btrfs: turn delayed_nodes_tree into an XArray

… in the btrfs_root struct and adjust all usages of this object to use
the XArray API, because it is notionally easier to use and understand,
as it provides array semantics, and also takes care of locking for us,
further simplifying the code.

Also use the opportunity to do some light refactoring.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Gabriel Niebler <gniebler@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/ctree.h

@@ -1222,10 +1222,10 @@ struct btrfs_root {
 	struct rb_root inode_tree;
 
 	/*
-	 * radix tree that keeps track of delayed nodes of every inode,
+	 * Xarray that keeps track of delayed nodes of every inode, protected
-	 * protected by inode_lock
+	 * by inode_lock
 	 */
-	struct radix_tree_root delayed_nodes_tree;
+	struct xarray delayed_nodes;
 	/*
 	 * right now this just gets used so that a root has its own devid
 	 * for stat.  It may be used for more later

fs/btrfs/delayed-inode.c

@@ -78,7 +78,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 	}
 
 	spin_lock(&root->inode_lock);
-	node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
+	node = xa_load(&root->delayed_nodes, ino);
 
 	if (node) {
 		if (btrfs_inode->delayed_node) {
@@ -90,9 +90,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 
 		/*
 		 * It's possible that we're racing into the middle of removing
-		 * this node from the radix tree.  In this case, the refcount
+		 * this node from the xarray.  In this case, the refcount
 		 * was zero and it should never go back to one.  Just return
-		 * NULL like it was never in the radix at all; our release
+		 * NULL like it was never in the xarray at all; our release
 		 * function is in the process of removing it.
 		 *
 		 * Some implementations of refcount_inc refuse to bump the
@@ -100,7 +100,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 		 * here, refcount_inc() may decide to just WARN_ONCE() instead
 		 * of actually bumping the refcount.
 		 *
-		 * If this node is properly in the radix, we want to bump the
+		 * If this node is properly in the xarray, we want to bump the
 		 * refcount twice, once for the inode and once for this get
 		 * operation.
 		 */
@@ -128,36 +128,30 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
 	u64 ino = btrfs_ino(btrfs_inode);
 	int ret;
 
-again:
+	do {
-	node = btrfs_get_delayed_node(btrfs_inode);
+		node = btrfs_get_delayed_node(btrfs_inode);
-	if (node)
+		if (node)
-		return node;
+			return node;
 
-	node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
+		node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
-	if (!node)
+		if (!node)
-		return ERR_PTR(-ENOMEM);
+			return ERR_PTR(-ENOMEM);
-	btrfs_init_delayed_node(node, root, ino);
+		btrfs_init_delayed_node(node, root, ino);
 
-	/* cached in the btrfs inode and can be accessed */
+		/* Cached in the inode and can be accessed */
-	refcount_set(&node->refs, 2);
+		refcount_set(&node->refs, 2);
 
-	ret = radix_tree_preload(GFP_NOFS);
+		spin_lock(&root->inode_lock);
-	if (ret) {
+		ret = xa_insert(&root->delayed_nodes, ino, node, GFP_NOFS);
-		kmem_cache_free(delayed_node_cache, node);
+		if (ret) {
-		return ERR_PTR(ret);
+			spin_unlock(&root->inode_lock);
-	}
+			kmem_cache_free(delayed_node_cache, node);
-
+			if (ret != -EBUSY)
-	spin_lock(&root->inode_lock);
+				return ERR_PTR(ret);
-	ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
+		}
-	if (ret == -EEXIST) {
+	} while (ret);
-		spin_unlock(&root->inode_lock);
-		kmem_cache_free(delayed_node_cache, node);
-		radix_tree_preload_end();
-		goto again;
-	}
 	btrfs_inode->delayed_node = node;
 	spin_unlock(&root->inode_lock);
-	radix_tree_preload_end();
 
 	return node;
 }
@@ -276,8 +270,7 @@ static void __btrfs_release_delayed_node(
 		 * back up.  We can delete it now.
 		 */
 		ASSERT(refcount_read(&delayed_node->refs) == 0);
-		radix_tree_delete(&root->delayed_nodes_tree,
+		xa_erase(&root->delayed_nodes, delayed_node->inode_id);
-				  delayed_node->inode_id);
 		spin_unlock(&root->inode_lock);
 		kmem_cache_free(delayed_node_cache, delayed_node);
 	}
@@ -1870,34 +1863,35 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode)
 
 void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 {
-	u64 inode_id = 0;
+	unsigned long index = 0;
+	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_delayed_node *delayed_nodes[8];
-	int i, n;
 
 	while (1) {
+		int n = 0;
+
 		spin_lock(&root->inode_lock);
-		n = radix_tree_gang_lookup(&root->delayed_nodes_tree,
+		if (xa_empty(&root->delayed_nodes)) {
-					   (void **)delayed_nodes, inode_id,
-					   ARRAY_SIZE(delayed_nodes));
-		if (!n) {
 			spin_unlock(&root->inode_lock);
-			break;
+			return;
 		}
 
-		inode_id = delayed_nodes[n - 1]->inode_id + 1;
+		xa_for_each_start(&root->delayed_nodes, index, delayed_node, index) {
-		for (i = 0; i < n; i++) {
 			/*
 			 * Don't increase refs in case the node is dead and
 			 * about to be removed from the tree in the loop below
 			 */
-			if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+			if (refcount_inc_not_zero(&delayed_node->refs)) {
-				delayed_nodes[i] = NULL;
+				delayed_nodes[n] = delayed_node;
+				n++;
+			}
+			if (n >= ARRAY_SIZE(delayed_nodes))
+				break;
 		}
+		index++;
 		spin_unlock(&root->inode_lock);
 
-		for (i = 0; i < n; i++) {
+		for (int i = 0; i < n; i++) {
-			if (!delayed_nodes[i])
-				continue;
 			__btrfs_kill_delayed_node(delayed_nodes[i]);
 			btrfs_release_delayed_node(delayed_nodes[i]);
 		}

fs/btrfs/disk-io.c

@@ -1160,7 +1160,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
 	root->inode_tree = RB_ROOT;
-	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
+	xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
 
 	btrfs_init_root_block_rsv(root);
 

fs/btrfs/inode.c

@@ -3881,7 +3881,7 @@ cache_index:
 	 * cache.
 	 *
 	 * This is required for both inode re-read from disk and delayed inode
-	 * in delayed_nodes_tree.
+	 * in the delayed_nodes xarray.
 	 */
 	if (BTRFS_I(inode)->last_trans == fs_info->generation)
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,