Merge tag 'f2fs-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/jaegeuk/f2fs

Pull f2fs fixes from Jaegeuk Kim:
 o Support swap file and link generic_file_remap_pages
 o Enhance the bio streaming flow and free section control
 o Major bug fix on recovery routine
 o Minor bug/warning fixes and code cleanups

* tag 'f2fs-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (22 commits)
  f2fs: use _safe() version of list_for_each
  f2fs: add comments of start_bidx_of_node
  f2fs: avoid issuing small bios due to several dirty node pages
  f2fs: support swapfile
  f2fs: add remap_pages as generic_file_remap_pages
  f2fs: add __init to functions in init_f2fs_fs
  f2fs: fix the debugfs entry creation path
  f2fs: add global mutex_lock to protect f2fs_stat_list
  f2fs: remove the blk_plug usage in f2fs_write_data_pages
  f2fs: avoid redundant time update for parent directory in f2fs_delete_entry
  f2fs: remove redundant call to set_blocksize in f2fs_fill_super
  f2fs: move f2fs_balance_fs to punch_hole
  f2fs: add f2fs_balance_fs in several interfaces
  f2fs: revisit the f2fs_gc flow
  f2fs: check return value during recovery
  f2fs: avoid null dereference in f2fs_acl_from_disk
  f2fs: initialize newly allocated dnode structure
  f2fs: update f2fs partition info about SIT/NAT layout
  f2fs: update f2fs document to reflect SIT/NAT layout correctly
  f2fs: remove unneeded INIT_LIST_HEAD at few places
  ...

Documentation/filesystems/f2fs.txt

@@ -175,9 +175,9 @@ consists of multiple segments as described below.
                                             align with the zone size <-|
                  |-> align with the segment size
      _________________________________________________________________________
-    |            |            |    Node     |   Segment   |   Segment  |      |
-    | Superblock | Checkpoint |   Address   |    Info.    |   Summary  | Main |
-    |    (SB)    |   (CP)     | Table (NAT) | Table (SIT) | Area (SSA) |      |
+    |            |            |   Segment   |    Node     |   Segment  |      |
+    | Superblock | Checkpoint |    Info.    |   Address   |   Summary  | Main |
+    |    (SB)    |   (CP)     | Table (SIT) | Table (NAT) | Area (SSA) |      |
     |____________|_____2______|______N______|______N______|______N_____|__N___|
                                                                        .      .
                                                              .                .
@@ -200,14 +200,14 @@ consists of multiple segments as described below.
  : It contains file system information, bitmaps for valid NAT/SIT sets, orphan
    inode lists, and summary entries of current active segments.
 
-- Node Address Table (NAT)
- : It is composed of a block address table for all the node blocks stored in
-   Main area.
-
 - Segment Information Table (SIT)
  : It contains segment information such as valid block count and bitmap for the
    validity of all the blocks.
 
+- Node Address Table (NAT)
+ : It is composed of a block address table for all the node blocks stored in
+   Main area.
+
 - Segment Summary Area (SSA)
  : It contains summary entries which contains the owner information of all the
    data and node blocks stored in Main area.
@@ -236,13 +236,13 @@ For file system consistency, each CP points to which NAT and SIT copies are
 valid, as shown as below.
 
   +--------+----------+---------+
-  |   CP   |    NAT   |   SIT   |
+  |   CP   |    SIT   |   NAT   |
   +--------+----------+---------+
   .         .          .          .
   .            .              .              .
   .               .                 .                 .
   +-------+-------+--------+--------+--------+--------+
-  | CP #0 | CP #1 | NAT #0 | NAT #1 | SIT #0 | SIT #1 |
+  | CP #0 | CP #1 | SIT #0 | SIT #1 | NAT #0 | NAT #1 |
   +-------+-------+--------+--------+--------+--------+
      |             ^                          ^
      |             |                          |

fs/f2fs/acl.c

@@ -191,15 +191,14 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 		retval = f2fs_getxattr(inode, name_index, "", value, retval);
 	}
 
-	if (retval < 0) {
-		if (retval == -ENODATA)
-			acl = NULL;
-		else
-			acl = ERR_PTR(retval);
-	} else {
+	if (retval > 0)
 		acl = f2fs_acl_from_disk(value, retval);
-	}
+	else if (retval == -ENODATA)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
 	kfree(value);
+
 	if (!IS_ERR(acl))
 		set_cached_acl(inode, type, acl);
 

fs/f2fs/checkpoint.c

@@ -214,7 +214,6 @@ void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		goto retry;
 	}
 	new->ino = ino;
-	INIT_LIST_HEAD(&new->list);
 
 	/* add new_oentry into list which is sorted by inode number */
 	if (orphan) {
@@ -772,7 +771,7 @@ void init_orphan_info(struct f2fs_sb_info *sbi)
 	sbi->n_orphans = 0;
 }
 
-int create_checkpoint_caches(void)
+int __init create_checkpoint_caches(void)
 {
 	orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
 			sizeof(struct orphan_inode_entry), NULL);

fs/f2fs/data.c

@@ -547,6 +547,15 @@ static int f2fs_write_data_page(struct page *page,
 
 #define MAX_DESIRED_PAGES_WP	4096
 
+static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
+			void *data)
+{
+	struct address_space *mapping = data;
+	int ret = mapping->a_ops->writepage(page, wbc);
+	mapping_set_error(mapping, ret);
+	return ret;
+}
+
 static int f2fs_write_data_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -563,7 +572,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 	if (!S_ISDIR(inode->i_mode))
 		mutex_lock(&sbi->writepages);
-	ret = generic_writepages(mapping, wbc);
+	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
 	if (!S_ISDIR(inode->i_mode))
 		mutex_unlock(&sbi->writepages);
 	f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
@@ -689,6 +698,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	return 0;
 }
 
+static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
+{
+	return generic_block_bmap(mapping, block, get_data_block_ro);
+}
+
 const struct address_space_operations f2fs_dblock_aops = {
 	.readpage	= f2fs_read_data_page,
 	.readpages	= f2fs_read_data_pages,
@@ -700,4 +714,5 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.invalidatepage	= f2fs_invalidate_data_page,
 	.releasepage	= f2fs_release_data_page,
 	.direct_IO	= f2fs_direct_IO,
+	.bmap		= f2fs_bmap,
 };

fs/f2fs/debug.c

@@ -26,6 +26,7 @@
 
 static LIST_HEAD(f2fs_stat_list);
 static struct dentry *debugfs_root;
+static DEFINE_MUTEX(f2fs_stat_mutex);
 
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
@@ -180,18 +181,14 @@ static int stat_show(struct seq_file *s, void *v)
 	int i = 0;
 	int j;
 
+	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
 
-		mutex_lock(&si->stat_lock);
-		if (!si->sbi) {
-			mutex_unlock(&si->stat_lock);
-			continue;
-		}
 		update_general_status(si->sbi);
 
 		seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
-		seq_printf(s, "[SB: 1] [CP: 2] [NAT: %d] [SIT: %d] ",
-			   si->nat_area_segs, si->sit_area_segs);
+		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
+			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
 			   si->ssa_area_segs, si->main_area_segs);
 		seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
@@ -286,8 +283,8 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
 				(si->base_mem + si->cache_mem) >> 10,
 				si->base_mem >> 10, si->cache_mem >> 10);
-		mutex_unlock(&si->stat_lock);
 	}
+	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
 }
 
@@ -303,7 +300,7 @@ static const struct file_operations stat_fops = {
 	.release = single_release,
 };
 
-static int init_stats(struct f2fs_sb_info *sbi)
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_stat_info *si;
@@ -313,9 +310,6 @@ static int init_stats(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	si = sbi->stat_info;
-	mutex_init(&si->stat_lock);
-	list_add_tail(&si->stat_list, &f2fs_stat_list);
-
 	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);
@@ -325,36 +319,34 @@ static int init_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;
-	return 0;
-}
 
-int f2fs_build_stats(struct f2fs_sb_info *sbi)
-{
-	int retval;
-
-	retval = init_stats(sbi);
-	if (retval)
-		return retval;
-
-	if (!debugfs_root)
-		debugfs_root = debugfs_create_dir("f2fs", NULL);
+	mutex_lock(&f2fs_stat_mutex);
+	list_add_tail(&si->stat_list, &f2fs_stat_list);
+	mutex_unlock(&f2fs_stat_mutex);
 
-	debugfs_create_file("status", S_IRUGO, debugfs_root, NULL, &stat_fops);
 	return 0;
 }
 
 void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = sbi->stat_info;
 
+	mutex_lock(&f2fs_stat_mutex);
 	list_del(&si->stat_list);
-	mutex_lock(&si->stat_lock);
-	si->sbi = NULL;
-	mutex_unlock(&si->stat_lock);
+	mutex_unlock(&f2fs_stat_mutex);
+
 	kfree(sbi->stat_info);
 }
 
-void destroy_root_stats(void)
+void __init f2fs_create_root_stats(void)
+{
+	debugfs_root = debugfs_create_dir("f2fs", NULL);
+	if (debugfs_root)
+		debugfs_create_file("status", S_IRUGO, debugfs_root,
+					 NULL, &stat_fops);
+}
+
+void f2fs_destroy_root_stats(void)
 {
 	debugfs_remove_recursive(debugfs_root);
 	debugfs_root = NULL;

fs/f2fs/dir.c

@@ -503,7 +503,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	}
 
 	if (inode) {
-		inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+		inode->i_ctime = CURRENT_TIME;
 		drop_nlink(inode);
 		if (S_ISDIR(inode->i_mode)) {
 			drop_nlink(inode);

fs/f2fs/f2fs.h

@@ -211,11 +211,11 @@ struct dnode_of_data {
 static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
 		struct page *ipage, struct page *npage, nid_t nid)
 {
+	memset(dn, 0, sizeof(*dn));
 	dn->inode = inode;
 	dn->inode_page = ipage;
 	dn->node_page = npage;
 	dn->nid = nid;
-	dn->inode_page_locked = 0;
 }
 
 /*
@@ -877,6 +877,8 @@ bool f2fs_empty_dir(struct inode *);
  * super.c
  */
 int f2fs_sync_fs(struct super_block *, int);
+extern __printf(3, 4)
+void f2fs_msg(struct super_block *, const char *, const char *, ...);
 
 /*
  * hash.c
@@ -912,7 +914,7 @@ int restore_node_summary(struct f2fs_sb_info *, unsigned int,
 void flush_nat_entries(struct f2fs_sb_info *);
 int build_node_manager(struct f2fs_sb_info *);
 void destroy_node_manager(struct f2fs_sb_info *);
-int create_node_manager_caches(void);
+int __init create_node_manager_caches(void);
 void destroy_node_manager_caches(void);
 
 /*
@@ -964,7 +966,7 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void block_operations(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool, bool);
 void init_orphan_info(struct f2fs_sb_info *);
-int create_checkpoint_caches(void);
+int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
 
 /*
@@ -984,9 +986,9 @@ 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);
-int f2fs_gc(struct f2fs_sb_info *, int);
+int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int create_gc_caches(void);
+int __init create_gc_caches(void);
 void destroy_gc_caches(void);
 
 /*
@@ -1058,7 +1060,8 @@ struct f2fs_stat_info {
 
 int f2fs_build_stats(struct f2fs_sb_info *);
 void f2fs_destroy_stats(struct f2fs_sb_info *);
-void destroy_root_stats(void);
+void __init f2fs_create_root_stats(void);
+void f2fs_destroy_root_stats(void);
 #else
 #define stat_inc_call_count(si)
 #define stat_inc_seg_count(si, type)
@@ -1068,7 +1071,8 @@ void destroy_root_stats(void);
 
 static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void destroy_root_stats(void) { }
+static inline void __init f2fs_create_root_stats(void) { }
+static inline void f2fs_destroy_root_stats(void) { }
 #endif
 
 extern const struct file_operations f2fs_dir_operations;

fs/f2fs/file.c

@@ -96,8 +96,9 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
-	.fault        = filemap_fault,
-	.page_mkwrite = f2fs_vm_page_mkwrite,
+	.fault		= filemap_fault,
+	.page_mkwrite	= f2fs_vm_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
@@ -137,6 +138,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (ret)
 		return ret;
 
+	/* guarantee free sections for fsync */
+	f2fs_balance_fs(sbi);
+
 	mutex_lock(&inode->i_mutex);
 
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
@@ -407,6 +411,8 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 		struct dnode_of_data dn;
 		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
+		f2fs_balance_fs(sbi);
+
 		mutex_lock_op(sbi, DATA_TRUNC);
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		err = get_dnode_of_data(&dn, index, RDONLY_NODE);
@@ -534,7 +540,6 @@ static long f2fs_fallocate(struct file *file, int mode,
 				loff_t offset, loff_t len)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
-	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	long ret;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -545,7 +550,10 @@ static long f2fs_fallocate(struct file *file, int mode,
 	else
 		ret = expand_inode_data(inode, offset, len, mode);
 
-	f2fs_balance_fs(sbi);
+	if (!ret) {
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
+	}
 	return ret;
 }