btrfs: qgroup: Introduce functions to release/free qgroup reserve data

space

Introduce functions btrfs_qgroup_release/free_data() to release/free
reserved data range.

Release means, just remove the data range from io_tree, but doesn't
free the reserved space.
This is for normal buffered write case, when data is written into disc
and its metadata is added into tree, its reserved space should still be
kept until commit_trans().
So in that case, we only release dirty range, but keep the reserved
space recorded some other place until commit_tran().

Free means not only remove data range, but also free reserved space.
This is used for case for cleanup and invalidate page.

Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 50662748532a3d461227d8aa80a397385aad607b..e05d1f6aa293f0e95768032c96ba225777036f10 100644 (file)
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2535,3 +2535,63 @@ cleanup:
        ulist_free(changeset.range_changed);
        return ret;
 }
+
+static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
+                                      int free)
+{
+       struct extent_changeset changeset;
+       int ret;
+
+       changeset.bytes_changed = 0;
+       changeset.range_changed = ulist_alloc(GFP_NOFS);
+       if (!changeset.range_changed)
+               return -ENOMEM;
+
+       ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, 
+                       start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
+                       &changeset);
+       if (ret < 0)
+               goto out;
+
+       if (free)
+               btrfs_qgroup_free(BTRFS_I(inode)->root,
+                                 changeset.bytes_changed);
+out:
+       ulist_free(changeset.range_changed);
+       return ret;
+}
+
+/*
+ * Free a reserved space range from io_tree and related qgroups
+ *
+ * Should be called when a range of pages get invalidated before reaching disk.
+ * Or for error cleanup case.
+ *
+ * For data written to disk, use btrfs_qgroup_release_data().
+ *
+ * NOTE: This function may sleep for memory allocation.
+ */
+int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
+{
+       return __btrfs_qgroup_release_data(inode, start, len, 1);
+}
+
+/*
+ * Release a reserved space range from io_tree only.
+ *
+ * Should be called when a range of pages get written to disk and corresponding
+ * FILE_EXTENT is inserted into corresponding root.
+ *
+ * Since new qgroup accounting framework will only update qgroup numbers at
+ * commit_transaction() time, its reserved space shouldn't be freed from
+ * related qgroups.
+ *
+ * But we should release the range from io_tree, to allow further write to be
+ * COWed.
+ *
+ * NOTE: This function may sleep for memory allocation.
+ */
+int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len)
+{
+       return __btrfs_qgroup_release_data(inode, start, len, 0);
+}

diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index bd17cc24335cf310c733e95a599b9ca8c747764b..564eb214774091da9ba03499eac3415059d15981 100644 (file)
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -83,4 +83,6 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 
 /* New io_tree based accurate qgroup reserve API */
 int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len);
 #endif /* __BTRFS_QGROUP__ */