->clear_inode() and ->delete_inode() are gone; ->evict_inode() should
be used instead. It gets called whenever the inode is evicted, whether it has
remaining links or not. Caller does *not* evict the pagecache or inode-associated
-metadata buffers; getting rid of those is responsibility of method, as it had
-been for ->delete_inode(). Caller makes sure async writeback cannot be running
-for the inode while (or after) ->evict_inode() is called.
+metadata buffers; the method has to use truncate_inode_pages_final() to get rid
+of those. Caller makes sure async writeback cannot be running for the inode while
+(or after) ->evict_inode() is called.
->drop_inode() returns int now; it's called on final iput() with
inode->i_lock held and it returns true if filesystems wants the inode to be
cl_sync_file_range(inode, 0, OBD_OBJECT_EOF,
CL_FSYNC_DISCARD, 1);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
/* Workaround for LU-118 */
if (inode->i_data.nrpages) {
{
struct v9fs_inode *v9inode = V9FS_I(inode);
- truncate_inode_pages(inode->i_mapping, 0);
+ truncate_inode_pages_final(inode->i_mapping);
clear_inode(inode);
filemap_fdatawrite(inode->i_mapping);
{
unsigned long cache_page;
pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
afs_give_up_callback(vnode);
dprintf("ino=%08lx\n", ino);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
invalidate_inode_buffers(inode);
clear_inode(inode);
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
- if (mapping->nrpages == 0)
+ if (mapping->nrpages == 0 && mapping->nrshadows == 0)
return;
invalidate_bh_lrus();
{
struct block_device *bdev = &BDEV_I(inode)->bdev;
struct list_head *p;
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
invalidate_inode_buffers(inode); /* is it needed here? */
clear_inode(inode);
spin_lock(&bdev_lock);
struct rb_node *node;
ASSERT(inode->i_state & I_FREEING);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
write_lock(&map_tree->lock);
while (!RB_EMPTY_ROOT(&map_tree->map)) {
static void
cifs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
cifs_fscache_release_inode_cookie(inode);
}
static void coda_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
coda_cache_clear_inode(inode);
}
*/
static void ecryptfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
iput(ecryptfs_inode_to_lower(inode));
}
struct ore_io_state *ios;
int ret;
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
/* TODO: should do better here */
if (inode->i_nlink || is_bad_inode(inode))
dquot_drop(inode);
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
sb_start_intwrite(inode->i_sb);
log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
ext3_discard_reservation(inode);
rsv = ei->i_block_alloc_info;
jbd2_complete_transaction(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
goto no_delete;
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
if (is_bad_inode(inode))
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
trace_f2fs_evict_inode(inode);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
static void fat_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
fat_truncate_blocks(inode, 0);
void
vxfs_evict_inode(struct inode *ip)
{
- truncate_inode_pages(&ip->i_data, 0);
+ truncate_inode_pages_final(&ip->i_data);
clear_inode(ip);
call_rcu(&ip->i_rcu, vxfs_i_callback);
}
static void fuse_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (inode->i_sb->s_flags & MS_ACTIVE) {
struct fuse_conn *fc = get_fuse_conn(inode);
fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
out:
/* Case 3 starts here */
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
gfs2_rs_delete(ip, NULL);
gfs2_ordered_del_inode(ip);
clear_inode(inode);
void hfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) {
HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
static void hfsplus_evict_inode(struct inode *inode)
{
hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (HFSPLUS_IS_RSRC(inode)) {
HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
static void hostfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (HOSTFS_I(inode)->fd != -1) {
close_file(&HOSTFS_I(inode)->fd);
void hpfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (!inode->i_nlink) {
hpfs_lock(inode->i_sb);
*/
spin_lock_irq(&inode->i_data.tree_lock);
BUG_ON(inode->i_data.nrpages);
+ BUG_ON(inode->i_data.nrshadows);
spin_unlock_irq(&inode->i_data.tree_lock);
BUG_ON(!list_empty(&inode->i_data.private_list));
BUG_ON(!(inode->i_state & I_FREEING));
if (op->evict_inode) {
op->evict_inode(inode);
} else {
- if (inode->i_data.nrpages)
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
}
if (S_ISBLK(inode->i_mode) && inode->i_bdev)
jffs2_dbg(1, "%s(): ino #%lu mode %o\n",
__func__, inode->i_ino, inode->i_mode);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
jffs2_do_clear_inode(c, f);
}
dquot_initialize(inode);
if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (test_cflag(COMMIT_Freewmap, inode))
jfs_free_zero_link(inode);
dquot_free_inode(inode);
}
} else {
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
}
clear_inode(inode);
dquot_drop(inode);
{
struct kernfs_node *kn = inode->i_private;
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
kernfs_put(kn);
}
do_delete_inode(inode);
}
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
/* Cheaper version of write_inode. All changes are concealed in
static void minix_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
minix_truncate(inode);
static void
ncp_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (S_ISDIR(inode->i_mode)) {
void nfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
nfs_clear_inode(inode);
}
*/
static void nfs4_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
pnfs_return_layout(inode);
pnfs_destroy_layout(NFS_I(inode));
int ret;
if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
- if (inode->i_data.nrpages)
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
nilfs_clear_inode(inode);
return;
}
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
- if (inode->i_data.nrpages)
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
/* TODO: some of the following operations may fail. */
nilfs_truncate_bmap(ii, 0);
{
ntfs_inode *ni = NTFS_I(vi);
- truncate_inode_pages(&vi->i_data, 0);
+ truncate_inode_pages_final(&vi->i_data);
clear_inode(vi);
#ifdef NTFS_RW
(unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
if (sync_data)
filemap_write_and_wait(inode->i_mapping);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
}
static void ocfs2_delete_inode(struct inode *inode)
(OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) {
ocfs2_delete_inode(inode);
} else {
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
}
ocfs2_clear_inode(inode);
}
*/
static void omfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (inode->i_nlink)
const struct proc_ns_operations *ns_ops;
void *ns;
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
/* Stop tracking associated processes */
if (!inode->i_nlink && !is_bad_inode(inode))
dquot_initialize(inode);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (inode->i_nlink)
goto no_delete;
static void sysv_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
sysv_truncate(inode);
dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
ubifs_assert(!atomic_read(&inode->i_count));
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (inode->i_nlink)
goto done;
want_delete = 1;
udf_setsize(inode, 0);
udf_update_inode(inode, IS_SYNC(inode));
- } else
- truncate_inode_pages(&inode->i_data, 0);
+ }
+ truncate_inode_pages_final(&inode->i_data);
invalidate_inode_buffers(inode);
clear_inode(inode);
if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB &&
if (!inode->i_nlink && !is_bad_inode(inode))
want_delete = 1;
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
if (want_delete) {
loff_t old_i_size;
/*UFS_I(inode)->i_dtime = CURRENT_TIME;*/
trace_xfs_evict_inode(ip);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
XFS_STATS_INC(vn_rele);
XFS_STATS_INC(vn_remove);
struct mutex i_mmap_mutex; /* protect tree, count, list */
/* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
+ unsigned long nrshadows; /* number of shadow entries */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
extern void truncate_inode_pages(struct address_space *, loff_t);
extern void truncate_inode_pages_range(struct address_space *,
loff_t lstart, loff_t lend);
+extern void truncate_inode_pages_final(struct address_space *);
/* generic vm_area_ops exported for stackable file systems */
extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */
AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */
AS_BALLOON_MAP = __GFP_BITS_SHIFT + 4, /* balloon page special map */
+ AS_EXITING = __GFP_BITS_SHIFT + 5, /* final truncate in progress */
};
static inline void mapping_set_error(struct address_space *mapping, int error)
return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
}
+static inline void mapping_set_exiting(struct address_space *mapping)
+{
+ set_bit(AS_EXITING, &mapping->flags);
+}
+
+static inline int mapping_exiting(struct address_space *mapping)
+{
+ return test_bit(AS_EXITING, &mapping->flags);
+}
+
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page);
+extern void __delete_from_page_cache(struct page *page, void *shadow);
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
/*
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
+static void page_cache_tree_delete(struct address_space *mapping,
+ struct page *page, void *shadow)
+{
+ if (shadow) {
+ void **slot;
+
+ slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+ radix_tree_replace_slot(slot, shadow);
+ mapping->nrshadows++;
+ /*
+ * Make sure the nrshadows update is committed before
+ * the nrpages update so that final truncate racing
+ * with reclaim does not see both counters 0 at the
+ * same time and miss a shadow entry.
+ */
+ smp_wmb();
+ } else
+ radix_tree_delete(&mapping->page_tree, page->index);
+ mapping->nrpages--;
+}
+
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
* is safe. The caller must hold the mapping's tree_lock.
*/
-void __delete_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page, void *shadow)
{
struct address_space *mapping = page->mapping;
else
cleancache_invalidate_page(mapping, page);
- radix_tree_delete(&mapping->page_tree, page->index);
+ page_cache_tree_delete(mapping, page, shadow);
+
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
- mapping->nrpages--;
+
__dec_zone_page_state(page, NR_FILE_PAGES);
if (PageSwapBacked(page))
__dec_zone_page_state(page, NR_SHMEM);
freepage = mapping->a_ops->freepage;
spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(page);
+ __delete_from_page_cache(page, NULL);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
new->index = offset;
spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(old);
+ __delete_from_page_cache(old, NULL);
error = radix_tree_insert(&mapping->page_tree, offset, new);
BUG_ON(error);
mapping->nrpages++;
if (!radix_tree_exceptional_entry(p))
return -EEXIST;
radix_tree_replace_slot(slot, page);
+ mapping->nrshadows--;
mapping->nrpages++;
return 0;
}
* without the tree itself locked. These unlocked entries
* need verification under the tree lock.
*/
- radix_tree_delete_item(&mapping->page_tree, index, entry);
+ if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry)
+ mapping->nrshadows--;
spin_unlock_irq(&mapping->tree_lock);
}
int i;
cleancache_invalidate_inode(mapping);
- if (mapping->nrpages == 0)
+ if (mapping->nrpages == 0 && mapping->nrshadows == 0)
return;
/* Offsets within partial pages */
EXPORT_SYMBOL(truncate_inode_pages);
/**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+ unsigned long nrshadows;
+ unsigned long nrpages;
+
+ /*
+ * Page reclaim can not participate in regular inode lifetime
+ * management (can't call iput()) and thus can race with the
+ * inode teardown. Tell it when the address space is exiting,
+ * so that it does not install eviction information after the
+ * final truncate has begun.
+ */
+ mapping_set_exiting(mapping);
+
+ /*
+ * When reclaim installs eviction entries, it increases
+ * nrshadows first, then decreases nrpages. Make sure we see
+ * this in the right order or we might miss an entry.
+ */
+ nrpages = mapping->nrpages;
+ smp_rmb();
+ nrshadows = mapping->nrshadows;
+
+ if (nrpages || nrshadows) {
+ /*
+ * As truncation uses a lockless tree lookup, cycle
+ * the tree lock to make sure any ongoing tree
+ * modification that does not see AS_EXITING is
+ * completed before starting the final truncate.
+ */
+ spin_lock_irq(&mapping->tree_lock);
+ spin_unlock_irq(&mapping->tree_lock);
+
+ truncate_inode_pages(mapping, 0);
+ }
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
+/**
* invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
* @mapping: the address_space which holds the pages to invalidate
* @start: the offset 'from' which to invalidate
goto failed;
BUG_ON(page_has_private(page));
- __delete_from_page_cache(page);
+ __delete_from_page_cache(page, NULL);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
freepage = mapping->a_ops->freepage;
- __delete_from_page_cache(page);
+ __delete_from_page_cache(page, NULL);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);