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, 17 insertions, 9 deletions

diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 752b177073b2..4bf5bdb3ea07 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -411,6 +411,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
 
 	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
@@ -418,7 +419,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 
 	next = find_next_bit(free_i->free_segmap,
 			start_segno + sbi->segs_per_sec, start_segno);
-	if (next >= start_segno + sbi->segs_per_sec) {
+	if (next >= start_segno + usable_segs) {
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
@@ -444,6 +445,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
+	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
 
 	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
@@ -453,7 +455,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 			goto skip_free;
 		next = find_next_bit(free_i->free_segmap,
 				start_segno + sbi->segs_per_sec, start_segno);
-		if (next >= start_segno + sbi->segs_per_sec) {
+		if (next >= start_segno + usable_segs) {
 			if (test_and_clear_bit(secno, free_i->free_secmap))
 				free_i->free_sections++;
 		}
@@ -546,8 +548,8 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
 	/* check current node segment */
 	for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
 		segno = CURSEG_I(sbi, i)->segno;
-		left_blocks = sbi->blocks_per_seg -
-			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+		left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
+				get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 
 		if (node_blocks > left_blocks)
 			return false;
@@ -555,7 +557,7 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
 
 	/* check current data segment */
 	segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
-	left_blocks = sbi->blocks_per_seg -
+	left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
 			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 	if (dent_blocks > left_blocks)
 		return false;
@@ -677,21 +679,22 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
 	int valid_blocks = 0;
 	int cur_pos = 0, next_pos;
+	unsigned int usable_blks_per_seg = f2fs_usable_blks_in_seg(sbi, segno);
 
 	/* check bitmap with valid block count */
 	do {
 		if (is_valid) {
 			next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 			valid_blocks += next_pos - cur_pos;
 		} else
 			next_pos = find_next_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 		cur_pos = next_pos;
 		is_valid = !is_valid;
-	} while (cur_pos < sbi->blocks_per_seg);
+	} while (cur_pos < usable_blks_per_seg);
 
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
 		f2fs_err(sbi, "Mismatch valid blocks %d vs. %d",
@@ -700,8 +703,13 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 		return -EFSCORRUPTED;
 	}
 
+	if (usable_blks_per_seg < sbi->blocks_per_seg)
+		f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map,
+				sbi->blocks_per_seg,
+				usable_blks_per_seg) != sbi->blocks_per_seg);
+
 	/* check segment usage, and check boundary of a given segment number */
-	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg
 					|| segno > TOTAL_SEGS(sbi) - 1)) {
 		f2fs_err(sbi, "Wrong valid blocks %d or segno %u",
 			 GET_SIT_VBLOCKS(raw_sit), segno);