1 files changed, 110 insertions, 59 deletions

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 966b413a33b..7187b14faa6 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -67,7 +67,7 @@ static void ordered_data_tree_panic(struct inode *inode, int errno,
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	btrfs_panic(fs_info, errno, "Inconsistency in ordered tree at offset "
-		    "%llu\n", offset);
+		    "%llu", offset);
 }
 
 /*
@@ -336,22 +336,26 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 		      entry->len);
 	*file_offset = dec_end;
 	if (dec_start > dec_end) {
-		printk(KERN_CRIT "bad ordering dec_start %llu end %llu\n",
-		       dec_start, dec_end);
+		btrfs_crit(BTRFS_I(inode)->root->fs_info,
+			"bad ordering dec_start %llu end %llu", dec_start, dec_end);
 	}
 	to_dec = dec_end - dec_start;
 	if (to_dec > entry->bytes_left) {
-		printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
-		       entry->bytes_left, to_dec);
+		btrfs_crit(BTRFS_I(inode)->root->fs_info,
+			"bad ordered accounting left %llu size %llu",
+			entry->bytes_left, to_dec);
 	}
 	entry->bytes_left -= to_dec;
 	if (!uptodate)
 		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-	if (entry->bytes_left == 0)
+	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-	else
+		if (waitqueue_active(&entry->wait))
+			wake_up(&entry->wait);
+	} else {
 		ret = 1;
+	}
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
@@ -401,17 +405,21 @@ have_entry:
 	}
 
 	if (io_size > entry->bytes_left) {
-		printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
+		btrfs_crit(BTRFS_I(inode)->root->fs_info,
+			   "bad ordered accounting left %llu size %llu",
 		       entry->bytes_left, io_size);
 	}
 	entry->bytes_left -= io_size;
 	if (!uptodate)
 		set_bit(BTRFS_ORDERED_IOERR, &entry->flags);
 
-	if (entry->bytes_left == 0)
+	if (entry->bytes_left == 0) {
 		ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
-	else
+		if (waitqueue_active(&entry->wait))
+			wake_up(&entry->wait);
+	} else {
 		ret = 1;
+	}
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
@@ -422,27 +430,48 @@ out:
 }
 
 /* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode)
+void btrfs_get_logged_extents(struct inode *inode,
+			      struct list_head *logged_list)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct btrfs_ordered_extent *ordered;
 	struct rb_node *n;
-	int index = log->log_transid % 2;
 
 	tree = &BTRFS_I(inode)->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
 		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		spin_lock(&log->log_extents_lock[index]);
-		if (list_empty(&ordered->log_list)) {
-			list_add_tail(&ordered->log_list, &log->logged_list[index]);
-			atomic_inc(&ordered->refs);
-		}
-		spin_unlock(&log->log_extents_lock[index]);
+		if (!list_empty(&ordered->log_list))
+			continue;
+		list_add_tail(&ordered->log_list, logged_list);
+		atomic_inc(&ordered->refs);
 	}
 	spin_unlock_irq(&tree->lock);
 }
 
+void btrfs_put_logged_extents(struct list_head *logged_list)
+{
+	struct btrfs_ordered_extent *ordered;
+
+	while (!list_empty(logged_list)) {
+		ordered = list_first_entry(logged_list,
+					   struct btrfs_ordered_extent,
+					   log_list);
+		list_del_init(&ordered->log_list);
+		btrfs_put_ordered_extent(ordered);
+	}
+}
+
+void btrfs_submit_logged_extents(struct list_head *logged_list,
+				 struct btrfs_root *log)
+{
+	int index = log->log_transid % 2;
+
+	spin_lock_irq(&log->log_extents_lock[index]);
+	list_splice_tail(logged_list, &log->logged_list[index]);
+	spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
 void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -455,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 					   log_list);
 		list_del_init(&ordered->log_list);
 		spin_unlock_irq(&log->log_extents_lock[index]);
+
+		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+			struct inode *inode = ordered->inode;
+			u64 start = ordered->file_offset;
+			u64 end = ordered->file_offset + ordered->len - 1;
+
+			WARN_ON(!inode);
+			filemap_fdatawrite_range(inode->i_mapping, start, end);
+		}
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
+
 		btrfs_put_ordered_extent(ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
@@ -520,7 +560,8 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);
-	tree->last = NULL;
+	if (tree->last == node)
+		tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
 	spin_unlock_irq(&tree->lock);
 
@@ -537,7 +578,9 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	 */
 	if (RB_EMPTY_ROOT(&tree->tree) &&
 	    !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
+		spin_lock(&root->fs_info->ordered_root_lock);
 		list_del_init(&BTRFS_I(inode)->ordered_operations);
+		spin_unlock(&root->fs_info->ordered_root_lock);
 	}
 
 	if (!root->nr_ordered_extents) {
@@ -563,72 +606,64 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 {
 	struct list_head splice, works;
 	struct btrfs_ordered_extent *ordered, *next;
-	struct inode *inode;
+	int count = 0;
 
 	INIT_LIST_HEAD(&splice);
 	INIT_LIST_HEAD(&works);
 
-	mutex_lock(&root->fs_info->ordered_operations_mutex);
+	mutex_lock(&root->ordered_extent_mutex);
 	spin_lock(&root->ordered_extent_lock);
 	list_splice_init(&root->ordered_extents, &splice);
-	while (!list_empty(&splice)) {
+	while (!list_empty(&splice) && nr) {
 		ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
 					   root_extent_list);
 		list_move_tail(&ordered->root_extent_list,
 			       &root->ordered_extents);
-		/*
-		 * the inode may be getting freed (in sys_unlink path).
-		 */
-		inode = igrab(ordered->inode);
-		if (!inode) {
-			cond_resched_lock(&root->ordered_extent_lock);
-			continue;
-		}
-
 		atomic_inc(&ordered->refs);
 		spin_unlock(&root->ordered_extent_lock);
 
-		ordered->flush_work.func = btrfs_run_ordered_extent_work;
+		btrfs_init_work(&ordered->flush_work,
+				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
-		btrfs_queue_worker(&root->fs_info->flush_workers,
-				   &ordered->flush_work);
+		btrfs_queue_work(root->fs_info->flush_workers,
+				 &ordered->flush_work);
 
 		cond_resched();
 		spin_lock(&root->ordered_extent_lock);
+		if (nr != -1)
+			nr--;
+		count++;
 	}
+	list_splice_tail(&splice, &root->ordered_extents);
 	spin_unlock(&root->ordered_extent_lock);
 
 	list_for_each_entry_safe(ordered, next, &works, work_list) {
 		list_del_init(&ordered->work_list);
 		wait_for_completion(&ordered->completion);
-
-		inode = ordered->inode;
 		btrfs_put_ordered_extent(ordered);
-		if (delay_iput)
-			btrfs_add_delayed_iput(inode);
-		else
-			iput(inode);
-
 		cond_resched();
 	}
-	mutex_unlock(&root->fs_info->ordered_operations_mutex);
+	mutex_unlock(&root->ordered_extent_mutex);
+
+	return count;
 }
 
-void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info,
-				    int delay_iput)
+void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
+	int done;
 
 	INIT_LIST_HEAD(&splice);
 
+	mutex_lock(&fs_info->ordered_operations_mutex);
 	spin_lock(&fs_info->ordered_root_lock);
 	list_splice_init(&fs_info->ordered_roots, &splice);
-	while (!list_empty(&splice)) {
+	while (!list_empty(&splice) && nr) {
 		root = list_first_entry(&splice, struct btrfs_root,
 					ordered_root);
 		root = btrfs_grab_fs_root(root);
@@ -637,12 +672,18 @@ void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info,
 			       &fs_info->ordered_roots);
 		spin_unlock(&fs_info->ordered_root_lock);
 
-		btrfs_wait_ordered_extents(root, delay_iput);
+		done = btrfs_wait_ordered_extents(root, nr);
 		btrfs_put_fs_root(root);
 
 		spin_lock(&fs_info->ordered_root_lock);
+		if (nr != -1) {
+			nr -= done;
+			WARN_ON(nr < 0);
+		}
 	}
+	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
+	mutex_unlock(&fs_info->ordered_operations_mutex);
 }
 
 /*
@@ -704,8 +745,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 		list_add_tail(&work->list, &works);
-		btrfs_queue_worker(&root->fs_info->flush_workers,
-				   &work->work);
+		btrfs_queue_work(root->fs_info->flush_workers,
+				 &work->work);
 
 		cond_resched();
 		spin_lock(&root->fs_info->ordered_root_lock);
@@ -752,8 +793,9 @@ void btrfs_start_ordered_extent(struct inode *inode,
 /*
  * Used to wait on ordered extents across a large range of bytes.
  */
-void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
+int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 {
+	int ret = 0;
 	u64 end;
 	u64 orig_end;
 	struct btrfs_ordered_extent *ordered;
@@ -769,8 +811,9 @@ void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 	/* start IO across the range first to instantiate any delalloc
 	 * extents
 	 */
-	filemap_fdatawrite_range(inode->i_mapping, start, orig_end);
-
+	ret = filemap_fdatawrite_range(inode->i_mapping, start, orig_end);
+	if (ret)
+		return ret;
 	/*
 	 * So with compression we will find and lock a dirty page and clear the
 	 * first one as dirty, setup an async extent, and immediately return
@@ -786,10 +829,15 @@ void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 	 * right and you are wrong.
 	 */
 	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-		     &BTRFS_I(inode)->runtime_flags))
-		filemap_fdatawrite_range(inode->i_mapping, start, orig_end);
-
-	filemap_fdatawait_range(inode->i_mapping, start, orig_end);
+		     &BTRFS_I(inode)->runtime_flags)) {
+		ret = filemap_fdatawrite_range(inode->i_mapping, start,
+					       orig_end);
+		if (ret)
+			return ret;
+	}
+	ret = filemap_fdatawait_range(inode->i_mapping, start, orig_end);
+	if (ret)
+		return ret;
 
 	end = orig_end;
 	while (1) {
@@ -800,17 +848,20 @@ void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
-		if (ordered->file_offset + ordered->len < start) {
+		if (ordered->file_offset + ordered->len <= start) {
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
 		btrfs_start_ordered_extent(inode, ordered, 1);
 		end = ordered->file_offset;
+		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
+			ret = -EIO;
 		btrfs_put_ordered_extent(ordered);
-		if (end == 0 || end == start)
+		if (ret || end == 0 || end == start)
 			break;
 		end--;
 	}
+	return ret;
 }
 
 /*
@@ -1094,7 +1145,7 @@ void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
 	 * if this file hasn't been changed since the last transaction
 	 * commit, we can safely return without doing anything
 	 */
-	if (last_mod < root->fs_info->last_trans_committed)
+	if (last_mod <= root->fs_info->last_trans_committed)
 		return;
 
 	spin_lock(&root->fs_info->ordered_root_lock);