Merge tag 'for-f2fs-3.15' 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.
   - introduce large directory support
   - introduce f2fs_issue_flush to merge redundant flush commands
   - merge write IOs as much as possible aligned to the segment
   - add sysfs entries to tune the f2fs configuration
   - use radix_tree for the free_nid_list to reduce in-memory operations
   - remove costly bit operations in f2fs_find_entry
   - enhance the readahead flow for CP/NAT/SIT/SSA blocks

  The other bug fixes are as follows:
   - recover xattr node blocks correctly after sudden-power-cut
   - fix to calculate the maximum number of node ids
   - enhance to handle many error cases

  And, there are a bunch of cleanups"

* tag 'for-f2fs-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (62 commits)
  f2fs: fix wrong statistics of inline data
  f2fs: check the acl's validity before setting
  f2fs: introduce f2fs_issue_flush to avoid redundant flush issue
  f2fs: fix to cover io->bio with io_rwsem
  f2fs: fix error path when fail to read inline data
  f2fs: use list_for_each_entry{_safe} for simplyfying code
  f2fs: avoid free slab cache under spinlock
  f2fs: avoid unneeded lookup when xattr name length is too long
  f2fs: avoid unnecessary bio submit when wait page writeback
  f2fs: return -EIO when node id is not matched
  f2fs: avoid RECLAIM_FS-ON-W warning
  f2fs: skip unnecessary node writes during fsync
  f2fs: introduce fi->i_sem to protect fi's info
  f2fs: change reclaim rate in percentage
  f2fs: add missing documentation for dir_level
  f2fs: remove unnecessary threshold
  f2fs: throttle the memory footprint with a sysfs entry
  f2fs: avoid to drop nat entries due to the negative nr_shrink
  f2fs: call f2fs_wait_on_page_writeback instead of native function
  f2fs: introduce nr_pages_to_write for segment alignment
  ...

1 files changed, 64 insertions, 33 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 856bdf994c0a..c756923a7302 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -51,6 +51,7 @@ enum {
 	Opt_disable_ext_identify,
 	Opt_inline_xattr,
 	Opt_inline_data,
+	Opt_flush_merge,
 	Opt_err,
 };
 
@@ -67,6 +68,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_disable_ext_identify, "disable_ext_identify"},
 	{Opt_inline_xattr, "inline_xattr"},
 	{Opt_inline_data, "inline_data"},
+	{Opt_flush_merge, "flush_merge"},
 	{Opt_err, NULL},
 };
 
@@ -74,6 +76,7 @@ static match_table_t f2fs_tokens = {
 enum {
 	GC_THREAD,	/* struct f2fs_gc_thread */
 	SM_INFO,	/* struct f2fs_sm_info */
+	NM_INFO,	/* struct f2fs_nm_info */
 	F2FS_SBI,	/* struct f2fs_sb_info */
 };
 
@@ -92,6 +95,8 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 		return (unsigned char *)sbi->gc_thread;
 	else if (struct_type == SM_INFO)
 		return (unsigned char *)SM_I(sbi);
+	else if (struct_type == NM_INFO)
+		return (unsigned char *)NM_I(sbi);
 	else if (struct_type == F2FS_SBI)
 		return (unsigned char *)sbi;
 	return NULL;
@@ -183,7 +188,9 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -196,6 +203,8 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(max_victim_search),
+	ATTR_LIST(dir_level),
+	ATTR_LIST(ram_thresh),
 	NULL,
 };
 
@@ -256,9 +265,9 @@ static int parse_options(struct super_block *sb, char *options)
 
 			if (!name)
 				return -ENOMEM;
-			if (!strncmp(name, "on", 2))
+			if (strlen(name) == 2 && !strncmp(name, "on", 2))
 				set_opt(sbi, BG_GC);
-			else if (!strncmp(name, "off", 3))
+			else if (strlen(name) == 3 && !strncmp(name, "off", 3))
 				clear_opt(sbi, BG_GC);
 			else {
 				kfree(name);
@@ -327,6 +336,9 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_inline_data:
 			set_opt(sbi, INLINE_DATA);
 			break;
+		case Opt_flush_merge:
+			set_opt(sbi, FLUSH_MERGE);
+			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -353,12 +365,16 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	fi->i_current_depth = 1;
 	fi->i_advise = 0;
 	rwlock_init(&fi->ext.ext_lock);
+	init_rwsem(&fi->i_sem);
 
 	set_inode_flag(fi, FI_NEW_INODE);
 
 	if (test_opt(F2FS_SB(sb), INLINE_XATTR))
 		set_inode_flag(fi, FI_INLINE_XATTR);
 
+	/* Will be used by directory only */
+	fi->i_dir_level = F2FS_SB(sb)->dir_level;
+
 	return &fi->vfs_inode;
 }
 
@@ -526,6 +542,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",disable_ext_identify");
 	if (test_opt(sbi, INLINE_DATA))
 		seq_puts(seq, ",inline_data");
+	if (test_opt(sbi, FLUSH_MERGE))
+		seq_puts(seq, ",flush_merge");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
 	return 0;
@@ -539,13 +557,22 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset)
 			le32_to_cpu(sbi->raw_super->segment_count_main);
 	int i;
 
+	seq_puts(seq, "format: segment_type|valid_blocks\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
 	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");
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		if ((i % 10) == 0)
+			seq_printf(seq, "%-5d", i);
+		seq_printf(seq, "%d|%-3u", se->type,
+					get_valid_blocks(sbi, i, 1));
+		if ((i % 10) == 9 || i == (total_segs - 1))
+			seq_putc(seq, '\n');
 		else
-			seq_puts(seq, " ");
+			seq_putc(seq, ' ');
 	}
+
 	return 0;
 }
 
@@ -640,6 +667,8 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 
 	if (unlikely(ino < F2FS_ROOT_INO(sbi)))
 		return ERR_PTR(-ESTALE);
+	if (unlikely(ino >= NM_I(sbi)->max_nid))
+		return ERR_PTR(-ESTALE);
 
 	/*
 	 * f2fs_iget isn't quite right if the inode is currently unallocated!
@@ -787,6 +816,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < NR_COUNT_TYPE; i++)
 		atomic_set(&sbi->nr_pages[i], 0);
+
+	sbi->dir_level = DEF_DIR_LEVEL;
 }
 
 /*
@@ -898,11 +929,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->por_doing = false;
 	spin_lock_init(&sbi->stat_lock);
 
-	mutex_init(&sbi->read_io.io_mutex);
+	init_rwsem(&sbi->read_io.io_rwsem);
 	sbi->read_io.sbi = sbi;
 	sbi->read_io.bio = NULL;
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		mutex_init(&sbi->write_io[i].io_mutex);
+		init_rwsem(&sbi->write_io[i].io_rwsem);
 		sbi->write_io[i].sbi = sbi;
 		sbi->write_io[i].bio = NULL;
 	}
@@ -991,28 +1022,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_root_inode;
 	}
 
-	/* recover fsynced data */
-	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
-		err = recover_fsync_data(sbi);
-		if (err)
-			f2fs_msg(sb, KERN_ERR,
-				"Cannot recover all fsync data errno=%ld", err);
-	}
-
-	/*
-	 * If filesystem is not mounted as read-only then
-	 * do start the gc_thread.
-	 */
-	if (!(sb->s_flags & MS_RDONLY)) {
-		/* After POR, we can run background GC thread.*/
-		err = start_gc_thread(sbi);
-		if (err)
-			goto free_gc;
-	}
-
 	err = f2fs_build_stats(sbi);
 	if (err)
-		goto free_gc;
+		goto free_root_inode;
 
 	if (f2fs_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -1034,17 +1046,36 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
 							"%s", sb->s_id);
 	if (err)
-		goto fail;
+		goto free_proc;
+
+	/* recover fsynced data */
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+		err = recover_fsync_data(sbi);
+		if (err)
+			f2fs_msg(sb, KERN_ERR,
+				"Cannot recover all fsync data errno=%ld", err);
+	}
 
+	/*
+	 * If filesystem is not mounted as read-only then
+	 * do start the gc_thread.
+	 */
+	if (!(sb->s_flags & MS_RDONLY)) {
+		/* After POR, we can run background GC thread.*/
+		err = start_gc_thread(sbi);
+		if (err)
+			goto free_kobj;
+	}
 	return 0;
-fail:
+
+free_kobj:
+	kobject_del(&sbi->s_kobj);
+free_proc:
 	if (sbi->s_proc) {
 		remove_proc_entry("segment_info", sbi->s_proc);
 		remove_proc_entry(sb->s_id, f2fs_proc_root);
 	}
 	f2fs_destroy_stats(sbi);
-free_gc:
-	stop_gc_thread(sbi);
 free_root_inode:
 	dput(sb->s_root);
 	sb->s_root = NULL;
@@ -1084,7 +1115,7 @@ MODULE_ALIAS_FS("f2fs");
 static int __init init_inodecache(void)
 {
 	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
-			sizeof(struct f2fs_inode_info), NULL);
+			sizeof(struct f2fs_inode_info));
 	if (!f2fs_inode_cachep)
 		return -ENOMEM;
 	return 0;