Merge branch 'for-linus-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "These are all over the place.

  The tracepoint part of the pull fixes a crash and adds a little more
  information to two tracepoints, while the rest are good old fashioned
  fixes"

* 'for-linus-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  btrfs: make tracepoint format strings more compact
  Btrfs: add truncated_len for ordered extent tracepoints
  Btrfs: add 'inode' for extent map tracepoint
  btrfs: fix crash when tracepoint arguments are freed by wq callbacks
  Btrfs: adjust outstanding_extents counter properly when dio write is split
  Btrfs: fix lockdep warning about log_mutex
  Btrfs: use down_read_nested to make lockdep silent
  btrfs: fix locking when we put back a delayed ref that's too new
  btrfs: fix error handling when run_delayed_extent_op fails
  btrfs: return the actual error value from  from btrfs_uuid_tree_iterate

fs/btrfs/async-thread.c

@@ -273,6 +273,8 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 	unsigned long flags;
 
 	while (1) {
+		void *wtag;
+
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
@@ -299,11 +301,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 		spin_unlock_irqrestore(lock, flags);
 
 		/*
-		 * we don't want to call the ordered free functions
-		 * with the lock held though
+		 * We don't want to call the ordered free functions with the
+		 * lock held though. Save the work as tag for the trace event,
+		 * because the callback could free the structure.
 		 */
+		wtag = work;
 		work->ordered_free(work);
-		trace_btrfs_all_work_done(work);
+		trace_btrfs_all_work_done(wq->fs_info, wtag);
 	}
 	spin_unlock_irqrestore(lock, flags);
 }
@@ -311,6 +315,7 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 static void normal_work_helper(struct btrfs_work *work)
 {
 	struct __btrfs_workqueue *wq;
+	void *wtag;
 	int need_order = 0;
 
 	/*
@@ -324,6 +329,8 @@ static void normal_work_helper(struct btrfs_work *work)
 	if (work->ordered_func)
 		need_order = 1;
 	wq = work->wq;
+	/* Safe for tracepoints in case work gets freed by the callback */
+	wtag = work;
 
 	trace_btrfs_work_sched(work);
 	thresh_exec_hook(wq);
@@ -333,7 +340,7 @@ static void normal_work_helper(struct btrfs_work *work)
 		run_ordered_work(wq);
 	}
 	if (!need_order)
-		trace_btrfs_all_work_done(work);
+		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
 void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,

fs/btrfs/extent-tree.c

@@ -2522,11 +2522,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		if (ref && ref->seq &&
 		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
-			btrfs_delayed_ref_unlock(locked_ref);
 			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
 			delayed_refs->num_heads_ready++;
 			spin_unlock(&delayed_refs->lock);
+			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 			cond_resched();
 			count++;
@@ -2572,7 +2572,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 					 */
 					if (must_insert_reserved)
 						locked_ref->must_insert_reserved = 1;
+					spin_lock(&delayed_refs->lock);
 					locked_ref->processing = 0;
+					delayed_refs->num_heads_ready++;
+					spin_unlock(&delayed_refs->lock);
 					btrfs_debug(fs_info,
 						    "run_delayed_extent_op returned %d",
 						    ret);
@@ -7384,7 +7387,8 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 
 		spin_unlock(&cluster->refill_lock);
 
-		down_read(&used_bg->data_rwsem);
+		/* We should only have one-level nested. */
+		down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING);
 
 		spin_lock(&cluster->refill_lock);
 		if (used_bg == cluster->block_group)

fs/btrfs/inode.c

@@ -7059,7 +7059,7 @@ insert:
 	write_unlock(&em_tree->lock);
 out:
 
-	trace_btrfs_get_extent(root, em);
+	trace_btrfs_get_extent(root, inode, em);
 
 	btrfs_free_path(path);
 	if (trans) {
@@ -7623,11 +7623,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode,
 	 * within our reservation, otherwise we need to adjust our inode
 	 * counter appropriately.
 	 */
-	if (dio_data->outstanding_extents) {
+	if (dio_data->outstanding_extents >= num_extents) {
 		dio_data->outstanding_extents -= num_extents;
 	} else {
+		/*
+		 * If dio write length has been split due to no large enough
+		 * contiguous space, we need to compensate our inode counter
+		 * appropriately.
+		 */
+		u64 num_needed = num_extents - dio_data->outstanding_extents;
+
 		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->outstanding_extents += num_extents;
+		BTRFS_I(inode)->outstanding_extents += num_needed;
 		spin_unlock(&BTRFS_I(inode)->lock);
 	}
 }

fs/btrfs/tree-log.c

@@ -37,6 +37,7 @@
  */
 #define LOG_INODE_ALL 0
 #define LOG_INODE_EXISTS 1
+#define LOG_OTHER_INODE 2
 
 /*
  * directory trouble cases
@@ -4641,7 +4642,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	if (S_ISDIR(inode->i_mode) ||
 	    (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 		       &BTRFS_I(inode)->runtime_flags) &&
-	     inode_only == LOG_INODE_EXISTS))
+	     inode_only >= LOG_INODE_EXISTS))
 		max_key.type = BTRFS_XATTR_ITEM_KEY;
 	else
 		max_key.type = (u8)-1;
@@ -4665,7 +4666,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	if (inode_only == LOG_OTHER_INODE) {
+		inode_only = LOG_INODE_EXISTS;
+		mutex_lock_nested(&BTRFS_I(inode)->log_mutex,
+				  SINGLE_DEPTH_NESTING);
+	} else {
+		mutex_lock(&BTRFS_I(inode)->log_mutex);
+	}
 
 	/*
 	 * a brute force approach to making sure we get the most uptodate
@@ -4817,7 +4824,7 @@ again:
 				 * unpin it.
 				 */
 				err = btrfs_log_inode(trans, root, other_inode,
-						      LOG_INODE_EXISTS,
+						      LOG_OTHER_INODE,
 						      0, LLONG_MAX, ctx);
 				iput(other_inode);
 				if (err)

fs/btrfs/uuid-tree.c

@@ -352,7 +352,5 @@ skip:
 
 out:
 	btrfs_free_path(path);
-	if (ret)
-		btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret);
-	return 0;
+	return ret;
 }