6 files changed, 189 insertions, 548 deletions

diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 1fa45695b68a..c219a053c7f6 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1207,6 +1207,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
 	dm_block_t held_root;
 
 	/*
+	 * We commit to ensure the btree roots which we increment in a
+	 * moment are up to date.
+	 */
+	__commit_transaction(pmd);
+
+	/*
 	 * Copy the superblock.
 	 */
 	dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION);
@@ -1538,7 +1544,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block)
 static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
 {
 	int r;
-	unsigned count;
+	unsigned count, total_count = 0;
 	struct dm_pool_metadata *pmd = td->pmd;
 	dm_block_t keys[1] = { td->id };
 	__le64 value;
@@ -1561,11 +1567,29 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
 	if (r)
 		return r;
 
-	r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
-	if (r)
-		return r;
+	/*
+	 * Remove leaves stops at the first unmapped entry, so we have to
+	 * loop round finding mapped ranges.
+	 */
+	while (begin < end) {
+		r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value);
+		if (r == -ENODATA)
+			break;
+
+		if (r)
+			return r;
+
+		if (begin >= end)
+			break;
+
+		r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
+		if (r)
+			return r;
+
+		total_count += count;
+	}
 
-	td->mapped_blocks -= count;
+	td->mapped_blocks -= total_count;
 	td->changed = 1;
 
 	/*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 807095f4c793..96a991821ae6 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -34,6 +34,7 @@
 
 #include <linux/kthread.h>
 #include <linux/blkdev.h>
+#include <linux/badblocks.h>
 #include <linux/sysctl.h>
 #include <linux/seq_file.h>
 #include <linux/fs.h>
@@ -709,8 +710,7 @@ void md_rdev_clear(struct md_rdev *rdev)
 		put_page(rdev->bb_page);
 		rdev->bb_page = NULL;
 	}
-	kfree(rdev->badblocks.page);
-	rdev->badblocks.page = NULL;
+	badblocks_exit(&rdev->badblocks);
 }
 EXPORT_SYMBOL_GPL(md_rdev_clear);
 
@@ -1360,8 +1360,6 @@ static __le32 calc_sb_1_csum(struct mdp_superblock_1 *sb)
 	return cpu_to_le32(csum);
 }
 
-static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
-			    int acknowledged);
 static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
 {
 	struct mdp_superblock_1 *sb;
@@ -1486,8 +1484,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 			count <<= sb->bblog_shift;
 			if (bb + 1 == 0)
 				break;
-			if (md_set_badblocks(&rdev->badblocks,
-					     sector, count, 1) == 0)
+			if (badblocks_set(&rdev->badblocks, sector, count, 1))
 				return -EINVAL;
 		}
 	} else if (sb->bblog_offset != 0)
@@ -2319,7 +2316,7 @@ repeat:
 			rdev_for_each(rdev, mddev) {
 				if (rdev->badblocks.changed) {
 					rdev->badblocks.changed = 0;
-					md_ack_all_badblocks(&rdev->badblocks);
+					ack_all_badblocks(&rdev->badblocks);
 					md_error(mddev, rdev);
 				}
 				clear_bit(Blocked, &rdev->flags);
@@ -2445,7 +2442,7 @@ repeat:
 			clear_bit(Blocked, &rdev->flags);
 
 		if (any_badblocks_changed)
-			md_ack_all_badblocks(&rdev->badblocks);
+			ack_all_badblocks(&rdev->badblocks);
 		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 	}
@@ -3046,11 +3043,17 @@ static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_
 static struct rdev_sysfs_entry rdev_recovery_start =
 __ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store);
 
-static ssize_t
-badblocks_show(struct badblocks *bb, char *page, int unack);
-static ssize_t
-badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack);
-
+/* sysfs access to bad-blocks list.
+ * We present two files.
+ * 'bad-blocks' lists sector numbers and lengths of ranges that
+ *    are recorded as bad.  The list is truncated to fit within
+ *    the one-page limit of sysfs.
+ *    Writing "sector length" to this file adds an acknowledged
+ *    bad block list.
+ * 'unacknowledged-bad-blocks' lists bad blocks that have not yet
+ *    been acknowledged.  Writing to this file adds bad blocks
+ *    without acknowledging them.  This is largely for testing.
+ */
 static ssize_t bb_show(struct md_rdev *rdev, char *page)
 {
 	return badblocks_show(&rdev->badblocks, page, 0);
@@ -3165,14 +3168,7 @@ int md_rdev_init(struct md_rdev *rdev)
 	 * This reserves the space even on arrays where it cannot
 	 * be used - I wonder if that matters
 	 */
-	rdev->badblocks.count = 0;
-	rdev->badblocks.shift = -1; /* disabled until explicitly enabled */
-	rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	seqlock_init(&rdev->badblocks.lock);
-	if (rdev->badblocks.page == NULL)
-		return -ENOMEM;
-
-	return 0;
+	return badblocks_init(&rdev->badblocks, 0);
 }
 EXPORT_SYMBOL_GPL(md_rdev_init);
 /*
@@ -8478,254 +8474,9 @@ void md_finish_reshape(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_finish_reshape);
 
-/* Bad block management.
- * We can record which blocks on each device are 'bad' and so just
- * fail those blocks, or that stripe, rather than the whole device.
- * Entries in the bad-block table are 64bits wide.  This comprises:
- * Length of bad-range, in sectors: 0-511 for lengths 1-512
- * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes)
- *  A 'shift' can be set so that larger blocks are tracked and
- *  consequently larger devices can be covered.
- * 'Acknowledged' flag - 1 bit. - the most significant bit.
- *
- * Locking of the bad-block table uses a seqlock so md_is_badblock
- * might need to retry if it is very unlucky.
- * We will sometimes want to check for bad blocks in a bi_end_io function,
- * so we use the write_seqlock_irq variant.
- *
- * When looking for a bad block we specify a range and want to
- * know if any block in the range is bad.  So we binary-search
- * to the last range that starts at-or-before the given endpoint,
- * (or "before the sector after the target range")
- * then see if it ends after the given start.
- * We return
- *  0 if there are no known bad blocks in the range
- *  1 if there are known bad block which are all acknowledged
- * -1 if there are bad blocks which have not yet been acknowledged in metadata.
- * plus the start/length of the first bad section we overlap.
- */
-int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
-		   sector_t *first_bad, int *bad_sectors)
-{
-	int hi;
-	int lo;
-	u64 *p = bb->page;
-	int rv;
-	sector_t target = s + sectors;
-	unsigned seq;
-
-	if (bb->shift > 0) {
-		/* round the start down, and the end up */
-		s >>= bb->shift;
-		target += (1<<bb->shift) - 1;
-		target >>= bb->shift;
-		sectors = target - s;
-	}
-	/* 'target' is now the first block after the bad range */
-
-retry:
-	seq = read_seqbegin(&bb->lock);
-	lo = 0;
-	rv = 0;
-	hi = bb->count;
-
-	/* Binary search between lo and hi for 'target'
-	 * i.e. for the last range that starts before 'target'
-	 */
-	/* INVARIANT: ranges before 'lo' and at-or-after 'hi'
-	 * are known not to be the last range before target.
-	 * VARIANT: hi-lo is the number of possible
-	 * ranges, and decreases until it reaches 1
-	 */
-	while (hi - lo > 1) {
-		int mid = (lo + hi) / 2;
-		sector_t a = BB_OFFSET(p[mid]);
-		if (a < target)
-			/* This could still be the one, earlier ranges
-			 * could not. */
-			lo = mid;
-		else
-			/* This and later ranges are definitely out. */
-			hi = mid;
-	}
-	/* 'lo' might be the last that started before target, but 'hi' isn't */
-	if (hi > lo) {
-		/* need to check all range that end after 's' to see if
-		 * any are unacknowledged.
-		 */
-		while (lo >= 0 &&
-		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
-			if (BB_OFFSET(p[lo]) < target) {
-				/* starts before the end, and finishes after
-				 * the start, so they must overlap
-				 */
-				if (rv != -1 && BB_ACK(p[lo]))
-					rv = 1;
-				else
-					rv = -1;
-				*first_bad = BB_OFFSET(p[lo]);
-				*bad_sectors = BB_LEN(p[lo]);
-			}
-			lo--;
-		}
-	}
-
-	if (read_seqretry(&bb->lock, seq))
-		goto retry;
-
-	return rv;
-}
-EXPORT_SYMBOL_GPL(md_is_badblock);
-
-/*
- * Add a range of bad blocks to the table.
- * This might extend the table, or might contract it
- * if two adjacent ranges can be merged.
- * We binary-search to find the 'insertion' point, then
- * decide how best to handle it.
- */
-static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
-			    int acknowledged)
-{
-	u64 *p;
-	int lo, hi;
-	int rv = 1;
-	unsigned long flags;
-
-	if (bb->shift < 0)
-		/* badblocks are disabled */
-		return 0;
-
-	if (bb->shift) {
-		/* round the start down, and the end up */
-		sector_t next = s + sectors;
-		s >>= bb->shift;
-		next += (1<<bb->shift) - 1;
-		next >>= bb->shift;
-		sectors = next - s;
-	}
-
-	write_seqlock_irqsave(&bb->lock, flags);
-
-	p = bb->page;
-	lo = 0;
-	hi = bb->count;
-	/* Find the last range that starts at-or-before 's' */
-	while (hi - lo > 1) {
-		int mid = (lo + hi) / 2;
-		sector_t a = BB_OFFSET(p[mid]);
-		if (a <= s)
-			lo = mid;
-		else
-			hi = mid;
-	}
-	if (hi > lo && BB_OFFSET(p[lo]) > s)
-		hi = lo;
-
-	if (hi > lo) {
-		/* we found a range that might merge with the start
-		 * of our new range
-		 */
-		sector_t a = BB_OFFSET(p[lo]);
-		sector_t e = a + BB_LEN(p[lo]);
-		int ack = BB_ACK(p[lo]);
-		if (e >= s) {
-			/* Yes, we can merge with a previous range */
-			if (s == a && s + sectors >= e)
-				/* new range covers old */
-				ack = acknowledged;
-			else
-				ack = ack && acknowledged;
-
-			if (e < s + sectors)
-				e = s + sectors;
-			if (e - a <= BB_MAX_LEN) {
-				p[lo] = BB_MAKE(a, e-a, ack);
-				s = e;
-			} else {
-				/* does not all fit in one range,
-				 * make p[lo] maximal
-				 */
-				if (BB_LEN(p[lo]) != BB_MAX_LEN)
-					p[lo] = BB_MAKE(a, BB_MAX_LEN, ack);
-				s = a + BB_MAX_LEN;
-			}
-			sectors = e - s;
-		}
-	}
-	if (sectors && hi < bb->count) {
-		/* 'hi' points to the first range that starts after 's'.
-		 * Maybe we can merge with the start of that range */
-		sector_t a = BB_OFFSET(p[hi]);
-		sector_t e = a + BB_LEN(p[hi]);
-		int ack = BB_ACK(p[hi]);
-		if (a <= s + sectors) {
-			/* merging is possible */
-			if (e <= s + sectors) {
-				/* full overlap */
-				e = s + sectors;
-				ack = acknowledged;
-			} else
-				ack = ack && acknowledged;
-
-			a = s;
-			if (e - a <= BB_MAX_LEN) {
-				p[hi] = BB_MAKE(a, e-a, ack);
-				s = e;
-			} else {
-				p[hi] = BB_MAKE(a, BB_MAX_LEN, ack);
-				s = a + BB_MAX_LEN;
-			}
-			sectors = e - s;
-			lo = hi;
-			hi++;
-		}
-	}
-	if (sectors == 0 && hi < bb->count) {
-		/* we might be able to combine lo and hi */
-		/* Note: 's' is at the end of 'lo' */
-		sector_t a = BB_OFFSET(p[hi]);
-		int lolen = BB_LEN(p[lo]);
-		int hilen = BB_LEN(p[hi]);
-		int newlen = lolen + hilen - (s - a);
-		if (s >= a && newlen < BB_MAX_LEN) {
-			/* yes, we can combine them */
-			int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]);
-			p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack);
-			memmove(p + hi, p + hi + 1,
-				(bb->count - hi - 1) * 8);
-			bb->count--;
-		}
-	}
-	while (sectors) {
-		/* didn't merge (it all).
-		 * Need to add a range just before 'hi' */
-		if (bb->count >= MD_MAX_BADBLOCKS) {
-			/* No room for more */
-			rv = 0;
-			break;
-		} else {
-			int this_sectors = sectors;
-			memmove(p + hi + 1, p + hi,
-				(bb->count - hi) * 8);
-			bb->count++;
-
-			if (this_sectors > BB_MAX_LEN)
-				this_sectors = BB_MAX_LEN;
-			p[hi] = BB_MAKE(s, this_sectors, acknowledged);
-			sectors -= this_sectors;
-			s += this_sectors;
-		}
-	}
-
-	bb->changed = 1;
-	if (!acknowledged)
-		bb->unacked_exist = 1;
-	write_sequnlock_irqrestore(&bb->lock, flags);
-
-	return rv;
-}
+/* Bad block management */
 
+/* Returns 1 on success, 0 on failure */
 int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		       int is_new)
 {
@@ -8734,114 +8485,19 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		s += rdev->new_data_offset;
 	else
 		s += rdev->data_offset;
-	rv = md_set_badblocks(&rdev->badblocks,
-			      s, sectors, 0);
-	if (rv) {
+	rv = badblocks_set(&rdev->badblocks, s, sectors, 0);
+	if (rv == 0) {
 		/* Make sure they get written out promptly */
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
 		set_bit(MD_CHANGE_PENDING, &rdev->mddev->flags);
 		md_wakeup_thread(rdev->mddev->thread);
-	}
-	return rv;
+		return 1;
+	} else
+		return 0;
 }
 EXPORT_SYMBOL_GPL(rdev_set_badblocks);
 
-/*
- * Remove a range of bad blocks from the table.
- * This may involve extending the table if we spilt a region,
- * but it must not fail.  So if the table becomes full, we just
- * drop the remove request.
- */
-static int md_clear_badblocks(struct badblocks *bb, sector_t s, int sectors)
-{
-	u64 *p;
-	int lo, hi;
-	sector_t target = s + sectors;
-	int rv = 0;
-
-	if (bb->shift > 0) {
-		/* When clearing we round the start up and the end down.
-		 * This should not matter as the shift should align with
-		 * the block size and no rounding should ever be needed.
-		 * However it is better the think a block is bad when it
-		 * isn't than to think a block is not bad when it is.
-		 */
-		s += (1<<bb->shift) - 1;
-		s >>= bb->shift;
-		target >>= bb->shift;
-		sectors = target - s;
-	}
-
-	write_seqlock_irq(&bb->lock);
-
-	p = bb->page;
-	lo = 0;
-	hi = bb->count;
-	/* Find the last range that starts before 'target' */
-	while (hi - lo > 1) {
-		int mid = (lo + hi) / 2;
-		sector_t a = BB_OFFSET(p[mid]);
-		if (a < target)
-			lo = mid;
-		else
-			hi = mid;
-	}
-	if (hi > lo) {
-		/* p[lo] is the last range that could overlap the
-		 * current range.  Earlier ranges could also overlap,
-		 * but only this one can overlap the end of the range.
-		 */
-		if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
-			/* Partial overlap, leave the tail of this range */
-			int ack = BB_ACK(p[lo]);
-			sector_t a = BB_OFFSET(p[lo]);
-			sector_t end = a + BB_LEN(p[lo]);
-
-			if (a < s) {
-				/* we need to split this range */
-				if (bb->count >= MD_MAX_BADBLOCKS) {
-					rv = -ENOSPC;
-					goto out;
-				}
-				memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
-				bb->count++;
-				p[lo] = BB_MAKE(a, s-a, ack);
-				lo++;
-			}
-			p[lo] = BB_MAKE(target, end - target, ack);
-			/* there is no longer an overlap */
-			hi = lo;
-			lo--;
-		}
-		while (lo >= 0 &&
-		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
-			/* This range does overlap */
-			if (BB_OFFSET(p[lo]) < s) {
-				/* Keep the early parts of this range. */
-				int ack = BB_ACK(p[lo]);
-				sector_t start = BB_OFFSET(p[lo]);
-				p[lo] = BB_MAKE(start, s - start, ack);
-				/* now low doesn't overlap, so.. */
-				break;
-			}
-			lo--;
-		}
-		/* 'lo' is strictly before, 'hi' is strictly after,
-		 * anything between needs to be discarded
-		 */
-		if (hi - lo > 1) {
-			memmove(p+lo+1, p+hi, (bb->count - hi) * 8);
-			bb->count -= (hi - lo - 1);
-		}
-	}
-
-	bb->changed = 1;
-out:
-	write_sequnlock_irq(&bb->lock);
-	return rv;
-}
-
 int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			 int is_new)
 {
@@ -8849,133 +8505,11 @@ int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		s += rdev->new_data_offset;
 	else
 		s += rdev->data_offset;
-	return md_clear_badblocks(&rdev->badblocks,
+	return badblocks_clear(&rdev->badblocks,
 				  s, sectors);
 }
 EXPORT_SYMBOL_GPL(rdev_clear_badblocks);
 
-/*
- * Acknowledge all bad blocks in a list.
- * This only succeeds if ->changed is clear.  It is used by
- * in-kernel metadata updates
- */
-void md_ack_all_badblocks(struct badblocks *bb)
-{
-	if (bb->page == NULL || bb->changed)
-		/* no point even trying */
-		return;
-	write_seqlock_irq(&bb->lock);
-
-	if (bb->changed == 0 && bb->unacked_exist) {
-		u64 *p = bb->page;
-		int i;
-		for (i = 0; i < bb->count ; i++) {
-			if (!BB_ACK(p[i])) {
-				sector_t start = BB_OFFSET(p[i]);
-				int len = BB_LEN(p[i]);
-				p[i] = BB_MAKE(start, len, 1);
-			}
-		}
-		bb->unacked_exist = 0;
-	}
-	write_sequnlock_irq(&bb->lock);
-}
-EXPORT_SYMBOL_GPL(md_ack_all_badblocks);
-
-/* sysfs access to bad-blocks list.
- * We present two files.
- * 'bad-blocks' lists sector numbers and lengths of ranges that
- *    are recorded as bad.  The list is truncated to fit within
- *    the one-page limit of sysfs.
- *    Writing "sector length" to this file adds an acknowledged
- *    bad block list.
- * 'unacknowledged-bad-blocks' lists bad blocks that have not yet
- *    been acknowledged.  Writing to this file adds bad blocks
- *    without acknowledging them.  This is largely for testing.
- */
-
-static ssize_t
-badblocks_show(struct badblocks *bb, char *page, int unack)
-{
-	size_t len;
-	int i;
-	u64 *p = bb->page;
-	unsigned seq;
-
-	if (bb->shift < 0)
-		return 0;
-
-retry:
-	seq = read_seqbegin(&bb->lock);
-
-	len = 0;
-	i = 0;
-
-	while (len < PAGE_SIZE && i < bb->count) {
-		sector_t s = BB_OFFSET(p[i]);
-		unsigned int length = BB_LEN(p[i]);
-		int ack = BB_ACK(p[i]);
-		i++;
-
-		if (unack && ack)
-			continue;
-
-		len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n",
-				(unsigned long long)s << bb->shift,
-				length << bb->shift);
-	}
-	if (unack && len == 0)
-		bb->unacked_exist = 0;
-
-	if (read_seqretry(&bb->lock, seq))
-		goto retry;
-
-	return len;
-}
-
-#define DO_DEBUG 1
-
-static ssize_t
-badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack)
-{
-	unsigned long long sector;
-	int length;
-	char newline;
-#ifdef DO_DEBUG
-	/* Allow clearing via sysfs *only* for testing/debugging.
-	 * Normally only a successful write may clear a badblock
-	 */
-	int clear = 0;
-	if (page[0] == '-') {
-		clear = 1;
-		page++;
-	}
-#endif /* DO_DEBUG */
-
-	switch (sscanf(page, "%llu %d%c", &sector, &length, &newline)) {
-	case 3:
-		if (newline != '\n')
-			return -EINVAL;
-	case 2:
-		if (length <= 0)
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-#ifdef DO_DEBUG
-	if (clear) {
-		md_clear_badblocks(bb, sector, length);
-		return len;
-	}
-#endif /* DO_DEBUG */
-	if (md_set_badblocks(bb, sector, length, !unack))
-		return len;
-	else
-		return -ENOSPC;
-}
-
 static int md_notify_reboot(struct notifier_block *this,
 			    unsigned long code, void *x)
 {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2bea51edfab7..389afc420db6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -17,6 +17,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/badblocks.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/mm.h>
@@ -28,13 +29,6 @@
 
 #define MaxSector (~(sector_t)0)
 
-/* Bad block numbers are stored sorted in a single page.
- * 64bits is used for each block or extent.
- * 54 bits are sector number, 9 bits are extent size,
- * 1 bit is an 'acknowledged' flag.
- */
-#define MD_MAX_BADBLOCKS	(PAGE_SIZE/8)
-
 /*
  * MD's 'extended' device
  */
@@ -117,22 +111,7 @@ struct md_rdev {
 	struct kernfs_node *sysfs_state; /* handle for 'state'
 					   * sysfs entry */
 
-	struct badblocks {
-		int	count;		/* count of bad blocks */
-		int	unacked_exist;	/* there probably are unacknowledged
-					 * bad blocks.  This is only cleared
-					 * when a read discovers none
-					 */
-		int	shift;		/* shift from sectors to block size
-					 * a -ve shift means badblocks are
-					 * disabled.*/
-		u64	*page;		/* badblock list */
-		int	changed;
-		seqlock_t lock;
-
-		sector_t sector;
-		sector_t size;		/* in sectors */
-	} badblocks;
+	struct badblocks badblocks;
 };
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
@@ -185,22 +164,11 @@ enum flag_bits {
 				 */
 };
 
-#define BB_LEN_MASK	(0x00000000000001FFULL)
-#define BB_OFFSET_MASK	(0x7FFFFFFFFFFFFE00ULL)
-#define BB_ACK_MASK	(0x8000000000000000ULL)
-#define BB_MAX_LEN	512
-#define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
-#define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
-#define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
-#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
-
-extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
-			  sector_t *first_bad, int *bad_sectors);
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 			      sector_t *first_bad, int *bad_sectors)
 {
 	if (unlikely(rdev->badblocks.count)) {
-		int rv = md_is_badblock(&rdev->badblocks, rdev->data_offset + s,
+		int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s,
 					sectors,
 					first_bad, bad_sectors);
 		if (rv)
@@ -213,8 +181,6 @@ extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				int is_new);
-extern void md_ack_all_badblocks(struct badblocks *bb);
-
 struct md_cluster_info;
 
 struct mddev {
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index c573402033b2..b1ced58eb5e1 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -63,6 +63,11 @@ int lower_bound(struct btree_node *n, uint64_t key)
 	return bsearch(n, key, 0);
 }
 
+static int upper_bound(struct btree_node *n, uint64_t key)
+{
+	return bsearch(n, key, 1);
+}
+
 void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
 		  struct dm_btree_value_type *vt)
 {
@@ -252,6 +257,16 @@ static void pop_frame(struct del_stack *s)
 	dm_tm_unlock(s->tm, f->b);
 }
 
+static void unlock_all_frames(struct del_stack *s)
+{
+	struct frame *f;
+
+	while (unprocessed_frames(s)) {
+		f = s->spine + s->top--;
+		dm_tm_unlock(s->tm, f->b);
+	}
+}
+
 int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 {
 	int r;
@@ -308,9 +323,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 			pop_frame(s);
 		}
 	}
-
 out:
+	if (r) {
+		/* cleanup all frames of del_stack */
+		unlock_all_frames(s);
+	}
 	kfree(s);
+
 	return r;
 }
 EXPORT_SYMBOL_GPL(dm_btree_del);
@@ -392,6 +411,82 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
 }
 EXPORT_SYMBOL_GPL(dm_btree_lookup);
 
+static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t root,
+				       uint64_t key, uint64_t *rkey, void *value_le)
+{
+	int r, i;
+	uint32_t flags, nr_entries;
+	struct dm_block *node;
+	struct btree_node *n;
+
+	r = bn_read_lock(info, root, &node);
+	if (r)
+		return r;
+
+	n = dm_block_data(node);
+	flags = le32_to_cpu(n->header.flags);
+	nr_entries = le32_to_cpu(n->header.nr_entries);
+
+	if (flags & INTERNAL_NODE) {
+		i = lower_bound(n, key);
+		if (i < 0 || i >= nr_entries) {
+			r = -ENODATA;
+			goto out;
+		}
+
+		r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
+		if (r == -ENODATA && i < (nr_entries - 1)) {
+			i++;
+			r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
+		}
+
+	} else {
+		i = upper_bound(n, key);
+		if (i < 0 || i >= nr_entries) {
+			r = -ENODATA;
+			goto out;
+		}
+
+		*rkey = le64_to_cpu(n->keys[i]);
+		memcpy(value_le, value_ptr(n, i), info->value_type.size);
+	}
+out:
+	dm_tm_unlock(info->tm, node);
+	return r;
+}
+
+int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
+			 uint64_t *keys, uint64_t *rkey, void *value_le)
+{
+	unsigned level;
+	int r = -ENODATA;
+	__le64 internal_value_le;
+	struct ro_spine spine;
+
+	init_ro_spine(&spine, info);
+	for (level = 0; level < info->levels - 1u; level++) {
+		r = btree_lookup_raw(&spine, root, keys[level],
+				     lower_bound, rkey,
+				     &internal_value_le, sizeof(uint64_t));
+		if (r)
+			goto out;
+
+		if (*rkey != keys[level]) {
+			r = -ENODATA;
+			goto out;
+		}
+
+		root = le64_to_cpu(internal_value_le);
+	}
+
+	r = dm_btree_lookup_next_single(info, root, keys[level], rkey, value_le);
+out:
+	exit_ro_spine(&spine);
+	return r;
+}
+
+EXPORT_SYMBOL_GPL(dm_btree_lookup_next);
+
 /*
  * Splits a node by creating a sibling node and shifting half the nodes
  * contents across.  Assumes there is a parent node, and it has room for
@@ -473,8 +568,10 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index,
 
 	r = insert_at(sizeof(__le64), pn, parent_index + 1,
 		      le64_to_cpu(rn->keys[0]), &location);
-	if (r)
+	if (r) {
+		unlock_block(s->info, right);
 		return r;
+	}
 
 	if (key < le64_to_cpu(rn->keys[0])) {
 		unlock_block(s->info, right);
diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h
index 11d8cf78621d..c74301fa5a37 100644
--- a/drivers/md/persistent-data/dm-btree.h
+++ b/drivers/md/persistent-data/dm-btree.h
@@ -110,6 +110,13 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
 		    uint64_t *keys, void *value_le);
 
 /*
+ * Tries to find the first key where the bottom level key is >= to that
+ * given.  Useful for skipping empty sections of the btree.
+ */
+int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
+			 uint64_t *keys, uint64_t *rkey, void *value_le);
+
+/*
  * Insertion (or overwrite an existing value).  O(ln(n))
  */
 int dm_btree_insert(struct dm_btree_info *info, dm_block_t root,
@@ -135,9 +142,10 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 		    uint64_t *keys, dm_block_t *new_root);
 
 /*
- * Removes values between 'keys' and keys2, where keys2 is keys with the
- * final key replaced with 'end_key'.  'end_key' is the one-past-the-end
- * value.  'keys' may be altered.
+ * Removes a _contiguous_ run of values starting from 'keys' and not
+ * reaching keys2 (where keys2 is keys with the final key replaced with
+ * 'end_key').  'end_key' is the one-past-the-end value.  'keys' may be
+ * altered.
  */
 int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root,
 			   uint64_t *keys, uint64_t end_key,
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 53091295fce9..fca6dbcf9a47 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -136,7 +136,7 @@ static int brb_push(struct bop_ring_buffer *brb,
 	return 0;
 }
 
-static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result)
 {
 	struct block_op *bop;
 
@@ -147,6 +147,17 @@ static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
 	result->type = bop->type;
 	result->block = bop->block;
 
+	return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb)
+{
+	struct block_op *bop;
+
+	if (brb_empty(brb))
+		return -ENODATA;
+
+	bop = brb->bops + brb->begin;
 	brb->begin = brb_next(brb, brb->begin);
 
 	return 0;
@@ -211,7 +222,7 @@ static int apply_bops(struct sm_metadata *smm)
 	while (!brb_empty(&smm->uncommitted)) {
 		struct block_op bop;
 
-		r = brb_pop(&smm->uncommitted, &bop);
+		r = brb_peek(&smm->uncommitted, &bop);
 		if (r) {
 			DMERR("bug in bop ring buffer");
 			break;
@@ -220,6 +231,8 @@ static int apply_bops(struct sm_metadata *smm)
 		r = commit_bop(smm, &bop);
 		if (r)
 			break;
+
+		brb_pop(&smm->uncommitted);
 	}
 
 	return r;
@@ -683,7 +696,6 @@ static struct dm_space_map bootstrap_ops = {
 static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 {
 	int r, i;
-	enum allocation_event ev;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 	dm_block_t old_len = smm->ll.nr_blocks;
 
@@ -705,11 +717,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 	 * allocate any new blocks.
 	 */
 	do {
-		for (i = old_len; !r && i < smm->begin; i++) {
-			r = sm_ll_inc(&smm->ll, i, &ev);
-			if (r)
-				goto out;
-		}
+		for (i = old_len; !r && i < smm->begin; i++)
+			r = add_bop(smm, BOP_INC, i);
+
+		if (r)
+			goto out;
+
 		old_len = smm->begin;
 
 		r = apply_bops(smm);
@@ -754,7 +767,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 {
 	int r;
 	dm_block_t i;
-	enum allocation_event ev;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
 	smm->begin = superblock + 1;
@@ -782,7 +794,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 	 * allocated blocks that they were built from.
 	 */
 	for (i = superblock; !r && i < smm->begin; i++)
-		r = sm_ll_inc(&smm->ll, i, &ev);
+		r = add_bop(smm, BOP_INC, i);
 
 	if (r)
 		return r;