This new function will do all the hard work to reserve precious space for a write.
The overall work flow will be the following. File A already has some dirty pages: 0 4K 8K 12K 16K |///////| |///////| And then, someone want to write some data into range [4K, 16K). |<------desired-------->| Unlike the old and wrong implement, which reserve 12K, this function will only reserve space for newly dirty part: |\\\\\\\| |\\\\\\\| Which only takes 8K reserve space, as other part has already allocated their own reserve space. So the final reserve map will be: |///////////////////////////////| This provides the basis to resolve the long existing qgroup limit bug. Signed-off-by: Qu Wenruo <quwen...@cn.fujitsu.com> --- v2: Add needed parameter for later trace functions --- fs/btrfs/qgroup.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/qgroup.h | 1 + 2 files changed, 58 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3bdf28e..e840f5c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2796,6 +2796,63 @@ insert: } /* + * Make sure the data space for [start, start + len) is reserved. + * It will either reserve new space from given qgroup or reuse the already + * reserved space. + * + * Return 0 for successful reserve. + * Return <0 for error. + * + * TODO: to handle nocow case, like NODATACOW or write into prealloc space + * along with other mixed case. + * Like write 2M, first 1M can be nocowed, but next 1M is on hole and need COW. + */ +int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) +{ + struct btrfs_inode *binode = BTRFS_I(inode); + struct btrfs_root *root = binode->root; + struct btrfs_qgroup_data_rsv_map *reserve_map; + struct data_rsv_range *tmp = NULL; + struct ulist *insert_list; + int ret; + + if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) || + len == 0) + return 0; + + if (!binode->qgroup_rsv_map) { + ret = btrfs_qgroup_init_data_rsv_map(inode); + if (ret < 0) + return ret; + } + reserve_map = binode->qgroup_rsv_map; + insert_list = ulist_alloc(GFP_NOFS); + if (!insert_list) + return -ENOMEM; + tmp = kzalloc(sizeof(*tmp), GFP_NOFS); + if (!tmp) { + ulist_free(insert_list); + return -ENOMEM; + } + + spin_lock(&reserve_map->lock); + ret = reserve_data_range(root, reserve_map, tmp, insert_list, start, + len, NULL); + /* + * For error and already exists case, free tmp memory. + * For tmp used case, set ret to 0, as some careless + * caller consider >0 as error. + */ + if (ret <= 0) + kfree(tmp); + else + ret = 0; + spin_unlock(&reserve_map->lock); + ulist_free(insert_list); + return ret; +} + +/* * Init data_rsv_map for a given inode. * * This is needed at write time as quota can be disabled and then enabled diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index c87b7dc..366b853 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -87,4 +87,5 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* for qgroup reserve */ int btrfs_qgroup_init_data_rsv_map(struct inode *inode); void btrfs_qgroup_free_data_rsv_map(struct inode *inode); +int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); #endif /* __BTRFS_QGROUP__ */ -- 2.6.1 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html