Merge tag 'md/4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:
 "This update includes:

   - new AVX512 instruction based raid6 gen/recovery algorithm

   - a couple of md-cluster related bug fixes

   - fix a potential deadlock

   - set nonrotational bit for raid array with SSD

   - set correct max_hw_sectors for raid5/6, which hopefuly can improve
     performance a little bit

   - other minor fixes"

* tag 'md/4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md: set rotational bit
  raid6/test/test.c: bug fix: Specify aligned(alignment) attributes to the char arrays
  raid5: handle register_shrinker failure
  raid5: fix to detect failure of register_shrinker
  md: fix a potential deadlock
  md/bitmap: fix wrong cleanup
  raid5: allow arbitrary max_hw_sectors
  lib/raid6: Add AVX512 optimized xor_syndrome functions
  lib/raid6/test/Makefile: Add avx512 gen_syndrome and recovery functions
  lib/raid6: Add AVX512 optimized recovery functions
  lib/raid6: Add AVX512 optimized gen_syndrome functions
  md-cluster: make resync lock also could be interruptted
  md-cluster: introduce dlm_lock_sync_interruptible to fix tasks hang
  md-cluster: convert the completion to wait queue
  md-cluster: protect md_find_rdev_nr_rcu with rcu lock
  md-cluster: clean related infos of cluster
  md: changes for MD_STILL_CLOSED flag
  md-cluster: remove some unnecessary dlm_unlock_sync
  md-cluster: use FORCEUNLOCK in lockres_free
  md-cluster: call md_kick_rdev_from_array once ack failed

1 files changed, 35 insertions, 9 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 915e84d631a2..eac84d8ff724 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5297,6 +5297,21 @@ int md_run(struct mddev *mddev)
 		return err;
 	}
 	if (mddev->queue) {
+		bool nonrot = true;
+
+		rdev_for_each(rdev, mddev) {
+			if (rdev->raid_disk >= 0 &&
+			    !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+				nonrot = false;
+				break;
+			}
+		}
+		if (mddev->degraded)
+			nonrot = false;
+		if (nonrot)
+			queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
+		else
+			queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = md_congested;
 	}
@@ -5454,12 +5469,14 @@ static void md_clean(struct mddev *mddev)
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->private = NULL;
+	mddev->cluster_info = NULL;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.default_space = 0;
 	mddev->bitmap_info.chunksize = 0;
 	mddev->bitmap_info.daemon_sleep = 0;
 	mddev->bitmap_info.max_write_behind = 0;
+	mddev->bitmap_info.nodes = 0;
 }
 
 static void __md_stop_writes(struct mddev *mddev)
@@ -5573,8 +5590,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	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))) {
+	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
@@ -5636,8 +5652,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	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))) {
+	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
@@ -6101,9 +6116,14 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
 			export_rdev(rdev);
 
 		if (mddev_is_clustered(mddev)) {
-			if (info->state & (1 << MD_DISK_CANDIDATE))
-				md_cluster_ops->new_disk_ack(mddev, (err == 0));
-			else {
+			if (info->state & (1 << MD_DISK_CANDIDATE)) {
+				if (!err) {
+					err = md_cluster_ops->new_disk_ack(mddev,
+						err == 0);
+					if (err)
+						md_kick_rdev_from_array(rdev);
+				}
+			} else {
 				if (err)
 					md_cluster_ops->add_new_disk_cancel(mddev);
 				else
@@ -6821,7 +6841,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EBUSY;
 			goto out;
 		}
-		set_bit(MD_STILL_CLOSED, &mddev->flags);
+		set_bit(MD_CLOSING, &mddev->flags);
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
@@ -7070,9 +7090,13 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	if ((err = mutex_lock_interruptible(&mddev->open_mutex)))
 		goto out;
 
+	if (test_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -ENODEV;
+	}
+
 	err = 0;
 	atomic_inc(&mddev->openers);
-	clear_bit(MD_STILL_CLOSED, &mddev->flags);
 	mutex_unlock(&mddev->open_mutex);
 
 	check_disk_change(bdev);
@@ -8873,7 +8897,9 @@ static void autostart_arrays(int part)
 		list_del(&node_detected_dev->list);
 		dev = node_detected_dev->dev;
 		kfree(node_detected_dev);
+		mutex_unlock(&detected_devices_mutex);
 		rdev = md_import_device(dev,0, 90);
+		mutex_lock(&detected_devices_mutex);
 		if (IS_ERR(rdev))
 			continue;