memory.c

 *
 * __ 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 restart_addr from 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;

	/*
	 * files that support invalidating or truncating portions of the
	 * file from under mmaped areas must have their ->fault function
	 * return a locked page (and set VM_FAULT_LOCKED in the return).
	 * This provides synchronisation against concurrent unmapping here.
	 */

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;
		}
	}

	restart_addr = zap_page_range(vma, start_addr,
					end_addr - start_addr, details);
	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);

	if (restart_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 = restart_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.
 * @mapping: 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);

	/* Protect against endless unmapping loops */
	mapping->truncate_count++;
	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);

/**
 * vmtruncate - unmap mappings "freed" by truncate() syscall
 * @inode: inode of the file used
 * @offset: file offset to start truncating
 *
 * 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)
{
	if (inode->i_size < offset) {
		unsigned long limit;

		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);
	} else {
		struct address_space *mapping = inode->i_mapping;

		/*
		 * truncation of in-use swapfiles is disallowed - it would
		 * cause subsequent swapout to scribble on the now-freed
		 * blocks.
		 */
		if (IS_SWAPFILE(inode))
			return -ETXTBSY;
		i_size_write(inode, offset);

		/*
		 * unmap_mapping_range is called twice, first simply for
		 * efficiency so that truncate_inode_pages does fewer
		 * single-page unmaps.  However after this first call, and
		 * before truncate_inode_pages finishes, it is possible for
		 * private pages to be COWed, which remain after
		 * truncate_inode_pages finishes, hence the second
		 * unmap_mapping_range call must be made for correctness.
		 */
		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
		truncate_inode_pages(mapping, offset);
		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
	}

	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;
}
EXPORT_SYMBOL(vmtruncate);

int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
{
	struct address_space *mapping = inode->i_mapping;

	/*
	 * If the underlying filesystem is not going to provide
	 * a way to truncate a range of blocks (punch a hole) -
	 * we should return failure right now.
	 */
	if (!inode->i_op || !inode->i_op->truncate_range)
		return -ENOSYS;

	mutex_lock(&inode->i_mutex);
	down_write(&inode->i_alloc_sem);
	unmap_mapping_range(mapping, offset, (end - offset), 1);
	truncate_inode_pages_range(mapping, offset, end);
	unmap_mapping_range(mapping, offset, (end - offset), 1);
	inode->i_op->truncate_range(inode, offset, end);
	up_write(&inode->i_alloc_sem);
	mutex_unlock(&inode->i_mutex);

	return 0;
}

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		int write_access, pte_t orig_pte)
{
	spinlock_t *ptl;
	struct page *page;
	swp_entry_t entry;
	pte_t pte;
	int ret = 0;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		goto out;

	entry = pte_to_swp_entry(orig_pte);
	if (is_migration_entry(entry)) {
		migration_entry_wait(mm, pmd, address);
		goto out;
	}
	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
	page = lookup_swap_cache(entry);
	if (!page) {
		grab_swap_token(); /* Contend for token _before_ read-in */
		page = swapin_readahead(entry,
					GFP_HIGHUSER_MOVABLE, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte
			 * while we released the pte lock.
			 */
			page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
			goto unlock;
		}

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

	mark_page_accessed(page);

	lock_page(page);
	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);

	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
		ret = VM_FAULT_OOM;
		unlock_page(page);
		goto out;
	}

	/*
	 * Back out if somebody else already faulted in this pte.
	 */
	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (unlikely(!pte_same(*page_table, orig_pte)))
		goto out_nomap;

	if (unlikely(!PageUptodate(page))) {
		ret = VM_FAULT_SIGBUS;
		goto out_nomap;
	}

	/* The page isn't present yet, go ahead with the fault. */

	inc_mm_counter(mm, anon_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;
	}

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

	swap_free(entry);
	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
		remove_exclusive_swap_page(page);
	unlock_page(page);

	if (write_access) {
		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
		if (ret & VM_FAULT_ERROR)
			ret &= VM_FAULT_ERROR;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, pte);
unlock:
	pte_unmap_unlock(page_table, ptl);
out:
	return ret;
out_nomap:
	mem_cgroup_uncharge_page(page);
	pte_unmap_unlock(page_table, ptl);
	unlock_page(page);
	page_cache_release(page);
	return ret;
}

/*
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		int write_access)
{
	struct page *page;
	spinlock_t *ptl;
	pte_t entry;

	/* Allocate our own private page. */
	pte_unmap(page_table);

	if (unlikely(anon_vma_prepare(vma)))
		goto oom;
	page = alloc_zeroed_user_highpage_movable(vma, address);
	if (!page)
		goto oom;
	__SetPageUptodate(page);

	if (mem_cgroup_charge(page, mm, GFP_KERNEL))
		goto oom_free_page;

	entry = mk_pte(page, vma->vm_page_prot);
	entry = maybe_mkwrite(pte_mkdirty(entry), vma);

	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (!pte_none(*page_table))
		goto release;
	inc_mm_counter(mm, anon_rss);
	SetPageSwapBacked(page);
	lru_cache_add_active_or_unevictable(page, vma);
	page_add_new_anon_rmap(page, vma, address);
	set_pte_at(mm, address, page_table, entry);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, entry);
unlock:
	pte_unmap_unlock(page_table, ptl);
	return 0;
release:
	mem_cgroup_uncharge_page(page);
	page_cache_release(page);
	goto unlock;
oom_free_page:
	page_cache_release(page);
oom:
	return VM_FAULT_OOM;
}

/*
 * __do_fault() tries to create a new page mapping. It aggressively
 * tries to share with existing pages, but makes a separate copy if
 * the FAULT_FLAG_WRITE is set in the flags parameter 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.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte neither mapped nor locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd,
		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
{
	pte_t *page_table;
	spinlock_t *ptl;
	struct page *page;
	pte_t entry;
	int anon = 0;
	struct page *dirty_page = NULL;
	struct vm_fault vmf;
	int ret;
	int page_mkwrite = 0;

	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
	vmf.pgoff = pgoff;
	vmf.flags = flags;
	vmf.page = NULL;

	ret = vma->vm_ops->fault(vma, &vmf);
	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
		return ret;

	/*
	 * For consistency in subsequent calls, make the faulted page always
	 * locked.
	 */
	if (unlikely(!(ret & VM_FAULT_LOCKED)))
		lock_page(vmf.page);
	else
		VM_BUG_ON(!PageLocked(vmf.page));

	/*
	 * Should we do an early C-O-W break?
	 */
	page = vmf.page;
	if (flags & FAULT_FLAG_WRITE) {
		if (!(vma->vm_flags & VM_SHARED)) {
			anon = 1;
			if (unlikely(anon_vma_prepare(vma))) {
				ret = VM_FAULT_OOM;
				goto out;
			}
			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
						vma, address);
			if (!page) {
				ret = VM_FAULT_OOM;
				goto out;
			}
			/*
			 * Don't let another task, with possibly unlocked vma,
			 * keep the mlocked page.
			 */
			if (vma->vm_flags & VM_LOCKED)
				clear_page_mlock(vmf.page);
			copy_user_highpage(page, vmf.page, address, vma);
			__SetPageUptodate(page);
		} else {
			/*
			 * If the page will be shareable, see if the backing
			 * address space wants to know that the page is about
			 * to become writable
			 */
			if (vma->vm_ops->page_mkwrite) {
				unlock_page(page);
				if (vma->vm_ops->page_mkwrite(vma, page) < 0) {
					ret = VM_FAULT_SIGBUS;
					anon = 1; /* no anon but release vmf.page */
					goto out_unlocked;
				}
				lock_page(page);
				/*
				 * XXX: this is not quite right (racy vs
				 * invalidate) to unlock and relock the page
				 * like this, however a better fix requires
				 * reworking page_mkwrite locking API, which
				 * is better done later.
				 */
				if (!page->mapping) {
					ret = 0;
					anon = 1; /* no anon but release vmf.page */
					goto out;
				}
				page_mkwrite = 1;
			}
		}

	}

	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
		ret = VM_FAULT_OOM;
		goto out;
	}

	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);

	/*
	 * 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 (likely(pte_same(*page_table, orig_pte))) {
		flush_icache_page(vma, page);
		entry = mk_pte(page, vma->vm_page_prot);
		if (flags & FAULT_FLAG_WRITE)
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		if (anon) {
			inc_mm_counter(mm, anon_rss);
			SetPageSwapBacked(page);
			lru_cache_add_active_or_unevictable(page, vma);
			page_add_new_anon_rmap(page, vma, address);
		} else {
			inc_mm_counter(mm, file_rss);
			page_add_file_rmap(page);
			if (flags & FAULT_FLAG_WRITE) {
				dirty_page = page;
				get_page(dirty_page);
			}
		}
//TODO:  is this safe?  do_anonymous_page() does it this way.
		set_pte_at(mm, address, page_table, entry);

		/* no need to invalidate: a not-present page won't be cached */
		update_mmu_cache(vma, address, entry);
	} else {
		mem_cgroup_uncharge_page(page);
		if (anon)
			page_cache_release(page);
		else
			anon = 1; /* no anon but release faulted_page */
	}

	pte_unmap_unlock(page_table, ptl);

out:
	unlock_page(vmf.page);
out_unlocked:
	if (anon)
		page_cache_release(vmf.page);
	else if (dirty_page) {
		if (vma->vm_file)
			file_update_time(vma->vm_file);

		set_page_dirty_balance(dirty_page, page_mkwrite);
		put_page(dirty_page);
	}

	return ret;
}

static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		int write_access, pte_t orig_pte)
{
	pgoff_t pgoff = (((address & PAGE_MASK)
			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);

	pte_unmap(page_table);
	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long address, pte_t *page_table, pmd_t *pmd,
		int write_access, pte_t orig_pte)
{
	unsigned int flags = FAULT_FLAG_NONLINEAR |
				(write_access ? FAULT_FLAG_WRITE : 0);
	pgoff_t pgoff;

	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
		return 0;

	if (unlikely(!(vma->vm_flags & VM_NONLINEAR) ||
			!(vma->vm_flags & VM_CAN_NONLINEAR))) {
		/*
		 * Page table corrupted: show pte and kill process.
		 */
		print_bad_pte(vma, orig_pte, address);
		return VM_FAULT_OOM;
	}

	pgoff = pte_to_pgoff(orig_pte);
	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}

/*
 * 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).
 *
 * We enter with non-exclusive mmap_sem (to exclude vma changes,
 * but allow concurrent faults), and pte mapped but not yet locked.
 * We return with mmap_sem still held, but pte unmapped and unlocked.
 */
static inline int handle_pte_fault(struct mm_struct *mm,
		struct vm_area_struct *vma, unsigned long address,
		pte_t *pte, pmd_t *pmd, int write_access)
{
	pte_t entry;
	spinlock_t *ptl;

	entry = *pte;
	if (!pte_present(entry)) {
		if (pte_none(entry)) {
			if (vma->vm_ops) {
				if (likely(vma->vm_ops->fault))
					return do_linear_fault(mm, vma, address,
						pte, pmd, write_access, entry);
			}
			return do_anonymous_page(mm, vma, address,
						 pte, pmd, write_access);
		}
		if (pte_file(entry))
			return do_nonlinear_fault(mm, vma, address,
					pte, pmd, write_access, entry);
		return do_swap_page(mm, vma, address,
					pte, pmd, write_access, entry);
	}

	ptl = pte_lockptr(mm, pmd);
	spin_lock(ptl);
	if (unlikely(!pte_same(*pte, entry)))
		goto unlock;
	if (write_access) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address,
					pte, pmd, ptl, entry);
		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	if (ptep_set_access_flags(vma, address, pte, entry, write_access)) {
		update_mmu_cache(vma, address, entry);
	} else {
		/*
		 * This is needed only for protection faults but the arch code
		 * is not yet telling us if this is a protection fault or not.
		 * This still avoids useless tlb flushes for .text page faults
		 * with threads.
		 */
		if (write_access)
			flush_tlb_page(vma, address);
	}
unlock:
	pte_unmap_unlock(pte, ptl);
	return 0;
}

/*
 * 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);

	count_vm_event(PGFAULT);

	if (unlikely(is_vm_hugetlb_page(vma)))
		return hugetlb_fault(mm, vma, address, write_access);

	pgd = pgd_offset(mm, address);
	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		return VM_FAULT_OOM;
	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		return VM_FAULT_OOM;
	pte = pte_alloc_map(mm, pmd, address);
	if (!pte)
		return VM_FAULT_OOM;

	return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
}

#ifndef __PAGETABLE_PUD_FOLDED
/*
 * Allocate page upper directory.
 * We've already handled the fast-path in-line.
 */
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pud_t *new = pud_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
	if (pgd_present(*pgd))		/* Another has populated it */
		pud_free(mm, new);
	else
		pgd_populate(mm, pgd, new);
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PUD_FOLDED */

#ifndef __PAGETABLE_PMD_FOLDED
/*
 * Allocate page middle directory.
 * We've already handled the fast-path in-line.
 */
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	pmd_t *new = pmd_alloc_one(mm, address);
	if (!new)
		return -ENOMEM;

	smp_wmb(); /* See comment in __pte_alloc */

	spin_lock(&mm->page_table_lock);
#ifndef __ARCH_HAS_4LEVEL_HACK
	if (pud_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pud_populate(mm, pud, new);
#else
	if (pgd_present(*pud))		/* Another has populated it */
		pmd_free(mm, new);
	else
		pgd_populate(mm, pud, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */
	spin_unlock(&mm->page_table_lock);
	return 0;
}
#endif /* __PAGETABLE_PMD_FOLDED */

int make_pages_present(unsigned long addr, unsigned long end)
{
	int ret, len, write;
	struct vm_area_struct * vma;

	vma = find_vma(current->mm, addr);
	if (!vma)
		return -ENOMEM;
	write = (vma->vm_flags & VM_WRITE) != 0;
	BUG_ON(addr >= end);
	BUG_ON(end > vma->vm_end);
	len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
	ret = get_user_pages(current, current->mm, addr,
			len, write, 0, NULL, NULL);
	if (ret < 0)
		return ret;
	return ret == len ? 0 : -EFAULT;
}

#if !defined(__HAVE_ARCH_GATE_AREA)

#if defined(AT_SYSINFO_EHDR)
static struct vm_area_struct gate_vma;

static int __init gate_vma_init(void)
{
	gate_vma.vm_mm = NULL;
	gate_vma.vm_start = FIXADDR_USER_START;
	gate_vma.vm_end = FIXADDR_USER_END;
	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
	gate_vma.vm_page_prot = __P101;
	/*
	 * Make sure the vDSO gets into every core dump.
	 * Dumping its contents makes post-mortem fully interpretable later
	 * without matching up the same kernel and hardware config to see
	 * what PC values meant.
	 */
	gate_vma.vm_flags |= VM_ALWAYSDUMP;
	return 0;
}
__initcall(gate_vma_init);
#endif

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef AT_SYSINFO_EHDR
	return &gate_vma;
#else
	return NULL;
#endif
}

int in_gate_area_no_task(unsigned long addr)
{
#ifdef AT_SYSINFO_EHDR
	if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
		return 1;
#endif
	return 0;
}

#endif	/* __HAVE_ARCH_GATE_AREA */

#ifdef CONFIG_HAVE_IOREMAP_PROT
static resource_size_t follow_phys(struct vm_area_struct *vma,
			unsigned long address, unsigned int flags,
			unsigned long *prot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;
	spinlock_t *ptl;
	resource_size_t phys_addr = 0;
	struct mm_struct *mm = vma->vm_mm;

	VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP)));

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto no_page_table;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		goto no_page_table;

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		goto no_page_table;

	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
	if (pmd_huge(*pmd))
		goto no_page_table;

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	if (!ptep)
		goto out;

	pte = *ptep;
	if (!pte_present(pte))
		goto unlock;
	if ((flags & FOLL_WRITE) && !pte_write(pte))
		goto unlock;
	phys_addr = pte_pfn(pte);
	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */

	*prot = pgprot_val(pte_pgprot(pte));

unlock:
	pte_unmap_unlock(ptep, ptl);
out:
	return phys_addr;
no_page_table:
	return 0;
}

int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write)
{
	resource_size_t phys_addr;
	unsigned long prot = 0;
	void *maddr;
	int offset = addr & (PAGE_SIZE-1);

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		return -EINVAL;

	phys_addr = follow_phys(vma, addr, write, &prot);

	if (!phys_addr)
		return -EINVAL;

	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
	if (write)
		memcpy_toio(maddr + offset, buf, len);
	else
		memcpy_fromio(buf, maddr + offset, len);
	iounmap(maddr);

	return len;
}
#endif

/*
 * Access another process' address space.
 * Source/target buffer must be kernel space,
 * Do not walk the page table directly, use get_user_pages
 */
int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
{
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	void *old_buf = buf;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	down_read(&mm->mmap_sem);
	/* ignore errors, just check how much was successfully transferred */
	while (len) {
		int bytes, ret, offset;
		void *maddr;
		struct page *page = NULL;

		ret = get_user_pages(tsk, mm, addr, 1,
				write, 1, &page, &vma);
		if (ret <= 0) {
			/*
			 * Check if this is a VM_IO | VM_PFNMAP VMA, which
			 * we can access using slightly different code.
			 */
#ifdef CONFIG_HAVE_IOREMAP_PROT
			vma = find_vma(mm, addr);
			if (!vma)
				break;
			if (vma->vm_ops && vma->vm_ops->access)
				ret = vma->vm_ops->access(vma, addr, buf,
							  len, write);
			if (ret <= 0)
#endif
				break;
			bytes = ret;
		} else {
			bytes = len;
			offset = addr & (PAGE_SIZE-1);
			if (bytes > PAGE_SIZE-offset)
				bytes = PAGE_SIZE-offset;

			maddr = kmap(page);
			if (write) {
				copy_to_user_page(vma, page, addr,