Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:

 - a raid5 writeback cache feature.

   The goal is to aggregate writes to make full stripe write and reduce
   read-modify-write. It's helpful for workload which does sequential
   write and follows fsync for example. This feature is experimental and
   off by default right now.

 - FAILFAST support.

   This fails IOs to broken raid disks quickly, so can improve latency.
   It's mainly for DASD storage, but some patches help normal raid array
   too.

 - support bad block for raid array with external metadata

 - AVX2 instruction support for raid6 parity calculation

 - normalize MD info output

 - add missing blktrace

 - other bug fixes

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (66 commits)
  md: separate flags for superblock changes
  md: MD_RECOVERY_NEEDED is set for mddev->recovery
  md: takeover should clear unrelated bits
  md/r5cache: after recovery, increase journal seq by 10000
  md/raid5-cache: fix crc in rewrite_data_only_stripes()
  md/raid5-cache: no recovery is required when create super-block
  md: fix refcount problem on mddev when stopping array.
  md/r5cache: do r5c_update_log_state after log recovery
  md/raid5-cache: adjust the write position of the empty block if no data blocks
  md/r5cache: run_no_space_stripes() when R5C_LOG_CRITICAL == 0
  md/raid5: limit request size according to implementation limits
  md/raid5-cache: do not need to set STRIPE_PREREAD_ACTIVE repeatedly
  md/raid5-cache: remove the unnecessary next_cp_seq field from the r5l_log
  md/raid5-cache: release the stripe_head at the appropriate location
  md/raid5-cache: use ring add to prevent overflow
  md/raid5-cache: remove unnecessary function parameters
  raid5-cache: don't set STRIPE_R5C_PARTIAL_STRIPE flag while load stripe into cache
  raid5-cache: add another check conditon before replaying one stripe
  md/r5cache: enable IRQs on error path
  md/r5cache: handle alloc_page failure
  ...

1 files changed, 165 insertions, 82 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 29e2df5..a1f3fbe 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -37,6 +37,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/ratelimit.h>
+#include <trace/events/block.h>
 #include "md.h"
 #include "raid1.h"
 #include "bitmap.h"
@@ -70,6 +71,9 @@ static void allow_barrier(struct r1conf *conf, sector_t start_next_window,
 			  sector_t bi_sector);
 static void lower_barrier(struct r1conf *conf);
 
+#define raid1_log(md, fmt, args...)				\
+	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
+
 static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct pool_info *pi = data;
@@ -325,6 +329,11 @@ static void raid1_end_read_request(struct bio *bio)
 
 	if (uptodate)
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
+	else if (test_bit(FailFast, &rdev->flags) &&
+		 test_bit(R1BIO_FailFast, &r1_bio->state))
+		/* This was a fail-fast read so we definitely
+		 * want to retry */
+		;
 	else {
 		/* If all other devices have failed, we want to return
 		 * the error upwards rather than fail the last device.
@@ -347,13 +356,10 @@ static void raid1_end_read_request(struct bio *bio)
 		 * oops, read error:
 		 */
 		char b[BDEVNAME_SIZE];
-		printk_ratelimited(
-			KERN_ERR "md/raid1:%s: %s: "
-			"rescheduling sector %llu\n",
-			mdname(conf->mddev),
-			bdevname(rdev->bdev,
-				 b),
-			(unsigned long long)r1_bio->sector);
+		pr_err_ratelimited("md/raid1:%s: %s: rescheduling sector %llu\n",
+				   mdname(conf->mddev),
+				   bdevname(rdev->bdev, b),
+				   (unsigned long long)r1_bio->sector);
 		set_bit(R1BIO_ReadError, &r1_bio->state);
 		reschedule_retry(r1_bio);
 		/* don't drop the reference on read_disk yet */
@@ -416,7 +422,24 @@ static void raid1_end_write_request(struct bio *bio)
 			set_bit(MD_RECOVERY_NEEDED, &
 				conf->mddev->recovery);
 
-		set_bit(R1BIO_WriteError, &r1_bio->state);
+		if (test_bit(FailFast, &rdev->flags) &&
+		    (bio->bi_opf & MD_FAILFAST) &&
+		    /* 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
+			set_bit(R1BIO_WriteError, &r1_bio->state);
 	} else {
 		/*
 		 * Set R1BIO_Uptodate in our master bio, so that we
@@ -534,6 +557,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	best_good_sectors = 0;
 	has_nonrot_disk = 0;
 	choose_next_idle = 0;
+	clear_bit(R1BIO_FailFast, &r1_bio->state);
 
 	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
 	    (mddev_is_clustered(conf->mddev) &&
@@ -607,6 +631,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		} else
 			best_good_sectors = sectors;
 
+		if (best_disk >= 0)
+			/* At least two disks to choose from so failfast is OK */
+			set_bit(R1BIO_FailFast, &r1_bio->state);
+
 		nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
 		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
@@ -645,11 +673,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 			}
 			break;
 		}
-		/* If device is idle, use it */
-		if (pending == 0) {
-			best_disk = disk;
-			break;
-		}
 
 		if (choose_next_idle)
 			continue;
@@ -672,7 +695,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	 * mixed ratation/non-rotational disks depending on workload.
 	 */
 	if (best_disk == -1) {
-		if (has_nonrot_disk)
+		if (has_nonrot_disk || min_pending == 0)
 			best_disk = best_pending_disk;
 		else
 			best_disk = best_dist_disk;
@@ -745,9 +768,14 @@ static void flush_pending_writes(struct r1conf *conf)
 
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
+			struct md_rdev *rdev = (void*)bio->bi_bdev;
 			bio->bi_next = NULL;
-			if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+			bio->bi_bdev = rdev->bdev;
+			if (test_bit(Faulty, &rdev->flags)) {
+				bio->bi_error = -EIO;
+				bio_endio(bio);
+			} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+					    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
 				bio_endio(bio);
 			else
@@ -832,7 +860,7 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
 	else if (conf->barrier && bio_data_dir(bio) == WRITE) {
 		if ((conf->mddev->curr_resync_completed
 		     >= bio_end_sector(bio)) ||
-		    (conf->next_resync + NEXT_NORMALIO_DISTANCE
+		    (conf->start_next_window + NEXT_NORMALIO_DISTANCE
 		     <= bio->bi_iter.bi_sector))
 			wait = false;
 		else
@@ -858,6 +886,7 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 		 * that queue to allow conf->start_next_window
 		 * to increase.
 		 */
+		raid1_log(conf->mddev, "wait barrier");
 		wait_event_lock_irq(conf->wait_barrier,
 				    !conf->array_frozen &&
 				    (!conf->barrier ||
@@ -937,6 +966,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
+	raid1_log(conf->mddev, "wait freeze");
 	wait_event_lock_irq_cmd(conf->wait_barrier,
 				conf->nr_pending == conf->nr_queued+extra,
 				conf->resync_lock,
@@ -1019,9 +1049,14 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
+		struct md_rdev *rdev = (void*)bio->bi_bdev;
 		bio->bi_next = NULL;
-		if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+		bio->bi_bdev = rdev->bdev;
+		if (test_bit(Faulty, &rdev->flags)) {
+			bio->bi_error = -EIO;
+			bio_endio(bio);
+		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -1136,6 +1171,7 @@ read_again:
 			 * take care not to over-take any writes
 			 * that are 'behind'
 			 */
+			raid1_log(mddev, "wait behind writes");
 			wait_event(bitmap->behind_wait,
 				   atomic_read(&bitmap->behind_writes) == 0);
 		}
@@ -1153,8 +1189,16 @@ read_again:
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid1_end_read_request;
 		bio_set_op_attrs(read_bio, op, do_sync);
+		if (test_bit(FailFast, &mirror->rdev->flags) &&
+		    test_bit(R1BIO_FailFast, &r1_bio->state))
+			read_bio->bi_opf |= MD_FAILFAST;
 		read_bio->bi_private = r1_bio;
 
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+					      read_bio, disk_devt(mddev->gendisk),
+					      r1_bio->sector);
+
 		if (max_sectors < r1_bio->sectors) {
 			/* could not read all from this device, so we will
 			 * need another r1_bio.
@@ -1195,6 +1239,7 @@ read_again:
 	 */
 	if (conf->pending_count >= max_queued_requests) {
 		md_wakeup_thread(mddev->thread);
+		raid1_log(mddev, "wait queued");
 		wait_event(conf->wait_barrier,
 			   conf->pending_count < max_queued_requests);
 	}
@@ -1286,6 +1331,7 @@ read_again:
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
 		r1_bio->state = 0;
 		allow_barrier(conf, start_next_window, bio->bi_iter.bi_sector);
+		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		start_next_window = wait_barrier(conf, bio);
 		/*
@@ -1363,10 +1409,21 @@ read_again:
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
 		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
+		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
+		    !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
+		    conf->raid_disks - mddev->degraded > 1)
+			mbio->bi_opf |= MD_FAILFAST;
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
 
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
+					      mbio, disk_devt(mddev->gendisk),
+					      r1_bio->sector);
+		/* flush_pending_writes() needs access to the rdev so...*/
+		mbio->bi_bdev = (void*)conf->mirrors[i].rdev;
+
 		cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
 		if (cb)
 			plug = container_of(cb, struct raid1_plug_cb, cb);
@@ -1436,6 +1493,7 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 	 * next level up know.
 	 * else mark the drive as failed
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_bit(In_sync, &rdev->flags)
 	    && (conf->raid_disks - mddev->degraded) == 1) {
 		/*
@@ -1445,10 +1503,10 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 		 * it is very likely to fail.
 		 */
 		conf->recovery_disabled = mddev->recovery_disabled;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
-	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
@@ -1459,36 +1517,35 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 	 * if recovery is running, make sure it aborts.
 	 */
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-	set_mask_bits(&mddev->flags, 0,
-		      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
-	printk(KERN_ALERT
-	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
-	       "md/raid1:%s: Operation continuing on %d devices.\n",
-	       mdname(mddev), bdevname(rdev->bdev, b),
-	       mdname(mddev), conf->raid_disks - mddev->degraded);
+	set_mask_bits(&mddev->sb_flags, 0,
+		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
+	pr_crit("md/raid1:%s: Disk failure on %s, disabling device.\n"
+		"md/raid1:%s: Operation continuing on %d devices.\n",
+		mdname(mddev), bdevname(rdev->bdev, b),
+		mdname(mddev), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(struct r1conf *conf)
 {
 	int i;
 
-	printk(KERN_DEBUG "RAID1 conf printout:\n");
+	pr_debug("RAID1 conf printout:\n");
 	if (!conf) {
-		printk(KERN_DEBUG "(!conf)\n");
+		pr_debug("(!conf)\n");
 		return;
 	}
-	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
-		conf->raid_disks);
+	pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
+		 conf->raid_disks);
 
 	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
 		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev)
-			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
-			       i, !test_bit(In_sync, &rdev->flags),
-			       !test_bit(Faulty, &rdev->flags),
-			       bdevname(rdev->bdev,b));
+			pr_debug(" disk %d, wo:%d, o:%d, dev:%s\n",
+				 i, !test_bit(In_sync, &rdev->flags),
+				 !test_bit(Faulty, &rdev->flags),
+				 bdevname(rdev->bdev,b));
 	}
 	rcu_read_unlock();
 }
@@ -1788,12 +1845,24 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 	sector_t sect = r1_bio->sector;
 	int sectors = r1_bio->sectors;
 	int idx = 0;
+	struct md_rdev *rdev;
+
+	rdev = conf->mirrors[r1_bio->read_disk].rdev;
+	if (test_bit(FailFast, &rdev->flags)) {
+		/* Don't try recovering from here - just fail it
+		 * ... unless it is the last working device of course */
+		md_error(mddev, rdev);
+		if (test_bit(Faulty, &rdev->flags))
+			/* Don't try to read from here, but make sure
+			 * put_buf does it's thing
+			 */
+			bio->bi_end_io = end_sync_write;
+	}
 
 	while(sectors) {
 		int s = sectors;
 		int d = r1_bio->read_disk;
 		int success = 0;
-		struct md_rdev *rdev;
 		int start;
 
 		if (s > (PAGE_SIZE>>9))
@@ -1825,11 +1894,10 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			 * work just disable and interrupt the recovery.
 			 * Don't fail devices as that won't really help.
 			 */
-			printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O read error"
-			       " for block %llu\n",
-			       mdname(mddev),
-			       bdevname(bio->bi_bdev, b),
-			       (unsigned long long)r1_bio->sector);
+			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
+					    mdname(mddev),
+					    bdevname(bio->bi_bdev, b),
+					    (unsigned long long)r1_bio->sector);
 			for (d = 0; d < conf->raid_disks * 2; d++) {
 				rdev = conf->mirrors[d].rdev;
 				if (!rdev || test_bit(Faulty, &rdev->flags))
@@ -2013,6 +2081,9 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 			continue;
 
 		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
+		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags))
+			wbio->bi_opf |= MD_FAILFAST;
+
 		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
 		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
@@ -2122,13 +2193,11 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
-					printk(KERN_INFO
-					       "md/raid1:%s: read error corrected "
-					       "(%d sectors at %llu on %s)\n",
-					       mdname(mddev), s,
-					       (unsigned long long)(sect +
-								    rdev->data_offset),
-					       bdevname(rdev->bdev, b));
+					pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %s)\n",
+						mdname(mddev), s,
+						(unsigned long long)(sect +
+								     rdev->data_offset),
+						bdevname(rdev->bdev, b));
 				}
 				rdev_dec_pending(rdev, mddev);
 			} else
@@ -2287,6 +2356,8 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	struct bio *bio;
 	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev;
+	dev_t bio_dev;
+	sector_t bio_sector;
 
 	clear_bit(R1BIO_ReadError, &r1_bio->state);
 	/* we got a read error. Maybe the drive is bad.  Maybe just
@@ -2300,10 +2371,14 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 
 	bio = r1_bio->bios[r1_bio->read_disk];
 	bdevname(bio->bi_bdev, b);
+	bio_dev = bio->bi_bdev->bd_dev;
+	bio_sector = conf->mirrors[r1_bio->read_disk].rdev->data_offset + r1_bio->sector;
 	bio_put(bio);
 	r1_bio->bios[r1_bio->read_disk] = NULL;
 
-	if (mddev->ro == 0) {
+	rdev = conf->mirrors[r1_bio->read_disk].rdev;
+	if (mddev->ro == 0
+	    && !test_bit(FailFast, &rdev->flags)) {
 		freeze_array(conf, 1);
 		fix_read_error(conf, r1_bio->read_disk,
 			       r1_bio->sector, r1_bio->sectors);
@@ -2312,14 +2387,13 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
 	}
 
-	rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
+	rdev_dec_pending(rdev, conf->mddev);
 
 read_more:
 	disk = read_balance(conf, r1_bio, &max_sectors);
 	if (disk == -1) {
-		printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O"
-		       " read error for block %llu\n",
-		       mdname(mddev), b, (unsigned long long)r1_bio->sector);
+		pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
+				    mdname(mddev), b, (unsigned long long)r1_bio->sector);
 		raid_end_bio_io(r1_bio);
 	} else {
 		const unsigned long do_sync
@@ -2330,16 +2404,17 @@ read_more:
 			 max_sectors);
 		r1_bio->bios[r1_bio->read_disk] = bio;
 		rdev = conf->mirrors[disk].rdev;
-		printk_ratelimited(KERN_ERR
-				   "md/raid1:%s: redirecting sector %llu"
-				   " to other mirror: %s\n",
-				   mdname(mddev),
-				   (unsigned long long)r1_bio->sector,
-				   bdevname(rdev->bdev, b));
+		pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n",
+				    mdname(mddev),
+				    (unsigned long long)r1_bio->sector,
+				    bdevname(rdev->bdev, b));
 		bio->bi_iter.bi_sector = r1_bio->sector + rdev->data_offset;
 		bio->bi_bdev = rdev->bdev;
 		bio->bi_end_io = raid1_end_read_request;
 		bio_set_op_attrs(bio, REQ_OP_READ, do_sync);
+		if (test_bit(FailFast, &rdev->flags) &&
+		    test_bit(R1BIO_FailFast, &r1_bio->state))
+			bio->bi_opf |= MD_FAILFAST;
 		bio->bi_private = r1_bio;
 		if (max_sectors < r1_bio->sectors) {
 			/* Drat - have to split this up more */
@@ -2353,6 +2428,8 @@ read_more:
 			else
 				mbio->bi_phys_segments++;
 			spin_unlock_irq(&conf->device_lock);
+			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+					      bio, bio_dev, bio_sector);
 			generic_make_request(bio);
 			bio = NULL;
 
@@ -2367,8 +2444,11 @@ read_more:
 				sectors_handled;
 
 			goto read_more;
-		} else
+		} else {
+			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+					      bio, bio_dev, bio_sector);
 			generic_make_request(bio);
+		}
 	}
 }
 
@@ -2384,10 +2464,10 @@ static void raid1d(struct md_thread *thread)
 	md_check_recovery(mddev);
 
 	if (!list_empty_careful(&conf->bio_end_io_list) &&
-	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
-		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 			while (!list_empty(&conf->bio_end_io_list)) {
 				list_move(conf->bio_end_io_list.prev, &tmp);
 				conf->nr_queued--;
@@ -2441,7 +2521,7 @@ static void raid1d(struct md_thread *thread)
 			generic_make_request(r1_bio->bios[r1_bio->read_disk]);
 
 		cond_resched();
-		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+		if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
 			md_check_recovery(mddev);
 	}
 	blk_finish_plug(&plug);
@@ -2623,6 +2703,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
 			bio->bi_bdev = rdev->bdev;
 			bio->bi_private = r1_bio;
+			if (test_bit(FailFast, &rdev->flags))
+				bio->bi_opf |= MD_FAILFAST;
 		}
 	}
 	rcu_read_unlock();
@@ -2642,7 +2724,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 							min_bad, 0
 					) && ok;
 			}
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		*skipped = 1;
 		put_buf(r1_bio);
 
@@ -2753,6 +2835,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (bio->bi_end_io == end_sync_read) {
 				read_targets--;
 				md_sync_acct(bio->bi_bdev, nr_sectors);
+				if (read_targets == 1)
+					bio->bi_opf &= ~MD_FAILFAST;
 				generic_make_request(bio);
 			}
 		}
@@ -2760,6 +2844,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		atomic_set(&r1_bio->remaining, 1);
 		bio = r1_bio->bios[r1_bio->read_disk];
 		md_sync_acct(bio->bi_bdev, nr_sectors);
+		if (read_targets == 1)
+			bio->bi_opf &= ~MD_FAILFAST;
 		generic_make_request(bio);
 
 	}
@@ -2875,12 +2961,8 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -ENOMEM;
 	conf->thread = md_register_thread(raid1d, mddev, "raid1");
-	if (!conf->thread) {
-		printk(KERN_ERR
-		       "md/raid1:%s: couldn't allocate thread\n",
-		       mdname(mddev));
+	if (!conf->thread)
 		goto abort;
-	}
 
 	return conf;
 
@@ -2905,13 +2987,13 @@ static int raid1_run(struct mddev *mddev)
 	bool discard_supported = false;
 
 	if (mddev->level != 1) {
-		printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n",
-		       mdname(mddev), mddev->level);
+		pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n",
+			mdname(mddev), mddev->level);
 		return -EIO;
 	}
 	if (mddev->reshape_position != MaxSector) {
-		printk(KERN_ERR "md/raid1:%s: reshape_position set but not supported\n",
-		       mdname(mddev));
+		pr_warn("md/raid1:%s: reshape_position set but not supported\n",
+			mdname(mddev));
 		return -EIO;
 	}
 	/*
@@ -2950,11 +3032,9 @@ static int raid1_run(struct mddev *mddev)
 		mddev->recovery_cp = MaxSector;
 
 	if (mddev->recovery_cp != MaxSector)
-		printk(KERN_NOTICE "md/raid1:%s: not clean"
-		       " -- starting background reconstruction\n",
-		       mdname(mddev));
-	printk(KERN_INFO
-		"md/raid1:%s: active with %d out of %d mirrors\n",
+		pr_info("md/raid1:%s: not clean -- starting background reconstruction\n",
+			mdname(mddev));
+	pr_info("md/raid1:%s: active with %d out of %d mirrors\n",
 		mdname(mddev), mddev->raid_disks - mddev->degraded,
 		mddev->raid_disks);
 
@@ -2964,6 +3044,7 @@ static int raid1_run(struct mddev *mddev)
 	mddev->thread = conf->thread;
 	conf->thread = NULL;
 	mddev->private = conf;
+	set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
 
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
@@ -3107,9 +3188,8 @@ static int raid1_reshape(struct mddev *mddev)
 			rdev->raid_disk = d2;
 			sysfs_unlink_rdev(mddev, rdev);
 			if (sysfs_link_rdev(mddev, rdev))
-				printk(KERN_WARNING
-				       "md/raid1:%s: cannot register rd%d\n",
-				       mdname(mddev), rdev->raid_disk);
+				pr_warn("md/raid1:%s: cannot register rd%d\n",
+					mdname(mddev), rdev->raid_disk);
 		}
 		if (rdev)
 			newmirrors[d2++].rdev = rdev;
@@ -3163,9 +3243,12 @@ static void *raid1_takeover(struct mddev *mddev)
 		mddev->new_layout = 0;
 		mddev->new_chunk_sectors = 0;
 		conf = setup_conf(mddev);
-		if (!IS_ERR(conf))
+		if (!IS_ERR(conf)) {
 			/* Array must appear to be quiesced */
 			conf->array_frozen = 1;
+			clear_bit(MD_HAS_JOURNAL, &mddev->flags);
+			clear_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+		}
 		return conf;
 	}
 	return ERR_PTR(-EINVAL);