summary refs log tree commit diff
path: root/drivers/md/md-cluster.c
diff options
context:
space:
mode:
authorGuoqing Jiang <gqjiang@suse.com>2018-07-02 16:26:24 +0800
committerShaohua Li <shli@fb.com>2018-07-05 11:17:01 -0700
commit010228e4a932ca1e8365e3b58c8e1e44c16ff793 (patch)
treef8d8ae841370481e52b254a50f54b23b44157cb1 /drivers/md/md-cluster.c
parent06c85639897cf3ea6a11c5cb6929fb0d9d7efea5 (diff)
downloadlinux-010228e4a932ca1e8365e3b58c8e1e44c16ff793.tar.gz
md-cluster: clear another node's suspend_area after the copy is finished
When one node leaves cluster or stops the resyncing
(resync or recovery) array, then other nodes need to
call recover_bitmaps to continue the unfinished task.

But we need to clear suspend_area later after other
nodes copy the resync information to their bitmap
(by call bitmap_copy_from_slot). Otherwise, all nodes
could write to the suspend_area even the suspend_area
is not handled by any node, because area_resyncing
returns 0 at the beginning of raid1_write_request.
Which means one node could write suspend_area while
another node is resyncing the same area, then data
could be inconsistent.

So let's clear suspend_area later to avoid above issue
with the protection of bm lock. Also it is straightforward
to clear suspend_area after nodes have copied the resync
info to bitmap.

Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Diffstat (limited to 'drivers/md/md-cluster.c')
-rw-r--r--drivers/md/md-cluster.c19
1 files changed, 10 insertions, 9 deletions
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 021cbf9ef1bf..1ac945f7a3c2 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -304,15 +304,6 @@ static void recover_bitmaps(struct md_thread *thread)
 	while (cinfo->recovery_map) {
 		slot = fls64((u64)cinfo->recovery_map) - 1;
 
-		/* Clear suspend_area associated with the bitmap */
-		spin_lock_irq(&cinfo->suspend_lock);
-		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
-			if (slot == s->slot) {
-				list_del(&s->list);
-				kfree(s);
-			}
-		spin_unlock_irq(&cinfo->suspend_lock);
-
 		snprintf(str, 64, "bitmap%04d", slot);
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
@@ -331,6 +322,16 @@ static void recover_bitmaps(struct md_thread *thread)
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
 		}
+
+		/* Clear suspend_area associated with the bitmap */
+		spin_lock_irq(&cinfo->suspend_lock);
+		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
+			if (slot == s->slot) {
+				list_del(&s->list);
+				kfree(s);
+			}
+		spin_unlock_irq(&cinfo->suspend_lock);
+
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
 				mddev->recovery_cp = lo;