1 files changed, 82 insertions, 18 deletions

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c54ea6586632..87bd37b70738 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/btrfs.h>
+#include <linux/sched/mm.h>
 
 #include "ctree.h"
 #include "transaction.h"
@@ -497,13 +498,13 @@ next2:
 			break;
 	}
 out:
+	btrfs_free_path(path);
 	fs_info->qgroup_flags |= flags;
 	if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
 		clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN &&
 		 ret >= 0)
 		ret = qgroup_rescan_init(fs_info, rescan_progress, 0);
-	btrfs_free_path(path);
 
 	if (ret < 0) {
 		ulist_free(fs_info->qgroup_ulist);
@@ -936,6 +937,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	struct btrfs_key found_key;
 	struct btrfs_qgroup *qgroup = NULL;
 	struct btrfs_trans_handle *trans = NULL;
+	struct ulist *ulist = NULL;
 	int ret = 0;
 	int slot;
 
@@ -943,8 +945,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	if (fs_info->quota_root)
 		goto out;
 
-	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
-	if (!fs_info->qgroup_ulist) {
+	ulist = ulist_alloc(GFP_KERNEL);
+	if (!ulist) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -952,6 +954,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	ret = btrfs_sysfs_add_qgroups(fs_info);
 	if (ret < 0)
 		goto out;
+
+	/*
+	 * Unlock qgroup_ioctl_lock before starting the transaction. This is to
+	 * avoid lock acquisition inversion problems (reported by lockdep) between
+	 * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we
+	 * start a transaction.
+	 * After we started the transaction lock qgroup_ioctl_lock again and
+	 * check if someone else created the quota root in the meanwhile. If so,
+	 * just return success and release the transaction handle.
+	 *
+	 * Also we don't need to worry about someone else calling
+	 * btrfs_sysfs_add_qgroups() after we unlock and getting an error because
+	 * that function returns 0 (success) when the sysfs entries already exist.
+	 */
+	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
 	/*
 	 * 1 for quota root item
 	 * 1 for BTRFS_QGROUP_STATUS item
@@ -961,12 +979,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	 * would be a lot of overkill.
 	 */
 	trans = btrfs_start_transaction(tree_root, 2);
+
+	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		trans = NULL;
 		goto out;
 	}
 
+	if (fs_info->quota_root)
+		goto out;
+
+	fs_info->qgroup_ulist = ulist;
+	ulist = NULL;
+
 	/*
 	 * initially create the quota tree
 	 */
@@ -1124,11 +1150,14 @@ out:
 	if (ret) {
 		ulist_free(fs_info->qgroup_ulist);
 		fs_info->qgroup_ulist = NULL;
-		if (trans)
-			btrfs_end_transaction(trans);
 		btrfs_sysfs_del_qgroups(fs_info);
 	}
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+	if (ret && trans)
+		btrfs_end_transaction(trans);
+	else if (trans)
+		ret = btrfs_end_transaction(trans);
+	ulist_free(ulist);
 	return ret;
 }
 
@@ -1141,19 +1170,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
 		goto out;
+	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 
 	/*
 	 * 1 For the root item
 	 *
 	 * We should also reserve enough items for the quota tree deletion in
 	 * btrfs_clean_quota_tree but this is not done.
+	 *
+	 * Also, we must always start a transaction without holding the mutex
+	 * qgroup_ioctl_lock, see btrfs_quota_enable().
 	 */
 	trans = btrfs_start_transaction(fs_info->tree_root, 1);
+
+	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
+		trans = NULL;
 		goto out;
 	}
 
+	if (!fs_info->quota_root)
+		goto out;
+
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
@@ -1167,13 +1206,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	ret = btrfs_clean_quota_tree(trans, quota_root);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
-		goto end_trans;
+		goto out;
 	}
 
 	ret = btrfs_del_root(trans, &quota_root->root_key);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
-		goto end_trans;
+		goto out;
 	}
 
 	list_del(&quota_root->dirty_list);
@@ -1185,10 +1224,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 
 	btrfs_put_root(quota_root);
 
-end_trans:
-	ret = btrfs_end_transaction(trans);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+	if (ret && trans)
+		btrfs_end_transaction(trans);
+	else if (trans)
+		ret = btrfs_end_transaction(trans);
+
 	return ret;
 }
 
@@ -1324,13 +1366,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 	struct btrfs_qgroup *member;
 	struct btrfs_qgroup_list *list;
 	struct ulist *tmp;
+	unsigned int nofs_flag;
 	int ret = 0;
 
 	/* Check the level of src and dst first */
 	if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
 		return -EINVAL;
 
+	/* We hold a transaction handle open, must do a NOFS allocation. */
+	nofs_flag = memalloc_nofs_save();
 	tmp = ulist_alloc(GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 	if (!tmp)
 		return -ENOMEM;
 
@@ -1387,10 +1433,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 	struct btrfs_qgroup_list *list;
 	struct ulist *tmp;
 	bool found = false;
+	unsigned int nofs_flag;
 	int ret = 0;
 	int ret2;
 
+	/* We hold a transaction handle open, must do a NOFS allocation. */
+	nofs_flag = memalloc_nofs_save();
 	tmp = ulist_alloc(GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 	if (!tmp)
 		return -ENOMEM;
 
@@ -3435,24 +3485,20 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode,
 {
 	struct rb_node *node;
 	struct rb_node *next;
-	struct ulist_node *entry = NULL;
+	struct ulist_node *entry;
 	int ret = 0;
 
 	node = reserved->range_changed.root.rb_node;
+	if (!node)
+		return 0;
 	while (node) {
 		entry = rb_entry(node, struct ulist_node, rb_node);
 		if (entry->val < start)
 			node = node->rb_right;
-		else if (entry)
-			node = node->rb_left;
 		else
-			break;
+			node = node->rb_left;
 	}
 
-	/* Empty changeset */
-	if (!entry)
-		return 0;
-
 	if (entry->val > start && rb_prev(&entry->rb_node))
 		entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node,
 				 rb_node);
@@ -3516,6 +3562,7 @@ static int try_flush_qgroup(struct btrfs_root *root)
 {
 	struct btrfs_trans_handle *trans;
 	int ret;
+	bool can_commit = true;
 
 	/*
 	 * We don't want to run flush again and again, so if there is a running
@@ -3527,6 +3574,20 @@ static int try_flush_qgroup(struct btrfs_root *root)
 		return 0;
 	}
 
+	/*
+	 * If current process holds a transaction, we shouldn't flush, as we
+	 * assume all space reservation happens before a transaction handle is
+	 * held.
+	 *
+	 * But there are cases like btrfs_delayed_item_reserve_metadata() where
+	 * we try to reserve space with one transction handle already held.
+	 * In that case we can't commit transaction, but at least try to end it
+	 * and hope the started data writes can free some space.
+	 */
+	if (current->journal_info &&
+	    current->journal_info != BTRFS_SEND_TRANS_STUB)
+		can_commit = false;
+
 	ret = btrfs_start_delalloc_snapshot(root);
 	if (ret < 0)
 		goto out;
@@ -3538,7 +3599,10 @@ static int try_flush_qgroup(struct btrfs_root *root)
 		goto out;
 	}
 
-	ret = btrfs_commit_transaction(trans);
+	if (can_commit)
+		ret = btrfs_commit_transaction(trans);
+	else
+		ret = btrfs_end_transaction(trans);
 out:
 	clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
 	wake_up(&root->qgroup_flush_wait);