Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

13 files changed, 259 insertions, 89 deletions

diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 73f5319295bc..c12cd809ab19 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -105,8 +105,14 @@ struct closure_syncer {
 
 static void closure_sync_fn(struct closure *cl)
 {
-	cl->s->done = 1;
-	wake_up_process(cl->s->task);
+	struct closure_syncer *s = cl->s;
+	struct task_struct *p;
+
+	rcu_read_lock();
+	p = READ_ONCE(s->task);
+	s->done = 1;
+	wake_up_process(p);
+	rcu_read_unlock();
 }
 
 void __sched __closure_sync(struct closure *cl)
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 8b123be05254..336f43910383 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -178,10 +178,9 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
 	while (size) {
 		struct keybuf_key *w;
 		unsigned int bytes = min(i->bytes, size);
-		int err = copy_to_user(buf, i->buf, bytes);
 
-		if (err)
-			return err;
+		if (copy_to_user(buf, i->buf, bytes))
+			return -EFAULT;
 
 		ret	 += bytes;
 		buf	 += bytes;
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index e2059af90791..627dcea0f5b6 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -964,6 +964,7 @@ KTYPE(bch_cache_set_internal);
 
 static int __bch_cache_cmp(const void *l, const void *r)
 {
+	cond_resched();
 	return *((uint16_t *)r) - *((uint16_t *)l);
 }
 
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index c9e44ac1f9a6..3f8577e2c13b 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -408,6 +408,7 @@ static int map_request(struct dm_rq_target_io *tio)
 		ret = dm_dispatch_clone_request(clone, rq);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
 			blk_rq_unprep_clone(clone);
+			blk_mq_cleanup_rq(clone);
 			tio->ti->type->release_clone_rq(clone, &tio->info);
 			tio->clone = NULL;
 			return DM_MAPIO_REQUEUE;
@@ -562,7 +563,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
 	if (err)
 		goto out_kfree_tag_set;
 
-	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
+	q = blk_mq_init_allocated_queue(md->tag_set, md->queue, true);
 	if (IS_ERR(q)) {
 		err = PTR_ERR(q);
 		goto out_tag_set;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 7354466ddc90..c766c559d36d 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -258,6 +258,11 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		     bio_sector < start_sector))
 		goto out_of_bounds;
 
+	if (unlikely(is_mddev_broken(tmp_dev->rdev, "linear"))) {
+		bio_io_error(bio);
+		return true;
+	}
+
 	if (unlikely(bio_end_sector(bio) > end_sector)) {
 		/* This bio crosses a device boundary, so we have to split it */
 		struct bio *split = bio_split(bio, end_sector - bio_sector,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 24638ccedce4..1be7abeb24fd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -376,6 +376,11 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 
+	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
+		bio_io_error(bio);
+		return BLK_QC_T_NONE;
+	}
+
 	blk_queue_split(q, &bio);
 
 	if (mddev == NULL || mddev->pers == NULL) {
@@ -1232,6 +1237,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_layout = mddev->layout;
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
+		if (mddev->level == 0)
+			mddev->layout = -1;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
@@ -1647,6 +1654,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
 	}
 
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
+	    sb->level != 0)
+		return -EINVAL;
+
 	if (!refdev) {
 		ret = 1;
 	} else {
@@ -1757,6 +1768,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 
+		if (mddev->level == 0 &&
+		    !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
+			mddev->layout = -1;
+
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
 
@@ -1826,8 +1841,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 				if (!(le32_to_cpu(sb->feature_map) &
 				      MD_FEATURE_RECOVERY_BITMAP))
 					rdev->saved_raid_disk = -1;
-			} else
-				set_bit(In_sync, &rdev->flags);
+			} else {
+				/*
+				 * If the array is FROZEN, then the device can't
+				 * be in_sync with rest of array.
+				 */
+				if (!test_bit(MD_RECOVERY_FROZEN,
+					      &mddev->recovery))
+					set_bit(In_sync, &rdev->flags);
+			}
 			rdev->raid_disk = role;
 			break;
 		}
@@ -3664,11 +3686,7 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
 		return -EINVAL;
 	if (decimals < 0)
 		decimals = 0;
-	while (decimals < scale) {
-		result *= 10;
-		decimals ++;
-	}
-	*res = result;
+	*res = result * int_pow(10, scale - decimals);
 	return 0;
 }
 
@@ -4155,12 +4173,17 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
  * active-idle
  *     like active, but no writes have been seen for a while (100msec).
  *
+ * broken
+ *     RAID0/LINEAR-only: same as clean, but array is missing a member.
+ *     It's useful because RAID0/LINEAR mounted-arrays aren't stopped
+ *     when a member is gone, so this state will at least alert the
+ *     user that something is wrong.
  */
 enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
-		   write_pending, active_idle, bad_word};
+		   write_pending, active_idle, broken, bad_word};
 static char *array_states[] = {
 	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
-	"write-pending", "active-idle", NULL };
+	"write-pending", "active-idle", "broken", NULL };
 
 static int match_word(const char *word, char **list)
 {
@@ -4176,7 +4199,7 @@ array_state_show(struct mddev *mddev, char *page)
 {
 	enum array_state st = inactive;
 
-	if (mddev->pers)
+	if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) {
 		switch(mddev->ro) {
 		case 1:
 			st = readonly;
@@ -4196,7 +4219,10 @@ array_state_show(struct mddev *mddev, char *page)
 				st = active;
 			spin_unlock(&mddev->lock);
 		}
-	else {
+
+		if (test_bit(MD_BROKEN, &mddev->flags) && st == clean)
+			st = broken;
+	} else {
 		if (list_empty(&mddev->disks) &&
 		    mddev->raid_disks == 0 &&
 		    mddev->dev_sectors == 0)
@@ -4310,6 +4336,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		break;
 	case write_pending:
 	case active_idle:
+	case broken:
 		/* these cannot be set */
 		break;
 	}
@@ -5182,6 +5209,34 @@ static struct md_sysfs_entry md_consistency_policy =
 __ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
        consistency_policy_store);
 
+static ssize_t fail_last_dev_show(struct mddev *mddev, char *page)
+{
+	return sprintf(page, "%d\n", mddev->fail_last_dev);
+}
+
+/*
+ * Setting fail_last_dev to true to allow last device to be forcibly removed
+ * from RAID1/RAID10.
+ */
+static ssize_t
+fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	int ret;
+	bool value;
+
+	ret = kstrtobool(buf, &value);
+	if (ret)
+		return ret;
+
+	if (value != mddev->fail_last_dev)
+		mddev->fail_last_dev = value;
+
+	return len;
+}
+static struct md_sysfs_entry md_fail_last_dev =
+__ATTR(fail_last_dev, S_IRUGO | S_IWUSR, fail_last_dev_show,
+       fail_last_dev_store);
+
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_layout.attr,
@@ -5198,6 +5253,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_array_size.attr,
 	&max_corr_read_errors.attr,
 	&md_consistency_policy.attr,
+	&md_fail_last_dev.attr,
 	NULL,
 };
 
@@ -5744,9 +5800,6 @@ int md_run(struct mddev *mddev)
 		md_update_sb(mddev, 0);
 
 	md_new_event(mddev);
-	sysfs_notify_dirent_safe(mddev->sysfs_state);
-	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
 
 bitmap_abort:
@@ -5767,6 +5820,7 @@ static int do_md_run(struct mddev *mddev)
 {
 	int err;
 
+	set_bit(MD_NOT_READY, &mddev->flags);
 	err = md_run(mddev);
 	if (err)
 		goto out;
@@ -5787,9 +5841,14 @@ static int do_md_run(struct mddev *mddev)
 
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
+	clear_bit(MD_NOT_READY, &mddev->flags);
 	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+	sysfs_notify(&mddev->kobj, NULL, "degraded");
 out:
+	clear_bit(MD_NOT_READY, &mddev->flags);
 	return err;
 }
 
@@ -6849,6 +6908,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->external	     = 0;
 
 	mddev->layout        = info->layout;
+	if (mddev->level == 0)
+		/* Cannot trust RAID0 layout info here */
+		mddev->layout = -1;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
 	if (mddev->persistent) {
@@ -8900,6 +8962,7 @@ void md_check_recovery(struct mddev *mddev)
 
 	if (mddev_trylock(mddev)) {
 		int spares = 0;
+		bool try_set_sync = mddev->safemode != 0;
 
 		if (!mddev->external && mddev->safemode == 1)
 			mddev->safemode = 0;
@@ -8945,7 +9008,7 @@ void md_check_recovery(struct mddev *mddev)
 			}
 		}
 
-		if (!mddev->external && !mddev->in_sync) {
+		if (try_set_sync && !mddev->external && !mddev->in_sync) {
 			spin_lock(&mddev->lock);
 			set_in_sync(mddev);
 			spin_unlock(&mddev->lock);
@@ -9043,7 +9106,8 @@ void md_reap_sync_thread(struct mddev *mddev)
 	/* resync has finished, collect result */
 	md_unregister_thread(&mddev->sync_thread);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    mddev->degraded != mddev->raid_disks) {
 		/* success...*/
 		/* activate any spares */
 		if (mddev->pers->spare_active(mddev)) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 10f98200e2f8..c5e3ff398b59 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -248,6 +248,12 @@ enum mddev_flags {
 	MD_UPDATING_SB,		/* md_check_recovery is updating the metadata
 				 * without explicitly holding reconfig_mutex.
 				 */
+	MD_NOT_READY,		/* do_md_run() is active, so 'array_state'
+				 * must not report that array is ready yet
+				 */
+	MD_BROKEN,              /* This is used in RAID-0/LINEAR only, to stop
+				 * I/O in case an array member is gone/failed.
+				 */
 };
 
 enum mddev_sb_flags {
@@ -487,6 +493,7 @@ struct mddev {
 	unsigned int			good_device_nr;	/* good device num within cluster raid */
 
 	bool	has_superblocks:1;
+	bool	fail_last_dev:1;
 };
 
 enum recovery_flags {
@@ -735,6 +742,19 @@ extern void mddev_create_wb_pool(struct mddev *mddev, struct md_rdev *rdev,
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
 struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
 
+static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type)
+{
+	int flags = rdev->bdev->bd_disk->flags;
+
+	if (!(flags & GENHD_FL_UP)) {
+		if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags))
+			pr_warn("md: %s: %s array has a missing/failed member\n",
+				mdname(rdev->mddev), md_type);
+		return true;
+	}
+	return false;
+}
+
 static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 {
 	int faulty = test_bit(Faulty, &rdev->flags);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index bf5cf184a260..f61693e59684 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -19,6 +19,9 @@
 #include "raid0.h"
 #include "raid5.h"
 
+static int default_layout = 0;
+module_param(default_layout, int, 0644);
+
 #define UNSUPPORTED_MDDEV_FLAGS		\
 	((1L << MD_HAS_JOURNAL) |	\
 	 (1L << MD_JOURNAL_CLEAN) |	\
@@ -139,6 +142,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	}
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
+
+	if (conf->nr_strip_zones == 1) {
+		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
+	} else if (default_layout == RAID0_ORIG_LAYOUT ||
+		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = default_layout;
+	} else {
+		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+		       mdname(mddev));
+		pr_err("md/raid0: please set raid.default_layout to 1 or 2\n");
+		err = -ENOTSUPP;
+		goto abort;
+	}
 	/*
 	 * now since we have the hard sector sizes, we can make sure
 	 * chunk size is a multiple of that sector size
@@ -547,10 +566,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
+	struct r0conf *conf = mddev->private;
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
 	sector_t bio_sector;
 	sector_t sector;
+	sector_t orig_sector;
 	unsigned chunk_sects;
 	unsigned sectors;
 
@@ -584,8 +605,26 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		bio = split;
 	}
 
+	orig_sector = sector;
 	zone = find_zone(mddev->private, &sector);
-	tmp_dev = map_sector(mddev, zone, sector, &sector);
+	switch (conf->layout) {
+	case RAID0_ORIG_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, orig_sector, &sector);
+		break;
+	case RAID0_ALT_MULTIZONE_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, sector, &sector);
+		break;
+	default:
+		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		bio_io_error(bio);
+		return true;
+	}
+
+	if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) {
+		bio_io_error(bio);
+		return true;
+	}
+
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h
index 540e65d92642..3816e5477db1 100644
--- a/drivers/md/raid0.h
+++ b/drivers/md/raid0.h
@@ -8,11 +8,25 @@ struct strip_zone {
 	int	 nb_dev;	/* # of devices attached to the zone */
 };
 
+/* Linux 3.14 (20d0189b101) made an unintended change to
+ * the RAID0 layout for multi-zone arrays (where devices aren't all
+ * the same size.
+ * RAID0_ORIG_LAYOUT restores the original layout
+ * RAID0_ALT_MULTIZONE_LAYOUT uses the altered layout
+ * The layouts are identical when there is only one zone (all
+ * devices the same size).
+ */
+
+enum r0layout {
+	RAID0_ORIG_LAYOUT = 1,
+	RAID0_ALT_MULTIZONE_LAYOUT = 2,
+};
 struct r0conf {
 	struct strip_zone	*strip_zone;
 	struct md_rdev		**devlist; /* lists of rdevs, pointed to
 					    * by strip_zone->dev */
 	int			nr_strip_zones;
+	enum r0layout		layout;
 };
 
 #endif
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 34e26834ad28..0466ee2453b4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -447,19 +447,21 @@ static void raid1_end_write_request(struct bio *bio)
 		    /* We never try FailFast to WriteMostly devices */
 		    !test_bit(WriteMostly, &rdev->flags)) {
 			md_error(r1_bio->mddev, rdev);
-			if (!test_bit(Faulty, &rdev->flags))
-				/* This is the only remaining device,
-				 * We need to retry the write without
-				 * FailFast
-				 */
-				set_bit(R1BIO_WriteError, &r1_bio->state);
-			else {
-				/* Finished with this branch */
-				r1_bio->bios[mirror] = NULL;
-				to_put = bio;
-			}
-		} else
+		}
+
+		/*
+		 * When the device is faulty, it is not necessary to
+		 * handle write error.
+		 * For failfast, this is the only remaining device,
+		 * We need to retry the write without FailFast.
+		 */
+		if (!test_bit(Faulty, &rdev->flags))
 			set_bit(R1BIO_WriteError, &r1_bio->state);
+		else {
+			/* Finished with this branch */
+			r1_bio->bios[mirror] = NULL;
+			to_put = bio;
+		}
 	} else {
 		/*
 		 * Set R1BIO_Uptodate in our master bio, so that we
@@ -872,8 +874,11 @@ static void flush_pending_writes(struct r1conf *conf)
  * backgroup IO calls must call raise_barrier.  Once that returns
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
+ *
+ * If resync/recovery is interrupted, returns -EINTR;
+ * Otherwise, returns 0.
  */
-static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static int raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
 	int idx = sector_to_idx(sector_nr);
 
@@ -1612,12 +1617,12 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks, ignore the error, let the
-	 * next level up know.
+	 * else if it is the last working disks with "fail_last_dev == false",
+	 * ignore the error, let the next level up know.
 	 * else mark the drive as failed
 	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags)
+	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
 	    && (conf->raid_disks - mddev->degraded) == 1) {
 		/*
 		 * Don't fail the drive, act as though we were just a
@@ -1901,6 +1906,22 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
 	} while (sectors_to_go > 0);
 }
 
+static void put_sync_write_buf(struct r1bio *r1_bio, int uptodate)
+{
+	if (atomic_dec_and_test(&r1_bio->remaining)) {
+		struct mddev *mddev = r1_bio->mddev;
+		int s = r1_bio->sectors;
+
+		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
+		    test_bit(R1BIO_WriteError, &r1_bio->state))
+			reschedule_retry(r1_bio);
+		else {
+			put_buf(r1_bio);
+			md_done_sync(mddev, s, uptodate);
+		}
+	}
+}
+
 static void end_sync_write(struct bio *bio)
 {
 	int uptodate = !bio->bi_status;
@@ -1927,16 +1948,7 @@ static void end_sync_write(struct bio *bio)
 		)
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
 
-	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		int s = r1_bio->sectors;
-		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
-		    test_bit(R1BIO_WriteError, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			put_buf(r1_bio);
-			md_done_sync(mddev, s, uptodate);
-		}
-	}
+	put_sync_write_buf(r1_bio, uptodate);
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
@@ -2219,17 +2231,7 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 		generic_make_request(wbio);
 	}
 
-	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		/* if we're here, all write(s) have completed, so clean up */
-		int s = r1_bio->sectors;
-		if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
-		    test_bit(R1BIO_WriteError, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			put_buf(r1_bio);
-			md_done_sync(mddev, s, 1);
-		}
-	}
+	put_sync_write_buf(r1_bio, 1);
 }
 
 /*
@@ -3127,6 +3129,13 @@ static int raid1_run(struct mddev *mddev)
 		    !test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
 		    test_bit(Faulty, &conf->mirrors[i].rdev->flags))
 			mddev->degraded++;
+	/*
+	 * RAID1 needs at least one disk in active
+	 */
+	if (conf->raid_disks - mddev->degraded < 1) {
+		ret = -EINVAL;
+		goto abort;
+	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
 		mddev->recovery_cp = MaxSector;
@@ -3160,8 +3169,12 @@ static int raid1_run(struct mddev *mddev)
 	ret = md_integrity_register(mddev);
 	if (ret) {
 		md_unregister_thread(&mddev->thread);
-		raid1_free(mddev, conf);
+		goto abort;
 	}
+	return 0;
+
+abort:
+	raid1_free(mddev, conf);
 	return ret;
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8a1354a08a1a..299c7b1c9718 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -465,19 +465,21 @@ static void raid10_end_write_request(struct bio *bio)
 			if (test_bit(FailFast, &rdev->flags) &&
 			    (bio->bi_opf & MD_FAILFAST)) {
 				md_error(rdev->mddev, rdev);
-				if (!test_bit(Faulty, &rdev->flags))
-					/* This is the only remaining device,
-					 * We need to retry the write without
-					 * FailFast
-					 */
-					set_bit(R10BIO_WriteError, &r10_bio->state);
-				else {
-					r10_bio->devs[slot].bio = NULL;
-					to_put = bio;
-					dec_rdev = 1;
-				}
-			} else
+			}
+
+			/*
+			 * When the device is faulty, it is not necessary to
+			 * handle write error.
+			 * For failfast, this is the only remaining device,
+			 * We need to retry the write without FailFast.
+			 */
+			if (!test_bit(Faulty, &rdev->flags))
 				set_bit(R10BIO_WriteError, &r10_bio->state);
+			else {
+				r10_bio->devs[slot].bio = NULL;
+				to_put = bio;
+				dec_rdev = 1;
+			}
 		}
 	} else {
 		/*
@@ -1638,12 +1640,12 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks, ignore the error, let the
-	 * next level up know.
+	 * else if it is the last working disks with "fail_last_dev == false",
+	 * ignore the error, let the next level up know.
 	 * else mark the drive as failed
 	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags)
+	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
 	    && !enough(conf, rdev->raid_disk)) {
 		/*
 		 * Don't fail the drive, just return an IO error.
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3de4e13bde98..223e97ab27e6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2526,7 +2526,8 @@ static void raid5_end_read_request(struct bio * bi)
 		int set_bad = 0;
 
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
-		atomic_inc(&rdev->read_errors);
+		if (!(bi->bi_status == BLK_STS_PROTECTION))
+			atomic_inc(&rdev->read_errors);
 		if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
 			pr_warn_ratelimited(
 				"md/raid:%s: read error on replacement device (sector %llu on %s).\n",
@@ -2549,16 +2550,24 @@ static void raid5_end_read_request(struct bio * bi)
 				(unsigned long long)s,
 				bdn);
 		} else if (atomic_read(&rdev->read_errors)
-			 > conf->max_nr_stripes)
-			pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
-			       mdname(conf->mddev), bdn);
-		else
+			 > conf->max_nr_stripes) {
+			if (!test_bit(Faulty, &rdev->flags)) {
+				pr_warn("md/raid:%s: %d read_errors > %d stripes\n",
+				    mdname(conf->mddev),
+				    atomic_read(&rdev->read_errors),
+				    conf->max_nr_stripes);
+				pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
+				    mdname(conf->mddev), bdn);
+			}
+		} else
 			retry = 1;
 		if (set_bad && test_bit(In_sync, &rdev->flags)
 		    && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 			retry = 1;
 		if (retry)
-			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
+			if (sh->qd_idx >= 0 && sh->pd_idx == i)
+				set_bit(R5_ReadError, &sh->dev[i].flags);
+			else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
 				set_bit(R5_ReadError, &sh->dev[i].flags);
 				clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
 			} else
@@ -4612,7 +4621,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_FULL_WRITE) |
 					  (1 << STRIPE_BIOFILL_RUN) |
 					  (1 << STRIPE_COMPUTE_RUN)  |
-					  (1 << STRIPE_OPS_REQ_PENDING) |
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
 					  (1 << STRIPE_BATCH_ERR) |
@@ -5491,7 +5499,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		return;
 
 	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
+	last_sector = bio_end_sector(bi);
 
 	bi->bi_next = NULL;
 
@@ -5718,7 +5726,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				do_flush = false;
 			}
 
-			set_bit(STRIPE_HANDLE, &sh->state);
+			if (!sh->batch_head)
+				set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&
 			    (bi->bi_opf & REQ_SYNC) &&
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index cf991f13403e..f90e0704bed9 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -357,7 +357,6 @@ enum {
 	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */
 	STRIPE_BIOFILL_RUN,
 	STRIPE_COMPUTE_RUN,
-	STRIPE_OPS_REQ_PENDING,
 	STRIPE_ON_UNPLUG_LIST,
 	STRIPE_DISCARD,
 	STRIPE_ON_RELEASE_LIST,
@@ -493,9 +492,7 @@ struct disk_info {
  */
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
-	int sectors = bio_sectors(bio);
-
-	if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
+	if (bio_end_sector(bio) < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
 		return NULL;