[PATCH 12/12] f2fs: use extent_cache by default

[Jaegeuk Kim]

We don't need to handle the duplicate extent infot showrmation.

The integrated rule is:
 - update on-disk extent with largest one tracked by in-memory extent_cache
 - destroy extent_tree for the truncation case
 - drop per-inode extent_cache by shrinker

Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
---
 fs/f2fs/data.c     | 349 ++++++++++++++++-------------------------------------
 fs/f2fs/f2fs.h     |  20 ++-
 fs/f2fs/inode.c    |  18 ++-
 fs/f2fs/namei.c    |   2 +
 fs/f2fs/shrinker.c |   2 +
 fs/f2fs/super.c    |   8 +-
 6 files changed, 136 insertions(+), 263 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 18bd0ac..e90522a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -266,103 +266,6 @@ 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)
-{
-	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)
@@ -394,23 +297,6 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 		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);
@@ -434,6 +320,9 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 	atomic_inc(&et->refcount);
 	up_write(&sbi->extent_tree_lock);
 
+	/* never died untill evict_inode */
+	F2FS_I(inode)->extent_tree = et;
+
 	return et;
 }
 
@@ -522,7 +411,7 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 				en->ei.len += ei->len;
 				if (den)
 					*den = __try_back_merge(sbi, et, en);
-				return en;
+				goto update_out;
 			}
 			p = &(*p)->rb_left;
 		} else if (ei->fofs >= en->ei.fofs + en->ei.len) {
@@ -530,7 +419,7 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 				en->ei.len += ei->len;
 				if (den)
 					*den = __try_front_merge(sbi, et, en);
-				return en;
+				goto update_out;
 			}
 			p = &(*p)->rb_right;
 		} else {
@@ -538,7 +427,11 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 		}
 	}
 
-	return __attach_extent_node(sbi, et, ei, parent, p);
+	en = __attach_extent_node(sbi, et, ei, parent, p);
+update_out:
+	if (en && en->ei.len > et->largest.len)
+		et->largest = en->ei;
+	return en;
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
@@ -570,26 +463,36 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 	return count - et->count;
 }
 
-static void f2fs_init_extent_tree(struct inode *inode,
-						struct f2fs_extent *i_ext)
+static void __drop_largest_extent(struct inode *inode, pgoff_t fofs)
+{
+	struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
+
+	if (largest->fofs <= fofs && largest->fofs + largest->len > fofs)
+		largest->len = 0;
+}
+
+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;
 
-	if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
+	if (!f2fs_may_extent_tree(inode))
 		return;
 
 	et = __grab_extent_tree(inode);
 
-	write_lock(&et->lock);
-	if (et->count)
-		goto out;
+	if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
+		return;
 
 	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
 		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
 
+	write_lock(&et->lock);
+	if (et->count)
+		goto out;
+
 	en = __insert_extent_tree(sbi, et, &ei, NULL);
 	if (en) {
 		et->cached_en = en;
@@ -600,21 +503,18 @@ static void f2fs_init_extent_tree(struct inode *inode,
 	}
 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_tree *et = F2FS_I(inode)->extent_tree;
 	struct extent_node *en;
 
-	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
+	f2fs_bug_on(sbi, !et);
 
-	et = __find_extent_tree(sbi, inode->i_ino);
-	if (!et)
-		return false;
+	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
 
 	read_lock(&et->lock);
 	en = __lookup_extent_tree(et, pgofs);
@@ -631,27 +531,35 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	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,
+/* return true, if on-disk extent should be updated */
+static bool 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_tree *et = F2FS_I(inode)->extent_tree;
 	struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL;
 	struct extent_node *den = NULL;
-	struct extent_info ei, dei;
+	struct extent_info ei, dei, prev;
 	unsigned int endofs;
 
-	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
+	if (!et)
+		return false;
 
-	et = __grab_extent_tree(inode);
+	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
 
 	write_lock(&et->lock);
 
+	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
+		write_unlock(&et->lock);
+		return false;
+	}
+
+	prev = et->largest;
+	dei.len = 0;
+
 	/* 1. lookup and remove existing extent info in cache */
 	en = __lookup_extent_tree(et, fofs);
 	if (!en)
@@ -660,6 +568,8 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 	dei = en->ei;
 	__detach_extent_node(sbi, et, en);
 
+	__drop_largest_extent(inode, fofs);
+
 	/* 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 */
@@ -683,6 +593,14 @@ update_extent:
 	if (blkaddr) {
 		set_extent_info(&ei, fofs, blkaddr, 1);
 		en3 = __insert_extent_tree(sbi, et, &ei, &den);
+
+		/* give up extent_cache, if split and small updates happen */
+		if (dei.len >= 1 &&
+				prev.len < F2FS_MIN_EXTENT_LEN &&
+				et->largest.len < F2FS_MIN_EXTENT_LEN) {
+			et->largest.len = 0;
+			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
+		}
 	}
 
 	/* 4. update in global extent list */
@@ -714,57 +632,12 @@ update_extent:
 	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;
+	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+		__free_extent_tree(sbi, et, true);
 
-		*ext = en->ei;
-		sync = true;
-	} else if (ext->len) {
-		ext->len = 0;
-		sync = true;
-	}
-out:
-	read_unlock(&et->lock);
-	atomic_dec(&et->refcount);
+	write_unlock(&et->lock);
 
-	if (sync)
-		update_inode_page(inode);
+	return !__is_extent_same(&prev, &et->largest);
 }
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -772,8 +645,7 @@ unsigned int 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;
+	struct radix_tree_root *root = &sbi->extent_tree_root;
 	unsigned int found;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 
@@ -788,10 +660,10 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	}
 	spin_unlock(&sbi->extent_lock);
 
-	if (!down_read_trylock(&sbi->extent_tree_lock))
+	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
 
-	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
+	while ((found = radix_tree_gang_lookup(root,
 				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
 		unsigned i;
 
@@ -799,27 +671,15 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 		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);
-
-	if (!down_write_trylock(&sbi->extent_tree_lock))
-		goto out;
-
-	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, et->ino);
-			kmem_cache_free(extent_tree_slab, et);
-			sbi->total_ext_tree--;
-			tree_cnt++;
+			if (!atomic_read(&et->refcount) && !et->count) {
+				radix_tree_delete(root, et->ino);
+				kmem_cache_free(extent_tree_slab, et);
+				sbi->total_ext_tree--;
+				tree_cnt++;
+			}
 		}
 	}
 	up_write(&sbi->extent_tree_lock);
@@ -829,63 +689,59 @@ out:
 	return node_cnt + tree_cnt;
 }
 
-void f2fs_destroy_extent_tree(struct inode *inode)
+void f2fs_destroy_extent_node(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et;
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 	unsigned int node_cnt = 0;
 
-	if (!test_opt(sbi, EXTENT_CACHE))
-		return;
-
-	et = __find_extent_tree(sbi, inode->i_ino);
 	if (!et)
-		goto out;
+		return;
 
-	/* free all extent info belong to this extent tree */
 	write_lock(&et->lock);
 	node_cnt = __free_extent_tree(sbi, et, true);
 	write_unlock(&et->lock);
+}
 
-	atomic_dec(&et->refcount);
+void f2fs_destroy_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	unsigned int node_cnt = 0;
 
-	/* try to find and delete extent tree entry in radix tree */
-	down_write(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
-	if (!et) {
-		up_write(&sbi->extent_tree_lock);
-		goto out;
+	if (!et)
+		return;
+
+	if (inode->i_nlink && !is_bad_inode(inode) && et->count) {
+		atomic_dec(&et->refcount);
+		return;
 	}
+
+	/* free all extent info belong to this extent tree */
+	f2fs_destroy_extent_node(inode);
+
+	/* delete extent tree entry in radix tree */
+	down_write(&sbi->extent_tree_lock);
+	atomic_dec(&et->refcount);
 	f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count);
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
 	sbi->total_ext_tree--;
 	up_write(&sbi->extent_tree_lock);
-out:
-	trace_f2fs_destroy_extent_tree(inode, node_cnt);
-	return;
-}
 
-void f2fs_init_extent_cache(struct inode *inode, struct f2fs_extent *i_ext)
-{
-	if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
-		f2fs_init_extent_tree(inode, i_ext);
+	F2FS_I(inode)->extent_tree = NULL;
 
-	write_lock(&F2FS_I(inode)->ext_lock);
-	get_extent_info(&F2FS_I(inode)->ext, *i_ext);
-	write_unlock(&F2FS_I(inode)->ext_lock);
+	trace_f2fs_destroy_extent_tree(inode, node_cnt);
+	return;
 }
 
 static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+	if (!f2fs_may_extent_tree(inode))
 		return false;
 
-	if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
-		return f2fs_lookup_extent_tree(inode, pgofs, ei);
-
-	return lookup_extent_info(inode, pgofs, ei);
+	return f2fs_lookup_extent_tree(inode, pgofs, ei);
 }
 
 void f2fs_update_extent_cache(struct dnode_of_data *dn)
@@ -893,19 +749,15 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
-
-	if (is_inode_flag_set(fi, FI_NO_EXTENT))
+	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
+	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
+
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
 							dn->ofs_in_node;
 
-	/* we should call update_extent_info() to update on-disk extent */
-	if (test_opt(F2FS_I_SB(dn->inode), EXTENT_CACHE))
-		f2fs_update_extent_tree(dn->inode, fofs, dn->data_blkaddr);
-
-	if (update_extent_info(dn->inode, fofs, dn->data_blkaddr))
+	if (f2fs_update_extent_tree(dn->inode, fofs, dn->data_blkaddr))
 		sync_inode_page(dn);
 }
 
@@ -1109,8 +961,6 @@ alloc:
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
 								&sum, seg);
-
-	/* direct IO doesn't use extent cache to maximize the performance */
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -1119,6 +969,9 @@ alloc:
 	if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
 
+	/* direct IO doesn't use extent cache to maximize the performance */
+	__drop_largest_extent(dn->inode, fofs);
+
 	return 0;
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index eeef3eb..281343c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -349,6 +349,7 @@ struct extent_tree {
 	nid_t ino;			/* inode number */
 	struct rb_root root;		/* root of extent info rb-tree */
 	struct extent_node *cached_en;	/* recently accessed extent node */
+	struct extent_info largest;	/* largested extent info */
 	rwlock_t lock;			/* protect extent info rb-tree */
 	atomic_t refcount;		/* reference count of rb-tree */
 	unsigned int count;		/* # of extent node in rb-tree*/
@@ -420,14 +421,14 @@ struct f2fs_inode_info {
 	unsigned int clevel;		/* maximum level of given file name */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
-	struct extent_info ext;		/* in-memory extent cache entry */
-	rwlock_t ext_lock;		/* rwlock for single extent cache */
 	struct inode_entry *dirty_dir;	/* the pointer of dirty dir */
 
 	struct radix_tree_root inmem_root;	/* radix tree for inmem pages */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
 
+	struct extent_tree *extent_tree;	/* cached extent_tree entry */
+
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 	/* Encryption params */
 	struct f2fs_crypt_info *i_crypt_info;
@@ -1548,6 +1549,17 @@ static inline bool is_dot_dotdot(const struct qstr *str)
 	return false;
 }
 
+static inline bool f2fs_may_extent_tree(struct inode *inode)
+{
+	mode_t mode = inode->i_mode;
+
+	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
+			is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+		return false;
+
+	return S_ISREG(mode);
+}
+
 #define get_inode_mode(i) \
 	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
@@ -1755,10 +1767,10 @@ void set_data_blkaddr(struct dnode_of_data *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
+void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
+void f2fs_destroy_extent_node(struct inode *);
 void f2fs_destroy_extent_tree(struct inode *);
-void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *);
 void f2fs_update_extent_cache(struct dnode_of_data *);
-void f2fs_preserve_extent_tree(struct inode *);
 struct page *get_read_data_page(struct inode *, pgoff_t, int);
 struct page *find_data_page(struct inode *, pgoff_t);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 757fed2..978a726 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -139,7 +139,7 @@ static int do_read_inode(struct inode *inode)
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
 
-	f2fs_init_extent_cache(inode, &ri->i_ext);
+	f2fs_init_extent_tree(inode, &ri->i_ext);
 
 	get_inline_info(fi, ri);
 
@@ -237,10 +237,11 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_size = cpu_to_le64(i_size_read(inode));
 	ri->i_blocks = cpu_to_le64(inode->i_blocks);
 
-	read_lock(&F2FS_I(inode)->ext_lock);
-	set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
-	read_unlock(&F2FS_I(inode)->ext_lock);
-
+	if (F2FS_I(inode)->extent_tree)
+		set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
+							&ri->i_ext);
+	else
+		memset(&ri->i_ext, 0, sizeof(ri->i_ext));
 	set_raw_inline(F2FS_I(inode), ri);
 
 	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
@@ -331,6 +332,8 @@ void f2fs_evict_inode(struct inode *inode)
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
 	remove_dirty_dir_inode(inode);
 
+	f2fs_destroy_extent_tree(inode);
+
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
@@ -350,11 +353,6 @@ no_delete:
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
 
-	/* update extent info in inode */
-	if (inode->i_nlink)
-		f2fs_preserve_extent_tree(inode);
-	f2fs_destroy_extent_tree(inode);
-
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 08656fc..df315dc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -65,6 +65,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
 
+	f2fs_init_extent_tree(inode, NULL);
+
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index a7d7a7c..2dfb08d 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -117,6 +117,8 @@ void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
 
 void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
 {
+	f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi));
+
 	spin_lock(&f2fs_list_lock);
 	list_del(&sbi->s_list);
 	spin_unlock(&f2fs_list_lock);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index a9db896..31ac3c7 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -422,7 +422,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	atomic_set(&fi->dirty_pages, 0);
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
-	rwlock_init(&fi->ext_lock);
 	init_rwsem(&fi->i_sem);
 	INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS);
 	INIT_LIST_HEAD(&fi->inmem_pages);
@@ -453,12 +452,17 @@ static int f2fs_drop_inode(struct inode *inode)
 	 */
 	if (!inode_unhashed(inode) && inode->i_state & I_SYNC) {
 		if (!inode->i_nlink && !is_bad_inode(inode)) {
+			/* to avoid evict_inode call simultaneously */
+			atomic_inc(&inode->i_count);
 			spin_unlock(&inode->i_lock);
 
 			/* some remained atomic pages should discarded */
 			if (f2fs_is_atomic_file(inode))
 				commit_inmem_pages(inode, true);
 
+			/* should remain fi->extent_tree for writepage */
+			f2fs_destroy_extent_node(inode);
+
 			sb_start_intwrite(inode->i_sb);
 			i_size_write(inode, 0);
 
@@ -473,6 +477,7 @@ static int f2fs_drop_inode(struct inode *inode)
 					F2FS_I(inode)->i_crypt_info);
 #endif
 			spin_lock(&inode->i_lock);
+			atomic_dec(&inode->i_count);
 		}
 		return 0;
 	}
@@ -719,6 +724,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 
 	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_DATA);
+	set_opt(sbi, EXTENT_CACHE);
 
 #ifdef CONFIG_F2FS_FS_XATTR
 	set_opt(sbi, XATTR_USER);
-- 
2.1.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/