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

5 files changed, 116 insertions, 47 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 13041ee37ad6..2d826927a3bf 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1903,10 +1903,8 @@ int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	struct bitmap_counts *counts;
 	struct bitmap *bitmap = bitmap_create(mddev, slot);
 
-	if (IS_ERR(bitmap)) {
-		bitmap_free(bitmap);
+	if (IS_ERR(bitmap))
 		return PTR_ERR(bitmap);
-	}
 
 	rv = bitmap_init_from_disk(bitmap, 0);
 	if (rv)
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 34a840d9df76..2b13117fb918 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -10,6 +10,7 @@
 
 
 #include <linux/module.h>
+#include <linux/kthread.h>
 #include <linux/dlm.h>
 #include <linux/sched.h>
 #include <linux/raid/md_p.h>
@@ -25,7 +26,8 @@ struct dlm_lock_resource {
 	struct dlm_lksb lksb;
 	char *name; /* lock name. */
 	uint32_t flags; /* flags to pass to dlm_lock() */
-	struct completion completion; /* completion for synchronized locking */
+	wait_queue_head_t sync_locking; /* wait queue for synchronized locking */
+	bool sync_locking_done;
 	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
 	struct mddev *mddev; /* pointing back to mddev. */
 	int mode;
@@ -118,7 +120,8 @@ static void sync_ast(void *arg)
 	struct dlm_lock_resource *res;
 
 	res = arg;
-	complete(&res->completion);
+	res->sync_locking_done = true;
+	wake_up(&res->sync_locking);
 }
 
 static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
@@ -130,7 +133,8 @@ static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
 			0, sync_ast, res, res->bast);
 	if (ret)
 		return ret;
-	wait_for_completion(&res->completion);
+	wait_event(res->sync_locking, res->sync_locking_done);
+	res->sync_locking_done = false;
 	if (res->lksb.sb_status == 0)
 		res->mode = mode;
 	return res->lksb.sb_status;
@@ -141,6 +145,44 @@ static int dlm_unlock_sync(struct dlm_lock_resource *res)
 	return dlm_lock_sync(res, DLM_LOCK_NL);
 }
 
+/*
+ * An variation of dlm_lock_sync, which make lock request could
+ * be interrupted
+ */
+static int dlm_lock_sync_interruptible(struct dlm_lock_resource *res, int mode,
+				       struct mddev *mddev)
+{
+	int ret = 0;
+
+	ret = dlm_lock(res->ls, mode, &res->lksb,
+			res->flags, res->name, strlen(res->name),
+			0, sync_ast, res, res->bast);
+	if (ret)
+		return ret;
+
+	wait_event(res->sync_locking, res->sync_locking_done
+				      || kthread_should_stop()
+				      || test_bit(MD_CLOSING, &mddev->flags));
+	if (!res->sync_locking_done) {
+		/*
+		 * the convert queue contains the lock request when request is
+		 * interrupted, and sync_ast could still be run, so need to
+		 * cancel the request and reset completion
+		 */
+		ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_CANCEL,
+			&res->lksb, res);
+		res->sync_locking_done = false;
+		if (unlikely(ret != 0))
+			pr_info("failed to cancel previous lock request "
+				 "%s return %d\n", res->name, ret);
+		return -EPERM;
+	} else
+		res->sync_locking_done = false;
+	if (res->lksb.sb_status == 0)
+		res->mode = mode;
+	return res->lksb.sb_status;
+}
+
 static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
 {
@@ -151,7 +193,8 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
 	if (!res)
 		return NULL;
-	init_completion(&res->completion);
+	init_waitqueue_head(&res->sync_locking);
+	res->sync_locking_done = false;
 	res->ls = cinfo->lockspace;
 	res->mddev = mddev;
 	res->mode = DLM_LOCK_IV;
@@ -194,25 +237,21 @@ out_err:
 
 static void lockres_free(struct dlm_lock_resource *res)
 {
-	int ret;
+	int ret = 0;
 
 	if (!res)
 		return;
 
-	/* cancel a lock request or a conversion request that is blocked */
-	res->flags |= DLM_LKF_CANCEL;
-retry:
-	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
-	if (unlikely(ret != 0)) {
-		pr_info("%s: failed to unlock %s return %d\n", __func__, res->name, ret);
-
-		/* if a lock conversion is cancelled, then the lock is put
-		 * back to grant queue, need to ensure it is unlocked */
-		if (ret == -DLM_ECANCEL)
-			goto retry;
-	}
-	res->flags &= ~DLM_LKF_CANCEL;
-	wait_for_completion(&res->completion);
+	/*
+	 * use FORCEUNLOCK flag, so we can unlock even the lock is on the
+	 * waiting or convert queue
+	 */
+	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_FORCEUNLOCK,
+		&res->lksb, res);
+	if (unlikely(ret != 0))
+		pr_err("failed to unlock %s return %d\n", res->name, ret);
+	else
+		wait_event(res->sync_locking, res->sync_locking_done);
 
 	kfree(res->name);
 	kfree(res->lksb.sb_lvbptr);
@@ -279,7 +318,7 @@ static void recover_bitmaps(struct md_thread *thread)
 			goto clear_bit;
 		}
 
-		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
+		ret = dlm_lock_sync_interruptible(bm_lockres, DLM_LOCK_PW, mddev);
 		if (ret) {
 			pr_err("md-cluster: Could not DLM lock %s: %d\n",
 					str, ret);
@@ -288,7 +327,7 @@ static void recover_bitmaps(struct md_thread *thread)
 		ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
 		if (ret) {
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
-			goto dlm_unlock;
+			goto clear_bit;
 		}
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
@@ -300,8 +339,6 @@ static void recover_bitmaps(struct md_thread *thread)
 			    md_wakeup_thread(mddev->thread);
 			}
 		}
-dlm_unlock:
-		dlm_unlock_sync(bm_lockres);
 clear_bit:
 		lockres_free(bm_lockres);
 		clear_bit(slot, &cinfo->recovery_map);
@@ -495,9 +532,10 @@ static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg
 
 static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
-						   le32_to_cpu(msg->raid_slot));
+	struct md_rdev *rdev;
 
+	rcu_read_lock();
+	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
 	if (rdev) {
 		set_bit(ClusterRemove, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -506,18 +544,21 @@ static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
 	else
 		pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
 			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
+	rcu_read_unlock();
 }
 
 static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
-						   le32_to_cpu(msg->raid_slot));
+	struct md_rdev *rdev;
 
+	rcu_read_lock();
+	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
 	if (rdev && test_bit(Faulty, &rdev->flags))
 		clear_bit(Faulty, &rdev->flags);
 	else
 		pr_warn("%s: %d Could not find disk(%d) which is faulty",
 			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
+	rcu_read_unlock();
 }
 
 static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
@@ -770,7 +811,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 			md_check_recovery(mddev);
 		}
 
-		dlm_unlock_sync(bm_lockres);
 		lockres_free(bm_lockres);
 	}
 out:
@@ -1006,7 +1046,7 @@ static void metadata_update_cancel(struct mddev *mddev)
 static int resync_start(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	return dlm_lock_sync(cinfo->resync_lockres, DLM_LOCK_EX);
+	return dlm_lock_sync_interruptible(cinfo->resync_lockres, DLM_LOCK_EX, mddev);
 }
 
 static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
@@ -1186,7 +1226,6 @@ static void unlock_all_bitmaps(struct mddev *mddev)
 	if (cinfo->other_bitmap_lockres) {
 		for (i = 0; i < mddev->bitmap_info.nodes - 1; i++) {
 			if (cinfo->other_bitmap_lockres[i]) {
-				dlm_unlock_sync(cinfo->other_bitmap_lockres[i]);
 				lockres_free(cinfo->other_bitmap_lockres[i]);
 			}
 		}
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;
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 20c667579ede..2b2041773e79 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -201,9 +201,8 @@ struct mddev {
 #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
 #define MD_UPDATE_SB_FLAGS (1 | 2 | 4)	/* If these are set, md_update_sb needed */
 #define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
-#define MD_STILL_CLOSED	4	/* If set, then array has not been opened since
-				 * md_ioctl checked on it.
-				 */
+#define MD_CLOSING	4	/* If set, we are closing the array, do not open
+				 * it then */
 #define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */
 #define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */
 #define MD_RELOAD_SB	7	/* Reload the superblock because another node
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5287e79e0b78..92ac251e91e6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6370,7 +6370,7 @@ static void free_conf(struct r5conf *conf)
 {
 	if (conf->log)
 		r5l_exit_log(conf->log);
-	if (conf->shrinker.seeks)
+	if (conf->shrinker.nr_deferred)
 		unregister_shrinker(&conf->shrinker);
 
 	free_thread_groups(conf);
@@ -6632,7 +6632,12 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf->shrinker.count_objects = raid5_cache_count;
 	conf->shrinker.batch = 128;
 	conf->shrinker.flags = 0;
-	register_shrinker(&conf->shrinker);
+	if (register_shrinker(&conf->shrinker)) {
+		printk(KERN_ERR
+		       "md/raid:%s: couldn't register shrinker.\n",
+		       mdname(mddev));
+		goto abort;
+	}
 
 	sprintf(pers_name, "raid%d", mddev->new_level);
 	conf->thread = md_register_thread(raid5d, mddev, pers_name);
@@ -7028,6 +7033,8 @@ static int raid5_run(struct mddev *mddev)
 		else
 			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
 						mddev->queue);
+
+		blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
 	}
 
 	if (journal_dev) {