From: Linus Torvalds Date: Mon, 30 Oct 2023 20:42:06 +0000 (-1000) Subject: Merge tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=d5acbc60fafbe0fc94c552ce916dd592cd4c6371;p=linux.git Merge tag 'for-6.7-tag' of git://git./linux/kernel/git/kdave/linux Pull btrfs updates from David Sterba: "New features: - raid-stripe-tree New tree for logical file extent mapping where the physical mapping may not match on multiple devices. This is now used in zoned mode to implement RAID0/RAID1* profiles, but can be used in non-zoned mode as well. The support for RAID56 is in development and will eventually fix the problems with the current implementation. This is a backward incompatible feature and has to be enabled at mkfs time. - simple quota accounting (squota) A simplified mode of qgroup that accounts all space on the initial extent owners (a subvolume), the snapshots are then cheap to create and delete. The deletion of snapshots in fully accounting qgroups is a known CPU/IO performance bottleneck. The squota is not suitable for the general use case but works well for containers where the original subvolume exists for the whole time. This is a backward incompatible feature as it needs extending some structures, but can be enabled on an existing filesystem. - temporary filesystem fsid (temp_fsid) The fsid identifies a filesystem and is hard coded in the structures, which disallows mounting the same fsid found on different devices. For a single device filesystem this is not strictly necessary, a new temporary fsid can be generated on mount e.g. after a device is cloned. This will be used by Steam Deck for root partition A/B testing, or can be used for VM root images. Other user visible changes: - filesystems with partially finished metadata_uuid conversion cannot be mounted anymore and the uuid fixup has to be done by btrfs-progs (btrfstune). Performance improvements: - reduce reservations for checksum deletions (with enabled free space tree by factor of 4), on a sample workload on file with many extents the deletion time decreased by 12% - make extent state merges more efficient during insertions, reduce rb-tree iterations (run time of critical functions reduced by 5%) Core changes: - the integrity check functionality has been removed, this was a debugging feature and removal does not affect other integrity checks like checksums or tree-checker - space reservation changes: - more efficient delayed ref reservations, this avoids building up too much work or overusing or exhausting the global block reserve in some situations - move delayed refs reservation to the transaction start time, this prevents some ENOSPC corner cases related to exhaustion of global reserve - improvements in reducing excessive reservations for block group items - adjust overcommit logic in near full situations, account for one more chunk to eventually allocate metadata chunk, this is mostly relevant for small filesystems (<10GiB) - single device filesystems are scanned but not registered (except seed devices), this allows temp_fsid to work - qgroup iterations do not need GFP_ATOMIC allocations anymore - cleanups, refactoring, reduced data structure size, function parameter simplifications, error handling fixes" * tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (156 commits) btrfs: open code timespec64 in struct btrfs_inode btrfs: remove redundant log root tree index assignment during log sync btrfs: remove redundant initialization of variable dirty in btrfs_update_time() btrfs: sysfs: show temp_fsid feature btrfs: disable the device add feature for temp-fsid btrfs: disable the seed feature for temp-fsid btrfs: update comment for temp-fsid, fsid, and metadata_uuid btrfs: remove pointless empty log context list check when syncing log btrfs: update comment for struct btrfs_inode::lock btrfs: remove pointless barrier from btrfs_sync_file() btrfs: add and use helpers for reading and writing last_trans_committed btrfs: add and use helpers for reading and writing fs_info->generation btrfs: add and use helpers for reading and writing log_transid btrfs: add and use helpers for reading and writing last_log_commit btrfs: support cloned-device mount capability btrfs: add helper function find_fsid_by_disk btrfs: stop reserving excessive space for block group item insertions btrfs: stop reserving excessive space for block group item updates btrfs: reorder btrfs_inode to fill gaps btrfs: open code btrfs_ordered_inode_tree in btrfs_inode ... --- d5acbc60fafbe0fc94c552ce916dd592cd4c6371 diff --cc fs/btrfs/delayed-inode.c index c401908eb4683,c640f87038a68..7381241334e8d --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@@ -1834,24 -1833,22 +1833,22 @@@ static void fill_stack_inode_item(struc btrfs_set_stack_inode_block_group(inode_item, 0); btrfs_set_stack_timespec_sec(&inode_item->atime, - inode->i_atime.tv_sec); + inode_get_atime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->atime, - inode->i_atime.tv_nsec); + inode_get_atime_nsec(inode)); btrfs_set_stack_timespec_sec(&inode_item->mtime, - inode->i_mtime.tv_sec); + inode_get_mtime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->mtime, - inode->i_mtime.tv_nsec); + inode_get_mtime_nsec(inode)); btrfs_set_stack_timespec_sec(&inode_item->ctime, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->ctime, - inode_get_ctime(inode).tv_nsec); + inode_get_ctime_nsec(inode)); - btrfs_set_stack_timespec_sec(&inode_item->otime, - BTRFS_I(inode)->i_otime.tv_sec); - btrfs_set_stack_timespec_nsec(&inode_item->otime, - BTRFS_I(inode)->i_otime.tv_nsec); + btrfs_set_stack_timespec_sec(&inode_item->otime, BTRFS_I(inode)->i_otime_sec); + btrfs_set_stack_timespec_nsec(&inode_item->otime, BTRFS_I(inode)->i_otime_nsec); } int btrfs_fill_inode(struct inode *inode, u32 *rdev) diff --cc fs/btrfs/file.c index 278a4ea651e1f,92419cb8508ae..f47731c45bb50 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@@ -2474,10 -2476,9 +2477,10 @@@ int btrfs_replace_file_extents(struct b inode_inc_iversion(&inode->vfs_inode); if (!extent_info || extent_info->update_times) - inode->vfs_inode.i_mtime = inode_set_ctime_current(&inode->vfs_inode); + inode_set_mtime_to_ts(&inode->vfs_inode, + inode_set_ctime_current(&inode->vfs_inode)); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, inode); if (ret) break; @@@ -2716,8 -2717,8 +2719,8 @@@ static int btrfs_punch_hole(struct fil ASSERT(trans != NULL); inode_inc_iversion(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); + ret = btrfs_update_inode(trans, BTRFS_I(inode)); updated_inode = true; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); diff --cc fs/btrfs/inode.c index 6e3ce1aecb6e8,b388505c91cc1..5e3fccddde0c6 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@@ -3922,24 -3928,22 +3928,22 @@@ static void fill_inode_item(struct btrf btrfs_set_token_inode_nlink(&token, item, inode->i_nlink); btrfs_set_token_timespec_sec(&token, &item->atime, - inode->i_atime.tv_sec); + inode_get_atime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->atime, - inode->i_atime.tv_nsec); + inode_get_atime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->mtime, - inode->i_mtime.tv_sec); + inode_get_mtime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->mtime, - inode->i_mtime.tv_nsec); + inode_get_mtime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->ctime, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->ctime, - inode_get_ctime(inode).tv_nsec); + inode_get_ctime_nsec(inode)); - btrfs_set_token_timespec_sec(&token, &item->otime, - BTRFS_I(inode)->i_otime.tv_sec); - btrfs_set_token_timespec_nsec(&token, &item->otime, - BTRFS_I(inode)->i_otime.tv_nsec); + btrfs_set_token_timespec_sec(&token, &item->otime, BTRFS_I(inode)->i_otime_sec); + btrfs_set_token_timespec_nsec(&token, &item->otime, BTRFS_I(inode)->i_otime_nsec); btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode)); btrfs_set_token_inode_generation(&token, item, @@@ -4132,8 -4135,9 +4135,8 @@@ err btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2); inode_inc_iversion(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); - inode_set_ctime_current(&inode->vfs_inode); - dir->vfs_inode.i_mtime = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); - ret = btrfs_update_inode(trans, root, dir); + ret = btrfs_update_inode(trans, dir); out: return ret; } @@@ -4305,8 -4309,8 +4308,8 @@@ static int btrfs_unlink_subvol(struct b btrfs_i_size_write(dir, dir->vfs_inode.i_size - fname.disk_name.len * 2); inode_inc_iversion(&dir->vfs_inode); - dir->vfs_inode.i_mtime = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); - ret = btrfs_update_inode_fallback(trans, root, dir); + ret = btrfs_update_inode_fallback(trans, dir); if (ret) btrfs_abort_transaction(trans, ret); out: @@@ -5582,6 -5585,6 +5585,7 @@@ static struct inode *new_simple_dir(str struct btrfs_key *key, struct btrfs_root *root) { ++ struct timespec64 ts; struct inode *inode = new_inode(dir->i_sb); if (!inode) @@@ -5600,9 -5603,10 +5604,13 @@@ inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &simple_dir_operations; inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO; - inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - inode->i_mtime = inode_set_ctime_current(inode); - inode->i_atime = dir->i_atime; - BTRFS_I(inode)->i_otime_sec = inode->i_mtime.tv_sec; - BTRFS_I(inode)->i_otime_nsec = inode->i_mtime.tv_nsec; ++ ++ ts = inode_set_ctime_current(inode); ++ inode_set_mtime_to_ts(inode, ts); + inode_set_atime_to_ts(inode, inode_get_atime(dir)); - BTRFS_I(inode)->i_otime = inode_get_mtime(inode); ++ BTRFS_I(inode)->i_otime_sec = ts.tv_sec; ++ BTRFS_I(inode)->i_otime_nsec = ts.tv_nsec; ++ inode->i_uid = dir->i_uid; inode->i_gid = dir->i_gid; @@@ -6160,6 -6164,6 +6168,7 @@@ static void btrfs_inherit_iflags(struc int btrfs_create_new_inode(struct btrfs_trans_handle *trans, struct btrfs_new_inode_args *args) { ++ struct timespec64 ts; struct inode *dir = args->dir; struct inode *inode = args->inode; const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name; @@@ -6277,8 -6281,10 +6286,9 @@@ goto discard; } - simple_inode_init_ts(inode); - BTRFS_I(inode)->i_otime = inode_get_mtime(inode); - inode->i_mtime = inode_set_ctime_current(inode); - inode->i_atime = inode->i_mtime; - BTRFS_I(inode)->i_otime_sec = inode->i_mtime.tv_sec; - BTRFS_I(inode)->i_otime_nsec = inode->i_mtime.tv_nsec; ++ ts = simple_inode_init_ts(inode); ++ BTRFS_I(inode)->i_otime_sec = ts.tv_sec; ++ BTRFS_I(inode)->i_otime_nsec = ts.tv_nsec; /* * We're going to fill the inode item now, so at this point the inode @@@ -6443,10 -6449,10 +6453,10 @@@ int btrfs_add_link(struct btrfs_trans_h * values (the ones it had when the fsync was done). */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) - parent_inode->vfs_inode.i_mtime = - inode_set_ctime_current(&parent_inode->vfs_inode); + inode_set_mtime_to_ts(&parent_inode->vfs_inode, + inode_set_ctime_current(&parent_inode->vfs_inode)); - ret = btrfs_update_inode(trans, root, parent_inode); + ret = btrfs_update_inode(trans, parent_inode); if (ret) btrfs_abort_transaction(trans, ret); return ret; diff --cc fs/btrfs/transaction.c index 38a2775c5c7b5,9694a3ca17390..6e63816dddcbe --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@@ -1860,9 -1911,8 +1911,9 @@@ static noinline int create_pending_snap btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size + fname.disk_name.len * 2); - parent_inode->i_mtime = inode_set_ctime_current(parent_inode); + inode_set_mtime_to_ts(parent_inode, + inode_set_ctime_current(parent_inode)); - ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode)); + ret = btrfs_update_inode_fallback(trans, BTRFS_I(parent_inode)); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; diff --cc fs/btrfs/volumes.c index 1f38affa4d9cb,1fdfa9153e30c..c87e18827a0a6 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@@ -457,86 -455,32 +455,34 @@@ static noinline struct btrfs_fs_device return NULL; } - /* - * First check if the metadata_uuid is different from the fsid in the given - * fs_devices. Then check if the given fsid is the same as the metadata_uuid - * in the fs_devices. If it is, return true; otherwise, return false. - */ - static inline bool check_fsid_changed(const struct btrfs_fs_devices *fs_devices, - const u8 *fsid) - { - return memcmp(fs_devices->fsid, fs_devices->metadata_uuid, - BTRFS_FSID_SIZE) != 0 && - memcmp(fs_devices->metadata_uuid, fsid, BTRFS_FSID_SIZE) == 0; - } - - static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( - struct btrfs_super_block *disk_super) - { - - struct btrfs_fs_devices *fs_devices; - - /* - * Handle scanned device having completed its fsid change but - * belonging to a fs_devices that was created by first scanning - * a device which didn't have its fsid/metadata_uuid changed - * at all and the CHANGING_FSID_V2 flag set. - */ - list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (!fs_devices->fsid_change) - continue; - - if (match_fsid_fs_devices(fs_devices, disk_super->metadata_uuid, - fs_devices->fsid)) - return fs_devices; - } - - /* - * Handle scanned device having completed its fsid change but - * belonging to a fs_devices that was created by a device that - * has an outdated pair of fsid/metadata_uuid and - * CHANGING_FSID_V2 flag set. - */ - list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (!fs_devices->fsid_change) - continue; - - if (check_fsid_changed(fs_devices, disk_super->metadata_uuid)) - return fs_devices; - } - - return find_fsid(disk_super->fsid, disk_super->metadata_uuid); - } - - static int btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, - int flush, struct block_device **bdev, + int flush, struct bdev_handle **bdev_handle, struct btrfs_super_block **disk_super) { + struct block_device *bdev; int ret; - *bdev = blkdev_get_by_path(device_path, flags, holder, NULL); + *bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL); - if (IS_ERR(*bdev)) { - ret = PTR_ERR(*bdev); + if (IS_ERR(*bdev_handle)) { + ret = PTR_ERR(*bdev_handle); goto error; } + bdev = (*bdev_handle)->bdev; if (flush) - sync_blockdev(*bdev); - ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); + sync_blockdev(bdev); + ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; } - invalidate_bdev(*bdev); - *disk_super = btrfs_read_dev_super(*bdev); + invalidate_bdev(bdev); + *disk_super = btrfs_read_dev_super(bdev); if (IS_ERR(*disk_super)) { ret = PTR_ERR(*disk_super); - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; }