Merge tag 'for-f2fs-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches:
   - support inline xattrs
   - add sysfs support to control GCs explicitly
   - add proc entry to show the current segment usage information
   - improve the GC/SSR performance

  The other bug fixes are as follows:
   - avoid the overflow on status calculation
   - fix some error handling routines
   - fix inconsistent xattr states after power-off-recovery
   - fix incorrect xattr node offset definition
   - fix deadlock condition in fsync
   - fix the fdatasync routine for power-off-recovery"

* tag 'for-f2fs-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: optimize gc for better performance
  f2fs: merge more bios of node block writes
  f2fs: avoid an overflow during utilization calculation
  f2fs: trigger GC when there are prefree segments
  f2fs: use strncasecmp() simplify the string comparison
  f2fs: fix omitting to update inode page
  f2fs: support the inline xattrs
  f2fs: add the truncate_xattr_node function
  f2fs: introduce __find_xattr for readability
  f2fs: reserve the xattr space dynamically
  f2fs: add flags for inline xattrs
  f2fs: fix error return code in init_f2fs_fs()
  f2fs: fix wrong BUG_ON condition
  f2fs: fix memory leak when init f2fs filesystem fail
  f2fs: fix a compound statement label error
  f2fs: avoid writing inode redundantly when creating a file
  f2fs: alloc_page() doesn't return an ERR_PTR
  f2fs: should cover i_xattr_nid with its xattr node page lock
  f2fs: check the free space first in new_node_page
  f2fs: clean up the needless end 'return' of void function
  ...

21 files changed, 890 insertions, 344 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
new file mode 100644
index 00000000000..31942efcaf0
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -0,0 +1,26 @@
+What:		/sys/fs/f2fs/<disk>/gc_max_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the maximun sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_min_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the minimum sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_no_gc_sleep_time
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the default sleep time for gc_thread. Time
+		 is in milliseconds.
+
+What:		/sys/fs/f2fs/<disk>/gc_idle
+Date:		July 2013
+Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
+Description:
+		 Controls the victim selection policy for garbage collection.
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index b91e2f26b67..3cd27bed634 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -18,8 +18,8 @@ according to its internal geometry or flash memory management scheme, namely FTL
 F2FS and its tools support various parameters not only for configuring on-disk
 layout, but also for selecting allocation and cleaning algorithms.
 
-The file system formatting tool, "mkfs.f2fs", is available from the following
-git tree:
+The following git tree provides the file system formatting tool (mkfs.f2fs),
+a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs).
 >> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
 
 For reporting bugs and sending patches, please use the following mailing list:
@@ -133,6 +133,38 @@ f2fs. Each file shows the whole f2fs information.
  - current memory footprint consumed by f2fs.
 
 ================================================================================
+SYSFS ENTRIES
+================================================================================
+
+Information about mounted f2f2 file systems can be found in
+/sys/fs/f2fs.  Each mounted filesystem will have a directory in
+/sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda).
+The files in each per-device directory are shown in table below.
+
+Files in /sys/fs/f2fs/<devname>
+(see also Documentation/ABI/testing/sysfs-fs-f2fs)
+..............................................................................
+ File                         Content
+
+ gc_max_sleep_time            This tuning parameter controls the maximum sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_min_sleep_time            This tuning parameter controls the minimum sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_no_gc_sleep_time          This tuning parameter controls the default sleep
+                              time for the garbage collection thread. Time is
+                              in milliseconds.
+
+ gc_idle                      This parameter controls the selection of victim
+                              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.
+
+================================================================================
 USAGE
 ================================================================================
 
@@ -149,8 +181,12 @@ USAGE
  # mkfs.f2fs -l label /dev/block_device
  # mount -t f2fs /dev/block_device /mnt/f2fs
 
-Format options
---------------
+mkfs.f2fs
+---------
+The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem,
+which builds a basic on-disk layout.
+
+The options consist of:
 -l [label]   : Give a volume label, up to 512 unicode name.
 -a [0 or 1]  : Split start location of each area for heap-based allocation.
                1 is set by default, which performs this.
@@ -164,6 +200,37 @@ Format options
 -t [0 or 1]  : Disable discard command or not.
                1 is set by default, which conducts discard.
 
+fsck.f2fs
+---------
+The fsck.f2fs is a tool to check the consistency of an f2fs-formatted
+partition, which examines whether the filesystem metadata and user-made data
+are cross-referenced correctly or not.
+Note that, initial version of the tool does not fix any inconsistency.
+
+The options consist of:
+  -d debug level [default:0]
+
+dump.f2fs
+---------
+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
+able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
+./dump_sit respectively.
+
+The options consist of:
+  -d debug level [default:0]
+  -i inode no (hex)
+  -s [SIT dump segno from #1~#2 (decimal), for all 0~-1]
+  -a [SSA dump segno from #1~#2 (decimal), for all 0~-1]
+
+Examples:
+# dump.f2fs -i [ino] /dev/sdx
+# dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
+# dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
+
 ================================================================================
 DESIGN
 ================================================================================
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 66a6b85a51d..bb312201ca9 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -182,7 +182,7 @@ const struct address_space_operations f2fs_meta_aops = {
 	.set_page_dirty	= f2fs_set_meta_page_dirty,
 };
 
-int check_orphan_space(struct f2fs_sb_info *sbi)
+int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 {
 	unsigned int max_orphans;
 	int err = 0;
@@ -197,10 +197,19 @@ int check_orphan_space(struct f2fs_sb_info *sbi)
 	mutex_lock(&sbi->orphan_inode_mutex);
 	if (sbi->n_orphans >= max_orphans)
 		err = -ENOSPC;
+	else
+		sbi->n_orphans++;
 	mutex_unlock(&sbi->orphan_inode_mutex);
 	return err;
 }
 
+void release_orphan_inode(struct f2fs_sb_info *sbi)
+{
+	mutex_lock(&sbi->orphan_inode_mutex);
+	sbi->n_orphans--;
+	mutex_unlock(&sbi->orphan_inode_mutex);
+}
+
 void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct list_head *head, *this;
@@ -229,21 +238,18 @@ retry:
 		list_add(&new->list, this->prev);
 	else
 		list_add_tail(&new->list, head);
-
-	sbi->n_orphans++;
 out:
 	mutex_unlock(&sbi->orphan_inode_mutex);
 }
 
 void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	struct list_head *this, *next, *head;
+	struct list_head *head;
 	struct orphan_inode_entry *orphan;
 
 	mutex_lock(&sbi->orphan_inode_mutex);
 	head = &sbi->orphan_inode_list;
-	list_for_each_safe(this, next, head) {
-		orphan = list_entry(this, struct orphan_inode_entry, list);
+	list_for_each_entry(orphan, head, list) {
 		if (orphan->ino == ino) {
 			list_del(&orphan->list);
 			kmem_cache_free(orphan_entry_slab, orphan);
@@ -373,7 +379,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
-	pre_version = le64_to_cpu(cp_block->checkpoint_ver);
+	pre_version = cur_cp_version(cp_block);
 
 	/* Read the 2nd cp block in this CP pack */
 	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
@@ -388,7 +394,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
-	cur_version = le64_to_cpu(cp_block->checkpoint_ver);
+	cur_version = cur_cp_version(cp_block);
 
 	if (cur_version == pre_version) {
 		*version = cur_version;
@@ -793,7 +799,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	 * Increase the version number so that
 	 * SIT entries and seg summaries are written at correct place
 	 */
-	ckpt_ver = le64_to_cpu(ckpt->checkpoint_ver);
+	ckpt_ver = cur_cp_version(ckpt);
 	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 035f9a345cd..941f9b9ca3a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -37,9 +37,9 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
 	struct page *node_page = dn->node_page;
 	unsigned int ofs_in_node = dn->ofs_in_node;
 
-	wait_on_page_writeback(node_page);
+	f2fs_wait_on_page_writeback(node_page, NODE, false);
 
-	rn = (struct f2fs_node *)page_address(node_page);
+	rn = F2FS_NODE(node_page);
 
 	/* Get physical address of data block */
 	addr_array = blkaddr_in_node(rn);
@@ -117,7 +117,8 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 	block_t start_blkaddr, end_blkaddr;
 
 	BUG_ON(blk_addr == NEW_ADDR);
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page)) + dn->ofs_in_node;
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+							dn->ofs_in_node;
 
 	/* Update the page address in the parent node */
 	__set_data_blkaddr(dn, blk_addr);
@@ -176,7 +177,6 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 end_update:
 	write_unlock(&fi->ext.ext_lock);
 	sync_inode_page(dn);
-	return;
 }
 
 struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
@@ -260,8 +260,17 @@ repeat:
 	if (PageUptodate(page))
 		return page;
 
-	BUG_ON(dn.data_blkaddr == NEW_ADDR);
-	BUG_ON(dn.data_blkaddr == NULL_ADDR);
+	/*
+	 * A new dentry page is allocated but not able to be written, since its
+	 * new inode page couldn't be allocated due to -ENOSPC.
+	 * In such the case, its blkaddr can be remained as NEW_ADDR.
+	 * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
+	 */
+	if (dn.data_blkaddr == NEW_ADDR) {
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
+		return page;
+	}
 
 	err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
 	if (err)
@@ -365,7 +374,6 @@ static void read_end_io(struct bio *bio, int err)
 		}
 		unlock_page(page);
 	} while (bvec >= bio->bi_io_vec);
-	kfree(bio->bi_private);
 	bio_put(bio);
 }
 
@@ -391,7 +399,6 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
 	bio->bi_end_io = read_end_io;
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
-		kfree(bio->bi_private);
 		bio_put(bio);
 		up_read(&sbi->bio_sem);
 		f2fs_put_page(page, 1);
@@ -442,7 +449,7 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
 		unsigned int end_offset;
 
 		end_offset = IS_INODE(dn.node_page) ?
-				ADDRS_PER_INODE :
+				ADDRS_PER_INODE(F2FS_I(inode)) :
 				ADDRS_PER_BLOCK;
 
 		clear_buffer_new(bh_result);
@@ -636,9 +643,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	int err = 0;
 	int ilock;
 
-	/* for nobh_write_end */
-	*fsdata = NULL;
-
 	f2fs_balance_fs(sbi);
 repeat:
 	page = grab_cache_page_write_begin(mapping, index, flags);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0d6c6aafb23..a84b0a8e685 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -29,7 +29,7 @@ static DEFINE_MUTEX(f2fs_stat_mutex);
 
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_stat_info *si = sbi->stat_info;
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
 	int i;
 
 	/* valid check of the segment numbers */
@@ -83,7 +83,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
  */
 static void update_sit_info(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_stat_info *si = sbi->stat_info;
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
 	unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist;
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned int segno, vblocks;
@@ -118,7 +118,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
  */
 static void update_mem_info(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_stat_info *si = sbi->stat_info;
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
 	unsigned npages;
 
 	if (si->base_mem)
@@ -253,21 +253,21 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->nats, NM_WOUT_THRESHOLD);
 		seq_printf(s, "  - SITs: %5d\n  - free_nids: %5d\n",
 			   si->sits, si->fnids);
-		seq_printf(s, "\nDistribution of User Blocks:");
-		seq_printf(s, " [ valid | invalid | free ]\n");
-		seq_printf(s, "  [");
+		seq_puts(s, "\nDistribution of User Blocks:");
+		seq_puts(s, " [ valid | invalid | free ]\n");
+		seq_puts(s, "  [");
 
 		for (j = 0; j < si->util_valid; j++)
-			seq_printf(s, "-");
-		seq_printf(s, "|");
+			seq_putc(s, '-');
+		seq_putc(s, '|');
 
 		for (j = 0; j < si->util_invalid; j++)
-			seq_printf(s, "-");
-		seq_printf(s, "|");
+			seq_putc(s, '-');
+		seq_putc(s, '|');
 
 		for (j = 0; j < si->util_free; j++)
-			seq_printf(s, "-");
-		seq_printf(s, "]\n\n");
+			seq_putc(s, '-');
+		seq_puts(s, "]\n\n");
 		seq_printf(s, "SSR: %u blocks in %u segments\n",
 			   si->block_count[SSR], si->segment_count[SSR]);
 		seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -305,11 +305,10 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_stat_info *si;
 
-	sbi->stat_info = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
-	if (!sbi->stat_info)
+	si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
+	if (!si)
 		return -ENOMEM;
 
-	si = sbi->stat_info;
 	si->all_area_segs = le32_to_cpu(raw_super->segment_count);
 	si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
 	si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -319,6 +318,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	si->main_area_zones = si->main_area_sections /
 				le32_to_cpu(raw_super->secs_per_zone);
 	si->sbi = sbi;
+	sbi->stat_info = si;
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
@@ -329,13 +329,13 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 
 void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_stat_info *si = sbi->stat_info;
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_del(&si->stat_list);
 	mutex_unlock(&f2fs_stat_mutex);
 
-	kfree(sbi->stat_info);
+	kfree(si);
 }
 
 void __init f2fs_create_root_stats(void)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 62f0d5977c6..384c6daf9a8 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -270,12 +270,27 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 	struct f2fs_node *rn;
 
 	/* copy name info. to this inode page */
-	rn = (struct f2fs_node *)page_address(ipage);
+	rn = F2FS_NODE(ipage);
 	rn->i.i_namelen = cpu_to_le32(name->len);
 	memcpy(rn->i.i_name, name->name, name->len);
 	set_page_dirty(ipage);
 }
 
+int update_dent_inode(struct inode *inode, const struct qstr *name)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *page;
+
+	page = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	init_dent_inode(name, page);
+	f2fs_put_page(page, 1);
+
+	return 0;
+}
+
 static int make_empty_dir(struct inode *inode,
 		struct inode *parent, struct page *page)
 {
@@ -557,6 +572,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 
 		if (inode->i_nlink == 0)
 			add_orphan_inode(sbi, inode->i_ino);
+		else
+			release_orphan_inode(sbi);
 	}
 
 	if (bit_pos == NR_DENTRY_IN_BLOCK) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 467d42d65c4..608f0df5b91 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/crc32.h>
 #include <linux/magic.h>
+#include <linux/kobject.h>
 
 /*
  * For mount options
@@ -28,6 +29,7 @@
 #define F2FS_MOUNT_XATTR_USER		0x00000010
 #define F2FS_MOUNT_POSIX_ACL		0x00000020
 #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
+#define F2FS_MOUNT_INLINE_XATTR		0x00000080
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -134,11 +136,13 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
 /*
  * For INODE and NODE manager
  */
-#define XATTR_NODE_OFFSET	(-1)	/*
-					 * store xattrs to one node block per
-					 * file keeping -1 as its node offset to
-					 * distinguish from index node blocks.
-					 */
+/*
+ * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
+ * as its node offset to distinguish from index node blocks.
+ * But some bits are used to mark the node block.
+ */
+#define XATTR_NODE_OFFSET	((((unsigned int)-1) << OFFSET_BIT_SHIFT) \
+				>> OFFSET_BIT_SHIFT)
 enum {
 	ALLOC_NODE,			/* allocate a new node page if needed */
 	LOOKUP_NODE,			/* look up a node without readahead */
@@ -178,6 +182,7 @@ struct f2fs_inode_info {
 	f2fs_hash_t chash;		/* hash value of given file name */
 	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 */
 };
 
@@ -296,15 +301,6 @@ struct f2fs_sm_info {
 };
 
 /*
- * For directory operation
- */
-#define	NODE_DIR1_BLOCK		(ADDRS_PER_INODE + 1)
-#define	NODE_DIR2_BLOCK		(ADDRS_PER_INODE + 2)
-#define	NODE_IND1_BLOCK		(ADDRS_PER_INODE + 3)
-#define	NODE_IND2_BLOCK		(ADDRS_PER_INODE + 4)
-#define	NODE_DIND_BLOCK		(ADDRS_PER_INODE + 5)
-
-/*
  * For superblock
  */
 /*
@@ -350,6 +346,7 @@ enum page_type {
 
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
+	struct proc_dir_entry *s_proc;		/* proc entry */
 	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
 	int s_dirty;				/* dirty flag for checkpoint */
@@ -429,6 +426,10 @@ struct f2fs_sb_info {
 #endif
 	unsigned int last_victim[2];		/* last victim segment # */
 	spinlock_t stat_lock;			/* lock for stat operations */
+
+	/* For sysfs suppport */
+	struct kobject s_kobj;
+	struct completion s_kobj_unregister;
 };
 
 /*
@@ -454,6 +455,11 @@ static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
 	return (struct f2fs_checkpoint *)(sbi->ckpt);
 }
 
+static inline struct f2fs_node *F2FS_NODE(struct page *page)
+{
+	return (struct f2fs_node *)page_address(page);
+}
+
 static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
 {
 	return (struct f2fs_nm_info *)(sbi->nm_info);
@@ -489,6 +495,11 @@ static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
 	sbi->s_dirty = 0;
 }
 
+static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
+{
+	return le64_to_cpu(cp->checkpoint_ver);
+}
+
 static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 {
 	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
@@ -677,7 +688,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
 {
 	block_t start_addr;
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	unsigned long long ckpt_version = le64_to_cpu(ckpt->checkpoint_ver);
+	unsigned long long ckpt_version = cur_cp_version(ckpt);
 
 	start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
 
@@ -812,7 +823,7 @@ static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
 
 static inline bool IS_INODE(struct page *page)
 {
-	struct f2fs_node *p = (struct f2fs_node *)page_address(page);
+	struct f2fs_node *p = F2FS_NODE(page);
 	return RAW_IS_INODE(p);
 }
 
@@ -826,7 +837,7 @@ static inline block_t datablock_addr(struct page *node_page,
 {
 	struct f2fs_node *raw_node;
 	__le32 *addr_array;
-	raw_node = (struct f2fs_node *)page_address(node_page);
+	raw_node = F2FS_NODE(node_page);
 	addr_array = blkaddr_in_node(raw_node);
 	return le32_to_cpu(addr_array[offset]);
 }
@@ -873,6 +884,7 @@ enum {
 	FI_NO_ALLOC,		/* should not allocate any blocks */
 	FI_UPDATE_DIR,		/* should update inode block for consistency */
 	FI_DELAY_IPUT,		/* used for the recovery */
+	FI_INLINE_XATTR,	/* used for inline xattr */
 };
 
 static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -905,6 +917,45 @@ static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
 	return 0;
 }
 
+static inline void get_inline_info(struct f2fs_inode_info *fi,
+					struct f2fs_inode *ri)
+{
+	if (ri->i_inline & F2FS_INLINE_XATTR)
+		set_inode_flag(fi, FI_INLINE_XATTR);
+}
+
+static inline void set_raw_inline(struct f2fs_inode_info *fi,
+					struct f2fs_inode *ri)
+{
+	ri->i_inline = 0;
+
+	if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+		ri->i_inline |= F2FS_INLINE_XATTR;
+}
+
+static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+{
+	if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+		return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
+	return DEF_ADDRS_PER_INODE;
+}
+
+static inline void *inline_xattr_addr(struct page *page)
+{
+	struct f2fs_inode *ri;
+	ri = (struct f2fs_inode *)page_address(page);
+	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
+					F2FS_INLINE_XATTR_ADDRS]);
+}
+
+static inline int inline_xattr_size(struct inode *inode)
+{
+	if (is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR))
+		return F2FS_INLINE_XATTR_ADDRS << 2;
+	else
+		return 0;
+}
+
 static inline int f2fs_readonly(struct super_block *sb)
 {
 	return sb->s_flags & MS_RDONLY;
@@ -947,6 +998,7 @@ 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 *);
+int update_dent_inode(struct inode *, const struct qstr *);
 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 *);
@@ -980,6 +1032,7 @@ int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 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 truncate_xattr_node(struct inode *, struct page *);
 int remove_inode_page(struct inode *);
 struct page *new_inode_page(struct inode *, const struct qstr *);
 struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
@@ -1012,7 +1065,8 @@ int npages_for_summary_flush(struct f2fs_sb_info *);
 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);
+void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool);
+void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
 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 *);
@@ -1037,7 +1091,8 @@ void destroy_segment_manager(struct f2fs_sb_info *);
 struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
 struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
 long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-int check_orphan_space(struct f2fs_sb_info *);
+int acquire_orphan_inode(struct f2fs_sb_info *);
+void release_orphan_inode(struct f2fs_sb_info *);
 void add_orphan_inode(struct f2fs_sb_info *, nid_t);
 void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
 int recover_orphan_inodes(struct f2fs_sb_info *);
@@ -1068,7 +1123,7 @@ int do_write_data_page(struct page *);
  */
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int);
+block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
 int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
 int __init create_gc_caches(void);
@@ -1112,11 +1167,16 @@ struct f2fs_stat_info {
 	unsigned base_mem, cache_mem;
 };
 
+static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
+{
+	return (struct f2fs_stat_info*)sbi->stat_info;
+}
+
 #define stat_inc_call_count(si)	((si)->call_count++)
 
 #define stat_inc_seg_count(sbi, type)					\
 	do {								\
-		struct f2fs_stat_info *si = sbi->stat_info;		\
+		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
 		(si)->tot_segs++;					\
 		if (type == SUM_TYPE_DATA)				\
 			si->data_segs++;				\
@@ -1129,14 +1189,14 @@ struct f2fs_stat_info {
 
 #define stat_inc_data_blk_count(sbi, blks)				\
 	do {								\
-		struct f2fs_stat_info *si = sbi->stat_info;		\
+		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
 		stat_inc_tot_blk_count(si, blks);			\
 		si->data_blks += (blks);				\
 	} while (0)
 
 #define stat_inc_node_blk_count(sbi, blks)				\
 	do {								\
-		struct f2fs_stat_info *si = sbi->stat_info;		\
+		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
 		stat_inc_tot_blk_count(si, blks);			\
 		si->node_blks += (blks);				\
 	} while (0)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index d2d2b7dbdcc..02c906971cc 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -112,11 +112,13 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
 	if (!dentry)
 		return 0;
 
-	inode = igrab(dentry->d_parent->d_inode);
-	dput(dentry);
+	if (update_dent_inode(inode, &dentry->d_name)) {
+		dput(dentry);
+		return 0;
+	}
 
-	*pino = inode->i_ino;
-	iput(inode);
+	*pino = parent_ino(dentry);
+	dput(dentry);
 	return 1;
 }
 
@@ -147,9 +149,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	mutex_lock(&inode->i_mutex);
 
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		goto out;
-
+	/*
+	 * Both of fdatasync() and fsync() are able to be recovered from
+	 * sudden-power-off.
+	 */
 	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
 		need_cp = true;
 	else if (file_wrong_pino(inode))
@@ -158,10 +161,14 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		need_cp = true;
 	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
+	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
+		need_cp = true;
 
 	if (need_cp) {
 		nid_t pino;
 
+		F2FS_I(inode)->xattr_ver = 0;
+
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
 		if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
@@ -205,7 +212,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	struct f2fs_node *raw_node;
 	__le32 *addr;
 
-	raw_node = page_address(dn->node_page);
+	raw_node = F2FS_NODE(dn->node_page);
 	addr = blkaddr_in_node(raw_node) + ofs;
 
 	for ( ; count > 0; count--, addr++, dn->ofs_in_node++) {
@@ -283,7 +290,7 @@ static int truncate_blocks(struct inode *inode, u64 from)
 	}
 
 	if (IS_INODE(dn.node_page))
-		count = ADDRS_PER_INODE;
+		count = ADDRS_PER_INODE(F2FS_I(inode));
 	else
 		count = ADDRS_PER_BLOCK;
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 35f9b1a196a..2f157e88368 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -29,10 +29,11 @@ static struct kmem_cache *winode_slab;
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
+	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
 	wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
 	long wait_ms;
 
-	wait_ms = GC_THREAD_MIN_SLEEP_TIME;
+	wait_ms = gc_th->min_sleep_time;
 
 	do {
 		if (try_to_freeze())
@@ -45,7 +46,7 @@ static int gc_thread_func(void *data)
 			break;
 
 		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
-			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
+			wait_ms = increase_sleep_time(gc_th, wait_ms);
 			continue;
 		}
 
@@ -66,15 +67,15 @@ static int gc_thread_func(void *data)
 			continue;
 
 		if (!is_idle(sbi)) {
-			wait_ms = increase_sleep_time(wait_ms);
+			wait_ms = increase_sleep_time(gc_th, wait_ms);
 			mutex_unlock(&sbi->gc_mutex);
 			continue;
 		}
 
 		if (has_enough_invalid_blocks(sbi))
-			wait_ms = decrease_sleep_time(wait_ms);
+			wait_ms = decrease_sleep_time(gc_th, wait_ms);
 		else
-			wait_ms = increase_sleep_time(wait_ms);
+			wait_ms = increase_sleep_time(gc_th, wait_ms);
 
 #ifdef CONFIG_F2FS_STAT_FS
 		sbi->bg_gc++;
@@ -82,7 +83,7 @@ static int gc_thread_func(void *data)
 
 		/* if return value is not zero, no victim was selected */
 		if (f2fs_gc(sbi))
-			wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
+			wait_ms = gc_th->no_gc_sleep_time;
 	} while (!kthread_should_stop());
 	return 0;
 }
@@ -101,6 +102,12 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
 		goto out;
 	}