f2fs: introduce mode=lfs mount option

This mount option is to enable original log-structured filesystem forcefully.
So, there should be no random writes for main area.

Especially, this supports host-managed SMR device.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

9 files changed, 74 insertions, 4 deletions

diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index c4b732b46..0ea1a51b1 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -143,6 +143,9 @@ noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 data_flush             Enable data flushing before checkpoint in order to
                        persist data of regular and symlink.
+mode=%s                Control block allocation mode which supports "adaptive"
+                       and "lfs". In "lfs" mode, there should be no random
+                       writes towards main area.
 
 ================================================================================
 DEBUGFS ENTRIES
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 99e75e5b9..fe540de91 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -982,7 +982,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * This avoids to conduct wrong roll-forward operations and uses
 	 * metapages, so should be called prior to sync_meta_pages below.
 	 */
-	if (discard_next_dnode(sbi, discard_blk))
+	if (!test_opt(sbi, LFS) && discard_next_dnode(sbi, discard_blk))
 		invalidate = true;
 
 	/* Flush all the NAT/SIT pages */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 58d7a12e9..42ee22270 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1737,6 +1737,8 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		return 0;
+	if (test_opt(F2FS_I_SB(inode), LFS))
+		return 0;
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 55e218355..5204cfea2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -112,6 +112,8 @@ static inline bool time_to_inject(int type)
 #define F2FS_MOUNT_FORCE_FG_GC		0x00004000
 #define F2FS_MOUNT_DATA_FLUSH		0x00008000
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
+#define F2FS_MOUNT_ADAPTIVE		0x00020000
+#define F2FS_MOUNT_LFS			0x00040000
 
 #define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 72493c230..e61e414dc 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -896,9 +896,15 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 		return full ? truncate_hole(inode, dst, dst + 1) : 0;
 
 	if (do_replace) {
-		struct page *ipage = get_node_page(sbi, inode->i_ino);
+		struct page *ipage;
 		struct node_info ni;
 
+		if (test_opt(sbi, LFS)) {
+			ret = -ENOTSUPP;
+			goto err_out;
+		}
+
+		ipage = get_node_page(sbi, inode->i_ino);
 		if (IS_ERR(ipage)) {
 			ret = PTR_ERR(ipage);
 			goto err_out;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 3c6425026..a214c365a 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -624,8 +624,12 @@ out:
 	if (err) {
 		bool invalidate = false;
 
-		if (discard_next_dnode(sbi, blkaddr))
+		if (test_opt(sbi, LFS)) {
+			update_meta_page(sbi, NULL, blkaddr);
 			invalidate = true;
+		} else if (discard_next_dnode(sbi, blkaddr)) {
+			invalidate = true;
+		}
 
 		/* Flush all the NAT/SIT pages */
 		while (get_pages(sbi, F2FS_DIRTY_META))
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index b489f7295..0b9e1a31e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -766,6 +766,7 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
 	unsigned int start = 0, end = -1;
+	unsigned int secno, start_segno;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -785,8 +786,22 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		if (!test_opt(sbi, DISCARD))
 			continue;
 
-		f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
+			continue;
+		}
+next:
+		secno = GET_SECNO(sbi, start);
+		start_segno = secno * sbi->segs_per_sec;
+		if (!IS_CURSEC(sbi, secno) &&
+			!get_valid_blocks(sbi, start, sbi->segs_per_sec))
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+				sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+		start = start_segno + sbi->segs_per_sec;
+		if (start < end)
+			goto next;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
@@ -1280,6 +1295,9 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
 	int i;
 
+	if (test_opt(sbi, LFS))
+		return;
+
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
 		__allocate_new_segments(sbi, i);
 }
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 43c6d0bab..1e7148897 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -469,6 +469,10 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+
+	if (test_opt(sbi, LFS))
+		return false;
+
 	return free_sections(sbi) <= (node_secs + 2 * dent_secs +
 						reserved_sections(sbi) + 1);
 }
@@ -532,6 +536,9 @@ static inline bool need_inplace_update(struct inode *inode)
 	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
 		return false;
 
+	if (test_opt(sbi, LFS))
+		return false;
+
 	if (policy & (0x1 << F2FS_IPU_FORCE))
 		return true;
 	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e9800b3f6..e54d8c7de 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -93,6 +93,7 @@ enum {
 	Opt_noextent_cache,
 	Opt_noinline_data,
 	Opt_data_flush,
+	Opt_mode,
 	Opt_fault_injection,
 	Opt_err,
 };
@@ -120,6 +121,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_noextent_cache, "noextent_cache"},
 	{Opt_noinline_data, "noinline_data"},
 	{Opt_data_flush, "data_flush"},
+	{Opt_mode, "mode=%s"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_err, NULL},
 };
@@ -501,6 +503,25 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_data_flush:
 			set_opt(sbi, DATA_FLUSH);
 			break;
+		case Opt_mode:
+			name = match_strdup(&args[0]);
+
+			if (!name)
+				return -ENOMEM;
+			if (strlen(name) == 8 &&
+					!strncmp(name, "adaptive", 8)) {
+				set_opt(sbi, ADAPTIVE);
+				clear_opt(sbi, LFS);
+			} else if (strlen(name) == 3 &&
+					!strncmp(name, "lfs", 3)) {
+				clear_opt(sbi, ADAPTIVE);
+				set_opt(sbi, LFS);
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
@@ -856,6 +877,12 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",noextent_cache");
 	if (test_opt(sbi, DATA_FLUSH))
 		seq_puts(seq, ",data_flush");
+
+	seq_puts(seq, ",mode=");
+	if (test_opt(sbi, ADAPTIVE))
+		seq_puts(seq, "adaptive");
+	else if (test_opt(sbi, LFS))
+		seq_puts(seq, "lfs");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
 	return 0;
@@ -938,6 +965,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, EXTENT_CACHE);
 	set_opt(sbi, FLUSH_MERGE);
+	set_opt(sbi, ADAPTIVE);
 
 #ifdef CONFIG_F2FS_FS_XATTR
 	set_opt(sbi, XATTR_USER);