Merge tag 'for-7.1-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A batch of fixes to simple quotas:

   - add conditional rescheduling point not dependent on the lock during
     inode iterations to avoid delays with PREEMPT_NONE enabled

   - fix subvolume deletion so it does not break the squota invariants

   - properly handle enabling squota, tracking extents in the initial
     transaction

   - catch and warn about underflows, clamp to zero to avoid further
     problems

  And one fix to inode size handling:

   - fix handling of preallocated extents beyond i_size when not using
     the no-holes feature"

* tag 'for-7.1-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: swallow btrfs_record_squota_delta() ENOENT
  btrfs: clamp to avoid squota underflow
  btrfs: fix squota accounting during enable generation
  btrfs: check for subvolume before deleting squota qgroup
  btrfs: always drop root->inodes lock before cond_resched()
  btrfs: mark file extent range dirty after converting prealloc extents

Author: torvalds

fs/btrfs/extent_map.c

@@ -1246,7 +1246,9 @@ static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root,
 		write_unlock(&tree->lock);
 next:
 		from = btrfs_ino(inode) + 1;
-		cond_resched_lock(&root->inodes.xa_lock);
+		xa_unlock(&root->inodes);
+		cond_resched();
+		xa_lock(&root->inodes);
 	}
 	xa_unlock(&root->inodes);
 

fs/btrfs/file.c

@@ -633,7 +633,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 							 trans->transid);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							end - other_start);
-			return 0;
+			goto mark_dirty;
 		}
 	}
 
@@ -661,7 +661,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 							other_end - start);
 			btrfs_set_file_extent_offset(leaf, fi,
 						     start - orig_offset);
-			return 0;
+			goto mark_dirty;
 		}
 	}
 
@@ -788,7 +788,12 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	return 0;
+mark_dirty:
+	ret = btrfs_inode_set_file_extent_range(inode, start, end - start);
+	if (ret)
+		btrfs_abort_transaction(trans, ret);
+
+	return ret;
 }
 
 /*

fs/btrfs/fs.h

@@ -155,6 +155,7 @@ enum {
 	BTRFS_FS_LOG_RECOVERING,
 	BTRFS_FS_OPEN,
 	BTRFS_FS_QUOTA_ENABLED,
+	BTRFS_FS_SQUOTA_ENABLING,
 	BTRFS_FS_UPDATE_UUID_TREE_GEN,
 	BTRFS_FS_CREATING_FREE_SPACE_TREE,
 	BTRFS_FS_BTREE_ERR,

fs/btrfs/inode.c

@@ -10699,7 +10699,9 @@ struct btrfs_inode *btrfs_find_first_inode(struct btrfs_root *root, u64 min_ino)
 			break;
 
 		from = btrfs_ino(inode) + 1;
-		cond_resched_lock(&root->inodes.xa_lock);
+		xa_unlock(&root->inodes);
+		cond_resched();
+		xa_lock(&root->inodes);
 	}
 	xa_unlock(&root->inodes);
 

fs/btrfs/qgroup.c

@@ -1107,7 +1107,13 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
 	if (simple) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
 		btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA);
-		btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid);
+		/*
+		 * Set the enable generation to the next transaction, as we cannot
+		 * ensure that extents written during this transaction will see any
+		 * state we have set here. So we should treat all extents of the
+		 * transaction as coming in before squotas was enabled.
+		 */
+		btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid + 1);
 	} else {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 	}
@@ -1210,7 +1216,15 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
 		goto out_free_path;
 	}
 
-	fs_info->qgroup_enable_gen = trans->transid;
+	/*
+	 * Set fs_info->qgroup_enable_gen and BTRFS_FS_SQUOTA_ENABLING
+	 * under the transaction handle. We want to ensure that all extents in
+	 * the next transaction definitely see them.
+	 */
+	if (simple) {
+		fs_info->qgroup_enable_gen = trans->transid + 1;
+		set_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags);
+	}
 
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	/*
@@ -1224,9 +1238,15 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
 	 */
 	ret = btrfs_commit_transaction(trans);
 	trans = NULL;
+
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	if (ret)
+	if (ret) {
+		if (simple) {
+			clear_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags);
+			fs_info->qgroup_enable_gen = 0;
+		}
 		goto out_free_path;
+	}
 
 	/*
 	 * Set quota enabled flag after committing the transaction, to avoid
@@ -1236,6 +1256,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
 	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_root = quota_root;
 	set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+	if (simple)
+		clear_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags);
 	spin_unlock(&fs_info->qgroup_lock);
 
 	/* Skip rescan for simple qgroups. */
@@ -1715,32 +1737,24 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	return ret;
 }
 
-static bool can_delete_parent_qgroup(struct btrfs_qgroup *qgroup)
-
+static bool can_delete_parent_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup)
 {
 	ASSERT(btrfs_qgroup_level(qgroup->qgroupid));
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		squota_check_parent_usage(fs_info, qgroup);
 	return list_empty(&qgroup->members);
 }
 
 /*
- * Return true if we can delete the squota qgroup and false otherwise.
- *
- * Rules for whether we can delete:
- *
- * A subvolume qgroup can be removed iff the subvolume is fully deleted, which
- * is iff there is 0 usage in the qgroup.
- *
- * A higher level qgroup can be removed iff it has no members.
- * Note: We audit its usage to warn on inconsitencies without blocking deletion.
+ * Because a shared extent can outlive its owning subvolume, we cannot delete a
+ * subvol squota qgroup until all of the extents it owns are gone, even if the
+ * subvolume itself has been deleted.
  */
-static bool can_delete_squota_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup)
+static bool can_delete_squota_subvol_qgroup(struct btrfs_fs_info *fs_info,
+					    struct btrfs_qgroup *qgroup)
 {
 	ASSERT(btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE);
-
-	if (btrfs_qgroup_level(qgroup->qgroupid) > 0) {
-		squota_check_parent_usage(fs_info, qgroup);
-		return can_delete_parent_qgroup(qgroup);
-	}
+	ASSERT(btrfs_qgroup_level(qgroup->qgroupid) == 0);
 
 	return !(qgroup->rfer || qgroup->excl || qgroup->rfer_cmpr || qgroup->excl_cmpr);
 }
@@ -1754,14 +1768,11 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup
 {
 	struct btrfs_key key;
 	BTRFS_PATH_AUTO_FREE(path);
-
-	/* Since squotas cannot be inconsistent, they have special rules for deletion. */
-	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
-		return can_delete_squota_qgroup(fs_info, qgroup);
+	int ret;
 
 	/* For higher level qgroup, we can only delete it if it has no child. */
 	if (btrfs_qgroup_level(qgroup->qgroupid))
-		return can_delete_parent_qgroup(qgroup);
+		return can_delete_parent_qgroup(fs_info, qgroup);
 
 	/*
 	 * For level-0 qgroups, we can only delete it if it has no subvolume
@@ -1777,10 +1788,21 @@ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup
 		return -ENOMEM;
 
 	/*
-	 * The @ret from btrfs_find_root() exactly matches our definition for
-	 * the return value, thus can be returned directly.
+	 * Any subvol qgroup, regardless of mode, cannot be deleted if the
+	 * subvol still exists.
 	 */
-	return btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL);
+	ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL);
+	/*
+	 * btrfs_find_root returns <0 on error, 0 if found, and >0 if not,
+	 * so the "found" and "error" cases match our desired return values.
+	 */
+	if (ret <= 0)
+		return ret;
+
+	/* Squotas require additional checks, even if the subvol is deleted. */
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		return can_delete_squota_subvol_qgroup(fs_info, qgroup);
+	return 1;
 }
 
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
@@ -4922,7 +4944,8 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 	u64 num_bytes = delta->num_bytes;
 	const int sign = (delta->is_inc ? 1 : -1);
 
-	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE &&
+	    !test_bit(BTRFS_FS_SQUOTA_ENABLING, &fs_info->flags))
 		return 0;
 
 	if (!btrfs_is_fstree(root))
@@ -4934,8 +4957,9 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 
 	spin_lock(&fs_info->qgroup_lock);
 	qgroup = find_qgroup_rb(fs_info, root);
-	if (!qgroup) {
-		ret = -ENOENT;
+	if (WARN_ON_ONCE(!qgroup)) {
+		btrfs_warn(fs_info, "squota failed to find qgroup for root %llu", root);
+		ret = 0;
 		goto out;
 	}
 
@@ -4944,8 +4968,19 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 	list_for_each_entry(qg, &qgroup_list, iterator) {
 		struct btrfs_qgroup_list *glist;
 
-		qg->excl += num_bytes * sign;
-		qg->rfer += num_bytes * sign;
+		ASSERT(qg->excl == qg->rfer);
+		if (WARN_ON_ONCE(sign < 0 && qg->excl < num_bytes)) {
+			btrfs_warn(fs_info,
+				   "squota underflow qg %hu/%llu excl %llu num_bytes %llu",
+				   btrfs_qgroup_level(qg->qgroupid),
+				   btrfs_qgroup_subvolid(qg->qgroupid),
+				   qg->excl, num_bytes);
+			qg->excl = 0;
+			qg->rfer = 0;
+		} else {
+			qg->excl += num_bytes * sign;
+			qg->rfer += num_bytes * sign;
+		}
 		qgroup_dirty(fs_info, qg);
 
 		list_for_each_entry(glist, &qg->groups, next_group)