shmem.c

/*
 * 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/uio.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 <linux/syscalls.h>
#include <linux/fcntl.h>
#include <uapi/linux/memfd.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 communicates with shmem_fault or shmem_writepage 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 {
	wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
	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));
}

static inline int shmem_reacct_size(unsigned long flags,
		loff_t oldsize, loff_t newsize)
{
	if (!(flags & VM_NORESERVE)) {
		if (VM_ACCT(newsize) > VM_ACCT(oldsize))
			return security_vm_enough_memory_mm(current->mm,
					VM_ACCT(newsize) - VM_ACCT(oldsize));
		else if (VM_ACCT(newsize) < VM_ACCT(oldsize))
			vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize));
	}
	return 0;
}

/*
 * ... 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 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, 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;
		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);
		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;
	while (index < end) {
		cond_resched();

		pvec.nr = find_get_entries(mapping, index,
				min(end - index, (pgoff_t)PAGEVEC_SIZE),
				pvec.pages, indices);
		if (!pvec.nr) {
			/* If all gone or hole-punch or unfalloc, we're done */
			if (index == start || end != -1)
				break;
			/* But if truncating, restart to make sure all gone */
			index = start;
			continue;
		}
		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;
				if (shmem_free_swap(mapping, index, page)) {
					/* Swap was replaced by page: retry */
					index--;
					break;
				}
				nr_swaps_freed++;
				continue;
			}

			lock_page(page);
			if (!unfalloc || !PageUptodate(page)) {
				if (page->mapping == mapping) {
					VM_BUG_ON_PAGE(PageWriteback(page), page);
					truncate_inode_page(mapping, page);
				} else {
					/* Page was replaced by swap: retry */
					unlock_page(page);
					index--;
					break;
				}
			}
			unlock_page(page);
		}
		pagevec_remove_exceptionals(&pvec);
		pagevec_release(&pvec);
		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;
	struct shmem_inode_info *info = SHMEM_I(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;

		/* protected by i_mutex */
		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
			return -EPERM;

		if (newsize != oldsize) {
			error = shmem_reacct_size(SHMEM_I(inode)->flags,
					oldsize, newsize);
			if (error)
				return error;
			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 -EAGAIN;	/* tell shmem_unuse we found nothing */

	/*
	 * 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,
						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);
		}
	}
	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;
	struct mem_cgroup *memcg;
	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_try_charge(page, current->mm, GFP_KERNEL, &memcg);
	if (error)
		goto out;
	/* No radix_tree_preload: swap entry keeps a place for page in tree */
	error = -EAGAIN;

	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)
			error = shmem_unuse_inode(info, swap, &page);
		else
			list_del_init(&info->swaplist);
		cond_resched();
		if (error != -EAGAIN)
			break;
		/* found nothing in this: move on to search the next */
	}
	mutex_unlock(&shmem_swaplist_mutex);

	if (error) {
		if (error != -ENOMEM)
			error = 0;
		mem_cgroup_cancel_charge(page, memcg);
	} else
		mem_cgroup_commit_charge(page, memcg, true);
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;

	/*
	 * Our 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 &&
			    !shmem_falloc->waitq &&
			    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);
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);
	}