btrfs: qgroup: Fix a race in delayed_ref which leads to abort trans
Between btrfs_allocerved_file_extent() and
btrfs_add_delayed_qgroup_reserve(), there is a window that delayed_refs
are run and delayed ref head maybe freed before
btrfs_add_delayed_qgroup_reserve().
This will cause btrfs_dad_delayed_qgroup_reserve() to return -ENOENT,
and cause transaction to be aborted.
This patch will record qgroup reserve space info into delayed_ref_head
at btrfs_add_delayed_ref(), to eliminate the race window.
Reported-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 1c3588a..e06dd75 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -535,7 +535,8 @@
struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_node *ref,
struct btrfs_qgroup_extent_record *qrecord,
- u64 bytenr, u64 num_bytes, int action, int is_data)
+ u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
+ int action, int is_data)
{
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
@@ -544,6 +545,9 @@
int count_mod = 1;
int must_insert_reserved = 0;
+ /* If reserved is provided, it must be a data extent. */
+ BUG_ON(!is_data && reserved);
+
/*
* the head node stores the sum of all the mods, so dropping a ref
* should drop the sum in the head node by one.
@@ -593,6 +597,11 @@
/* Record qgroup extent info if provided */
if (qrecord) {
+ if (ref_root && reserved) {
+ head_ref->qgroup_ref_root = ref_root;
+ head_ref->qgroup_reserved = reserved;
+ }
+
qrecord->bytenr = bytenr;
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
@@ -611,6 +620,8 @@
existing = htree_insert(&delayed_refs->href_root,
&head_ref->href_node);
if (existing) {
+ WARN_ON(ref_root && reserved && existing->qgroup_ref_root
+ && existing->qgroup_reserved);
update_existing_head_ref(delayed_refs, &existing->node, ref);
/*
* we've updated the existing ref, free the newly
@@ -777,7 +788,7 @@
* the spin lock
*/
head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
- bytenr, num_bytes, action, 0);
+ bytenr, num_bytes, 0, 0, action, 0);
add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, level, action);
@@ -800,7 +811,7 @@
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
u64 parent, u64 ref_root,
- u64 owner, u64 offset, int action,
+ u64 owner, u64 offset, u64 reserved, int action,
struct btrfs_delayed_extent_op *extent_op)
{
struct btrfs_delayed_data_ref *ref;
@@ -839,7 +850,8 @@
* the spin lock
*/
head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
- bytenr, num_bytes, action, 1);
+ bytenr, num_bytes, ref_root, reserved,
+ action, 1);
add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, owner, offset,
@@ -894,7 +906,7 @@
spin_lock(&delayed_refs->lock);
add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr,
- num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
+ num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
extent_op->is_data);
spin_unlock(&delayed_refs->lock);