Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Peter Anvin:
 "This is a huge set of several partly interrelated (and concurrently
  developed) changes, which is why the branch history is messier than
  one would like.

  The *really* big items are two humonguous patchsets mostly developed
  by Yinghai Lu at my request, which completely revamps the way we
  create initial page tables.  In particular, rather than estimating how
  much memory we will need for page tables and then build them into that
  memory -- a calculation that has shown to be incredibly fragile -- we
  now build them (on 64 bits) with the aid of a "pseudo-linear mode" --
  a #PF handler which creates temporary page tables on demand.

  This has several advantages:

  1. It makes it much easier to support things that need access to data
     very early (a followon patchset uses this to load microcode way
     early in the kernel startup).

  2. It allows the kernel and all the kernel data objects to be invoked
     from above the 4 GB limit.  This allows kdump to work on very large
     systems.

  3. It greatly reduces the difference between Xen and native (Xen's
     equivalent of the #PF handler are the temporary page tables created
     by the domain builder), eliminating a bunch of fragile hooks.

  The patch series also gets us a bit closer to W^X.

  Additional work in this pull is the 64-bit get_user() work which you
  were also involved with, and a bunch of cleanups/speedups to
  __phys_addr()/__pa()."

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (105 commits)
  x86, mm: Move reserving low memory later in initialization
  x86, doc: Clarify the use of asm("%edx") in uaccess.h
  x86, mm: Redesign get_user with a __builtin_choose_expr hack
  x86: Be consistent with data size in getuser.S
  x86, mm: Use a bitfield to mask nuisance get_user() warnings
  x86/kvm: Fix compile warning in kvm_register_steal_time()
  x86-32: Add support for 64bit get_user()
  x86-32, mm: Remove reference to alloc_remap()
  x86-32, mm: Remove reference to resume_map_numa_kva()
  x86-32, mm: Rip out x86_32 NUMA remapping code
  x86/numa: Use __pa_nodebug() instead
  x86: Don't panic if can not alloc buffer for swiotlb
  mm: Add alloc_bootmem_low_pages_nopanic()
  x86, 64bit, mm: hibernate use generic mapping_init
  x86, 64bit, mm: Mark data/bss/brk to nx
  x86: Merge early kernel reserve for 32bit and 64bit
  x86: Add Crash kernel low reservation
  x86, kdump: Remove crashkernel range find limit for 64bit
  memblock: Add memblock_mem_size()
  x86, boot: Not need to check setup_header version for setup_data
  ...

12 files changed, 634 insertions, 554 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d7aea41563b3..d41815265a0b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -17,86 +17,132 @@
 #include <asm/proto.h>
 #include <asm/dma.h>		/* for MAX_DMA_PFN */
 
-unsigned long __initdata pgt_buf_start;
-unsigned long __meminitdata pgt_buf_end;
-unsigned long __meminitdata pgt_buf_top;
+#include "mm_internal.h"
 
-int after_bootmem;
+static unsigned long __initdata pgt_buf_start;
+static unsigned long __initdata pgt_buf_end;
+static unsigned long __initdata pgt_buf_top;
 
-int direct_gbpages
-#ifdef CONFIG_DIRECT_GBPAGES
-				= 1
-#endif
-;
+static unsigned long min_pfn_mapped;
 
-struct map_range {
-	unsigned long start;
-	unsigned long end;
-	unsigned page_size_mask;
-};
+static bool __initdata can_use_brk_pgt = true;
 
 /*
- * First calculate space needed for kernel direct mapping page tables to cover
- * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
- * pages. Then find enough contiguous space for those page tables.
+ * Pages returned are already directly mapped.
+ *
+ * Changing that is likely to break Xen, see commit:
+ *
+ *    279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve
+ *
+ * for detailed information.
  */
-static void __init find_early_table_space(struct map_range *mr, int nr_range)
+__ref void *alloc_low_pages(unsigned int num)
 {
+	unsigned long pfn;
 	int i;
-	unsigned long puds = 0, pmds = 0, ptes = 0, tables;
-	unsigned long start = 0, good_end;
-	phys_addr_t base;
 
-	for (i = 0; i < nr_range; i++) {
-		unsigned long range, extra;
+	if (after_bootmem) {
+		unsigned int order;
 
-		range = mr[i].end - mr[i].start;
-		puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
+		order = get_order((unsigned long)num << PAGE_SHIFT);
+		return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK |
+						__GFP_ZERO, order);
+	}
 
-		if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) {
-			extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT);
-			pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT;
-		} else {
-			pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT;
-		}
+	if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
+		unsigned long ret;
+		if (min_pfn_mapped >= max_pfn_mapped)
+			panic("alloc_low_page: ran out of memory");
+		ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT,
+					max_pfn_mapped << PAGE_SHIFT,
+					PAGE_SIZE * num , PAGE_SIZE);
+		if (!ret)
+			panic("alloc_low_page: can not alloc memory");
+		memblock_reserve(ret, PAGE_SIZE * num);
+		pfn = ret >> PAGE_SHIFT;
+	} else {
+		pfn = pgt_buf_end;
+		pgt_buf_end += num;
+		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
+			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
+	}
 
-		if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) {
-			extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT);
-#ifdef CONFIG_X86_32
-			extra += PMD_SIZE;
-#endif
-			ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		} else {
-			ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		}
+	for (i = 0; i < num; i++) {
+		void *adr;
+
+		adr = __va((pfn + i) << PAGE_SHIFT);
+		clear_page(adr);
 	}
 
-	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
-	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
-	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
+	return __va(pfn << PAGE_SHIFT);
+}
 
-#ifdef CONFIG_X86_32
-	/* for fixmap */
-	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-#endif
-	good_end = max_pfn_mapped << PAGE_SHIFT;
+/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
+#define INIT_PGT_BUF_SIZE	(5 * PAGE_SIZE)
+RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
+void  __init early_alloc_pgt_buf(void)
+{
+	unsigned long tables = INIT_PGT_BUF_SIZE;
+	phys_addr_t base;
 
-	base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
-	if (!base)
-		panic("Cannot find space for the kernel page tables");
+	base = __pa(extend_brk(tables, PAGE_SIZE));
 
 	pgt_buf_start = base >> PAGE_SHIFT;
 	pgt_buf_end = pgt_buf_start;
 	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
+}
+
+int after_bootmem;
+
+int direct_gbpages
+#ifdef CONFIG_DIRECT_GBPAGES
+				= 1
+#endif
+;
 
-	printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
-		mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT,
-		(pgt_buf_top << PAGE_SHIFT) - 1);
+static void __init init_gbpages(void)
+{
+#ifdef CONFIG_X86_64
+	if (direct_gbpages && cpu_has_gbpages)
+		printk(KERN_INFO "Using GB pages for direct mapping\n");
+	else
+		direct_gbpages = 0;
+#endif
 }
 
-void __init native_pagetable_reserve(u64 start, u64 end)
+struct map_range {
+	unsigned long start;
+	unsigned long end;
+	unsigned page_size_mask;
+};
+
+static int page_size_mask;
+
+static void __init probe_page_size_mask(void)
 {
-	memblock_reserve(start, end - start);
+	init_gbpages();
+
+#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK)
+	/*
+	 * 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.
+	 */
+	if (direct_gbpages)
+		page_size_mask |= 1 << PG_LEVEL_1G;
+	if (cpu_has_pse)
+		page_size_mask |= 1 << PG_LEVEL_2M;
+#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;
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -122,58 +168,51 @@ static int __meminit save_mr(struct map_range *mr, int 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.
+ * adjust the page_size_mask for small range to go with
+ *	big page size instead small one if nearby are ram too.
  */
-unsigned long __init_refok init_memory_mapping(unsigned long start,
-					       unsigned long end)
+static void __init_refok adjust_range_page_size_mask(struct map_range *mr,
+							 int nr_range)
 {
-	unsigned long page_size_mask = 0;
-	unsigned long start_pfn, end_pfn;
-	unsigned long ret = 0;
-	unsigned long pos;
-
-	struct map_range mr[NR_RANGE_MR];
-	int nr_range, i;
-	int use_pse, use_gbpages;
+	int i;
 
-	printk(KERN_INFO "init_memory_mapping: [mem %#010lx-%#010lx]\n",
-	       start, end - 1);
+	for (i = 0; i < nr_range; i++) {
+		if ((page_size_mask & (1<<PG_LEVEL_2M)) &&
+		    !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) {
+			unsigned long start = round_down(mr[i].start, PMD_SIZE);
+			unsigned long end = round_up(mr[i].end, PMD_SIZE);
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
-	/*
-	 * 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;
+#ifdef CONFIG_X86_32
+			if ((end >> PAGE_SHIFT) > max_low_pfn)
+				continue;
 #endif
 
-	/* Enable PSE if available */
-	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
+			if (memblock_is_region_memory(start, end - start))
+				mr[i].page_size_mask |= 1<<PG_LEVEL_2M;
+		}
+		if ((page_size_mask & (1<<PG_LEVEL_1G)) &&
+		    !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) {
+			unsigned long start = round_down(mr[i].start, PUD_SIZE);
+			unsigned long end = round_up(mr[i].end, PUD_SIZE);
 
-	/* Enable PGE if available */
-	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
-		__supported_pte_mask |= _PAGE_GLOBAL;
+			if (memblock_is_region_memory(start, end - start))
+				mr[i].page_size_mask |= 1<<PG_LEVEL_1G;
+		}
 	}
+}
 
-	if (use_gbpages)
-		page_size_mask |= 1 << PG_LEVEL_1G;
-	if (use_pse)
-		page_size_mask |= 1 << PG_LEVEL_2M;
+static int __meminit split_mem_range(struct map_range *mr, int nr_range,
+				     unsigned long start,
+				     unsigned long end)
+{
+	unsigned long start_pfn, end_pfn, limit_pfn;
+	unsigned long pfn;
+	int i;
 
-	memset(mr, 0, sizeof(mr));
-	nr_range = 0;
+	limit_pfn = PFN_DOWN(end);
 
 	/* head if not big page alignment ? */
-	start_pfn = start >> PAGE_SHIFT;
-	pos = start_pfn << PAGE_SHIFT;
+	pfn = start_pfn = PFN_DOWN(start);
 #ifdef CONFIG_X86_32
 	/*
 	 * Don't use a large page for the first 2/4MB of memory
@@ -181,66 +220,60 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	 * and overlapping MTRRs into large pages can cause
 	 * slowdowns.
 	 */
-	if (pos == 0)
-		end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
+	if (pfn == 0)
+		end_pfn = PFN_DOWN(PMD_SIZE);
 	else
-		end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
-				 << (PMD_SHIFT - PAGE_SHIFT);
+		end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
 #else /* CONFIG_X86_64 */
-	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
-			<< (PMD_SHIFT - PAGE_SHIFT);
+	end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
 #endif
-	if (end_pfn > (end >> PAGE_SHIFT))
-		end_pfn = end >> PAGE_SHIFT;
+	if (end_pfn > limit_pfn)
+		end_pfn = limit_pfn;
 	if (start_pfn < end_pfn) {
 		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
-		pos = end_pfn << PAGE_SHIFT;
+		pfn = end_pfn;
 	}
 
 	/* big page (2M) range */
-	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
-			 << (PMD_SHIFT - PAGE_SHIFT);
+	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
 #ifdef CONFIG_X86_32
-	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
 #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));
+	end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
+	if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE)))
+		end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
 #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;
+		pfn = end_pfn;
 	}
 
 #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);
+	start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE));
 	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;
+		pfn = end_pfn;
 	}
 
 	/* 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);
+	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
 	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;
+		pfn = end_pfn;
 	}
 #endif
 
 	/* tail is not big page (2M) alignment */
-	start_pfn = pos>>PAGE_SHIFT;
-	end_pfn = end>>PAGE_SHIFT;
+	start_pfn = pfn;
+	end_pfn = limit_pfn;
 	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 
 	/* try to merge same page size and continuous */
@@ -257,59 +290,169 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 		nr_range--;
 	}
 
+	if (!after_bootmem)
+		adjust_range_page_size_mask(mr, nr_range);
+
 	for (i = 0; i < nr_range; i++)
 		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
 				mr[i].start, mr[i].end - 1,
 			(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(mr, nr_range);
+	return nr_range;
+}
+
+struct range pfn_mapped[E820_X_MAX];
+int nr_pfn_mapped;
+
+static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
+					     nr_pfn_mapped, start_pfn, end_pfn);
+	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX);
+
+	max_pfn_mapped = max(max_pfn_mapped, end_pfn);
+
+	if (start_pfn < (1UL<<(32-PAGE_SHIFT)))
+		max_low_pfn_mapped = max(max_low_pfn_mapped,
+					 min(end_pfn, 1UL<<(32-PAGE_SHIFT)));
+}
+
+bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_pfn_mapped; i++)
+		if ((start_pfn >= pfn_mapped[i].start) &&
+		    (end_pfn <= pfn_mapped[i].end))
+			return true;
+
+	return false;
+}
+
+/*
+ * 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)
+{
+	struct map_range mr[NR_RANGE_MR];
+	unsigned long ret = 0;
+	int nr_range, i;
+
+	pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n",
+	       start, end - 1);
+
+	memset(mr, 0, sizeof(mr));
+	nr_range = split_mem_range(mr, 0, start, end);
 
 	for (i = 0; i < nr_range; i++)
 		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
 						   mr[i].page_size_mask);
 
-#ifdef CONFIG_X86_32
-	early_ioremap_page_table_range_init();
+	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);
 
-	load_cr3(swapper_pg_dir);
-#endif
+	return ret >> PAGE_SHIFT;
+}
 
-	__flush_tlb_all();
+/*
+ * would have hole in the middle or ends, and only ram parts will be mapped.
+ */
+static unsigned long __init init_range_memory_mapping(
+					   unsigned long r_start,
+					   unsigned long r_end)
+{
+	unsigned long start_pfn, end_pfn;
+	unsigned long mapped_ram_size = 0;
+	int i;
 
-	/*
-	 * Reserve the kernel pagetable pages we used (pgt_buf_start -
-	 * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
-	 * so that they can be reused for other purposes.
-	 *
-	 * On native it just means calling memblock_reserve, on Xen it also
-	 * means marking RW the pagetable pages that we allocated before
-	 * but that haven't been used.
-	 *
-	 * In fact on xen we mark RO the whole range pgt_buf_start -
-	 * pgt_buf_top, because we have to make sure that when
-	 * init_memory_mapping reaches the pagetable pages area, it maps
-	 * RO all the pagetable pages, including the ones that are beyond
-	 * pgt_buf_end at that time.
-	 */
-	if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-		x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
-				PFN_PHYS(pgt_buf_end));
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+		u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end);
+		u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end);
+		if (start >= end)
+			continue;
 
-	if (!after_bootmem)
-		early_memtest(start, end);
+		/*
+		 * if it is overlapping with brk pgt, we need to
+		 * alloc pgt buf from memblock instead.
+		 */
+		can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >=
+				    min(end, (u64)pgt_buf_top<<PAGE_SHIFT);
+		init_memory_mapping(start, end);
+		mapped_ram_size += end - start;
+		can_use_brk_pgt = true;
+	}
 
-	return ret >> PAGE_SHIFT;
+	return mapped_ram_size;
 }
 
+/* (PUD_SHIFT-PMD_SHIFT)/2 */
+#define STEP_SIZE_SHIFT 5
+void __init init_mem_mapping(void)
+{
+	unsigned long end, real_end, start, last_start;
+	unsigned long step_size;
+	unsigned long addr;
+	unsigned long mapped_ram_size = 0;
+	unsigned long new_mapped_ram_size;
+
+	probe_page_size_mask();
+
+#ifdef CONFIG_X86_64
+	end = max_pfn << PAGE_SHIFT;
+#else
+	end = max_low_pfn << PAGE_SHIFT;
+#endif
+
+	/* the ISA range is always mapped regardless of memory holes */
+	init_memory_mapping(0, ISA_END_ADDRESS);
+
+	/* xen has big range in reserved near end of ram, skip it at first */
+	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE,
+			 PAGE_SIZE);
+	real_end = addr + PMD_SIZE;
+
+	/* step_size need to be small so pgt_buf from BRK could cover it */
+	step_size = PMD_SIZE;
+	max_pfn_mapped = 0; /* will get exact value next */
+	min_pfn_mapped = real_end >> PAGE_SHIFT;
+	last_start = start = real_end;
+	while (last_start > ISA_END_ADDRESS) {
+		if (last_start > step_size) {
+			start = round_down(last_start - 1, step_size);
+			if (start < ISA_END_ADDRESS)
+				start = ISA_END_ADDRESS;
+		} else
+			start = ISA_END_ADDRESS;
+		new_mapped_ram_size = init_range_memory_mapping(start,
+							last_start);
+		last_start = start;
+		min_pfn_mapped = last_start >> PAGE_SHIFT;
+		/* only increase step_size after big range get mapped */
+		if (new_mapped_ram_size > mapped_ram_size)
+			step_size <<= STEP_SIZE_SHIFT;
+		mapped_ram_size += new_mapped_ram_size;
+	}
+
+	if (real_end < end)
+		init_range_memory_mapping(real_end, end);
+
+#ifdef CONFIG_X86_64
+	if (max_pfn > max_low_pfn) {
+		/* can we preseve max_low_pfn ?*/
+		max_low_pfn = max_pfn;
+	}
+#else
+	early_ioremap_page_table_range_init();
+#endif
+
+	load_cr3(swapper_pg_dir);
+	__flush_tlb_all();
+
+	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
+}
 
 /*
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 745d66b843c8..b299724f6e34 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -53,25 +53,14 @@
 #include <asm/page_types.h>
 #include <asm/init.h>
 
+#include "mm_internal.h"
+
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
 
 bool __read_mostly __vmalloc_start_set = false;
 
-static __init void *alloc_low_page(void)
-{
-	unsigned long pfn = pgt_buf_end++;
-	void *adr;
-
-	if (pfn >= pgt_buf_top)
-		panic("alloc_low_page: ran out of memory");
-
-	adr = __va(pfn * PAGE_SIZE);
-	clear_page(adr);
-	return adr;
-}
-
 /*
  * Creates a middle page table and puts a pointer to it in the
  * given global directory entry. This only returns the gd entry
@@ -84,10 +73,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
-		if (after_bootmem)
-			pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
-		else
-			pmd_table = (pmd_t *)alloc_low_page();
+		pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
@@ -109,17 +95,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
-		pte_t *page_table = NULL;
-
-		if (after_bootmem) {
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
-			page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
-#endif
-			if (!page_table)
-				page_table =
-				(pte_t *)alloc_bootmem_pages(PAGE_SIZE);
-		} else
-			page_table = (pte_t *)alloc_low_page();
+		pte_t *page_table = (pte_t *)alloc_low_page();
 
 		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -146,8 +122,39 @@ pte_t * __init populate_extra_pte(unsigned long vaddr)
 	return one_page_table_init(pmd) + pte_idx;
 }
 
+static unsigned long __init
+page_table_range_init_count(unsigned long start, unsigned long end)
+{
+	unsigned long count = 0;
+#ifdef CONFIG_HIGHMEM
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+	int pgd_idx, pmd_idx;
+	unsigned long vaddr;
+
+	if (pmd_idx_kmap_begin == pmd_idx_kmap_end)
+		return 0;
+
+	vaddr = start;
+	pgd_idx = pgd_index(vaddr);
+
+	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
+		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
+							pmd_idx++) {
+			if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin &&
+			    (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end)
+				count++;
+			vaddr += PMD_SIZE;
+		}
+		pmd_idx = 0;
+	}
+#endif
+	return count;
+}
+
 static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
-					   unsigned long vaddr, pte_t *lastpte)
+					   unsigned long vaddr, pte_t *lastpte,
+					   void **adr)
 {
 #ifdef CONFIG_HIGHMEM
 	/*
@@ -161,16 +168,15 @@ 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) < pgt_buf_start
-		|| (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) {
+	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) {
 		pte_t *newpte;
 		int i;
 
 		BUG_ON(after_bootmem);
-		newpte = alloc_low_page();
+		newpte = *adr;
 		for (i = 0; i < PTRS_PER_PTE; i++)
 			set_pte(newpte + i, pte[i]);
+		*adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE);
 
 		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
@@ -204,6 +210,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 	pgd_t *pgd;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
+	unsigned long count = page_table_range_init_count(start, end);
+	void *adr = NULL;
+
+	if (count)
+		adr = alloc_low_pages(count);
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
@@ -216,7 +227,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
 							pmd++, pmd_idx++) {
 			pte = page_table_kmap_check(one_page_table_init(pmd),
-			                            pmd, vaddr, pte);
+						    pmd, vaddr, pte, &adr);
 
 			vaddr += PMD_SIZE;
 		}
@@ -310,6 +321,7 @@ repeat:
 					__pgprot(PTE_IDENT_ATTR |
 						 _PAGE_PSE);
 
+				pfn &= PMD_MASK >> PAGE_SHIFT;
 				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
 					PAGE_OFFSET + PAGE_SIZE-1;
 
@@ -455,9 +467,14 @@ void __init native_pagetable_init(void)
 
 	/*
 	 * Remove any mappings which extend past the end of physical
-	 * memory from the boot time page table:
+	 * memory from the boot time page table.
+	 * In virtual address space, we should have at least two pages
+	 * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END
+	 * definition. And max_low_pfn is set to VMALLOC_END physical
+	 * address. If initial memory mapping is doing right job, we
+	 * should have pte used near max_low_pfn or one pmd is not present.
 	 */
-	for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
+	for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
 		va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
 		pgd = base + pgd_index(va);
 		if (!pgd_present(*pgd))
@@ -468,10 +485,19 @@ void __init native_pagetable_init(void)
 		if (!pmd_present(*pmd))
 			break;
 
+		/* should not be large page here */
+		if (pmd_large(*pmd)) {
+			pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n",
+				pfn, pmd, __pa(pmd));
+			BUG_ON(1);
+		}
+
 		pte = pte_offset_kernel(pmd, va);
 		if (!pte_present(*pte))
 			break;
 
+		printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n",
+				pfn, pmd, __pa(pmd), pte, __pa(pte));
 		pte_clear(NULL, va, pte);
 	}
 	paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
@@ -550,7 +576,7 @@ early_param("highmem", parse_highmem);
  * artificially via the highmem=x boot parameter then create
  * it:
  */
-void __init lowmem_pfn_init(void)
+static void __init lowmem_pfn_init(void)
 {
 	/* max_low_pfn is 0, we already have early_res support */
 	max_low_pfn = max_pfn;
@@ -586,7 +612,7 @@ void __init lowmem_pfn_init(void)
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
  */
-void __init highmem_pfn_init(void)
+static void __init highmem_pfn_init(void)
 {
 	max_low_pfn = MAXMEM_PFN;
 
@@ -669,8 +695,6 @@ void __init setup_bootmem_allocator(void)
 	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);
-
-	after_bootmem = 1;
 }
 
 /*
@@ -753,6 +777,8 @@ void __init mem_init(void)
 		if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
 			reservedpages++;
 
+	after_bootmem = 1;
+
 	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
 	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d6eeead43758..3eba7f429880 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -54,6 +54,82 @@
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
 
+#include "mm_internal.h"
+
+static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+			   unsigned long addr, unsigned long end)
+{
+	addr &= PMD_MASK;
+	for (; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+
+		if (!pmd_present(*pmd))
+			set_pmd(pmd, __pmd(addr | pmd_flag));
+	}
+}
+static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		next = (addr & PUD_MASK) + PUD_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, 0);
+			ident_pmd_init(info->pmd_flag, pmd, addr, next);
+			continue;
+		}
+		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
+		if (!pmd)
+			return -ENOMEM;
+		ident_pmd_init(info->pmd_flag, pmd, addr, next);
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+			      unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+		pud_t *pud;
+
+		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pgd_present(*pgd)) {
+			pud = pud_offset(pgd, 0);
+			result = ident_pud_init(info, pud, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+		result = ident_pud_init(info, pud, addr, next);
+		if (result)
+			return result;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -302,10 +378,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+	unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE;
 	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
 
+	/*
+	 * Native path, max_pfn_mapped is not set yet.
+	 * Xen has valid max_pfn_mapped set in
+	 *	arch/x86/xen/mmu.c:xen_setup_kernel_pagetable().
+	 */
+	if (max_pfn_mapped)
+		vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+
 	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -314,69 +398,24 @@ void __init cleanup_highmap(void)
 	}
 }
 
-static __ref void *alloc_low_page(unsigned long *phys)
-{
-	unsigned long pfn = pgt_buf_end++;
-	void *adr;
-
-	if (after_bootmem) {
-		adr = (void *)get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
-		*phys = __pa(adr);
-
-		return adr;
-	}
-
-	if (pfn >= pgt_buf_top)
-		panic("alloc_low_page: ran out of memory");
-
-	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	clear_page(adr);
-	*phys  = pfn * PAGE_SIZE;
-	return adr;
-}
-
-static __ref void *map_low_page(void *virt)
-{
-	void *adr;
-	unsigned long phys, left;
-
-	if (after_bootmem)
-		return virt;
-
-	phys = __pa(virt);
-	left = phys & (PAGE_SIZE - 1);
-	adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
-	adr = (void *)(((unsigned long)adr) | left);
-
-	return adr;
-}
-
-static __ref void unmap_low_page(void *adr)
-{
-	if (after_bootmem)
-		return;
-
-	early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
-}
-
 static unsigned long __meminit
 phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 	      pgprot_t prot)
 {
-	unsigned pages = 0;
+	unsigned long pages = 0, next;
 	unsigned long last_map_addr = end;
 	int i;