Merge tag 'md/4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:
 "This update mainly fixes bugs.

   - a raid5 discard related fix from Jes
   - a MD multipath bio clone fix from Ming
   - raid1 error handling deadlock fix from Nate and corresponding
     raid10 fix from myself
   - a raid5 stripe batch fix from Neil
   - a patch from Sebastian to avoid unnecessary uevent
   - several cleanup/debug patches"

* tag 'md/4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md/raid5: Cleanup cpu hotplug notifier
  raid10: include bio_end_io_list in nr_queued to prevent freeze_array hang
  raid1: include bio_end_io_list in nr_queued to prevent freeze_array hang
  md: fix typos for stipe
  md/bitmap: remove redundant return in bitmap_checkpage
  md/raid1: remove unnecessary BUG_ON
  md: multipath: don't hardcopy bio in .make_request path
  md/raid5: output stripe state for debug
  md/raid5: preserve STRIPE_PREREAD_ACTIVE in break_stripe_batch_list
  Update MD git tree URL
  md/bitmap: remove redundant check
  MD: warn for potential deadlock
  md: Drop sending a change uevent when stopping
  RAID5: revert e9e4c377 to fix a livelock
  RAID5: check_reshape() shouldn't call mddev_suspend
  md/raid5: Compare apples to apples (or sectors to sectors)

MAINTAINERS

@@ -10291,7 +10291,7 @@ F:	drivers/media/pci/solo6x10/
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Shaohua Li <shli@kernel.org>
 L:	linux-raid@vger.kernel.org
-T:	git git://neil.brown.name/md
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git
 S:	Supported
 F:	drivers/md/
 F:	include/linux/raid/

drivers/md/bitmap.c

@@ -98,7 +98,6 @@ __acquires(bitmap->lock)
 		   bitmap->bp[page].hijacked) {
 		/* somebody beat us to getting the page */
 		kfree(mappage);
-		return 0;
 	} else {
 
 		/* no page was in place and we have one, so install it */
@@ -510,8 +509,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	sb->chunksize = cpu_to_le32(chunksize);
 
 	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
-	if (!daemon_sleep ||
-	    (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
+	if (!daemon_sleep || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
 		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
 		daemon_sleep = 5 * HZ;
 	}

drivers/md/bitmap.h

@@ -49,8 +49,8 @@
  * When we set a bit, or in the counter (to start a write), if the fields is
  * 0, we first set the disk bit and set the counter to 1.
  *
- * If the counter is 0, the on-disk bit is clear and the stipe is clean
- * Anything that dirties the stipe pushes the counter to 2 (at least)
+ * If the counter is 0, the on-disk bit is clear and the stripe is clean
+ * Anything that dirties the stripe pushes the counter to 2 (at least)
  * and sets the on-disk bit (lazily).
  * If a periodic sweep find the counter at 2, it is decremented to 1.
  * If the sweep find the counter at 1, the on-disk bit is cleared and the

drivers/md/md.c

@@ -305,6 +305,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
  */
 void mddev_suspend(struct mddev *mddev)
 {
+	WARN_ON_ONCE(current == mddev->thread->tsk);
 	if (mddev->suspended++)
 		return;
 	synchronize_rcu();
@@ -5671,7 +5672,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		export_array(mddev);
 
 		md_clean(mddev);
-		kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
 	}

drivers/md/multipath.c

@@ -129,7 +129,9 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	}
 	multipath = conf->multipaths + mp_bh->path;
 
-	mp_bh->bio = *bio;
+	bio_init(&mp_bh->bio);
+	__bio_clone_fast(&mp_bh->bio, bio);
+
 	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
 	mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;

drivers/md/raid1.c

@@ -2274,6 +2274,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 	if (fail) {
 		spin_lock_irq(&conf->device_lock);
 		list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+		conf->nr_queued++;
 		spin_unlock_irq(&conf->device_lock);
 		md_wakeup_thread(conf->mddev->thread);
 	} else {
@@ -2391,8 +2392,10 @@ static void raid1d(struct md_thread *thread)
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
-			list_add(&tmp, &conf->bio_end_io_list);
-			list_del_init(&conf->bio_end_io_list);
+			while (!list_empty(&conf->bio_end_io_list)) {
+				list_move(conf->bio_end_io_list.prev, &tmp);
+				conf->nr_queued--;
+			}
 		}
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		while (!list_empty(&tmp)) {
@@ -2695,7 +2698,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			    !conf->fullsync &&
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
-			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
 			if ((len >> 9) > sync_blocks)
 				len = sync_blocks<<9;
 		}

drivers/md/raid10.c

@@ -2664,6 +2664,7 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 		if (fail) {
 			spin_lock_irq(&conf->device_lock);
 			list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+			conf->nr_queued++;
 			spin_unlock_irq(&conf->device_lock);
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
@@ -2691,8 +2692,10 @@ static void raid10d(struct md_thread *thread)
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
-			list_add(&tmp, &conf->bio_end_io_list);
-			list_del_init(&conf->bio_end_io_list);
+			while (!list_empty(&conf->bio_end_io_list)) {
+				list_move(conf->bio_end_io_list.prev, &tmp);
+				conf->nr_queued--;
+			}
 		}
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		while (!list_empty(&tmp)) {

drivers/md/raid5.c

@@ -340,8 +340,7 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 					 int hash)
 {
 	int size;
-	unsigned long do_wakeup = 0;
-	int i = 0;
+	bool do_wakeup = false;
 	unsigned long flags;
 
 	if (hash == NR_STRIPE_HASH_LOCKS) {
@@ -362,19 +361,15 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 			    !list_empty(list))
 				atomic_dec(&conf->empty_inactive_list_nr);
 			list_splice_tail_init(list, conf->inactive_list + hash);
-			do_wakeup |= 1 << hash;
+			do_wakeup = true;
 			spin_unlock_irqrestore(conf->hash_locks + hash, flags);
 		}
 		size--;
 		hash--;
 	}
 
-	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
-		if (do_wakeup & (1 << i))
-			wake_up(&conf->wait_for_stripe[i]);
-	}
-
 	if (do_wakeup) {
+		wake_up(&conf->wait_for_stripe);
 		if (atomic_read(&conf->active_stripes) == 0)
 			wake_up(&conf->wait_for_quiescent);
 		if (conf->retry_read_aligned)
@@ -687,15 +682,14 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 			if (!sh) {
 				set_bit(R5_INACTIVE_BLOCKED,
 					&conf->cache_state);
-				wait_event_exclusive_cmd(
-					conf->wait_for_stripe[hash],
+				wait_event_lock_irq(
+					conf->wait_for_stripe,
 					!list_empty(conf->inactive_list + hash) &&
 					(atomic_read(&conf->active_stripes)
 					 < (conf->max_nr_stripes * 3 / 4)
 					 || !test_bit(R5_INACTIVE_BLOCKED,
 						      &conf->cache_state)),
-					spin_unlock_irq(conf->hash_locks + hash),
-					spin_lock_irq(conf->hash_locks + hash));
+					*(conf->hash_locks + hash));
 				clear_bit(R5_INACTIVE_BLOCKED,
 					  &conf->cache_state);
 			} else {
@@ -720,9 +714,6 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 		}
 	} while (sh == NULL);
 
-	if (!list_empty(conf->inactive_list + hash))
-		wake_up(&conf->wait_for_stripe[hash]);
-
 	spin_unlock_irq(conf->hash_locks + hash);
 	return sh;
 }
@@ -2089,6 +2080,14 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	unsigned long cpu;
 	int err = 0;
 
+	/*
+	 * Never shrink. And mddev_suspend() could deadlock if this is called
+	 * from raid5d. In that case, scribble_disks and scribble_sectors
+	 * should equal to new_disks and new_sectors
+	 */
+	if (conf->scribble_disks >= new_disks &&
+	    conf->scribble_sectors >= new_sectors)
+		return 0;
 	mddev_suspend(conf->mddev);
 	get_online_cpus();
 	for_each_present_cpu(cpu) {
@@ -2110,6 +2109,10 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 	}
 	put_online_cpus();
 	mddev_resume(conf->mddev);
+	if (!err) {
+		conf->scribble_disks = new_disks;
+		conf->scribble_sectors = new_sectors;
+	}
 	return err;
 }
 
@@ -2190,7 +2193,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	cnt = 0;
 	list_for_each_entry(nsh, &newstripes, lru) {
 		lock_device_hash_lock(conf, hash);
-		wait_event_exclusive_cmd(conf->wait_for_stripe[hash],
+		wait_event_cmd(conf->wait_for_stripe,
 				    !list_empty(conf->inactive_list + hash),
 				    unlock_device_hash_lock(conf, hash),
 				    lock_device_hash_lock(conf, hash));
@@ -4233,10 +4236,9 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 
 		list_del_init(&sh->batch_list);
 
-		WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+		WARN_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
 					  (1 << STRIPE_SYNCING) |
 					  (1 << STRIPE_REPLACED) |
-					  (1 << STRIPE_PREREAD_ACTIVE) |
 					  (1 << STRIPE_DELAYED) |
 					  (1 << STRIPE_BIT_DELAY) |
 					  (1 << STRIPE_FULL_WRITE) |
@@ -4246,11 +4248,14 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
 					  (1 << STRIPE_BATCH_ERR) |
-					  (1 << STRIPE_BITMAP_PENDING)));
-		WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
-					      (1 << STRIPE_REPLACED)));
+					  (1 << STRIPE_BITMAP_PENDING)),
+			"stripe state: %lx\n", sh->state);
+		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+					      (1 << STRIPE_REPLACED)),
+			"head stripe state: %lx\n", head_sh->state);
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+					    (1 << STRIPE_PREREAD_ACTIVE) |
 					    (1 << STRIPE_DEGRADED)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
@@ -6376,6 +6381,8 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 		break;
 	default:
@@ -6413,6 +6420,12 @@ static int raid5_alloc_percpu(struct r5conf *conf)
 	}
 	put_online_cpus();
 
+	if (!err) {
+		conf->scribble_disks = max(conf->raid_disks,
+			conf->previous_raid_disks);
+		conf->scribble_sectors = max(conf->chunk_sectors,
+			conf->prev_chunk_sectors);
+	}
 	return err;
 }
 
@@ -6503,9 +6516,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	seqcount_init(&conf->gen_lock);
 	mutex_init(&conf->cache_size_mutex);
 	init_waitqueue_head(&conf->wait_for_quiescent);
-	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
-		init_waitqueue_head(&conf->wait_for_stripe[i]);
-	}
+	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
 	INIT_LIST_HEAD(&conf->hold_list);
@@ -7014,7 +7025,7 @@ static int raid5_run(struct mddev *mddev)
 		}
 
 		if (discard_supported &&
-		   mddev->queue->limits.max_discard_sectors >= stripe &&
+		    mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
 		    mddev->queue->limits.discard_granularity >= stripe)
 			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
 						mddev->queue);

drivers/md/raid5.h

@@ -510,6 +510,8 @@ struct r5conf {
 					      * conversions
 					      */
 	} __percpu *percpu;
+	int scribble_disks;
+	int scribble_sectors;
 #ifdef CONFIG_HOTPLUG_CPU
 	struct notifier_block	cpu_notify;
 #endif
@@ -522,7 +524,7 @@ struct r5conf {
 	atomic_t		empty_inactive_list_nr;
 	struct llist_head	released_stripes;
 	wait_queue_head_t	wait_for_quiescent;
-	wait_queue_head_t	wait_for_stripe[NR_STRIPE_HASH_LOCKS];
+	wait_queue_head_t	wait_for_stripe;
 	wait_queue_head_t	wait_for_overlap;
 	unsigned long		cache_state;
 #define R5_INACTIVE_BLOCKED	1	/* release of inactive stripes blocked,