Merge branch 'md-next' into md-linus

14 files changed, 3168 insertions, 1232 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 2d826927a3bf..9fb2ccac958a 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -27,6 +27,7 @@
 #include <linux/mount.h>
 #include <linux/buffer_head.h>
 #include <linux/seq_file.h>
+#include <trace/events/block.h>
 #include "md.h"
 #include "bitmap.h"
 
@@ -208,11 +209,13 @@ static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *mdde
 
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
-	struct md_rdev *rdev = NULL;
+	struct md_rdev *rdev;
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
 
+restart:
+	rdev = NULL;
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
 		int size = PAGE_SIZE;
 		loff_t offset = mddev->bitmap_info.offset;
@@ -268,8 +271,8 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 			       page);
 	}
 
-	if (wait)
-		md_super_wait(mddev);
+	if (wait && md_super_wait(mddev) < 0)
+		goto restart;
 	return 0;
 
  bad_alignment:
@@ -405,10 +408,10 @@ static int read_page(struct file *file, unsigned long index,
 		ret = -EIO;
 out:
 	if (ret)
-		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %d\n",
-			(int)PAGE_SIZE,
-			(unsigned long long)index << PAGE_SHIFT,
-			ret);
+		pr_err("md: bitmap read error: (%dB @ %llu): %d\n",
+		       (int)PAGE_SIZE,
+		       (unsigned long long)index << PAGE_SHIFT,
+		       ret);
 	return ret;
 }
 
@@ -416,6 +419,28 @@ out:
  * bitmap file superblock operations
  */
 
+/*
+ * bitmap_wait_writes() should be called before writing any bitmap
+ * blocks, to ensure previous writes, particularly from
+ * bitmap_daemon_work(), have completed.
+ */
+static void bitmap_wait_writes(struct bitmap *bitmap)
+{
+	if (bitmap->storage.file)
+		wait_event(bitmap->write_wait,
+			   atomic_read(&bitmap->pending_writes)==0);
+	else
+		/* Note that we ignore the return value.  The writes
+		 * might have failed, but that would just mean that
+		 * some bits which should be cleared haven't been,
+		 * which is safe.  The relevant bitmap blocks will
+		 * probably get written again, but there is no great
+		 * loss if they aren't.
+		 */
+		md_super_wait(bitmap->mddev);
+}
+
+
 /* update the event counter and sync the superblock to disk */
 void bitmap_update_sb(struct bitmap *bitmap)
 {
@@ -455,24 +480,24 @@ void bitmap_print_sb(struct bitmap *bitmap)
 	if (!bitmap || !bitmap->storage.sb_page)
 		return;
 	sb = kmap_atomic(bitmap->storage.sb_page);
-	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
-	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
-	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
-	printk(KERN_DEBUG "          uuid: %08x.%08x.%08x.%08x\n",
-					*(__u32 *)(sb->uuid+0),
-					*(__u32 *)(sb->uuid+4),
-					*(__u32 *)(sb->uuid+8),
-					*(__u32 *)(sb->uuid+12));
-	printk(KERN_DEBUG "        events: %llu\n",
-			(unsigned long long) le64_to_cpu(sb->events));
-	printk(KERN_DEBUG "events cleared: %llu\n",
-			(unsigned long long) le64_to_cpu(sb->events_cleared));
-	printk(KERN_DEBUG "         state: %08x\n", le32_to_cpu(sb->state));
-	printk(KERN_DEBUG "     chunksize: %d B\n", le32_to_cpu(sb->chunksize));
-	printk(KERN_DEBUG "  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
-	printk(KERN_DEBUG "     sync size: %llu KB\n",
-			(unsigned long long)le64_to_cpu(sb->sync_size)/2);
-	printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));
+	pr_debug("%s: bitmap file superblock:\n", bmname(bitmap));
+	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));
+	pr_debug("       version: %d\n", le32_to_cpu(sb->version));
+	pr_debug("          uuid: %08x.%08x.%08x.%08x\n",
+		 *(__u32 *)(sb->uuid+0),
+		 *(__u32 *)(sb->uuid+4),
+		 *(__u32 *)(sb->uuid+8),
+		 *(__u32 *)(sb->uuid+12));
+	pr_debug("        events: %llu\n",
+		 (unsigned long long) le64_to_cpu(sb->events));
+	pr_debug("events cleared: %llu\n",
+		 (unsigned long long) le64_to_cpu(sb->events_cleared));
+	pr_debug("         state: %08x\n", le32_to_cpu(sb->state));
+	pr_debug("     chunksize: %d B\n", le32_to_cpu(sb->chunksize));
+	pr_debug("  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
+	pr_debug("     sync size: %llu KB\n",
+		 (unsigned long long)le64_to_cpu(sb->sync_size)/2);
+	pr_debug("max write behind: %d\n", le32_to_cpu(sb->write_behind));
 	kunmap_atomic(sb);
 }
 
@@ -506,14 +531,14 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	BUG_ON(!chunksize);
 	if (!is_power_of_2(chunksize)) {
 		kunmap_atomic(sb);
-		printk(KERN_ERR "bitmap chunksize not a power of 2\n");
+		pr_warn("bitmap chunksize not a power of 2\n");
 		return -EINVAL;
 	}
 	sb->chunksize = cpu_to_le32(chunksize);
 
 	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
 	if (!daemon_sleep || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
-		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
+		pr_debug("Choosing daemon_sleep default (5 sec)\n");
 		daemon_sleep = 5 * HZ;
 	}
 	sb->daemon_sleep = cpu_to_le32(daemon_sleep);
@@ -584,7 +609,7 @@ re_read:
 		/* to 4k blocks */
 		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);
 		offset = bitmap->mddev->bitmap_info.offset + (bitmap->cluster_slot * (bm_blocks << 3));
-		pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
+		pr_debug("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
 			bitmap->cluster_slot, offset);
 	}
 
@@ -634,7 +659,7 @@ re_read:
 	else if (write_behind > COUNTER_MAX)
 		reason = "write-behind limit out of range (0 - 16383)";
 	if (reason) {
-		printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
+		pr_warn("%s: invalid bitmap file superblock: %s\n",
 			bmname(bitmap), reason);
 		goto out;
 	}
@@ -648,18 +673,15 @@ re_read:
 		 * bitmap's UUID and event counter to the mddev's
 		 */
 		if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
-			printk(KERN_INFO
-			       "%s: bitmap superblock UUID mismatch\n",
-			       bmname(bitmap));
+			pr_warn("%s: bitmap superblock UUID mismatch\n",
+				bmname(bitmap));
 			goto out;
 		}
 		events = le64_to_cpu(sb->events);
 		if (!nodes && (events < bitmap->mddev->events)) {
-			printk(KERN_INFO
-			       "%s: bitmap file is out of date (%llu < %llu) "
-			       "-- forcing full recovery\n",
-			       bmname(bitmap), events,
-			       (unsigned long long) bitmap->mddev->events);
+			pr_warn("%s: bitmap file is out of date (%llu < %llu) -- forcing full recovery\n",
+				bmname(bitmap), events,
+				(unsigned long long) bitmap->mddev->events);
 			set_bit(BITMAP_STALE, &bitmap->flags);
 		}
 	}
@@ -679,8 +701,8 @@ out:
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		err = md_setup_cluster(bitmap->mddev, nodes);
 		if (err) {
-			pr_err("%s: Could not setup cluster service (%d)\n",
-					bmname(bitmap), err);
+			pr_warn("%s: Could not setup cluster service (%d)\n",
+				bmname(bitmap), err);
 			goto out_no_sb;
 		}
 		bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev);
@@ -847,15 +869,13 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 				ptr = file_path(bitmap->storage.file,
 					     path, PAGE_SIZE);
 
-			printk(KERN_ALERT
-			      "%s: kicking failed bitmap file %s from array!\n",
-			      bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
+			pr_warn("%s: kicking failed bitmap file %s from array!\n",
+				bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
 
 			kfree(path);
 		} else
-			printk(KERN_ALERT
-			       "%s: disabling internal bitmap due to errors\n",
-			       bmname(bitmap));
+			pr_warn("%s: disabling internal bitmap due to errors\n",
+				bmname(bitmap));
 	}
 }
 
@@ -983,6 +1003,7 @@ void bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
+	int writing = 0;
 
 	if (!bitmap || !bitmap->storage.filemap ||
 	    test_bit(BITMAP_STALE, &bitmap->flags))
@@ -997,15 +1018,19 @@ void bitmap_unplug(struct bitmap *bitmap)
 		need_write = test_and_clear_page_attr(bitmap, i,
 						      BITMAP_PAGE_NEEDWRITE);
 		if (dirty || need_write) {
+			if (!writing) {
+				bitmap_wait_writes(bitmap);
+				if (bitmap->mddev->queue)
+					blk_add_trace_msg(bitmap->mddev->queue,
+							  "md bitmap_unplug");
+			}
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			write_page(bitmap, bitmap->storage.filemap[i], 0);
+			writing = 1;
 		}
 	}
-	if (bitmap->storage.file)
-		wait_event(bitmap->write_wait,
-			   atomic_read(&bitmap->pending_writes)==0);
-	else
-		md_super_wait(bitmap->mddev);
+	if (writing)
+		bitmap_wait_writes(bitmap);
 
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
@@ -1056,14 +1081,13 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 
 	outofdate = test_bit(BITMAP_STALE, &bitmap->flags);
 	if (outofdate)
-		printk(KERN_INFO "%s: bitmap file is out of date, doing full "
-			"recovery\n", bmname(bitmap));
+		pr_warn("%s: bitmap file is out of date, doing full recovery\n", bmname(bitmap));
 
 	if (file && i_size_read(file->f_mapping->host) < store->bytes) {
-		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
-		       bmname(bitmap),
-		       (unsigned long) i_size_read(file->f_mapping->host),
-		       store->bytes);
+		pr_warn("%s: bitmap file too short %lu < %lu\n",
+			bmname(bitmap),
+			(unsigned long) i_size_read(file->f_mapping->host),
+			store->bytes);
 		goto err;
 	}
 
@@ -1137,16 +1161,15 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		offset = 0;
 	}
 
-	printk(KERN_INFO "%s: bitmap initialized from disk: "
-	       "read %lu pages, set %lu of %lu bits\n",
-	       bmname(bitmap), store->file_pages,
-	       bit_cnt, chunks);
+	pr_debug("%s: bitmap initialized from disk: read %lu pages, set %lu of %lu bits\n",
+		 bmname(bitmap), store->file_pages,
+		 bit_cnt, chunks);
 
 	return 0;
 
  err:
-	printk(KERN_INFO "%s: bitmap initialisation failed: %d\n",
-	       bmname(bitmap), ret);
+	pr_warn("%s: bitmap initialisation failed: %d\n",
+		bmname(bitmap), ret);
 	return ret;
 }
 
@@ -1225,6 +1248,10 @@ void bitmap_daemon_work(struct mddev *mddev)
 	}
 	bitmap->allclean = 1;
 
+	if (bitmap->mddev->queue)
+		blk_add_trace_msg(bitmap->mddev->queue,
+				  "md bitmap_daemon_work");
+
 	/* Any file-page which is PENDING now needs to be written.
 	 * So set NEEDWRITE now, then after we make any last-minute changes
 	 * we will write it.
@@ -1289,6 +1316,7 @@ void bitmap_daemon_work(struct mddev *mddev)
 	}
 	spin_unlock_irq(&counts->lock);
 
+	bitmap_wait_writes(bitmap);
 	/* Now start writeout on any page in NEEDWRITE that isn't DIRTY.
 	 * DIRTY pages need to be written by bitmap_unplug so it can wait
 	 * for them.
@@ -1595,7 +1623,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
 	bitmap->mddev->curr_resync_completed = sector;
-	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+	set_bit(MD_SB_CHANGE_CLEAN, &bitmap->mddev->sb_flags);
 	sector &= ~((1ULL << bitmap->counts.chunkshift) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
@@ -1825,8 +1853,8 @@ struct bitmap *bitmap_create(struct mddev *mddev, int slot)
 	if (err)
 		goto error;
 
-	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
-	       bitmap->counts.pages, bmname(bitmap));
+	pr_debug("created bitmap (%lu pages) for device %s\n",
+		 bitmap->counts.pages, bmname(bitmap));
 
 	err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0;
 	if (err)
@@ -2029,8 +2057,10 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 					   !bitmap->mddev->bitmap_info.external,
 					   mddev_is_clustered(bitmap->mddev)
 					   ? bitmap->cluster_slot : 0);
-	if (ret)
+	if (ret) {
+		bitmap_file_unmap(&store);
 		goto err;
+	}
 
 	pages = DIV_ROUND_UP(chunks, PAGE_COUNTER_RATIO);
 
@@ -2089,7 +2119,7 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 				bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift +
 									     BITMAP_BLOCK_SHIFT);
 				blocks = old_counts.chunks << old_counts.chunkshift;
-				pr_err("Could not pre-allocate in-memory bitmap for cluster raid\n");
+				pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n");
 				break;
 			} else
 				bitmap->counts.bp[page].count += 1;
@@ -2266,7 +2296,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 		/* Ensure new bitmap info is stored in
 		 * metadata promptly.
 		 */
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
 	}
 	rv = 0;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 6d53810963f7..953159d9a825 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2011,7 +2011,7 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 		sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
 
 		/* Force writing of superblocks to disk */
-		set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &rdev->mddev->sb_flags);
 
 		/* Any superblock is better than none, choose that if given */
 		return refdev ? 0 : 1;
@@ -3497,7 +3497,7 @@ static void rs_update_sbs(struct raid_set *rs)
 	struct mddev *mddev = &rs->md;
 	int ro = mddev->ro;
 
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	mddev->ro = 0;
 	md_update_sb(mddev, 1);
 	mddev->ro = ro;
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 86f5d435901d..5975c9915684 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -21,6 +21,7 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <trace/events/block.h>
 #include "md.h"
 #include "linear.h"
 
@@ -101,8 +102,8 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 		sector_t sectors;
 
 		if (j < 0 || j >= raid_disks || disk->rdev) {
-			printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n",
-			       mdname(mddev));
+			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
+				mdname(mddev));
 			goto out;
 		}
 
@@ -123,8 +124,8 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			discard_supported = true;
 	}
 	if (cnt != raid_disks) {
-		printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n",
-		       mdname(mddev));
+		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
+			mdname(mddev));
 		goto out;
 	}
 
@@ -227,22 +228,22 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 	}
 
 	do {
-		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
+		sector_t bio_sector = bio->bi_iter.bi_sector;
+		tmp_dev = which_dev(mddev, bio_sector);
 		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
 		end_sector = tmp_dev->end_sector;
 		data_offset = tmp_dev->rdev->data_offset;
 		bio->bi_bdev = tmp_dev->rdev->bdev;
 
-		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
-			     bio->bi_iter.bi_sector < start_sector))
+		if (unlikely(bio_sector >= end_sector ||
+			     bio_sector < start_sector))
 			goto out_of_bounds;
 
 		if (unlikely(bio_end_sector(bio) > end_sector)) {
 			/* This bio crosses a device boundary, so we have to
 			 * split it.
 			 */
-			split = bio_split(bio, end_sector -
-					  bio->bi_iter.bi_sector,
+			split = bio_split(bio, end_sector - bio_sector,
 					  GFP_NOIO, fs_bio_set);
 			bio_chain(split, bio);
 		} else {
@@ -256,15 +257,18 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
 			/* Just ignore it */
 			bio_endio(split);
-		} else
+		} else {
+			if (mddev->gendisk)
+				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
+						      split, disk_devt(mddev->gendisk),
+						      bio_sector);
 			generic_make_request(split);
+		}
 	} while (split != bio);
 	return;
 
 out_of_bounds:
-	printk(KERN_ERR
-	       "md/linear:%s: make_request: Sector %llu out of bounds on "
-	       "dev %s: %llu sectors, offset %llu\n",
+	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",
 	       mdname(mddev),
 	       (unsigned long long)bio->bi_iter.bi_sector,
 	       bdevname(tmp_dev->rdev->bdev, b),
@@ -275,7 +279,6 @@ out_of_bounds:
 
 static void linear_status (struct seq_file *seq, struct mddev *mddev)
 {
-
 	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f975cd08923d..82821ee0d57f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -30,6 +30,18 @@
    You should have received a copy of the GNU General Public License
    (for example /usr/src/linux/COPYING); if not, write to the Free
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+   Errors, Warnings, etc.
+   Please use:
+     pr_crit() for error conditions that risk data loss
+     pr_err() for error conditions that are unexpected, like an IO error
+         or internal inconsistency
+     pr_warn() for error conditions that could have been predicated, like
+         adding a device to an array when it has incompatible metadata
+     pr_info() for every interesting, very rare events, like an array starting
+         or stopping, or resync starting or stopping
+     pr_debug() for everything else.
+
 */
 
 #include <linux/kthread.h>
@@ -52,6 +64,7 @@
 #include <linux/raid/md_p.h>
 #include <linux/raid/md_u.h>
 #include <linux/slab.h>
+#include <trace/events/block.h>
 #include "md.h"
 #include "bitmap.h"
 #include "md-cluster.h"
@@ -684,11 +697,8 @@ static inline sector_t calc_dev_sboffset(struct md_rdev *rdev)
 static int alloc_disk_sb(struct md_rdev *rdev)
 {
 	rdev->sb_page = alloc_page(GFP_KERNEL);
-	if (!rdev->sb_page) {
-		printk(KERN_ALERT "md: out of memory.\n");
+	if (!rdev->sb_page)
 		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -715,9 +725,15 @@ static void super_written(struct bio *bio)
 	struct mddev *mddev = rdev->mddev;
 
 	if (bio->bi_error) {
-		printk("md: super_written gets error=%d\n", bio->bi_error);
+		pr_err("md: super_written gets error=%d\n", bio->bi_error);
 		md_error(mddev, rdev);
-	}
+		if (!test_bit(Faulty, &rdev->flags)
+		    && (bio->bi_opf & MD_FAILFAST)) {
+			set_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags);
+			set_bit(LastDev, &rdev->flags);
+		}
+	} else
+		clear_bit(LastDev, &rdev->flags);
 
 	if (atomic_dec_and_test(&mddev->pending_writes))
 		wake_up(&mddev->sb_wait);
@@ -734,7 +750,13 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	 * if zero is reached.
 	 * If an error occurred, call md_error
 	 */
-	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);
+	struct bio *bio;
+	int ff = 0;
+
+	if (test_bit(Faulty, &rdev->flags))
+		return;
+
+	bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);
 
 	atomic_inc(&rdev->nr_pending);
 
@@ -743,16 +765,24 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA;
+
+	if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) &&
+	    test_bit(FailFast, &rdev->flags) &&
+	    !test_bit(LastDev, &rdev->flags))
+		ff = MD_FAILFAST;
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA | ff;
 
 	atomic_inc(&mddev->pending_writes);
 	submit_bio(bio);
 }
 
-void md_super_wait(struct mddev *mddev)
+int md_super_wait(struct mddev *mddev)
 {
 	/* wait for all superblock writes that were scheduled to complete */
 	wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0);
+	if (test_and_clear_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags))
+		return -EAGAIN;
+	return 0;
 }
 
 int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
@@ -795,8 +825,8 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 	return 0;
 
 fail:
-	printk(KERN_WARNING "md: disabled device %s, could not read superblock.\n",
-		bdevname(rdev->bdev,b));
+	pr_err("md: disabled device %s, could not read superblock.\n",
+	       bdevname(rdev->bdev,b));
 	return -EINVAL;
 }
 
@@ -818,7 +848,6 @@ static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
 
 	if (!tmp1 || !tmp2) {
 		ret = 0;
-		printk(KERN_INFO "md.c sb_equal(): failed to allocate memory!\n");
 		goto abort;
 	}
 
@@ -932,7 +961,7 @@ int md_check_no_bitmap(struct mddev *mddev)
 {
 	if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset)
 		return 0;
-	printk(KERN_ERR "%s: bitmaps are not supported for %s\n",
+	pr_warn("%s: bitmaps are not supported for %s\n",
 		mdname(mddev), mddev->pers->name);
 	return 1;
 }
@@ -956,7 +985,8 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	rdev->sb_start = calc_dev_sboffset(rdev);
 
 	ret = read_disk_sb(rdev, MD_SB_BYTES);
-	if (ret) return ret;
+	if (ret)
+		return ret;
 
 	ret = -EINVAL;
 
@@ -964,17 +994,15 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	sb = page_address(rdev->sb_page);
 
 	if (sb->md_magic != MD_SB_MAGIC) {
-		printk(KERN_ERR "md: invalid raid superblock magic on %s\n",
-		       b);
+		pr_warn("md: invalid raid superblock magic on %s\n", b);
 		goto abort;
 	}
 
 	if (sb->major_version != 0 ||
 	    sb->minor_version < 90 ||
 	    sb->minor_version > 91) {
-		printk(KERN_WARNING "Bad version number %d.%d on %s\n",
-			sb->major_version, sb->minor_version,
-			b);
+		pr_warn("Bad version number %d.%d on %s\n",
+			sb->major_version, sb->minor_version, b);
 		goto abort;
 	}
 
@@ -982,8 +1010,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		goto abort;
 
 	if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
-		printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
-			b);
+		pr_warn("md: invalid superblock checksum on %s\n", b);
 		goto abort;
 	}
 
@@ -1004,14 +1031,13 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = page_address(refdev->sb_page);
 		if (!uuid_equal(refsb, sb)) {
-			printk(KERN_WARNING "md: %s has different UUID to %s\n",
+			pr_warn("md: %s has different UUID to %s\n",
 				b, bdevname(refdev->bdev,b2));
 			goto abort;
 		}
 		if (!sb_equal(refsb, sb)) {
-			printk(KERN_WARNING "md: %s has same UUID"
-			       " but different superblock to %s\n",
-			       b, bdevname(refdev->bdev, b2));
+			pr_warn("md: %s has same UUID but different superblock to %s\n",
+				b, bdevname(refdev->bdev, b2));
 			goto abort;
 		}
 		ev1 = md_event(sb);
@@ -1158,6 +1184,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		}
 		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
 			set_bit(WriteMostly, &rdev->flags);
+		if (desc->state & (1<<MD_DISK_FAILFAST))
+			set_bit(FailFast, &rdev->flags);
 	} else /* MULTIPATH are always insync */
 		set_bit(In_sync, &rdev->flags);
 	return 0;
@@ -1283,6 +1311,8 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 		}
 		if (test_bit(WriteMostly, &rdev2->flags))
 			d->state |= (1<<MD_DISK_WRITEMOSTLY);
+		if (test_bit(FailFast, &rdev2->flags))
+			d->state |= (1<<MD_DISK_FAILFAST);
 	}
 	/* now set the "removed" and "faulty" bits on any missing devices */
 	for (i=0 ; i < mddev->raid_disks ; i++) {
@@ -1324,9 +1354,10 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) &&
 	    rdev->mddev->level >= 1)
 		num_sectors = (sector_t)(2ULL << 32) - 2;
-	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
+	do {
+		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
 		       rdev->sb_page);
-	md_super_wait(rdev->mddev);
+	} while (md_super_wait(rdev->mddev) < 0);
 	return num_sectors;
 }
 
@@ -1413,13 +1444,13 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		return -EINVAL;
 
 	if (calc_sb_1_csum(sb) != sb->sb_csum) {
-		printk("md: invalid superblock checksum on %s\n",
+		pr_warn("md: invalid superblock checksum on %s\n",
 			bdevname(rdev->bdev,b));
 		return -EINVAL;
 	}
 	if (le64_to_cpu(sb->data_size) < 10) {
-		printk("md: data_size too small on %s\n",
-		       bdevname(rdev->bdev,b));
+		pr_warn("md: data_size too small on %s\n",
+			bdevname(rdev->bdev,b));
 		return -EINVAL;
 	}
 	if (sb->pad0 ||
@@ -1503,8 +1534,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		    sb->level != refsb->level ||
 		    sb->layout != refsb->layout ||
 		    sb->chunksize != refsb->chunksize) {
-			printk(KERN_WARNING "md: %s has strangely different"
-				" superblock to %s\n",
+			pr_warn("md: %s has strangely different superblock to %s\n",
 				bdevname(rdev->bdev,b),
 				bdevname(refdev->bdev,b2));
 			return -EINVAL;
@@ -1646,8 +1676,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		case MD_DISK_ROLE_JOURNAL: /* journal device */
 			if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
 				/* journal device without journal feature */
-				printk(KERN_WARNING
-				  "md: journal device provided without journal feature, ignoring the device\n");
+				pr_warn("md: journal device provided without journal feature, ignoring the device\n");
 				return -EINVAL;
 			}
 			set_bit(Journal, &rdev->flags);
@@ -1669,6 +1698,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		}
 		if (sb->devflags & WriteMostly1)
 			set_bit(WriteMostly, &rdev->flags);
+		if (sb->devflags & FailFast1)
+			set_bit(FailFast, &rdev->flags);
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
 			set_bit(Replacement, &rdev->flags);
 	} else /* MULTIPATH are always insync */
@@ -1707,6 +1738,10 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
 	sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
 	sb->level = cpu_to_le32(mddev->level);
 	sb->layout = cpu_to_le32(mddev->layout);
+	if (test_bit(FailFast, &rdev->flags))
+		sb->devflags |= FailFast1;
+	else
+		sb->devflags &= ~FailFast1;
 
 	if (test_bit(WriteMostly, &rdev->flags))
 		sb->devflags |= WriteMostly1;
@@ -1863,9 +1898,10 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 	sb->data_size = cpu_to_le64(num_sectors);
 	sb->super_offset = rdev->sb_start;
 	sb->sb_csum = calc_sb_1_csum(sb);
-	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
-		       rdev->sb_page);
-	md_super_wait(rdev->mddev);
+	do {
+		md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
+			       rdev->sb_page);
+	} while (md_super_wait(rdev->mddev) < 0);
 	return num_sectors;
 
 }
@@ -2004,9 +2040,9 @@ int md_integrity_register(struct mddev *mddev)
 	blk_integrity_register(mddev->gendisk,
 			       bdev_get_integrity(reference->bdev));
 
-	printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev));
+	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
 	if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
-		printk(KERN_ERR "md: failed to create integrity pool for %s\n",
+		pr_err("md: failed to create integrity pool for %s\n",
 		       mdname(mddev));
 		return -EINVAL;
 	}
@@ -2034,8 +2070,8 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 		return 0;
 
 	if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) {
-		printk(KERN_NOTICE "%s: incompatible integrity profile for %s\n",
-				mdname(mddev), bdevname(rdev->bdev, name));
+		pr_err("%s: incompatible integrity profile for %s\n",
+		       mdname(mddev), bdevname(rdev->bdev, name));
 		return -ENXIO;
 	}
 
@@ -2089,15 +2125,15 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	rcu_read_unlock();
 	if (!test_bit(Journal, &rdev->flags) &&
 	    mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
-		printk(KERN_WARNING "md: %s: array is limited to %d devices\n",
-		       mdname(mddev), mddev->max_disks);
+		pr_warn("md: %s: array is limited to %d devices\n",
+			mdname(mddev), mddev->max_disks);
 		return -EBUSY;
 	}
 	bdevname(rdev->bdev,b);
 	strreplace(b, '/', '!');
 
 	rdev->mddev = mddev;
-	printk(KERN_INFO "md: bind<%s>\n", b);
+	pr_debug("md: bind<%s>\n", b);
 
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
@@ -2116,8 +2152,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	return 0;
 
  fail:
-	printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
-	       b, mdname(mddev));
+	pr_warn("md: failed to register dev-%s for %s\n",
+		b, mdname(mddev));
 	return err;
 }
 
@@ -2134,7 +2170,7 @@ static void unbind_rdev_from_array(struct md_rdev *rdev)
 
 	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
 	list_del_rcu(&rdev->same_set);
-	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
+	pr_debug("md: unbind<%s>\n", bdevname(rdev->bdev,b));
 	rdev->mddev = NULL;
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
@@ -2164,8 +2200,7 @@ static int lock_rdev(struct md_rdev *rdev, dev_t dev, int shared)
 	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
 				 shared ? (struct md_rdev *)lock_rdev : rdev);
 	if (IS_ERR(bdev)) {
-		printk(KERN_ERR "md: could not open %s.\n",
-			__bdevname(dev, b));
+		pr_warn("md: could not open %s.\n", __bdevname(dev, b));
 		return PTR_ERR(bdev);
 	}
 	rdev->bdev = bdev;
@@ -2185,8 +2220,7 @@ static void export_rdev(struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 
-	printk(KERN_INFO "md: export_rdev(%s)\n",
-		bdevname(rdev->bdev,b));
+	pr_debug("md: export_rdev(%s)\n", bdevname(rdev->bdev,b));
 	md_rdev_clear(rdev);
 #ifndef MODULE
 	if (test_bit(AutoDetected, &rdev->flags))
@@ -2288,24 +2322,24 @@ void md_update_sb(struct mddev *mddev, int force_change)
 
 	if (mddev->ro) {
 		if (force_change)
-			set_bit(MD_CHANGE_DEVS, &mddev->flags);
+			set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		return;
 	}
 
 repeat:
 	if (mddev_is_clustered(mddev)) {
-		if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
+		if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags))
 			force_change = 1;
-		if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
+		if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags))
 			nospares = 1;
 		ret = md_cluster_ops->metadata_update_start(mddev);
 		/* Has someone else has updated the sb */
 		if (!does_sb_need_changing(mddev)) {
 			if (ret == 0)
 				md_cluster_ops->metadata_update_cancel(mddev);
-			bit_clear_unless(&mddev->flags, BIT(MD_CHANGE_PENDING),
-							 BIT(MD_CHANGE_DEVS) |
-							 BIT(MD_CHANGE_CLEAN));
+			bit_clear_unless(&mddev->sb_flags, BIT(MD_SB_CHANGE_PENDING),
+							 BIT(MD_SB_CHANGE_DEVS) |
+							 BIT(MD_SB_CHANGE_CLEAN));
 			return;
 		}
 	}
@@ -2321,10 +2355,10 @@ repeat:
 
 	}
 	if (!mddev->persistent) {
-		clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
-		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
+		clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
+		clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		if (!mddev->external) {
-			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
 			rdev_for_each(rdev, mddev) {
 				if (rdev->badblocks.changed) {
 					rdev->badblocks.changed = 0;
@@ -2344,9 +2378,9 @@ repeat:
 
 	mddev->utime = ktime_get_real_seconds();
 
-	if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
+	if (test_and_clear_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags))
 		force_change = 1;
-	if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
+	if (test_and_clear_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags))