mdadm/0006-imsm-update-metadata-correctly-while-raid10-double-d.patch

From d7a1fda2769ba272d89de6caeab35d52b73a9c3c Mon Sep 17 00:00:00 2001
From: Mariusz Tkaczyk <mariusz.tkaczyk@intel.com>
Date: Wed, 17 Oct 2018 12:11:41 +0200
Subject: [PATCH 5/5] imsm: update metadata correctly while raid10 double
 degradation
Git-commit: d7a1fda2769ba272d89de6caeab35d52b73a9c3c
Patch-mainline: mdadm-4.1+
References: jsc#SLE-10078, jsc#SLE-9348

Mdmon calls end_migration() when map state changes from normal to
degraded. It is not valid because in raid 10 double degradation case
mdmon breaks checkpointing but array is still rebuilding.
In this case mdmon has to mark map as degraded and continues marking
recovery checkpoint in metadata. Migration can be finished only if newly
failed device is a rebuilding device.

Add catching double degraded to degraded transition. Migration is
finished but map state doesn't change, array is still degraded.

Update failed_disk_num correctly. If double degradation
happens rebuild will start on the lowest slot, but this variable points
to the first failed slot. If second fail happens while rebuild this
variable shouldn't be updated until rebuild is not finished.

Signed-off-by: Mariusz Tkaczyk <mariusz.tkaczyk@intel.com>
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
Signed-off-by: Coly Li <colyli@suse.de>

---
 super-intel.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/super-intel.c b/super-intel.c
index 6438987b778c..d2035ccd8270 100644
--- a/super-intel.c
+++ b/super-intel.c
@@ -8136,7 +8136,8 @@ static int mark_failure(struct intel_super *super,
 			set_imsm_ord_tbl_ent(map2, slot2,
 					     idx | IMSM_ORD_REBUILD);
 	}
-	if (map->failed_disk_num == 0xff)
+	if (map->failed_disk_num == 0xff ||
+		(!is_rebuilding(dev) && map->failed_disk_num > slot))
 		map->failed_disk_num = slot;
 
 	clear_disk_badblocks(super->bbm_log, ord_to_idx(ord));
@@ -8558,13 +8559,25 @@ static void imsm_set_disk(struct active_array *a, int n, int state)
 			break;
 		}
 		if (is_rebuilding(dev)) {
-			dprintf_cont("while rebuilding.");
+			dprintf_cont("while rebuilding ");
 			if (map->map_state != map_state)  {
-				dprintf_cont(" Map state change");
-				end_migration(dev, super, map_state);
+				dprintf_cont("map state change ");
+				if (n == map->failed_disk_num) {
+					dprintf_cont("end migration");
+					end_migration(dev, super, map_state);
+				} else {
+					dprintf_cont("raid10 double degradation, map state change");
+					map->map_state = map_state;
+				}
 				super->updates_pending++;
-			} else if (!rebuild_done) {
+			} else if (!rebuild_done)
 				break;
+			else if (n == map->failed_disk_num) {
+				/* r10 double degraded to degraded transition */
+				dprintf_cont("raid10 double degradation end migration");
+				end_migration(dev, super, map_state);
+				a->last_checkpoint = 0;
+				super->updates_pending++;
 			}
 
 			/* check if recovery is really finished */
@@ -8575,7 +8588,7 @@ static void imsm_set_disk(struct active_array *a, int n, int state)
 				}
 			if (recovery_not_finished) {
 				dprintf_cont("\n");
-				dprintf("Rebuild has not finished yet, state not changed");
+				dprintf_cont("Rebuild has not finished yet, map state changes only if raid10 double degradation happens");
 				if (a->last_checkpoint < mdi->recovery_start) {
 					a->last_checkpoint =
 						mdi->recovery_start;
-- 
2.14.0.rc0.dirty