Merge tag 'f2fs-for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs update from Jaegeuk Kim:
 "[Major bug fixes]
   o Store device file information correctly
   o Fix -EIO handling with respect to power-off-recovery
   o Allocate blocks with global locks
   o Fix wrong calculation of the SSR cost

  [Cleanups]
   o Get rid of fake on-stack dentries

  [Enhancement]
   o Support (un)freeze_fs
   o Enhance the f2fs_gc flow
   o Support 32-bit binary execution on 64-bit kernel"

* tag 'f2fs-for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (29 commits)
  f2fs: avoid build warning
  f2fs: add compat_ioctl to provide backward compatability
  f2fs: fix calculation of max. gc cost in the SSR case
  f2fs: clarify and enhance the f2fs_gc flow
  f2fs: optimize the return condition for has_not_enough_free_secs
  f2fs: make an accessor to get sections for particular block type
  f2fs: mark gc_thread as NULL when thread creation is failed
  f2fs: name gc task as per the block device
  f2fs: remove unnecessary gc option check and balance_fs
  f2fs: remove repeated F2FS_SET_SB_DIRT call
  f2fs: when check superblock failed, try to check another superblock
  f2fs: use F2FS_BLKSIZE to judge bloksize and page_cache_size
  f2fs: add device name in debugfs
  f2fs: stop repeated checking if cp is needed
  f2fs: avoid balanc_fs during evict_inode
  f2fs: remove the use of page_cache_release
  f2fs: fix typo mistake for data_version description
  f2fs: reorganize code for ra_node_page
  f2fs: avoid redundant call to has_not_enough_free_secs in f2fs_gc
  f2fs: add un/freeze_fs into super_operations
  ...

fs/f2fs/checkpoint.c

@@ -72,22 +72,22 @@ static int f2fs_write_meta_page(struct page *page,
 {
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	int err;
 
-	wait_on_page_writeback(page);
-
-	err = write_meta_page(sbi, page, wbc);
-	if (err) {
+	/* Should not write any meta pages, if any IO error was occurred */
+	if (wbc->for_reclaim ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
+		dec_page_count(sbi, F2FS_DIRTY_META);
 		wbc->pages_skipped++;
 		set_page_dirty(page);
+		return AOP_WRITEPAGE_ACTIVATE;
 	}
 
-	dec_page_count(sbi, F2FS_DIRTY_META);
+	wait_on_page_writeback(page);
 
-	/* In this case, we should not unlock this page */
-	if (err != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return err;
+	write_meta_page(sbi, page);
+	dec_page_count(sbi, F2FS_DIRTY_META);
+	unlock_page(page);
+	return 0;
 }
 
 static int f2fs_write_meta_pages(struct address_space *mapping,
@@ -138,7 +138,10 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 			BUG_ON(page->mapping != mapping);
 			BUG_ON(!PageDirty(page));
 			clear_page_dirty_for_io(page);
-			f2fs_write_meta_page(page, &wbc);
+			if (f2fs_write_meta_page(page, &wbc)) {
+				unlock_page(page);
+				break;
+			}
 			if (nwritten++ >= nr_to_write)
 				break;
 		}
@@ -161,7 +164,6 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(sbi, F2FS_DIRTY_META);
-		F2FS_SET_SB_DIRT(sbi);
 		return 1;
 	}
 	return 0;
@@ -216,19 +218,11 @@ retry:
 	new->ino = ino;
 
 	/* add new_oentry into list which is sorted by inode number */
-	if (orphan) {
-		struct orphan_inode_entry *prev;
-
-		/* get previous entry */
-		prev = list_entry(orphan->list.prev, typeof(*prev), list);
-		if (&prev->list != head)
-			/* insert new orphan inode entry */
-			list_add(&new->list, &prev->list);
-		else
-			list_add(&new->list, head);
-	} else {
+	if (orphan)
+		list_add(&new->list, this->prev);
+	else
 		list_add_tail(&new->list, head);
-	}
+
 	sbi->n_orphans++;
 out:
 	mutex_unlock(&sbi->orphan_inode_mutex);
@@ -545,7 +539,7 @@ retry:
 /*
  * Freeze all the FS-operations for checkpoint.
  */
-void block_operations(struct f2fs_sb_info *sbi)
+static void block_operations(struct f2fs_sb_info *sbi)
 {
 	int t;
 	struct writeback_control wbc = {
@@ -717,27 +711,24 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	sbi->alloc_valid_block_count = 0;
 
 	/* Here, we only have one bio having CP pack */
-	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))
-		sbi->sb->s_flags |= MS_RDONLY;
-	else
-		sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
 
-	clear_prefree_segments(sbi);
-	F2FS_RESET_SB_DIRT(sbi);
+	if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		clear_prefree_segments(sbi);
+		F2FS_RESET_SB_DIRT(sbi);
+	}
 }
 
 /*
  * We guarantee that this checkpoint procedure should not fail.
  */
-void write_checkpoint(struct f2fs_sb_info *sbi, bool blocked, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
 
-	if (!blocked) {
-		mutex_lock(&sbi->cp_mutex);
-		block_operations(sbi);
-	}
+	mutex_lock(&sbi->cp_mutex);
+	block_operations(sbi);
 
 	f2fs_submit_bio(sbi, DATA, true);
 	f2fs_submit_bio(sbi, NODE, true);

fs/f2fs/debug.c

@@ -183,10 +183,12 @@ static int stat_show(struct seq_file *s, void *v)
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+		char devname[BDEVNAME_SIZE];
 
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
+		seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
+			bdevname(si->sbi->sb->s_bdev, devname), i++);
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",

fs/f2fs/dir.c

@@ -265,7 +265,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	mutex_unlock_op(sbi, DENTRY_OPS);
 }
 
-void init_dent_inode(struct dentry *dentry, struct page *ipage)
+void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_node *rn;
 
@@ -274,20 +274,19 @@ void init_dent_inode(struct dentry *dentry, struct page *ipage)
 
 	wait_on_page_writeback(ipage);
 
-	/* copy dentry info. to this inode page */
+	/* copy name info. to this inode page */
 	rn = (struct f2fs_node *)page_address(ipage);
-	rn->i.i_namelen = cpu_to_le32(dentry->d_name.len);
-	memcpy(rn->i.i_name, dentry->d_name.name, dentry->d_name.len);
+	rn->i.i_namelen = cpu_to_le32(name->len);
+	memcpy(rn->i.i_name, name->name, name->len);
 	set_page_dirty(ipage);
 }
 
-static int init_inode_metadata(struct inode *inode, struct dentry *dentry)
+static int init_inode_metadata(struct inode *inode,
+		struct inode *dir, const struct qstr *name)
 {
-	struct inode *dir = dentry->d_parent->d_inode;
-
 	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
 		int err;
-		err = new_inode_page(inode, dentry);
+		err = new_inode_page(inode, name);
 		if (err)
 			return err;
 
@@ -310,7 +309,7 @@ static int init_inode_metadata(struct inode *inode, struct dentry *dentry)
 		if (IS_ERR(ipage))
 			return PTR_ERR(ipage);
 		set_cold_node(inode, ipage);
-		init_dent_inode(dentry, ipage);
+		init_dent_inode(name, ipage);
 		f2fs_put_page(ipage, 1);
 	}
 	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
@@ -371,7 +370,7 @@ next:
 	goto next;
 }
 
-int f2fs_add_link(struct dentry *dentry, struct inode *inode)
+int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode)
 {
 	unsigned int bit_pos;
 	unsigned int level;
@@ -380,17 +379,15 @@ int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 	f2fs_hash_t dentry_hash;
 	struct f2fs_dir_entry *de;
 	unsigned int nbucket, nblock;
-	struct inode *dir = dentry->d_parent->d_inode;
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const char *name = dentry->d_name.name;
-	size_t namelen = dentry->d_name.len;
+	size_t namelen = name->len;
 	struct page *dentry_page = NULL;
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	int slots = GET_DENTRY_SLOTS(namelen);
 	int err = 0;
 	int i;
 
-	dentry_hash = f2fs_dentry_hash(name, dentry->d_name.len);
+	dentry_hash = f2fs_dentry_hash(name->name, name->len);
 	level = 0;
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -433,7 +430,7 @@ start:
 	++level;
 	goto start;
 add_dentry:
-	err = init_inode_metadata(inode, dentry);
+	err = init_inode_metadata(inode, dir, name);
 	if (err)
 		goto fail;
 
@@ -442,7 +439,7 @@ add_dentry:
 	de = &dentry_blk->dentry[bit_pos];
 	de->hash_code = dentry_hash;
 	de->name_len = cpu_to_le16(namelen);
-	memcpy(dentry_blk->filename[bit_pos], name, namelen);
+	memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode);
 	for (i = 0; i < slots; i++)

fs/f2fs/f2fs.h

@@ -103,6 +103,20 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
 	return before;
 }
 
+/*
+ * ioctl commands
+ */
+#define F2FS_IOC_GETFLAGS               FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS               FS_IOC_SETFLAGS
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define F2FS_IOC32_GETFLAGS             FS_IOC32_GETFLAGS
+#define F2FS_IOC32_SETFLAGS             FS_IOC32_SETFLAGS
+#endif
+
 /*
  * For INODE and NODE manager
  */
@@ -141,7 +155,7 @@ struct f2fs_inode_info {
 
 	/* Use below internally in f2fs*/
 	unsigned long flags;		/* use to pass per-file flags */
-	unsigned long long data_version;/* lastes version of data for fsync */
+	unsigned long long data_version;/* latest version of data for fsync */
 	atomic_t dirty_dents;		/* # of dirty dentry pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
@@ -573,6 +587,14 @@ static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
 	return atomic_read(&sbi->nr_pages[count_type]);
 }
 
+static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
+{
+	unsigned int pages_per_sec = sbi->segs_per_sec *
+					(1 << sbi->log_blocks_per_seg);
+	return ((get_pages(sbi, block_type) + pages_per_sec - 1)
+			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+}
+
 static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
 {
 	block_t ret;
@@ -842,12 +864,12 @@ void f2fs_truncate(struct inode *);
 int f2fs_setattr(struct dentry *, struct iattr *);
 int truncate_hole(struct inode *, pgoff_t, pgoff_t);
 long f2fs_ioctl(struct file *, unsigned int, unsigned long);
+long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /*
  * inode.c
  */
 void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget_nowait(struct super_block *, unsigned long);
 struct inode *f2fs_iget(struct super_block *, unsigned long);
 void update_inode(struct inode *, struct page *);
 int f2fs_write_inode(struct inode *, struct writeback_control *);
@@ -867,12 +889,18 @@ 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(struct dentry *, struct page *);
-int f2fs_add_link(struct dentry *, 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 *);
 bool f2fs_empty_dir(struct inode *);
 
+static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
+{
+	return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name,
+				inode);
+}
+
 /*
  * super.c
  */
@@ -896,7 +924,7 @@ 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 *, struct dentry *);
+int new_inode_page(struct inode *, const struct qstr *);
 struct page *new_node_page(struct dnode_of_data *, unsigned int);
 void ra_node_page(struct f2fs_sb_info *, nid_t);
 struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
@@ -929,8 +957,7 @@ void allocate_new_segments(struct f2fs_sb_info *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 struct bio *f2fs_bio_alloc(struct block_device *, int);
 void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
-int write_meta_page(struct f2fs_sb_info *, struct page *,
-					struct writeback_control *);
+void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
 					block_t, block_t *);
 void write_data_page(struct inode *, struct page *, struct dnode_of_data*,
@@ -963,8 +990,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *);
 void set_dirty_dir_page(struct inode *, struct page *);
 void remove_dirty_dir_inode(struct inode *);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void block_operations(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool, bool);
+void write_checkpoint(struct f2fs_sb_info *, bool);
 void init_orphan_info(struct f2fs_sb_info *);
 int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);

fs/f2fs/file.c

@@ -15,6 +15,7 @@
 #include <linux/writeback.h>
 #include <linux/falloc.h>
 #include <linux/types.h>
+#include <linux/compat.h>
 #include <linux/uaccess.h>
 #include <linux/mount.h>
 
@@ -157,11 +158,11 @@ 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;
-	if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
+	else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
 		need_cp = true;
-	if (!space_for_roll_forward(sbi))
+	else if (!space_for_roll_forward(sbi))
 		need_cp = true;
-	if (need_to_sync_dir(sbi, inode))
+	else if (need_to_sync_dir(sbi, inode))
 		need_cp = true;
 
 	if (need_cp) {
@@ -298,8 +299,6 @@ void f2fs_truncate(struct inode *inode)
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
 	}
-
-	f2fs_balance_fs(F2FS_SB(inode->i_sb));
 }
 
 static int f2fs_getattr(struct vfsmount *mnt,
@@ -356,6 +355,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			attr->ia_size != i_size_read(inode)) {
 		truncate_setsize(inode, attr->ia_size);
 		f2fs_truncate(inode);
+		f2fs_balance_fs(F2FS_SB(inode->i_sb));
 	}
 
 	__setattr_copy(inode, attr);
@@ -387,12 +387,17 @@ const struct inode_operations f2fs_file_inode_operations = {
 static void fill_zero(struct inode *inode, pgoff_t index,
 					loff_t start, loff_t len)
 {
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *page;
 
 	if (!len)
 		return;
 
+	f2fs_balance_fs(sbi);
+
+	mutex_lock_op(sbi, DATA_NEW);
 	page = get_new_data_page(inode, index, false);
+	mutex_unlock_op(sbi, DATA_NEW);
 
 	if (!IS_ERR(page)) {
 		wait_on_page_writeback(page);
@@ -630,6 +635,23 @@ out:
 	}
 }
 
+#ifdef CONFIG_COMPAT
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case F2FS_IOC32_GETFLAGS:
+		cmd = F2FS_IOC_GETFLAGS;
+		break;
+	case F2FS_IOC32_SETFLAGS:
+		cmd = F2FS_IOC_SETFLAGS;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
+
 const struct file_operations f2fs_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -641,6 +663,9 @@ const struct file_operations f2fs_file_operations = {
 	.fsync		= f2fs_sync_file,
 	.fallocate	= f2fs_fallocate,
 	.unlocked_ioctl	= f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= f2fs_compat_ioctl,
+#endif
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 };

fs/f2fs/gc.c

@@ -44,10 +44,10 @@ static int gc_thread_func(void *data)
 		if (kthread_should_stop())
 			break;
 
-		f2fs_balance_fs(sbi);
-
-		if (!test_opt(sbi, BG_GC))
+		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
+			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
 			continue;
+		}
 
 		/*
 		 * [GC triggering condition]
@@ -78,7 +78,8 @@ static int gc_thread_func(void *data)
 
 		sbi->bg_gc++;
 
-		if (f2fs_gc(sbi) == GC_NONE)
+		/* if return value is not zero, no victim was selected */
+		if (f2fs_gc(sbi))
 			wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
 		else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
 			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
@@ -90,7 +91,10 @@ static int gc_thread_func(void *data)
 int start_gc_thread(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_gc_kthread *gc_th;
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
 
+	if (!test_opt(sbi, BG_GC))
+		return 0;
 	gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
 	if (!gc_th)
 		return -ENOMEM;
@@ -98,9 +102,10 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
 	sbi->gc_thread = gc_th;
 	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
 	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
-				GC_THREAD_NAME);
+			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(gc_th->f2fs_gc_task)) {
 		kfree(gc_th);
+		sbi->gc_thread = NULL;
 		return -ENOMEM;
 	}
 	return 0;
@@ -141,6 +146,9 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 				struct victim_sel_policy *p)
 {
+	/* SSR allocates in a segment unit */
+	if (p->alloc_mode == SSR)
+		return 1 << sbi->log_blocks_per_seg;
 	if (p->gc_mode == GC_GREEDY)
 		return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
@@ -356,7 +364,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
 	sentry = get_seg_entry(sbi, segno);
 	ret = f2fs_test_bit(offset, sentry->cur_valid_map);
 	mutex_unlock(&sit_i->sentry_lock);
-	return ret ? GC_OK : GC_NEXT;
+	return ret;
 }
 
 /*
@@ -364,7 +372,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
  * On validity, copy that node with cold status, otherwise (invalid node)
  * ignore that.
  */
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
 		struct f2fs_summary *sum, unsigned int segno, int gc_type)
 {
 	bool initial = true;
@@ -376,21 +384,12 @@ next_step:
 	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
 		nid_t nid = le32_to_cpu(entry->nid);
 		struct page *node_page;
-		int err;
 
-		/*
-		 * It makes sure that free segments are able to write
-		 * all the dirty node pages before CP after this CP.
-		 * So let's check the space of dirty node pages.
-		 */
-		if (should_do_checkpoint(sbi)) {
-			mutex_lock(&sbi->cp_mutex);
-			block_operations(sbi);
-			return GC_BLOCKED;
-		}
+		/* stop BG_GC if there is not enough free sections. */
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+			return;
 
-		err = check_valid_map(sbi, segno, off);
-		if (err == GC_NEXT)
+		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
 
 		if (initial) {
@@ -420,7 +419,6 @@ next_step:
 		};
 		sync_node_pages(sbi, 0, &wbc);
 	}
-	return GC_DONE;
 }
 
 /*
@@ -463,13 +461,13 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 	node_page = get_node_page(sbi, nid);
 	if (IS_ERR(node_page))
-		return GC_NEXT;
+		return 0;
 
 	get_node_info(sbi, nid, dni);
 
 	if (sum->version != dni->version) {
 		f2fs_put_page(node_page, 1);
-		return GC_NEXT;
+		return 0;
 	}
 
 	*nofs = ofs_of_node(node_page);
@@ -477,8 +475,8 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	f2fs_put_page(node_page, 1);
 
 	if (source_blkaddr != blkaddr)
-		return GC_NEXT;
-	return GC_OK;
+		return 0;
+	return 1;
 }
 
 static void move_data_page(struct inode *inode, struct page *page, int gc_type)
@@ -519,13 +517,13 @@ out:
  * If the parent node is not valid or the data block address is different,
  * the victim data block is ignored.
  */
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		struct list_head *ilist, unsigned int segno, int gc_type)
 {
 	struct super_block *sb = sbi->sb;
 	struct f2fs_summary *entry;
 	block_t start_addr;
-	int err, off;
+	int off;
 	int phase = 0;
 
 	start_addr = START_BLOCK(sbi, segno);
@@ -539,20 +537,11 @@ next_step:
 		unsigned int ofs_in_node, nofs;
 		block_t start_bidx;
 
-		/*
-		 * It makes sure that free segments are able to write
-		 * all the dirty node pages before CP after this CP.
-		 * So let's check the space of dirty node pages.
-		 */
-		if (should_do_checkpoint(sbi)) {
-			mutex_lock(&sbi->cp_mutex);
-			block_operations(sbi);
-			err = GC_BLOCKED;
-			goto stop;
-		}
+		/* stop BG_GC if there is not enough free sections. */
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+			return;
 
-		err = check_valid_map(sbi, segno, off);
-		if (err == GC_NEXT)
+		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
 
 		if (phase == 0) {
@@ -561,8 +550,7 @@ next_step:
 		}
 
 		/* Get an inode by ino with checking validity */
-		err = check_dnode(sbi, entry, &dni, start_addr + off, &nofs);
-		if (err == GC_NEXT)
+		if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
 			continue;
 
 		if (phase == 1) {
@@ -574,7 +562,7 @@ next_step:
 		ofs_in_node = le16_to_cpu(entry->ofs_in_node);
 
 		if (phase == 2) {
-			inode = f2fs_iget_nowait(sb, dni.ino);
+			inode = f2fs_iget(sb, dni.ino);
 			if (IS_ERR(inode))
 				continue;
 
@@ -602,11 +590,9 @@ next_iput:
 	}
 	if (++phase < 4)
 		goto next_step;
-	err = GC_DONE;
-stop:
+
 	if (gc_type == FG_GC)
 		f2fs_submit_bio(sbi, DATA, true);
-	return err;
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -620,17 +606,16 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 	return ret;
 }
 
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
 				struct list_head *ilist, int gc_type)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
-	int ret = GC_DONE;
 
 	/* read segment summary of victim */
 	sum_page = get_sum_page(sbi, segno);
 	if (IS_ERR(sum_page))
-		return GC_ERROR;
+		return;
 
 	/*
 	 * CP needs to lock sum_page. In this time, we don't need
@@ -642,17 +627,16 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
 
 	switch (GET_SUM_TYPE((&sum->footer))) {
 	case SUM_TYPE_NODE:
-		ret = gc_node_segment(sbi, sum->entries, segno, gc_type);
+		gc_node_segment(sbi, sum->entries, segno, gc_type);
 		break;
 	case SUM_TYPE_DATA:
-		ret = gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
+		gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
 		break;
 	}
 	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
 	stat_inc_call_count(sbi->stat_info);
 
 	f2fs_put_page(sum_page, 0);
-	return ret;
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi)
@@ -660,40 +644,38 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 	struct list_head ilist;
 	unsigned int segno, i;
 	int gc_type = BG_GC;
-	int gc_status = GC_NONE;
+	int nfree = 0;
+	int ret = -1;
 
 	INIT_LIST_HEAD(&ilist);
 gc_more:
 	if (!(sbi->sb->s_flags & MS_ACTIVE))
 		goto stop;
 
-	if (has_not_enough_free_secs(sbi))
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree))
 		gc_type = FG_GC;
 
 	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
 		goto stop;
+	ret = 0;
 
-	for (i = 0; i < sbi->segs_per_sec; i++) {
-		/*
-		 * do_garbage_collect will give us three gc_status:
-		 * GC_ERROR, GC_DONE, and GC_BLOCKED.
-		 * If GC is finished uncleanly, we have to return
-		 * the victim to dirty segment list.
-		 */
-		gc_status = do_garbage_collect(sbi, segno + i, &ilist, gc_type);
-		if (gc_status != GC_DONE)
-			break;
-	}
-	if (has_not_enough_free_secs(sbi)) {
-		write_checkpoint(sbi, (gc_status == GC_BLOCKED), false);
-		if (has_not_enough_free_secs(sbi))
-			goto gc_more;
-	}
+	for (i = 0; i < sbi->segs_per_sec; i++)
+		do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+
+	if (gc_type == FG_GC &&
+			get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+		nfree++;
+
+	if (has_not_enough_free_secs(sbi, nfree))
+		goto gc_more;
+
+	if (gc_type == FG_GC)
+		write_checkpoint(sbi, false);
 stop:
 	mutex_unlock(&sbi->gc_mutex);
 
 	put_gc_inode(&ilist);
-	return gc_status;
+	return ret;
 }
 
 void build_gc_manager(struct f2fs_sb_info *sbi)

fs/f2fs/gc.h

@@ -8,7 +8,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#define GC_THREAD_NAME	"f2fs_gc_task"
 #define GC_THREAD_MIN_WB_PAGES		1	/*
 						 * a threshold to determine
 						 * whether IO subsystem is idle
@@ -23,15 +22,6 @@
 /* Search max. number of dirty segments to select a victim segment */
 #define MAX_VICTIM_SEARCH	20
 
-enum {
-	GC_NONE = 0,
-	GC_ERROR,
-	GC_OK,
-	GC_NEXT,
-	GC_BLOCKED,
-	GC_DONE,
-};
-
 struct f2fs_gc_kthread {
 	struct task_struct *f2fs_gc_task;
 	wait_queue_head_t gc_wait_queue_head;
@@ -104,14 +94,3 @@ static inline int is_idle(struct f2fs_sb_info *sbi)
 	struct request_list *rl = &q->root_rl;
 	return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
 }
-
-static inline bool should_do_checkpoint(struct f2fs_sb_info *sbi)
-{
-	unsigned int pages_per_sec = sbi->segs_per_sec *
-					(1 << sbi->log_blocks_per_seg);
-	int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
-			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
-	int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
-			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
-	return free_sections(sbi) <= (node_secs + 2 * dent_secs + 2);
-}

fs/f2fs/inode.c

@@ -16,11 +16,6 @@
 #include "f2fs.h"
 #include "node.h"
 
-struct f2fs_iget_args {
-	u64 ino;
-	int on_free;
-};
-
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
@@ -40,34 +35,6 @@ void f2fs_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_DIRSYNC;
 }
 
-static int f2fs_iget_test(struct inode *inode, void *data)
-{
-	struct f2fs_iget_args *args = data;
-
-	if (inode->i_ino != args->ino)
-		return 0;
-	if (inode->i_state & (I_FREEING | I_WILL_FREE)) {
-		args->on_free = 1;
-		return 0;
-	}
-	return 1;
-}
-
-struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino)
-{
-	struct f2fs_iget_args args = {
-		.ino = ino,
-		.on_free = 0
-	};
-	struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args);
-
-	if (inode)
-		return inode;
-	if (!args.on_free)
-		return f2fs_iget(sb, ino);
-	return ERR_PTR(-ENOENT);
-}
-
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -100,6 +67,10 @@ static int do_read_inode(struct inode *inode)
 	inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
 	inode->i_generation = le32_to_cpu(ri->i_generation);
+	if (ri->i_addr[0])
+		inode->i_rdev = old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+	else
+		inode->i_rdev = new_decode_dev(le32_to_cpu(ri->i_addr[1]));
 
 	fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
 	fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
@@ -203,6 +174,20 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
 	ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
 	ri->i_generation = cpu_to_le32(inode->i_generation);
+
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+		if (old_valid_dev(inode->i_rdev)) {
+			ri->i_addr[0] =
+				cpu_to_le32(old_encode_dev(inode->i_rdev));
+			ri->i_addr[1] = 0;
+		} else {
+			ri->i_addr[0] = 0;
+			ri->i_addr[1] =
+				cpu_to_le32(new_encode_dev(inode->i_rdev));
+			ri->i_addr[2] = 0;
+		}
+	}
+
 	set_cold_node(inode, node_page);
 	set_page_dirty(node_page);
 }
@@ -260,6 +245,7 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
+	sb_start_intwrite(inode->i_sb);
 	set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
 	i_size_write(inode, 0);
 
@@ -267,6 +253,7 @@ void f2fs_evict_inode(struct inode *inode)
 		f2fs_truncate(inode);
 
 	remove_inode_page(inode);
+	sb_end_intwrite(inode->i_sb);
 no_delete:
 	clear_inode(inode);
 }

fs/f2fs/node.c

@@ -104,7 +104,7 @@ static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid)
 			f2fs_put_page(page, 1);
 			continue;
 		}
-		page_cache_release(page);
+		f2fs_put_page(page, 0);
 	}
 }
 
@@ -660,7 +660,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	int err = 0, cont = 1;
 	int level, offset[4], noffset[4];
-	unsigned int nofs;
+	unsigned int nofs = 0;
 	struct f2fs_node *rn;
 	struct dnode_of_data dn;
 	struct page *page;
@@ -780,7 +780,7 @@ int remove_inode_page(struct inode *inode)
 	return 0;
 }
 
-int new_inode_page(struct inode *inode, struct dentry *dentry)
+int new_inode_page(struct inode *inode, const struct qstr *name)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *page;
@@ -790,7 +790,7 @@ int new_inode_page(struct inode *inode, struct dentry *dentry)
 	set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
 	mutex_lock_op(sbi, NODE_NEW);
 	page = new_node_page(&dn, 0);
-	init_dent_inode(dentry, page);
+	init_dent_inode(name, page);
 	mutex_unlock_op(sbi, NODE_NEW);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
@@ -874,15 +874,11 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 		return;
 
 	if (read_node_page(apage, READA))
-		goto unlock_out;
+		unlock_page(apage);
 
-	page_cache_release(apage);
-	return;
-
-unlock_out:
-	unlock_page(apage);
 release_out:
-	page_cache_release(apage);
+	f2fs_put_page(apage, 0);
+	return;
 }
 
 struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1139,7 +1135,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 	/* First check balancing cached NAT entries */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
-		write_checkpoint(sbi, false, false);
+		write_checkpoint(sbi, false);
 		return 0;
 	}
 

fs/f2fs/recovery.c

@@ -42,7 +42,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 {
 	struct f2fs_node *raw_node = (struct f2fs_node *)kmap(ipage);
 	struct f2fs_inode *raw_inode = &(raw_node->i);
-	struct dentry dent, parent;
+	struct qstr name;
 	struct f2fs_dir_entry *de;
 	struct page *page;
 	struct inode *dir;
@@ -57,17 +57,15 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 		goto out;
 	}
 
-	parent.d_inode = dir;
-	dent.d_parent = &parent;
-	dent.d_name.len = le32_to_cpu(raw_inode->i_namelen);
-	dent.d_name.name = raw_inode->i_name;
+	name.len = le32_to_cpu(raw_inode->i_namelen);
+	name.name = raw_inode->i_name;
 
-	de = f2fs_find_entry(dir, &dent.d_name, &page);
+	de = f2fs_find_entry(dir, &name, &page);
 	if (de) {
 		kunmap(page);
 		f2fs_put_page(page, 0);
 	} else {
-		err = f2fs_add_link(&dent, inode);
+		err = __f2fs_add_link(dir, &name, inode);
 	}
 	iput(dir);
 out:
@@ -226,7 +224,7 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	f2fs_put_page(node_page, 1);
 
 	/* Deallocate previous index in the node page */
-	inode = f2fs_iget_nowait(sbi->sb, ino);
+	inode = f2fs_iget(sbi->sb, ino);
 	if (IS_ERR(inode))
 		return;
 
@@ -373,5 +371,5 @@ void recover_fsync_data(struct f2fs_sb_info *sbi)
 out:
 	destroy_fsync_dnodes(sbi, &inode_list);
 	kmem_cache_destroy(fsync_entry_slab);
-	write_checkpoint(sbi, false, false);
+	write_checkpoint(sbi, false);
 }

fs/f2fs/segment.c

@@ -29,7 +29,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi)
 	 * We should do GC or end up with checkpoint, if there are so many dirty
 	 * dir/node pages without enough free segments.
 	 */
-	if (has_not_enough_free_secs(sbi)) {
+	if (has_not_enough_free_secs(sbi, 0)) {
 		mutex_lock(&sbi->gc_mutex);
 		f2fs_gc(sbi);
 	}
@@ -308,7 +308,7 @@ static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi,
 	 * If there is not enough reserved sections,
 	 * we should not reuse prefree segments.
 	 */
-	if (has_not_enough_free_secs(sbi))
+	if (has_not_enough_free_secs(sbi, 0))
 		return NULL_SEGNO;
 
 	/*
@@ -536,6 +536,23 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
 	}
 }
 
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+
+	if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
+		return v_ops->get_victim(sbi,
+				&(curseg)->next_segno, BG_GC, type, SSR);
+
+	/* For data segments, let's do SSR more intensively */
+	for (; type >= CURSEG_HOT_DATA; type--)
+		if (v_ops->get_victim(sbi, &(curseg)->next_segno,
+						BG_GC, type, SSR))
+			return 1;
+	return 0;
+}
+
 /*
  * flush out current segment and replace it with new segment
  * This function should be returned with success, otherwise BUG
@@ -600,6 +617,7 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 			if (page->mapping)
 				set_bit(AS_EIO, &page->mapping->flags);
 			set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
+			p->sbi->sb->s_flags |= MS_RDONLY;
 		}
 		end_page_writeback(page);
 		dec_page_count(p->sbi, F2FS_WRITEBACK);
@@ -815,15 +833,10 @@ static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-int write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
-			struct writeback_control *wbc)
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
-	if (wbc->for_reclaim)
-		return AOP_WRITEPAGE_ACTIVATE;
-
 	set_page_writeback(page);
 	submit_write_page(sbi, page, page->index, META);
-	return 0;
 }
 
 void write_node_page(struct f2fs_sb_info *sbi, struct page *page,

fs/f2fs/segment.h

@@ -450,29 +450,16 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 	return (free_sections(sbi) < overprovision_sections(sbi));
 }
 
-static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	return DIRTY_I(sbi)->v_ops->get_victim(sbi,
-				&(curseg)->next_segno, BG_GC, type, SSR);
-}
-
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi)
-{
-	unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) *
-			sbi->segs_per_sec;
-	int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
-			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
-	int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
-			>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
 	if (sbi->por_doing)
 		return false;
 
-	if (free_sections(sbi) <= (node_secs + 2 * dent_secs +
-						reserved_sections(sbi)))
-		return true;
-	return false;
+	return ((free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
+						reserved_sections(sbi)));
 }
 
 static inline int utilization(struct f2fs_sb_info *sbi)

fs/f2fs/super.c

@@ -112,7 +112,7 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_stats(sbi);
 	stop_gc_thread(sbi);
 
-	write_checkpoint(sbi, false, true);
+	write_checkpoint(sbi, true);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
@@ -136,13 +136,29 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 		return 0;
 
 	if (sync)
-		write_checkpoint(sbi, false, false);
+		write_checkpoint(sbi, false);
 	else
 		f2fs_balance_fs(sbi);
 
 	return 0;
 }
 
+static int f2fs_freeze(struct super_block *sb)
+{
+	int err;
+
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	err = f2fs_sync_fs(sb, 1);
+	return err;
+}
+
+static int f2fs_unfreeze(struct super_block *sb)
+{
+	return 0;
+}
+
 static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
@@ -198,7 +214,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",noacl");
 #endif
 	if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
-		seq_puts(seq, ",disable_ext_indentify");
+		seq_puts(seq, ",disable_ext_identify");
 
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
@@ -213,6 +229,8 @@ static struct super_operations f2fs_sops = {
 	.evict_inode	= f2fs_evict_inode,
 	.put_super	= f2fs_put_super,
 	.sync_fs	= f2fs_sync_fs,
+	.freeze_fs	= f2fs_freeze,
+	.unfreeze_fs	= f2fs_unfreeze,
 	.statfs		= f2fs_statfs,
 };
 
@@ -366,14 +384,23 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
+	/* Currently, support only 4KB page cache size */
+	if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid page_cache_size (%lu), supports only 4KB\n",
+			PAGE_CACHE_SIZE);
+		return 1;
+	}
+
 	/* Currently, support only 4KB block size */
 	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
-	if (blocksize != PAGE_CACHE_SIZE) {
+	if (blocksize != F2FS_BLKSIZE) {
 		f2fs_msg(sb, KERN_INFO,
 			"Invalid blocksize (%u), supports only 4KB\n",
 			blocksize);
 		return 1;
 	}
+
 	if (le32_to_cpu(raw_super->log_sectorsize) !=
 					F2FS_LOG_SECTOR_SIZE) {
 		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
@@ -387,10 +414,11 @@ static int sanity_check_raw_super(struct super_block *sb,
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
-				struct f2fs_checkpoint *ckpt)
+static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -401,6 +429,11 @@ static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
 
 	if (fsmeta >= total)
 		return 1;
+
+	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
+		return 1;
+	}
 	return 0;
 }
 
@@ -429,6 +462,32 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 }
 
+static int validate_superblock(struct super_block *sb,
+		struct f2fs_super_block **raw_super,
+		struct buffer_head **raw_super_buf, sector_t block)
+{
+	const char *super = (block == 0 ? "first" : "second");
+
+	/* read f2fs raw super block */
+	*raw_super_buf = sb_bread(sb, block);
+	if (!*raw_super_buf) {
+		f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
+				super);
+		return 1;
+	}
+
+	*raw_super = (struct f2fs_super_block *)
+		((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+
+	/* sanity checking of raw super */
+	if (!sanity_check_raw_super(sb, *raw_super))
+		return 0;
+
+	f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
+				"in %s superblock", super);
+	return 1;
+}
+
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct f2fs_sb_info *sbi;
@@ -449,16 +508,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	/* read f2fs raw super block */
-	raw_super_buf = sb_bread(sb, 0);
-	if (!raw_super_buf) {
-		err = -EIO;
-		f2fs_msg(sb, KERN_ERR, "unable to read superblock");
-		goto free_sbi;
+	if (validate_superblock(sb, &raw_super, &raw_super_buf, 0)) {
+		brelse(raw_super_buf);
+		if (validate_superblock(sb, &raw_super, &raw_super_buf, 1))
+			goto free_sb_buf;
 	}
-	raw_super = (struct f2fs_super_block *)
-			((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET);
-
 	/* init some FS parameters */
 	sbi->active_logs = NR_CURSEG_TYPE;
 
@@ -474,12 +528,6 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (parse_options(sb, sbi, (char *)data))
 		goto free_sb_buf;
 
-	/* sanity checking of raw super */
-	if (sanity_check_raw_super(sb, raw_super)) {
-		f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem");
-		goto free_sb_buf;
-	}
-
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
@@ -525,7 +573,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 
 	/* sanity checking of checkpoint */
 	err = -EINVAL;
-	if (sanity_check_ckpt(raw_super, sbi->ckpt)) {
+	if (sanity_check_ckpt(sbi)) {
 		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
 		goto free_cp;
 	}