[PATCH 07/10] xfs: add "fail at unmount" error handling configuration

[Dave Chinner <david@fromorbit.com>]

From: Dave Chinner <dchinner@redhat.com>

If we take "retry forever" literally on metadata IO errors, we can
hang an unmount retries those writes forever. This is the default
behaviour, unfortunately. Add a error configuration option for this
behaviour and default it to "fail" so that an unmount will trigger
actual 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 do 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.

The config is done by a separate boolean sysfs option rather than a
new fail_speed enum, as fail_at_unmount is relevant to both
XFS_ERR_FAIL_NEVER and XFS_ERR_FAIL_SLOW options.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/xfs_buf_item.c |  4 ++++
 fs/xfs/xfs_mount.c    |  9 +++++++++
 fs/xfs/xfs_mount.h    |  2 ++
 fs/xfs/xfs_sysfs.c    | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 51 insertions(+)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index c785698..cf8aec0 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -999,6 +999,10 @@ xfs_buf_iodone_callback_error(
 		break;
 	}
 
+	/* At unmount we may treat errors differently */
+	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && cfg->fail_at_unmount)
+		goto permanent_error;
+
 	/* still a transient error, higher layers will retry */
 	xfs_buf_ioerror(bp, 0);
 	xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 4245b7f3..c2096a0 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -960,6 +960,7 @@ xfs_mountfs(
  out_rele_rip:
 	IRELE(rip);
  out_log_dealloc:
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_unmount(mp);
  out_fail_wait:
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
@@ -1009,6 +1010,14 @@ 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 iin AIL pushing from hanging the unmount.
+	 */
+	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+	/*
 	 * Flush all pending changes from the AIL.
 	 */
 	xfs_ail_push_all_sync(mp->m_ail);
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a684a72b..c86fe43 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -64,6 +64,7 @@ struct xfs_error_cfg {
 	int		fail_speed;
 	int		max_retries;	/* INT_MAX = retry forever */
 	unsigned long	retry_timeout;	/* in jiffies, 0 = no timeout */
+	bool		fail_at_unmount;
 };
 
 typedef struct xfs_mount {
@@ -186,6 +187,7 @@ 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
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 1f078e1..921b079 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -361,10 +361,43 @@ retry_timeout_seconds_show(
 }
 XFS_SYSFS_ATTR_RW(retry_timeout_seconds);
 
+static ssize_t
+fail_at_unmount_store(
+	const char	*buf,
+	size_t		count,
+	void		*data)
+{
+	struct xfs_error_cfg *cfg = data;
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val < 0 || val > 1)
+		return -EINVAL;
+
+	cfg->fail_at_unmount = val;
+	return count;
+}
+
+static ssize_t
+fail_at_unmount_show(
+	char	*buf,
+	void	*data)
+{
+	struct xfs_error_cfg *cfg = data;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", cfg->fail_at_unmount);
+}
+XFS_SYSFS_ATTR_RW(fail_at_unmount);
+
 static struct attribute *xfs_error_attrs[] = {
 	ATTR_LIST(failure_speed),
 	ATTR_LIST(max_retries),
 	ATTR_LIST(retry_timeout_seconds),
+	ATTR_LIST(fail_at_unmount),
 	NULL,
 };
 
@@ -426,6 +459,7 @@ struct xfs_error_init {
 	int		fail_speed;
 	int		max_retries;
 	int		retry_timeout;	/* in seconds */
+	bool		fail_at_unmount;
 };
 
 static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = {
@@ -433,6 +467,7 @@ static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = {
 	  .fail_speed = XFS_ERR_FAIL_NEVER,
 	  .max_retries = INT_MAX,
 	  .retry_timeout = 0,
+	  .fail_at_unmount = true,
 	},
 };
 
@@ -466,6 +501,7 @@ xfs_error_sysfs_init_class(
 		cfg->max_retries = init[i].max_retries;
 		cfg->retry_timeout = msecs_to_jiffies(
 					init[i].retry_timeout * MSEC_PER_SEC);
+		cfg->fail_at_unmount = init[i].fail_at_unmount;
 	}
 	return 0;
 
-- 
2.1.4

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs