From 0b4d29fa98ca1a49c4498353253f857573871ba0 Mon Sep 17 00:00:00 2001 From: Mark Harmstone Date: Wed, 7 Jan 2026 14:09:02 +0000 Subject: [PATCH] btrfs: add METADATA_REMAP chunk type Add a new METADATA_REMAP chunk type, which is a metadata chunk that holds the remap tree. This is needed for bootstrapping purposes: the remap tree can't itself be remapped, and must be relocated the existing way, by COWing every leaf. The remap tree can't go in the SYSTEM chunk as space there is limited, because a copy of the chunk item gets placed in the superblock. The changes in fs/btrfs/volumes.h are because we're adding a new block group type bit after the profile bits, and so can no longer rely on the const_ilog2 trick. The sizing to 32MB per chunk, matching the SYSTEM chunk, is an estimate here, we can adjust it later if it proves to be too big or too small. This works out to be ~500,000 remap items, which for a 4KB block size covers ~2GB of remapped data in the worst case and ~500TB in the best case. Reviewed-by: Boris Burkov Signed-off-by: Mark Harmstone Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-rsv.c | 8 ++++++++ fs/btrfs/block-rsv.h | 1 + fs/btrfs/disk-io.c | 1 + fs/btrfs/fs.h | 2 ++ fs/btrfs/space-info.c | 13 ++++++++++++- fs/btrfs/sysfs.c | 2 ++ fs/btrfs/tree-checker.c | 13 +++++++++++-- fs/btrfs/volumes.c | 3 +++ fs/btrfs/volumes.h | 10 +++++++++- include/uapi/linux/btrfs_tree.h | 4 +++- 10 files changed, 52 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 96cf7a1629870..e823230c09b7c 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -419,6 +419,9 @@ void btrfs_init_root_block_rsv(struct btrfs_root *root) case BTRFS_TREE_LOG_OBJECTID: root->block_rsv = &fs_info->treelog_rsv; break; + case BTRFS_REMAP_TREE_OBJECTID: + root->block_rsv = &fs_info->remap_block_rsv; + break; default: root->block_rsv = NULL; break; @@ -432,6 +435,9 @@ void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info) space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); fs_info->chunk_block_rsv.space_info = space_info; + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA_REMAP); + fs_info->remap_block_rsv.space_info = space_info; + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); fs_info->global_block_rsv.space_info = space_info; fs_info->trans_block_rsv.space_info = space_info; @@ -458,6 +464,8 @@ void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info) WARN_ON(fs_info->trans_block_rsv.reserved > 0); WARN_ON(fs_info->chunk_block_rsv.size > 0); WARN_ON(fs_info->chunk_block_rsv.reserved > 0); + WARN_ON(fs_info->remap_block_rsv.size > 0); + WARN_ON(fs_info->remap_block_rsv.reserved > 0); WARN_ON(fs_info->delayed_block_rsv.size > 0); WARN_ON(fs_info->delayed_block_rsv.reserved > 0); WARN_ON(fs_info->delayed_refs_rsv.reserved > 0); diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index 79ae9d05cd914..8359fb96bc3c7 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -22,6 +22,7 @@ enum btrfs_rsv_type { BTRFS_BLOCK_RSV_DELALLOC, BTRFS_BLOCK_RSV_TRANS, BTRFS_BLOCK_RSV_CHUNK, + BTRFS_BLOCK_RSV_REMAP, BTRFS_BLOCK_RSV_DELOPS, BTRFS_BLOCK_RSV_DELREFS, BTRFS_BLOCK_RSV_TREELOG, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index faa1c2c20ecd3..922e69038d810 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2751,6 +2751,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) BTRFS_BLOCK_RSV_GLOBAL); btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK); + btrfs_init_block_rsv(&fs_info->remap_block_rsv, BTRFS_BLOCK_RSV_REMAP); btrfs_init_block_rsv(&fs_info->treelog_rsv, BTRFS_BLOCK_RSV_TREELOG); btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY); btrfs_init_block_rsv(&fs_info->delayed_block_rsv, diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index e3e5e52e97a2a..195428ecfd75d 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -509,6 +509,8 @@ struct btrfs_fs_info { struct btrfs_block_rsv trans_block_rsv; /* Block reservation for chunk tree */ struct btrfs_block_rsv chunk_block_rsv; + /* Block reservation for remap tree. */ + struct btrfs_block_rsv remap_block_rsv; /* Block reservation for delayed operations */ struct btrfs_block_rsv delayed_block_rsv; /* Block reservation for delayed refs */ diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 1d76242f5e0df..2c9cf1ab232bf 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -215,7 +215,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags) if (flags & BTRFS_BLOCK_GROUP_DATA) return BTRFS_MAX_DATA_CHUNK_SIZE; - else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) + else if (flags & (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA_REMAP)) return SZ_32M; /* Handle BTRFS_BLOCK_GROUP_METADATA */ @@ -348,6 +348,8 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) if (mixed) { flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA; ret = create_space_info(fs_info, flags); + if (ret) + goto out; } else { flags = BTRFS_BLOCK_GROUP_METADATA; ret = create_space_info(fs_info, flags); @@ -356,7 +358,15 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) flags = BTRFS_BLOCK_GROUP_DATA; ret = create_space_info(fs_info, flags); + if (ret) + goto out; + } + + if (features & BTRFS_FEATURE_INCOMPAT_REMAP_TREE) { + flags = BTRFS_BLOCK_GROUP_METADATA_REMAP; + ret = create_space_info(fs_info, flags); } + out: return ret; } @@ -611,6 +621,7 @@ static void dump_global_block_rsv(struct btrfs_fs_info *fs_info) DUMP_BLOCK_RSV(fs_info, global_block_rsv); DUMP_BLOCK_RSV(fs_info, trans_block_rsv); DUMP_BLOCK_RSV(fs_info, chunk_block_rsv); + DUMP_BLOCK_RSV(fs_info, remap_block_rsv); DUMP_BLOCK_RSV(fs_info, delayed_block_rsv); DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv); } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 8834a1dd499c9..27bfb7b55ec41 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1929,6 +1929,8 @@ static const char *alloc_name(struct btrfs_space_info *space_info) case BTRFS_BLOCK_GROUP_SYSTEM: ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_PRIMARY); return "system"; + case BTRFS_BLOCK_GROUP_METADATA_REMAP: + return "metadata-remap"; default: WARN_ON(1); return "invalid-combination"; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index aedc208a95b83..a6c158cd8fcd2 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -748,17 +748,26 @@ static int check_block_group_item(struct extent_buffer *leaf, return -EUCLEAN; } + if (unlikely(flags & BTRFS_BLOCK_GROUP_METADATA_REMAP && + !btrfs_fs_incompat(fs_info, REMAP_TREE))) { + block_group_err(leaf, slot, +"invalid flags, have 0x%llx (METADATA_REMAP flag set) but no remap-tree incompat flag", + flags); + return -EUCLEAN; + } + type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; if (unlikely(type != BTRFS_BLOCK_GROUP_DATA && type != BTRFS_BLOCK_GROUP_METADATA && type != BTRFS_BLOCK_GROUP_SYSTEM && + type != BTRFS_BLOCK_GROUP_METADATA_REMAP && type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { block_group_err(leaf, slot, -"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", +"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, - BTRFS_BLOCK_GROUP_SYSTEM, + BTRFS_BLOCK_GROUP_SYSTEM, BTRFS_BLOCK_GROUP_METADATA_REMAP, BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA); return -EUCLEAN; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d2b7352eb7cbe..eda6505f3ee59 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -231,6 +231,9 @@ void btrfs_describe_block_groups(u64 bg_flags, char *buf, u32 size_buf) DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_DATA, "data"); DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_SYSTEM, "system"); DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_METADATA, "metadata"); + /* Block groups containing the remap tree. */ + DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_METADATA_REMAP, "metadata-remap"); + /* Block group that has been remapped. */ DESCRIBE_FLAG(BTRFS_BLOCK_GROUP_REMAPPED, "remapped"); DESCRIBE_FLAG(BTRFS_AVAIL_ALLOC_BIT_SINGLE, "single"); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 59347a4bb1852..e4b3cb50f94a7 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -58,7 +58,6 @@ static_assert(ilog2(BTRFS_STRIPE_LEN) == BTRFS_STRIPE_LEN_SHIFT); */ static_assert(const_ffs(BTRFS_BLOCK_GROUP_RAID0) < const_ffs(BTRFS_BLOCK_GROUP_PROFILE_MASK & ~BTRFS_BLOCK_GROUP_RAID0)); -static_assert(ilog2(BTRFS_BLOCK_GROUP_RAID0) > ilog2(BTRFS_BLOCK_GROUP_TYPE_MASK)); /* ilog2() can handle both constants and variables */ #define BTRFS_BG_FLAG_TO_INDEX(profile) \ @@ -80,6 +79,15 @@ enum btrfs_raid_types { BTRFS_NR_RAID_TYPES }; +static_assert(BTRFS_RAID_RAID0 == 1); +static_assert(BTRFS_RAID_RAID1 == 2); +static_assert(BTRFS_RAID_DUP == 3); +static_assert(BTRFS_RAID_RAID10 == 4); +static_assert(BTRFS_RAID_RAID5 == 5); +static_assert(BTRFS_RAID_RAID6 == 6); +static_assert(BTRFS_RAID_RAID1C3 == 7); +static_assert(BTRFS_RAID_RAID1C4 == 8); + /* * Use sequence counter to get consistent device stat data on * 32-bit processors. diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index f011d34cb699b..76578426671c7 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1169,12 +1169,14 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RAID1C3 (1ULL << 9) #define BTRFS_BLOCK_GROUP_RAID1C4 (1ULL << 10) #define BTRFS_BLOCK_GROUP_REMAPPED (1ULL << 11) +#define BTRFS_BLOCK_GROUP_METADATA_REMAP (1ULL << 12) #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) #define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ BTRFS_BLOCK_GROUP_SYSTEM | \ - BTRFS_BLOCK_GROUP_METADATA) + BTRFS_BLOCK_GROUP_METADATA | \ + BTRFS_BLOCK_GROUP_METADATA_REMAP) #define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ BTRFS_BLOCK_GROUP_RAID1 | \ -- 2.47.3