Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs update from Chris Mason:
 "The biggest feature in the pull is the new (and still experimental)
  raid56 code that David Woodhouse started long ago.  I'm still working
  on the parity logging setup that will avoid inconsistent parity after
  a crash, so this is only for testing right now.  But, I'd really like
  to get it out to a broader audience to hammer out any performance
  issues or other problems.

  scrub does not yet correct errors on raid5/6 either.

  Josef has another pass at fsync performance.  The big change here is
  to combine waiting for metadata with waiting for data, which is a big
  latency win.  It is also step one toward using atomics from the
  hardware during a commit.

  Mark Fasheh has a new way to use btrfs send/receive to send only the
  metadata changes.  SUSE is using this to make snapper more efficient
  at finding changes between snapshosts.

  Snapshot-aware defrag is also included.

  Otherwise we have a large number of fixes and cleanups.  Eric Sandeen
  wins the award for removing the most lines, and I'm hoping we steal
  this idea from XFS over and over again."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (118 commits)
  btrfs: fixup/remove module.h usage as required
  Btrfs: delete inline extents when we find them during logging
  btrfs: try harder to allocate raid56 stripe cache
  Btrfs: cleanup to make the function btrfs_delalloc_reserve_metadata more logic
  Btrfs: don't call btrfs_qgroup_free if just btrfs_qgroup_reserve fails
  Btrfs: remove reduplicate check about root in the function btrfs_clean_quota_tree
  Btrfs: return ENOMEM rather than use BUG_ON when btrfs_alloc_path fails
  Btrfs: fix missing deleted items in btrfs_clean_quota_tree
  btrfs: use only inline_pages from extent buffer
  Btrfs: fix wrong reserved space when deleting a snapshot/subvolume
  Btrfs: fix wrong reserved space in qgroup during snap/subv creation
  Btrfs: remove unnecessary dget_parent/dput when creating the pending snapshot
  btrfs: remove a printk from scan_one_device
  Btrfs: fix NULL pointer after aborting a transaction
  Btrfs: fix memory leak of log roots
  Btrfs: copy everything if we've created an inline extent
  btrfs: cleanup for open-coded alignment
  Btrfs: do not change inode flags in rename
  Btrfs: use reserved space for creating a snapshot
  clear chunk_alloc flag on retryable failure
  ...

1 files changed, 51 insertions, 1 deletions

diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index c9d703693df0..f75fcaf79aeb 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -132,6 +132,15 @@ struct btrfs_delayed_ref_root {
         unsigned long num_heads_ready;
 
         /*
+         * bumped when someone is making progress on the delayed
+         * refs, so that other procs know they are just adding to
+         * contention intead of helping
+         */
+        atomic_t procs_running_refs;
+        atomic_t ref_seq;
+        wait_queue_head_t wait;
+
+        /*
          * set when the tree is flushing before a transaction commit,
          * used by the throttling code to decide if new updates need
          * to be run right away
@@ -141,12 +150,47 @@ struct btrfs_delayed_ref_root {
         u64 run_delayed_start;
 };
 
+extern struct kmem_cache *btrfs_delayed_ref_head_cachep;
+extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
+extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
+extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
+
+int btrfs_delayed_ref_init(void);
+void btrfs_delayed_ref_exit(void);
+
+static inline struct btrfs_delayed_extent_op *
+btrfs_alloc_delayed_extent_op(void)
+{
+        return kmem_cache_alloc(btrfs_delayed_extent_op_cachep, GFP_NOFS);
+}
+
+static inline void
+btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op)
+{
+        if (op)
+                kmem_cache_free(btrfs_delayed_extent_op_cachep, op);
+}
+
 static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 {
         WARN_ON(atomic_read(&ref->refs) == 0);
         if (atomic_dec_and_test(&ref->refs)) {
                 WARN_ON(ref->in_tree);
-                kfree(ref);
+                switch (ref->type) {
+                case BTRFS_TREE_BLOCK_REF_KEY:
+                case BTRFS_SHARED_BLOCK_REF_KEY:
+                        kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+                        break;
+                case BTRFS_EXTENT_DATA_REF_KEY:
+                case BTRFS_SHARED_DATA_REF_KEY:
+                        kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+                        break;
+                case 0:
+                        kmem_cache_free(btrfs_delayed_ref_head_cachep, ref);
+                        break;
+                default:
+                        BUG();
+                }
         }
 }
 
@@ -176,8 +220,14 @@ struct btrfs_delayed_ref_head *
 btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
 int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
                            struct btrfs_delayed_ref_head *head);
+static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
+{
+        mutex_unlock(&head->mutex);
+}
+
 int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
                            struct list_head *cluster, u64 search_start);
+void btrfs_release_ref_cluster(struct list_head *cluster);
 
 int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
                             struct btrfs_delayed_ref_root *delayed_refs,