Merge tag 'for-f2fs-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "The major work includes fixing and enhancing the existing extent_cache
  feature, which has been well settling down so far and now it becomes a
  default mount option accordingly.

  Also, this version newly registers a f2fs memory shrinker to reclaim
  several objects consumed by a couple of data structures in order to
  avoid memory pressures.

  Another new feature is to add ioctl(F2FS_GARBAGE_COLLECT) which
  triggers a cleaning job explicitly by users.

  Most of the other patches are to fix bugs occurred in the corner cases
  across the whole code area"

* tag 'for-f2fs-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (85 commits)
  f2fs: upset segment_info repair
  f2fs: avoid accessing NULL pointer in f2fs_drop_largest_extent
  f2fs: update extent tree in batches
  f2fs: fix to release inode correctly
  f2fs: handle f2fs_truncate error correctly
  f2fs: avoid unneeded initializing when converting inline dentry
  f2fs: atomically set inode->i_flags
  f2fs: fix wrong pointer access during try_to_free_nids
  f2fs: use __GFP_NOFAIL to avoid infinite loop
  f2fs: lookup neighbor extent nodes for merging later
  f2fs: split __insert_extent_tree_ret for readability
  f2fs: kill dead code in __insert_extent_tree
  f2fs: adjust showing of extent cache stat
  f2fs: add largest/cached stat in extent cache
  f2fs: fix incorrect mapping for bmap
  f2fs: add annotation for space utilization of regular/inline dentry
  f2fs: fix to update cached_en of extent tree properly
  f2fs: fix typo
  f2fs: check the node block address of newly allocated nid
  f2fs: go out for insert_inode_locked failure
  ...

26 files changed, 1903 insertions, 1026 deletions

diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e9e750e59efc..e2d5105b7214 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -143,7 +143,9 @@ fastboot               This option is used when a system wants to reduce mount
 extent_cache           Enable an extent cache based on rb-tree, it can cache
                        as many as extent which map between contiguous logical
                        address and physical address per inode, resulting in
-                       increasing the cache hit ratio.
+                       increasing the cache hit ratio. Set by default.
+noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+                       the above extent_cache mount option.
 noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 73db93cc55fd..205cd5d687e4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4416,6 +4416,7 @@ F:	include/linux/fscache*.h
 F2FS FILE SYSTEM
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
 M:	Changman Lee <cm224.lee@samsung.com>
+R:	Chao Yu <chao2.yu@samsung.com>
 L:	linux-f2fs-devel@lists.sourceforge.net
 W:	http://en.wikipedia.org/wiki/F2FS
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
@@ -4424,6 +4425,7 @@ F:	Documentation/filesystems/f2fs.txt
 F:	Documentation/ABI/testing/sysfs-fs-f2fs
 F:	fs/f2fs/
 F:	include/linux/f2fs_fs.h
+F:	include/trace/events/f2fs.h
 
 FUJITSU FR-V (FRV) PORT
 M:	David Howells <dhowells@redhat.com>
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index c629762005bc..b0a9dc929f88 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -45,7 +45,7 @@ config F2FS_FS_POSIX_ACL
 	default y
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
-	  gourps beyond the owner/group/world scheme.
+	  groups beyond the owner/group/world scheme.
 
 	  To learn more about Access Control Lists, visit the POSIX ACLs for
 	  Linux website <http://acl.bestbits.at/>.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 396be1a39e55..08e101ed914c 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o
 
 f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o inline.o
 f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
+f2fs-y		+= shrinker.o extent_cache.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b70bbe1a6a8c..c5a38e352a80 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -69,14 +69,24 @@ repeat:
 
 	fio.page = page;
 
-	if (f2fs_submit_page_bio(&fio))
+	if (f2fs_submit_page_bio(&fio)) {
+		f2fs_put_page(page, 1);
 		goto repeat;
+	}
 
 	lock_page(page);
 	if (unlikely(page->mapping != mapping)) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+
+	/*
+	 * if there is any IO error when accessing device, make our filesystem
+	 * readonly and make sure do not write checkpoint with non-uptodate
+	 * meta page.
+	 */
+	if (unlikely(!PageUptodate(page)))
+		f2fs_stop_checkpoint(sbi);
 out:
 	return page;
 }
@@ -326,26 +336,18 @@ const struct address_space_operations f2fs_meta_aops = {
 static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	struct inode_management *im = &sbi->im[type];
-	struct ino_entry *e;
+	struct ino_entry *e, *tmp;
+
+	tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
 retry:
-	if (radix_tree_preload(GFP_NOFS)) {
-		cond_resched();
-		goto retry;
-	}
+	radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
 
 	spin_lock(&im->ino_lock);
-
 	e = radix_tree_lookup(&im->ino_root, ino);
 	if (!e) {
-		e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
-		if (!e) {
-			spin_unlock(&im->ino_lock);
-			radix_tree_preload_end();
-			goto retry;
-		}
+		e = tmp;
 		if (radix_tree_insert(&im->ino_root, ino, e)) {
 			spin_unlock(&im->ino_lock);
-			kmem_cache_free(ino_entry_slab, e);
 			radix_tree_preload_end();
 			goto retry;
 		}
@@ -358,6 +360,9 @@ retry:
 	}
 	spin_unlock(&im->ino_lock);
 	radix_tree_preload_end();
+
+	if (e != tmp)
+		kmem_cache_free(ino_entry_slab, tmp);
 }
 
 static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -458,24 +463,34 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 	__remove_ino_entry(sbi, ino, ORPHAN_INO);
 }
 
-static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	struct inode *inode = f2fs_iget(sbi->sb, ino);
-	f2fs_bug_on(sbi, IS_ERR(inode));
+	struct inode *inode;
+
+	inode = f2fs_iget(sbi->sb, ino);
+	if (IS_ERR(inode)) {
+		/*
+		 * there should be a bug that we can't find the entry
+		 * to orphan inode.
+		 */
+		f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
+		return PTR_ERR(inode);
+	}
+
 	clear_nlink(inode);
 
 	/* truncate all the data during iput */
 	iput(inode);
+	return 0;
 }
 
-void recover_orphan_inodes(struct f2fs_sb_info *sbi)
+int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 {
 	block_t start_blk, orphan_blocks, i, j;
+	int err;
 
 	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
-		return;
-
-	set_sbi_flag(sbi, SBI_POR_DOING);
+		return 0;
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
 	orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
@@ -489,14 +504,17 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
 		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
 			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
-			recover_orphan_inode(sbi, ino);
+			err = recover_orphan_inode(sbi, ino);
+			if (err) {
+				f2fs_put_page(page, 1);
+				return err;
+			}
 		}
 		f2fs_put_page(page, 1);
 	}
 	/* clear Orphan Flag */
 	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
-	clear_sbi_flag(sbi, SBI_POR_DOING);
-	return;
+	return 0;
 }
 
 static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -504,7 +522,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	struct list_head *head;
 	struct f2fs_orphan_block *orphan_blk = NULL;
 	unsigned int nentries = 0;
-	unsigned short index;
+	unsigned short index = 1;
 	unsigned short orphan_blocks;
 	struct page *page = NULL;
 	struct ino_entry *orphan = NULL;
@@ -512,11 +530,6 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 
 	orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
 
-	for (index = 0; index < orphan_blocks; index++)
-		grab_meta_page(sbi, start_blk + index);
-
-	index = 1;
-
 	/*
 	 * we don't need to do spin_lock(&im->ino_lock) here, since all the
 	 * orphan inode operations are covered under f2fs_lock_op().
@@ -527,12 +540,10 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	/* loop for each orphan inode entry and write them in Jornal block */
 	list_for_each_entry(orphan, head, list) {
 		if (!page) {
-			page = find_get_page(META_MAPPING(sbi), start_blk++);
-			f2fs_bug_on(sbi, !page);
+			page = grab_meta_page(sbi, start_blk++);
 			orphan_blk =
 				(struct f2fs_orphan_block *)page_address(page);
 			memset(orphan_blk, 0, sizeof(*orphan_blk));
-			f2fs_put_page(page, 0);
 		}
 
 		orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
@@ -704,7 +715,8 @@ void update_dirty_page(struct inode *inode, struct page *page)
 	struct inode_entry *new;
 	int ret = 0;
 
-	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
+	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+			!S_ISLNK(inode->i_mode))
 		return;
 
 	if (!S_ISDIR(inode->i_mode)) {
@@ -892,12 +904,15 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u32 crc32 = 0;
 	int i;
 	int cp_payload_blks = __cp_payload(sbi);
+	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
+	bool invalidate = false;
 
 	/*
 	 * This avoids to conduct wrong roll-forward operations and uses
 	 * metapages, so should be called prior to sync_meta_pages below.
 	 */
-	discard_next_dnode(sbi, NEXT_FREE_BLKADDR(sbi, curseg));
+	if (discard_next_dnode(sbi, discard_blk))
+		invalidate = true;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1026,6 +1041,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* wait for previous submitted meta pages writeback */
 	wait_on_all_pages_writeback(sbi);
 
+	/*
+	 * invalidate meta page which is used temporarily for zeroing out
+	 * block at the end of warm node chain.
+	 */
+	if (invalidate)
+		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
+								discard_blk);
+
 	release_dirty_inode(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
index 95b8f936f00b..9f77de2ef317 100644
--- a/fs/f2fs/crypto_key.c
+++ b/fs/f2fs/crypto_key.c
@@ -92,8 +92,7 @@ static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
 	if (!ci)
 		return;
 
-	if (ci->ci_keyring_key)
-		key_put(ci->ci_keyring_key);
+	key_put(ci->ci_keyring_key);
 	crypto_free_ablkcipher(ci->ci_ctfm);
 	kmem_cache_free(f2fs_crypt_info_cachep, ci);
 }
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index c414d49aa2de..a82abe921b89 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -14,6 +14,7 @@
 #include <linux/mpage.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
+#include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/prefetch.h>
@@ -26,9 +27,6 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
-static struct kmem_cache *extent_tree_slab;
-static struct kmem_cache *extent_node_slab;
-
 static void f2fs_read_end_io(struct bio *bio)
 {
 	struct bio_vec *bvec;
@@ -92,8 +90,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 {
 	struct bio *bio;
 
-	/* No failure on bio allocation */
-	bio = bio_alloc(GFP_NOIO, npages);
+	bio = f2fs_bio_alloc(npages);
 
 	bio->bi_bdev = sbi->sb->s_bdev;
 	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
@@ -158,7 +155,6 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
-		f2fs_put_page(page, 1);
 		return -EFAULT;
 	}
 
@@ -266,645 +262,17 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 	return err;
 }
 
-static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs,
-							struct extent_info *ei)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	pgoff_t start_fofs, end_fofs;
-	block_t start_blkaddr;
-
-	read_lock(&fi->ext_lock);
-	if (fi->ext.len == 0) {
-		read_unlock(&fi->ext_lock);
-		return false;
-	}
-
-	stat_inc_total_hit(inode->i_sb);
-
-	start_fofs = fi->ext.fofs;
-	end_fofs = fi->ext.fofs + fi->ext.len - 1;
-	start_blkaddr = fi->ext.blk;
-
-	if (pgofs >= start_fofs && pgofs <= end_fofs) {
-		*ei = fi->ext;
-		stat_inc_read_hit(inode->i_sb);
-		read_unlock(&fi->ext_lock);
-		return true;
-	}
-	read_unlock(&fi->ext_lock);
-	return false;
-}
-
-static bool update_extent_info(struct inode *inode, pgoff_t fofs,
-								block_t blkaddr)
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	pgoff_t start_fofs, end_fofs;
-	block_t start_blkaddr, end_blkaddr;
-	int need_update = true;
-
-	write_lock(&fi->ext_lock);
-
-	start_fofs = fi->ext.fofs;
-	end_fofs = fi->ext.fofs + fi->ext.len - 1;
-	start_blkaddr = fi->ext.blk;
-	end_blkaddr = fi->ext.blk + fi->ext.len - 1;
-
-	/* Drop and initialize the matched extent */
-	if (fi->ext.len == 1 && fofs == start_fofs)
-		fi->ext.len = 0;
-
-	/* Initial extent */
-	if (fi->ext.len == 0) {
-		if (blkaddr != NULL_ADDR) {
-			fi->ext.fofs = fofs;
-			fi->ext.blk = blkaddr;
-			fi->ext.len = 1;
-		}
-		goto end_update;
-	}
-
-	/* Front merge */
-	if (fofs == start_fofs - 1 && blkaddr == start_blkaddr - 1) {
-		fi->ext.fofs--;
-		fi->ext.blk--;
-		fi->ext.len++;
-		goto end_update;
-	}
-
-	/* Back merge */
-	if (fofs == end_fofs + 1 && blkaddr == end_blkaddr + 1) {
-		fi->ext.len++;
-		goto end_update;
-	}
-
-	/* Split the existing extent */
-	if (fi->ext.len > 1 &&
-		fofs >= start_fofs && fofs <= end_fofs) {
-		if ((end_fofs - fofs) < (fi->ext.len >> 1)) {
-			fi->ext.len = fofs - start_fofs;
-		} else {
-			fi->ext.fofs = fofs + 1;
-			fi->ext.blk = start_blkaddr + fofs - start_fofs + 1;
-			fi->ext.len -= fofs - start_fofs + 1;
-		}
-	} else {
-		need_update = false;
-	}
-
-	/* Finally, if the extent is very fragmented, let's drop the cache. */
-	if (fi->ext.len < F2FS_MIN_EXTENT_LEN) {
-		fi->ext.len = 0;
-		set_inode_flag(fi, FI_NO_EXTENT);
-		need_update = true;
-	}
-end_update:
-	write_unlock(&fi->ext_lock);
-	return need_update;
-}
-
-static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_info *ei,
-				struct rb_node *parent, struct rb_node **p)
-{
-	struct extent_node *en;
-
-	en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
-	if (!en)
-		return NULL;
-
-	en->ei = *ei;
-	INIT_LIST_HEAD(&en->list);
-
-	rb_link_node(&en->rb_node, parent, p);
-	rb_insert_color(&en->rb_node, &et->root);
-	et->count++;
-	atomic_inc(&sbi->total_ext_node);
-	return en;
-}
-
-static void __detach_extent_node(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_node *en)
-{
-	rb_erase(&en->rb_node, &et->root);
-	et->count--;
-	atomic_dec(&sbi->total_ext_node);
-
-	if (et->cached_en == en)
-		et->cached_en = NULL;
-}
-
-static struct extent_tree *__find_extent_tree(struct f2fs_sb_info *sbi,
-							nid_t ino)
-{
-	struct extent_tree *et;
-
-	down_read(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
-	if (!et) {
-		up_read(&sbi->extent_tree_lock);
-		return NULL;
-	}
-	atomic_inc(&et->refcount);
-	up_read(&sbi->extent_tree_lock);
-
-	return et;
-}
-
-static struct extent_tree *__grab_extent_tree(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et;
-	nid_t ino = inode->i_ino;
-
-	down_write(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
-	if (!et) {
-		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
-		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
-		memset(et, 0, sizeof(struct extent_tree));
-		et->ino = ino;
-		et->root = RB_ROOT;
-		et->cached_en = NULL;
-		rwlock_init(&et->lock);
-		atomic_set(&et->refcount, 0);
-		et->count = 0;
-		sbi->total_ext_tree++;
-	}
-	atomic_inc(&et->refcount);
-	up_write(&sbi->extent_tree_lock);
-
-	return et;
-}
-
-static struct extent_node *__lookup_extent_tree(struct extent_tree *et,
-							unsigned int fofs)
-{
-	struct rb_node *node = et->root.rb_node;
-	struct extent_node *en;
-
-	if (et->cached_en) {
-		struct extent_info *cei = &et->cached_en->ei;
-
-		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
-			return et->cached_en;
-	}
-
-	while (node) {
-		en = rb_entry(node, struct extent_node, rb_node);
-
-		if (fofs < en->ei.fofs) {
-			node = node->rb_left;
-		} else if (fofs >= en->ei.fofs + en->ei.len) {
-			node = node->rb_right;
-		} else {
-			et->cached_en = en;
-			return en;
-		}
-	}
-	return NULL;
-}
-
-static struct extent_node *__try_back_merge(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_node *en)
-{
-	struct extent_node *prev;
-	struct rb_node *node;
-
-	node = rb_prev(&en->rb_node);
-	if (!node)
-		return NULL;
-
-	prev = rb_entry(node, struct extent_node, rb_node);
-	if (__is_back_mergeable(&en->ei, &prev->ei)) {
-		en->ei.fofs = prev->ei.fofs;
-		en->ei.blk = prev->ei.blk;
-		en->ei.len += prev->ei.len;
-		__detach_extent_node(sbi, et, prev);
-		return prev;
-	}
-	return NULL;
-}
-
-static struct extent_node *__try_front_merge(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_node *en)
-{
-	struct extent_node *next;
-	struct rb_node *node;
-
-	node = rb_next(&en->rb_node);
-	if (!node)
-		return NULL;
-
-	next = rb_entry(node, struct extent_node, rb_node);
-	if (__is_front_mergeable(&en->ei, &next->ei)) {
-		en->ei.len += next->ei.len;
-		__detach_extent_node(sbi, et, next);
-		return next;
-	}
-	return NULL;
-}
-
-static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, struct extent_info *ei,
-				struct extent_node **den)
-{
-	struct rb_node **p = &et->root.rb_node;
-	struct rb_node *parent = NULL;
-	struct extent_node *en;
-
-	while (*p) {
-		parent = *p;
-		en = rb_entry(parent, struct extent_node, rb_node);
-
-		if (ei->fofs < en->ei.fofs) {
-			if (__is_front_mergeable(ei, &en->ei)) {
-				f2fs_bug_on(sbi, !den);
-				en->ei.fofs = ei->fofs;
-				en->ei.blk = ei->blk;
-				en->ei.len += ei->len;
-				*den = __try_back_merge(sbi, et, en);
-				return en;
-			}
-			p = &(*p)->rb_left;
-		} else if (ei->fofs >= en->ei.fofs + en->ei.len) {
-			if (__is_back_mergeable(ei, &en->ei)) {
-				f2fs_bug_on(sbi, !den);
-				en->ei.len += ei->len;
-				*den = __try_front_merge(sbi, et, en);
-				return en;
-			}
-			p = &(*p)->rb_right;
-		} else {
-			f2fs_bug_on(sbi, 1);
-		}
-	}
-
-	return __attach_extent_node(sbi, et, ei, parent, p);
-}
-
-static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et, bool free_all)
-{
-	struct rb_node *node, *next;
-	struct extent_node *en;
-	unsigned int count = et->count;
-
-	node = rb_first(&et->root);
-	while (node) {
-		next = rb_next(node);
-		en = rb_entry(node, struct extent_node, rb_node);
-
-		if (free_all) {
-			spin_lock(&sbi->extent_lock);
-			if (!list_empty(&en->list))
-				list_del_init(&en->list);
-			spin_unlock(&sbi->extent_lock);
-		}
-
-		if (free_all || list_empty(&en->list)) {
-			__detach_extent_node(sbi, et, en);
-			kmem_cache_free(extent_node_slab, en);
-		}
-		node = next;
-	}
-
-	return count - et->count;
-}
-
-static void f2fs_init_extent_tree(struct inode *inode,
-						struct f2fs_extent *i_ext)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et;
-	struct extent_node *en;
 	struct extent_info ei;
+	struct inode *inode = dn->inode;
 
-	if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
-		return;
-
-	et = __grab_extent_tree(inode);
-
-	write_lock(&et->lock);
-	if (et->count)
-		goto out;
-
-	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
-		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
-
-	en = __insert_extent_tree(sbi, et, &ei, NULL);
-	if (en) {
-		et->cached_en = en;
-
-		spin_lock(&sbi->extent_lock);
-		list_add_tail(&en->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
-	}
-out:
-	write_unlock(&et->lock);
-	atomic_dec(&et->refcount);
-}
-
-static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
-							struct extent_info *ei)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et;
-	struct extent_node *en;
-
-	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
-
-	et = __find_extent_tree(sbi, inode->i_ino);
-	if (!et)
-		return false;
-
-	read_lock(&et->lock);
-	en = __lookup_extent_tree(et, pgofs);
-	if (en) {
-		*ei = en->ei;
-		spin_lock(&sbi->extent_lock);
-		if (!list_empty(&en->list))
-			list_move_tail(&en->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
-		stat_inc_read_hit(sbi->sb);
-	}
-	stat_inc_total_hit(sbi->sb);
-	read_unlock(&et->lock);
-
-	trace_f2fs_lookup_extent_tree_end(inode, pgofs, en);
-
-	atomic_dec(&et->refcount);
-	return en ? true : false;
-}
-
-static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
-							block_t blkaddr)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et;
-	struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL;
-	struct extent_node *den = NULL;
-	struct extent_info ei, dei;
-	unsigned int endofs;
-
-	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
-
-	et = __grab_extent_tree(inode);
-
-	write_lock(&et->lock);
-
-	/* 1. lookup and remove existing extent info in cache */
-	en = __lookup_extent_tree(et, fofs);
-	if (!en)
-		goto update_extent;
-
-	dei = en->ei;
-	__detach_extent_node(sbi, et, en);
-
-	/* 2. if extent can be split more, split and insert the left part */
-	if (dei.len > 1) {
-		/*  insert left part of split extent into cache */
-		if (fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
-			set_extent_info(&ei, dei.fofs, dei.blk,
-							fofs - dei.fofs);
-			en1 = __insert_extent_tree(sbi, et, &ei, NULL);
-		}
-
-		/* insert right part of split extent into cache */
-		endofs = dei.fofs + dei.len - 1;
-		if (endofs - fofs >= F2FS_MIN_EXTENT_LEN) {
-			set_extent_info(&ei, fofs + 1,
-				fofs - dei.fofs + dei.blk, endofs - fofs);
-			en2 = __insert_extent_tree(sbi, et, &ei, NULL);
-		}
-	}
-
-update_extent:
-	/* 3. update extent in extent cache */
-	if (blkaddr) {
-		set_extent_info(&ei, fofs, blkaddr, 1);
-		en3 = __insert_extent_tree(sbi, et, &ei, &den);
-	}
-
-	/* 4. update in global extent list */
-	spin_lock(&sbi->extent_lock);
-	if (en && !list_empty(&en->list))
-		list_del(&en->list);
-	/*
-	 * en1 and en2 split from en, they will become more and more smaller
-	 * fragments after splitting several times. So if the length is smaller
-	 * than F2FS_MIN_EXTENT_LEN, we will not add them into extent tree.
-	 */
-	if (en1)
-		list_add_tail(&en1->list, &sbi->extent_list);
-	if (en2)
-		list_add_tail(&en2->list, &sbi->extent_list);
-	if (en3) {
-		if (list_empty(&en3->list))
-			list_add_tail(&en3->list, &sbi->extent_list);
-		else
-			list_move_tail(&en3->list, &sbi->extent_list);
-	}
-	if (den && !list_empty(&den->list))
-		list_del(&den->list);
-	spin_unlock(&sbi->extent_lock);
-
-	/* 5. release extent node */
-	if (en)
-		kmem_cache_free(extent_node_slab, en);
-	if (den)
-		kmem_cache_free(extent_node_slab, den);
-
-	write_unlock(&et->lock);
-	atomic_dec(&et->refcount);
-}
-
-void f2fs_preserve_extent_tree(struct inode *inode)
-{
-	struct extent_tree *et;
-	struct extent_info *ext = &F2FS_I(inode)->ext;
-	bool sync = false;
-
-	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
-		return;
-
-	et = __find_extent_tree(F2FS_I_SB(inode), inode->i_ino);
-	if (!et) {
-		if (ext->len) {
-			ext->len = 0;
-			update_inode_page(inode);
-		}
-		return;
-	}
-
-	read_lock(&et->lock);
-	if (et->count) {
-		struct extent_node *en;
-
-		if (et->cached_en) {
-			en = et->cached_en;
-		} else {
-			struct rb_node *node = rb_first(&et->root);
-
-			if (!node)
-				node = rb_last(&et->root);
-			en = rb_entry(node, struct extent_node, rb_node);
-		}
-
-		if (__is_extent_same(ext, &en->ei))
-			goto out;
-
-		*ext = en->ei;
-		sync = true;
-	} else if (ext->len) {
-		ext->len = 0;
-		sync = true;
-	}
-out:
-	read_unlock(&et->lock);
-	atomic_dec(&et->refcount);
-
-	if (sync)
-		update_inode_page(inode);
-}
-
-void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
-{
-	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
-	struct extent_node *en, *tmp;
-	unsigned long ino = F2FS_ROOT_INO(sbi);
-	struct radix_tree_iter iter;
-	void **slot;
-	unsigned int found;
-	unsigned int node_cnt = 0, tree_cnt = 0;
-
-	if (!test_opt(sbi, EXTENT_CACHE))
-		return;
-
-	if (available_free_memory(sbi, EXTENT_CACHE))
-		return;
-
-	spin_lock(&sbi->extent_lock);
-	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
-		if (!nr_shrink--)
-			break;
-		list_del_init(&en->list);
-	}
-	spin_unlock(&sbi->extent_lock);
-
-	down_read(&sbi->extent_tree_lock);
-	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
-				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
-		unsigned i;
-
-		ino = treevec[found - 1]->ino + 1;
-		for (i = 0; i < found; i++) {
-			struct extent_tree *et = treevec[i];
-
-			atomic_inc(&et->refcount);
-			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et, false);
-			write_unlock(&et->lock);
-			atomic_dec(&et->refcount);
-		}
-	}
-	up_read(&sbi->extent_tree_lock);
-
-	down_write(&sbi->extent_tree_lock);
-	radix_tree_for_each_slot(slot, &sbi->extent_tree_root, &iter,
-							F2FS_ROOT_INO(sbi)) {
-		struct extent_tree *et = (struct extent_tree *)*slot;
-
-		if (!atomic_read(&et->refcount) && !et->count) {
-			radix_tree_delete(&sbi->extent_tree_root