Merge tag 'md/3.19' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Three fixes for md.

   I did have a largish set of locking changes queued, but late testing
  showed they weren't quite as stable as I thought and while I fixed
  what I found, I decided it safer to delay them a release ...
  particularly as I'll be AFK for a few weeks.  So expect a larger batch
  next time :-)"

* tag 'md/3.19' of git://neil.brown.name/md:
  md: Check MD_RECOVERY_RUNNING as well as ->sync_thread.
  md: fix semicolon.cocci warnings
  md/raid5: fetch_block must fetch all the blocks handle_stripe_dirtying wants.

2 files changed, 32 insertions, 13 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 056ccd28c037..709755fb6d7b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2691,7 +2691,8 @@ static ssize_t new_offset_store(struct md_rdev *rdev,
         if (kstrtoull(buf, 10, &new_offset) < 0)
                 return -EINVAL;
 
-        if (mddev->sync_thread)
+        if (mddev->sync_thread ||
+            test_bit(MD_RECOVERY_RUNNING,&mddev->recovery))
                 return -EBUSY;
         if (new_offset == rdev->data_offset)
                 /* reset is always permitted */
@@ -3268,6 +3269,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
          */
 
         if (mddev->sync_thread ||
+            test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
             mddev->reshape_position != MaxSector ||
             mddev->sysfs_active)
                 return -EBUSY;
@@ -4022,6 +4024,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
                 clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
         if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
+                flush_workqueue(md_misc_wq);
                 if (mddev->sync_thread) {
                         set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                         md_reap_sync_thread(mddev);
@@ -5040,6 +5043,7 @@ static void md_clean(struct mddev *mddev)
 static void __md_stop_writes(struct mddev *mddev)
 {
         set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+        flush_workqueue(md_misc_wq);
         if (mddev->sync_thread) {
                 set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                 md_reap_sync_thread(mddev);
@@ -5100,19 +5104,22 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
                 set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 md_wakeup_thread(mddev->thread);
         }
-        if (mddev->sync_thread) {
+        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
                 set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+        if (mddev->sync_thread)
                 /* Thread might be blocked waiting for metadata update
                  * which will now never happen */
                 wake_up_process(mddev->sync_thread->tsk);
-        }
+
         mddev_unlock(mddev);
-        wait_event(resync_wait, mddev->sync_thread == NULL);
+        wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
+                                          &mddev->recovery));
         mddev_lock_nointr(mddev);
 
         mutex_lock(&mddev->open_mutex);
         if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
             mddev->sync_thread ||
+            test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
             (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
                 printk("md: %s still in use.\n",mdname(mddev));
                 if (did_freeze) {
@@ -5158,20 +5165,24 @@ static int do_md_stop(struct mddev *mddev, int mode,
                 set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 md_wakeup_thread(mddev->thread);
         }
-        if (mddev->sync_thread) {
+        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
                 set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+        if (mddev->sync_thread)
                 /* Thread might be blocked waiting for metadata update
                  * which will now never happen */
                 wake_up_process(mddev->sync_thread->tsk);
-        }
+
         mddev_unlock(mddev);
-        wait_event(resync_wait, mddev->sync_thread == NULL);
+        wait_event(resync_wait, (mddev->sync_thread == NULL &&
+                                 !test_bit(MD_RECOVERY_RUNNING,
+                                           &mddev->recovery)));
         mddev_lock_nointr(mddev);
 
         mutex_lock(&mddev->open_mutex);
         if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
             mddev->sysfs_active ||
             mddev->sync_thread ||
+            test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
             (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
                 printk("md: %s still in use.\n",mdname(mddev));
                 mutex_unlock(&mddev->open_mutex);
@@ -5946,7 +5957,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
          * of each device.  If num_sectors is zero, we find the largest size
          * that fits.
          */
-        if (mddev->sync_thread)
+        if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+            mddev->sync_thread)
                 return -EBUSY;
         if (mddev->ro)
                 return -EROFS;
@@ -5977,7 +5989,9 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
         if (raid_disks <= 0 ||
             (mddev->max_disks && raid_disks >= mddev->max_disks))
                 return -EINVAL;
-        if (mddev->sync_thread || mddev->reshape_position != MaxSector)
+        if (mddev->sync_thread ||
+            test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+            mddev->reshape_position != MaxSector)
                 return -EBUSY;
 
         rdev_for_each(rdev, mddev) {
@@ -6965,7 +6979,7 @@ static unsigned int mdstat_poll(struct file *filp, poll_table *wait)
         int mask;
 
         if (md_unloading)
-                return POLLIN|POLLRDNORM|POLLERR|POLLPRI;;
+                return POLLIN|POLLRDNORM|POLLERR|POLLPRI;
         poll_wait(filp, &md_event_waiters, wait);
 
         /* always allow read */
@@ -7589,6 +7603,7 @@ static void md_start_sync(struct work_struct *ws)
                 clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
                 clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
                 clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+                wake_up(&resync_wait);
                 if (test_and_clear_bit(MD_RECOVERY_RECOVER,
                                        &mddev->recovery))
                         if (mddev->sysfs_action)
@@ -7757,6 +7772,7 @@ void md_check_recovery(struct mddev *mddev)
         not_running:
                 if (!mddev->sync_thread) {
                         clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+                        wake_up(&resync_wait);
                         if (test_and_clear_bit(MD_RECOVERY_RECOVER,
                                                &mddev->recovery))
                                 if (mddev->sysfs_action)
@@ -7775,7 +7791,6 @@ void md_reap_sync_thread(struct mddev *mddev)
 
         /* resync has finished, collect result */
         md_unregister_thread(&mddev->sync_thread);
-        wake_up(&resync_wait);
         if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
             !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
                 /* success...*/
@@ -7803,6 +7818,7 @@ void md_reap_sync_thread(struct mddev *mddev)
         clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
         clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
         clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+        wake_up(&resync_wait);
         /* flag recovery needed just to double check */
         set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
         sysfs_notify_dirent_safe(mddev->sysfs_action);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9c66e5997fc8..c1b0d52bfcb0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2917,8 +2917,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
              (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
               (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
               !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
-             (sh->raid_conf->level == 6 && s->failed && s->to_write &&
-              s->to_write - s->non_overwrite < sh->raid_conf->raid_disks - 2 &&
+             ((sh->raid_conf->level == 6 ||
+               sh->sector >= sh->raid_conf->mddev->recovery_cp)
+              && s->failed && s->to_write &&
+              (s->to_write - s->non_overwrite <
+               sh->raid_conf->raid_disks - sh->raid_conf->max_degraded) &&
               (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
                 /* we would like to get this block, possibly by computing it,
                  * otherwise read it if the backing disk is insync