Merge tag 'md/4.1-rc7-fixes' of git://neil.brown.name/md

Pull three more md fixes from Neil Brown:
 "Hasn't been a good cycle for md has it :-(

  The main issue fixed here is a rare race which can result in two
  reshape threads running at once, which doesn't end well.

  Also a minor issue with a write to a sysfs file returning the wrong
  value.  Backports to 4.0-stable are indicated"

* tag 'md/4.1-rc7-fixes' of git://neil.brown.name/md:
  md: make sure MD_RECOVERY_DONE is clear before starting recovery/resync
  md: Close race when setting 'action' to 'idle'.
  md: don't return 0 from array_state_store

3 files changed, 10 insertions, 6 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 27506302eb7a..4dbed4a67aaf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3834,7 +3834,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
                                 err = -EBUSY;
                 }
                 spin_unlock(&mddev->lock);
-                return err;
+                return err ?: len;
         }
         err = mddev_lock(mddev);
         if (err)
@@ -4217,13 +4217,14 @@ action_store(struct mddev *mddev, const char *page, size_t len)
                         set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 else
                         clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-                flush_workqueue(md_misc_wq);
-                if (mddev->sync_thread) {
-                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-                        if (mddev_lock(mddev) == 0) {
+                if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
+                    mddev_lock(mddev) == 0) {
+                        flush_workqueue(md_misc_wq);
+                        if (mddev->sync_thread) {
+                                set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                                 md_reap_sync_thread(mddev);
-                                mddev_unlock(mddev);
                         }
+                        mddev_unlock(mddev);
                 }
         } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
                    test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
@@ -8261,6 +8262,7 @@ void md_reap_sync_thread(struct mddev *mddev)
         if (mddev_is_clustered(mddev))
                 md_cluster_ops->metadata_update_finish(mddev);
         clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+        clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
         clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
         clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
         clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e793ab6b3570..f55c3f35b746 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4156,6 +4156,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 
         clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
         clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+        clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
         set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
         set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 553d54b87052..b6793d2e051f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7354,6 +7354,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 
         clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
         clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+        clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
         set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
         set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
         mddev->sync_thread = md_register_thread(md_do_sync, mddev,