which otherwise needs to support splitting
-	 * large pages into small in interrupt context, etc.
-	 */
-	int use_pse = 0;
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	for_each_online_node(nodeid)
+		bootmap = setup_node_bootmem(nodeid, node_start_pfn[nodeid],
+					node_end_pfn[nodeid], bootmap);
 #else
-	int use_pse = cpu_has_pse;
-#endif
-
-	/*
-	 * Find space for the kernel direct mapping tables.
-	 */
-	if (!after_init_bootmem)
-		find_early_table_space(end, use_pse);
-
-#ifdef CONFIG_X86_PAE
-	set_nx();
-	if (nx_enabled)
-		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
+	bootmap = setup_node_bootmem(0, 0, max_low_pfn, bootmap);
 #endif
 
-	/* Enable PSE if available */
-	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
-
-	/* Enable PGE if available */
-	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
-		__supported_pte_mask |= _PAGE_GLOBAL;
-	}
-
-	/*
-	 * Don't use a large page for the first 2/4MB of memory
-	 * because there are often fixed size MTRRs in there
-	 * and overlapping MTRRs into large pages can cause
-	 * slowdowns.
-	 */
-	big_page_start = PMD_SIZE;
-
-	if (start < big_page_start) {
-		start_pfn = start >> PAGE_SHIFT;
-		end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT);
-	} else {
-		/* head is not big page alignment ? */
-		start_pfn = start >> PAGE_SHIFT;
-		end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
-				 << (PMD_SHIFT - PAGE_SHIFT);
-	}
-	if (start_pfn < end_pfn)
-		kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0);
-
-	/* big page range */
-	start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
-			 << (PMD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < (big_page_start >> PAGE_SHIFT))
-		start_pfn =  big_page_start >> PAGE_SHIFT;
-	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < end_pfn)
-		kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn,
-					     use_pse);
-
-	/* tail is not big page alignment ? */
-	start_pfn = end_pfn;
-	if (start_pfn > (big_page_start>>PAGE_SHIFT)) {
-		end_pfn = end >> PAGE_SHIFT;
-		if (start_pfn < end_pfn)
-			kernel_physical_mapping_init(pgd_base, start_pfn,
-							 end_pfn, 0);
-	}
-
-	early_ioremap_page_table_range_init(pgd_base);
-
-	load_cr3(swapper_pg_dir);
-
-	__flush_tlb_all();
-
-	if (!after_init_bootmem)
-		reserve_early(table_start << PAGE_SHIFT,
-				 table_end << PAGE_SHIFT, "PGTABLE");
-
-	if (!after_init_bootmem)
-		early_memtest(start, end);
-
-	return end >> PAGE_SHIFT;
+	after_bootmem = 1;
 }
 
-
 /*
  * paging_init() sets up the page tables - note that the first 8MB are
  * already mapped by head.S.
@@ -1217,13 +1087,6 @@ void mark_rodata_ro(void)
 }
 #endif
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_init_pages("initrd memory", start, end);
-}
-#endif
-
 int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 				   int flags)
 {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 07f44d491df..8a853bc3b28 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -48,6 +48,7 @@
 #include <asm/kdebug.h>
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
+#include <asm/init.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -61,12 +62,6 @@ static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-int direct_gbpages
-#ifdef CONFIG_DIRECT_GBPAGES
-				= 1
-#endif
-;
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -87,8 +82,6 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-int after_bootmem;
-
 pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
@@ -325,13 +318,9 @@ void __init cleanup_highmap(void)
 	}
 }
 
-static unsigned long __initdata table_start;
-static unsigned long __meminitdata table_end;
-static unsigned long __meminitdata table_top;
-
 static __ref void *alloc_low_page(unsigned long *phys)
 {
-	unsigned long pfn = table_end++;
+	unsigned long pfn = e820_table_end++;
 	void *adr;
 
 	if (after_bootmem) {
@@ -341,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
 		return adr;
 	}
 
-	if (pfn >= table_top)
+	if (pfn >= e820_table_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
@@ -581,58 +570,10 @@ phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return phys_pud_init(pud, addr, end, page_size_mask);
 }
 
-static void __init find_early_table_space(unsigned long end, int use_pse,
-					  int use_gbpages)
-{
-	unsigned long puds, pmds, ptes, tables, start;
-
-	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
-	if (use_gbpages) {
-		unsigned long extra;
-		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
-		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
-	} else
-		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
-
-	if (use_pse) {
-		unsigned long extra;
-		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
-		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	} else
-		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
-
-	/*
-	 * RED-PEN putting page tables only on node 0 could
-	 * cause a hotspot and fill up ZONE_DMA. The page tables
-	 * need roughly 0.5KB per GB.
-	 */
-	start = 0x8000;
-	table_start = find_e820_area(start, end, tables, PAGE_SIZE);
-	if (table_start == -1UL)
-		panic("Cannot find space for the kernel page tables");
-
-	table_start >>= PAGE_SHIFT;
-	table_end = table_start;
-	table_top = table_start + (tables >> PAGE_SHIFT);
-
-	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT);
-}
-
-static void __init init_gbpages(void)
-{
-	if (direct_gbpages && cpu_has_gbpages)
-		printk(KERN_INFO "Using GB pages for direct mapping\n");
-	else
-		direct_gbpages = 0;
-}
-
-static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
-						unsigned long end,
-						unsigned long page_size_mask)
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+			     unsigned long end,
+			     unsigned long page_size_mask)
 {
 
 	unsigned long next, last_map_addr = end;
@@ -669,176 +610,6 @@ static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
 	return last_map_addr;
 }
 
-struct map_range {
-	unsigned long start;
-	unsigned long end;
-	unsigned page_size_mask;
-};
-
-#define NR_RANGE_MR 5
-
-static int save_mr(struct map_range *mr, int nr_range,
-		   unsigned long start_pfn, unsigned long end_pfn,
-		   unsigned long page_size_mask)
-{
-
-	if (start_pfn < end_pfn) {
-		if (nr_range >= NR_RANGE_MR)
-			panic("run out of range for init_memory_mapping\n");
-		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
-		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
-		mr[nr_range].page_size_mask = page_size_mask;
-		nr_range++;
-	}
-
-	return nr_range;
-}
-
-/*
- * Setup the direct mapping of the physical memory at PAGE_OFFSET.
- * This runs before bootmem is initialized and gets pages directly from
- * the physical memory. To access them they are temporarily mapped.
- */
-unsigned long __init_refok init_memory_mapping(unsigned long start,
-					       unsigned long end)
-{
-	unsigned long last_map_addr = 0;
-	unsigned long page_size_mask = 0;
-	unsigned long start_pfn, end_pfn;
-	unsigned long pos;
-
-	struct map_range mr[NR_RANGE_MR];
-	int nr_range, i;
-	int use_pse, use_gbpages;
-
-	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
-
-	/*
-	 * Find space for the kernel direct mapping tables.
-	 *
-	 * Later we should allocate these tables in the local node of the
-	 * memory mapped. Unfortunately this is done currently before the
-	 * nodes are discovered.
-	 */
-	if (!after_bootmem)
-		init_gbpages();
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
-	 * This will simplify cpa(), which otherwise needs to support splitting
-	 * large pages into small in interrupt context, etc.
-	 */
-	use_pse = use_gbpages = 0;
-#else
-	use_pse = cpu_has_pse;
-	use_gbpages = direct_gbpages;
-#endif
-
-	if (use_gbpages)
-		page_size_mask |= 1 << PG_LEVEL_1G;
-	if (use_pse)
-		page_size_mask |= 1 << PG_LEVEL_2M;
-
-	memset(mr, 0, sizeof(mr));
-	nr_range = 0;
-
-	/* head if not big page alignment ?*/
-	start_pfn = start >> PAGE_SHIFT;
-	pos = start_pfn << PAGE_SHIFT;
-	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
-			<< (PMD_SHIFT - PAGE_SHIFT);
-	if (end_pfn > (end >> PAGE_SHIFT))
-		end_pfn = end >> PAGE_SHIFT;
-	if (start_pfn < end_pfn) {
-		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
-		pos = end_pfn << PAGE_SHIFT;
-	}
-
-	/* big page (2M) range*/
-	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
-			 << (PMD_SHIFT - PAGE_SHIFT);
-	end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
-			 << (PUD_SHIFT - PAGE_SHIFT);
-	if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
-		end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
-	if (start_pfn < end_pfn) {
-		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
-				page_size_mask & (1<<PG_LEVEL_2M));
-		pos = end_pfn << PAGE_SHIFT;
-	}
-
-	/* big page (1G) range */
-	start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
-			 << (PUD_SHIFT - PAGE_SHIFT);
-	end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < end_pfn) {
-		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
-				page_size_mask &
-				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
-		pos = end_pfn << PAGE_SHIFT;
-	}
-
-	/* tail is not big page (1G) alignment */
-	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
-			 << (PMD_SHIFT - PAGE_SHIFT);
-	end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < end_pfn) {
-		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
-				page_size_mask & (1<<PG_LEVEL_2M));
-		pos = end_pfn << PAGE_SHIFT;
-	}
-
-	/* tail is not big page (2M) alignment */
-	start_pfn = pos>>PAGE_SHIFT;
-	end_pfn = end>>PAGE_SHIFT;
-	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
-
-	/* try to merge same page size and continuous */
-	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
-		unsigned long old_start;
-		if (mr[i].end != mr[i+1].start ||
-		    mr[i].page_size_mask != mr[i+1].page_size_mask)
-			continue;
-		/* move it */
-		old_start = mr[i].start;
-		memmove(&mr[i], &mr[i+1],
-			 (nr_range - 1 - i) * sizeof (struct map_range));
-		mr[i--].start = old_start;
-		nr_range--;
-	}
-
-	for (i = 0; i < nr_range; i++)
-		printk(KERN_DEBUG " %010lx - %010lx page %s\n",
-				mr[i].start, mr[i].end,
-			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
-			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
-
-	if (!after_bootmem)
-		find_early_table_space(end, use_pse, use_gbpages);
-
-	for (i = 0; i < nr_range; i++)
-		last_map_addr = kernel_physical_mapping_init(
-					mr[i].start, mr[i].end,
-					mr[i].page_size_mask);
-
-	if (!after_bootmem)
-		mmu_cr4_features = read_cr4();
-	__flush_tlb_all();
-
-	if (!after_bootmem && table_end > table_start)
-		reserve_early(table_start << PAGE_SHIFT,
-				 table_end << PAGE_SHIFT, "PGTABLE");
-
-	printk(KERN_INFO "last_map_addr: %lx end: %lx\n",
-			 last_map_addr, end);
-
-	if (!after_bootmem)
-		early_memtest(start, end);
-
-	return last_map_addr >> PAGE_SHIFT;
-}
-
 #ifndef CONFIG_NUMA
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -910,28 +681,6 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain address
- * is valid. The argument is a physical page number.
- *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
- */
-int devmem_is_allowed(unsigned long pagenr)
-{
-	if (pagenr <= 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
-		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
-	return 0;
-}
-
-
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
 			 kcore_modules, kcore_vsyscall;
 
@@ -1019,13 +768,6 @@ void mark_rodata_ro(void)
 
 #endif
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_init_pages("initrd memory", start, end);
-}
-#endif
-
 int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 				   int flags)
 {
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 433f7bd4648..62773abdf08 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -38,8 +38,7 @@ unsigned long __phys_addr(unsigned long x)
 	} else {
 		VIRTUAL_BUG_ON(x < PAGE_OFFSET);
 		x -= PAGE_OFFSET;
-		VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM :
-					!phys_addr_valid(x));
+		VIRTUAL_BUG_ON(!phys_addr_valid(x));
 	}
 	return x;
 }
@@ -56,10 +55,8 @@ bool __virt_addr_valid(unsigned long x)
 		if (x < PAGE_OFFSET)
 			return false;
 		x -= PAGE_OFFSET;
-		if (system_state == SYSTEM_BOOTING ?
-				x > MAXMEM : !phys_addr_valid(x)) {
+		if (!phys_addr_valid(x))
 			return false;
-		}
 	}
 
 	return pfn_valid(x >> PAGE_SHIFT);
@@ -76,10 +73,9 @@ static inline int phys_addr_valid(unsigned long addr)
 #ifdef CONFIG_DEBUG_VIRTUAL
 unsigned long __phys_addr(unsigned long x)
 {
-	/* VMALLOC_* aren't constants; not available at the boot time */
+	/* VMALLOC_* aren't constants  */
 	VIRTUAL_BUG_ON(x < PAGE_OFFSET);
-	VIRTUAL_BUG_ON(system_state != SYSTEM_BOOTING &&
-		is_vmalloc_addr((void *) x));
+	VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x));
 	return x - PAGE_OFFSET;
 }
 EXPORT_SYMBOL(__phys_addr);
@@ -89,7 +85,7 @@ bool __virt_addr_valid(unsigned long x)
 {
 	if (x < PAGE_OFFSET)
 		return false;
-	if (system_state != SYSTEM_BOOTING && is_vmalloc_addr((void *) x))
+	if (__vmalloc_start_set && is_vmalloc_addr((void *) x))
 		return false;
 	return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT);
 }
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 451fe95a035..3daefa04ace 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -416,10 +416,11 @@ void __init initmem_init(unsigned long start_pfn,
 	for_each_online_node(nid)
 		propagate_e820_map_node(nid);
 
-	for_each_online_node(nid)
+	for_each_online_node(nid) {
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
+		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
+	}
 
-	NODE_DATA(0)->bdata = &bootmem_node_data[0];
 	setup_bootmem_allocator();
 }