f2fs: support zone capacity less than zone size

NVMe Zoned Namespace devices can have zone-capacity less than zone-size.
Zone-capacity indicates the maximum number of sectors that are usable in
a zone beginning from the first sector of the zone. This makes the sectors
sectors after the zone-capacity till zone-size to be unusable.
This patch set tracks zone-size and zone-capacity in zoned devices and
calculate the usable blocks per segment and usable segments per section.

If zone-capacity is less than zone-size mark only those segments which
start before zone-capacity as free segments. All segments at and beyond
zone-capacity are treated as permanently used segments. In cases where
zone-capacity does not align with segment size the last segment will start
before zone-capacity and end beyond the zone-capacity of the zone. For
such spanning segments only sectors within the zone-capacity are used.

During writes and GC manage the usable segments in a section and usable
blocks per segment. Segments which are beyond zone-capacity are never
allocated, and do not need to be garbage collected, only the segments
which are before zone-capacity needs to garbage collected.
For spanning segments based on the number of usable blocks in that
segment, write to blocks only up to zone-capacity.

Zone-capacity is device specific and cannot be configured by the user.
Since NVMe ZNS device zones are sequentially write only, a block device
with conventional zones or any normal block device is needed along with
the ZNS device for the metadata operations of F2fs.

A typical nvme-cli output of a zoned device shows zone start and capacity
and write pointer as below:

SLBA: 0x0     WP: 0x0     Cap: 0x18800 State: EMPTY Type: SEQWRITE_REQ
SLBA: 0x20000 WP: 0x20000 Cap: 0x18800 State: EMPTY Type: SEQWRITE_REQ
SLBA: 0x40000 WP: 0x40000 Cap: 0x18800 State: EMPTY Type: SEQWRITE_REQ

Here zone size is 64MB, capacity is 49MB, WP is at zone start as the zones
are in EMPTY state. For each zone, only zone start + 49MB is usable area,
any lba/sector after 49MB cannot be read or written to, the drive will fail
any attempts to read/write. So, the second zone starts at 64MB and is
usable till 113MB (64 + 49) and the range between 113 and 128MB is
again unusable. The next zone starts at 128MB, and so on.

Signed-off-by: Aravind Ramesh <aravind.ramesh@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 144 insertions, 12 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index e247a5ef3713..6a8c92f4c536 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -859,20 +859,22 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned short valid_blocks, ckpt_valid_blocks;
+	unsigned int usable_blocks;
 
 	if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
 		return;
 
+	usable_blocks = f2fs_usable_blks_in_seg(sbi, segno);
 	mutex_lock(&dirty_i->seglist_lock);
 
 	valid_blocks = get_valid_blocks(sbi, segno, false);
 	ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);
 
 	if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
-				ckpt_valid_blocks == sbi->blocks_per_seg)) {
+		ckpt_valid_blocks == usable_blocks)) {
 		__locate_dirty_segment(sbi, segno, PRE);
 		__remove_dirty_segment(sbi, segno, DIRTY);
-	} else if (valid_blocks < sbi->blocks_per_seg) {
+	} else if (valid_blocks < usable_blocks) {
 		__locate_dirty_segment(sbi, segno, DIRTY);
 	} else {
 		/* Recovery routine with SSR needs this */
@@ -915,9 +917,11 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
 	for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
 		se = get_seg_entry(sbi, segno);
 		if (IS_NODESEG(se->type))
-			holes[NODE] += sbi->blocks_per_seg - se->valid_blocks;
+			holes[NODE] += f2fs_usable_blks_in_seg(sbi, segno) -
+							se->valid_blocks;
 		else
-			holes[DATA] += sbi->blocks_per_seg - se->valid_blocks;
+			holes[DATA] += f2fs_usable_blks_in_seg(sbi, segno) -
+							se->valid_blocks;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
@@ -2167,7 +2171,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
 
 	f2fs_bug_on(sbi, (new_vblocks < 0 ||
-				(new_vblocks > sbi->blocks_per_seg)));
+			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
 
 	se->valid_blocks = new_vblocks;
 	se->mtime = get_mtime(sbi, false);
@@ -2933,9 +2937,9 @@ out:
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	if (curseg->next_blkoff < sbi->blocks_per_seg)
-		return true;
-	return false;
+
+	return curseg->next_blkoff < f2fs_usable_blks_in_seg(sbi,
+							curseg->segno);
 }
 
 int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
@@ -4294,9 +4298,12 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 {
 	unsigned int start;
 	int type;
+	struct seg_entry *sentry;
 
 	for (start = 0; start < MAIN_SEGS(sbi); start++) {
-		struct seg_entry *sentry = get_seg_entry(sbi, start);
+		if (f2fs_usable_blks_in_seg(sbi, start) == 0)
+			continue;
+		sentry = get_seg_entry(sbi, start);
 		if (!sentry->valid_blocks)
 			__set_free(sbi, start);
 		else
@@ -4316,7 +4323,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int segno = 0, offset = 0, secno;
-	block_t valid_blocks;
+	block_t valid_blocks, usable_blks_in_seg;
 	block_t blks_per_sec = BLKS_PER_SEC(sbi);
 
 	while (1) {
@@ -4326,9 +4333,10 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 			break;
 		offset = segno + 1;
 		valid_blocks = get_valid_blocks(sbi, segno, false);
-		if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
+		usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno);
+		if (valid_blocks == usable_blks_in_seg || !valid_blocks)
 			continue;
-		if (valid_blocks > sbi->blocks_per_seg) {
+		if (valid_blocks > usable_blks_in_seg) {
 			f2fs_bug_on(sbi, 1);
 			continue;
 		}
@@ -4678,6 +4686,101 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
 
 	return 0;
 }
+
+static bool is_conv_zone(struct f2fs_sb_info *sbi, unsigned int zone_idx,
+						unsigned int dev_idx)
+{
+	if (!bdev_is_zoned(FDEV(dev_idx).bdev))
+		return true;
+	return !test_bit(zone_idx, FDEV(dev_idx).blkz_seq);
+}
+
+/* Return the zone index in the given device */
+static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno,
+					int dev_idx)
+{
+	block_t sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
+
+	return (sec_start_blkaddr - FDEV(dev_idx).start_blk) >>
+						sbi->log_blocks_per_blkz;
+}
+
+/*
+ * Return the usable segments in a section based on the zone's
+ * corresponding zone capacity. Zone is equal to a section.
+ */
+static inline unsigned int f2fs_usable_zone_segs_in_sec(
+		struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	unsigned int dev_idx, zone_idx, unusable_segs_in_sec;
+
+	dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno));
+	zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx);
+
+	/* Conventional zone's capacity is always equal to zone size */
+	if (is_conv_zone(sbi, zone_idx, dev_idx))
+		return sbi->segs_per_sec;
+
+	/*
+	 * If the zone_capacity_blocks array is NULL, then zone capacity
+	 * is equal to the zone size for all zones
+	 */
+	if (!FDEV(dev_idx).zone_capacity_blocks)
+		return sbi->segs_per_sec;
+
+	/* Get the segment count beyond zone capacity block */
+	unusable_segs_in_sec = (sbi->blocks_per_blkz -
+				FDEV(dev_idx).zone_capacity_blocks[zone_idx]) >>
+				sbi->log_blocks_per_seg;
+	return sbi->segs_per_sec - unusable_segs_in_sec;
+}
+
+/*
+ * Return the number of usable blocks in a segment. The number of blocks
+ * returned is always equal to the number of blocks in a segment for
+ * segments fully contained within a sequential zone capacity or a
+ * conventional zone. For segments partially contained in a sequential
+ * zone capacity, the number of usable blocks up to the zone capacity
+ * is returned. 0 is returned in all other cases.
+ */
+static inline unsigned int f2fs_usable_zone_blks_in_seg(
+			struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	block_t seg_start, sec_start_blkaddr, sec_cap_blkaddr;
+	unsigned int zone_idx, dev_idx, secno;
+
+	secno = GET_SEC_FROM_SEG(sbi, segno);
+	seg_start = START_BLOCK(sbi, segno);
+	dev_idx = f2fs_target_device_index(sbi, seg_start);
+	zone_idx = get_zone_idx(sbi, secno, dev_idx);
+
+	/*
+	 * Conventional zone's capacity is always equal to zone size,
+	 * so, blocks per segment is unchanged.
+	 */
+	if (is_conv_zone(sbi, zone_idx, dev_idx))
+		return sbi->blocks_per_seg;
+
+	if (!FDEV(dev_idx).zone_capacity_blocks)
+		return sbi->blocks_per_seg;
+
+	sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
+	sec_cap_blkaddr = sec_start_blkaddr +
+				FDEV(dev_idx).zone_capacity_blocks[zone_idx];
+
+	/*
+	 * If segment starts before zone capacity and spans beyond
+	 * zone capacity, then usable blocks are from seg start to
+	 * zone capacity. If the segment starts after the zone capacity,
+	 * then there are no usable blocks.
+	 */
+	if (seg_start >= sec_cap_blkaddr)
+		return 0;
+	if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr)
+		return sec_cap_blkaddr - seg_start;
+
+	return sbi->blocks_per_seg;
+}
 #else
 int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
 {
@@ -4688,7 +4791,36 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
 {
 	return 0;
 }
+
+static inline unsigned int f2fs_usable_zone_blks_in_seg(struct f2fs_sb_info *sbi,
+							unsigned int segno)
+{
+	return 0;
+}
+
+static inline unsigned int f2fs_usable_zone_segs_in_sec(struct f2fs_sb_info *sbi,
+							unsigned int segno)
+{
+	return 0;
+}
 #endif
+unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
+					unsigned int segno)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return f2fs_usable_zone_blks_in_seg(sbi, segno);
+
+	return sbi->blocks_per_seg;
+}
+
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
+					unsigned int segno)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return f2fs_usable_zone_segs_in_sec(sbi, segno);
+
+	return sbi->segs_per_sec;
+}
 
 /*
  * Update min, max modified time for cost-benefit GC algorithm