btrfs: qgroup: Introduce btrfs_qgroup_reserve_data function

Introduce a new function, btrfs_qgroup_reserve_data(), which will use
io_tree to accurate qgroup reserve, to avoid reserved space leaking.

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

3 files changed, 52 insertions, 0 deletions

diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 51e1b7143256..f4c1ae11855f 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -19,6 +19,7 @@
 #define EXTENT_NEED_WAIT        (1U << 13)
 #define EXTENT_DAMAGED          (1U << 14)
 #define EXTENT_NORESERVE        (1U << 15)
+#define EXTENT_QGROUP_RESERVED  (1U << 16)
 #define EXTENT_IOBITS           (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS          (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d904ee1c5349..50662748532a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2486,3 +2486,52 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
                 btrfs_queue_work(fs_info->qgroup_rescan_workers,
                                  &fs_info->qgroup_rescan_work);
 }
+
+/*
+ * Reserve qgroup space for range [start, start + len).
+ *
+ * This function will either reserve space from related qgroups or doing
+ * nothing if the range is already reserved.
+ *
+ * Return 0 for successful reserve
+ * Return <0 for error (including -EQUOT)
+ *
+ * NOTE: this function may sleep for memory allocation.
+ */
+int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
+{
+        struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct extent_changeset changeset;
+        struct ulist_node *unode;
+        struct ulist_iterator uiter;
+        int ret;
+
+        if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) ||
+            len == 0)
+                return 0;
+
+        changeset.bytes_changed = 0;
+        changeset.range_changed = ulist_alloc(GFP_NOFS);
+
+        ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
+                        start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
+                        &changeset);
+        if (ret < 0)
+                goto cleanup;
+        ret = btrfs_qgroup_reserve(root, changeset.bytes_changed);
+        if (ret < 0)
+                goto cleanup;
+
+        ulist_free(changeset.range_changed);
+        return ret;
+
+cleanup:
+        /* cleanup already reserved ranges */
+        ULIST_ITER_INIT(&uiter);
+        while ((unode = ulist_next(changeset.range_changed, &uiter)))
+                clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
+                                 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
+                                 GFP_NOFS);
+        ulist_free(changeset.range_changed);
+        return ret;
+}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 6387dcfa354c..bd17cc24335c 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -81,4 +81,6 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
                                u64 rfer, u64 excl);
 #endif
 
+/* New io_tree based accurate qgroup reserve API */
+int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len);
 #endif /* __BTRFS_QGROUP__ */