btrfs: track original extent owner in head_ref

Simple quotas requires tracking the original creating root of any given
extent. This gets complicated when multiple subvolumes create
overlapping/contradictory refs in the same transaction. For example,
due to modifying or deleting an extent while also snapshotting it.

To resolve this in a general way, take advantage of the fact that we are
essentially already tracking this for handling releasing reservations.
The head ref coalesces the various refs and uses must_insert_reserved to
check if it needs to create an extent/free reservation. Store the ref
that set must_insert_reserved as the owning ref on the head ref.

Note that this can result in writing an extent for the very first time
with an owner different from its only ref, but it will look the same as
if you first created it with the original owning ref, then added the
other ref, then removed the owning ref.

Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9d6a5dafd9b8f5aa8091ae1a02beab54a95af0af..207e1efa6f159ef4fc5d712ab439f3fa5a658450 100644 (file)
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -678,6 +678,15 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
        BUG_ON(existing->is_data != update->is_data);
 
        spin_lock(&existing->lock);
+
+       /*
+        * When freeing an extent, we may not know the owning root when we
+        * first create the head_ref. However, some deref before the last deref
+        * will know it, so we just need to update the head_ref accordingly.
+        */
+       if (!existing->owning_root)
+               existing->owning_root = update->owning_root;
+
        if (update->must_insert_reserved) {
                /* if the extent was freed and then
                 * reallocated before the delayed ref
@@ -687,6 +696,7 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
                 * Set it again here
                 */
                existing->must_insert_reserved = update->must_insert_reserved;
+               existing->owning_root = update->owning_root;
 
                /*
                 * update the num_bytes so we make sure the accounting
@@ -751,7 +761,7 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
                                  struct btrfs_qgroup_extent_record *qrecord,
                                  u64 bytenr, u64 num_bytes, u64 ref_root,
                                  u64 reserved, int action, bool is_data,
-                                 bool is_system)
+                                 bool is_system, u64 owning_root)
 {
        int count_mod = 1;
        bool must_insert_reserved = false;
@@ -792,6 +802,7 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
        head_ref->num_bytes = num_bytes;
        head_ref->ref_mod = count_mod;
        head_ref->must_insert_reserved = must_insert_reserved;
+       head_ref->owning_root = owning_root;
        head_ref->is_data = is_data;
        head_ref->is_system = is_system;
        head_ref->ref_tree = RB_ROOT_CACHED;
@@ -982,7 +993,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
        init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
                              generic_ref->tree_ref.ref_root, 0, action,
-                             false, is_system);
+                             false, is_system, generic_ref->owning_root);
        head_ref->extent_op = extent_op;
 
        delayed_refs = &trans->transaction->delayed_refs;
@@ -1073,7 +1084,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
        }
 
        init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
-                             reserved, action, true, false);
+                             reserved, action, true, false, generic_ref->owning_root);
        head_ref->extent_op = NULL;
 
        delayed_refs = &trans->transaction->delayed_refs;
@@ -1119,7 +1130,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
                return -ENOMEM;
 
        init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
-                             BTRFS_UPDATE_DELAYED_HEAD, false, false);
+                             BTRFS_UPDATE_DELAYED_HEAD, false, false, 0);
        head_ref->extent_op = extent_op;
 
        delayed_refs = &trans->transaction->delayed_refs;

diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 84b37888bff3c45a820bd85c7beee094cb5c6338..47e4bdf4fb30b9c577a61e09ef4b3d72e1d2962b 100644 (file)
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -110,6 +110,12 @@ struct btrfs_delayed_ref_head {
         */
        int ref_mod;
 
+       /*
+        * The root that triggered the allocation when must_insert_reserved is
+        * set to true.
+        */
+       u64 owning_root;
+
        /*
         * when a new extent is allocated, it is just reserved in memory
         * The actual extent isn't inserted into the extent allocation tree
@@ -123,6 +129,7 @@ struct btrfs_delayed_ref_head {
         * the free has happened.
         */
        bool must_insert_reserved;
+
        bool is_data;
        bool is_system;
        bool processing;