md: Use ->curr_resync as last completed request when cleanly aborting resync.

If a resync is aborted cleanly, ->curr_resync is a reliable
record of where we got up to.
If there was an error it is less reliable but we always know that
->curr_resync_completed is safe.

So add a flag MD_RECOVERY_ERROR to differentiate between these cases
and set recovery_cp accordingly.

Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

2 files changed, 10 insertions, 2 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6aefa443481..30ba223e5ed 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7180,6 +7180,7 @@ void md_done_sync(struct mddev *mddev, int blocks, int ok)
         wake_up(&mddev->recovery_wait);
         if (!ok) {
                 set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+                set_bit(MD_RECOVERY_ERROR, &mddev->recovery);
                 md_wakeup_thread(mddev->thread);
                 // stop recovery, signal do_sync ....
         }
@@ -7574,8 +7575,13 @@ void md_do_sync(struct md_thread *thread)
                                         printk(KERN_INFO
                                                "md: checkpointing %s of %s.\n",
                                                desc, mdname(mddev));
-                                        mddev->recovery_cp =
-                                                mddev->curr_resync_completed;
+                                        if (test_bit(MD_RECOVERY_ERROR,
+                                                &mddev->recovery))
+                                                mddev->recovery_cp =
+                                                        mddev->curr_resync_completed;
+                                        else
+                                                mddev->recovery_cp =
+                                                        mddev->curr_resync;
                                 }
                         } else
                                 mddev->recovery_cp = MaxSector;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index af443ab868d..c29e62ebc48 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -307,6 +307,7 @@ struct mddev {
          * REQUEST:  user-space has requested a sync (used with SYNC)
          * CHECK:    user-space request for check-only, no repair
          * RESHAPE:  A reshape is happening
+         * ERROR:    sync-action interrupted because io-error
          *
          * If neither SYNC or RESHAPE are set, then it is a recovery.
          */
@@ -320,6 +321,7 @@ struct mddev {
 #define MD_RECOVERY_CHECK       7
 #define MD_RECOVERY_RESHAPE     8
 #define MD_RECOVERY_FROZEN      9
+#define MD_RECOVERY_ERROR       10
 
         unsigned long                   recovery;
         /* If a RAID personality determines that recovery (of a particular