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>

Documentation/filesystems/f2fs.rst

@@ -766,3 +766,18 @@ Compress metadata layout::
 	+-------------+-------------+----------+----------------------------+
 	| data length | data chksum | reserved |      compressed data       |
 	+-------------+-------------+----------+----------------------------+
+
+NVMe Zoned Namespace devices
+----------------------------
+
+- ZNS defines a per-zone capacity which can be equal or less than the
+  zone-size. Zone-capacity is the number of usable blocks in the zone.
+  F2fs checks if zone-capacity is less than zone-size, if it is, then any
+  segment which starts after the zone-capacity is marked as not-free in
+  the free segment bitmap at initial mount time. These segments are marked
+  as permanently used so they are not allocated for writes and
+  consequently are not needed to be garbage collected. In case the
+  zone-capacity is not aligned to default segment size(2MB), then a segment
+  can start before the zone-capacity and span across zone-capacity boundary.
+  Such spanning segments are also considered as usable segments. All blocks
+  past the zone-capacity are considered unusable in these segments.

fs/f2fs/f2fs.h

@@ -1209,6 +1209,7 @@ struct f2fs_dev_info {
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_blkz;		/* Total number of zones */
 	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
+	block_t *zone_capacity_blocks;  /* Array of zone capacity in blks */
 #endif
 };
 
@@ -3378,6 +3379,10 @@ void f2fs_destroy_segment_manager_caches(void);
 int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
 enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
 			enum page_type type, enum temp_type temp);
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
+			unsigned int segno);
+unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
+			unsigned int segno);
 
 /*
  * checkpoint.c

fs/f2fs/gc.c

@@ -266,13 +266,14 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned char age = 0;
 	unsigned char u;
 	unsigned int i;
+	unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi, segno);
 
-	for (i = 0; i < sbi->segs_per_sec; i++)
+	for (i = 0; i < usable_segs_per_sec; i++)
 		mtime += get_seg_entry(sbi, start + i)->mtime;
 	vblocks = get_valid_blocks(sbi, segno, true);
 
-	mtime = div_u64(mtime, sbi->segs_per_sec);
-	vblocks = div_u64(vblocks, sbi->segs_per_sec);
+	mtime = div_u64(mtime, usable_segs_per_sec);
+	vblocks = div_u64(vblocks, usable_segs_per_sec);
 
 	u = (vblocks * 100) >> sbi->log_blocks_per_seg;
 
@@ -536,6 +537,7 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
 	int phase = 0;
 	bool fggc = (gc_type == FG_GC);
 	int submitted = 0;
+	unsigned int usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno);
 
 	start_addr = START_BLOCK(sbi, segno);
 
@@ -545,7 +547,7 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
 	if (fggc && phase == 2)
 		atomic_inc(&sbi->wb_sync_req[NODE]);
 
-	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
+	for (off = 0; off < usable_blks_in_seg; off++, entry++) {
 		nid_t nid = le32_to_cpu(entry->nid);
 		struct page *node_page;
 		struct node_info ni;
@@ -1033,13 +1035,14 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	int off;
 	int phase = 0;
 	int submitted = 0;
+	unsigned int usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno);
 
 	start_addr = START_BLOCK(sbi, segno);
 
 next_step:
 	entry = sum;
 
-	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
+	for (off = 0; off < usable_blks_in_seg; off++, entry++) {
 		struct page *data_page;
 		struct inode *inode;
 		struct node_info dni; /* dnode info for the data */
@@ -1204,6 +1207,15 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 	if (__is_large_section(sbi))
 		end_segno = rounddown(end_segno, sbi->segs_per_sec);
 
+	/*
+	 * zone-capacity can be less than zone-size in zoned devices,
+	 * resulting in less than expected usable segments in the zone,
+	 * calculate the end segno in the zone which can be garbage collected
+	 */
+	if (f2fs_sb_has_blkzoned(sbi))
+		end_segno -= sbi->segs_per_sec -
+					f2fs_usable_segs_in_sec(sbi, segno);
+
 	/* readahead multi ssa blocks those have contiguous address */
 	if (__is_large_section(sbi))
 		f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
@@ -1356,7 +1368,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
 		goto stop;
 
 	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
-	if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
+	if (gc_type == FG_GC &&
+		seg_freed == f2fs_usable_segs_in_sec(sbi, segno))
 		sec_freed++;
 	total_freed += seg_freed;
 

fs/f2fs/gc.h

@@ -44,13 +44,49 @@ struct gc_inode_list {
 /*
  * inline functions
  */
+
+/*
+ * On a Zoned device zone-capacity can be less than zone-size and if
+ * zone-capacity is not aligned to f2fs segment size(2MB), then the segment
+ * starting just before zone-capacity has some blocks spanning across the
+ * zone-capacity, these blocks are not usable.
+ * Such spanning segments can be in free list so calculate the sum of usable
+ * blocks in currently free segments including normal and spanning segments.
+ */
+static inline block_t free_segs_blk_count_zoned(struct f2fs_sb_info *sbi)
+{
+	block_t free_seg_blks = 0;
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	int j;
+
+	spin_lock(&free_i->segmap_lock);
+	for (j = 0; j < MAIN_SEGS(sbi); j++)
+		if (!test_bit(j, free_i->free_segmap))
+			free_seg_blks += f2fs_usable_blks_in_seg(sbi, j);
+	spin_unlock(&free_i->segmap_lock);
+
+	return free_seg_blks;
+}
+
+static inline block_t free_segs_blk_count(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return free_segs_blk_count_zoned(sbi);
+
+	return free_segments(sbi) << sbi->log_blocks_per_seg;
+}
+
 static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
 {
-	if (free_segments(sbi) < overprovision_segments(sbi))
+	block_t free_blks, ovp_blks;
+
+	free_blks = free_segs_blk_count(sbi);
+	ovp_blks = overprovision_segments(sbi) << sbi->log_blocks_per_seg;
+
+	if (free_blks < ovp_blks)
 		return 0;
-	else
-		return (free_segments(sbi) - overprovision_segments(sbi))
-			<< sbi->log_blocks_per_seg;
+
+	return free_blks - ovp_blks;
 }
 
 static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi)