19 files changed, 126 insertions, 58 deletions

diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 646fe85261c1..18526d44688d 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -11,6 +11,7 @@
 #include "bset.h"
 
 #include <linux/console.h>
+#include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/prefetch.h>
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index a43eedd5804d..450d0e848ae4 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -32,6 +32,9 @@
 #include <linux/prefetch.h>
 #include <linux/random.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/clock.h>
+#include <linux/rculist.h>
+
 #include <trace/events/bcache.h>
 
 /*
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 9b2fe2d3e3a9..1ec84ca81146 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -3,6 +3,7 @@
 
 #include <linux/llist.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/workqueue.h>
 
 /*
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index b3ff57d61dde..f90f13616980 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -13,6 +13,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/sort.h>
+#include <linux/sched/clock.h>
 
 static const char * const cache_replacement_policies[] = {
 	"lru",
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index dde6172f3f10..8c3a938f4bf0 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/types.h>
+#include <linux/sched/clock.h>
 
 #include "util.h"
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cf2cbc211d83..5d13930f0f22 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -4,8 +4,8 @@
 
 #include <linux/blkdev.h>
 #include <linux/errno.h>
-#include <linux/blkdev.h>
 #include <linux/kernel.h>
+#include <linux/sched/clock.h>
 #include <linux/llist.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 69e1ae59cab8..6ac2e48b9235 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -13,6 +13,7 @@
 
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/sched/clock.h>
 #include <trace/events/bcache.h>
 
 /* Rate limiting */
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index d36d427a9efb..df4859f6ac6a 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -11,6 +11,7 @@
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/jiffies.h>
 #include <linux/vmalloc.h>
 #include <linux/shrinker.h>
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1cb2ca9dfae3..389a3637ffcc 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1536,7 +1536,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	down_read(&key->sem);
 
-	ukp = user_key_payload(key);
+	ukp = user_key_payload_locked(key);
 	if (!ukp) {
 		up_read(&key->sem);
 		key_put(key);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a5a9b17f0f7f..4da6fc6b1ffd 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/miscdevice.h>
+#include <linux/sched/mm.h>
 #include <linux/init.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5c9e95d66f3b..f8564d63982f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -101,6 +101,8 @@ struct raid_dev {
 #define CTR_FLAG_RAID10_USE_NEAR_SETS	(1 << __CTR_FLAG_RAID10_USE_NEAR_SETS)
 #define CTR_FLAG_JOURNAL_DEV		(1 << __CTR_FLAG_JOURNAL_DEV)
 
+#define RESUME_STAY_FROZEN_FLAGS (CTR_FLAG_DELTA_DISKS | CTR_FLAG_DATA_OFFSET)
+
 /*
  * Definitions of various constructor flags to
  * be used in checks of valid / invalid flags
@@ -3462,9 +3464,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv)
 	else if (!strcasecmp(argv[0], "recover"))
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	else {
-		if (!strcasecmp(argv[0], "check"))
+		if (!strcasecmp(argv[0], "check")) {
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		else if (!strcasecmp(argv[0], "repair")) {
+			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		} else if (!strcasecmp(argv[0], "repair")) {
 			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		} else
@@ -3771,7 +3775,15 @@ static void raid_resume(struct dm_target *ti)
 	mddev->ro = 0;
 	mddev->in_sync = 0;
 
-	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	/*
+	 * Keep the RAID set frozen if reshape/rebuild flags are set.
+	 * The RAID set is unfrozen once the next table load/resume,
+	 * which clears the reshape/rebuild flags, occurs.
+	 * This ensures that the constructor for the inactive table
+	 * retrieves an up-to-date reshape_position.
+	 */
+	if (!(rs->ctr_flags & RESUME_STAY_FROZEN_FLAGS))
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
 	if (mddev->suspended)
 		mddev_resume(mddev);
@@ -3779,7 +3791,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 10, 0},
+	.version = {1, 10, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9f37d7fc2786..dfb75979e455 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched/signal.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
 #include <linux/mempool.h>
@@ -988,26 +989,29 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
 	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
 	struct bio_list list;
 	struct bio *bio;
+	int i;
 
 	INIT_LIST_HEAD(&o->cb.list);
 
 	if (unlikely(!current->bio_list))
 		return;
 
-	list = *current->bio_list;
-	bio_list_init(current->bio_list);
-
-	while ((bio = bio_list_pop(&list))) {
-		struct bio_set *bs = bio->bi_pool;
-		if (unlikely(!bs) || bs == fs_bio_set) {
-			bio_list_add(current->bio_list, bio);
-			continue;
+	for (i = 0; i < 2; i++) {
+		list = current->bio_list[i];
+		bio_list_init(&current->bio_list[i]);
+
+		while ((bio = bio_list_pop(&list))) {
+			struct bio_set *bs = bio->bi_pool;
+			if (unlikely(!bs) || bs == fs_bio_set) {
+				bio_list_add(&current->bio_list[i], bio);
+				continue;
+			}
+
+			spin_lock(&bs->rescue_lock);
+			bio_list_add(&bs->rescue_list, bio);
+			queue_work(bs->rescue_workqueue, &bs->rescue_work);
+			spin_unlock(&bs->rescue_lock);
 		}
-
-		spin_lock(&bs->rescue_lock);
-		bio_list_add(&bs->rescue_list, bio);
-		queue_work(bs->rescue_workqueue, &bs->rescue_work);
-		spin_unlock(&bs->rescue_lock);
 	}
 }
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 2b13117fb918..321ecac23027 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -777,7 +777,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 		bm_lockres->flags |= DLM_LKF_NOQUEUE;
 		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
 		if (ret == -EAGAIN) {
-			memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE);
 			s = read_resync_info(mddev, bm_lockres);
 			if (s) {
 				pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n",
@@ -974,6 +973,7 @@ static int leave(struct mddev *mddev)
 	lockres_free(cinfo->bitmap_lockres);
 	unlock_all_bitmaps(mddev);
 	dlm_release_lockspace(cinfo->lockspace, 2);
+	kfree(cinfo);
 	return 0;
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 985374f20e2e..f6ae1d67bcd0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -44,6 +44,7 @@
 
 */
 
+#include <linux/sched/signal.h>
 #include <linux/kthread.h>
 #include <linux/blkdev.h>
 #include <linux/badblocks.h>
@@ -439,14 +440,6 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 }
 EXPORT_SYMBOL(md_flush_request);
 
-void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
-{
-	struct mddev *mddev = cb->data;
-	md_wakeup_thread(mddev->thread);
-	kfree(cb);
-}
-EXPORT_SYMBOL(md_unplug);
-
 static inline struct mddev *mddev_get(struct mddev *mddev)
 {
 	atomic_inc(&mddev->active);
@@ -1886,7 +1879,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	}
 	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
-	sb->super_offset = rdev->sb_start;
+	sb->super_offset = cpu_to_le64(rdev->sb_start);
 	sb->sb_csum = calc_sb_1_csum(sb);
 	do {
 		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
@@ -2294,7 +2287,7 @@ static bool does_sb_need_changing(struct mddev *mddev)
 	/* Check if any mddev parameters have changed */
 	if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
 	    (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
-	    (mddev->layout != le64_to_cpu(sb->layout)) ||
+	    (mddev->layout != le32_to_cpu(sb->layout)) ||
 	    (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
 	    (mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
 		return true;
@@ -6457,11 +6450,10 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->layout        = info->layout;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
-	mddev->max_disks     = MD_SB_DISKS;
-
 	if (mddev->persistent) {
-		mddev->flags         = 0;
-		mddev->sb_flags         = 0;
+		mddev->max_disks = MD_SB_DISKS;
+		mddev->flags = 0;
+		mddev->sb_flags = 0;
 	}
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 
@@ -6532,8 +6524,12 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 			return -ENOSPC;
 	}
 	rv = mddev->pers->resize(mddev, num_sectors);
-	if (!rv)
-		revalidate_disk(mddev->gendisk);
+	if (!rv) {
+		if (mddev->queue) {
+			set_capacity(mddev->gendisk, mddev->array_sectors);
+			revalidate_disk(mddev->gendisk);
+		}
+	}
 	return rv;
 }
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b8859cbf84b6..dde8ecb760c8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -676,16 +676,10 @@ extern void mddev_resume(struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   struct mddev *mddev);
 
-extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
 extern void md_kick_rdev_from_array(struct md_rdev * rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
-static inline int mddev_check_plugged(struct mddev *mddev)
-{
-	return !!blk_check_plugged(md_unplug, mddev,
-				   sizeof(struct blk_plug_cb));
-}
 
 static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 {
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 0863905dee02..8589e0a14068 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -13,6 +13,7 @@
 #include <linux/rwsem.h>
 #include <linux/device-mapper.h>
 #include <linux/stacktrace.h>
+#include <linux/sched/task.h>
 
 #define DM_MSG_PREFIX "block manager"
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7453d94eeed7..a34f58772022 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -37,7 +37,10 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/ratelimit.h>
+#include <linux/sched/signal.h>
+
 #include <trace/events/block.h>
+
 #include "md.h"
 #include "raid1.h"
 #include "bitmap.h"
@@ -1024,7 +1027,7 @@ static int get_unqueued_pending(struct r1conf *conf)
 static void freeze_array(struct r1conf *conf, int extra)
 {
 	/* Stop sync I/O and normal I/O and wait for everything to
-	 * go quite.
+	 * go quiet.
 	 * This is called in two situations:
 	 * 1) management command handlers (reshape, remove disk, quiesce).
 	 * 2) one normal I/O request failed.
@@ -1584,9 +1587,30 @@ static void raid1_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
-		if (bio_data_dir(split) == READ)
+		if (bio_data_dir(split) == READ) {
 			raid1_read_request(mddev, split);
-		else
+
+			/*
+			 * If a bio is splitted, the first part of bio will
+			 * pass barrier but the bio is queued in
+			 * current->bio_list (see generic_make_request). If
+			 * there is a raise_barrier() called here, the second
+			 * part of bio can't pass barrier. But since the first
+			 * part bio isn't dispatched to underlaying disks yet,
+			 * the barrier is never released, hence raise_barrier
+			 * will alays wait. We have a deadlock.
+			 * Note, this only happens in read path. For write
+			 * path, the first part of bio is dispatched in a
+			 * schedule() call (because of blk plug) or offloaded
+			 * to raid10d.
+			 * Quitting from the function immediately can change
+			 * the bio order queued in bio_list and avoid the deadlock.
+			 */
+			if (split != bio) {
+				generic_make_request(bio);
+				break;
+			}
+		} else
 			raid1_write_request(mddev, split);
 	} while (split != bio);
 }
@@ -3243,8 +3267,6 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, newsize);
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {
 		mddev->recovery_cp = mddev->dev_sectors;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 063c43d83b72..e89a8d78a9ed 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -974,7 +974,8 @@ static void wait_barrier(struct r10conf *conf)
 				    !conf->barrier ||
 				    (atomic_read(&conf->nr_pending) &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 		if (!conf->nr_waiting)
@@ -1477,11 +1478,24 @@ retry_write:
 			mbio->bi_bdev = (void*)rdev;
 
 			atomic_inc(&r10_bio->remaining);
+
+			cb = blk_check_plugged(raid10_unplug, mddev,
+					       sizeof(*plug));
+			if (cb)
+				plug = container_of(cb, struct raid10_plug_cb,
+						    cb);
+			else
+				plug = NULL;
 			spin_lock_irqsave(&conf->device_lock, flags);
-			bio_list_add(&conf->pending_bio_list, mbio);
-			conf->pending_count++;
+			if (plug) {
+				bio_list_add(&plug->pending, mbio);
+				plug->pending_cnt++;
+			} else {
+				bio_list_add(&conf->pending_bio_list, mbio);
+				conf->pending_count++;
+			}
 			spin_unlock_irqrestore(&conf->device_lock, flags);
-			if (!mddev_check_plugged(mddev))
+			if (!plug)
 				md_wakeup_thread(mddev->thread);
 		}
 	}
@@ -1571,7 +1585,25 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
 		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
 	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
@@ -3943,10 +3975,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, size);
-	if (mddev->queue) {
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
-	}
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > oldsize) {
 		mddev->recovery_cp = oldsize;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2ce23b01dbb2..ed5cd705b985 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -55,6 +55,8 @@
 #include <linux/ratelimit.h>
 #include <linux/nodemask.h>
 #include <linux/flex_array.h>
+#include <linux/sched/signal.h>
+
 #include <trace/events/block.h>
 
 #include "md.h"
@@ -1399,7 +1401,8 @@ static int set_syndrome_sources(struct page **srcs,
 		     (test_bit(R5_Wantdrain, &dev->flags) ||
 		      test_bit(R5_InJournal, &dev->flags))) ||
 		    (srctype == SYNDROME_SRC_WRITTEN &&
-		     dev->written)) {
+		     (dev->written ||
+		      test_bit(R5_InJournal, &dev->flags)))) {
 			if (test_bit(R5_InJournal, &dev->flags))
 				srcs[slot] = sh->dev[i].orig_page;
 			else
@@ -7603,8 +7606,6 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 			return ret;
 	}
 	md_set_array_sectors(mddev, newsize);
-	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp > mddev->dev_sectors) {
 		mddev->recovery_cp = mddev->dev_sectors;