int ehea_create_busmap( void )
{
	u64 vaddr = EHEA_BUSMAP_START;
	unsigned long high_section_index = 0;
	int i;

	/*
	 * Sections are not in ascending order -> Loop over all sections and
	 * find the highest PFN to compute the required map size.
	*/
	ehea_bmap.valid_sections = 0;

	for (i = 0; i < NR_MEM_SECTIONS; i++)
		if (valid_section_nr(i))
			high_section_index = i;

	ehea_bmap.entries = high_section_index + 1;
	ehea_bmap.vaddr = vmalloc(ehea_bmap.entries * sizeof(*ehea_bmap.vaddr));

	if (!ehea_bmap.vaddr)
		return -ENOMEM;

	for (i = 0 ; i < ehea_bmap.entries; i++) {
		unsigned long pfn = section_nr_to_pfn(i);

		if (pfn_valid(pfn)) {
			ehea_bmap.vaddr[i] = vaddr;
			vaddr += EHEA_SECTSIZE;
			ehea_bmap.valid_sections++;
		} else
			ehea_bmap.vaddr[i] = 0;
	}

	return 0;
}

/*
 * The performance critical leaf functions are made noinline otherwise gcc
 * inlines everything into a single function which results in too much
 * register pressure.
 */
static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long mask, result;
	pte_t *ptep;

	result = _PAGE_PRESENT|_PAGE_USER;
	if (write)
		result |= _PAGE_RW;
	mask = result | _PAGE_SPECIAL;

	ptep = pte_offset_kernel(&pmd, addr);
	do {
		pte_t pte = ACCESS_ONCE(*ptep);
		struct page *page;

		if ((pte_val(pte) & mask) != result)
			return 0;
		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
		page = pte_page(pte);
		if (!page_cache_get_speculative(page))
			return 0;
		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
			put_page(page);
			return 0;
		}
		pages[*nr] = page;
		(*nr)++;

	} while (ptep++, addr += PAGE_SIZE, addr != end);

	return 1;
}

/* Is address valid for reading? */
static int valid_address(struct KBacktraceIterator *kbt, VirtualAddress address)
{
	HV_PTE *l1_pgtable = kbt->pgtable;
	HV_PTE *l2_pgtable;
	unsigned long pfn;
	HV_PTE pte;
	struct page *page;

	if (l1_pgtable == NULL)
		return 0;	/* can't read user space in other tasks */

	pte = l1_pgtable[HV_L1_INDEX(address)];
	if (!hv_pte_get_present(pte))
		return 0;
	pfn = hv_pte_get_pfn(pte);
	if (pte_huge(pte)) {
		if (!pfn_valid(pfn)) {
			pr_err("huge page has bad pfn %#lx\n", pfn);
			return 0;
		}
		return hv_pte_get_present(pte) && hv_pte_get_readable(pte);
	}

	page = pfn_to_page(pfn);
	if (PageHighMem(page)) {
		pr_err("L2 page table not in LOWMEM (%#llx)\n",
		       HV_PFN_TO_CPA(pfn));
		return 0;
	}
	l2_pgtable = (HV_PTE *)pfn_to_kaddr(pfn);
	pte = l2_pgtable[HV_L2_INDEX(address)];
	return hv_pte_get_present(pte) && hv_pte_get_readable(pte);
}

void __init page_ext_init(void)
{
	unsigned long pfn;
	int nid;

	if (!invoke_need_callbacks())
		return;

	for_each_node_state(nid, N_MEMORY) {
		unsigned long start_pfn, end_pfn;

		start_pfn = node_start_pfn(nid);
		end_pfn = node_end_pfn(nid);
		/*
		 * start_pfn and end_pfn may not be aligned to SECTION and the
		 * page->flags of out of node pages are not initialized.  So we
		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
		 */
		for (pfn = start_pfn; pfn < end_pfn;
			pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {

			if (!pfn_valid(pfn))
				continue;
			/*
			 * Nodes's pfns can be overlapping.
			 * We know some arch can have a nodes layout such as
			 * -------------pfn-------------->
			 * N0 | N1 | N2 | N0 | N1 | N2|....
			 */
			if (pfn_to_nid(pfn) != nid)
				continue;
			if (init_section_page_ext(pfn, nid))
				goto oom;
		}
	}

void __update_cache(unsigned long address, pte_t pte)
{
	struct page *page;
	unsigned long pfn, addr;
	int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;

	pfn = pte_pfn(pte);
	if (unlikely(!pfn_valid(pfn)))
		return;
	page = pfn_to_page(pfn);
	if (Page_dcache_dirty(page)) {
		if (PageHighMem(page))
			addr = (unsigned long)kmap_atomic(page);
		else
			addr = (unsigned long)page_address(page);

		if (exec || pages_do_alias(addr, address & PAGE_MASK))
			flush_data_cache_page(addr);

		if (PageHighMem(page))
			__kunmap_atomic((void *)addr);

		ClearPageDcacheDirty(page);
	}
}

void __update_cache(struct vm_area_struct *vma, unsigned long address,
	pte_t pte)
{
	struct page *page;
	unsigned long pfn, addr;
	int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;

	pfn = pte_pfn(pte);
	if (unlikely(!pfn_valid(pfn))) {
		wmb();
		return;
	}
	page = pfn_to_page(pfn);
	if (page_mapped(page) && Page_dcache_dirty(page)) {
		void *kaddr = NULL;
		if (PageHighMem(page)) {
			addr = (unsigned long)kmap_atomic(page);
			kaddr = (void *)addr;
		} else
			addr = (unsigned long) page_address(page);
		if (exec || (cpu_has_dc_aliases &&
		    pages_do_alias(addr, address & PAGE_MASK))) {
			flush_data_cache_page(addr);
			ClearPageDcacheDirty(page);
		}

		if (kaddr)
			kunmap_atomic((void *)kaddr);
	}
	wmb();  /* finish any outstanding arch cache flushes before ret to user */
}

void show_mem(void)
{
#ifndef CONFIG_NEED_MULTIPLE_NODES  /* XXX(hch): later.. */
	int pfn, total = 0, reserved = 0;
	int shared = 0, cached = 0;
	int highmem = 0;
	struct page *page;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
	pfn = max_mapnr;
	while (pfn-- > 0) {
		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		total++;
		if (PageHighMem(page))
			highmem++;
		if (PageReserved(page))
			reserved++;
		else if (PageSwapCache(page))
			cached++;
		else if (page_count(page))
			shared += page_count(page) - 1;
	}
	printk("%d pages of RAM\n", total);
	printk("%d pages of HIGHMEM\n", highmem);
	printk("%d reserved pages\n", reserved);
	printk("%d pages shared\n", shared);
	printk("%d pages swap cached\n", cached);
#endif
}

void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t pte)
{
	struct mm_struct *mm;
	struct tsb *tsb;
	unsigned long tag, flags;
	unsigned long tsb_index, tsb_hash_shift;

	if (tlb_type != hypervisor) {
		unsigned long pfn = pte_pfn(pte);
		unsigned long pg_flags;
		struct page *page;

		if (pfn_valid(pfn) &&
		    (page = pfn_to_page(pfn), page_mapping(page)) &&
		    ((pg_flags = page->flags) & (1UL << PG_dcache_dirty))) {
			int cpu = ((pg_flags >> PG_dcache_cpu_shift) &
				   PG_dcache_cpu_mask);
			int this_cpu = get_cpu();

			/* This is just to optimize away some function calls
			 * in the SMP case.
			 */
			if (cpu == this_cpu)
				flush_dcache_page_impl(page);
			else
				smp_flush_dcache_page_impl(page, cpu);

			clear_dcache_dirty_cpu(page, cpu);

			put_cpu();
		}

void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t pte)
{
	struct page *page;
	unsigned long pfn;
	unsigned long pg_flags;

	pfn = pte_pfn(pte);
	if (pfn_valid(pfn) &&
	    (page = pfn_to_page(pfn), page_mapping(page)) &&
	    ((pg_flags = page->flags) & (1UL << PG_dcache_dirty))) {
		int cpu = ((pg_flags >> 24) & (NR_CPUS - 1UL));
		int this_cpu = get_cpu();

		/* This is just to optimize away some function calls
		 * in the SMP case.
		 */
		if (cpu == this_cpu)
			flush_dcache_page_impl(page);
		else
			smp_flush_dcache_page_impl(page, cpu);

		clear_dcache_dirty_cpu(page, cpu);

		put_cpu();
	}

static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
	struct page *page;
	struct page_ext *page_ext;
	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
	unsigned long end_pfn = pfn + zone->spanned_pages;
	unsigned long count = 0;

	/* Scan block by block. First and last block may be incomplete */
	pfn = zone->zone_start_pfn;

	/*
	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
	 * a zone boundary, it will be double counted between zones. This does
	 * not matter as the mixed block count will still be correct
	 */
	for (; pfn < end_pfn; ) {
		if (!pfn_valid(pfn)) {
			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
			continue;
		}

		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		page = pfn_to_page(pfn);

		for (; pfn < block_end_pfn; pfn++) {
			if (!pfn_valid_within(pfn))
				continue;

			page = pfn_to_page(pfn);

			/*
			 * We are safe to check buddy flag and order, because
			 * this is init stage and only single thread runs.
			 */
			if (PageBuddy(page)) {
				pfn += (1UL << page_order(page)) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);

			/* Maybe overraping zone */
			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
				continue;

			/* Found early allocated page */
			set_page_owner(page, 0, 0);
			count++;
		}
	}

	pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
		pgdat->node_id, zone->name, count);
}

static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
{
	pte_t pte = READ_ONCE(*src_ptep);

	if (pte_valid(pte)) {
		/*
		 * Resume will overwrite areas that may be marked
		 * read only (code, rodata). Clear the RDONLY bit from
		 * the temporary mappings we use during restore.
		 */
		set_pte(dst_ptep, pte_mkwrite(pte));
	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
		/*
		 * debug_pagealloc will removed the PTE_VALID bit if
		 * the page isn't in use by the resume kernel. It may have
		 * been in use by the original kernel, in which case we need
		 * to put it back in our copy to do the restore.
		 *
		 * Before marking this entry valid, check the pfn should
		 * be mapped.
		 */
		BUG_ON(!pfn_valid(pte_pfn(pte)));

		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
	}
}

static void
count_pmd_pages(struct mm_struct * mm, struct vm_area_struct * vma,
                pmd_t *dir, unsigned long address, unsigned long end,
                signed char *data_buf, int node_map)
{
    pte_t * pte;
    unsigned long pmd_end;
    struct page *page;
    unsigned long pfn;
    int val, index;

    if (pmd_none(*dir))
        return;
    pmd_end = (address + PMD_SIZE) & PMD_MASK;
    if (end > pmd_end)
        end = pmd_end;
    index = 0;
    do {
        pte = pte_offset_map(dir, address);
        if (!pte_none(pte) && pte_present(*pte)) {
            pfn = pte_pfn(*pte);
            if (pfn_valid(pfn)) {
                page = pfn_to_page(pfn);
                val = node_map ? page_to_nid(page) :
                      page_count(page);
                val = (val > 99) ? 99 : val;
                data_buf[index] = val;
            }
        }
        address += PAGE_SIZE;
        pte++;
        index++;
    } while (address && (address < end));
    return;
}

static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
{
	unsigned long block_sz, start_pfn;
	int sections_per_block;
	int i, nid;

	start_pfn = base >> PAGE_SHIFT;

	lock_device_hotplug();

	if (!pfn_valid(start_pfn))
		goto out;

	block_sz = pseries_memory_block_size();
	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
	nid = memory_add_physaddr_to_nid(base);

	for (i = 0; i < sections_per_block; i++) {
		remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE);
		base += MIN_MEMORY_BLOCK_SIZE;
	}

out:
	/* Update memory regions for memory remove */
	memblock_remove(base, memblock_size);
	unlock_device_hotplug();
	return 0;
}

/*
 * map a kernel virtual address or kernel logical address to a phys address
 */
static inline u32 physical_address(u32 virt, int write)
{
    struct page *page;
       /* kernel static-mapped address */
    DPRINTK(" get physical address: virt %x , write %d\n", virt, write);
    if (virt_addr_valid(virt)) 
    {
        return __pa((u32) virt);
    }
    if (virt >= high_memory)
	    return 0;
    
    if (virt >= TASK_SIZE)
    {
        page = follow_page(find_extend_vma(&init_mm, virt), (u32) virt, write);
    }
    else
    {
        page = follow_page(find_extend_vma(current->mm, virt), (u32) virt, write);
    }
    
    if (pfn_valid(page_to_pfn(page)))
    {
        return ((page_to_pfn(page) << PAGE_SHIFT) |
                       ((u32) virt & (PAGE_SIZE - 1)));
    }
    else
    {
        return 0;
    }
}

void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
		      pte_t * pte)
{
	struct page *page;
	unsigned long flags;
	unsigned long pfn = pte_pfn(*pte);

	if (!pfn_valid(pfn))
		return;

	if (vma->vm_mm == current->active_mm) {
		local_irq_save(flags);
		__nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN);
		__nds32__tlbop_rwr(*pte);
		__nds32__isb();
		local_irq_restore(flags);
	}

	page = pfn_to_page(pfn);
	if (test_and_clear_bit(PG_dcache_dirty, &page->flags) ||
	    (vma->vm_flags & VM_EXEC)) {
		local_irq_save(flags);
		cpu_dcache_wbinval_page((unsigned long)page_address(page));
		local_irq_restore(flags);
	}
}

static int __init my_init(void)
{
	int i;
	unsigned long CountFree = 0, CountLocked = 0, CountDirty = 0, CountUp2Date = 0;
	struct page *cp;

	for (i=0; i <= get_num_physpages(); i++)
	{
		if (pfn_valid(i)) 
		{
			cp = pfn_to_page(i);
			if (!page_count(cp))
			{
				CountFree++;
			}
			else
			{
				CountLocked += PageLocked(cp);
				CountDirty  += PageDirty(cp);
				CountUp2Date+= PageUptodate(cp);
			}
		}
	}

	pr_info("\n       Pages Free = %lu", CountFree);
	pr_info("\n     Pages Locked = %lu", CountLocked);
	pr_info("\n     Pages Dirty  = %lu", CountDirty);
	pr_info("\n Pages Up to date = %lu \n", CountUp2Date);
					
	return 0;
}

static ssize_t kpageflags_read(struct file *file, char __user *buf,
			     size_t count, loff_t *ppos)
{
	u64 __user *out = (u64 __user *)buf;
	struct page *ppage;
	unsigned long src = *ppos;
	unsigned long pfn;
	ssize_t ret = 0;

	pfn = src / KPMSIZE;
	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;

	while (count > 0) {
		if (pfn_valid(pfn))
			ppage = pfn_to_page(pfn);
		else
			ppage = NULL;

		if (put_user(stable_page_flags(ppage), out)) {
			ret = -EFAULT;
			break;
		}

		pfn++;
		out++;
		count -= KPMSIZE;
	}

	*ppos += (char __user *)out - buf;
	if (!ret)
		ret = (char __user *)out - buf;
	return ret;
}

/*
 * Handle i/d cache flushing, called from set_pte_at() or ptep_set_access_flags()
 */
static pte_t do_dcache_icache_coherency(pte_t pte, unsigned long addr)
{
	unsigned long pfn = pte_pfn(pte);
	struct page *page;

	if (unlikely(!pfn_valid(pfn)))
		return pte;
	page = pfn_to_page(pfn);

#ifdef CONFIG_8xx
       /* On 8xx, cache control instructions (particularly
        * "dcbst" from flush_dcache_icache) fault as write
        * operation if there is an unpopulated TLB entry
        * for the address in question. To workaround that,
        * we invalidate the TLB here, thus avoiding dcbst
        * misbehaviour.
        */
       _tlbil_va(addr, 0 /* 8xx doesn't care about PID */);
#endif

	if (!PageReserved(page) && !test_bit(PG_arch_1, &page->flags)) {
		pr_devel("do_dcache_icache_coherency... flushing\n");
		flush_dcache_icache_page(page);
		set_bit(PG_arch_1, &page->flags);
	}
	else
		pr_devel("do_dcache_icache_coherency... already clean\n");
	return __pte(pte_val(pte) | _PAGE_HWEXEC);
}

void __init page_cgroup_init(void)
{
	unsigned long pfn;
	int nid;

	if (mem_cgroup_disabled())
		return;

	for_each_node_state(nid, N_HIGH_MEMORY) {
		unsigned long start_pfn, end_pfn;

		start_pfn = node_start_pfn(nid);
		end_pfn = node_end_pfn(nid);
		for (pfn = start_pfn;
		     pfn < end_pfn;
                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {

			if (!pfn_valid(pfn))
				continue;
			if (pfn_to_nid(pfn) != nid)
				continue;
			if (init_section_page_cgroup(pfn, nid))
				goto oom;
		}
	}

/*
 * The probe routines leave the pages reserved, just as the bootmem code does.
 * Make sure they're still that way.
 */
static bool pages_correctly_reserved(unsigned long start_pfn)
{
	int i, j;
	struct page *page;
	unsigned long pfn = start_pfn;

	/*
	 * memmap between sections is not contiguous except with
	 * SPARSEMEM_VMEMMAP. We lookup the page once per section
	 * and assume memmap is contiguous within each section
	 */
	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
		if (WARN_ON_ONCE(!pfn_valid(pfn)))
			return false;
		page = pfn_to_page(pfn);

		for (j = 0; j < PAGES_PER_SECTION; j++) {
			if (PageReserved(page + j))
				continue;

			printk(KERN_WARNING "section number %ld page number %d "
				"not reserved, was it already online?\n",
				pfn_to_section_nr(pfn), j);

			return false;
		}
	}

	return true;
}