1 files changed, 414 insertions, 157 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 32ba13b0f818..306049edd553 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
@@ -47,6 +48,14 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
 static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
@@ -135,26 +144,17 @@ static __init void *spp_getpage(void)
         return ptr;
 }
 
-static void
-set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
+void
+set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 {
-        pgd_t *pgd;
         pud_t *pud;
         pmd_t *pmd;
-        pte_t *pte, new_pte;
-
-        pr_debug("set_pte_phys %lx to %lx\n", vaddr, phys);
+        pte_t *pte;
 
-        pgd = pgd_offset_k(vaddr);
-        if (pgd_none(*pgd)) {
-                printk(KERN_ERR
-                        "PGD FIXMAP MISSING, it should be setup in head.S!\n");
-                return;
-        }
-        pud = pud_offset(pgd, vaddr);
+        pud = pud_page + pud_index(vaddr);
         if (pud_none(*pud)) {
                 pmd = (pmd_t *) spp_getpage();
-                set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
+                pud_populate(&init_mm, pud, pmd);
                 if (pmd != pmd_offset(pud, 0)) {
                         printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
                                 pmd, pmd_offset(pud, 0));
@@ -164,13 +164,12 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
         pmd = pmd_offset(pud, vaddr);
         if (pmd_none(*pmd)) {
                 pte = (pte_t *) spp_getpage();
-                set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
+                pmd_populate_kernel(&init_mm, pmd, pte);
                 if (pte != pte_offset_kernel(pmd, 0)) {
                         printk(KERN_ERR "PAGETABLE BUG #02!\n");
                         return;
                 }
         }
-        new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
 
         pte = pte_offset_kernel(pmd, vaddr);
         if (!pte_none(*pte) && pte_val(new_pte) &&
@@ -185,6 +184,64 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
         __flush_tlb_one(vaddr);
 }
 
+void
+set_pte_vaddr(unsigned long vaddr, pte_t pteval)
+{
+        pgd_t *pgd;
+        pud_t *pud_page;
+
+        pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));
+
+        pgd = pgd_offset_k(vaddr);
+        if (pgd_none(*pgd)) {
+                printk(KERN_ERR
+                        "PGD FIXMAP MISSING, it should be setup in head.S!\n");
+                return;
+        }
+        pud_page = (pud_t*)pgd_page_vaddr(*pgd);
+        set_pte_vaddr_pud(pud_page, vaddr, pteval);
+}
+
+/*
+ * Create large page table mappings for a range of physical addresses.
+ */
+static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
+                                                pgprot_t prot)
+{
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+
+        BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
+        for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
+                pgd = pgd_offset_k((unsigned long)__va(phys));
+                if (pgd_none(*pgd)) {
+                        pud = (pud_t *) spp_getpage();
+                        set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
+                                                _PAGE_USER));
+                }
+                pud = pud_offset(pgd, (unsigned long)__va(phys));
+                if (pud_none(*pud)) {
+                        pmd = (pmd_t *) spp_getpage();
+                        set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
+                                                _PAGE_USER));
+                }
+                pmd = pmd_offset(pud, phys);
+                BUG_ON(!pmd_none(*pmd));
+                set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
+        }
+}
+
+void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
+{
+        __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
+}
+
+void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
+{
+        __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
+}
+
 /*
  * The head.S code sets up the kernel high mapping:
  *
@@ -206,27 +263,16 @@ void __init cleanup_highmap(void)
         pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
         for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
-                if (!pmd_present(*pmd))
+                if (pmd_none(*pmd))
                         continue;
                 if (vaddr < (unsigned long) _text || vaddr > end)
                         set_pmd(pmd, __pmd(0));
         }
 }
 
-/* NOTE: this is meant to be run only at boot */
-void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
-{
-        unsigned long address = __fix_to_virt(idx);
-
-        if (idx >= __end_of_fixed_addresses) {
-                printk(KERN_ERR "Invalid __set_fixmap\n");
-                return;
-        }
-        set_pte_phys(address, phys, prot);
-}
-
 static unsigned long __initdata table_start;
 static unsigned long __meminitdata table_end;
+static unsigned long __meminitdata table_top;
 
 static __meminit void *alloc_low_page(unsigned long *phys)
 {
@@ -240,7 +286,7 @@ static __meminit void *alloc_low_page(unsigned long *phys)
                 return adr;
         }
 
-        if (pfn >= end_pfn)
+        if (pfn >= table_top)
                 panic("alloc_low_page: ran out of memory");
 
         adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
@@ -257,65 +303,61 @@ static __meminit void unmap_low_page(void *adr)
         early_iounmap(adr, PAGE_SIZE);
 }
 
-/* Must run before zap_low_mappings */
-__meminit void *early_ioremap(unsigned long addr, unsigned long size)
+static unsigned long __meminit
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
 {
-        pmd_t *pmd, *last_pmd;
-        unsigned long vaddr;
-        int i, pmds;
+        unsigned pages = 0;
+        unsigned long last_map_addr = end;
+        int i;
+
+        pte_t *pte = pte_page + pte_index(addr);
 
-        pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
-        vaddr = __START_KERNEL_map;
-        pmd = level2_kernel_pgt;
-        last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;
+        for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {
 
-        for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
-                for (i = 0; i < pmds; i++) {
-                        if (pmd_present(pmd[i]))
-                                goto continue_outer_loop;
+                if (addr >= end) {
+                        if (!after_bootmem) {
+                                for(; i < PTRS_PER_PTE; i++, pte++)
+                                        set_pte(pte, __pte(0));
+                        }
+                        break;
                 }
-                vaddr += addr & ~PMD_MASK;
-                addr &= PMD_MASK;
 
-                for (i = 0; i < pmds; i++, addr += PMD_SIZE)
-                        set_pmd(pmd+i, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
-                __flush_tlb_all();
+                if (pte_val(*pte))
+                        continue;
 
-                return (void *)vaddr;
-continue_outer_loop:
-                ;
+                if (0)
+                        printk("   pte=%p addr=%lx pte=%016lx\n",
+                               pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
+                set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL));
+                last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
+                pages++;
         }
-        printk(KERN_ERR "early_ioremap(0x%lx, %lu) failed\n", addr, size);
+        update_page_count(PG_LEVEL_4K, pages);
 
-        return NULL;
+        return last_map_addr;
 }
 
-/*
- * To avoid virtual aliases later:
- */
-__meminit void early_iounmap(void *addr, unsigned long size)
+static unsigned long __meminit
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end)
 {
-        unsigned long vaddr;
-        pmd_t *pmd;
-        int i, pmds;
-
-        vaddr = (unsigned long)addr;
-        pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
-        pmd = level2_kernel_pgt + pmd_index(vaddr);
+        pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
 
-        for (i = 0; i < pmds; i++)
-                pmd_clear(pmd + i);
-
-        __flush_tlb_all();
+        return phys_pte_init(pte, address, end);
 }
 
 static unsigned long __meminit
-phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
+phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
+                         unsigned long page_size_mask)
 {
+        unsigned long pages = 0;
+        unsigned long last_map_addr = end;
+
         int i = pmd_index(address);
 
         for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
+                unsigned long pte_phys;
                 pmd_t *pmd = pmd_page + pmd_index(address);
+                pte_t *pte;
 
                 if (address >= end) {
                         if (!after_bootmem) {
@@ -325,31 +367,50 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
                         break;
                 }
 
-                if (pmd_val(*pmd))
+                if (pmd_val(*pmd)) {
+                        if (!pmd_large(*pmd))
+                                last_map_addr = phys_pte_update(pmd, address,
+                                                                 end);
+                        continue;
+                }
+
+                if (page_size_mask & (1<<PG_LEVEL_2M)) {
+                        pages++;
+                        set_pte((pte_t *)pmd,
+                                pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+                        last_map_addr = (address & PMD_MASK) + PMD_SIZE;
                         continue;
+                }
 
-                set_pte((pte_t *)pmd,
-                        pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+                pte = alloc_low_page(&pte_phys);
+                last_map_addr = phys_pte_init(pte, address, end);
+                unmap_low_page(pte);
+
+                pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
         }
-        return address;
+        update_page_count(PG_LEVEL_2M, pages);
+        return last_map_addr;
 }
 
 static unsigned long __meminit
-phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
+phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
+                         unsigned long page_size_mask)
 {
         pmd_t *pmd = pmd_offset(pud, 0);
         unsigned long last_map_addr;
 
         spin_lock(&init_mm.page_table_lock);
-        last_map_addr = phys_pmd_init(pmd, address, end);
+        last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
         spin_unlock(&init_mm.page_table_lock);
         __flush_tlb_all();
         return last_map_addr;
 }
 
 static unsigned long __meminit
-phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
+phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
+                         unsigned long page_size_mask)
 {
+        unsigned long pages = 0;
         unsigned long last_map_addr = end;
         int i = pud_index(addr);
 
@@ -369,11 +430,13 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 
                 if (pud_val(*pud)) {
                         if (!pud_large(*pud))
-                                last_map_addr = phys_pmd_update(pud, addr, end);
+                                last_map_addr = phys_pmd_update(pud, addr, end,
+                                                         page_size_mask);
                         continue;
                 }
 
-                if (direct_gbpages) {
+                if (page_size_mask & (1<<PG_LEVEL_1G)) {
+                        pages++;
                         set_pte((pte_t *)pud,
                                 pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
                         last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
@@ -383,27 +446,50 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
                 pmd = alloc_low_page(&pmd_phys);
 
                 spin_lock(&init_mm.page_table_lock);
-                set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
-                last_map_addr = phys_pmd_init(pmd, addr, end);
+                last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
+                unmap_low_page(pmd);
+                pud_populate(&init_mm, pud, __va(pmd_phys));
                 spin_unlock(&init_mm.page_table_lock);
 
-                unmap_low_page(pmd);
         }
         __flush_tlb_all();
+        update_page_count(PG_LEVEL_1G, pages);
 
-        return last_map_addr >> PAGE_SHIFT;
+        return last_map_addr;
+}
+
+static unsigned long __meminit
+phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
+                 unsigned long page_size_mask)
+{
+        pud_t *pud;
+
+        pud = (pud_t *)pgd_page_vaddr(*pgd);
+
+        return phys_pud_init(pud, addr, end, page_size_mask);
 }
 
 static void __init find_early_table_space(unsigned long end)
 {
-        unsigned long puds, pmds, tables, start;
+        unsigned long puds, pmds, ptes, tables, start;
 
         puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
         tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
-        if (!direct_gbpages) {
+        if (direct_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 += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
-        }
+        tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+
+        if (cpu_has_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 += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
 
         /*
          * RED-PEN putting page tables only on node 0 could
@@ -417,10 +503,10 @@ static void __init find_early_table_space(unsigned long end)
 
         table_start >>= PAGE_SHIFT;
         table_end = table_start;
+        table_top = table_start + (tables >> PAGE_SHIFT);
 
-        early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
-                end, table_start << PAGE_SHIFT,
-                (table_start << PAGE_SHIFT) + tables);
+        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)
@@ -431,7 +517,7 @@ static void __init init_gbpages(void)
                 direct_gbpages = 0;
 }
 
-#ifdef CONFIG_MEMTEST_BOOTPARAM
+#ifdef CONFIG_MEMTEST
 
 static void __init memtest(unsigned long start_phys, unsigned long size,
                                  unsigned pattern)
@@ -493,7 +579,8 @@ static void __init memtest(unsigned long start_phys, unsigned long size,
 
 }
 
-static int memtest_pattern __initdata = CONFIG_MEMTEST_BOOTPARAM_VALUE;
+/* default is disabled */
+static int memtest_pattern __initdata;
 
 static int __init parse_memtest(char *arg)
 {
@@ -506,7 +593,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-        unsigned long t_start, t_size;
+        u64 t_start, t_size;
         unsigned pattern;
 
         if (!memtest_pattern)
@@ -525,8 +612,9 @@ static void __init early_memtest(unsigned long start, unsigned long end)
                         if (t_start + t_size > end)
                                 t_size = end - t_start;
 
-                        printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
-                                t_start, t_start + t_size, pattern);
+                        printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
+                                (unsigned long long)t_start,
+                                (unsigned long long)t_start + t_size, pattern);
 
                         memtest(t_start, t_size, pattern);
 
@@ -541,15 +629,85 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 }
 #endif
 
+static 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;
+
+        start = (unsigned long)__va(start);
+        end = (unsigned long)__va(end);
+
+        for (; start < end; start = next) {
+                pgd_t *pgd = pgd_offset_k(start);
+                unsigned long pud_phys;
+                pud_t *pud;
+
+                next = (start + PGDIR_SIZE) & PGDIR_MASK;
+                if (next > end)
+                        next = end;
+
+                if (pgd_val(*pgd)) {
+                        last_map_addr = phys_pud_update(pgd, __pa(start),
+                                                 __pa(end), page_size_mask);
+                        continue;
+                }
+
+                if (after_bootmem)
+                        pud = pud_offset(pgd, start & PGDIR_MASK);
+                else
+                        pud = alloc_low_page(&pud_phys);
+
+                last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
+                                                 page_size_mask);
+                unmap_low_page(pud);
+                pgd_populate(&init_mm, pgd_offset_k(start),
+                             __va(pud_phys));
+        }
+
+        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 __init_refok init_memory_mapping(unsigned long start,
+                                               unsigned long end)
 {
-        unsigned long next, last_map_addr = end;
-        unsigned long start_phys = start, end_phys = end;
+        unsigned long last_map_addr = 0;
+        unsigned long page_size_mask = 0;
+        unsigned long start_pfn, end_pfn;
+
+        struct map_range mr[NR_RANGE_MR];
+        int nr_range, i;
 
         printk(KERN_INFO "init_memory_mapping\n");
 
@@ -560,48 +718,115 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned lon
          * memory mapped. Unfortunately this is done currently before the
          * nodes are discovered.
          */
-        if (!after_bootmem) {
+        if (!after_bootmem)
                 init_gbpages();
-                find_early_table_space(end);
+
+        if (direct_gbpages)
+                page_size_mask |= 1 << PG_LEVEL_1G;
+        if (cpu_has_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;
+        end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT)
+                        << (PMD_SHIFT - PAGE_SHIFT);
+        nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+
+        /* big page (2M) range*/
+        start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
+                         << (PMD_SHIFT - PAGE_SHIFT);
+        end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT)
+                         << (PUD_SHIFT - PAGE_SHIFT);
+        if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)))
+                end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT));
+        nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                        page_size_mask & (1<<PG_LEVEL_2M));
+
+        /* big page (1G) range */
+        start_pfn = end_pfn;
+        end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+        nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                                page_size_mask &
+                                 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+
+        /* tail is not big page (1G) alignment */
+        start_pfn = end_pfn;
+        end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+        nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+                        page_size_mask & (1<<PG_LEVEL_2M));
+
+        /* tail is not big page (2M) alignment */
+        start_pfn = end_pfn;
+        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--;
         }
 
-        start = (unsigned long)__va(start);
-        end = (unsigned long)__va(end);
+        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"));
 
-        for (; start < end; start = next) {
-                pgd_t *pgd = pgd_offset_k(start);
-                unsigned long pud_phys;
-                pud_t *pud;
-
-                if (after_bootmem)
-                        pud = pud_offset(pgd, start & PGDIR_MASK);
-                else
-                        pud = alloc_low_page(&pud_phys);
+        if (!after_bootmem)
+                find_early_table_space(end);
 
-                next = start + PGDIR_SIZE;
-                if (next > end)
-                        next = end;
-                last_map_addr = phys_pud_init(pud, __pa(start), __pa(next));
-                if (!after_bootmem)
-                        set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
-                unmap_low_page(pud);
-        }
+        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)
+        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_phys, end_phys);
+                early_memtest(start, end);
 
-        return last_map_addr;
+        return last_map_addr >> PAGE_SHIFT;
 }
 
 #ifndef CONFIG_NUMA
+void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
+{
+        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);
+        /* 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);
+        early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
+        reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
+}
+
 void __init paging_init(void)
 {
         unsigned long max_zone_pfns[MAX_NR_ZONES];
@@ -609,9 +834,9 @@ void __init paging_init(void)
         memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
         max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
         max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
-        max_zone_pfns[ZONE_NORMAL] = end_pfn;
+        max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
-        memory_present(0, 0, end_pfn);
+        memory_present(0, 0, max_pfn);
         sparse_init();
         free_area_init_nodes(max_zone_pfns);
 }
@@ -693,8 +918,8 @@ void __init mem_init(void)
 #else
         totalram_pages = free_all_bootmem();
 #endif
-        reservedpages = end_pfn - totalram_pages -
-                                        absent_pages_in_range(0, end_pfn);
+        reservedpages = max_pfn - totalram_pages -
+                                        absent_pages_in_range(0, max_pfn);
         after_bootmem = 1;
 
         codesize =  (unsigned long) &_etext - (unsigned long) &_text;
@@ -713,7 +938,7 @@ void __init mem_init(void)
         printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
                                 "%ldk reserved, %ldk data, %ldk init)\n",
                 (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
-                end_pfn << (PAGE_SHIFT-10),
+                max_pfn << (PAGE_SHIFT-10),
                 codesize >> 10,
                 reservedpages << (PAGE_SHIFT-10),
                 datasize >> 10,
@@ -766,6 +991,13 @@ EXPORT_SYMBOL_GPL(rodata_test_data);
 void mark_rodata_ro(void)
 {
         unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
+        unsigned long rodata_start =
+                ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+        /* Dynamic tracing modifies the kernel text section */
+        start = rodata_start;
+#endif
 
         printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
                (end - start) >> 10);
@@ -775,8 +1007,7 @@ void mark_rodata_ro(void)
          * The rodata section (but not the kernel text!) should also be
          * not-executable.
          */
-        start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
-        set_memory_nx(start, (end - start) >> PAGE_SHIFT);
+        set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
 
         rodata_test();
 
@@ -798,24 +1029,26 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
+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 >= end_pfn) {
+        if (pfn >= max_pfn) {
                 /*
                  * This can happen with kdump kernels when accessing
                  * firmware tables:
                  */
                 if (pfn < max_pfn_mapped)
-                        return;
+                        return -EFAULT;
 
-                printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n",
+                printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
                                 phys, len);
-                return;
+                return -EFAULT;
         }
 
         /* Should check here against the e820 map to avoid double free */
@@ -823,9 +1056,13 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
         nid = phys_to_nid(phys);
         next_nid = phys_to_nid(phys + len - 1);
         if (nid == next_nid)
-                reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+                ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
         else
-                reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+                ret = reserve_bootmem(phys, len, flags);
+
+        if (ret != 0)
+                return ret;
+
 #else
         reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
@@ -834,6 +1071,8 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
                 dma_reserve += len / PAGE_SIZE;
                 set_dma_reserve(dma_reserve);
         }
+
+        return 0;
 }
 
 int kern_addr_valid(unsigned long addr)
@@ -938,7 +1177,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
         pmd_t *pmd;
 
         for (; addr < end; addr = next) {
-                next = pmd_addr_end(addr, end);
+                void *p = NULL;
 
                 pgd = vmemmap_pgd_populate(addr, node);
                 if (!pgd)
@@ -948,33 +1187,51 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
                 if (!pud)
                         return -ENOMEM;
 
-                pmd = pmd_offset(pud, addr);
-                if (pmd_none(*pmd)) {
-                        pte_t entry;
-                        void *p;
+                if (!cpu_has_pse) {
+                        next = (addr + PAGE_SIZE) & PAGE_MASK;
+                        pmd = vmemmap_pmd_populate(pud, addr, node);
+
+                        if (!pmd)
+                                return -ENOMEM;
+
+                        p = vmemmap_pte_populate(pmd, addr, node);
 
-                        p = vmemmap_alloc_block(PMD_SIZE, node);
                         if (!p)
                                 return -ENOMEM;
 
-                        entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-                                                        PAGE_KERNEL_LARGE);
-                        set_pmd(pmd, __pmd(pte_val(entry)));
-
-                        /* check to see if we have contiguous blocks */
-                        if (p_end != p || node_start != node) {
-                                if (p_start)
-                                        printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-                                                addr_start, addr_end-1, p_start, p_end-1, node_start);
-                                addr_start = addr;
-                                node_start = node;
-                                p_start = p;
-                        }
-                        addr_end = addr + PMD_SIZE;
-                        p_end = p + PMD_SIZE;
+                        addr_end = addr + PAGE_SIZE;
+                        p_end = p + PAGE_SIZE;
                 } else {
-                        vmemmap_verify((pte_t *)pmd, node, addr, next);
+                        next = pmd_addr_end(addr, end);
+
+                        pmd = pmd_offset(pud, addr);
+                        if (pmd_none(*pmd)) {
+                                pte_t entry;
+
+                                p = vmemmap_alloc_block(PMD_SIZE, node);
+                                if (!p)
+                                        return -ENOMEM;
+
+                                entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
+                                                PAGE_KERNEL_LARGE);
+                                set_pmd(pmd, __pmd(pte_val(entry)));
+
+                                /* check to see if we have contiguous blocks */
+                                if (p_end != p || node_start != node) {
+                                        if (p_start)
+                                                printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+                                                       addr_start, addr_end-1, p_start, p_end-1, node_start);
+                                        addr_start = addr;
+                                        node_start = node;
+                                        p_start = p;
+                                }
+
+                                addr_end = addr + PMD_SIZE;
+                                p_end = p + PMD_SIZE;
+                        } else
+                                vmemmap_verify((pte_t *)pmd, node, addr, next);
                 }
+
         }
         return 0;
 }