btrfs: zoned: add a dedicated data relocation block group

Relocation in a zoned filesystem can fail with a transaction abort with
error -22 (EINVAL). This happens because the relocation code assumes that
the extents we relocated the data to have the same size the source extents
had and ensures this by preallocating the extents.

But in a zoned filesystem we currently can't preallocate the extents as
this would break the sequential write required rule. Therefore it can
happen that the writeback process kicks in while we're still adding pages
to a delalloc range and starts writing out dirty pages.

This then creates destination extents that are smaller than the source
extents, triggering the following safety check in get_new_location():

 1034         if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) {
 1035                 ret = -EINVAL;
 1036                 goto out;
 1037         }

Temporarily create a dedicated block group for the relocation process, so
no non-relocation data writes can interfere with the relocation writes.

This is needed that we can switch the relocation process on a zoned
filesystem from the REQ_OP_ZONE_APPEND writing we use for data to a scheme
like in a non-zoned filesystem using REQ_OP_WRITE and preallocation.

Fixes: 32430c614844 ("btrfs: zoned: enable relocation on a zoned filesystem")
Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 49 insertions, 2 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 74ac37c5f218..9b7cbb669a58 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 @@ search:
 		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 @@ again:
 	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 @@ again:
 
 			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);