diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 1302bf8d0be1d692c77f5fbf88a78e64006c1277..46fdef7bbe20c65be3f1e24815ad9ecef383bf9f 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -903,6 +903,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
spin_unlock(&cluster->refill_lock);
btrfs_clear_treelog_bg(block_group);
+ btrfs_clear_data_reloc_bg(block_group);
path = btrfs_alloc_path();
if (!path) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f6e624098d531dc14d6779427ec22734e11d13b2..41f1718a83df922d4e7241276ca0af5888de3d7d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1018,6 +1018,13 @@ struct btrfs_fs_info {
spinlock_t treelog_bg_lock;
u64 treelog_bg;
+ /*
+ * Start of the dedicated data relocation block group, protected by
+ * relocation_bg_lock.
+ */
+ spinlock_t relocation_bg_lock;
+ u64 data_reloc_bg;
+
spinlock_t zone_active_bgs_lock;
struct list_head zone_active_bgs;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d63c5e776a964dfd4d514e63784d36b6086c9975..be382276d24f321cfb9aeb7684f9f3abfc72b272 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2885,6 +2885,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
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);
+ spin_lock_init(&fs_info->relocation_bg_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
mutex_init(&fs_info->reclaim_bgs_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 74ac37c5f21810187c6e3a46058f847753fa47bf..9b7cbb669a589c649e006e2955b6966f2240914c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3497,6 +3497,9 @@ struct find_free_extent_ctl {
/* Allocation is called for tree-log */
bool for_treelog;
+ /* Allocation is called for data relocation */
+ bool for_data_reloc;
+
/* RAID index, converted from flags */
int index;
@@ -3758,6 +3761,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
u64 avail;
u64 bytenr = block_group->start;
u64 log_bytenr;
+ u64 data_reloc_bytenr;
int ret = 0;
bool skip;
@@ -3775,6 +3779,19 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
if (skip)
return 1;
+ /*
+ * Do not allow non-relocation blocks in the dedicated relocation block
+ * group, and vice versa.
+ */
+ spin_lock(&fs_info->relocation_bg_lock);
+ data_reloc_bytenr = fs_info->data_reloc_bg;
+ if (data_reloc_bytenr &&
+ ((ffe_ctl->for_data_reloc && bytenr != data_reloc_bytenr) ||
+ (!ffe_ctl->for_data_reloc && bytenr == data_reloc_bytenr)))
+ skip = true;
+ spin_unlock(&fs_info->relocation_bg_lock);
+ if (skip)
+ return 1;
/* Check RO and no space case before trying to activate it */
spin_lock(&block_group->lock);
if (block_group->ro ||
@@ -3790,10 +3807,14 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
spin_lock(&fs_info->treelog_bg_lock);
+ spin_lock(&fs_info->relocation_bg_lock);
ASSERT(!ffe_ctl->for_treelog ||
block_group->start == fs_info->treelog_bg ||
fs_info->treelog_bg == 0);
+ ASSERT(!ffe_ctl->for_data_reloc ||
+ block_group->start == fs_info->data_reloc_bg ||
+ fs_info->data_reloc_bg == 0);
if (block_group->ro) {
ret = 1;
@@ -3810,6 +3831,16 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
goto out;
}
+ /*
+ * Do not allow currently used block group to be the data relocation
+ * dedicated block group.
+ */
+ if (ffe_ctl->for_data_reloc && !fs_info->data_reloc_bg &&
+ (block_group->used || block_group->reserved)) {
+ ret = 1;
+ goto out;
+ }
+
WARN_ON_ONCE(block_group->alloc_offset > block_group->zone_capacity);
avail = block_group->zone_capacity - block_group->alloc_offset;
if (avail < num_bytes) {
@@ -3828,6 +3859,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
if (ffe_ctl->for_treelog && !fs_info->treelog_bg)
fs_info->treelog_bg = block_group->start;
+ if (ffe_ctl->for_data_reloc && !fs_info->data_reloc_bg)
+ fs_info->data_reloc_bg = block_group->start;
+
ffe_ctl->found_offset = start + block_group->alloc_offset;
block_group->alloc_offset += num_bytes;
spin_lock(&ctl->tree_lock);
@@ -3844,6 +3878,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
out:
if (ret && ffe_ctl->for_treelog)
fs_info->treelog_bg = 0;
+ if (ret && ffe_ctl->for_data_reloc)
+ fs_info->data_reloc_bg = 0;
+ spin_unlock(&fs_info->relocation_bg_lock);
spin_unlock(&fs_info->treelog_bg_lock);
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
@@ -4112,6 +4149,12 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
ffe_ctl->hint_byte = fs_info->treelog_bg;
spin_unlock(&fs_info->treelog_bg_lock);
}
+ if (ffe_ctl->for_data_reloc) {
+ spin_lock(&fs_info->relocation_bg_lock);
+ if (fs_info->data_reloc_bg)
+ ffe_ctl->hint_byte = fs_info->data_reloc_bg;
+ spin_unlock(&fs_info->relocation_bg_lock);
+ }
return 0;
default:
BUG();
@@ -4245,6 +4288,8 @@ static noinline int find_free_extent(struct btrfs_root *root,
if (unlikely(block_group->ro)) {
if (ffe_ctl->for_treelog)
btrfs_clear_treelog_bg(block_group);
+ if (ffe_ctl->for_data_reloc)
+ btrfs_clear_data_reloc_bg(block_group);
continue;
}
@@ -4438,6 +4483,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
u64 flags;
int ret;
bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
+ bool for_data_reloc = (btrfs_is_data_reloc_root(root) && is_data);
flags = get_alloc_profile_by_root(root, is_data);
again:
@@ -4451,6 +4497,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
ffe_ctl.delalloc = delalloc;
ffe_ctl.hint_byte = hint_byte;
ffe_ctl.for_treelog = for_treelog;
+ ffe_ctl.for_data_reloc = for_data_reloc;
ret = find_free_extent(root, ins, &ffe_ctl);
if (!ret && !is_data) {
@@ -4470,8 +4517,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
sinfo = btrfs_find_space_info(fs_info, flags);
btrfs_err(fs_info,
- "allocation failed flags %llu, wanted %llu tree-log %d",
- flags, num_bytes, for_treelog);
+ "allocation failed flags %llu, wanted %llu tree-log %d, relocation: %d",
+ flags, num_bytes, for_treelog, for_data_reloc);
if (sinfo)
btrfs_dump_space_info(fs_info, sinfo,
num_bytes, 1);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 28a06c2d80adb8b9bb8fd7003e5cf46d10f4a9ec..c7fe3e11e6853b9870b55a5e0674f9182aa42202 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1954,3 +1954,13 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len
out:
btrfs_put_block_group(block_group);
}
+
+void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = bg->fs_info;
+
+ spin_lock(&fs_info->relocation_bg_lock);
+ if (fs_info->data_reloc_bg == bg->start)
+ fs_info->data_reloc_bg = 0;
+ spin_unlock(&fs_info->relocation_bg_lock);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 9c512402d7f42a8b7bde9c0c0665a89496d578aa..e53ab7b96437e79264d50372876bfc8f674bbf5a 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -75,6 +75,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices,
int raid_index);
void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,
u64 length);
+void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg);
#else /* CONFIG_BLK_DEV_ZONED */
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
struct blk_zone *zone)
@@ -229,6 +230,8 @@ static inline bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices,
static inline void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info,
u64 logical, u64 length) { }
+static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { }
+
#endif
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)