/*
   * Resizable virtual memory filesystem for Linux.
   *
   * Copyright (C) 2000 Linus Torvalds.
   *		 2000 Transmeta Corp.
   *		 2000-2001 Christoph Rohland
   *		 2000-2001 SAP AG
   *		 2002 Red Hat Inc.

   * Copyright (C) 2002-2011 Hugh Dickins.
   * Copyright (C) 2011 Google Inc.

   * Copyright (C) 2002-2005 VERITAS Software Corporation.

   * Copyright (C) 2004 Andi Kleen, SuSE Labs
   *
   * Extended attribute support for tmpfs:
   * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
   * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
   *

   * tiny-shmem:
   * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com>
   *

   * This file is released under the GPL.
   */

  #include <linux/fs.h>
  #include <linux/init.h>
  #include <linux/vfs.h>
  #include <linux/mount.h>

  #include <linux/ramfs.h>

  #include <linux/pagemap.h>

  #include <linux/file.h>
  #include <linux/mm.h>

  #include <linux/export.h>

  #include <linux/swap.h>

  #include <linux/aio.h>

  
  static struct vfsmount *shm_mnt;
  
  #ifdef CONFIG_SHMEM

  /*
   * This virtual memory filesystem is heavily based on the ramfs. It
   * extends ramfs by the ability to use swap and honor resource limits
   * which makes it a completely usable filesystem.
   */

  #include <linux/xattr.h>

  #include <linux/exportfs.h>

  #include <linux/posix_acl.h>

  #include <linux/posix_acl_xattr.h>

  #include <linux/mman.h>

  #include <linux/string.h>
  #include <linux/slab.h>
  #include <linux/backing-dev.h>
  #include <linux/shmem_fs.h>

  #include <linux/writeback.h>

  #include <linux/blkdev.h>

  #include <linux/pagevec.h>

  #include <linux/percpu_counter.h>

  #include <linux/falloc.h>

  #include <linux/splice.h>

  #include <linux/security.h>
  #include <linux/swapops.h>
  #include <linux/mempolicy.h>
  #include <linux/namei.h>

  #include <linux/ctype.h>

  #include <linux/migrate.h>

  #include <linux/highmem.h>

  #include <linux/seq_file.h>

  #include <linux/magic.h>

  #include <asm/uaccess.h>

  #include <asm/pgtable.h>

  #define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)

  #define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)

  /* Pretend that each entry is of this size in directory's i_size */
  #define BOGO_DIRENT_SIZE 20

  /* Symlink up to this size is kmalloc'ed instead of using a swappable page */
  #define SHORT_SYMLINK_LEN 128

  /*
   * shmem_fallocate and shmem_writepage communicate via inode->i_private
   * (with i_mutex making sure that it has only one user at a time):
   * we would prefer not to enlarge the shmem inode just for that.
   */
  struct shmem_falloc {
  	pgoff_t start;		/* start of range currently being fallocated */
  	pgoff_t next;		/* the next page offset to be fallocated */
  	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
  	pgoff_t nr_unswapped;	/* how often writepage refused to swap out */
  };

  /* Flag allocation requirements to shmem_getpage */

  enum sgp_type {

  	SGP_READ,	/* don't exceed i_size, don't allocate page */
  	SGP_CACHE,	/* don't exceed i_size, may allocate page */

  	SGP_DIRTY,	/* like SGP_CACHE, but set new page dirty */

  	SGP_WRITE,	/* may exceed i_size, may allocate !Uptodate page */
  	SGP_FALLOC,	/* like SGP_WRITE, but make existing page Uptodate */

  };

  #ifdef CONFIG_TMPFS

  static unsigned long shmem_default_max_blocks(void)
  {
  	return totalram_pages / 2;
  }
  
  static unsigned long shmem_default_max_inodes(void)
  {
  	return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
  }

  #endif

  static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
  static int shmem_replace_page(struct page **pagep, gfp_t gfp,
  				struct shmem_inode_info *info, pgoff_t index);

  static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
  	struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type);
  
  static inline int shmem_getpage(struct inode *inode, pgoff_t index,
  	struct page **pagep, enum sgp_type sgp, int *fault_type)
  {
  	return shmem_getpage_gfp(inode, index, pagep, sgp,
  			mapping_gfp_mask(inode->i_mapping), fault_type);
  }

  static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
  {
  	return sb->s_fs_info;
  }
  
  /*
   * shmem_file_setup pre-accounts the whole fixed size of a VM object,
   * for shared memory and for shared anonymous (/dev/zero) mappings
   * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
   * consistent with the pre-accounting of private mappings ...
   */
  static inline int shmem_acct_size(unsigned long flags, loff_t size)
  {

  	return (flags & VM_NORESERVE) ?

  		0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size));

  }
  
  static inline void shmem_unacct_size(unsigned long flags, loff_t size)
  {

  	if (!(flags & VM_NORESERVE))

  		vm_unacct_memory(VM_ACCT(size));
  }
  
  /*
   * ... whereas tmpfs objects are accounted incrementally as
   * pages are allocated, in order to allow huge sparse files.
   * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
   * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
   */
  static inline int shmem_acct_block(unsigned long flags)
  {

  	return (flags & VM_NORESERVE) ?

  		security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0;

  }
  
  static inline void shmem_unacct_blocks(unsigned long flags, long pages)
  {

  	if (flags & VM_NORESERVE)

  		vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
  }

  static const struct super_operations shmem_ops;

  static const struct address_space_operations shmem_aops;

  static const struct file_operations shmem_file_operations;

  static const struct inode_operations shmem_inode_operations;
  static const struct inode_operations shmem_dir_inode_operations;
  static const struct inode_operations shmem_special_inode_operations;

  static const struct vm_operations_struct shmem_vm_ops;

  static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {

  	.ra_pages	= 0,	/* No readahead */

  	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,

  };
  
  static LIST_HEAD(shmem_swaplist);

  static DEFINE_MUTEX(shmem_swaplist_mutex);

  static int shmem_reserve_inode(struct super_block *sb)
  {
  	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
  	if (sbinfo->max_inodes) {
  		spin_lock(&sbinfo->stat_lock);
  		if (!sbinfo->free_inodes) {
  			spin_unlock(&sbinfo->stat_lock);
  			return -ENOSPC;
  		}
  		sbinfo->free_inodes--;
  		spin_unlock(&sbinfo->stat_lock);
  	}
  	return 0;
  }
  
  static void shmem_free_inode(struct super_block *sb)
  {
  	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
  	if (sbinfo->max_inodes) {
  		spin_lock(&sbinfo->stat_lock);
  		sbinfo->free_inodes++;
  		spin_unlock(&sbinfo->stat_lock);
  	}
  }

  /**

   * shmem_recalc_inode - recalculate the block usage of an inode

   * @inode: inode to recalc
   *
   * We have to calculate the free blocks since the mm can drop
   * undirtied hole pages behind our back.
   *
   * But normally   info->alloced == inode->i_mapping->nrpages + info->swapped
   * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
   *
   * It has to be called with the spinlock held.
   */
  static void shmem_recalc_inode(struct inode *inode)
  {
  	struct shmem_inode_info *info = SHMEM_I(inode);
  	long freed;
  
  	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
  	if (freed > 0) {

  		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
  		if (sbinfo->max_blocks)
  			percpu_counter_add(&sbinfo->used_blocks, -freed);

  		info->alloced -= freed;

  		inode->i_blocks -= freed * BLOCKS_PER_PAGE;

  		shmem_unacct_blocks(info->flags, freed);

  	}
  }

  /*
   * Replace item expected in radix tree by a new item, while holding tree lock.
   */
  static int shmem_radix_tree_replace(struct address_space *mapping,
  			pgoff_t index, void *expected, void *replacement)
  {
  	void **pslot;

  	void *item;

  
  	VM_BUG_ON(!expected);

  	VM_BUG_ON(!replacement);

  	pslot = radix_tree_lookup_slot(&mapping->page_tree, index);

  	if (!pslot)
  		return -ENOENT;
  	item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);

  	if (item != expected)
  		return -ENOENT;

  	radix_tree_replace_slot(pslot, replacement);

  	return 0;
  }
  
  /*

   * Sometimes, before we decide whether to proceed or to fail, we must check
   * that an entry was not already brought back from swap by a racing thread.
   *
   * Checking page is not enough: by the time a SwapCache page is locked, it
   * might be reused, and again be SwapCache, using the same swap as before.
   */
  static bool shmem_confirm_swap(struct address_space *mapping,
  			       pgoff_t index, swp_entry_t swap)
  {
  	void *item;
  
  	rcu_read_lock();
  	item = radix_tree_lookup(&mapping->page_tree, index);
  	rcu_read_unlock();
  	return item == swp_to_radix_entry(swap);
  }
  
  /*

   * Like add_to_page_cache_locked, but error if expected item has gone.
   */
  static int shmem_add_to_page_cache(struct page *page,
  				   struct address_space *mapping,
  				   pgoff_t index, gfp_t gfp, void *expected)
  {

  	int error;

  	VM_BUG_ON_PAGE(!PageLocked(page), page);
  	VM_BUG_ON_PAGE(!PageSwapBacked(page), page);

  	page_cache_get(page);
  	page->mapping = mapping;
  	page->index = index;
  
  	spin_lock_irq(&mapping->tree_lock);

  	if (!expected)

  		error = radix_tree_insert(&mapping->page_tree, index, page);
  	else
  		error = shmem_radix_tree_replace(mapping, index, expected,
  								 page);

  	if (!error) {

  		mapping->nrpages++;
  		__inc_zone_page_state(page, NR_FILE_PAGES);
  		__inc_zone_page_state(page, NR_SHMEM);
  		spin_unlock_irq(&mapping->tree_lock);
  	} else {
  		page->mapping = NULL;
  		spin_unlock_irq(&mapping->tree_lock);
  		page_cache_release(page);

  	}

  	return error;
  }
  
  /*

   * Like delete_from_page_cache, but substitutes swap for page.
   */
  static void shmem_delete_from_page_cache(struct page *page, void *radswap)
  {
  	struct address_space *mapping = page->mapping;
  	int error;
  
  	spin_lock_irq(&mapping->tree_lock);
  	error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
  	page->mapping = NULL;
  	mapping->nrpages--;
  	__dec_zone_page_state(page, NR_FILE_PAGES);
  	__dec_zone_page_state(page, NR_SHMEM);
  	spin_unlock_irq(&mapping->tree_lock);
  	page_cache_release(page);
  	BUG_ON(error);
  }
  
  /*

   * Remove swap entry from radix tree, free the swap and its page cache.
   */
  static int shmem_free_swap(struct address_space *mapping,
  			   pgoff_t index, void *radswap)
  {

  	void *old;

  
  	spin_lock_irq(&mapping->tree_lock);

  	old = radix_tree_delete_item(&mapping->page_tree, index, radswap);

  	spin_unlock_irq(&mapping->tree_lock);

  	if (old != radswap)
  		return -ENOENT;
  	free_swap_and_cache(radix_to_swp_entry(radswap));
  	return 0;

  }
  
  /*

   * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
   */
  void shmem_unlock_mapping(struct address_space *mapping)
  {
  	struct pagevec pvec;
  	pgoff_t indices[PAGEVEC_SIZE];
  	pgoff_t index = 0;
  
  	pagevec_init(&pvec, 0);
  	/*
  	 * Minor point, but we might as well stop if someone else SHM_LOCKs it.
  	 */
  	while (!mapping_unevictable(mapping)) {
  		/*
  		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
  		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
  		 */

  		pvec.nr = find_get_entries(mapping, index,
  					   PAGEVEC_SIZE, pvec.pages, indices);

  		if (!pvec.nr)
  			break;
  		index = indices[pvec.nr - 1] + 1;

  		pagevec_remove_exceptionals(&pvec);

  		check_move_unevictable_pages(pvec.pages, pvec.nr);
  		pagevec_release(&pvec);
  		cond_resched();
  	}

  }
  
  /*
   * Remove range of pages and swap entries from radix tree, and free them.

   * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.

   */

  static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
  								 bool unfalloc)

  {

  	struct address_space *mapping = inode->i_mapping;

  	struct shmem_inode_info *info = SHMEM_I(inode);

  	pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

  	pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT;
  	unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1);
  	unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);

  	struct pagevec pvec;

  	pgoff_t indices[PAGEVEC_SIZE];
  	long nr_swaps_freed = 0;

  	pgoff_t index;

  	int i;

  	if (lend == -1)
  		end = -1;	/* unsigned, so actually very big */

  
  	pagevec_init(&pvec, 0);
  	index = start;

  	while (index < end) {

  		pvec.nr = find_get_entries(mapping, index,
  			min(end - index, (pgoff_t)PAGEVEC_SIZE),
  			pvec.pages, indices);

  		if (!pvec.nr)
  			break;

  		mem_cgroup_uncharge_start();
  		for (i = 0; i < pagevec_count(&pvec); i++) {
  			struct page *page = pvec.pages[i];

  			index = indices[i];

  			if (index >= end)

  				break;

  			if (radix_tree_exceptional_entry(page)) {

  				if (unfalloc)
  					continue;

  				nr_swaps_freed += !shmem_free_swap(mapping,
  								index, page);

  				continue;

  			}
  
  			if (!trylock_page(page))

  				continue;

  			if (!unfalloc || !PageUptodate(page)) {
  				if (page->mapping == mapping) {

  					VM_BUG_ON_PAGE(PageWriteback(page), page);

  					truncate_inode_page(mapping, page);
  				}

  			}

  			unlock_page(page);
  		}

  		pagevec_remove_exceptionals(&pvec);

  		pagevec_release(&pvec);

  		mem_cgroup_uncharge_end();
  		cond_resched();
  		index++;
  	}

  	if (partial_start) {

  		struct page *page = NULL;
  		shmem_getpage(inode, start - 1, &page, SGP_READ, NULL);
  		if (page) {

  			unsigned int top = PAGE_CACHE_SIZE;
  			if (start > end) {
  				top = partial_end;
  				partial_end = 0;
  			}
  			zero_user_segment(page, partial_start, top);
  			set_page_dirty(page);
  			unlock_page(page);
  			page_cache_release(page);
  		}
  	}
  	if (partial_end) {
  		struct page *page = NULL;
  		shmem_getpage(inode, end, &page, SGP_READ, NULL);
  		if (page) {
  			zero_user_segment(page, 0, partial_end);

  			set_page_dirty(page);
  			unlock_page(page);
  			page_cache_release(page);
  		}
  	}

  	if (start >= end)
  		return;

  
  	index = start;
  	for ( ; ; ) {
  		cond_resched();

  
  		pvec.nr = find_get_entries(mapping, index,

  				min(end - index, (pgoff_t)PAGEVEC_SIZE),

  				pvec.pages, indices);

  		if (!pvec.nr) {

  			if (index == start || unfalloc)

  				break;
  			index = start;
  			continue;
  		}

  		if ((index == start || unfalloc) && indices[0] >= end) {

  			pagevec_remove_exceptionals(&pvec);

  			pagevec_release(&pvec);

  			break;
  		}
  		mem_cgroup_uncharge_start();
  		for (i = 0; i < pagevec_count(&pvec); i++) {
  			struct page *page = pvec.pages[i];

  			index = indices[i];

  			if (index >= end)

  				break;

  			if (radix_tree_exceptional_entry(page)) {

  				if (unfalloc)
  					continue;

  				nr_swaps_freed += !shmem_free_swap(mapping,
  								index, page);
  				continue;
  			}

  			lock_page(page);

  			if (!unfalloc || !PageUptodate(page)) {
  				if (page->mapping == mapping) {

  					VM_BUG_ON_PAGE(PageWriteback(page), page);

  					truncate_inode_page(mapping, page);
  				}

  			}

  			unlock_page(page);
  		}

  		pagevec_remove_exceptionals(&pvec);

  		pagevec_release(&pvec);

  		mem_cgroup_uncharge_end();
  		index++;
  	}

  	spin_lock(&info->lock);

  	info->swapped -= nr_swaps_freed;

  	shmem_recalc_inode(inode);
  	spin_unlock(&info->lock);

  }

  void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
  {
  	shmem_undo_range(inode, lstart, lend, false);

  	inode->i_ctime = inode->i_mtime = CURRENT_TIME;

  }

  EXPORT_SYMBOL_GPL(shmem_truncate_range);

  static int shmem_setattr(struct dentry *dentry, struct iattr *attr)

  {
  	struct inode *inode = dentry->d_inode;

  	int error;

  	error = inode_change_ok(inode, attr);
  	if (error)
  		return error;

  	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
  		loff_t oldsize = inode->i_size;
  		loff_t newsize = attr->ia_size;

  		if (newsize != oldsize) {
  			i_size_write(inode, newsize);
  			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
  		}
  		if (newsize < oldsize) {
  			loff_t holebegin = round_up(newsize, PAGE_SIZE);
  			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
  			shmem_truncate_range(inode, newsize, (loff_t)-1);
  			/* unmap again to remove racily COWed private pages */
  			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
  		}

  	}

  	setattr_copy(inode, attr);

  	if (attr->ia_valid & ATTR_MODE)

  		error = posix_acl_chmod(inode, inode->i_mode);

  	return error;
  }

  static void shmem_evict_inode(struct inode *inode)

  {

  	struct shmem_inode_info *info = SHMEM_I(inode);

  	if (inode->i_mapping->a_ops == &shmem_aops) {

  		shmem_unacct_size(info->flags, inode->i_size);
  		inode->i_size = 0;

  		shmem_truncate_range(inode, 0, (loff_t)-1);

  		if (!list_empty(&info->swaplist)) {

  			mutex_lock(&shmem_swaplist_mutex);

  			list_del_init(&info->swaplist);

  			mutex_unlock(&shmem_swaplist_mutex);

  		}

  	} else
  		kfree(info->symlink);

  	simple_xattrs_free(&info->xattrs);

  	WARN_ON(inode->i_blocks);

  	shmem_free_inode(inode->i_sb);

  	clear_inode(inode);

  }

  /*
   * If swap found in inode, free it and move page from swapcache to filecache.
   */

  static int shmem_unuse_inode(struct shmem_inode_info *info,

  			     swp_entry_t swap, struct page **pagep)

  {

  	struct address_space *mapping = info->vfs_inode.i_mapping;

  	void *radswap;

  	pgoff_t index;

  	gfp_t gfp;
  	int error = 0;

  	radswap = swp_to_radix_entry(swap);

  	index = radix_tree_locate_item(&mapping->page_tree, radswap);

  	if (index == -1)

  		return 0;

  	/*
  	 * Move _head_ to start search for next from here.

  	 * But be careful: shmem_evict_inode checks list_empty without taking

  	 * mutex, and there's an instant in list_move_tail when info->swaplist

  	 * would appear empty, if it were the only one on shmem_swaplist.

  	 */
  	if (shmem_swaplist.next != &info->swaplist)
  		list_move_tail(&shmem_swaplist, &info->swaplist);

  	gfp = mapping_gfp_mask(mapping);
  	if (shmem_should_replace_page(*pagep, gfp)) {
  		mutex_unlock(&shmem_swaplist_mutex);
  		error = shmem_replace_page(pagep, gfp, info, index);
  		mutex_lock(&shmem_swaplist_mutex);
  		/*
  		 * We needed to drop mutex to make that restrictive page

  		 * allocation, but the inode might have been freed while we
  		 * dropped it: although a racing shmem_evict_inode() cannot
  		 * complete without emptying the radix_tree, our page lock
  		 * on this swapcache page is not enough to prevent that -
  		 * free_swap_and_cache() of our swap entry will only
  		 * trylock_page(), removing swap from radix_tree whatever.
  		 *
  		 * We must not proceed to shmem_add_to_page_cache() if the
  		 * inode has been freed, but of course we cannot rely on
  		 * inode or mapping or info to check that.  However, we can
  		 * safely check if our swap entry is still in use (and here
  		 * it can't have got reused for another page): if it's still
  		 * in use, then the inode cannot have been freed yet, and we
  		 * can safely proceed (if it's no longer in use, that tells
  		 * nothing about the inode, but we don't need to unuse swap).

  		 */
  		if (!page_swapcount(*pagep))
  			error = -ENOENT;
  	}

  	/*

  	 * We rely on shmem_swaplist_mutex, not only to protect the swaplist,
  	 * but also to hold up shmem_evict_inode(): so inode cannot be freed
  	 * beneath us (pagelock doesn't help until the page is in pagecache).

  	 */

  	if (!error)
  		error = shmem_add_to_page_cache(*pagep, mapping, index,

  						GFP_NOWAIT, radswap);

  	if (error != -ENOMEM) {

  		/*
  		 * Truncation and eviction use free_swap_and_cache(), which
  		 * only does trylock page: if we raced, best clean up here.
  		 */

  		delete_from_swap_cache(*pagep);
  		set_page_dirty(*pagep);

  		if (!error) {
  			spin_lock(&info->lock);
  			info->swapped--;
  			spin_unlock(&info->lock);
  			swap_free(swap);
  		}

  		error = 1;	/* not an error, but entry was found */

  	}

  	return error;

  }
  
  /*

   * Search through swapped inodes to find and replace swap by page.

   */

  int shmem_unuse(swp_entry_t swap, struct page *page)

  {

  	struct list_head *this, *next;

  	struct shmem_inode_info *info;
  	int found = 0;

  	int error = 0;
  
  	/*
  	 * There's a faint possibility that swap page was replaced before

  	 * caller locked it: caller will come back later with the right page.

  	 */

  	if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))

  		goto out;

  
  	/*
  	 * Charge page using GFP_KERNEL while we can wait, before taking
  	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
  	 * Charged back to the user (not to caller) when swap account is used.

  	 */

  	error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL);

  	if (error)
  		goto out;

  	/* No radix_tree_preload: swap entry keeps a place for page in tree */

  	mutex_lock(&shmem_swaplist_mutex);

  	list_for_each_safe(this, next, &shmem_swaplist) {
  		info = list_entry(this, struct shmem_inode_info, swaplist);

  		if (info->swapped)

  			found = shmem_unuse_inode(info, swap, &page);

  		else
  			list_del_init(&info->swaplist);

  		cond_resched();

  		if (found)

  			break;

  	}

  	mutex_unlock(&shmem_swaplist_mutex);

  	if (found < 0)
  		error = found;
  out:

  	unlock_page(page);
  	page_cache_release(page);

  	return error;

  }
  
  /*
   * Move the page from the page cache to the swap cache.
   */
  static int shmem_writepage(struct page *page, struct writeback_control *wbc)
  {
  	struct shmem_inode_info *info;

  	struct address_space *mapping;

  	struct inode *inode;

  	swp_entry_t swap;
  	pgoff_t index;

  
  	BUG_ON(!PageLocked(page));

  	mapping = page->mapping;
  	index = page->index;
  	inode = mapping->host;
  	info = SHMEM_I(inode);
  	if (info->flags & VM_LOCKED)
  		goto redirty;

  	if (!total_swap_pages)

  		goto redirty;

  	/*
  	 * shmem_backing_dev_info's capabilities prevent regular writeback or
  	 * sync from ever calling shmem_writepage; but a stacking filesystem

  	 * might use ->writepage of its underlying filesystem, in which case

  	 * tmpfs should write out to swap only in response to memory pressure,

  	 * and not for the writeback threads or sync.

  	 */

  	if (!wbc->for_reclaim) {
  		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
  		goto redirty;
  	}

  
  	/*
  	 * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC
  	 * value into swapfile.c, the only way we can correctly account for a
  	 * fallocated page arriving here is now to initialize it and write it.

  	 *
  	 * That's okay for a page already fallocated earlier, but if we have
  	 * not yet completed the fallocation, then (a) we want to keep track
  	 * of this page in case we have to undo it, and (b) it may not be a
  	 * good idea to continue anyway, once we're pushing into swap.  So
  	 * reactivate the page, and let shmem_fallocate() quit when too many.

  	 */
  	if (!PageUptodate(page)) {

  		if (inode->i_private) {
  			struct shmem_falloc *shmem_falloc;
  			spin_lock(&inode->i_lock);
  			shmem_falloc = inode->i_private;
  			if (shmem_falloc &&
  			    index >= shmem_falloc->start &&
  			    index < shmem_falloc->next)
  				shmem_falloc->nr_unswapped++;
  			else
  				shmem_falloc = NULL;
  			spin_unlock(&inode->i_lock);
  			if (shmem_falloc)
  				goto redirty;
  		}

  		clear_highpage(page);
  		flush_dcache_page(page);
  		SetPageUptodate(page);
  	}

  	swap = get_swap_page();
  	if (!swap.val)
  		goto redirty;

  	/*
  	 * Add inode to shmem_unuse()'s list of swapped-out inodes,

  	 * if it's not already there.  Do it now before the page is
  	 * moved to swap cache, when its pagelock no longer protects

  	 * the inode from eviction.  But don't unlock the mutex until

  	 * we've incremented swapped, because shmem_unuse_inode() will
  	 * prune a !swapped inode from the swaplist under this mutex.

  	 */

  	mutex_lock(&shmem_swaplist_mutex);
  	if (list_empty(&info->swaplist))
  		list_add_tail(&info->swaplist, &shmem_swaplist);

  	if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {

  		swap_shmem_alloc(swap);

  		shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
  
  		spin_lock(&info->lock);
  		info->swapped++;
  		shmem_recalc_inode(inode);

  		spin_unlock(&info->lock);

  
  		mutex_unlock(&shmem_swaplist_mutex);

  		BUG_ON(page_mapped(page));

  		swap_writepage(page, wbc);

  		return 0;
  	}

  	mutex_unlock(&shmem_swaplist_mutex);

  	swapcache_free(swap, NULL);

  redirty:
  	set_page_dirty(page);

  	if (wbc->for_reclaim)
  		return AOP_WRITEPAGE_ACTIVATE;	/* Return with page locked */
  	unlock_page(page);
  	return 0;

  }
  
  #ifdef CONFIG_NUMA

  #ifdef CONFIG_TMPFS

  static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)

  {

  	char buffer[64];

  	if (!mpol || mpol->mode == MPOL_DEFAULT)

  		return;		/* show nothing */

  	mpol_to_str(buffer, sizeof(buffer), mpol);

  
  	seq_printf(seq, ",mpol=%s", buffer);

  }

  
  static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
  {
  	struct mempolicy *mpol = NULL;
  	if (sbinfo->mpol) {
  		spin_lock(&sbinfo->stat_lock);	/* prevent replace/use races */
  		mpol = sbinfo->mpol;
  		mpol_get(mpol);
  		spin_unlock(&sbinfo->stat_lock);
  	}
  	return mpol;
  }

  #endif /* CONFIG_TMPFS */

  static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
  			struct shmem_inode_info *info, pgoff_t index)

  {

  	struct vm_area_struct pvma;

  	struct page *page;

  	/* Create a pseudo vma that just contains the policy */

  	pvma.vm_start = 0;

  	/* Bias interleave by inode number to distribute better across nodes */
  	pvma.vm_pgoff = index + info->vfs_inode.i_ino;

  	pvma.vm_ops = NULL;

  	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
  
  	page = swapin_readahead(swap, gfp, &pvma, 0);
  
  	/* Drop reference taken by mpol_shared_policy_lookup() */
  	mpol_cond_put(pvma.vm_policy);
  
  	return page;

  }

  static struct page *shmem_alloc_page(gfp_t gfp,

  			struct shmem_inode_info *info, pgoff_t index)

  {
  	struct vm_area_struct pvma;

  	struct page *page;

  	/* Create a pseudo vma that just contains the policy */
  	pvma.vm_start = 0;

  	/* Bias interleave by inode number to distribute better across nodes */
  	pvma.vm_pgoff = index + info->vfs_inode.i_ino;

  	pvma.vm_ops = NULL;

  	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);

  	page = alloc_page_vma(gfp, &pvma, 0);
  
  	/* Drop reference taken by mpol_shared_policy_lookup() */
  	mpol_cond_put(pvma.vm_policy);
  
  	return page;

  }

  #else /* !CONFIG_NUMA */
  #ifdef CONFIG_TMPFS

  static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)

  {
  }
  #endif /* CONFIG_TMPFS */

  static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
  			struct shmem_inode_info *info, pgoff_t index)

  {

  	return swapin_readahead(swap, gfp, NULL, 0);

  }

  static inline struct page *shmem_alloc_page(gfp_t gfp,

  			struct shmem_inode_info *info, pgoff_t index)

  {

  	return alloc_page(gfp);

  }

  #endif /* CONFIG_NUMA */

  #if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS)
  static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
  {
  	return NULL;
  }
  #endif

  /*

   * When a page is moved from swapcache to shmem filecache (either by the
   * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of
   * shmem_unuse_inode()), it may have been read in earlier from swap, in
   * ignorance of the mapping it belongs to.  If that mapping has special
   * constraints (like the gma500 GEM driver, which requires RAM below 4GB),
   * we may need to copy to a suitable page before moving to filecache.
   *
   * In a future release, this may well be extended to respect cpuset and
   * NUMA mempolicy, and applied also to anonymous pages in do_swap_page();
   * but for now it is a simple matter of zone.
   */
  static bool shmem_should_replace_page(struct page *page, gfp_t gfp)
  {
  	return page_zonenum(page) > gfp_zone(gfp);
  }
  
  static int shmem_replace_page(struct page **pagep, gfp_t gfp,
  				struct shmem_inode_info *info, pgoff_t index)
  {
  	struct page *oldpage, *newpage;
  	struct address_space *swap_mapping;
  	pgoff_t swap_index;
  	int error;
  
  	oldpage = *pagep;
  	swap_index = page_private(oldpage);
  	swap_mapping = page_mapping(oldpage);
  
  	/*
  	 * We have arrived here because our zones are constrained, so don't
  	 * limit chance of success by further cpuset and node constraints.
  	 */
  	gfp &= ~GFP_CONSTRAINT_MASK;
  	newpage = shmem_alloc_page(gfp, info, index);
  	if (!newpage)
  		return -ENOMEM;

  	page_cache_get(newpage);
  	copy_highpage(newpage, oldpage);

  	flush_dcache_page(newpage);

  	__set_page_locked(newpage);

  	SetPageUptodate(newpage);

  	SetPageSwapBacked(newpage);

  	set_page_private(newpage, swap_index);

  	SetPageSwapCache(newpage);
  
  	/*
  	 * Our caller will very soon move newpage out of swapcache, but it's
  	 * a nice clean interface for us to replace oldpage by newpage there.
  	 */
  	spin_lock_irq(&swap_mapping->tree_lock);
  	error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
  								   newpage);

  	if (!error) {
  		__inc_zone_page_state(newpage, NR_FILE_PAGES);
  		__dec_zone_page_state(oldpage, NR_FILE_PAGES);
  	}

  	spin_unlock_irq(&swap_mapping->tree_lock);

  	if (unlikely(error)) {
  		/*
  		 * Is this possible?  I think not, now that our callers check
  		 * both PageSwapCache and page_private after getting page lock;
  		 * but be defensive.  Reverse old to newpage for clear and free.
  		 */
  		oldpage = newpage;
  	} else {
  		mem_cgroup_replace_page_cache(oldpage, newpage);
  		lru_cache_add_anon(newpage);
  		*pagep = newpage;
  	}

  
  	ClearPageSwapCache(oldpage);
  	set_page_private(oldpage, 0);
  
  	unlock_page(oldpage);
  	page_cache_release(oldpage);
  	page_cache_release(oldpage);

  	return error;

  }
  
  /*

   * shmem_getpage_gfp - find page in cache, or get from swap, or allocate

   *
   * If we allocate a new one we do not mark it dirty. That's up to the
   * vm. If we swap it in we mark it dirty since we also free the swap
   * entry since a page cannot live in both the swap and page cache
   */

  static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,

  	struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type)

  {
  	struct address_space *mapping = inode->i_mapping;

  	struct shmem_inode_info *info;

  	struct shmem_sb_info *sbinfo;

  	struct page *page;

  	swp_entry_t swap;
  	int error;

  	int once = 0;

  	int alloced = 0;

  	if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))

  		return -EFBIG;

  repeat:

  	swap.val = 0;

  	page = find_lock_entry(mapping, index);

  	if (radix_tree_exceptional_entry(page)) {
  		swap = radix_to_swp_entry(page);
  		page = NULL;
  	}

  	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&

  	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
  		error = -EINVAL;
  		goto failed;
  	}

  	/* fallocated page? */
  	if (page && !PageUptodate(page)) {
  		if (sgp != SGP_READ)
  			goto clear;
  		unlock_page(page);
  		page_cache_release(page);
  		page = NULL;
  	}

  	if (page || (sgp == SGP_READ && !swap.val)) {

  		*pagep = page;
  		return 0;

  	}
  
  	/*

  	 * Fast cache lookup did not find it:
  	 * bring it back from swap or allocate.

  	 */

  	info = SHMEM_I(inode);
  	sbinfo = SHMEM_SB(inode->i_sb);

  	if (swap.val) {
  		/* Look it up and read it in.. */

  		page = lookup_swap_cache(swap);
  		if (!page) {

  			/* here we actually do the io */

  			if (fault_type)
  				*fault_type |= VM_FAULT_MAJOR;

  			page = shmem_swapin(swap, gfp, info, index);

  			if (!page) {

  				error = -ENOMEM;
  				goto failed;

  			}

  		}
  
  		/* We have to do this with page locked to prevent races */

  		lock_page(page);

  		if (!PageSwapCache(page) || page_private(page) != swap.val ||

  		    !shmem_confirm_swap(mapping, index, swap)) {

  			error = -EEXIST;	/* try again */

  			goto unlock;

  		}

  		if (!PageUptodate(page)) {

  			error = -EIO;

  			goto failed;

  		}

  		wait_on_page_writeback(page);

  		if (shmem_should_replace_page(page, gfp)) {
  			error = shmem_replace_page(&page, gfp, info, index);
  			if (error)
  				goto failed;

  		}

  		error = mem_cgroup_charge_file(page, current->mm,

  						gfp & GFP_RECLAIM_MASK);

  		if (!error) {

  			error = shmem_add_to_page_cache(page, mapping, index,
  						gfp, swp_to_radix_entry(swap));

  			/*
  			 * We already confirmed swap under page lock, and make
  			 * no memory allocation here, so usually no possibility
  			 * of error; but free_swap_and_cache() only trylocks a
  			 * page, so it is just possible that the entry has been
  			 * truncated or holepunched since swap was confirmed.
  			 * shmem_undo_range() will have done some of the
  			 * unaccounting, now delete_from_swap_cache() will do
  			 * the rest (including mem_cgroup_uncharge_swapcache).
  			 * Reset swap.val? No, leave it so "failed" goes back to
  			 * "repeat": reading a hole and writing should succeed.
  			 */
  			if (error)
  				delete_from_swap_cache(page);

  		}

  		if (error)
  			goto failed;
  
  		spin_lock(&info->lock);

  		info->swapped--;

  		shmem_recalc_inode(inode);

  		spin_unlock(&info->lock);

  
  		delete_from_swap_cache(page);

  		set_page_dirty(page);
  		swap_free(swap);

  	} else {
  		if (shmem_acct_block(info->flags)) {
  			error = -ENOSPC;
  			goto failed;

  		}

  		if (sbinfo->max_blocks) {

  			if (percpu_counter_compare(&sbinfo->used_blocks,

  						sbinfo->max_blocks) >= 0) {
  				error = -ENOSPC;
  				goto unacct;
  			}

  			percpu_counter_inc(&sbinfo->used_blocks);

  		}

  		page = shmem_alloc_page(gfp, info, index);
  		if (!page) {
  			error = -ENOMEM;
  			goto decused;

  		}

  		SetPageSwapBacked(page);
  		__set_page_locked(page);

  		error = mem_cgroup_charge_file(page, current->mm,

  						gfp & GFP_RECLAIM_MASK);

  		if (error)
  			goto decused;

  		error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);

  		if (!error) {
  			error = shmem_add_to_page_cache(page, mapping, index,
  							gfp, NULL);
  			radix_tree_preload_end();
  		}
  		if (error) {
  			mem_cgroup_uncharge_cache_page(page);
  			goto decused;
  		}

  		lru_cache_add_anon(page);
  
  		spin_lock(&info->lock);

  		info->alloced++;

  		inode->i_blocks += BLOCKS_PER_PAGE;
  		shmem_recalc_inode(inode);

  		spin_unlock(&info->lock);

  		alloced = true;

  		/*

  		 * Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
  		 */
  		if (sgp == SGP_FALLOC)
  			sgp = SGP_WRITE;
  clear:
  		/*
  		 * Let SGP_WRITE caller clear ends if write does not fill page;
  		 * but SGP_FALLOC on a page fallocated earlier must initialize
  		 * it now, lest undo on failure cancel our earlier guarantee.

  		 */
  		if (sgp != SGP_WRITE) {
  			clear_highpage(page);
  			flush_dcache_page(page);
  			SetPageUptodate(page);
  		}

  		if (sgp == SGP_DIRTY)

  			set_page_dirty(page);

  	}

  	/* Perhaps the file has been truncated since we checked */

  	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&

  	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
  		error = -EINVAL;

  		if (alloced)
  			goto trunc;
  		else
  			goto failed;

  	}

  	*pagep = page;
  	return 0;

  	/*

  	 * Error recovery.

  	 */

  trunc:

  	info = SHMEM_I(inode);

  	ClearPageDirty(page);
  	delete_from_page_cache(page);
  	spin_lock(&info->lock);
  	info->alloced--;
  	inode->i_blocks -= BLOCKS_PER_PAGE;

  	spin_unlock(&info->lock);

  decused:

  	sbinfo = SHMEM_SB(inode->i_sb);

  	if (sbinfo->max_blocks)
  		percpu_counter_add(&sbinfo->used_blocks, -1);
  unacct:
  	shmem_unacct_blocks(info->flags, 1);
  failed:

  	if (swap.val && error != -EINVAL &&
  	    !shmem_confirm_swap(mapping, index, swap))
  		error = -EEXIST;
  unlock:

  	if (page) {

  		unlock_page(page);

  		page_cache_release(page);

  	}
  	if (error == -ENOSPC && !once++) {
  		info = SHMEM_I(inode);
  		spin_lock(&info->lock);
  		shmem_recalc_inode(inode);
  		spin_unlock(&info->lock);

  		goto repeat;

  	}

  	if (error == -EEXIST)	/* from above or from radix_tree_insert */

  		goto repeat;
  	return error;

  }

  static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)

  {

  	struct inode *inode = file_inode(vma->vm_file);

  	int error;

  	int ret = VM_FAULT_LOCKED;

  	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);

  	if (error)
  		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);

  	if (ret & VM_FAULT_MAJOR) {
  		count_vm_event(PGMAJFAULT);
  		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
  	}

  	return ret;

  }

  #ifdef CONFIG_NUMA

  static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)

  {

  	struct inode *inode = file_inode(vma->vm_file);

  	return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol);

  }

  static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
  					  unsigned long addr)

  {

  	struct inode *inode = file_inode(vma->vm_file);

  	pgoff_t index;

  	index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
  	return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index);

  }
  #endif
  
  int shmem_lock(struct file *file, int lock, struct user_struct *user)
  {

  	struct inode *inode = file_inode(file);

  	struct shmem_inode_info *info = SHMEM_I(inode);
  	int retval = -ENOMEM;
  
  	spin_lock(&info->lock);
  	if (lock && !(info->flags & VM_LOCKED)) {
  		if (!user_shm_lock(inode->i_size, user))
  			goto out_nomem;
  		info->flags |= VM_LOCKED;

  		mapping_set_unevictable(file->f_mapping);

  	}
  	if (!lock && (info->flags & VM_LOCKED) && user) {
  		user_shm_unlock(inode->i_size, user);
  		info->flags &= ~VM_LOCKED;

  		mapping_clear_unevictable(file->f_mapping);

  	}
  	retval = 0;

  out_nomem:
  	spin_unlock(&info->lock);
  	return retval;
  }

  static int shmem_mmap(struct file *file, struct vm_area_struct *vma)

  {
  	file_accessed(file);
  	vma->vm_ops = &shmem_vm_ops;
  	return 0;
  }

  static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,

  				     umode_t mode, dev_t dev, unsigned long flags)

  {
  	struct inode *inode;
  	struct shmem_inode_info *info;
  	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);

  	if (shmem_reserve_inode(sb))
  		return NULL;

  
  	inode = new_inode(sb);
  	if (inode) {

  		inode->i_ino = get_next_ino();

  		inode_init_owner(inode, dir, mode);

  		inode->i_blocks = 0;

  		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
  		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;

  		inode->i_generation = get_seconds();

  		info = SHMEM_I(inode);
  		memset(info, 0, (char *)inode - (char *)info);
  		spin_lock_init(&info->lock);

  		info->flags = flags & VM_NORESERVE;

  		INIT_LIST_HEAD(&info->swaplist);

  		simple_xattrs_init(&info->xattrs);

  		cache_no_acl(inode);

  
  		switch (mode & S_IFMT) {
  		default:

  			inode->i_op = &shmem_special_inode_operations;

  			init_special_inode(inode, mode, dev);
  			break;
  		case S_IFREG:

  			inode->i_mapping->a_ops = &shmem_aops;

  			inode->i_op = &shmem_inode_operations;
  			inode->i_fop = &shmem_file_operations;

  			mpol_shared_policy_init(&info->policy,
  						 shmem_get_sbmpol(sbinfo));

  			break;
  		case S_IFDIR:

  			inc_nlink(inode);

  			/* Some things misbehave if size == 0 on a directory */
  			inode->i_size = 2 * BOGO_DIRENT_SIZE;
  			inode->i_op = &shmem_dir_inode_operations;
  			inode->i_fop = &simple_dir_operations;
  			break;
  		case S_IFLNK:
  			/*
  			 * Must not load anything in the rbtree,
  			 * mpol_free_shared_policy will not be called.
  			 */

  			mpol_shared_policy_init(&info->policy, NULL);

  			break;
  		}

  	} else
  		shmem_free_inode(sb);

  	return inode;
  }

  bool shmem_mapping(struct address_space *mapping)
  {
  	return mapping->backing_dev_info == &shmem_backing_dev_info;
  }

  #ifdef CONFIG_TMPFS

  static const struct inode_operations shmem_symlink_inode_operations;

  static const struct inode_operations shmem_short_symlink_operations;

  #ifdef CONFIG_TMPFS_XATTR
  static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
  #else
  #define shmem_initxattrs NULL
  #endif

  static int

  shmem_write_begin(struct file *file, struct address_space *mapping,
  			loff_t pos, unsigned len, unsigned flags,
  			struct page **pagep, void **fsdata)

  {

  	struct inode *inode = mapping->host;
  	pgoff_t index = pos >> PAGE_CACHE_SHIFT;

  	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
  }
  
  static int
  shmem_write_end(struct file *file, struct address_space *mapping,
  			loff_t pos, unsigned len, unsigned copied,
  			struct page *page, void *fsdata)
  {
  	struct inode *inode = mapping->host;

  	if (pos + copied > inode->i_size)
  		i_size_write(inode, pos + copied);

  	if (!PageUptodate(page)) {
  		if (copied < PAGE_CACHE_SIZE) {
  			unsigned from = pos & (PAGE_CACHE_SIZE - 1);
  			zero_user_segments(page, 0, from,
  					from + copied, PAGE_CACHE_SIZE);
  		}
  		SetPageUptodate(page);
  	}

  	set_page_dirty(page);

  	unlock_page(page);

  	page_cache_release(page);

  	return copied;

  }

  static ssize_t shmem_file_aio_read(struct kiocb *iocb,
  		const struct iovec *iov, unsigned long nr_segs, loff_t pos)

  {

  	struct file *file = iocb->ki_filp;
  	struct inode *inode = file_inode(file);

  	struct address_space *mapping = inode->i_mapping;

  	pgoff_t index;
  	unsigned long offset;

  	enum sgp_type sgp = SGP_READ;

  	int error = 0;

  	ssize_t retval;
  	size_t count;
  	loff_t *ppos = &iocb->ki_pos;
  	struct iov_iter iter;
  
  	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
  	if (retval)
  		return retval;
  	iov_iter_init(&iter, iov, nr_segs, count, 0);

  
  	/*
  	 * Might this read be for a stacking filesystem?  Then when reading
  	 * holes of a sparse file, we actually need to allocate those pages,
  	 * and even mark them dirty, so it cannot exceed the max_blocks limit.
  	 */
  	if (segment_eq(get_fs(), KERNEL_DS))
  		sgp = SGP_DIRTY;

  
  	index = *ppos >> PAGE_CACHE_SHIFT;
  	offset = *ppos & ~PAGE_CACHE_MASK;
  
  	for (;;) {
  		struct page *page = NULL;

  		pgoff_t end_index;
  		unsigned long nr, ret;

  		loff_t i_size = i_size_read(inode);
  
  		end_index = i_size >> PAGE_CACHE_SHIFT;
  		if (index > end_index)
  			break;
  		if (index == end_index) {
  			nr = i_size & ~PAGE_CACHE_MASK;
  			if (nr <= offset)
  				break;
  		}

  		error = shmem_getpage(inode, index, &page, sgp, NULL);
  		if (error) {
  			if (error == -EINVAL)
  				error = 0;

  			break;
  		}

  		if (page)
  			unlock_page(page);

  
  		/*
  		 * We must evaluate after, since reads (unlike writes)

  		 * are called without i_mutex protection against truncate

  		 */
  		nr = PAGE_CACHE_SIZE;
  		i_size = i_size_read(inode);
  		end_index = i_size >> PAGE_CACHE_SHIFT;
  		if (index == end_index) {
  			nr = i_size & ~PAGE_CACHE_MASK;
  			if (nr <= offset) {
  				if (page)
  					page_cache_release(page);
  				break;
  			}
  		}
  		nr -= offset;
  
  		if (page) {
  			/*
  			 * If users can be writing to this page using arbitrary
  			 * virtual addresses, take care about potential aliasing
  			 * before reading the page on the kernel side.
  			 */
  			if (mapping_writably_mapped(mapping))
  				flush_dcache_page(page);
  			/*
  			 * Mark the page accessed if we read the beginning.
  			 */
  			if (!offset)
  				mark_page_accessed(page);

  		} else {

  			page = ZERO_PAGE(0);

  			page_cache_get(page);
  		}

  
  		/*
  		 * Ok, we have the page, and it's up-to-date, so
  		 * now we can copy it to user space...

  		 */

  		ret = copy_page_to_iter(page, offset, nr, &iter);
  		retval += ret;

  		offset += ret;
  		index += offset >> PAGE_CACHE_SHIFT;
  		offset &= ~PAGE_CACHE_MASK;
  
  		page_cache_release(page);

  		if (!iov_iter_count(&iter))

  			break;

  		if (ret < nr) {
  			error = -EFAULT;
  			break;
  		}

  		cond_resched();
  	}
  
  	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;

  	file_accessed(file);
  	return retval ? retval : error;

  }

  static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
  				struct pipe_inode_info *pipe, size_t len,
  				unsigned int flags)
  {
  	struct address_space *mapping = in->f_mapping;

  	struct inode *inode = mapping->host;

  	unsigned int loff, nr_pages, req_pages;
  	struct page *pages[PIPE_DEF_BUFFERS];
  	struct partial_page partial[PIPE_DEF_BUFFERS];
  	struct page *page;
  	pgoff_t index, end_index;
  	loff_t isize, left;
  	int error, page_nr;
  	struct splice_pipe_desc spd = {
  		.pages = pages,
  		.partial = partial,

  		.nr_pages_max = PIPE_DEF_BUFFERS,

  		.flags = flags,
  		.ops = &page_cache_pipe_buf_ops,
  		.spd_release = spd_release_page,
  	};

  	isize = i_size_read(inode);

  	if (unlikely(*ppos >= isize))
  		return 0;
  
  	left = isize - *ppos;
  	if (unlikely(left < len))
  		len = left;
  
  	if (splice_grow_spd(pipe, &spd))
  		return -ENOMEM;
  
  	index = *ppos >> PAGE_CACHE_SHIFT;
  	loff = *ppos & ~PAGE_CACHE_MASK;
  	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

  	nr_pages = min(req_pages, spd.nr_pages_max);

  	spd.nr_pages = find_get_pages_contig(mapping, index,
  						nr_pages, spd.pages);
  	index += spd.nr_pages;

  	error = 0;

  	while (spd.nr_pages < nr_pages) {

  		error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL);
  		if (error)
  			break;
  		unlock_page(page);

  		spd.pages[spd.nr_pages++] = page;
  		index++;
  	}

  	index = *ppos >> PAGE_CACHE_SHIFT;
  	nr_pages = spd.nr_pages;
  	spd.nr_pages = 0;

  	for (page_nr = 0; page_nr < nr_pages; page_nr++) {
  		unsigned int this_len;
  
  		if (!len)
  			break;

  		this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
  		page = spd.pages[page_nr];

  		if (!PageUptodate(page) || page->mapping != mapping) {

  			error = shmem_getpage(inode, index, &page,
  							SGP_CACHE, NULL);
  			if (error)

  				break;

  			unlock_page(page);
  			page_cache_release(spd.pages[page_nr]);
  			spd.pages[page_nr] = page;

  		}

  
  		isize = i_size_read(inode);