xfs: Add infrastructure needed for error propagation during buffer IO failure

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@redhat.com>
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index f6a8422e9562cd476537869eebc4abf59a3f9bdb..7573a1f0bc9a8cac94d8c7f13ca298307808fe11 100644 (file)
--- 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;

diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6bdad6f5893453d534b147caa1ba52fd2fb6ec4c..442d679210a18198236a969026beeef43027e8c6 100644 (file)
--- 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,