xfs: add "fail at unmount" error handling configuration

If we take "retry forever" literally on metadata IO errors, we can
hang at unmount, once it retries those writes forever. This is the
default behavior, unfortunately.

Add an error configuration option for this behavior and default it
to "fail" so that an unmount will trigger actuall errors, a shutdown
and allow the unmount to succeed. It will be noisy, though, as it
will log the errors and shutdown that occurs.

To fix this, we need to mark the filesystem as being in the process
of unmounting. Do this with a mount flag that is added at the
appropriate time (i.e. before the blocking AIL sync). We also need
to add this flag if mount fails after the initial phase of log
recovery has been run.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

fs/xfs/xfs_buf_item.c

@@ -1106,6 +1106,10 @@ xfs_buf_iodone_callback_error(
 	    time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
 			goto permanent_error;
 
+	/* At unmount we may treat errors differently */
+	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
+		goto permanent_error;
+
 	/* still a transient error, higher layers will retry */
 	xfs_buf_ioerror(bp, 0);
 	xfs_buf_relse(bp);

fs/xfs/xfs_mount.c

@@ -681,6 +681,9 @@ xfs_mountfs(
 
 	xfs_set_maxicount(mp);
 
+	/* enable fail_at_unmount as default */
+	mp->m_fail_unmount = 1;
+
 	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
 	if (error)
 		goto out;
@@ -962,6 +965,7 @@ xfs_mountfs(
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
  out_log_dealloc:
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);
  out_fail_wait:
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -1012,6 +1016,14 @@ xfs_unmountfs(
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
+	/*
+	 * We now need to tell the world we are unmounting. This will allow
+	 * us to detect that the filesystem is going away and we should error
+	 * out anything that we have been retrying in the background. This will
+	 * prevent neverending retries in AIL pushing from hanging the unmount.
+	 */
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
 	/*
 	 * Flush all pending changes from the AIL.
 	 */

fs/xfs/xfs_mount.h

@@ -177,6 +177,7 @@ typedef struct xfs_mount {
 	 */
 	__uint32_t		m_generation;
 
+	bool			m_fail_unmount;
 #ifdef DEBUG
 	/*
 	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
@@ -195,6 +196,7 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_WSYNC		(1ULL << 0)	/* for nfs - all metadata ops
 						   must be synchronous except
 						   for space allocations */
+#define XFS_MOUNT_UNMOUNTING	(1ULL << 1)	/* filesystem is unmounting */
 #define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
 						   operations, typically for

fs/xfs/xfs_sysfs.c

@@ -381,6 +381,13 @@ to_error_cfg(struct kobject *kobject)
 	return container_of(kobj, struct xfs_error_cfg, kobj);
 }
 
+static inline struct xfs_mount *
+err_to_mp(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
+	return container_of(kobj, struct xfs_mount, m_error_kobj);
+}
+
 static ssize_t
 max_retries_show(
 	struct kobject	*kobject,
@@ -447,6 +454,38 @@ retry_timeout_seconds_store(
 }
 XFS_SYSFS_ATTR_RW(retry_timeout_seconds);
 
+static ssize_t
+fail_at_unmount_show(
+	struct kobject	*kobject,
+	char		*buf)
+{
+	struct xfs_mount	*mp = err_to_mp(kobject);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_unmount);
+}
+
+static ssize_t
+fail_at_unmount_store(
+	struct kobject	*kobject,
+	const char	*buf,
+	size_t		count)
+{
+	struct xfs_mount	*mp = err_to_mp(kobject);
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val < 0 || val > 1)
+		return -EINVAL;
+
+	mp->m_fail_unmount = val;
+	return count;
+}
+XFS_SYSFS_ATTR_RW(fail_at_unmount);
+
 static struct attribute *xfs_error_attrs[] = {
 	ATTR_LIST(max_retries),
 	ATTR_LIST(retry_timeout_seconds),
@@ -462,6 +501,7 @@ struct kobj_type xfs_error_cfg_ktype = {
 
 struct kobj_type xfs_error_ktype = {
 	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
 };
 
 /*
@@ -548,6 +588,12 @@ xfs_error_sysfs_init(
 	if (error)
 		return error;
 
+	error = sysfs_create_file(&mp->m_error_kobj.kobject,
+				  ATTR_LIST(fail_at_unmount));
+
+	if (error)
+		goto out_error;
+
 	/* .../xfs/<dev>/error/metadata/ */
 	error = xfs_error_sysfs_init_class(mp, XFS_ERR_METADATA,
 				"metadata", &mp->m_error_meta_kobj,