This is a note to let you know that I've just added the patch titled
xfs: Add infrastructure needed for error propagation during buffer IO failure
to the 4.13-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
xfs-add-infrastructure-needed-for-error-propagation-during-buffer-io-failure.patch
and it can be found in the queue-4.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Mon Sep 18 10:25:08 CEST 2017
From: Christoph Hellwig <hch@xxxxxx>
Date: Sun, 17 Sep 2017 14:06:09 -0700
Subject: xfs: Add infrastructure needed for error propagation during buffer IO failure
To: stable@xxxxxxxxxxxxxxx
Cc: linux-xfs@xxxxxxxxxxxxxxx, Carlos Maiolino <cmaiolino@xxxxxxxxxx>, "Darrick J . Wong" <darrick.wong@xxxxxxxxxx>
Message-ID: <20170917210631.10725-4-hch@xxxxxx>
From: Carlos Maiolino <cmaiolino@xxxxxxxxxx>
commit 0b80ae6ed13169bd3a244e71169f2cc020b0c57a upstream.
With the current code, XFS never re-submit a failed buffer for IO,
because the failed item in the buffer is kept in the flush locked state
forever.
To be able to resubmit an log item for IO, we need a way to mark an item
as failed, if, for any reason the buffer which the item belonged to
failed during writeback.
Add a new log item callback to be used after an IO completion failure
and make the needed clean ups.
Reviewed-by: Brian Foster <bfoster@xxxxxxxxxx>
Signed-off-by: Carlos Maiolino <cmaiolino@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/xfs/xfs_buf_item.c | 32 +++++++++++++++++++++++++++++++-
fs/xfs/xfs_trans.h | 7 +++++--
2 files changed, 36 insertions(+), 3 deletions(-)
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -29,6 +29,7 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_log.h"
+#include "xfs_inode.h"
kmem_zone_t *xfs_buf_item_zone;
@@ -1054,6 +1055,31 @@ xfs_buf_do_callbacks(
}
}
+/*
+ * Invoke the error state callback for each log item affected by the failed I/O.
+ *
+ * If a metadata buffer write fails with a non-permanent error, the buffer is
+ * eventually resubmitted and so the completion callbacks are not run. The error
+ * state may need to be propagated to the log items attached to the buffer,
+ * however, so the next AIL push of the item knows hot to handle it correctly.
+ */
+STATIC void
+xfs_buf_do_callbacks_fail(
+ struct xfs_buf *bp)
+{
+ struct xfs_log_item *next;
+ struct xfs_log_item *lip = bp->b_fspriv;
+ struct xfs_ail *ailp = lip->li_ailp;
+
+ spin_lock(&ailp->xa_lock);
+ for (; lip; lip = next) {
+ next = lip->li_bio_list;
+ if (lip->li_ops->iop_error)
+ lip->li_ops->iop_error(lip, bp);
+ }
+ spin_unlock(&ailp->xa_lock);
+}
+
static bool
xfs_buf_iodone_callback_error(
struct xfs_buf *bp)
@@ -1123,7 +1149,11 @@ xfs_buf_iodone_callback_error(
if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
goto permanent_error;
- /* still a transient error, higher layers will retry */
+ /*
+ * Still a transient error, run IO completion failure callbacks and let
+ * the higher layers retry the buffer.
+ */
+ xfs_buf_do_callbacks_fail(bp);
xfs_buf_ioerror(bp, 0);
xfs_buf_relse(bp);
return true;
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -64,11 +64,13 @@ typedef struct xfs_log_item {
} xfs_log_item_t;
#define XFS_LI_IN_AIL 0x1
-#define XFS_LI_ABORTED 0x2
+#define XFS_LI_ABORTED 0x2
+#define XFS_LI_FAILED 0x4
#define XFS_LI_FLAGS \
{ XFS_LI_IN_AIL, "IN_AIL" }, \
- { XFS_LI_ABORTED, "ABORTED" }
+ { XFS_LI_ABORTED, "ABORTED" }, \
+ { XFS_LI_FAILED, "FAILED" }
struct xfs_item_ops {
void (*iop_size)(xfs_log_item_t *, int *, int *);
@@ -79,6 +81,7 @@ struct xfs_item_ops {
void (*iop_unlock)(xfs_log_item_t *);
xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
+ void (*iop_error)(xfs_log_item_t *, xfs_buf_t *);
};
void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
Patches currently in stable-queue which might be from hch@xxxxxx are
queue-4.13/xfs-open-code-xfs_buf_item_dirty.patch
queue-4.13/xfs-properly-retry-failed-inode-items-in-case-of-error-during-buffer-writeback.patch
queue-4.13/xfs-use-kmem_free-to-free-return-value-of-kmem_zalloc.patch
queue-4.13/xfs-add-infrastructure-needed-for-error-propagation-during-buffer-io-failure.patch
queue-4.13/xfs-don-t-set-v3-xflags-for-v2-inodes.patch
queue-4.13/xfs-toggle-readonly-state-around-xfs_log_mount_finish.patch
queue-4.13/xfs-fix-log-recovery-corruption-error-due-to-tail-overwrite.patch
queue-4.13/xfs-move-bmbt-owner-change-to-last-step-of-extent-swap.patch
queue-4.13/xfs-check-for-race-with-xfs_reclaim_inode-in-xfs_ifree_cluster.patch
queue-4.13/xfs-always-verify-the-log-tail-during-recovery.patch
queue-4.13/xfs-open-code-end_buffer_async_write-in-xfs_finish_page_writeback.patch
queue-4.13/xfs-relog-dirty-buffers-during-swapext-bmbt-owner-change.patch
queue-4.13/xfs-disable-per-inode-dax-flag.patch
queue-4.13/xfs-refactor-buffer-logging-into-buffer-dirtying-helper.patch
queue-4.13/xfs-fix-recovery-failure-when-log-record-header-wraps-log-end.patch
queue-4.13/xfs-skip-bmbt-block-ino-validation-during-owner-change.patch
queue-4.13/xfs-don-t-log-dirty-ranges-for-ordered-buffers.patch
queue-4.13/xfs-stop-searching-for-free-slots-in-an-inode-chunk-when-there-are-none.patch
queue-4.13/xfs-fix-incorrect-log_flushed-on-fsync.patch
queue-4.13/xfs-evict-all-inodes-involved-with-log-redo-item.patch
queue-4.13/xfs-write-unmount-record-for-ro-mounts.patch
queue-4.13/xfs-remove-unnecessary-dirty-bli-format-check-for-ordered-bufs.patch
queue-4.13/xfs-disallow-marking-previously-dirty-buffers-as-ordered.patch
queue-4.13/xfs-handle-efscorrupted-during-head-tail-verification.patch
queue-4.13/xfs-ordered-buffer-log-items-are-never-formatted.patch