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

…l/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 @@ void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		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 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	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)