Merge tag 'md/4.5' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Mostly clustered-raid1 and raid5 journal updates.  one Y2038 fix and
  other minor stuff.

  One patch removes me from the MAINTAINERS file and adds a record of my
  md maintainership to Credits"

Many thanks to Neil, who has been around for a _looong_ time.

* tag 'md/4.5' of git://neil.brown.name/md: (26 commits)
  md/raid: only permit hot-add of compatible integrity profiles
  Remove myself as MD Maintainer, and add to Credits.
  raid5-cache: handle journal hotadd in quiesce
  MD: add journal with array suspended
  md: set MD_HAS_JOURNAL in correct places
  md: Remove 'ready' field from mddev.
  md: remove unnecesary md_new_event_inintr
  raid5: allow r5l_io_unit allocations to fail
  raid5-cache: use a mempool for the metadata block
  raid5-cache: use a bio_set
  raid5-cache: add journal hot add/remove support
  drivers: md: use ktime_get_real_seconds()
  md: avoid warning for 32-bit sector_t
  raid5-cache: free meta_page earlier
  raid5-cache: simplify r5l_move_io_unit_list
  md: update comment for md_allow_write
  md-cluster: update comments for MD_CLUSTER_SEND_LOCKED_ALREADY
  md-cluster: Protect communication with mutexes
  md-cluster: Defer MD reloading to mddev->thread
  md-cluster: update the documentation
  ...

1 files changed, 26 insertions, 10 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 704ef7fcfbf8..a086014dcd49 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -772,8 +772,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 	int hash;
 	int dd_idx;
 
-	if (!stripe_can_batch(sh))
-		return;
 	/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
 	tmp_sec = sh->sector;
 	if (!sector_div(tmp_sec, conf->chunk_sectors))
@@ -7141,14 +7139,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct disk_info *p = conf->disks + number;
 
 	print_raid5_conf(conf);
-	if (test_bit(Journal, &rdev->flags)) {
+	if (test_bit(Journal, &rdev->flags) && conf->log) {
+		struct r5l_log *log;
 		/*
-		 * journal disk is not removable, but we need give a chance to
-		 * update superblock of other disks. Otherwise journal disk
-		 * will be considered as 'fresh'
+		 * we can't wait pending write here, as this is called in
+		 * raid5d, wait will deadlock.
 		 */
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
-		return -EINVAL;
+		if (atomic_read(&mddev->writes_pending))
+			return -EBUSY;
+		log = conf->log;
+		conf->log = NULL;
+		synchronize_rcu();
+		r5l_exit_log(log);
+		return 0;
 	}
 	if (rdev == p->rdev)
 		rdevp = &p->rdev;
@@ -7212,8 +7215,21 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int first = 0;
 	int last = conf->raid_disks - 1;
 
-	if (test_bit(Journal, &rdev->flags))
-		return -EINVAL;
+	if (test_bit(Journal, &rdev->flags)) {
+		char b[BDEVNAME_SIZE];
+		if (conf->log)
+			return -EBUSY;
+
+		rdev->raid_disk = 0;
+		/*
+		 * The array is in readonly mode if journal is missing, so no
+		 * write requests running. We should be safe
+		 */
+		r5l_init_log(conf, rdev);
+		printk(KERN_INFO"md/raid:%s: using device %s as journal\n",
+		       mdname(mddev), bdevname(rdev->bdev, b));
+		return 0;
+	}
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;