Merge tag 'for-f2fs-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches:
   - remount_fs callback function
   - restore parent inode number to enhance the fsync performance
   - xattr security labels
   - reduce the number of redundant lock/unlock data pages
   - avoid frequent write_inode calls

  The other minor bug fixes are as follows.
   - endian conversion bugs
   - various bugs in the roll-forward recovery routine"

* tag 'for-f2fs-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (56 commits)
  f2fs: fix to recover i_size from roll-forward
  f2fs: remove the unused argument "sbi" of func destroy_fsync_dnodes()
  f2fs: remove reusing any prefree segments
  f2fs: code cleanup and simplify in func {find/add}_gc_inode
  f2fs: optimize the init_dirty_segmap function
  f2fs: fix an endian conversion bug detected by sparse
  f2fs: fix crc endian conversion
  f2fs: add remount_fs callback support
  f2fs: recover wrong pino after checkpoint during fsync
  f2fs: optimize do_write_data_page()
  f2fs: make locate_dirty_segment() as static
  f2fs: remove unnecessary parameter "offset" from __add_sum_entry()
  f2fs: avoid freqeunt write_inode calls
  f2fs: optimise the truncate_data_blocks_range() range
  f2fs: use the F2FS specific flags in f2fs_ioctl()
  f2fs: sync dir->i_size with its block allocation
  f2fs: fix i_blocks translation on various types of files
  f2fs: set sb->s_fs_info before calling parse_options()
  f2fs: support xattr security labels
  f2fs: fix iget/iput of dir during recovery
  ...

18 files changed, 741 insertions, 447 deletions

diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index fd27e7e6326..e06e0995e00 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -51,3 +51,15 @@ config F2FS_FS_POSIX_ACL
 	  Linux website <http://acl.bestbits.at/>.
 
 	  If you don't know what Access Control Lists are, say N
+
+config F2FS_FS_SECURITY
+	bool "F2FS Security Labels"
+	depends on F2FS_FS_XATTR
+	help
+	  Security labels provide an access control facility to support Linux
+	  Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO
+	  Linux. This option enables an extended attribute handler for file
+	  security labels in the f2fs filesystem, so that it requires enabling
+	  the extended attribute support in advance.
+
+	  If you are not using a security module, say N.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 44abc2f286e..b7826ec1b47 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -250,7 +250,7 @@ static int f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 		}
 	}
 
-	error = f2fs_setxattr(inode, name_index, "", value, size);
+	error = f2fs_setxattr(inode, name_index, "", value, size, NULL);
 
 	kfree(value);
 	if (!error)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b1de01da1a4..66a6b85a51d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -357,8 +357,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	unsigned long blk_size = sbi->blocksize;
 	struct f2fs_checkpoint *cp_block;
 	unsigned long long cur_version = 0, pre_version = 0;
-	unsigned int crc = 0;
 	size_t crc_offset;
+	__u32 crc = 0;
 
 	/* Read the 1st cp block in this CP pack */
 	cp_page_1 = get_meta_page(sbi, cp_addr);
@@ -369,7 +369,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp1;
 
-	crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
@@ -384,7 +384,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp2;
 
-	crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
@@ -450,13 +450,30 @@ fail_no_cp:
 	return -EINVAL;
 }
 
-void set_dirty_dir_page(struct inode *inode, struct page *page)
+static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct list_head *head = &sbi->dir_inode_list;
-	struct dir_inode_entry *new;
 	struct list_head *this;
 
+	list_for_each(this, head) {
+		struct dir_inode_entry *entry;
+		entry = list_entry(this, struct dir_inode_entry, list);
+		if (entry->inode == inode)
+			return -EEXIST;
+	}
+	list_add_tail(&new->list, head);
+#ifdef CONFIG_F2FS_STAT_FS
+	sbi->n_dirty_dirs++;
+#endif
+	return 0;
+}
+
+void set_dirty_dir_page(struct inode *inode, struct page *page)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct dir_inode_entry *new;
+
 	if (!S_ISDIR(inode->i_mode))
 		return;
 retry:
@@ -469,23 +486,31 @@ retry:
 	INIT_LIST_HEAD(&new->list);
 
 	spin_lock(&sbi->dir_inode_lock);
-	list_for_each(this, head) {
-		struct dir_inode_entry *entry;
-		entry = list_entry(this, struct dir_inode_entry, list);
-		if (entry->inode == inode) {
-			kmem_cache_free(inode_entry_slab, new);
-			goto out;
-		}
-	}
-	list_add_tail(&new->list, head);
-	sbi->n_dirty_dirs++;
+	if (__add_dirty_inode(inode, new))
+		kmem_cache_free(inode_entry_slab, new);
 
-	BUG_ON(!S_ISDIR(inode->i_mode));
-out:
 	inc_page_count(sbi, F2FS_DIRTY_DENTS);
 	inode_inc_dirty_dents(inode);
 	SetPagePrivate(page);
+	spin_unlock(&sbi->dir_inode_lock);
+}
 
+void add_dirty_dir_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct dir_inode_entry *new;
+retry:
+	new = kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
+	if (!new) {
+		cond_resched();
+		goto retry;
+	}
+	new->inode = inode;
+	INIT_LIST_HEAD(&new->list);
+
+	spin_lock(&sbi->dir_inode_lock);
+	if (__add_dirty_inode(inode, new))
+		kmem_cache_free(inode_entry_slab, new);
 	spin_unlock(&sbi->dir_inode_lock);
 }
 
@@ -499,8 +524,10 @@ void remove_dirty_dir_inode(struct inode *inode)
 		return;
 
 	spin_lock(&sbi->dir_inode_lock);
-	if (atomic_read(&F2FS_I(inode)->dirty_dents))
-		goto out;
+	if (atomic_read(&F2FS_I(inode)->dirty_dents)) {
+		spin_unlock(&sbi->dir_inode_lock);
+		return;
+	}
 
 	list_for_each(this, head) {
 		struct dir_inode_entry *entry;
@@ -508,12 +535,38 @@ void remove_dirty_dir_inode(struct inode *inode)
 		if (entry->inode == inode) {
 			list_del(&entry->list);
 			kmem_cache_free(inode_entry_slab, entry);
+#ifdef CONFIG_F2FS_STAT_FS
 			sbi->n_dirty_dirs--;
+#endif
+			break;
+		}
+	}
+	spin_unlock(&sbi->dir_inode_lock);
+
+	/* Only from the recovery routine */
+	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
+		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
+		iput(inode);
+	}
+}
+
+struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct list_head *head = &sbi->dir_inode_list;
+	struct list_head *this;
+	struct inode *inode = NULL;
+
+	spin_lock(&sbi->dir_inode_lock);
+	list_for_each(this, head) {
+		struct dir_inode_entry *entry;
+		entry = list_entry(this, struct dir_inode_entry, list);
+		if (entry->inode->i_ino == ino) {
+			inode = entry->inode;
 			break;
 		}
 	}
-out:
 	spin_unlock(&sbi->dir_inode_lock);
+	return inode;
 }
 
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -595,7 +648,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	block_t start_blk;
 	struct page *cp_page;
 	unsigned int data_sum_blocks, orphan_blocks;
-	unsigned int crc32 = 0;
+	__u32 crc32 = 0;
 	void *kaddr;
 	int i;
 
@@ -664,8 +717,8 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
 	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
-	*(__le32 *)((unsigned char *)ckpt +
-				le32_to_cpu(ckpt->checksum_offset))
+	*((__le32 *)((unsigned char *)ckpt +
+				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
 
 	start_blk = __start_cp_addr(sbi);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ce11d9a92ae..035f9a345cd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -68,7 +68,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 					struct buffer_head *bh_result)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
+#ifdef CONFIG_F2FS_STAT_FS
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+#endif
 	pgoff_t start_fofs, end_fofs;
 	block_t start_blkaddr;
 
@@ -78,7 +80,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		return 0;
 	}
 
+#ifdef CONFIG_F2FS_STAT_FS
 	sbi->total_hit_ext++;
+#endif
 	start_fofs = fi->ext.fofs;
 	end_fofs = fi->ext.fofs + fi->ext.len - 1;
 	start_blkaddr = fi->ext.blk_addr;
@@ -96,7 +100,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		else
 			bh_result->b_size = UINT_MAX;
 
+#ifdef CONFIG_F2FS_STAT_FS
 		sbi->read_hit_ext++;
+#endif
 		read_unlock(&fi->ext.ext_lock);
 		return 1;
 	}
@@ -199,7 +205,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	if (dn.data_blkaddr == NEW_ADDR)
 		return ERR_PTR(-EINVAL);
 
-	page = grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -233,18 +239,23 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct page *page;
 	int err;
 
+repeat:
+	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-	if (err)
+	if (err) {
+		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
+	}
 	f2fs_put_dnode(&dn);
 
-	if (dn.data_blkaddr == NULL_ADDR)
+	if (dn.data_blkaddr == NULL_ADDR) {
+		f2fs_put_page(page, 1);
 		return ERR_PTR(-ENOENT);
-repeat:
-	page = grab_cache_page(mapping, index);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	}
 
 	if (PageUptodate(page))
 		return page;
@@ -274,9 +285,10 @@ repeat:
  *
  * Also, caller should grab and release a mutex by calling mutex_lock_op() and
  * mutex_unlock_op().
+ * Note that, npage is set only by make_empty_dir.
  */
-struct page *get_new_data_page(struct inode *inode, pgoff_t index,
-						bool new_i_size)
+struct page *get_new_data_page(struct inode *inode,
+		struct page *npage, pgoff_t index, bool new_i_size)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct address_space *mapping = inode->i_mapping;
@@ -284,18 +296,20 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
 	struct dnode_of_data dn;
 	int err;
 
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	set_new_dnode(&dn, inode, npage, npage, 0);
 	err = get_dnode_of_data(&dn, index, ALLOC_NODE);
 	if (err)
 		return ERR_PTR(err);
 
 	if (dn.data_blkaddr == NULL_ADDR) {
 		if (reserve_new_block(&dn)) {
-			f2fs_put_dnode(&dn);
+			if (!npage)
+				f2fs_put_dnode(&dn);
 			return ERR_PTR(-ENOSPC);
 		}
 	}
-	f2fs_put_dnode(&dn);
+	if (!npage)
+		f2fs_put_dnode(&dn);
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
@@ -325,6 +339,8 @@ repeat:
 	if (new_i_size &&
 		i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
 		i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
+		/* Only the directory inode sets new_i_size */
+		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
 		mark_inode_dirty_sync(inode);
 	}
 	return page;
@@ -481,8 +497,9 @@ int do_write_data_page(struct page *page)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (old_blk_addr != NEW_ADDR && !is_cold_data(page) &&
-				need_inplace_update(inode)) {
+	if (unlikely(old_blk_addr != NEW_ADDR &&
+			!is_cold_data(page) &&
+			need_inplace_update(inode))) {
 		rewrite_data_page(F2FS_SB(inode->i_sb), page,
 						old_blk_addr);
 	} else {
@@ -684,6 +701,27 @@ err:
 	return err;
 }
 
+static int f2fs_write_end(struct file *file,
+			struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned copied,
+			struct page *page, void *fsdata)
+{
+	struct inode *inode = page->mapping->host;
+
+	SetPageUptodate(page);
+	set_page_dirty(page);
+
+	if (pos + copied > i_size_read(inode)) {
+		i_size_write(inode, pos + copied);
+		mark_inode_dirty(inode);
+		update_inode_page(inode);
+	}
+
+	unlock_page(page);
+	page_cache_release(page);
+	return copied;
+}
+
 static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
 {
@@ -741,7 +779,7 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.writepage	= f2fs_write_data_page,
 	.writepages	= f2fs_write_data_pages,
 	.write_begin	= f2fs_write_begin,
-	.write_end	= nobh_write_end,
+	.write_end	= f2fs_write_end,
 	.set_page_dirty	= f2fs_set_data_page_dirty,
 	.invalidatepage	= f2fs_invalidate_data_page,
 	.releasepage	= f2fs_release_data_page,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 8d9943786c3..0d6c6aafb23 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -175,12 +175,12 @@ get_cache:
 
 static int stat_show(struct seq_file *s, void *v)
 {
-	struct f2fs_stat_info *si, *next;
+	struct f2fs_stat_info *si;
 	int i = 0;
 	int j;
 
 	mutex_lock(&f2fs_stat_mutex);
-	list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
 		char devname[BDEVNAME_SIZE];
 
 		update_general_status(si->sbi);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 600bb5efe60..9d1cd423450 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -13,6 +13,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "acl.h"
+#include "xattr.h"
 
 static unsigned long dir_blocks(struct inode *inode)
 {
@@ -215,9 +216,9 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 
 struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
 {
-	struct page *page = NULL;
-	struct f2fs_dir_entry *de = NULL;
-	struct f2fs_dentry_block *dentry_blk = NULL;
+	struct page *page;
+	struct f2fs_dir_entry *de;
+	struct f2fs_dentry_block *dentry_blk;
 
 	page = get_lock_data_page(dir, 0);
 	if (IS_ERR(page))
@@ -264,15 +265,10 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_put_page(page, 1);
 }
 
-void init_dent_inode(const struct qstr *name, struct page *ipage)
+static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_node *rn;
 
-	if (IS_ERR(ipage))
-		return;
-
-	wait_on_page_writeback(ipage);
-
 	/* copy name info. to this inode page */
 	rn = (struct f2fs_node *)page_address(ipage);
 	rn->i.i_namelen = cpu_to_le32(name->len);
@@ -280,14 +276,15 @@ void init_dent_inode(const struct qstr *name, struct page *ipage)
 	set_page_dirty(ipage);
 }
 
-static int make_empty_dir(struct inode *inode, struct inode *parent)
+static int make_empty_dir(struct inode *inode,
+		struct inode *parent, struct page *page)
 {
 	struct page *dentry_page;
 	struct f2fs_dentry_block *dentry_blk;
 	struct f2fs_dir_entry *de;
 	void *kaddr;
 
-	dentry_page = get_new_data_page(inode, 0, true);
+	dentry_page = get_new_data_page(inode, page, 0, true);
 	if (IS_ERR(dentry_page))
 		return PTR_ERR(dentry_page);
 
@@ -317,63 +314,76 @@ static int make_empty_dir(struct inode *inode, struct inode *parent)
 	return 0;
 }
 
-static int init_inode_metadata(struct inode *inode,
+static struct page *init_inode_metadata(struct inode *inode,
 		struct inode *dir, const struct qstr *name)
 {
+	struct page *page;
+	int err;
+
 	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
-		int err;
-		err = new_inode_page(inode, name);
-		if (err)
-			return err;
+		page = new_inode_page(inode, name);
+		if (IS_ERR(page))
+			return page;
 
 		if (S_ISDIR(inode->i_mode)) {
-			err = make_empty_dir(inode, dir);
-			if (err) {
-				remove_inode_page(inode);
-				return err;
-			}
+			err = make_empty_dir(inode, dir, page);
+			if (err)
+				goto error;
 		}
 
 		err = f2fs_init_acl(inode, dir);
-		if (err) {
-			remove_inode_page(inode);
-			return err;
-		}
+		if (err)
+			goto error;
+
+		err = f2fs_init_security(inode, dir, name, page);
+		if (err)
+			goto error;
+
+		wait_on_page_writeback(page);
 	} else {
-		struct page *ipage;
-		ipage = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
-		if (IS_ERR(ipage))
-			return PTR_ERR(ipage);
-		set_cold_node(inode, ipage);
-		init_dent_inode(name, ipage);
-		f2fs_put_page(ipage, 1);
+		page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+		if (IS_ERR(page))
+			return page;
+
+		wait_on_page_writeback(page);
+		set_cold_node(inode, page);
 	}
+
+	init_dent_inode(name, page);
+
+	/*
+	 * This file should be checkpointed during fsync.
+	 * We lost i_pino from now on.
+	 */
 	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+		file_lost_pino(inode);
 		inc_nlink(inode);
-		update_inode_page(inode);
 	}
-	return 0;
+	return page;
+
+error:
+	f2fs_put_page(page, 1);
+	remove_inode_page(inode);
+	return ERR_PTR(err);
 }
 
 static void update_parent_metadata(struct inode *dir, struct inode *inode,
 						unsigned int current_depth)
 {
-	bool need_dir_update = false;
-
 	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
 		if (S_ISDIR(inode->i_mode)) {
 			inc_nlink(dir);
-			need_dir_update = true;
+			set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
 		}
 		clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
 	}
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	if (F2FS_I(dir)->i_current_depth != current_depth) {
 		F2FS_I(dir)->i_current_depth = current_depth;
-		need_dir_update = true;
+		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
 	}
 
-	if (need_dir_update)
+	if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR))
 		update_inode_page(dir);
 	else
 		mark_inode_dirty(dir);
@@ -423,6 +433,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *in
 	struct page *dentry_page = NULL;
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	int slots = GET_DENTRY_SLOTS(namelen);
+	struct page *page;
 	int err = 0;
 	int i;
 
@@ -448,7 +459,7 @@ start:
 	bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
-		dentry_page = get_new_data_page(dir, block, true);
+		dentry_page = get_new_data_page(dir, NULL, block, true);
 		if (IS_ERR(dentry_page))
 			return PTR_ERR(dentry_page);
 
@@ -465,12 +476,13 @@ start:
 	++level;
 	goto start;
 add_dentry:
-	err = init_inode_metadata(inode, dir, name);
-	if (err)
-		goto fail;
-
 	wait_on_page_writeback(dentry_page);
 
+	page = init_inode_metadata(inode, dir, name);
+	if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+		goto fail;
+	}
 	de = &dentry_blk->dentry[bit_pos];
 	de->hash_code = dentry_hash;
 	de->name_len = cpu_to_le16(namelen);
@@ -481,11 +493,14 @@ add_dentry:
 		test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
 	set_page_dirty(dentry_page);
 
-	update_parent_metadata(dir, inode, current_depth);
-
-	/* update parent inode number before releasing dentry page */
+	/* we don't need to mark_inode_dirty now */
 	F2FS_I(inode)->i_pino = dir->i_ino;
+	update_inode(inode, page);
+	f2fs_put_page(page, 1);
+
+	update_parent_metadata(dir, inode, current_depth);
 fail:
+	clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
 	return err;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 20aab02f2a4..467d42d65c4 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -37,21 +37,35 @@
 		typecheck(unsigned long long, b) &&			\
 		((long long)((a) - (b)) > 0))
 
-typedef u64 block_t;
+typedef u32 block_t;	/*
+			 * should not change u32, since it is the on-disk block
+			 * address format, __le32.
+			 */
 typedef u32 nid_t;
 
 struct f2fs_mount_info {
 	unsigned int	opt;
 };
 
-static inline __u32 f2fs_crc32(void *buff, size_t len)
+#define CRCPOLY_LE 0xedb88320
+
+static inline __u32 f2fs_crc32(void *buf, size_t len)
 {
-	return crc32_le(F2FS_SUPER_MAGIC, buff, len);
+	unsigned char *p = (unsigned char *)buf;
+	__u32 crc = F2FS_SUPER_MAGIC;
+	int i;
+
+	while (len--) {
+		crc ^= *p++;
+		for (i = 0; i < 8; i++)
+			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+	}
+	return crc;
 }
 
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buff, size_t buff_size)
+static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
 {
-	return f2fs_crc32(buff, buff_size) == blk_crc;
+	return f2fs_crc32(buf, buf_size) == blk_crc;
 }
 
 /*
@@ -148,7 +162,7 @@ struct extent_info {
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
  */
 #define FADVISE_COLD_BIT	0x01
-#define FADVISE_CP_BIT		0x02
+#define FADVISE_LOST_PINO_BIT	0x02
 
 struct f2fs_inode_info {
 	struct inode vfs_inode;		/* serve a vfs inode */
@@ -369,7 +383,6 @@ struct f2fs_sb_info {
 	/* for directory inode management */
 	struct list_head dir_inode_list;	/* dir inode list */
 	spinlock_t dir_inode_lock;		/* for dir inode list lock */
-	unsigned int n_dirty_dirs;		/* # of dir inodes */
 
 	/* basic file system units */
 	unsigned int log_sectors_per_block;	/* log2 sectors per block */
@@ -406,12 +419,15 @@ struct f2fs_sb_info {
 	 * for stat information.
 	 * one is for the LFS mode, and the other is for the SSR mode.
 	 */
+#ifdef CONFIG_F2FS_STAT_FS
 	struct f2fs_stat_info *stat_info;	/* FS status information */
 	unsigned int segment_count[2];		/* # of allocated segments */
 	unsigned int block_count[2];		/* # of allocated blocks */
-	unsigned int last_victim[2];		/* last victim segment # */
 	int total_hit_ext, read_hit_ext;	/* extent cache hit ratio */
 	int bg_gc;				/* background gc calls */
+	unsigned int n_dirty_dirs;		/* # of dir inodes */
+#endif
+	unsigned int last_victim[2];		/* last victim segment # */
 	spinlock_t stat_lock;			/* lock for stat operations */
 };
 
@@ -495,9 +511,17 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 
 static inline void mutex_lock_all(struct f2fs_sb_info *sbi)
 {
-	int i = 0;
-	for (; i < NR_GLOBAL_LOCKS; i++)
-		mutex_lock(&sbi->fs_lock[i]);
+	int i;
+
+	for (i = 0; i < NR_GLOBAL_LOCKS; i++) {
+		/*
+		 * This is the only time we take multiple fs_lock[]
+		 * instances; the order is immaterial since we
+		 * always hold cp_mutex, which serializes multiple
+		 * such operations.
+		 */
+		mutex_lock_nest_lock(&sbi->fs_lock[i], &sbi->cp_mutex);
+	}
 }
 
 static inline void mutex_unlock_all(struct f2fs_sb_info *sbi)
@@ -843,9 +867,12 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
 /* used for f2fs_inode_info->flags */
 enum {
 	FI_NEW_INODE,		/* indicate newly allocated inode */
+	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
 	FI_INC_LINK,		/* need to increment i_nlink */
 	FI_ACL_MODE,		/* indicate acl mode */
 	FI_NO_ALLOC,		/* should not allocate any blocks */
+	FI_UPDATE_DIR,		/* should update inode block for consistency */
+	FI_DELAY_IPUT,		/* used for the recovery */
 };
 
 static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -878,14 +905,21 @@ static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
 	return 0;
 }
 
+static inline int f2fs_readonly(struct super_block *sb)
+{
+	return sb->s_flags & MS_RDONLY;
+}
+
 /*
  * file.c
  */
 int f2fs_sync_file(struct file *, loff_t, loff_t, int);
 void truncate_data_blocks(struct dnode_of_data *);
 void f2fs_truncate(struct inode *);
+int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 int f2fs_setattr(struct dentry *, struct iattr *);
 int truncate_hole(struct inode *, pgoff_t, pgoff_t);
+int truncate_data_blocks_range(struct dnode_of_data *, int);
 long f2fs_ioctl(struct file *, unsigned int, unsigned long);
 long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
 
@@ -913,7 +947,6 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
 ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
 void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
 				struct page *, struct inode *);
-void init_dent_inode(const struct qstr *, struct page *);
 int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
 void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
 int f2fs_make_empty(struct inode *, struct inode *);
@@ -948,8 +981,8 @@ void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
 int remove_inode_page(struct inode *);
-int new_inode_page(struct inode *, const struct qstr *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int);
+struct page *new_inode_page(struct inode *, const struct qstr *);
+struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
 void ra_node_page(struct f2fs_sb_info *, nid_t);
 struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_node_page_ra(struct page *, int);
@@ -974,7 +1007,6 @@ void destroy_node_manager_caches(void);
  */
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
-void locate_dirty_segment(struct f2fs_sb_info *, unsigned int);
 void clear_prefree_segments(struct f2fs_sb_info *);
 int npages_for_summary_flush(struct f2fs_sb_info *);
 void allocate_new_segments(struct f2fs_sb_info *);
@@ -1011,7 +1043,9 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
 int recover_orphan_inodes(struct f2fs_sb_info *);
 int get_valid_checkpoint(struct f2fs_sb_info *);
 void set_dirty_dir_page(struct inode *, struct page *);
+void add_dirty_dir_inode(struct inode *);
 void remove_dirty_dir_inode(struct inode *);
+struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool);
 void init_orphan_info(struct f2fs_sb_info *);
@@ -1025,7 +1059,7 @@ int reserve_new_block(struct dnode_of_data *);
 void update_extent_cache(block_t, struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
-struct page *get_new_data_page(struct inode *, pgoff_t, bool);
+struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int);
 int do_write_data_page(struct page *);
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 1cae864f8df..d2d2b7dbdcc 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -63,9 +63,10 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	f2fs_put_dnode(&dn);
 	mutex_unlock_op(sbi, ilock);
 
+	file_update_time(vma->vm_file);
 	lock_page(page);
 	if (page->mapping != inode->i_mapping ||
-			page_offset(page) >= i_size_read(inode) ||
+			page_offset(page) > i_size_read(inode) ||
 			!PageUptodate(page)) {
 		unlock_page(page);
 		err = -EFAULT;
@@ -76,10 +77,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	 * check to see if the page is mapped already (no holes)
 	 */
 	if (PageMappedToDisk(page))
-		goto out;
-
-	/* fill the page */
-	wait_on_page_writeback(page);
+		goto mapped;
 
 	/* page is wholly or partially inside EOF */
 	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
@@ -90,7 +88,9 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	set_page_dirty(page);
 	SetPageUptodate(page);
 
-	file_update_time(vma->vm_file);
+mapped:
+	/* fill the page */
+	wait_on_page_writeback(page);
 out:
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(err);
@@ -102,6 +102,24 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.remap_pages	= generic_file_remap_pages,
 };
 
+static int get_parent_ino(struct inode *inode, nid_t *pino)
+{
+	struct dentry *dentry;
+
+	inode = igrab(inode);
+	dentry = d_find_any_alias(inode);
+	iput(inode);
+	if (!dentry)
+		return 0;
+
+	inode = igrab(dentry->d_parent->d_inode);
+	dput(dentry);
+
+	*pino = inode->i_ino;
+	iput(inode);
+	return 1;
+}
+
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
@@ -114,7 +132,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		.for_reclaim = 0,
 	};
 
-	if (inode->i_sb->s_flags & MS_RDONLY)
+	if (f2fs_readonly(inode->i_sb))
 		return 0;
 
 	trace_f2fs_sync_file_enter(inode);
@@ -134,7 +152,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
 		need_cp = true;
-	else if (is_cp_file(inode))
+	else if (file_wrong_pino(inode))
 		need_cp = true;
 	else if (!space_for_roll_forward(sbi))
 		need_cp = true;
@@ -142,11 +160,23 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		need_cp = true;
 
 	if (need_cp) {
+		nid_t pino;
+
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
+		if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
+					get_parent_ino(inode, &pino)) {
+			F2FS_I(inode)->i_pino = pino;
+			file_got_pino(inode);
+			mark_inode_dirty_sync(inode);
+			ret = f2fs_write_inode(inode, NULL);
+			if (ret)
+				goto out;
+		}
 	} else {
 		/* if there is no written node page, write its inode page */
 		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
+			mark_inode_dirty_sync(inode);
 			ret = f2fs_write_inode(inode, NULL);
 			if (ret)
 				goto out;
@@ -168,7 +198,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 {
 	int nr_free = 0, ofs = dn->ofs_in_node;
 	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
@@ -185,10 +215,10 @@ static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 
 		update_extent_cache(NULL_ADDR, dn);
 		invalidate_blocks(sbi, blkadd