memory.c

	do {
		next = pgd_addr_end(addr, end);
		err = zeromap_pud_range(mm, pgd, addr, next, prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	spin_unlock(&mm->page_table_lock);
	return err;
}

/*
 * maps a range of physical memory into the requested pages. the old
 * mappings are removed. any references to nonexistent pages results
 * in null mappings (currently treated as "copy-on-access")
 */
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pte_t *pte;

	pte = pte_alloc_map(mm, pmd, addr);
	if (!pte)
		return -ENOMEM;
	do {
		BUG_ON(!pte_none(*pte));
		if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
			set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
	return 0;
}

static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (remap_pte_range(mm, pmd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (remap_pmd_range(mm, pud, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

/*  Note: this is only safe if the mm semaphore is held when called. */
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
		    unsigned long pfn, unsigned long size, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + size;
	struct mm_struct *mm = vma->vm_mm;
	int err;

	/*
	 * Physically remapped pages are special. Tell the
	 * rest of the world about it:
	 *   VM_IO tells people not to look at these pages
	 *	(accesses can have side effects).
	 *   VM_RESERVED tells swapout not to try to touch
	 *	this region.
	 */
	vma->vm_flags |= VM_IO | VM_RESERVED;

	BUG_ON(addr >= end);
	pfn -= addr >> PAGE_SHIFT;
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	spin_lock(&mm->page_table_lock);
	do {
		next = pgd_addr_end(addr, end);
		err = remap_pud_range(mm, pgd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	spin_unlock(&mm->page_table_lock);
	return err;
}
EXPORT_SYMBOL(remap_pfn_range);

/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pte = pte_mkwrite(pte);
	return pte;
}

/*
 * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
 */
static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address, 
		pte_t *page_table)
{
	pte_t entry;

	entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
			      vma);
	ptep_establish(vma, address, page_table, entry);
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
}

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * Goto-purists beware: the only reason for goto's here is that it results
 * in better assembly code.. The "default" path will see no jumps at all.
 *
 * Note that this routine assumes that the protection checks have been
 * done by the caller (the low-level page fault routine in most cases).
 * Thus we can safely just mark it writable once we've done any necessary
 * COW.
 *
 * We also mark the page dirty at this point even though the page will
 * change only once the write actually happens. This avoids a few races,
 * and potentially makes it more efficient.
 *
 * We hold the mm semaphore and the page_table_lock on entry and exit
 * with the page_table_lock released.
 */
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
	unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
{
	struct page *old_page, *new_page;
	unsigned long pfn = pte_pfn(pte);
	pte_t entry;

	if (unlikely(!pfn_valid(pfn))) {
		/*
		 * This should really halt the system so it can be debugged or
		 * at least the kernel stops what it's doing before it corrupts
		 * data, but for the moment just pretend this is OOM.
		 */
		pte_unmap(page_table);
		printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
				address);
		spin_unlock(&mm->page_table_lock);
		return VM_FAULT_OOM;
	}
	old_page = pfn_to_page(pfn);

	if (!TestSetPageLocked(old_page)) {
		int reuse = can_share_swap_page(old_page);
		unlock_page(old_page);
		if (reuse) {
			flush_cache_page(vma, address, pfn);
			entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
					      vma);
			ptep_set_access_flags(vma, address, page_table, entry, 1);
			update_mmu_cache(vma, address, entry);
			lazy_mmu_prot_update(entry);
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			return VM_FAULT_MINOR;
		}
	}
	pte_unmap(page_table);

	/*
	 * Ok, we need to copy. Oh, well..
	 */
	if (!PageReserved(old_page))
		page_cache_get(old_page);
	spin_unlock(&mm->page_table_lock);

	if (unlikely(anon_vma_prepare(vma)))
		goto no_new_page;
	if (old_page == ZERO_PAGE(address)) {
		new_page = alloc_zeroed_user_highpage(vma, address);
		if (!new_page)
			goto no_new_page;
	} else {
		new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
		if (!new_page)
			goto no_new_page;
		copy_user_highpage(new_page, old_page, address);
	}
	/*
	 * Re-check the pte - we dropped the lock
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (likely(pte_same(*page_table, pte))) {
		if (PageAnon(old_page))
			dec_mm_counter(mm, anon_rss);
		if (PageReserved(old_page))
			inc_mm_counter(mm, rss);
		else
			page_remove_rmap(old_page);
		flush_cache_page(vma, address, pfn);
		break_cow(vma, new_page, address, page_table);
		lru_cache_add_active(new_page);
		page_add_anon_rmap(new_page, vma, address);

		/* Free the old page.. */
		new_page = old_page;
	}
	pte_unmap(page_table);
	page_cache_release(new_page);
	page_cache_release(old_page);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;

no_new_page:
	page_cache_release(old_page);
	return VM_FAULT_OOM;
}

/*
 * Helper functions for unmap_mapping_range().
 *
 * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
 *
 * We have to restart searching the prio_tree whenever we drop the lock,
 * since the iterator is only valid while the lock is held, and anyway
 * a later vma might be split and reinserted earlier while lock dropped.
 *
 * The list of nonlinear vmas could be handled more efficiently, using
 * a placeholder, but handle it in the same way until a need is shown.
 * It is important to search the prio_tree before nonlinear list: a vma
 * may become nonlinear and be shifted from prio_tree to nonlinear list
 * while the lock is dropped; but never shifted from list to prio_tree.
 *
 * In order to make forward progress despite restarting the search,
 * vm_truncate_count is used to mark a vma as now dealt with, so we can
 * quickly skip it next time around.  Since the prio_tree search only
 * shows us those vmas affected by unmapping the range in question, we
 * can't efficiently keep all vmas in step with mapping->truncate_count:
 * so instead reset them all whenever it wraps back to 0 (then go to 1).
 * mapping->truncate_count and vma->vm_truncate_count are protected by
 * i_mmap_lock.
 *
 * In order to make forward progress despite repeatedly restarting some
 * large vma, note the break_addr set by unmap_vmas when it breaks out:
 * and restart from that address when we reach that vma again.  It might
 * have been split or merged, shrunk or extended, but never shifted: so
 * restart_addr remains valid so long as it remains in the vma's range.
 * unmap_mapping_range forces truncate_count to leap over page-aligned
 * values so we can save vma's restart_addr in its truncate_count field.
 */
#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))

static void reset_vma_truncate_counts(struct address_space *mapping)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
		vma->vm_truncate_count = 0;
	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
		vma->vm_truncate_count = 0;
}

static int unmap_mapping_range_vma(struct vm_area_struct *vma,
		unsigned long start_addr, unsigned long end_addr,
		struct zap_details *details)
{
	unsigned long restart_addr;
	int need_break;

again:
	restart_addr = vma->vm_truncate_count;
	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
		start_addr = restart_addr;
		if (start_addr >= end_addr) {
			/* Top of vma has been split off since last time */
			vma->vm_truncate_count = details->truncate_count;
			return 0;
		}
	}

	details->break_addr = end_addr;
	zap_page_range(vma, start_addr, end_addr - start_addr, details);

	/*
	 * We cannot rely on the break test in unmap_vmas:
	 * on the one hand, we don't want to restart our loop
	 * just because that broke out for the page_table_lock;
	 * on the other hand, it does no test when vma is small.
	 */
	need_break = need_resched() ||
			need_lockbreak(details->i_mmap_lock);

	if (details->break_addr >= end_addr) {
		/* We have now completed this vma: mark it so */
		vma->vm_truncate_count = details->truncate_count;
		if (!need_break)
			return 0;
	} else {
		/* Note restart_addr in vma's truncate_count field */
		vma->vm_truncate_count = details->break_addr;
		if (!need_break)
			goto again;
	}

	spin_unlock(details->i_mmap_lock);
	cond_resched();
	spin_lock(details->i_mmap_lock);
	return -EINTR;
}

static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	pgoff_t vba, vea, zba, zea;

restart:
	vma_prio_tree_foreach(vma, &iter, root,
			details->first_index, details->last_index) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;

		vba = vma->vm_pgoff;
		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
		zba = details->first_index;
		if (zba < vba)
			zba = vba;
		zea = details->last_index;
		if (zea > vea)
			zea = vea;

		if (unmap_mapping_range_vma(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
				details) < 0)
			goto restart;
	}
}

static inline void unmap_mapping_range_list(struct list_head *head,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;

	/*
	 * In nonlinear VMAs there is no correspondence between virtual address
	 * offset and file offset.  So we must perform an exhaustive search
	 * across *all* the pages in each nonlinear VMA, not just the pages
	 * whose virtual address lies outside the file truncation point.
	 */
restart:
	list_for_each_entry(vma, head, shared.vm_set.list) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;
		details->nonlinear_vma = vma;
		if (unmap_mapping_range_vma(vma, vma->vm_start,
					vma->vm_end, details) < 0)
			goto restart;
	}
}

/**
 * unmap_mapping_range - unmap the portion of all mmaps
 * in the specified address_space corresponding to the specified
 * page range in the underlying file.
 * @address_space: the address space containing mmaps to be unmapped.
 * @holebegin: byte in first page to unmap, relative to the start of
 * the underlying file.  This will be rounded down to a PAGE_SIZE
 * boundary.  Note that this is different from vmtruncate(), which
 * must keep the partial page.  In contrast, we must get rid of
 * partial pages.
 * @holelen: size of prospective hole in bytes.  This will be rounded
 * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
 * end of the file.
 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
 * but 0 when invalidating pagecache, don't throw away private data.
 */
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows)
{
	struct zap_details details;
	pgoff_t hba = holebegin >> PAGE_SHIFT;
	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Check for overflow. */
	if (sizeof(holelen) > sizeof(hlen)) {
		long long holeend =
			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (holeend & ~(long long)ULONG_MAX)
			hlen = ULONG_MAX - hba + 1;
	}

	details.check_mapping = even_cows? NULL: mapping;
	details.nonlinear_vma = NULL;
	details.first_index = hba;
	details.last_index = hba + hlen - 1;
	if (details.last_index < details.first_index)
		details.last_index = ULONG_MAX;
	details.i_mmap_lock = &mapping->i_mmap_lock;

	spin_lock(&mapping->i_mmap_lock);

	/* serialize i_size write against truncate_count write */
	smp_wmb();
	/* Protect against page faults, and endless unmapping loops */
	mapping->truncate_count++;
	/*
	 * For archs where spin_lock has inclusive semantics like ia64
	 * this smp_mb() will prevent to read pagetable contents
	 * before the truncate_count increment is visible to
	 * other cpus.
	 */
	smp_mb();
	if (unlikely(is_restart_addr(mapping->truncate_count))) {
		if (mapping->truncate_count == 0)
			reset_vma_truncate_counts(mapping);
		mapping->truncate_count++;
	}
	details.truncate_count = mapping->truncate_count;

	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
		unmap_mapping_range_tree(&mapping->i_mmap, &details);
	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
	spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * Handle all mappings that got truncated by a "truncate()"
 * system call.
 *
 * NOTE! We have to be ready to update the memory sharing
 * between the file and the memory map for a potential last
 * incomplete page.  Ugly, but necessary.
 */
int vmtruncate(struct inode * inode, loff_t offset)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned long limit;

	if (inode->i_size < offset)
		goto do_expand;
	/*
	 * truncation of in-use swapfiles is disallowed - it would cause
	 * subsequent swapout to scribble on the now-freed blocks.
	 */
	if (IS_SWAPFILE(inode))
		goto out_busy;
	i_size_write(inode, offset);
	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
	truncate_inode_pages(mapping, offset);
	goto out_truncate;

do_expand:
	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && offset > limit)
		goto out_sig;
	if (offset > inode->i_sb->s_maxbytes)
		goto out_big;
	i_size_write(inode, offset);

out_truncate:
	if (inode->i_op && inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out_big:
	return -EFBIG;
out_busy:
	return -ETXTBSY;
}

EXPORT_SYMBOL(vmtruncate);

/* 
 * Primitive swap readahead code. We simply read an aligned block of
 * (1 << page_cluster) entries in the swap area. This method is chosen
 * because it doesn't cost us any seek time.  We also make sure to queue
 * the 'original' request together with the readahead ones...  
 *
 * This has been extended to use the NUMA policies from the mm triggering
 * the readahead.
 *
 * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
 */
void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
{
#ifdef CONFIG_NUMA
	struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
#endif
	int i, num;
	struct page *new_page;
	unsigned long offset;

	/*
	 * Get the number of handles we should do readahead io to.
	 */
	num = valid_swaphandles(entry, &offset);
	for (i = 0; i < num; offset++, i++) {
		/* Ok, do the async read-ahead now */
		new_page = read_swap_cache_async(swp_entry(swp_type(entry),
							   offset), vma, addr);
		if (!new_page)
			break;
		page_cache_release(new_page);
#ifdef CONFIG_NUMA
		/*
		 * Find the next applicable VMA for the NUMA policy.
		 */
		addr += PAGE_SIZE;
		if (addr == 0)
			vma = NULL;
		if (vma) {
			if (addr >= vma->vm_end) {
				vma = next_vma;
				next_vma = vma ? vma->vm_next : NULL;
			}
			if (vma && addr < vma->vm_start)
				vma = NULL;
		} else {
			if (next_vma && addr >= next_vma->vm_start) {
				vma = next_vma;
				next_vma = vma->vm_next;
			}
		}
#endif
	}
	lru_add_drain();	/* Push any new pages onto the LRU now */
}

/*
 * We hold the mm semaphore and the page_table_lock on entry and
 * should release the pagetable lock on exit..
 */
static int do_swap_page(struct mm_struct * mm,
	struct vm_area_struct * vma, unsigned long address,
	pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
{
	struct page *page;
	swp_entry_t entry = pte_to_swp_entry(orig_pte);
	pte_t pte;
	int ret = VM_FAULT_MINOR;

	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
	page = lookup_swap_cache(entry);
	if (!page) {
 		swapin_readahead(entry, address, vma);
 		page = read_swap_cache_async(entry, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte while
			 * we released the page table lock.
			 */
			spin_lock(&mm->page_table_lock);
			page_table = pte_offset_map(pmd, address);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			else
				ret = VM_FAULT_MINOR;
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}

		/* Had to read the page from swap area: Major fault */
		ret = VM_FAULT_MAJOR;
		inc_page_state(pgmajfault);
		grab_swap_token();
	}

	mark_page_accessed(page);
	lock_page(page);

	/*
	 * Back out if somebody else faulted in this pte while we
	 * released the page table lock.
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (unlikely(!pte_same(*page_table, orig_pte))) {
		pte_unmap(page_table);
		spin_unlock(&mm->page_table_lock);
		unlock_page(page);
		page_cache_release(page);
		ret = VM_FAULT_MINOR;
		goto out;
	}

	/* The page isn't present yet, go ahead with the fault. */
		
	swap_free(entry);
	if (vm_swap_full())
		remove_exclusive_swap_page(page);

	inc_mm_counter(mm, rss);
	pte = mk_pte(page, vma->vm_page_prot);
	if (write_access && can_share_swap_page(page)) {
		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
		write_access = 0;
	}
	unlock_page(page);

	flush_icache_page(vma, page);
	set_pte_at(mm, address, page_table, pte);
	page_add_anon_rmap(page, vma, address);

	if (write_access) {
		if (do_wp_page(mm, vma, address,
				page_table, pmd, pte) == VM_FAULT_OOM)
			ret = VM_FAULT_OOM;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, pte);
	lazy_mmu_prot_update(pte);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
}

/*
 * We are called with the MM semaphore and page_table_lock
 * spinlock held to protect against concurrent faults in
 * multithreaded programs. 
 */
static int
do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		pte_t *page_table, pmd_t *pmd, int write_access,
		unsigned long addr)
{
	pte_t entry;
	struct page * page = ZERO_PAGE(addr);

	/* Read-only mapping of ZERO_PAGE. */
	entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));

	/* ..except if it's a write access */
	if (write_access) {
		/* Allocate our own private page. */
		pte_unmap(page_table);
		spin_unlock(&mm->page_table_lock);

		if (unlikely(anon_vma_prepare(vma)))
			goto no_mem;
		page = alloc_zeroed_user_highpage(vma, addr);
		if (!page)
			goto no_mem;

		spin_lock(&mm->page_table_lock);
		page_table = pte_offset_map(pmd, addr);

		if (!pte_none(*page_table)) {
			pte_unmap(page_table);
			page_cache_release(page);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}
		inc_mm_counter(mm, rss);
		entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
							 vma->vm_page_prot)),
				      vma);
		lru_cache_add_active(page);
		SetPageReferenced(page);
		page_add_anon_rmap(page, vma, addr);
	}

	set_pte_at(mm, addr, page_table, entry);
	pte_unmap(page_table);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, entry);
	lazy_mmu_prot_update(entry);
	spin_unlock(&mm->page_table_lock);
out:
	return VM_FAULT_MINOR;
no_mem:
	return VM_FAULT_OOM;
}

/*
 * do_no_page() tries to create a new page mapping. It aggressively
 * tries to share with existing pages, but makes a separate copy if
 * the "write_access" parameter is true in order to avoid the next
 * page fault.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 *
 * This is called with the MM semaphore held and the page table
 * spinlock held. Exit with the spinlock released.
 */
static int
do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
	unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
{
	struct page * new_page;
	struct address_space *mapping = NULL;
	pte_t entry;
	unsigned int sequence = 0;
	int ret = VM_FAULT_MINOR;
	int anon = 0;

	if (!vma->vm_ops || !vma->vm_ops->nopage)
		return do_anonymous_page(mm, vma, page_table,
					pmd, write_access, address);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);

	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;
		sequence = mapping->truncate_count;
		smp_rmb(); /* serializes i_size against truncate_count */
	}
retry:
	cond_resched();
	new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
	/*
	 * No smp_rmb is needed here as long as there's a full
	 * spin_lock/unlock sequence inside the ->nopage callback
	 * (for the pagecache lookup) that acts as an implicit
	 * smp_mb() and prevents the i_size read to happen
	 * after the next truncate_count read.
	 */

	/* no page was available -- either SIGBUS or OOM */
	if (new_page == NOPAGE_SIGBUS)
		return VM_FAULT_SIGBUS;
	if (new_page == NOPAGE_OOM)
		return VM_FAULT_OOM;

	/*
	 * Should we do an early C-O-W break?
	 */
	if (write_access && !(vma->vm_flags & VM_SHARED)) {
		struct page *page;

		if (unlikely(anon_vma_prepare(vma)))
			goto oom;
		page = alloc_page_vma(GFP_HIGHUSER, vma, address);
		if (!page)
			goto oom;
		copy_user_highpage(page, new_page, address);
		page_cache_release(new_page);
		new_page = page;
		anon = 1;
	}

	spin_lock(&mm->page_table_lock);
	/*
	 * For a file-backed vma, someone could have truncated or otherwise
	 * invalidated this page.  If unmap_mapping_range got called,
	 * retry getting the page.
	 */
	if (mapping && unlikely(sequence != mapping->truncate_count)) {
		sequence = mapping->truncate_count;
		spin_unlock(&mm->page_table_lock);
		page_cache_release(new_page);
		goto retry;
	}
	page_table = pte_offset_map(pmd, address);

	/*
	 * This silly early PAGE_DIRTY setting removes a race
	 * due to the bad i386 page protection. But it's valid
	 * for other architectures too.
	 *
	 * Note that if write_access is true, we either now have
	 * an exclusive copy of the page, or this is a shared mapping,
	 * so we can make it writable and dirty to avoid having to
	 * handle that later.
	 */
	/* Only go through if we didn't race with anybody else... */
	if (pte_none(*page_table)) {
		if (!PageReserved(new_page))
			inc_mm_counter(mm, rss);

		flush_icache_page(vma, new_page);
		entry = mk_pte(new_page, vma->vm_page_prot);
		if (write_access)
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		set_pte_at(mm, address, page_table, entry);
		if (anon) {
			lru_cache_add_active(new_page);
			page_add_anon_rmap(new_page, vma, address);
		} else
			page_add_file_rmap(new_page);
		pte_unmap(page_table);
	} else {
		/* One of our sibling threads was faster, back out. */
		pte_unmap(page_table);
		page_cache_release(new_page);
		spin_unlock(&mm->page_table_lock);
		goto out;
	}

	/* no need to invalidate: a not-present page shouldn't be cached */
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
oom:
	page_cache_release(new_page);
	ret = VM_FAULT_OOM;
	goto out;
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 */
static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
	unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
{
	unsigned long pgoff;
	int err;

	BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
	/*
	 * Fall back to the linear mapping if the fs does not support
	 * ->populate:
	 */
	if (!vma->vm_ops || !vma->vm_ops->populate || 
			(write_access && !(vma->vm_flags & VM_SHARED))) {
		pte_clear(mm, address, pte);
		return do_no_page(mm, vma, address, write_access, pte, pmd);
	}

	pgoff = pte_to_pgoff(*pte);

	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);

	err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0);
	if (err == -ENOMEM)
		return VM_FAULT_OOM;
	if (err)
		return VM_FAULT_SIGBUS;
	return VM_FAULT_MAJOR;
}

/*
 * These routines also need to handle stuff like marking pages dirty
 * and/or accessed for architectures that don't do it in hardware (most
 * RISC architectures).  The early dirtying is also good on the i386.
 *
 * There is also a hook called "update_mmu_cache()" that architectures
 * with external mmu caches can use to update those (ie the Sparc or
 * PowerPC hashed page tables that act as extended TLBs).
 *
 * Note the "page_table_lock". It is to protect against kswapd removing
 * pages from under us. Note that kswapd only ever _removes_ pages, never
 * adds them. As such, once we have noticed that the page is not present,
 * we can drop the lock early.
 *
 * The adding of pages is protected by the MM semaphore (which we hold),
 * so we don't need to worry about a page being suddenly been added into
 * our VM.
 *
 * We enter with the pagetable spinlock held, we are supposed to
 * release it when done.
 */
static inline int handle_pte_fault(struct mm_struct *mm,
	struct vm_area_struct * vma, unsigned long address,
	int write_access, pte_t *pte, pmd_t *pmd)
{
	pte_t entry;

	entry = *pte;
	if (!pte_present(entry)) {
		/*
		 * If it truly wasn't present, we know that kswapd
		 * and the PTE updates will not touch it later. So
		 * drop the lock.
		 */
		if (pte_none(entry))
			return do_no_page(mm, vma, address, write_access, pte, pmd);
		if (pte_file(entry))
			return do_file_page(mm, vma, address, write_access, pte, pmd);
		return do_swap_page(mm, vma, address, pte, pmd, entry, write_access);
	}

	if (write_access) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address, pte, pmd, entry);

		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	ptep_set_access_flags(vma, address, pte, entry, write_access);
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;
}

/*
 * By the time we get here, we already hold the mm semaphore
 */
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
		unsigned long address, int write_access)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	__set_current_state(TASK_RUNNING);

	inc_page_state(pgfault);

	if (is_vm_hugetlb_page(vma))
		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */

	/*
	 * We need the page table lock to synchronize with kswapd
	 * and the SMP-safe atomic PTE updates.
	 */
	pgd = pgd_offset(mm, address);
	spin_lock(&mm->page_table_lock);

	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		goto oom;

	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		goto oom;

	pte = pte_alloc_map(mm, pmd, address);
	if (!pte)
		goto oom;
	
	return handle_pte_fault(mm, vma, address, write_access, pte, pmd);

 oom:
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_OOM;
}

#ifndef __PAGETABLE_PUD_FOLDED
/*
 * Allocate page upper directory.
 *
 * We've already handled the fast-path in-line, and we own the
 * page table lock.
 */
pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pud_t *new;

	spin_unlock(&mm->page_table_lock);
	new = pud_alloc_one(mm, address);
	spin_lock(&mm->page_table_lock);
	if (!new)
		return NULL;

	/*
	 * Because we dropped the lock, we should re-check the