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
  ...

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.

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:
@@ -132,6 +132,38 @@ f2fs. Each file shows the whole f2fs information.
  - average SIT information about whole segments
  - 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
 ================================================================================

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 */

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);

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)

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) {

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 */
 };
 
@@ -295,15 +300,6 @@ struct f2fs_sm_info {
 	unsigned int ovp_segments;	/* # of overprovision segments */
 };
 
-/*
- * 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)

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;
 

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;
 	}
 
+	gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
+	gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
+	gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
+
+	gc_th->gc_idle = 0;
+
 	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,
@@ -125,9 +132,17 @@ void stop_gc_thread(struct f2fs_sb_info *sbi)
 	sbi->gc_thread = NULL;
 }
 
-static int select_gc_type(int gc_type)
+static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type)
 {
-	return (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+	int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+
+	if (gc_th && gc_th->gc_idle) {
+		if (gc_th->gc_idle == 1)
+			gc_mode = GC_CB;
+		else if (gc_th->gc_idle == 2)
+			gc_mode = GC_GREEDY;
+	}
+	return gc_mode;
 }
 
 static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
@@ -138,12 +153,18 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 	if (p->alloc_mode == SSR) {
 		p->gc_mode = GC_GREEDY;
 		p->dirty_segmap = dirty_i->dirty_segmap[type];
+		p->max_search = dirty_i->nr_dirty[type];
 		p->ofs_unit = 1;
 	} else {
-		p->gc_mode = select_gc_type(gc_type);
+		p->gc_mode = select_gc_type(sbi->gc_thread, gc_type);
 		p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
+		p->max_search = dirty_i->nr_dirty[DIRTY];
 		p->ofs_unit = sbi->segs_per_sec;
 	}
+
+	if (p->max_search > MAX_VICTIM_SEARCH)
+		p->max_search = MAX_VICTIM_SEARCH;
+
 	p->offset = sbi->last_victim[p->gc_mode];
 }
 
@@ -290,7 +311,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		if (cost == max_cost)
 			continue;
 
-		if (nsearched++ >= MAX_VICTIM_SEARCH) {
+		if (nsearched++ >= p.max_search) {
 			sbi->last_victim[p.gc_mode] = segno;
 			break;
 		}
@@ -407,8 +428,7 @@ next_step:
 
 		/* set page dirty and write it */
 		if (gc_type == FG_GC) {
-			f2fs_submit_bio(sbi, NODE, true);
-			wait_on_page_writeback(node_page);
+			f2fs_wait_on_page_writeback(node_page, NODE, true);
 			set_page_dirty(node_page);
 		} else {
 			if (!PageWriteback(node_page))
@@ -447,7 +467,7 @@ next_step:
  * as indirect or double indirect node blocks, are given, it must be a caller's
  * bug.
  */
-block_t start_bidx_of_node(unsigned int node_ofs)
+block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
 {
 	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
 	unsigned int bidx;
@@ -464,7 +484,7 @@ block_t start_bidx_of_node(unsigned int node_ofs)
 		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 5 - dec;
 	}
-	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE;
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
 }
 
 static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -508,10 +528,7 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 	} else {
 		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
-		if (PageWriteback(page)) {
-			f2fs_submit_bio(sbi, DATA, true);
-			wait_on_page_writeback(page);
-		}
+		f2fs_wait_on_page_writeback(page, DATA, true);
 
 		if (clear_page_dirty_for_io(page) &&
 			S_ISDIR(inode->i_mode)) {
@@ -575,7 +592,6 @@ next_step:
 			continue;
 		}
 
-		start_bidx = start_bidx_of_node(nofs);
 		ofs_in_node = le16_to_cpu(entry->ofs_in_node);
 
 		if (phase == 2) {
@@ -583,6 +599,8 @@ next_step:
 			if (IS_ERR(inode))
 				continue;
 
+			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+
 			data_page = find_data_page(inode,
 					start_bidx + ofs_in_node, false);
 			if (IS_ERR(data_page))
@@ -593,6 +611,8 @@ next_step:
 		} else {
 			inode = find_gc_inode(dni.ino, ilist);
 			if (inode) {
+				start_bidx = start_bidx_of_node(nofs,
+								F2FS_I(inode));
 				data_page = get_lock_data_page(inode,
 						start_bidx + ofs_in_node);
 				if (IS_ERR(data_page))

fs/f2fs/gc.h

@@ -13,18 +13,26 @@
 						 * whether IO subsystem is idle
 						 * or not
 						 */
-#define GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
-#define GC_THREAD_MAX_SLEEP_TIME	60000
-#define GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
+#define DEF_GC_THREAD_MAX_SLEEP_TIME	60000
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
 /* Search max. number of dirty segments to select a victim segment */
-#define MAX_VICTIM_SEARCH	20
+#define MAX_VICTIM_SEARCH 4096 /* covers 8GB */
 
 struct f2fs_gc_kthread {
 	struct task_struct *f2fs_gc_task;
 	wait_queue_head_t gc_wait_queue_head;
+
+	/* for gc sleep time */
+	unsigned int min_sleep_time;
+	unsigned int max_sleep_time;
+	unsigned int no_gc_sleep_time;
+
+	/* for changing gc mode */
+	unsigned int gc_idle;
 };
 
 struct inode_entry {
@@ -56,25 +64,25 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
 }
 
-static inline long increase_sleep_time(long wait)
+static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
 {
-	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+	if (wait == gc_th->no_gc_sleep_time)
 		return wait;
 
-	wait += GC_THREAD_MIN_SLEEP_TIME;
-	if (wait > GC_THREAD_MAX_SLEEP_TIME)
-		wait = GC_THREAD_MAX_SLEEP_TIME;
+	wait += gc_th->min_sleep_time;
+	if (wait > gc_th->max_sleep_time)
+		wait = gc_th->max_sleep_time;
 	return wait;
 }
 
-static inline long decrease_sleep_time(long wait)
+static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
 {
-	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
-		wait = GC_THREAD_MAX_SLEEP_TIME;
+	if (wait == gc_th->no_gc_sleep_time)
+		wait = gc_th->max_sleep_time;
 
-	wait -= GC_THREAD_MIN_SLEEP_TIME;
-	if (wait <= GC_THREAD_MIN_SLEEP_TIME)
-		wait = GC_THREAD_MIN_SLEEP_TIME;
+	wait -= gc_th->min_sleep_time;
+	if (wait <= gc_th->min_sleep_time)
+		wait = gc_th->min_sleep_time;
 	return wait;
 }
 

fs/f2fs/inode.c

@@ -56,7 +56,7 @@ static int do_read_inode(struct inode *inode)
 	if (IS_ERR(node_page))
 		return PTR_ERR(node_page);
 
-	rn = page_address(node_page);
+	rn = F2FS_NODE(node_page);
 	ri = &(rn->i);
 
 	inode->i_mode = le16_to_cpu(ri->i_mode);
@@ -85,6 +85,7 @@ static int do_read_inode(struct inode *inode)
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	get_extent_info(&fi->ext, ri->i_ext);
+	get_inline_info(fi, ri);
 	f2fs_put_page(node_page, 1);
 	return 0;
 }
@@ -151,9 +152,9 @@ void update_inode(struct inode *inode, struct page *node_page)
 	struct f2fs_node *rn;
 	struct f2fs_inode *ri;
 
-	wait_on_page_writeback(node_page);
+	f2fs_wait_on_page_writeback(node_page, NODE, false);
 
-	rn = page_address(node_page);
+	rn = F2FS_NODE(node_page);
 	ri = &(rn->i);
 
 	ri->i_mode = cpu_to_le16(inode->i_mode);
@@ -164,6 +165,7 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_size = cpu_to_le64(i_size_read(inode));
 	ri->i_blocks = cpu_to_le64(inode->i_blocks);
 	set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
+	set_raw_inline(F2FS_I(inode), ri);
 
 	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
 	ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
@@ -221,9 +223,6 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
 		return 0;
 
-	if (wbc)
-		f2fs_balance_fs(sbi);
-
 	/*
 	 * We need to lock here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
@@ -231,6 +230,10 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	ilock = mutex_lock_op(sbi);
 	ret = update_inode_page(inode);
 	mutex_unlock_op(sbi, ilock);
+
+	if (wbc)
+		f2fs_balance_fs(sbi);
+
 	return ret;
 }
 

fs/f2fs/namei.c

@@ -83,21 +83,11 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
 {
 	size_t slen = strlen(s);
 	size_t sublen = strlen(sub);
-	int ret;
 
 	if (sublen > slen)
 		return 0;
 
-	ret = memcmp(s + slen - sublen, sub, sublen);
-	if (ret) {	/* compare upper case */
-		int i;
-		char upper_sub[8];
-		for (i = 0; i < sublen && i < sizeof(upper_sub); i++)
-			upper_sub[i] = toupper(sub[i]);
-		return !memcmp(s + slen - sublen, upper_sub, sublen);
-	}
-
-	return !ret;
+	return !strncasecmp(s + slen - sublen, sub, sublen);
 }
 
 /*
@@ -239,7 +229,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	if (!de)
 		goto fail;
 
-	err = check_orphan_space(sbi);
+	err = acquire_orphan_inode(sbi);
 	if (err) {
 		kunmap(page);
 		f2fs_put_page(page, 0);
@@ -393,7 +383,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct inode *old_inode = old_dentry->d_inode;
 	struct inode *new_inode = new_dentry->d_inode;
 	struct page *old_dir_page;
-	struct page *old_page;
+	struct page *old_page, *new_page;
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
@@ -415,7 +405,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	ilock = mutex_lock_op(sbi);
 
 	if (new_inode) {
-		struct page *new_page;
 
 		err = -ENOTEMPTY;
 		if (old_dir_entry && !f2fs_empty_dir(new_inode))
@@ -427,14 +416,28 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_entry)
 			goto out_dir;
 
+		err = acquire_orphan_inode(sbi);
+		if (err)
+			goto put_out_dir;
+
+		if (update_dent_inode(old_inode, &new_dentry->d_name)) {
+			release_orphan_inode(sbi);
+			goto put_out_dir;
+		}
+
 		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
 
 		new_inode->i_ctime = CURRENT_TIME;
 		if (old_dir_entry)
 			drop_nlink(new_inode);
 		drop_nlink(new_inode);
+
 		if (!new_inode->i_nlink)
 			add_orphan_inode(sbi, new_inode->i_ino);
+		else
+			release_orphan_inode(sbi);
+
+		update_inode_page(old_inode);
 		update_inode_page(new_inode);
 	} else {
 		err = f2fs_add_link(new_dentry, old_inode);
@@ -467,6 +470,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	mutex_unlock_op(sbi, ilock);
 	return 0;
 
+put_out_dir:
+	f2fs_put_page(new_page, 1);
 out_dir:
 	if (old_dir_entry) {
 		kunmap(old_dir_page);

fs/f2fs/node.c

@@ -315,9 +315,10 @@ cache:
  * The maximum depth is four.
  * Offset[0] will have raw inode offset.
  */
-static int get_node_path(long block, int offset[4], unsigned int noffset[4])
+static int get_node_path(struct f2fs_inode_info *fi, long block,
+				int offset[4], unsigned int noffset[4])
 {
-	const long direct_index = ADDRS_PER_INODE;
+	const long direct_index = ADDRS_PER_INODE(fi);
 	const long direct_blks = ADDRS_PER_BLOCK;
 	const long dptrs_per_blk = NIDS_PER_BLOCK;
 	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -405,7 +406,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	int level, i;
 	int err = 0;
 
-	level = get_node_path(index, offset, noffset);
+	level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
 
 	nids[0] = dn->inode->i_ino;
 	npage[0] = dn->inode_page;
@@ -565,7 +566,7 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
 		return PTR_ERR(page);
 	}
 
-	rn = (struct f2fs_node *)page_address(page);
+	rn = F2FS_NODE(page);
 	if (depth < 3) {
 		for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
 			child_nid = le32_to_cpu(rn->in.nid[i]);
@@ -687,7 +688,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
-	level = get_node_path(from, offset, noffset);
+	level = get_node_path(F2FS_I(inode), from, offset, noffset);
 restart:
 	page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(page)) {
@@ -698,7 +699,7 @@ restart:
 	set_new_dnode(&dn, inode, page, NULL, 0);
 	unlock_page(page);
 
-	rn = page_address(page);
+	rn = F2FS_NODE(page);
 	switch (level) {
 	case 0:
 	case 1:
@@ -771,6 +772,33 @@ fail:
 	return err > 0 ? 0 : err;
 }
 
+int truncate_xattr_node(struct inode *inode, struct page *page)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	nid_t nid = F2FS_I(inode)->i_xattr_nid;
+	struct dnode_of_data dn;
+	struct page *npage;
+
+	if (!nid)
+		return 0;
+
+	npage = get_node_page(sbi, nid);
+	if (IS_ERR(npage))
+		return PTR_ERR(npage);
+
+	F2FS_I(inode)->i_xattr_nid = 0;
+
+	/* need to do checkpoint during fsync */
+	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
+
+	set_new_dnode(&dn, inode, page, npage, nid);
+
+	if (page)
+		dn.inode_page_locked = 1;
+	truncate_node(&dn);
+	return 0;
+}
+
 /*
  * Caller should grab and release a mutex by calling mutex_lock_op() and
  * mutex_unlock_op().
@@ -781,22 +809,16 @@ int remove_inode_page(struct inode *inode)
 	struct page *page;
 	nid_t ino = inode->i_ino;
 	struct dnode_of_data dn;
+	int err;
 
 	page = get_node_page(sbi, ino);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	if (F2FS_I(inode)->i_xattr_nid) {
-		nid_t nid = F2FS_I(inode)->i_xattr_nid;
-		struct page *npage = get_node_page(sbi, nid);
-
-		if (IS_ERR(npage))
-			return PTR_ERR(npage);
-
-		F2FS_I(inode)->i_xattr_nid = 0;
-		set_new_dnode(&dn, inode, page, npage, nid);
-		dn.inode_page_locked = 1;
-		truncate_node(&dn);
+	err = truncate_xattr_node(inode, page);
+	if (err) {
+		f2fs_put_page(page, 1);
+		return err;
 	}
 
 	/* 0 is possible, after f2fs_new_inode() is failed */
@@ -833,29 +855,32 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	get_node_info(sbi, dn->nid, &old_ni);
+	if (!inc_valid_node_count(sbi, dn->inode, 1)) {
+		err = -ENOSPC;
+		goto fail;
+	}
 
-	SetPageUptodate(page);
-	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
+	get_node_info(sbi, dn->nid, &old_ni);
 
 	/* Reinitialize old_ni with new node page */
 	BUG_ON(old_ni.blk_addr != NULL_ADDR);
 	new_ni = old_ni;
 	new_ni.ino = dn->inode->i_ino;
-
-	if (!inc_valid_node_count(sbi, dn->inode, 1)) {
-		err = -ENOSPC;
-		goto fail;
-	}
 	set_node_addr(sbi, &new_ni, NEW_ADDR);
+
+	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
+	SetPageUptodate(page);
+	set_page_dirty(page);
+
+	if (ofs == XATTR_NODE_OFFSET)
+		F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
 
 	dn->node_page = page;
 	if (ipage)
 		update_inode(dn->inode, ipage);
 	else
 		sync_inode_page(dn);
-	set_page_dirty(page);
 	if (ofs == 0)
 		inc_valid_inode_count(sbi);
 
@@ -916,7 +941,6 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 		f2fs_put_page(apage, 0);
 	else if (err == LOCKED_PAGE)
 		f2fs_put_page(apage, 1);
-	return;
 }
 
 struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1167,9 +1191,9 @@ static int f2fs_write_node_page(struct page *page,
 /*
  * It is very important to gather dirty pages and write at once, so that we can
  * submit a big bio without interfering other data writes.
- * Be default, 512 pages (2MB), a segment size, is quite reasonable.
+ * Be default, 512 pages (2MB) * 3 node types, is more reasonable.
  */
-#define COLLECT_DIRTY_NODES	512
+#define COLLECT_DIRTY_NODES	1536
 static int f2fs_write_node_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -1187,9 +1211,10 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 		return 0;
 
 	/* if mounting is failed, skip writing node pages */
-	wbc->nr_to_write = max_hw_blocks(sbi);
+	wbc->nr_to_write = 3 * max_hw_blocks(sbi);
 	sync_node_pages(sbi, 0, wbc);
-	wbc->nr_to_write = nr_to_write - (max_hw_blocks(sbi) - wbc->nr_to_write);
+	wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) -
+						wbc->nr_to_write);
 	return 0;
 }
 
@@ -1444,6 +1469,9 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 
+	if (!nid)
+		return;
+
 	spin_lock(&nm_i->free_nid_list_lock);
 	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
 	BUG_ON(!i || i->state != NID_ALLOC);
@@ -1484,8 +1512,8 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	SetPageUptodate(ipage);
 	fill_node_footer(ipage, ino, ino, 0, true);
 
-	src = (struct f2fs_node *)page_address(page);
-	dst = (struct f2fs_node *)page_address(ipage);
+	src = F2FS_NODE(page);
+	dst = F2FS_NODE(ipage);
 
 	memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i);
 	dst->i.i_size = 0;
@@ -1515,8 +1543,8 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 
 	/* alloc temporal page for read node */
 	page = alloc_page(GFP_NOFS | __GFP_ZERO);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
+	if (!page)
+		return -ENOMEM;
 	lock_page(page);
 
 	/* scan the node segment */
@@ -1535,7 +1563,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 			goto out;
 
 		lock_page(page);
-		rn = (struct f2fs_node *)page_address(page);
+		rn = F2FS_NODE(page);
 		sum_entry->nid = rn->footer.nid;
 		sum_entry->version = 0;
 		sum_entry->ofs_in_node = 0;

fs/f2fs/node.h

@@ -155,8 +155,7 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
-	void *kaddr = page_address(page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(page);
 	if (reset)
 		memset(rn, 0, sizeof(*rn));
 	rn->footer.nid = cpu_to_le32(nid);
@@ -166,10 +165,8 @@ static inline void fill_node_footer(struct page *page, nid_t nid,
 
 static inline void copy_node_footer(struct page *dst, struct page *src)
 {
-	void *src_addr = page_address(src);
-	void *dst_addr = page_address(dst);
-	struct f2fs_node *src_rn = (struct f2fs_node *)src_addr;
-	struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr;
+	struct f2fs_node *src_rn = F2FS_NODE(src);
+	struct f2fs_node *dst_rn = F2FS_NODE(dst);
 	memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
 }
 
@@ -177,45 +174,40 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	void *kaddr = page_address(page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(page);
+
 	rn->footer.cp_ver = ckpt->checkpoint_ver;
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
 
 static inline nid_t ino_of_node(struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(node_page);
 	return le32_to_cpu(rn->footer.ino);
 }
 
 static inline nid_t nid_of_node(struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(node_page);
 	return le32_to_cpu(rn->footer.nid);
 }
 
 static inline unsigned int ofs_of_node(struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(node_page);
 	unsigned flag = le32_to_cpu(rn->footer.flag);
 	return flag >> OFFSET_BIT_SHIFT;
 }
 
 static inline unsigned long long cpver_of_node(struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(node_page);
 	return le64_to_cpu(rn->footer.cp_ver);
 }
 
 static inline block_t next_blkaddr_of_node(struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(node_page);
 	return le32_to_cpu(rn->footer.next_blkaddr);
 }
 
@@ -237,6 +229,10 @@ static inline block_t next_blkaddr_of_node(struct page *node_page)
 static inline bool IS_DNODE(struct page *node_page)
 {
 	unsigned int ofs = ofs_of_node(node_page);
+
+	if (ofs == XATTR_NODE_OFFSET)
+		return false;
+
 	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
 			ofs == 5 + 2 * NIDS_PER_BLOCK)
 		return false;
@@ -250,7 +246,7 @@ static inline bool IS_DNODE(struct page *node_page)
 
 static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
 {
-	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+	struct f2fs_node *rn = F2FS_NODE(p);
 
 	wait_on_page_writeback(p);
 
@@ -263,7 +259,8 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
 
 static inline nid_t get_nid(struct page *p, int off, bool i)
 {
-	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+	struct f2fs_node *rn = F2FS_NODE(p);
+
 	if (i)
 		return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
 	return le32_to_cpu(rn->in.nid[off]);
@@ -314,8 +311,7 @@ static inline void clear_cold_data(struct page *page)
 
 static inline int is_node(struct page *page, int type)
 {
-	void *kaddr = page_address(page);
-	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	struct f2fs_node *rn = F2FS_NODE(page);
 	return le32_to_cpu(rn->footer.flag) & (1 << type);
 }
 
@@ -325,7 +321,7 @@ static inline int is_node(struct page *page, int type)
 
 static inline void set_cold_node(struct inode *inode, struct page *page)
 {
-	struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+	struct f2fs_node *rn = F2FS_NODE(page);
 	unsigned int flag = le32_to_cpu(rn->footer.flag);
 
 	if (S_ISDIR(inode->i_mode))
@@ -337,7 +333,7 @@ static inline void set_cold_node(struct inode *inode, struct page *page)
 
 static inline void set_mark(struct page *page, int mark, int type)
 {
-	struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+	struct f2fs_node *rn = F2FS_NODE(page);
 	unsigned int flag = le32_to_cpu(rn->footer.flag);
 	if (mark)
 		flag |= (0x1 << type);

fs/f2fs/recovery.c

@@ -40,8 +40,7 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
 
 static int recover_dentry(struct page *ipage, struct inode *inode)
 {
-	void *kaddr = page_address(ipage);
-	struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
+	struct f2fs_node *raw_node = F2FS_NODE(ipage);
 	struct f2fs_inode *raw_inode = &(raw_node->i);
 	nid_t pino = le32_to_cpu(raw_inode->i_pino);
 	struct f2fs_dir_entry *de;
@@ -93,8 +92,7 @@ out:
 
 static int recover_inode(struct inode *inode, struct page *node_page)
 {
-	void *kaddr = page_address(node_page);
-	struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
+	struct f2fs_node *raw_node = F2FS_NODE(node_page);
 	struct f2fs_inode *raw_inode = &(raw_node->i);
 
 	if (!IS_INODE(node_page))
@@ -119,7 +117,7 @@ static int recover_inode(struct inode *inode, struct page *node_page)
 
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
-	unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
 	struct page *page;
 	block_t blkaddr;
@@ -131,8 +129,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 
 	/* read node page */
 	page = alloc_page(GFP_F2FS_ZERO);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
+	if (!page)
+		return -ENOMEM;
 	lock_page(page);
 
 	while (1) {
@@ -215,6 +213,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	void *kaddr;
 	struct inode *inode;
 	struct page *node_page;
+	unsigned int offset;
 	block_t bidx;
 	int i;
 
@@ -259,8 +258,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	node_page = get_node_page(sbi, nid);
 	if (IS_ERR(node_page))
 		return PTR_ERR(node_page);
-	bidx = start_bidx_of_node(ofs_of_node(node_page)) +
-					le16_to_cpu(sum.ofs_in_node);
+
+	offset = ofs_of_node(node_page);
 	ino = ino_of_node(node_page);
 	f2fs_put_page(node_page, 1);
 
@@ -269,6 +268,9 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
+	bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
+					le16_to_cpu(sum.ofs_in_node);
+
 	truncate_hole(inode, bidx, bidx + 1);
 	iput(inode);
 	return 0;
@@ -277,6 +279,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 					struct page *page, block_t blkaddr)
 {
+	struct f2fs_inode_info *fi = F2FS_I(inode);
 	unsigned int start, end;
 	struct dnode_of_data dn;
 	struct f2fs_summary sum;
@@ -284,9 +287,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	int err = 0, recovered = 0;
 	int ilock;
 
-	start = start_bidx_of_node(ofs_of_node(page));
+	start = start_bidx_of_node(ofs_of_node(page), fi);
 	if (IS_INODE(page))
-		end = start + ADDRS_PER_INODE;
+		end = start + ADDRS_PER_INODE(fi);
 	else
 		end = start + ADDRS_PER_BLOCK;
 
@@ -357,7 +360,7 @@ err:
 static int recover_data(struct f2fs_sb_info *sbi,
 				struct list_head *head, int type)
 {
-	unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
 	struct page *page;
 	int err = 0;
@@ -369,7 +372,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
 
 	/* read node page */
 	page = alloc_page(GFP_NOFS | __GFP_ZERO);
-	if (IS_ERR(page))
+	if (!page)
 		return -ENOMEM;
 
 	lock_page(page);

fs/f2fs/segment.c

@@ -117,7 +117,6 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	}
 
 	mutex_unlock(&dirty_i->seglist_lock);
-	return;
 }
 
 /*
@@ -261,7 +260,6 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
 	void *addr = curseg->sum_blk;
 	addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
 	memcpy(addr, sum, sizeof(struct f2fs_summary));
-	return;
 }
 
 /*
@@ -542,12 +540,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
-	if (force) {
+	if (force)
 		new_curseg(sbi, type, true);
-		goto out;
-	}
-
-	if (type == CURSEG_WARM_NODE)
+	else if (type == CURSEG_WARM_NODE)
 		new_curseg(sbi, type, false);
 	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
 		new_curseg(sbi, type, false);
@@ -555,11 +550,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 		change_curseg(sbi, type, true);
 	else
 		new_curseg(sbi, type, false);
-out:
 #ifdef CONFIG_F2FS_STAT_FS
 	sbi->segment_count[curseg->alloc_type]++;
 #endif
-	return;
 }
 
 void allocate_new_segments(struct f2fs_sb_info *sbi)
@@ -611,18 +604,12 @@ static void f2fs_end_io_write(struct bio *bio, int err)
 struct bio *f2fs_bio_alloc(struct block_device *bdev, int npages)
 {
 	struct bio *bio;
-	struct bio_private *priv;
-retry:
-	priv = kmalloc(sizeof(struct bio_private), GFP_NOFS);
-	if (!priv) {
-		cond_resched();
-		goto retry;
-	}
 
 	/* No failure on bio allocation */
 	bio = bio_alloc(GFP_NOIO, npages);
 	bio->bi_bdev = bdev;
-	bio->bi_private = priv;
+	bio->bi_private = NULL;
+
 	return bio;
 }
 
@@ -681,8 +668,17 @@ static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page,
 		do_submit_bio(sbi, type, false);
 alloc_new:
 	if (sbi->bio[type] == NULL) {
+		struct bio_private *priv;
+retry:
+		priv = kmalloc(sizeof(struct bio_private), GFP_NOFS);
+		if (!priv) {
+			cond_resched();
+			goto retry;
+		}
+
 		sbi->bio[type] = f2fs_bio_alloc(bdev, max_hw_blocks(sbi));
 		sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+		sbi->bio[type]->bi_private = priv;
 		/*
 		 * The end_io will be assigned at the sumbission phase.
 		 * Until then, let bio_add_page() merge consecutive IOs as much
@@ -702,6 +698,16 @@ alloc_new:
 	trace_f2fs_submit_write_page(page, blk_addr, type);
 }
 
+void f2fs_wait_on_page_writeback(struct page *page,
+				enum page_type type, bool sync)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+	if (PageWriteback(page)) {
+		f2fs_submit_bio(sbi, type, sync);
+		wait_on_page_writeback(page);
+	}
+}
+
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1179,7 +1185,6 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
 	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
 		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
-	return;
 }
 
 int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,

fs/f2fs/segment.h

@@ -142,6 +142,7 @@ struct victim_sel_policy {
 	int alloc_mode;			/* LFS or SSR */
 	int gc_mode;			/* GC_CB or GC_GREEDY */
 	unsigned long *dirty_segmap;	/* dirty segment bitmap */
+	unsigned int max_search;	/* maximum # of segments to search */
 	unsigned int offset;		/* last scanned bitmap offset */
 	unsigned int ofs_unit;		/* bitmap search unit */
 	unsigned int min_cost;		/* minimum cost */
@@ -453,7 +454,8 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
 
 static inline bool need_SSR(struct f2fs_sb_info *sbi)
 {
-	return (free_sections(sbi) < overprovision_sections(sbi));
+	return ((prefree_segments(sbi) / sbi->segs_per_sec)
+			+ free_sections(sbi) < overprovision_sections(sbi));
 }
 
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
@@ -470,7 +472,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 
 static inline int utilization(struct f2fs_sb_info *sbi)
 {
-	return div_u64(valid_user_blocks(sbi) * 100, sbi->user_block_count);
+	return div_u64((u64)valid_user_blocks(sbi) * 100, sbi->user_block_count);
 }
 
 /*

fs/f2fs/super.c

@@ -18,20 +18,25 @@
 #include <linux/parser.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/proc_fs.h>
 #include <linux/random.h>
 #include <linux/exportfs.h>
 #include <linux/blkdev.h>
 #include <linux/f2fs_fs.h>
+#include <linux/sysfs.h>
 
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
 #include "xattr.h"
+#include "gc.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
 
+static struct proc_dir_entry *f2fs_proc_root;
 static struct kmem_cache *f2fs_inode_cachep;
+static struct kset *f2fs_kset;
 
 enum {
 	Opt_gc_background,
@@ -42,6 +47,7 @@ enum {
 	Opt_noacl,
 	Opt_active_logs,
 	Opt_disable_ext_identify,
+	Opt_inline_xattr,
 	Opt_err,
 };
 
@@ -54,9 +60,117 @@ static match_table_t f2fs_tokens = {
 	{Opt_noacl, "noacl"},
 	{Opt_active_logs, "active_logs=%u"},
 	{Opt_disable_ext_identify, "disable_ext_identify"},
+	{Opt_inline_xattr, "inline_xattr"},
 	{Opt_err, NULL},
 };
 
+/* Sysfs support for f2fs */
+struct f2fs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
+	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
+			 const char *, size_t);
+	int offset;
+};
+
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi, char *buf)
+{
+	struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
+	unsigned int *ui;
+
+	if (!gc_kth)
+		return -EINVAL;
+
+	ui = (unsigned int *)(((char *)gc_kth) + a->offset);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi,
+			const char *buf, size_t count)
+{
+	struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
+	unsigned long t;
+	unsigned int *ui;
+	ssize_t ret;
+
+	if (!gc_kth)
+		return -EINVAL;
+
+	ui = (unsigned int *)(((char *)gc_kth) + a->offset);
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret < 0)
+		return ret;
+	*ui = t;
+	return count;
+}
+
+static ssize_t f2fs_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
+						const char *buf, size_t len)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+									s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void f2fs_sb_release(struct kobject *kobj)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	complete(&sbi->s_kobj_unregister);
+}
+
+#define F2FS_ATTR_OFFSET(_name, _mode, _show, _store, _elname) \
+static struct f2fs_attr f2fs_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.show	= _show,					\
+	.store	= _store,					\
+	.offset = offsetof(struct f2fs_gc_kthread, _elname),	\
+}
+
+#define F2FS_RW_ATTR(name, elname)	\
+	F2FS_ATTR_OFFSET(name, 0644, f2fs_sbi_show, f2fs_sbi_store, elname)
+
+F2FS_RW_ATTR(gc_min_sleep_time, min_sleep_time);
+F2FS_RW_ATTR(gc_max_sleep_time, max_sleep_time);
+F2FS_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time);
+F2FS_RW_ATTR(gc_idle, gc_idle);
+
+#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
+static struct attribute *f2fs_attrs[] = {
+	ATTR_LIST(gc_min_sleep_time),
+	ATTR_LIST(gc_max_sleep_time),
+	ATTR_LIST(gc_no_gc_sleep_time),
+	ATTR_LIST(gc_idle),
+	NULL,
+};
+
+static const struct sysfs_ops f2fs_attr_ops = {
+	.show	= f2fs_attr_show,
+	.store	= f2fs_attr_store,
+};
+
+static struct kobj_type f2fs_ktype = {
+	.default_attrs	= f2fs_attrs,
+	.sysfs_ops	= &f2fs_attr_ops,
+	.release	= f2fs_sb_release,
+};
+
 void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -126,11 +240,18 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_nouser_xattr:
 			clear_opt(sbi, XATTR_USER);
 			break;
+		case Opt_inline_xattr:
+			set_opt(sbi, INLINE_XATTR);
+			break;
 #else
 		case Opt_nouser_xattr:
 			f2fs_msg(sb, KERN_INFO,
 				"nouser_xattr options not supported");
 			break;
+		case Opt_inline_xattr:
+			f2fs_msg(sb, KERN_INFO,
+				"inline_xattr options not supported");
+			break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 		case Opt_noacl:
@@ -180,6 +301,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	set_inode_flag(fi, FI_NEW_INODE);
 
+	if (test_opt(F2FS_SB(sb), INLINE_XATTR))
+		set_inode_flag(fi, FI_INLINE_XATTR);
+
 	return &fi->vfs_inode;
 }
 
@@ -205,7 +329,6 @@ static int f2fs_drop_inode(struct inode *inode)
 static void f2fs_dirty_inode(struct inode *inode, int flags)
 {
 	set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
-	return;
 }
 
 static void f2fs_i_callback(struct rcu_head *head)
@@ -223,6 +346,12 @@ static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
+	if (sbi->s_proc) {
+		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry(sb->s_id, f2fs_proc_root);
+	}
+	kobject_del(&sbi->s_kobj);
+
 	f2fs_destroy_stats(sbi);
 	stop_gc_thread(sbi);
 
@@ -236,6 +365,8 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_segment_manager(sbi);
 
 	kfree(sbi->ckpt);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
 
 	sb->s_fs_info = NULL;
 	brelse(sbi->raw_super_buf);
@@ -325,6 +456,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",user_xattr");
 	else
 		seq_puts(seq, ",nouser_xattr");
+	if (test_opt(sbi, INLINE_XATTR))
+		seq_puts(seq, ",inline_xattr");
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 	if (test_opt(sbi, POSIX_ACL))
@@ -340,6 +473,36 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
+static int segment_info_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i;
+
+	for (i = 0; i < total_segs; i++) {
+		seq_printf(seq, "%u", get_valid_blocks(sbi, i, 1));
+		if (i != 0 && (i % 10) == 0)
+			seq_puts(seq, "\n");
+		else
+			seq_puts(seq, " ");
+	}
+	return 0;
+}
+
+static int segment_info_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+}
+
+static const struct file_operations f2fs_seq_segment_info_fops = {
+	.owner = THIS_MODULE,
+	.open = segment_info_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -455,7 +618,7 @@ static const struct export_operations f2fs_export_ops = {
 
 static loff_t max_file_size(unsigned bits)
 {
-	loff_t result = ADDRS_PER_INODE;
+	loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
 	loff_t leaf_count = ADDRS_PER_BLOCK;
 
 	/* two direct node blocks */
@@ -766,6 +929,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto fail;
 
+	if (f2fs_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
+
+	if (sbi->s_proc)
+		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_info_fops, sb);
+
 	if (test_opt(sbi, DISCARD)) {
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 		if (!blk_queue_discard(q))
@@ -774,6 +944,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 					"the device does not support discard");
 	}
 
+	sbi->s_kobj.kset = f2fs_kset;
+	init_completion(&sbi->s_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
+							"%s", sb->s_id);
+	if (err)
+		goto fail;
+
 	return 0;
 fail:
 	stop_gc_thread(sbi);
@@ -841,29 +1018,49 @@ static int __init init_f2fs_fs(void)
 		goto fail;
 	err = create_node_manager_caches();
 	if (err)
-		goto fail;
+		goto free_inodecache;
 	err = create_gc_caches();
 	if (err)
-		goto fail;
+		goto free_node_manager_caches;
 	err = create_checkpoint_caches();
 	if (err)
-		goto fail;
+		goto free_gc_caches;
+	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
+	if (!f2fs_kset) {
+		err = -ENOMEM;
+		goto free_checkpoint_caches;
+	}
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
-		goto fail;
+		goto free_kset;
 	f2fs_create_root_stats();
+	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+	return 0;
+
+free_kset:
+	kset_unregister(f2fs_kset);
+free_checkpoint_caches:
+	destroy_checkpoint_caches();
+free_gc_caches:
+	destroy_gc_caches();
+free_node_manager_caches:
+	destroy_node_manager_caches();
+free_inodecache:
+	destroy_inodecache();
 fail:
 	return err;
 }
 
 static void __exit exit_f2fs_fs(void)
 {
+	remove_proc_entry("fs/f2fs", NULL);
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	destroy_checkpoint_caches();
 	destroy_gc_caches();
 	destroy_node_manager_caches();
 	destroy_inodecache();
+	kset_unregister(f2fs_kset);
 }
 
 module_init(init_f2fs_fs)

fs/f2fs/xattr.c

@@ -246,40 +246,170 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
 	return handler;
 }
 
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index,
+					size_t name_len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+
+	list_for_each_xattr(entry, base_addr) {
+		if (entry->e_name_index != name_index)
+			continue;
+		if (entry->e_name_len != name_len)
+			continue;
+		if (!memcmp(entry->e_name, name, name_len))
+			break;
+	}
+	return entry;
+}
+
+static void *read_all_xattrs(struct inode *inode, struct page *ipage)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_xattr_header *header;
+	size_t size = PAGE_SIZE, inline_size = 0;
+	void *txattr_addr;
+
+	inline_size = inline_xattr_size(inode);
+
+	txattr_addr = kzalloc(inline_size + size, GFP_KERNEL);
+	if (!txattr_addr)
+		return NULL;
+
+	/* read from inline xattr */
+	if (inline_size) {
+		struct page *page = NULL;
+		void *inline_addr;
+
+		if (ipage) {
+			inline_addr = inline_xattr_addr(ipage);
+		} else {
+			page = get_node_page(sbi, inode->i_ino);
+			if (IS_ERR(page))
+				goto fail;
+			inline_addr = inline_xattr_addr(page);
+		}
+		memcpy(txattr_addr, inline_addr, inline_size);
+		f2fs_put_page(page, 1);
+	}
+
+	/* read from xattr node block */
+	if (F2FS_I(inode)->i_xattr_nid) {
+		struct page *xpage;
+		void *xattr_addr;
+
+		/* The inode already has an extended attribute block. */
+		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+		if (IS_ERR(xpage))
+			goto fail;
+
+		xattr_addr = page_address(xpage);
+		memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
+		f2fs_put_page(xpage, 1);
+	}
+
+	header = XATTR_HDR(txattr_addr);
+
+	/* never been allocated xattrs */
+	if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
+		header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
+		header->h_refcount = cpu_to_le32(1);
+	}
+	return txattr_addr;
+fail:
+	kzfree(txattr_addr);
+	return NULL;
+}
+
+static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
+				void *txattr_addr, struct page *ipage)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	size_t inline_size = 0;
+	void *xattr_addr;
+	struct page *xpage;
+	nid_t new_nid = 0;
+	int err;
+
+	inline_size = inline_xattr_size(inode);
+
+	if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
+		if (!alloc_nid(sbi, &new_nid))
+			return -ENOSPC;
+
+	/* write to inline xattr */
+	if (inline_size) {
+		struct page *page = NULL;
+		void *inline_addr;
+
+		if (ipage) {
+			inline_addr = inline_xattr_addr(ipage);
+		} else {
+			page = get_node_page(sbi, inode->i_ino);
+			if (IS_ERR(page)) {
+				alloc_nid_failed(sbi, new_nid);
+				return PTR_ERR(page);
+			}
+			inline_addr = inline_xattr_addr(page);
+		}
+		memcpy(inline_addr, txattr_addr, inline_size);
+		f2fs_put_page(page, 1);
+
+		/* no need to use xattr node block */
+		if (hsize <= inline_size) {
+			err = truncate_xattr_node(inode, ipage);
+			alloc_nid_failed(sbi, new_nid);
+			return err;
+		}
+	}
+
+	/* write to xattr node block */
+	if (F2FS_I(inode)->i_xattr_nid) {
+		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+		if (IS_ERR(xpage)) {
+			alloc_nid_failed(sbi, new_nid);
+			return PTR_ERR(xpage);
+		}
+		BUG_ON(new_nid);
+	} else {
+		struct dnode_of_data dn;
+		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
+		xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
+		if (IS_ERR(xpage)) {
+			alloc_nid_failed(sbi, new_nid);
+			return PTR_ERR(xpage);
+		}
+		alloc_nid_done(sbi, new_nid);
+	}
+
+	xattr_addr = page_address(xpage);
+	memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
+						sizeof(struct node_footer));
+	set_page_dirty(xpage);
+	f2fs_put_page(xpage, 1);
+
+	/* need to checkpoint during fsync */
+	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
+	return 0;
+}
+
 int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
 		void *buffer, size_t buffer_size)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *entry;
-	struct page *page;
 	void *base_addr;
-	int error = 0, found = 0;
+	int error = 0;
 	size_t value_len, name_len;
 
 	if (name == NULL)
 		return -EINVAL;
 	name_len = strlen(name);
 
-	if (!fi->i_xattr_nid)
-		return -ENODATA;
+	base_addr = read_all_xattrs(inode, NULL);
+	if (!base_addr)
+		return -ENOMEM;
 
-	page = get_node_page(sbi, fi->i_xattr_nid);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
-	base_addr = page_address(page);
-
-	list_for_each_xattr(entry, base_addr) {
-		if (entry->e_name_index != name_index)
-			continue;
-		if (entry->e_name_len != name_len)
-			continue;
-		if (!memcmp(entry->e_name, name, name_len)) {
-			found = 1;
-			break;
-		}
-	}
-	if (!found) {
+	entry = __find_xattr(base_addr, name_index, name_len, name);
+	if (IS_XATTR_LAST_ENTRY(entry)) {
 		error = -ENODATA;
 		goto cleanup;
 	}
@@ -298,28 +428,21 @@ int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
 	error = value_len;
 
 cleanup:
-	f2fs_put_page(page, 1);
+	kzfree(base_addr);
 	return error;
 }
 
 ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
 	struct inode *inode = dentry->d_inode;
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *entry;
-	struct page *page;
 	void *base_addr;
 	int error = 0;
 	size_t rest = buffer_size;
 
-	if (!fi->i_xattr_nid)
-		return 0;
-
-	page = get_node_page(sbi, fi->i_xattr_nid);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
-	base_addr = page_address(page);
+	base_addr = read_all_xattrs(inode, NULL);
+	if (!base_addr)
+		return -ENOMEM;
 
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
@@ -342,7 +465,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	}
 	error = buffer_size - rest;
 cleanup:
-	f2fs_put_page(page, 1);
+	kzfree(base_addr);
 	return error;
 }
 
@@ -351,14 +474,13 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_xattr_header *header = NULL;
 	struct f2fs_xattr_entry *here, *last;
-	struct page *page;
 	void *base_addr;
-	int error, found, free, newsize;
+	int found, newsize;
 	size_t name_len;
-	char *pval;
 	int ilock;
+	__u32 new_hsize;
+	int error = -ENOMEM;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -368,67 +490,21 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 
 	name_len = strlen(name);
 
-	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN)
+	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode))
 		return -ERANGE;
 
 	f2fs_balance_fs(sbi);
 
 	ilock = mutex_lock_op(sbi);
 
-	if (!fi->i_xattr_nid) {
-		/* Allocate new attribute block */
-		struct dnode_of_data dn;
-
-		if (!alloc_nid(sbi, &fi->i_xattr_nid)) {
-			error = -ENOSPC;
-			goto exit;
-		}
-		set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid);
-		mark_inode_dirty(inode);
-
-		page = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
-		if (IS_ERR(page)) {
-			alloc_nid_failed(sbi, fi->i_xattr_nid);
-			fi->i_xattr_nid = 0;
-			error = PTR_ERR(page);
-			goto exit;
-		}
-
-		alloc_nid_done(sbi, fi->i_xattr_nid);
-		base_addr = page_address(page);
-		header = XATTR_HDR(base_addr);
-		header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
-		header->h_refcount = cpu_to_le32(1);
-	} else {
-		/* The inode already has an extended attribute block. */
-		page = get_node_page(sbi, fi->i_xattr_nid);
-		if (IS_ERR(page)) {
-			error = PTR_ERR(page);
-			goto exit;
-		}
-
-		base_addr = page_address(page);
-		header = XATTR_HDR(base_addr);
-	}
-
-	if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
-		error = -EIO;
-		goto cleanup;
-	}
+	base_addr = read_all_xattrs(inode, ipage);
+	if (!base_addr)
+		goto exit;
 
 	/* find entry with wanted name. */
-	found = 0;
-	list_for_each_xattr(here, base_addr) {
-		if (here->e_name_index != name_index)
-			continue;
-		if (here->e_name_len != name_len)
-			continue;
-		if (!memcmp(here->e_name, name, name_len)) {
-			found = 1;
-			break;
-		}
-	}
+	here = __find_xattr(base_addr, name_index, name_len, name);
 
+	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
 	last = here;
 
 	while (!IS_XATTR_LAST_ENTRY(last))
@@ -439,22 +515,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 
 	/* 1. Check space */
 	if (value) {
-		/* If value is NULL, it is remove operation.
+		int free;
+		/*
+		 * If value is NULL, it is remove operation.
 		 * In case of update operation, we caculate free.
 		 */
-		free = MIN_OFFSET - ((char *)last - (char *)header);
+		free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr);
 		if (found)
 			free = free - ENTRY_SIZE(here);
 
 		if (free < newsize) {
 			error = -ENOSPC;
-			goto cleanup;
+			goto exit;
 		}
 	}
 
 	/* 2. Remove old entry */
 	if (found) {
-		/* If entry is found, remove old entry.
+		/*
+		 * If entry is found, remove old entry.
 		 * If not found, remove operation is not needed.
 		 */
 		struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here);
@@ -465,10 +544,15 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 		memset(last, 0, oldsize);
 	}
 
+	new_hsize = (char *)last - (char *)base_addr;
+
 	/* 3. Write new entry */
 	if (value) {
-		/* Before we come here, old entry is removed.
-		 * We just write new entry. */
+		char *pval;
+		/*
+		 * Before we come here, old entry is removed.
+		 * We just write new entry.
+		 */
 		memset(last, 0, newsize);
 		last->e_name_index = name_index;
 		last->e_name_len = name_len;
@@ -476,26 +560,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
 		pval = last->e_name + name_len;
 		memcpy(pval, value, value_len);
 		last->e_value_size = cpu_to_le16(value_len);
+		new_hsize += newsize;
 	}
 
-	set_page_dirty(page);
-	f2fs_put_page(page, 1);
+	error = write_all_xattrs(inode, new_hsize, base_addr, ipage);
+	if (error)
+		goto exit;
 
 	if (is_inode_flag_set(fi, FI_ACL_MODE)) {
 		inode->i_mode = fi->i_acl_mode;
 		inode->i_ctime = CURRENT_TIME;
 		clear_inode_flag(fi, FI_ACL_MODE);
 	}
+
 	if (ipage)
 		update_inode(inode, ipage);
 	else
 		update_inode_page(inode);
-	mutex_unlock_op(sbi, ilock);
-
-	return 0;
-cleanup:
-	f2fs_put_page(page, 1);
 exit:
 	mutex_unlock_op(sbi, ilock);
+	kzfree(base_addr);
 	return error;
 }

fs/f2fs/xattr.h

@@ -51,7 +51,7 @@ struct f2fs_xattr_entry {
 
 #define XATTR_HDR(ptr)		((struct f2fs_xattr_header *)(ptr))
 #define XATTR_ENTRY(ptr)	((struct f2fs_xattr_entry *)(ptr))
-#define XATTR_FIRST_ENTRY(ptr)	(XATTR_ENTRY(XATTR_HDR(ptr)+1))
+#define XATTR_FIRST_ENTRY(ptr)	(XATTR_ENTRY(XATTR_HDR(ptr) + 1))
 #define XATTR_ROUND		(3)
 
 #define XATTR_ALIGN(size)	((size + XATTR_ROUND) & ~XATTR_ROUND)
@@ -69,17 +69,16 @@ struct f2fs_xattr_entry {
 				!IS_XATTR_LAST_ENTRY(entry);\
 				entry = XATTR_NEXT_ENTRY(entry))
 
+#define MIN_OFFSET(i)	XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE -	\
+				sizeof(struct node_footer) - sizeof(__u32))
 
-#define MIN_OFFSET	XATTR_ALIGN(PAGE_SIZE - \
-			sizeof(struct node_footer) - \
-			sizeof(__u32))
-
-#define MAX_VALUE_LEN	(MIN_OFFSET - sizeof(struct f2fs_xattr_header) - \
-			sizeof(struct f2fs_xattr_entry))
+#define MAX_VALUE_LEN(i)	(MIN_OFFSET(i) -			\
+				sizeof(struct f2fs_xattr_header) -	\
+				sizeof(struct f2fs_xattr_entry))
 
 /*
  * On-disk structure of f2fs_xattr
- * We use only 1 block for xattr.
+ * We use inline xattrs space + 1 block for xattr.
  *
  * +--------------------+
  * | f2fs_xattr_header  |

include/linux/f2fs_fs.h

@@ -140,14 +140,24 @@ struct f2fs_extent {
 } __packed;
 
 #define F2FS_NAME_LEN		255
-#define ADDRS_PER_INODE         923	/* Address Pointers in an Inode */
-#define ADDRS_PER_BLOCK         1018	/* Address Pointers in a Direct Block */
-#define NIDS_PER_BLOCK          1018	/* Node IDs in an Indirect Block */
+#define F2FS_INLINE_XATTR_ADDRS	50	/* 200 bytes for inline xattrs */
+#define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
+#define ADDRS_PER_INODE(fi)	addrs_per_inode(fi)
+#define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
+#define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
+
+#define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
+#define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
+#define	NODE_IND1_BLOCK		(DEF_ADDRS_PER_INODE + 3)
+#define	NODE_IND2_BLOCK		(DEF_ADDRS_PER_INODE + 4)
+#define	NODE_DIND_BLOCK		(DEF_ADDRS_PER_INODE + 5)
+
+#define F2FS_INLINE_XATTR	0x01	/* file inline xattr flag */
 
 struct f2fs_inode {
 	__le16 i_mode;			/* file mode */
 	__u8 i_advise;			/* file hints */
-	__u8 i_reserved;		/* reserved */
+	__u8 i_inline;			/* file inline flags */
 	__le32 i_uid;			/* user ID */
 	__le32 i_gid;			/* group ID */
 	__le32 i_links;			/* links count */
@@ -170,7 +180,7 @@ struct f2fs_inode {
 
 	struct f2fs_extent i_ext;	/* caching a largest extent */
 
-	__le32 i_addr[ADDRS_PER_INODE];	/* Pointers to data blocks */
+	__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */
 
 	__le32 i_nid[5];		/* direct(2), indirect(2),
 						double_indirect(1) node id */