mm + fs: store shadow entries in page cache

Reclaim will be leaving shadow entries in the page cache radix tree upon
evicting the real page.  As those pages are found from the LRU, an
iput() can lead to the inode being freed concurrently.  At this point,
reclaim must no longer install shadow pages because the inode freeing
code needs to ensure the page tree is really empty.

Add an address_space flag, AS_EXITING, that the inode freeing code sets
under the tree lock before doing the final truncate.  Reclaim will check
for this flag before installing shadow pages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/filesystems/porting

@@ -295,9 +295,9 @@ in the beginning of ->setattr unconditionally.
 	->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

drivers/staging/lustre/lustre/llite/llite_lib.c

@@ -1877,7 +1877,7 @@ void ll_delete_inode(struct inode *inode)
 		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) {

fs/9p/vfs_inode.c

@@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode)
 {
 	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);
 

fs/affs/inode.c

@@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode)
 {
 	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;

fs/afs/inode.c

@@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode)
 
 	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);

fs/bfs/inode.c

@@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode)
 
 	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);
 

fs/block_dev.c

@@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	invalidate_bh_lrus();
@@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode)
 {
 	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);

fs/btrfs/inode.c

@@ -4593,7 +4593,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 	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)) {

fs/cifs/cifsfs.c

@@ -286,7 +286,7 @@ cifs_destroy_inode(struct inode *inode)
 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);
 }

fs/coda/inode.c

@@ -250,7 +250,7 @@ static void coda_put_super(struct super_block *sb)
 
 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);
 }

fs/ecryptfs/super.c

@@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
  */
 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));
 }

fs/exofs/inode.c

@@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *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))

fs/ext2/inode.c

@@ -78,7 +78,7 @@ void ext2_evict_inode(struct 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);

fs/ext3/inode.c

@@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode)
 		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;

fs/ext4/inode.c

@@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode)
 			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;
@@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode)
 
 	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))

fs/f2fs/inode.c

@@ -260,7 +260,7 @@ void f2fs_evict_inode(struct 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))

fs/fat/inode.c

@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(fat_build_inode);
 
 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);

fs/freevxfs/vxfs_inode.c

@@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head)
 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);
 }

fs/fuse/inode.c

@@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode)
 
 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/gfs2/super.c

@@ -1558,7 +1558,7 @@ static void gfs2_evict_inode(struct inode *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);

fs/hfs/inode.c

@@ -547,7 +547,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 
 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;

fs/hfsplus/super.c

@@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode,
 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;

fs/hostfs/hostfs_kern.c

@@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 
 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);

fs/hpfs/inode.c

@@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode)
 
 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);

fs/inode.c

@@ -503,6 +503,7 @@ void clear_inode(struct inode *inode)
 	 */
 	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));
@@ -548,8 +549,7 @@ static void evict(struct inode *inode)
 	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)

fs/jffs2/fs.c

@@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode)
 
 	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);
 }

fs/jfs/inode.c

@@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode)
 		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);
@@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *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);

fs/kernfs/inode.c

@@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *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);
 }

fs/logfs/readwrite.c

@@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode)
 			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

fs/minix/inode.c

@@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data);
 
 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);

fs/ncpfs/inode.c

@@ -296,7 +296,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 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)) {

fs/nfs/inode.c

@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 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);
 }

fs/nfs/nfs4super.c

@@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
  */
 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));

fs/nilfs2/inode.c

@@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *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);

fs/ntfs/inode.c

@@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi)
 {
 	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

fs/ocfs2/inode.c

@@ -964,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode,
 		(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)
@@ -1181,7 +1181,7 @@ void ocfs2_evict_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);
 }

fs/omfs/inode.c

@@ -183,7 +183,7 @@ int omfs_sync_inode(struct 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)