7 files changed, 62 insertions, 9 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 862fbc2..564a7de 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -378,7 +378,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 
 	ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_error(root->fs_info, ret, "kobj add dev failed");
+		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
 
 	printk_in_rcu(KERN_INFO
 		      "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a9aadb2..f556c37 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2842,6 +2842,7 @@ int open_ctree(struct super_block *sb,
 	    !extent_buffer_uptodate(chunk_root->node)) {
 		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
+		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
 	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
@@ -2879,7 +2880,7 @@ retry_root_backup:
 	    !extent_buffer_uptodate(tree_root->node)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
 		       sb->s_id);
-
+		tree_root->node = NULL;
 		goto recovery_tree_root;
 	}
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1c2bd17..07204bf 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2296,9 +2296,22 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 static inline struct btrfs_delayed_ref_node *
 select_delayed_ref(struct btrfs_delayed_ref_head *head)
 {
+	struct btrfs_delayed_ref_node *ref;
+
 	if (list_empty(&head->ref_list))
 		return NULL;
 
+	/*
+	 * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first.
+	 * This is to prevent a ref count from going down to zero, which deletes
+	 * the extent item from the extent tree, when there still are references
+	 * to add, which would fail because they would not find the extent item.
+	 */
+	list_for_each_entry(ref, &head->ref_list, list) {
+		if (ref->action == BTRFS_ADD_DELAYED_REF)
+			return ref;
+	}
+
 	return list_entry(head->ref_list.next, struct btrfs_delayed_ref_node,
 			  list);
 }
@@ -4214,6 +4227,24 @@ out:
 	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
 	mutex_unlock(&fs_info->chunk_mutex);
+	/*
+	 * When we allocate a new chunk we reserve space in the chunk block
+	 * reserve to make sure we can COW nodes/leafs in the chunk tree or
+	 * add new nodes/leafs to it if we end up needing to do it when
+	 * inserting the chunk item and updating device items as part of the
+	 * second phase of chunk allocation, performed by
+	 * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
+	 * large number of new block groups to create in our transaction
+	 * handle's new_bgs list to avoid exhausting the chunk block reserve
+	 * in extreme cases - like having a single transaction create many new
+	 * block groups when starting to write out the free space caches of all
+	 * the block groups that were made dirty during the lifetime of the
+	 * transaction.
+	 */
+	if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+		btrfs_create_pending_block_groups(trans, trans->root);
+		btrfs_trans_release_chunk_metadata(trans);
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b33c0cf..e33dff3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4209,7 +4209,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	u64 extent_num_bytes = 0;
 	u64 extent_offset = 0;
 	u64 item_end = 0;
-	u64 last_size = (u64)-1;
+	u64 last_size = new_size;
 	u32 found_type = (u8)-1;
 	int found_extent;
 	int del_item;
@@ -4493,8 +4493,7 @@ out:
 			btrfs_abort_transaction(trans, root, ret);
 	}
 error:
-	if (last_size != (u64)-1 &&
-	    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
 
 	btrfs_free_path(path);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5d91776..0770c91 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3090,7 +3090,7 @@ out_unlock:
 static long btrfs_ioctl_file_extent_same(struct file *file,
 			struct btrfs_ioctl_same_args __user *argp)
 {
-	struct btrfs_ioctl_same_args *same;
+	struct btrfs_ioctl_same_args *same = NULL;
 	struct btrfs_ioctl_same_extent_info *info;
 	struct inode *src = file_inode(file);
 	u64 off;
@@ -3120,6 +3120,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
 
 	if (IS_ERR(same)) {
 		ret = PTR_ERR(same);
+		same = NULL;
 		goto out;
 	}
 
@@ -3190,6 +3191,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
 
 out:
 	mnt_drop_write_file(file);
+	kfree(same);
 	return ret;
 }
 
@@ -3586,6 +3588,20 @@ process_slot:
 				u64 trim = 0;
 				u64 aligned_end = 0;
 
+				/*
+				 * Don't copy an inline extent into an offset
+				 * greater than zero. Having an inline extent
+				 * at such an offset results in chaos as btrfs
+				 * isn't prepared for such cases. Just skip
+				 * this case for the same reasons as commented
+				 * at btrfs_ioctl_clone().
+				 */
+				if (last_dest_end > 0) {
+					ret = -EOPNOTSUPP;
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
+
 				if (off > key.offset) {
 					skip = off - key.offset;
 					new_key.offset += skip;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e9ace09..8a82029 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1651,6 +1651,11 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 				/* Exclusive -> exclusive, nothing changed */
 			}
 		}
+
+		/* For exclusive extent, free its reserved bytes too */
+		if (nr_old_roots == 0 && nr_new_roots == 1 &&
+		    cur_new_count == nr_new_roots)
+			qg->reserved -= num_bytes;
 		if (dirty)
 			qgroup_dirty(fs_info, qg);
 	}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c0f18e7..f5021fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -761,7 +761,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	if (!list_empty(&trans->ordered)) {
 		spin_lock(&info->trans_lock);
-		list_splice(&trans->ordered, &cur_trans->pending_ordered);
+		list_splice_init(&trans->ordered, &cur_trans->pending_ordered);
 		spin_unlock(&info->trans_lock);
 	}
 
@@ -1866,7 +1866,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	}
 
 	spin_lock(&root->fs_info->trans_lock);
-	list_splice(&trans->ordered, &cur_trans->pending_ordered);
+	list_splice_init(&trans->ordered, &cur_trans->pending_ordered);
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
 		spin_unlock(&root->fs_info->trans_lock);
 		atomic_inc(&cur_trans->use_count);
@@ -2152,7 +2152,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	if (current != root->fs_info->transaction_kthread)
+	if (current != root->fs_info->transaction_kthread &&
+	    current != root->fs_info->cleaner_kthread)
 		btrfs_run_delayed_iputs(root);
 
 	return ret;