[PATCH v2 00/17] ZNS Support for Btrfs

@@ -202,6 +202,7 @@ struct btrfs_block_group {
 	 */
 	u64 alloc_offset;
 	u64 zone_unusable;
+	u64 zone_capacity;
 	u64 meta_write_pointer;
 };
 

@@ -1039,6 +1039,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	int i;
 	unsigned int nofs_flag;
 	u64 *alloc_offsets = NULL;
+	u64 *caps = NULL;
 	u64 last_alloc = 0;
 	u32 num_sequential = 0, num_conventional = 0;
 

@@ -1069,6 +1070,12 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		return -ENOMEM;
 	}
 
+	caps = kcalloc(map->num_stripes, sizeof(*caps), GFP_NOFS);
+	if (!caps) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < map->num_stripes; i++) {
 		bool is_sequential;
 		struct blk_zone zone;

@@ -1131,6 +1138,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			goto out;
 		}
 
+		caps[i] = zone.capacity << SECTOR_SHIFT;
+
 		switch (zone.cond) {
 		case BLK_ZONE_COND_OFFLINE:
 		case BLK_ZONE_COND_READONLY:

@@ -1144,7 +1153,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			alloc_offsets[i] = 0;
 			break;
 		case BLK_ZONE_COND_FULL:
-			alloc_offsets[i] = fs_info->zone_size;
+			alloc_offsets[i] = caps[i];
 			break;
 		default:
 			/* Partially used zone */

@@ -1169,6 +1178,9 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		 * calculate_alloc_pointer() which takes extent buffer
 		 * locks to avoid deadlock.
 		 */
+
+		/* Zone capacity is always zone size in emulation */
+		cache->zone_capacity = cache->length;
 		if (new) {
 			cache->alloc_offset = 0;
 			goto out;

@@ -1195,6 +1207,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			goto out;
 		}
 		cache->alloc_offset = alloc_offsets[0];
+		cache->zone_capacity = caps[0];
 		break;
 	case BTRFS_BLOCK_GROUP_DUP:
 	case BTRFS_BLOCK_GROUP_RAID1:

@@ -1218,6 +1231,14 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		ret = -EIO;
 	}
 
+	if (cache->alloc_offset > cache->zone_capacity) {
+		btrfs_err(fs_info,
+"zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
+			  cache->alloc_offset, cache->zone_capacity,
+			  cache->start);
+		ret = -EIO;
+	}
+
 	/* An extent is allocated after the write pointer */
 	if (!ret && num_conventional && last_alloc > cache->alloc_offset) {
 		btrfs_err(fs_info,

@@ -1229,6 +1250,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	if (!ret)
 		cache->meta_write_pointer = cache->alloc_offset + cache->start;
 
+	kfree(caps);
 	kfree(alloc_offsets);
 	free_extent_map(em);
 

@@ -2037,6 +2037,11 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	 */
 	if (btrfs_is_zoned(info)) {
 		btrfs_calc_zone_unusable(cache);
+		/*
+		 * Should not have any excluded extents. Just in case,
+		 * though
+		 */
+		btrfs_free_excluded_extents(cache);
 	} else if (cache->length == cache->used) {
 		cache->last_byte_to_unpin = (u64)-1;
 		cache->cached = BTRFS_CACHE_FINISHED;

@@ -1273,9 +1273,6 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
 	cache->cached = BTRFS_CACHE_FINISHED;
 	cache->free_space_ctl->free_space = free;
 	cache->zone_unusable = unusable;
-
-	/* Should not have any excluded extents. Just in case, though */
-	btrfs_free_excluded_extents(cache);
 }
 
 void btrfs_redirty_list_add(struct btrfs_transaction *trans,

@@ -2486,7 +2486,8 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 	 */
 	trace_btrfs_add_block_group(fs_info, cache, 1);
 	btrfs_update_space_info(fs_info, cache->flags, size, bytes_used,
-				cache->bytes_super, 0, &cache->space_info);
+				cache->bytes_super, cache->zone_unusable,
+				&cache->space_info);
 	btrfs_update_global_block_rsv(fs_info);
 
 	link_block_group(cache);

@@ -2601,7 +2602,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
 	if (!--cache->ro) {
 		if (btrfs_is_zoned(cache->fs_info)) {
 			/* Migrate zone_unusable bytes back */
-			cache->zone_unusable = cache->alloc_offset - cache->used;
+			cache->zone_unusable = (cache->alloc_offset - cache->used) +
+				(cache->length - cache->zone_capacity);
 			sinfo->bytes_zone_unusable += cache->zone_unusable;
 			sinfo->bytes_readonly -= cache->zone_unusable;
 		}

@@ -3796,7 +3796,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 		goto out;
 	}
 
-	avail = block_group->length - block_group->alloc_offset;
+	WARN_ON_ONCE(block_group->alloc_offset > block_group->zone_capacity);
+	avail = block_group->zone_capacity - block_group->alloc_offset;
 	if (avail < num_bytes) {
 		if (ffe_ctl->max_extent_size < avail) {
 			/*

@@ -2539,10 +2539,15 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 	u64 offset = bytenr - block_group->start;
 	u64 to_free, to_unusable;
 	const int bg_reclaim_threshold = READ_ONCE(fs_info->bg_reclaim_threshold);
+	bool initial = (size == block_group->length);
+
+	WARN_ON(!initial && offset + size > block_group->zone_capacity);
 
 	spin_lock(&ctl->tree_lock);
 	if (!used)
 		to_free = size;
+	else if (initial)
+		to_free = block_group->zone_capacity;
 	else if (offset >= block_group->alloc_offset)
 		to_free = size;
 	else if (offset + size <= block_group->alloc_offset)

@@ -2755,7 +2760,8 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 	 */
 	if (btrfs_is_zoned(fs_info)) {
 		btrfs_info(fs_info, "free space %llu",
-			   block_group->length - block_group->alloc_offset);
+			   block_group->zone_capacity -
+			   block_group->alloc_offset);
 		return;
 	}
 

@@ -1265,8 +1265,9 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
 		return;
 
 	WARN_ON(cache->bytes_super != 0);
-	unusable = cache->alloc_offset - cache->used;
-	free = cache->length - cache->alloc_offset;
+	unusable = (cache->alloc_offset - cache->used) +
+		(cache->length - cache->zone_capacity);
+	free = cache->zone_capacity - cache->alloc_offset;
 
 	/* We only need ->free_space in ALLOC_SEQ block groups */
 	cache->last_byte_to_unpin = (u64)-1;

@@ -2540,6 +2540,7 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 	u64 to_free, to_unusable;
 	const int bg_reclaim_threshold = READ_ONCE(fs_info->bg_reclaim_threshold);
 	bool initial = (size == block_group->length);
+	u64 reclaimable_unusable;
 
 	WARN_ON(!initial && offset + size > block_group->zone_capacity);
 

@@ -2570,12 +2571,15 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
 		spin_unlock(&block_group->lock);
 	}
 
+	reclaimable_unusable = block_group->zone_unusable -
+		(block_group->length - block_group->zone_capacity);
 	/* All the region is now unusable. Mark it as unused and reclaim */
 	if (block_group->zone_unusable == block_group->length) {
 		btrfs_mark_bg_unused(block_group);
 	} else if (bg_reclaim_threshold &&
-		   block_group->zone_unusable >=
-		   div_factor_fine(block_group->length, bg_reclaim_threshold)) {
+		   reclaimable_unusable >=
+		   div_factor_fine(block_group->zone_capacity,
+				   bg_reclaim_threshold)) {
 		btrfs_mark_bg_to_reclaim(block_group);
 	}
 

@@ -45,6 +45,14 @@
  */
 #define BTRFS_MAX_ZONE_SIZE		SZ_8G
 
+#define SUPER_INFO_SECTORS	((u64)BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT)
+
+static inline bool sb_zone_is_full(struct blk_zone *zone)
+{
+	return (zone->cond == BLK_ZONE_COND_FULL) ||
+		(zone->wp + SUPER_INFO_SECTORS > zone->start + zone->capacity);
+}
+
 static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
 {
 	struct blk_zone *zones = data;

@@ -60,14 +68,13 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 	bool empty[BTRFS_NR_SB_LOG_ZONES];
 	bool full[BTRFS_NR_SB_LOG_ZONES];
 	sector_t sector;
+	int i;
 
-	ASSERT(zones[0].type != BLK_ZONE_TYPE_CONVENTIONAL &&
-	       zones[1].type != BLK_ZONE_TYPE_CONVENTIONAL);
-
-	empty[0] = (zones[0].cond == BLK_ZONE_COND_EMPTY);
-	empty[1] = (zones[1].cond == BLK_ZONE_COND_EMPTY);
-	full[0] = (zones[0].cond == BLK_ZONE_COND_FULL);
-	full[1] = (zones[1].cond == BLK_ZONE_COND_FULL);
+	for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
+		ASSERT(zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL);
+		empty[i] = (zones[i].cond == BLK_ZONE_COND_EMPTY);
+		full[i] = sb_zone_is_full(&zones[i]);
+	}
 
 	/*
 	 * Possible states of log buffer zones

@@ -664,7 +671,7 @@ static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
 			reset = &zones[1];
 
 		if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
-			ASSERT(reset->cond == BLK_ZONE_COND_FULL);
+			ASSERT(sb_zone_is_full(reset));
 
 			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
 					       reset->start, reset->len,

@@ -683,9 +683,20 @@ static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
 			reset->wp = reset->start;
 		}
 	} else if (ret != -ENOENT) {
-		/* For READ, we want the precious one */
+		/*
+		 * For READ, we want the previous one. Move write pointer
+		 * to the end of a zone, if it is at the head of a zone.
+		 */
+		u64 zone_end = 0;
+
 		if (wp == zones[0].start << SECTOR_SHIFT)
-			wp = (zones[1].start + zones[1].len) << SECTOR_SHIFT;
+			zone_end = zones[1].start + zones[1].capacity;
+		else if (wp == zones[1].start << SECTOR_SHIFT)
+			zone_end = zones[0].start + zones[0].capacity;
+		if (zone_end)
+			wp = ALIGN_DOWN(zone_end << SECTOR_SHIFT,
+					BTRFS_SUPER_INFO_SIZE);
+
 		wp -= BTRFS_SUPER_INFO_SIZE;
 	}
 

@@ -3881,7 +3881,9 @@ static int write_dev_supers(struct btrfs_device *device,
 			bio->bi_opf |= REQ_FUA;
 
 		btrfsic_submit_bio(bio);
-		btrfs_advance_sb_log(device, i);
+
+		if (btrfs_advance_sb_log(device, i))
+			errors++;
 	}
 	return errors < i ? 0 : -1;
 }

@@ -789,36 +789,57 @@ static inline bool is_sb_log_zone(struct btrfs_zoned_device_info *zinfo,
 	return true;
 }
 
-void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
+int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 {
 	struct btrfs_zoned_device_info *zinfo = device->zone_info;
 	struct blk_zone *zone;
+	int i;
 
 	if (!is_sb_log_zone(zinfo, mirror))
-		return;
+		return 0;
 
 	zone = &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror];
-	if (zone->cond != BLK_ZONE_COND_FULL) {
+	for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
+		/* Advance the next zone */
+		if (zone->cond == BLK_ZONE_COND_FULL) {
+			zone++;
+			continue;
+		}
+
 		if (zone->cond == BLK_ZONE_COND_EMPTY)
 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
-		zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
+		zone->wp += SUPER_INFO_SECTORS;
+
+		if (sb_zone_is_full(zone)) {
+			/*
+			 * No room left to write new superblock. Since
+			 * superblock is written with REQ_SYNC, it is safe
+			 * to finish the zone now.
+			 *
+			 * If the write pointer is exactly at the capacity,
+			 * explicit ZONE_FINISH is not necessary.
+			 */
+			if (zone->wp != zone->start + zone->capacity) {
+				int ret;
+
+				ret = blkdev_zone_mgmt(device->bdev,
+						       REQ_OP_ZONE_FINISH,
+						       zone->start, zone->len,
+						       GFP_NOFS);
+				if (ret)
+					return ret;
+			}
 
-		if (zone->wp == zone->start + zone->len)
+			zone->wp = zone->start + zone->len;
 			zone->cond = BLK_ZONE_COND_FULL;
-
-		return;
+		}
+		return 0;
 	}
 
-	zone++;
-	ASSERT(zone->cond != BLK_ZONE_COND_FULL);
-	if (zone->cond == BLK_ZONE_COND_EMPTY)
-		zone->cond = BLK_ZONE_COND_IMP_OPEN;
-
-	zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
-
-	if (zone->wp == zone->start + zone->len)
-		zone->cond = BLK_ZONE_COND_FULL;
+	/* All the zones are FULL. Should not reach here. */
+	ASSERT(0);
+	return -EIO;
 }
 
 int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)

@@ -40,7 +40,7 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
 			       u64 *bytenr_ret);
 int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
 			  u64 *bytenr_ret);
-void btrfs_advance_sb_log(struct btrfs_device *device, int mirror);
+int btrfs_advance_sb_log(struct btrfs_device *device, int mirror);
 int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror);
 u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
 				 u64 hole_end, u64 num_bytes);

@@ -113,8 +113,10 @@ static inline int btrfs_sb_log_location(struct btrfs_device *device, int mirror,
 	return 0;
 }
 
-static inline void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
-{ }
+static inline int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
+{
+	return 0;
+}
 
 static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 {

@@ -4,6 +4,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/sched/mm.h>
+#include <linux/atomic.h>
 #include "ctree.h"
 #include "volumes.h"
 #include "zoned.h"

@@ -38,6 +39,15 @@
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/* Number of minimal activate zones we want.
+ *
+ * - BTRFS_SUPER_MIRROR_MAX zones for superblock mirrors
+ * - 3 zones to ensure at least one zone per SYSTEM, META and DATA block group
+ * - 1 zone for tree-log dedicated block group
+ * - 1 zone for relocation
+ */
+#define BTRFS_MIN_ACTIVE_ZONES (BTRFS_SUPER_MIRROR_MAX + 5)
+
 /*
  * Maximum supported zone size. Currently, SMR disks have a zone size of
  * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not

@@ -303,6 +313,9 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_zoned_device_info *zone_info = NULL;
 	struct block_device *bdev = device->bdev;
+	struct request_queue *queue = bdev_get_queue(bdev);
+	unsigned int max_active_zones;
+	unsigned int nactive;
 	sector_t nr_sectors;
 	sector_t sector = 0;
 	struct blk_zone *zones = NULL;

@@ -358,6 +371,17 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
+	max_active_zones = queue_max_active_zones(queue);
+	if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) {
+		btrfs_err_in_rcu(fs_info,
+"zoned: %s: max active zones %u is too small. Need at least %u active zones",
+				 rcu_str_deref(device->name), max_active_zones,
+				 BTRFS_MIN_ACTIVE_ZONES);
+		ret = -EINVAL;
+		goto out;
+	}
+	zone_info->max_active_zones = max_active_zones;
+
 	zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
 	if (!zone_info->seq_zones) {
 		ret = -ENOMEM;

@@ -370,6 +394,12 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		goto out;
 	}
 
+	zone_info->active_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
+	if (!zone_info->active_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL);
 	if (!zones) {
 		ret = -ENOMEM;

@@ -377,6 +407,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 	}
 
 	/* Get zones type */
+	nactive = 0;
 	while (sector < nr_sectors) {
 		nr_zones = BTRFS_REPORT_NR_ZONES;
 		ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, zones,

@@ -387,8 +418,17 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		for (i = 0; i < nr_zones; i++) {
 			if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ)
 				__set_bit(nreported, zone_info->seq_zones);
-			if (zones[i].cond == BLK_ZONE_COND_EMPTY)
+			switch (zones[i].cond) {
+			case BLK_ZONE_COND_EMPTY:
 				__set_bit(nreported, zone_info->empty_zones);
+				break;
+			case BLK_ZONE_COND_IMP_OPEN:
+			case BLK_ZONE_COND_EXP_OPEN:
+			case BLK_ZONE_COND_CLOSED:
+				__set_bit(nreported, zone_info->active_zones);
+				nactive++;
+				break;
+			}
 			nreported++;
 		}
 		sector = zones[nr_zones - 1].start + zones[nr_zones - 1].len;

@@ -403,6 +443,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		goto out;
 	}
 
+	if (max_active_zones) {
+		if (nactive > max_active_zones) {
+			btrfs_err_in_rcu(device->fs_info,
+			"zoned: %d active zones on %s exceeds max_active_zones %d",
+					 nactive, rcu_str_deref(device->name),
+					 max_active_zones);
+			ret = -EIO;
+			goto out;
+		}
+		atomic_set(&zone_info->active_zones_left,
+			   max_active_zones - nactive);
+	}
+
 	/* Validate superblock log */
 	nr_zones = BTRFS_NR_SB_LOG_ZONES;
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {

@@ -485,6 +538,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 out:
 	kfree(zones);
 out_free_zone_info:
+	bitmap_free(zone_info->active_zones);
 	bitmap_free(zone_info->empty_zones);
 	bitmap_free(zone_info->seq_zones);
 	kfree(zone_info);

@@ -500,6 +554,7 @@ void btrfs_destroy_dev_zone_info(struct btrfs_device *device)
 	if (!zone_info)
 		return;
 
+	bitmap_free(zone_info->active_zones);
 	bitmap_free(zone_info->seq_zones);
 	bitmap_free(zone_info->empty_zones);
 	kfree(zone_info);

@@ -23,8 +23,11 @@ struct btrfs_zoned_device_info {
 	u64 zone_size;
 	u8  zone_size_shift;
 	u32 nr_zones;
+	unsigned int max_active_zones;
+	atomic_t active_zones_left;
 	unsigned long *seq_zones;
 	unsigned long *empty_zones;
+	unsigned long *active_zones;
 	struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX];
 };
 

@@ -144,6 +144,7 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
 		 */
 		WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root));
 		kfree(cache->free_space_ctl);
+		kfree(cache->physical_map);
 		kfree(cache);
 	}
 }

@@ -204,6 +204,7 @@ struct btrfs_block_group {
 	u64 zone_unusable;
 	u64 zone_capacity;
 	u64 meta_write_pointer;
+	struct map_lookup *physical_map;
 };
 
 static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)

@@ -1158,10 +1158,19 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 
 	map = em->map_lookup;
 
+	cache->physical_map = kmalloc(map_lookup_size(map->num_stripes),
+				      GFP_NOFS);
+	if (!cache->physical_map) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memcpy(cache->physical_map, map, map_lookup_size(map->num_stripes));
+
 	alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS);
 	if (!alloc_offsets) {
-		free_extent_map(em);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	caps = kcalloc(map->num_stripes, sizeof(*caps), GFP_NOFS);

@@ -1344,6 +1353,10 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	if (!ret)
 		cache->meta_write_pointer = cache->alloc_offset + cache->start;
 
+	if (ret) {
+		kfree(cache->physical_map);
+		cache->physical_map = NULL;
+	}
 	kfree(caps);
 	kfree(alloc_offsets);
 	free_extent_map(em);

@@ -1898,6 +1898,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 	INIT_LIST_HEAD(&cache->discard_list);
 	INIT_LIST_HEAD(&cache->dirty_list);
 	INIT_LIST_HEAD(&cache->io_list);
+	INIT_LIST_HEAD(&cache->active_bg_list);
 	btrfs_init_free_space_ctl(cache, cache->free_space_ctl);
 	atomic_set(&cache->frozen, 0);
 	mutex_init(&cache->free_space_lock);

@@ -3843,6 +3844,16 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	}
 	spin_unlock(&info->unused_bgs_lock);
 
+	spin_lock(&info->zone_active_bgs_lock);
+	while (!list_empty(&info->zone_active_bgs)) {
+		block_group = list_first_entry(&info->zone_active_bgs,
+					       struct btrfs_block_group,
+					       active_bg_list);
+		list_del_init(&block_group->active_bg_list);
+		btrfs_put_block_group(block_group);
+	}
+	spin_unlock(&info->zone_active_bgs_lock);
+
 	spin_lock(&info->block_group_cache_lock);
 	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
 		block_group = rb_entry(n, struct btrfs_block_group,

@@ -98,6 +98,7 @@ struct btrfs_block_group {
 	unsigned int to_copy:1;
 	unsigned int relocating_repair:1;
 	unsigned int chunk_item_inserted:1;
+	unsigned int zone_is_active:1;
 
 	int disk_cache_state;
 

@@ -205,6 +206,7 @@ struct btrfs_block_group {
 	u64 zone_capacity;
 	u64 meta_write_pointer;
 	struct map_lookup *physical_map;
+	struct list_head active_bg_list;
 };
 
 static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)

@@ -1017,6 +1017,9 @@ struct btrfs_fs_info {
 	spinlock_t treelog_bg_lock;
 	u64 treelog_bg;
 
+	spinlock_t zone_active_bgs_lock;
+	struct list_head zone_active_bgs;
+
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	spinlock_t ref_verify_lock;
 	struct rb_root block_tree;

@@ -2883,6 +2883,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
 	spin_lock_init(&fs_info->treelog_bg_lock);
+	spin_lock_init(&fs_info->zone_active_bgs_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->unused_bg_unpin_mutex);
 	mutex_init(&fs_info->reclaim_bgs_lock);

@@ -2896,6 +2897,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
 	INIT_LIST_HEAD(&fs_info->unused_bgs);
 	INIT_LIST_HEAD(&fs_info->reclaim_bgs);
+	INIT_LIST_HEAD(&fs_info->zone_active_bgs);
 #ifdef CONFIG_BTRFS_DEBUG
 	INIT_LIST_HEAD(&fs_info->allocated_roots);
 	INIT_LIST_HEAD(&fs_info->allocated_ebs);

@@ -2763,9 +2763,10 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 	 * out the free space after the allocation offset.
 	 */
 	if (btrfs_is_zoned(fs_info)) {
-		btrfs_info(fs_info, "free space %llu",
+		btrfs_info(fs_info, "free space %llu active %d",
 			   block_group->zone_capacity -
-			   block_group->alloc_offset);
+			   block_group->alloc_offset,
+			   block_group->zone_is_active);
 		return;
 	}
 

@@ -989,6 +989,41 @@ u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
 	return pos;
 }
 
+static bool btrfs_dev_set_active_zone(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+	unsigned int zno = pos >> zone_info->zone_size_shift;
+
+	/* We can use any number of zones */
+	if (!zone_info->max_active_zones)
+		return true;
+
+	if (!test_bit(zno, zone_info->active_zones)) {
+		/* Active zone left? */
+		if (atomic_dec_if_positive(&zone_info->active_zones_left) < 0)
+			return false;
+		if (test_and_set_bit(zno, zone_info->active_zones)) {
+			/* Someone already set the bit */
+			atomic_inc(&zone_info->active_zones_left);
+		}
+	}
+
+	return true;
+}
+
+static void btrfs_dev_clear_active_zone(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+	unsigned int zno = pos >> zone_info->zone_size_shift;
+
+	/* We can use any number of zones */
+	if (!zone_info->max_active_zones)
+		return;
+
+	if (test_and_clear_bit(zno, zone_info->active_zones))
+		atomic_inc(&zone_info->active_zones_left);
+}
+
 int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 			    u64 length, u64 *bytes)
 {

@@ -1004,6 +1039,7 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 	*bytes = length;
 	while (length) {
 		btrfs_dev_set_zone_empty(device, physical);
+		btrfs_dev_clear_active_zone(device, physical);
 		physical += device->zone_info->zone_size;
 		length -= device->zone_info->zone_size;
 	}

@@ -1657,3 +1693,163 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
 
 	return device;
 }
+
+/**
+ * btrfs_zone_activate - activate block group and underlying device zones
+ *
+ * @block_group: the block group to activate
+ *
+ * @return: true on success, false otherwise
+ */
+bool btrfs_zone_activate(struct btrfs_block_group *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	struct map_lookup *map;
+	struct btrfs_device *device;
+	u64 physical;
+	bool ret;
+
+	if (!btrfs_is_zoned(block_group->fs_info))
+		return true;
+
+	map = block_group->physical_map;
+	/* Currently support SINGLE profile only */
+	ASSERT(map->num_stripes == 1);
+	device = map->stripes[0].dev;
+	physical = map->stripes[0].physical;
+
+	if (!device->zone_info->max_active_zones)
+		return true;
+
+	spin_lock(&block_group->lock);
+
+	if (block_group->zone_is_active) {
+		ret = true;
+		goto out_unlock;
+	}
+
+	/* No space left */
+	if (block_group->alloc_offset == block_group->zone_capacity) {
+		ret = false;
+		goto out_unlock;
+	}
+
+	if (!btrfs_dev_set_active_zone(device, physical)) {
+		/* Cannot activate the zone */
+		ret = false;
+		goto out_unlock;
+	}
+
+	/* Successfully activated all the zones */
+	block_group->zone_is_active = 1;
+
+	spin_unlock(&block_group->lock);
+
+	/* for the active BG list */
+	btrfs_get_block_group(block_group);
+
+	spin_lock(&fs_info->zone_active_bgs_lock);
+	ASSERT(list_empty(&block_group->active_bg_list));
+	list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
+
+	return true;
+
+out_unlock:
+	spin_unlock(&block_group->lock);
+	return ret;
+}
+
+int btrfs_zone_finish(struct btrfs_block_group *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	struct map_lookup *map;
+	struct btrfs_device *device;
+	u64 physical;
+	int ret = 0;
+
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	map = block_group->physical_map;
+	/* Currently support SINGLE profile only */
+	ASSERT(map->num_stripes == 1);
+
+	device = map->stripes[0].dev;
+	physical = map->stripes[0].physical;
+
+	if (!device->zone_info->max_active_zones)
+		return 0;
+
+	spin_lock(&block_group->lock);
+	if (!block_group->zone_is_active) {
+		spin_unlock(&block_group->lock);
+		return 0;
+	}
+
+	/* Check if we have unwritten allocated space */
+	if ((block_group->flags &
+	     (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) &&
+	    block_group->alloc_offset > block_group->meta_write_pointer) {
+		spin_unlock(&block_group->lock);
+		return -EAGAIN;
+	}
+	spin_unlock(&block_group->lock);
+
+	ret = btrfs_inc_block_group_ro(block_group, false);
+	if (ret)
+		return ret;
+
+	/* Ensure all writes in this block group finish */
+	btrfs_wait_block_group_reservations(block_group);
+	/*
+	 * No need to wait nocow writers. Zoned btrfs does not allow
+	 * nocow anyway.
+	 */
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start,
+				 block_group->length);
+
+	spin_lock(&block_group->lock);
+
+	/*
+	 * Bail out if someone already deactivated the block group, or
+	 * allocated space is left in the block group.
+	 */
+	if (!block_group->zone_is_active) {
+		spin_unlock(&block_group->lock);
+		btrfs_dec_block_group_ro(block_group);
+		return 0;
+	}
+
+	if (block_group->reserved) {
+		spin_unlock(&block_group->lock);
+		btrfs_dec_block_group_ro(block_group);
+		return -EAGAIN;
+	}
+
+	block_group->zone_is_active = 0;
+	block_group->alloc_offset = block_group->zone_capacity;
+	block_group->free_space_ctl->free_space = 0;
+	btrfs_clear_treelog_bg(block_group);
+	spin_unlock(&block_group->lock);
+
+	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
+			       physical >> SECTOR_SHIFT,
+			       device->zone_info->zone_size >> SECTOR_SHIFT,
+			       GFP_NOFS);
+	btrfs_dec_block_group_ro(block_group);
+
+	if (!ret) {
+		btrfs_dev_clear_active_zone(device, physical);
+
+		spin_lock(&fs_info->zone_active_bgs_lock);
+		ASSERT(!list_empty(&block_group->active_bg_list));
+		list_del_init(&block_group->active_bg_list);
+		spin_unlock(&fs_info->zone_active_bgs_lock);
+
+		/* for active_bg_list */
+		btrfs_put_block_group(block_group);
+	}
+
+	return ret;
+}

@@ -69,6 +69,8 @@ int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 				  u64 physical_start, u64 physical_pos);
 struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
 					    u64 logical, u64 length);
+bool btrfs_zone_activate(struct btrfs_block_group *block_group);
+int btrfs_zone_finish(struct btrfs_block_group *block_group);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)

@@ -204,6 +206,16 @@ static inline struct btrfs_device *btrfs_zoned_get_device(
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline bool btrfs_zone_activate(struct btrfs_block_group *block_group)
+{
+	return true;
+}
+
+static inline int btrfs_zone_finish(struct btrfs_block_group *block_group)
+{
+	return 0;
+}
+
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)

@@ -3773,6 +3773,18 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
 	if (skip)
 		return 1;
 
+	/* Check RO and no space case before trying to activate it */
+	spin_lock(&block_group->lock);
+	if (block_group->ro ||
+	    block_group->alloc_offset == block_group->zone_capacity) {
+		spin_unlock(&block_group->lock);
+		return 1;
+	}
+	spin_unlock(&block_group->lock);
+
+	if (!btrfs_zone_activate(block_group))
+		return 1;
+
 	spin_lock(&space_info->lock);
 	spin_lock(&block_group->lock);
 	spin_lock(&fs_info->treelog_bg_lock);

@@ -1170,6 +1170,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	unsigned int nofs_flag;
 	u64 *alloc_offsets = NULL;
 	u64 *caps = NULL;
+	unsigned long *active = NULL;
 	u64 last_alloc = 0;
 	u32 num_sequential = 0, num_conventional = 0;
 

@@ -1215,6 +1216,12 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		goto out;
 	}
 
+	active = bitmap_zalloc(map->num_stripes, GFP_NOFS);
+	if (!active) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < map->num_stripes; i++) {
 		bool is_sequential;
 		struct blk_zone zone;

@@ -1298,8 +1305,16 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			/* Partially used zone */
 			alloc_offsets[i] =
 					((zone.wp - zone.start) << SECTOR_SHIFT);
+			__set_bit(i, active);
 			break;
 		}
+
+		/*
+		 * Consider a zone as active if we can allow any number of
+		 * active zones.
+		 */
+		if (!device->zone_info->max_active_zones)
+			__set_bit(i, active);
 	}
 
 	if (num_sequential > 0)