Merge tag 'for-f2fs-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This series adds two ioctls to control cached data and fragmented
  files.  Most of the rest fixes missing error cases and bugs that we
  have not covered so far.  Summary:

  Enhancements:
   - support an ioctl to execute online file defragmentation
   - support an ioctl to flush cached data
   - speed up shrinking of extent_cache entries
   - handle broken superblock
   - refector dirty inode management infra
   - revisit f2fs_map_blocks to handle more cases
   - reduce global lock coverage
   - add detecting user's idle time

  Major bug fixes:
   - fix data race condition on cached nat entries
   - fix error cases of volatile and atomic writes"

* tag 'for-f2fs-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (87 commits)
  f2fs: should unset atomic flag after successful commit
  f2fs: fix wrong memory condition check
  f2fs: monitor the number of background checkpoint
  f2fs: detect idle time depending on user behavior
  f2fs: introduce time and interval facility
  f2fs: skip releasing nodes in chindless extent tree
  f2fs: use atomic type for node count in extent tree
  f2fs: recognize encrypted data in f2fs_fiemap
  f2fs: clean up f2fs_balance_fs
  f2fs: remove redundant calls
  f2fs: avoid unnecessary f2fs_balance_fs calls
  f2fs: check the page status filled from disk
  f2fs: introduce __get_node_page to reuse common code
  f2fs: check node id earily when readaheading node page
  f2fs: read isize while holding i_mutex in fiemap
  Revert "f2fs: check the node block address of newly allocated nid"
  f2fs: cover more area with nat_tree_lock
  f2fs: introduce max_file_blocks in sbi
  f2fs crypto: check CONFIG_F2FS_FS_XATTR for encrypted symlink
  f2fs: introduce zombie list for fast shrinking extent trees
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -87,6 +87,12 @@ Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:
 		 Controls the checkpoint timing.
 
+What:		/sys/fs/f2fs/<disk>/idle_interval
+Date:		January 2016
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the idle timing.
+
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>

Documentation/filesystems/f2fs.txt

@@ -102,7 +102,7 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        collection, triggered in background when I/O subsystem is
                        idle. If background_gc=on, it will turn on the garbage
                        collection and if background_gc=off, garbage collection
-                       will be truned off. If background_gc=sync, it will turn
+                       will be turned off. If background_gc=sync, it will turn
                        on synchronous garbage collection running in background.
                        Default value for this option is on. So garbage
                        collection is on by default.
@@ -145,10 +145,12 @@ 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. Set by default.
-noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+noextent_cache         Disable 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.
+data_flush             Enable data flushing before checkpoint in order to
+                       persist data of regular and symlink.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -192,7 +194,7 @@ Files in /sys/fs/f2fs/<devname>
                               policy for garbage collection. Setting gc_idle = 0
                               (default) will disable this option. Setting
                               gc_idle = 1 will select the Cost Benefit approach
-                              & setting gc_idle = 2 will select the greedy aproach.
+                              & setting gc_idle = 2 will select the greedy approach.
 
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
@@ -298,7 +300,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
 file. Each file is dump_ssa and dump_sit.
 
 The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
-It shows on-disk inode information reconized by a given inode number, and is
+It shows on-disk inode information recognized by a given inode number, and is
 able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
 ./dump_sit respectively.
 

fs/f2fs/debug.c

@@ -38,12 +38,15 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
 	si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
 	si->total_ext = atomic64_read(&sbi->total_hit_ext);
-	si->ext_tree = sbi->total_ext_tree;
+	si->ext_tree = atomic_read(&sbi->total_ext_tree);
+	si->zombie_tree = atomic_read(&sbi->total_zombie_tree);
 	si->ext_node = atomic_read(&sbi->total_ext_node);
 	si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
 	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
-	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
+	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
+	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
 	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
@@ -105,7 +108,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 
 	bimodal = 0;
 	total_vblocks = 0;
-	blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
+	blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
 	hblks_per_sec = blks_per_sec / 2;
 	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
 		vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
@@ -189,10 +192,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
 	for (i = 0; i <= UPDATE_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
-	si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree);
+	si->cache_mem += atomic_read(&sbi->total_ext_tree) *
+						sizeof(struct extent_tree);
 	si->cache_mem += atomic_read(&sbi->total_ext_node) *
 						sizeof(struct extent_node);
 
@@ -267,7 +270,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->dirty_count);
 		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
 			   si->prefree_count, si->free_segs, si->free_secs);
-		seq_printf(s, "CP calls: %d\n", si->cp_count);
+		seq_printf(s, "CP calls: %d (BG: %d)\n",
+				si->cp_count, si->bg_cp_count);
 		seq_printf(s, "GC calls: %d (BG: %d)\n",
 			   si->call_count, si->bg_gc);
 		seq_printf(s, "  - data segments : %d (%d)\n",
@@ -288,8 +292,8 @@ static int stat_show(struct seq_file *s, void *v)
 				!si->total_ext ? 0 :
 				div64_u64(si->hit_total * 100, si->total_ext),
 				si->hit_total, si->total_ext);
-		seq_printf(s, "  - Inner Struct Count: tree: %d, node: %d\n",
-				si->ext_tree, si->ext_node);
+		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
+				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
 		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
 			   si->inmem_pages, si->wb_pages);
@@ -297,6 +301,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
+		seq_printf(s, "  - datas: %4d in files:%4d\n",
+			   si->ndirty_data, si->ndirty_files);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
@@ -404,20 +410,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	kfree(si);
 }
 
-void __init f2fs_create_root_stats(void)
+int __init f2fs_create_root_stats(void)
 {
 	struct dentry *file;
 
 	f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
 	if (!f2fs_debugfs_root)
-		return;
+		return -ENOMEM;
 
 	file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
 			NULL, &stat_fops);
 	if (!file) {
 		debugfs_remove(f2fs_debugfs_root);
 		f2fs_debugfs_root = NULL;
+		return -ENOMEM;
 	}
+
+	return 0;
 }
 
 void f2fs_destroy_root_stats(void)

fs/f2fs/dir.c

@@ -172,8 +172,6 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 
 	namehash = f2fs_dentry_hash(&name);
 
-	f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
-
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
 
@@ -238,6 +236,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 		goto out;
 
 	max_depth = F2FS_I(dir)->i_current_depth;
+	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
+		f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
+				"Corrupted max_depth of %lu: %u",
+				dir->i_ino, max_depth);
+		max_depth = MAX_DIR_HASH_DEPTH;
+		F2FS_I(dir)->i_current_depth = max_depth;
+		mark_inode_dirty(dir);
+	}
 
 	for (level = 0; level < max_depth; level++) {
 		de = find_in_level(dir, level, &fname, res_page);
@@ -444,7 +450,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_blocks(inode, 0, false);
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 	remove_inode_page(inode);
 	return ERR_PTR(err);
 }
@@ -630,6 +636,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	f2fs_put_page(dentry_page, 1);
 out:
 	f2fs_fname_free_filename(&fname);
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 	return err;
 }
 
@@ -651,6 +658,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
 	clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
 fail:
 	up_write(&F2FS_I(inode)->i_sem);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return err;
 }
 
@@ -695,6 +703,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
 	int i;
 
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+
 	if (f2fs_has_inline_dentry(dir))
 		return f2fs_delete_inline_entry(dentry, page, dir, inode);
 
@@ -855,23 +865,25 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 
 	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n, false);
-		if (IS_ERR(dentry_page))
+		if (IS_ERR(dentry_page)) {
+			err = PTR_ERR(dentry_page);
+			if (err == -ENOENT)
 				continue;
+			else
+				goto out;
+		}
 
 		dentry_blk = kmap(dentry_page);
 
 		make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
 
-		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr))
-			goto stop;
-
-		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
+		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
 			kunmap(dentry_page);
 			f2fs_put_page(dentry_page, 1);
-		dentry_page = NULL;
+			break;
 		}
-stop:
-	if (dentry_page && !IS_ERR(dentry_page)) {
+
+		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
 	}

fs/f2fs/extent_cache.c

@@ -36,7 +36,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
 
 	rb_link_node(&en->rb_node, parent, p);
 	rb_insert_color(&en->rb_node, &et->root);
-	et->count++;
+	atomic_inc(&et->node_cnt);
 	atomic_inc(&sbi->total_ext_node);
 	return en;
 }
@@ -45,7 +45,7 @@ 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(&et->node_cnt);
 	atomic_dec(&sbi->total_ext_node);
 
 	if (et->cached_en == en)
@@ -68,11 +68,13 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 		et->root = RB_ROOT;
 		et->cached_en = NULL;
 		rwlock_init(&et->lock);
-		atomic_set(&et->refcount, 0);
-		et->count = 0;
-		sbi->total_ext_tree++;
+		INIT_LIST_HEAD(&et->list);
+		atomic_set(&et->node_cnt, 0);
+		atomic_inc(&sbi->total_ext_tree);
+	} else {
+		atomic_dec(&sbi->total_zombie_tree);
+		list_del_init(&et->list);
 	}
-	atomic_inc(&et->refcount);
 	up_write(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
@@ -131,7 +133,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
-	unsigned int count = et->count;
+	unsigned int count = atomic_read(&et->node_cnt);
 
 	node = rb_first(&et->root);
 	while (node) {
@@ -152,7 +154,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 		node = next;
 	}
 
-	return count - et->count;
+	return count - atomic_read(&et->node_cnt);
 }
 
 static void __drop_largest_extent(struct inode *inode,
@@ -164,34 +166,33 @@ static void __drop_largest_extent(struct inode *inode,
 		largest->len = 0;
 }
 
-void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs)
-{
-	if (!f2fs_may_extent_tree(inode))
-		return;
-
-	__drop_largest_extent(inode, fofs, 1);
-}
-
-void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+/* return true, if inode page is changed */
+bool 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 (!f2fs_may_extent_tree(inode))
-		return;
+	if (!f2fs_may_extent_tree(inode)) {
+		/* drop largest extent */
+		if (i_ext && i_ext->len) {
+			i_ext->len = 0;
+			return true;
+		}
+		return false;
+	}
 
 	et = __grab_extent_tree(inode);
 
-	if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
-		return;
+	if (!i_ext || !i_ext->len)
+		return false;
 
 	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)
+	if (atomic_read(&et->node_cnt))
 		goto out;
 
 	en = __init_extent_tree(sbi, et, &ei);
@@ -202,6 +203,7 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 	}
 out:
 	write_unlock(&et->lock);
+	return false;
 }
 
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
@@ -549,45 +551,44 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 {
 	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
+	struct extent_tree *et, *next;
 	struct extent_node *en, *tmp;
 	unsigned long ino = F2FS_ROOT_INO(sbi);
-	struct radix_tree_root *root = &sbi->extent_tree_root;
 	unsigned int found;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
+	bool do_free = false;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return 0;
 
+	if (!atomic_read(&sbi->total_zombie_tree))
+		goto free_node;
+
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
-	while ((found = radix_tree_gang_lookup(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];
-
-			if (!atomic_read(&et->refcount)) {
+	list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
+		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
 			node_cnt += __free_extent_tree(sbi, et, true);
 			write_unlock(&et->lock);
+		}
 
-				radix_tree_delete(root, et->ino);
+		list_del_init(&et->list);
+		radix_tree_delete(&sbi->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
-				sbi->total_ext_tree--;
+		atomic_dec(&sbi->total_ext_tree);
+		atomic_dec(&sbi->total_zombie_tree);
 		tree_cnt++;
 
 		if (node_cnt + tree_cnt >= nr_shrink)
 			goto unlock_out;
 	}
-		}
-	}
 	up_write(&sbi->extent_tree_lock);
 
+free_node:
 	/* 2. remove LRU extent entries */
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
@@ -599,15 +600,19 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 		if (!remained--)
 			break;
 		list_del_init(&en->list);
+		do_free = true;
 	}
 	spin_unlock(&sbi->extent_lock);
 
+	if (do_free == false)
+		goto unlock_out;
+
 	/*
 	 * reset ino for searching victims from beginning of global extent tree.
 	 */
 	ino = F2FS_ROOT_INO(sbi);
 
-	while ((found = radix_tree_gang_lookup(root,
+	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
 				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
 		unsigned i;
 
@@ -615,9 +620,13 @@ 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];
 
-			write_lock(&et->lock);
+			if (!atomic_read(&et->node_cnt))
+				continue;
+
+			if (write_trylock(&et->lock)) {
 				node_cnt += __free_extent_tree(sbi, et, false);
 				write_unlock(&et->lock);
+			}
 
 			if (node_cnt + tree_cnt >= nr_shrink)
 				goto unlock_out;
@@ -637,7 +646,7 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 	unsigned int node_cnt = 0;
 
-	if (!et)
+	if (!et || !atomic_read(&et->node_cnt))
 		return 0;
 
 	write_lock(&et->lock);
@@ -656,8 +665,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	if (!et)
 		return;
 
-	if (inode->i_nlink && !is_bad_inode(inode) && et->count) {
-		atomic_dec(&et->refcount);
+	if (inode->i_nlink && !is_bad_inode(inode) &&
+					atomic_read(&et->node_cnt)) {
+		down_write(&sbi->extent_tree_lock);
+		list_add_tail(&et->list, &sbi->zombie_list);
+		atomic_inc(&sbi->total_zombie_tree);
+		up_write(&sbi->extent_tree_lock);
 		return;
 	}
 
@@ -666,11 +679,10 @@ void f2fs_destroy_extent_tree(struct inode *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);
+	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
-	sbi->total_ext_tree--;
+	atomic_dec(&sbi->total_ext_tree);
 	up_write(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
@@ -722,7 +734,9 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi)
 	init_rwsem(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
-	sbi->total_ext_tree = 0;
+	atomic_set(&sbi->total_ext_tree, 0);
+	INIT_LIST_HEAD(&sbi->zombie_list);
+	atomic_set(&sbi->total_zombie_tree, 0);
 	atomic_set(&sbi->total_ext_node, 0);
 }
 

fs/f2fs/gc.c

@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/freezer.h>
-#include <linux/blkdev.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -173,9 +172,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 {
 	/* SSR allocates in a segment unit */
 	if (p->alloc_mode == SSR)
-		return 1 << sbi->log_blocks_per_seg;
+		return sbi->blocks_per_seg;
 	if (p->gc_mode == GC_GREEDY)
-		return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
+		return sbi->blocks_per_seg * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
 		return UINT_MAX;
 	else /* No other gc_mode */
@@ -832,8 +831,10 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
 
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
 		goto stop;
+	}
 
 	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
 		gc_type = FG_GC;

fs/f2fs/gc.h

@@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
 		return true;
 	return false;
 }
-
-static inline int is_idle(struct f2fs_sb_info *sbi)
-{
-	struct block_device *bdev = sbi->sb->s_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	struct request_list *rl = &q->root_rl;
-	return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
-}

fs/f2fs/inline.c

@@ -16,9 +16,6 @@
 
 bool f2fs_may_inline_data(struct inode *inode)
 {
-	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
-		return false;
-
 	if (f2fs_is_atomic_file(inode))
 		return false;
 
@@ -177,6 +174,9 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	struct page *ipage, *page;
 	int err = 0;
 
+	if (!f2fs_has_inline_data(inode))
+		return 0;
+
 	page = grab_cache_page(inode->i_mapping, 0);
 	if (!page)
 		return -ENOMEM;
@@ -199,6 +199,9 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	f2fs_unlock_op(sbi);
 
 	f2fs_put_page(page, 1);
+
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	return err;
 }
 

fs/f2fs/inode.c

@@ -138,7 +138,8 @@ 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_tree(inode, &ri->i_ext);
+	if (f2fs_init_extent_tree(inode, &ri->i_ext))
+		set_page_dirty(node_page);
 
 	get_inline_info(fi, ri);
 
@@ -222,7 +223,7 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 	return ERR_PTR(ret);
 }
 
-void update_inode(struct inode *inode, struct page *node_page)
+int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
@@ -260,15 +261,16 @@ void update_inode(struct inode *inode, struct page *node_page)
 
 	__set_inode_rdev(inode, ri);
 	set_cold_node(inode, node_page);
-	set_page_dirty(node_page);
-
 	clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+
+	return set_page_dirty(node_page);
 }
 
-void update_inode_page(struct inode *inode)
+int update_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *node_page;
+	int ret = 0;
 retry:
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
@@ -279,10 +281,11 @@ void update_inode_page(struct inode *inode)
 		} else if (err != -ENOENT) {
 			f2fs_stop_checkpoint(sbi);
 		}
-		return;
+		return 0;
 	}
-	update_inode(inode, node_page);
+	ret = update_inode(inode, node_page);
 	f2fs_put_page(node_page, 1);
+	return ret;
 }
 
 int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -300,9 +303,8 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	update_inode_page(inode);
-
-	f2fs_balance_fs(sbi);
+	if (update_inode_page(inode))
+		f2fs_balance_fs(sbi, true);
 	return 0;
 }
 
@@ -328,7 +330,7 @@ void f2fs_evict_inode(struct inode *inode)
 		goto out_clear;
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 
 	f2fs_destroy_extent_tree(inode);
 
@@ -358,9 +360,9 @@ void f2fs_evict_inode(struct inode *inode)
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
 	if (is_inode_flag_set(fi, FI_APPEND_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
+		add_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
+		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 	if (is_inode_flag_set(fi, FI_FREE_NID)) {
 		if (err && err != -ENOENT)
 			alloc_nid_done(sbi, inode->i_ino);

fs/f2fs/namei.c

@@ -60,7 +60,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
-	if (f2fs_may_inline_data(inode))
+	if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
 	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
@@ -128,8 +128,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -142,6 +140,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	ino = inode->i_ino;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -172,7 +172,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 		!f2fs_is_child_context_consistent_with_parent(dir, inode))
 		return -EPERM;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	inode->i_ctime = CURRENT_TIME;
 	ihold(inode);
@@ -214,6 +214,15 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	struct page *page;
 	int err = 0;
 
+	if (f2fs_readonly(sbi->sb)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"skip recovering inline_dots inode (ino:%lu, pino:%u) "
+			"in readonly mountpoint", dir->i_ino, pino);
+		return 0;
+	}
+
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	de = f2fs_find_entry(dir, &dot, &page);
@@ -288,12 +297,13 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	int err = -ENOENT;
 
 	trace_f2fs_unlink_enter(dir, dentry);
-	f2fs_balance_fs(sbi);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de)
 		goto fail;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err) {
@@ -344,8 +354,6 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	if (len > dir->i_sb->s_blocksize)
 		return -ENAMETOOLONG;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -357,6 +365,8 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -437,8 +447,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -448,6 +456,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
+	f2fs_balance_fs(sbi, true);
+
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
@@ -485,8 +495,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -494,6 +502,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_op = &f2fs_special_inode_operations;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -520,9 +530,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	if (!whiteout)
-		f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -536,6 +543,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err)
@@ -608,8 +617,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out;
 	}
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry)
 		goto out;
@@ -639,6 +646,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_entry)
 			goto out_whiteout;
 
+		f2fs_balance_fs(sbi, true);
+
 		f2fs_lock_op(sbi);
 
 		err = acquire_orphan_inode(sbi);
@@ -670,6 +679,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		update_inode_page(old_inode);
 		update_inode_page(new_inode);
 	} else {
+		f2fs_balance_fs(sbi, true);
+
 		f2fs_lock_op(sbi);
 
 		err = f2fs_add_link(new_dentry, old_inode);
@@ -767,8 +778,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 								new_inode)))
 		return -EPERM;
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry)
 		goto out;
@@ -811,6 +820,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_new_dir;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
@@ -933,7 +944,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct f2fs_str cstr;
+	struct f2fs_str cstr = FSTR_INIT(NULL, 0);
 	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
 	struct f2fs_encrypted_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
@@ -956,6 +967,12 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	/* Symlink is encrypted */
 	sd = (struct f2fs_encrypted_symlink_data *)caddr;
 	cstr.len = le16_to_cpu(sd->len);
+
+	/* this is broken symlink case */
+	if (unlikely(cstr.len == 0)) {
+		res = -ENOENT;
+		goto errout;
+	}
 	cstr.name = kmalloc(cstr.len, GFP_NOFS);
 	if (!cstr.name) {
 		res = -ENOMEM;
@@ -964,7 +981,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	memcpy(cstr.name, sd->encrypted_path, cstr.len);
 
 	/* this is broken symlink case */
-	if (cstr.name[0] == 0 && cstr.len == 0) {
+	if (unlikely(cstr.name[0] == 0)) {
 		res = -ENOENT;
 		goto errout;
 	}
@@ -1005,10 +1022,12 @@ const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.get_link       = f2fs_encrypted_get_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
+#ifdef CONFIG_F2FS_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= f2fs_listxattr,
 	.removexattr	= generic_removexattr,
+#endif
 };
 #endif
 

fs/f2fs/node.h

@@ -183,7 +183,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
 
 	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
 		(seg_off << sbi->log_blocks_per_seg << 1) +
-		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
+		(block_off & (sbi->blocks_per_seg - 1)));
 
 	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
 		block_addr += sbi->blocks_per_seg;
@@ -317,7 +317,7 @@ static inline bool IS_DNODE(struct page *node_page)
 	return true;
 }
 
-static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
+static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
@@ -327,7 +327,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
 	else
 		rn->in.nid[off] = cpu_to_le32(nid);
-	set_page_dirty(p);
+	return set_page_dirty(p);
 }
 
 static inline nid_t get_nid(struct page *p, int off, bool i)

fs/f2fs/recovery.c

@@ -168,6 +168,32 @@ static void recover_inode(struct inode *inode, struct page *page)
 			ino_of_node(page), name);
 }
 
+static bool is_same_inode(struct inode *inode, struct page *ipage)
+{
+	struct f2fs_inode *ri = F2FS_INODE(ipage);
+	struct timespec disk;
+
+	if (!IS_INODE(ipage))
+		return true;
+
+	disk.tv_sec = le64_to_cpu(ri->i_ctime);
+	disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
+	if (timespec_compare(&inode->i_ctime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_atime);
+	disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
+	if (timespec_compare(&inode->i_atime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_mtime);
+	disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
+	if (timespec_compare(&inode->i_mtime, &disk) > 0)
+		return false;
+
+	return true;
+}
+
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
@@ -197,7 +223,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 			goto next;
 
 		entry = get_fsync_inode(head, ino_of_node(page));
-		if (!entry) {
+		if (entry) {
+			if (!is_same_inode(entry->inode, page))
+				goto next;
+		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
 				if (err)
@@ -459,8 +488,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	return err;
 }
 
-static int recover_data(struct f2fs_sb_info *sbi,
-				struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
 {
 	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
@@ -469,7 +497,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
 	block_t blkaddr;
 
 	/* get node pages in the current segment */
-	curseg = CURSEG_I(sbi, type);
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	while (1) {
@@ -556,7 +584,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 	need_writecp = true;
 
 	/* step #2: recover data */
-	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	err = recover_data(sbi, &inode_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
 out:
@@ -595,7 +623,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 			.reason = CP_RECOVERY,
 		};
 		mutex_unlock(&sbi->cp_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}

fs/f2fs/segment.c

@@ -86,6 +86,7 @@ static inline unsigned long __reverse_ffs(unsigned long word)
 /*
  * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
  * f2fs_set_bit makes MSB and LSB reversed in a byte.
+ * @size must be integral times of unsigned long.
  * Example:
  *                             MSB <--> LSB
  *   f2fs_set_bit(0, bitmap) => 1000 0000
@@ -95,94 +96,73 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
+
+	while (1) {
+		if (*p == 0)
+			goto pass;
 
 		tmp = __reverse_ulong((unsigned char *)p);
-	tmp &= ~0UL >> offset;
 
+		tmp &= ~0UL >> offset;
 		if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG-1)) {
-		tmp = __reverse_ulong((unsigned char *)p);
+			tmp &= (~0UL << (BITS_PER_LONG - size));
 		if (tmp)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
 	return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp &= (~0UL << (BITS_PER_LONG - size));
-	if (!tmp)		/* Are any bits set? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffs(tmp);
+found:
+	return result - size + __reverse_ffs(tmp);
 }
 
 static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
+
+	while (1) {
+		if (*p == ~0UL)
+			goto pass;
 
 		tmp = __reverse_ulong((unsigned char *)p);
-	tmp |= ~((~0UL << offset) >> offset);
 
+		if (offset)
+			tmp |= ~0UL << (BITS_PER_LONG - offset);
 		if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp != ~0UL)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG - 1)) {
-		tmp = __reverse_ulong((unsigned char *)p);
+			tmp |= ~0UL >> size;
 		if (tmp != ~0UL)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
 	return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp |= ~(~0UL << (BITS_PER_LONG - size));
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffz(tmp);
+found:
+	return result - size + __reverse_ffz(tmp);
 }
 
 void register_inmem_page(struct inode *inode, struct page *page)
@@ -233,7 +213,7 @@ int commit_inmem_pages(struct inode *inode, bool abort)
 	 * inode becomes free by iget_locked in f2fs_iget.
 	 */
 	if (!abort) {
-		f2fs_balance_fs(sbi);
+		f2fs_balance_fs(sbi, true);
 		f2fs_lock_op(sbi);
 	}
 
@@ -257,6 +237,7 @@ int commit_inmem_pages(struct inode *inode, bool abort)
 				submit_bio = true;
 			}
 		} else {
+			ClearPageUptodate(cur->page);
 			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
 		}
 		set_page_private(cur->page, 0);
@@ -281,8 +262,10 @@ int commit_inmem_pages(struct inode *inode, bool abort)
  * This function balances dirty node and dentry pages.
  * In addition, it controls garbage collection.
  */
-void f2fs_balance_fs(struct f2fs_sb_info *sbi)
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
+	if (!need)
+		return;
 	/*
 	 * We should do GC or end up with checkpoint, if there are so many dirty
 	 * dir/node pages without enough free segments.
@@ -310,8 +293,12 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
 			excess_prefree_segs(sbi) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
-			jiffies > sbi->cp_expires)
+			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
+		if (test_opt(sbi, DATA_FLUSH))
+			sync_dirty_inodes(sbi, FILE_INODE);
 		f2fs_sync_fs(sbi->sb, true);
+		stat_inc_bg_cp_count(sbi->stat_info);
+	}
 }
 
 static int issue_flush_thread(void *data)
@@ -1134,6 +1121,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
+	int err = 0;
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
@@ -1164,12 +1152,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 				sbi->segs_per_sec) - 1, end_segno);
 
 		mutex_lock(&sbi->gc_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	}
 out:
 	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
-	return 0;
+	return err;
 }
 
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
@@ -1749,13 +1737,13 @@ int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
 			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
 				return i;
 		}
-		if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
+		if (alloc && __has_cursum_space(sum, 1, NAT_JOURNAL))
 			return update_nats_in_cursum(sum, 1);
 	} else if (type == SIT_JOURNAL) {
 		for (i = 0; i < sits_in_cursum(sum); i++)
 			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
 				return i;
-		if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
+		if (alloc && __has_cursum_space(sum, 1, SIT_JOURNAL))
 			return update_sits_in_cursum(sum, 1);
 	}
 	return -1;

fs/f2fs/shrinker.c

@@ -32,7 +32,8 @@ static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 
 static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
 {
-	return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node);
+	return atomic_read(&sbi->total_zombie_tree) +
+				atomic_read(&sbi->total_ext_node);
 }
 
 unsigned long f2fs_shrink_count(struct shrinker *shrink,

fs/f2fs/xattr.c

@@ -571,7 +571,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	if (ipage)
 		return __f2fs_setxattr(inode, index, name, value,
 						size, ipage, flags);
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
 	/* protect xattr_ver */
@@ -580,5 +580,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 
+	f2fs_update_time(sbi, REQ_TIME);
 	return err;
 }

include/linux/f2fs_fs.h

@@ -51,6 +51,7 @@
 #define MAX_ACTIVE_DATA_LOGS	8
 
 #define VERSION_LEN	256
+#define MAX_VOLUME_NAME		512
 
 /*
  * For superblock
@@ -84,7 +85,7 @@ struct f2fs_super_block {
 	__le32 node_ino;		/* node inode number */
 	__le32 meta_ino;		/* meta inode number */
 	__u8 uuid[16];			/* 128-bit uuid for volume */
-	__le16 volume_name[512];	/* volume name */
+	__le16 volume_name[MAX_VOLUME_NAME];	/* volume name */
 	__le32 extension_count;		/* # of extensions below */
 	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
 	__le32 cp_payload;

include/trace/events/f2fs.h

@@ -1265,6 +1265,44 @@ TRACE_EVENT(f2fs_destroy_extent_tree,
 		__entry->node_cnt)
 );
 
+DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
+
+	TP_PROTO(struct super_block *sb, int type, int count),
+
+	TP_ARGS(sb, type, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, type)
+		__field(int, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->type	= type;
+		__entry->count	= count;
+	),
+
+	TP_printk("dev = (%d,%d), %s, dirty count = %d",
+		show_dev(__entry),
+		show_file_type(__entry->type),
+		__entry->count)
+);
+
+DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_enter,
+
+	TP_PROTO(struct super_block *sb, int type, int count),
+
+	TP_ARGS(sb, type, count)
+);
+
+DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit,
+
+	TP_PROTO(struct super_block *sb, int type, int count),
+
+	TP_ARGS(sb, type, count)
+);
+
 #endif /* _TRACE_F2FS_H */
 
  /* This part must be outside protection */