f2fs: Add option to limit required GC for checkpoint=disable

This extends the checkpoint option to allow checkpoint=disable:%u[%]
This allows you to specify what how much of the disk you are willing
to lose access to while mounting with checkpoint=disable. If the amount
lost would be higher, the mount will return -EAGAIN. This can be given
as a percent of total space, or in blocks.

Currently, we need to run garbage collection until the amount of holes
is smaller than the OVP space. With the new option, f2fs can mark
space as unusable up front instead of requiring garbage collection until
the number of holes is small enough.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

4 files changed, 73 insertions, 25 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9a2a1b49c3ef..9674a85154b2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -136,6 +136,9 @@ struct f2fs_mount_info {
 	int alloc_mode;			/* segment allocation policy */
 	int fsync_mode;			/* fsync policy */
 	bool test_dummy_encryption;	/* test dummy encryption */
+	block_t unusable_cap;		/* Amount of space allowed to be
+					 * unusable when disabling checkpoint
+					 */
 };
 
 #define F2FS_FEATURE_ENCRYPT		0x0001
@@ -3085,7 +3088,8 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
 void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
 					struct cp_control *cpc);
 void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
-int f2fs_disable_cp_again(struct f2fs_sb_info *sbi);
+block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
+int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
 void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
 int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
 void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 71f8913aa5f9..54a3e398d1ea 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -873,13 +873,14 @@ void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-int f2fs_disable_cp_again(struct f2fs_sb_info *sbi)
+block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
 {
-	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	int ovp_hole_segs =
 		(overprovision_segments(sbi) - reserved_segments(sbi));
 	block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg;
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	block_t holes[2] = {0, 0};	/* DATA and NODE */
+	block_t unusable;
 	struct seg_entry *se;
 	unsigned int segno;
 
@@ -893,7 +894,17 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi)
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
-	if (holes[DATA] > ovp_holes || holes[NODE] > ovp_holes)
+	unusable = holes[DATA] > holes[NODE] ? holes[DATA] : holes[NODE];
+	if (unusable > ovp_holes)
+		return unusable - ovp_holes;
+	return 0;
+}
+
+int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable)
+{
+	int ovp_hole_segs =
+		(overprovision_segments(sbi) - reserved_segments(sbi));
+	if (unusable > F2FS_OPTION(sbi).unusable_cap)
 		return -EAGAIN;
 	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&
 		dirty_segments(sbi) > ovp_hole_segs)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4b547024571f..15d7e30bfc72 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -136,7 +136,10 @@ enum {
 	Opt_alloc,
 	Opt_fsync,
 	Opt_test_dummy_encryption,
-	Opt_checkpoint,
+	Opt_checkpoint_disable,
+	Opt_checkpoint_disable_cap,
+	Opt_checkpoint_disable_cap_perc,
+	Opt_checkpoint_enable,
 	Opt_err,
 };
 
@@ -195,7 +198,10 @@ static match_table_t f2fs_tokens = {
 	{Opt_alloc, "alloc_mode=%s"},
 	{Opt_fsync, "fsync_mode=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
-	{Opt_checkpoint, "checkpoint=%s"},
+	{Opt_checkpoint_disable, "checkpoint=disable"},
+	{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
+	{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},
+	{Opt_checkpoint_enable, "checkpoint=enable"},
 	{Opt_err, NULL},
 };
 
@@ -772,22 +778,30 @@ static int parse_options(struct super_block *sb, char *options)
 					"Test dummy encryption mount option ignored");
 #endif
 			break;
-		case Opt_checkpoint:
-			name = match_strdup(&args[0]);
-			if (!name)
-				return -ENOMEM;
-
-			if (strlen(name) == 6 &&
-					!strncmp(name, "enable", 6)) {
-				clear_opt(sbi, DISABLE_CHECKPOINT);
-			} else if (strlen(name) == 7 &&
-					!strncmp(name, "disable", 7)) {
-				set_opt(sbi, DISABLE_CHECKPOINT);
-			} else {
-				kvfree(name);
+		case Opt_checkpoint_disable_cap_perc:
+			if (args->from && match_int(args, &arg))
 				return -EINVAL;
-			}
-			kvfree(name);
+			if (arg < 0 || arg > 100)
+				return -EINVAL;
+			if (arg == 100)
+				F2FS_OPTION(sbi).unusable_cap =
+					sbi->user_block_count;
+			else
+				F2FS_OPTION(sbi).unusable_cap =
+					(sbi->user_block_count / 100) *	arg;
+			set_opt(sbi, DISABLE_CHECKPOINT);
+			break;
+		case Opt_checkpoint_disable_cap:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			F2FS_OPTION(sbi).unusable_cap = arg;
+			set_opt(sbi, DISABLE_CHECKPOINT);
+			break;
+		case Opt_checkpoint_disable:
+			set_opt(sbi, DISABLE_CHECKPOINT);
+			break;
+		case Opt_checkpoint_enable:
+			clear_opt(sbi, DISABLE_CHECKPOINT);
 			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
@@ -1412,8 +1426,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",alloc_mode=%s", "reuse");
 
 	if (test_opt(sbi, DISABLE_CHECKPOINT))
-		seq_puts(seq, ",checkpoint=disable");
-
+		seq_printf(seq, ",checkpoint=disable:%u",
+				F2FS_OPTION(sbi).unusable_cap);
 	if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX)
 		seq_printf(seq, ",fsync_mode=%s", "posix");
 	else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
@@ -1442,6 +1456,7 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, EXTENT_CACHE);
 	set_opt(sbi, NOHEAP);
 	clear_opt(sbi, DISABLE_CHECKPOINT);
+	F2FS_OPTION(sbi).unusable_cap = 0;
 	sbi->sb->s_flags |= SB_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
 	set_opt(sbi, DISCARD);
@@ -1470,6 +1485,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 	struct cp_control cpc;
 	int err = 0;
 	int ret;
+	block_t unusable;
 
 	if (s_flags & SB_RDONLY) {
 		f2fs_msg(sbi->sb, KERN_ERR,
@@ -1497,7 +1513,8 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 		goto restore_flag;
 	}
 
-	if (f2fs_disable_cp_again(sbi)) {
+	unusable = f2fs_get_unusable_blocks(sbi);
+	if (f2fs_disable_cp_again(sbi, unusable)) {
 		err = -EAGAIN;
 		goto restore_flag;
 	}
@@ -1510,7 +1527,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 		goto out_unlock;
 
 	spin_lock(&sbi->stat_lock);
-	sbi->unusable_block_count = 0;
+	sbi->unusable_block_count = unusable;
 	spin_unlock(&sbi->stat_lock);
 
 out_unlock:
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 729f46a3c9ee..fa184880cff3 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -68,6 +68,20 @@ static ssize_t dirty_segments_show(struct f2fs_attr *a,
 		(unsigned long long)(dirty_segments(sbi)));
 }
 
+static ssize_t unusable_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	block_t unusable;
+
+	if (test_opt(sbi, DISABLE_CHECKPOINT))
+		unusable = sbi->unusable_block_count;
+	else
+		unusable = f2fs_get_unusable_blocks(sbi);
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)unusable);
+}
+
+
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -440,6 +454,7 @@ F2FS_GENERAL_RO_ATTR(dirty_segments);
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 F2FS_GENERAL_RO_ATTR(features);
 F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
+F2FS_GENERAL_RO_ATTR(unusable);
 
 #ifdef CONFIG_FS_ENCRYPTION
 F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@@ -495,6 +510,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(inject_type),
 #endif
 	ATTR_LIST(dirty_segments),
+	ATTR_LIST(unusable),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(features),
 	ATTR_LIST(reserved_blocks),