[PATCH 0/3] Badblock tracking for gendisks

[PATCH 0/3] Badblock tracking for gendisks

[Vishal Verma]

Patch 1 copies badblock management code into a header of its own,
making it generally available. It follows common libraries of code
such as linked lists, where anyone may embed a core data structure
in another place, and use the provided accessor functions to
manipulate the data.

Patch 2 adds badblock tracking to gendisks (in preparation for use
by NVDIMM devices). Right now, it is turned on unconditionally - I'd
appreciate comments on if that is the right path.

Patch 3 converts md over to use the new badblocks 'library'. I have
done some pretty simple testing on this - created a raid 1 device,
made sure the sysfs entries show up, and can be used to add and view
badblocks. A closer look by the md folks would be nice here.

Vishal Verma (3):
  badblocks: Add core badblock management code
  block: Add badblock management for gendisks
  md: convert to use the generic badblocks code

 block/genhd.c             |  64 ++++++
 drivers/md/md.c           | 495 ++------------------------------------------
 drivers/md/md.h           |  31 +--
 include/linux/badblocks.h | 512 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/genhd.h     |   6 +
 5 files changed, 603 insertions(+), 505 deletions(-)
 create mode 100644 include/linux/badblocks.h

-- 
2.5.0

[PATCH 1/3] badblocks: Add core badblock management code

[Vishal Verma]

Take the core badblocks implementation from md, and make it generally
available. This follows the same style as kernel implementations of
linked lists, rb-trees etc, where you can have a structure that can be
embedded anywhere, and accessor functions to manipulate the data.

The only changes in this copy of the code are ones to generalize
function/variable names from md-specific ones. Also add init and free
functions.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 include/linux/badblocks.h | 512 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 512 insertions(+)
 create mode 100644 include/linux/badblocks.h

diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h
new file mode 100644
index 0000000..94fa348
--- /dev/null
+++ b/include/linux/badblocks.h
@@ -0,0 +1,512 @@
+#ifndef _LINUX_BADBLOCKS_H
+#define _LINUX_BADBLOCKS_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+
+#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))
+
+/* 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 MAX_BADBLOCKS	(PAGE_SIZE/8)
+
+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 */
+};
+
+/* 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 badblocks_check
+ * 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.
+ */
+static inline int badblocks_check(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;
+}
+
+/*
+ * 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 inline int badblocks_set(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 >= 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;
+}
+
+/*
+ * 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 inline int badblocks_clear(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 >= 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;
+}
+
+/*
+ * Acknowledge all bad blocks in a list.
+ * This only succeeds if ->changed is clear.  It is used by
+ * in-kernel metadata updates
+ */
+static inline void 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);
+}
+
+/* sysfs access to bad-blocks list. */
+static inline 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 inline 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) {
+		badblocks_clear(bb, sector, length);
+		return len;
+	}
+#endif /* DO_DEBUG */
+	if (badblocks_set(bb, sector, length, !unack))
+		return len;
+	else
+		return -ENOSPC;
+}
+
+static inline int badblocks_init(struct badblocks *bb, int enable)
+{
+	bb->count = 0;
+	if (enable)
+		bb->shift = 0;
+	else
+		bb->shift = -1;
+	bb->page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (bb->page == NULL)
+		return -ENOMEM;
+	seqlock_init(&bb->lock);
+
+	return 0;
+}
+
+static inline void badblocks_free(struct badblocks *bb)
+{
+	kfree(bb->page);
+}
+
+#endif
-- 
2.5.0

Re: [PATCH 1/3] badblocks: Add core badblock management code

[Jens Axboe]

On 11/20/2015 05:49 PM, Vishal Verma wrote:
> Take the core badblocks implementation from md, and make it generally
> available. This follows the same style as kernel implementations of
> linked lists, rb-trees etc, where you can have a structure that can be
> embedded anywhere, and accessor functions to manipulate the data.
>
> The only changes in this copy of the code are ones to generalize
> function/variable names from md-specific ones. Also add init and free
> functions.

Split this into a .c file with the code.

-- 
Jens Axboe

[PATCH 2/3] block: Add badblock management for gendisks

[Vishal Verma]

NVDIMM devices, which can behave more like DRAM rather than block
devices, may develop bad cache lines, or 'poison'. A block device
exposed by the pmem driver can then consume poison via a read (or
write), and cause a machine check. On platforms without machine
check recovery features, this would mean a crash.

The block device maintaining a runtime list of all known sectors that
have poison can directly avoid this, and also provide a path forward
to enable proper handling/recovery for DAX faults on such a device.

Use the new badblock management interfaces to add a badblocks list to
gendisks.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 block/genhd.c         | 64 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/genhd.h |  6 +++++
 2 files changed, 70 insertions(+)

diff --git a/block/genhd.c b/block/genhd.c
index 0c706f3..4209c32 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/log2.h>
 #include <linux/pm_runtime.h>
+#include <linux/badblocks.h>
 
 #include "blk.h"
 
@@ -505,6 +506,20 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
+static void disk_alloc_badblocks(struct gendisk *disk)
+{
+	disk->bb = kzalloc(sizeof(disk->bb), GFP_KERNEL);
+	if (!disk->bb) {
+		pr_warn("%s: failed to allocate space for badblocks\n",
+			disk->disk_name);
+		return;
+	}
+
+	if (badblocks_init(disk->bb, 1))
+		pr_warn("%s: failed to initialize badblocks\n",
+			disk->disk_name);
+}
+
 static void register_disk(struct gendisk *disk)
 {
 	struct device *ddev = disk_to_dev(disk);
@@ -609,6 +624,7 @@ void add_disk(struct gendisk *disk)
 	disk->first_minor = MINOR(devt);
 
 	disk_alloc_events(disk);
+	disk_alloc_badblocks(disk);
 
 	/* Register BDI before referencing it from bdev */
 	bdi = &disk->queue->backing_dev_info;
@@ -657,6 +673,9 @@ void del_gendisk(struct gendisk *disk)
 	blk_unregister_queue(disk);
 	blk_unregister_region(disk_devt(disk), disk->minors);
 
+	badblocks_free(disk->bb);
+	kfree(disk->bb);
+
 	part_stat_set_all(&disk->part0, 0);
 	disk->part0.stamp = 0;
 
@@ -670,6 +689,48 @@ void del_gendisk(struct gendisk *disk)
 }
 EXPORT_SYMBOL(del_gendisk);
 
+/*
+ * The gendisk usage of badblocks does not track acknowledgements for
+ * badblocks. We always assume they are acknowledged.
+ */
+int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors,
+		   sector_t *first_bad, int *bad_sectors)
+{
+	return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors);
+}
+EXPORT_SYMBOL(disk_check_badblocks);
+
+int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors)
+{
+	return badblocks_set(disk->bb, s, sectors, 1);
+}
+EXPORT_SYMBOL(disk_set_badblocks);
+
+int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors)
+{
+	return badblocks_clear(disk->bb, s, sectors);
+}
+EXPORT_SYMBOL(disk_clear_badblocks);
+
+/* sysfs access to bad-blocks list. */
+static ssize_t disk_badblocks_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return badblocks_show(disk->bb, page, 0);
+}
+
+static ssize_t disk_badblocks_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *page, size_t len)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return badblocks_store(disk->bb, page, len, 0);
+}
+
 /**
  * get_gendisk - get partitioning information for a given device
  * @devt: device to get partitioning information for
@@ -988,6 +1049,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
+		disk_badblocks_store);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -1009,6 +1072,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
+	&dev_attr_badblocks.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 2adbfa6..5563bde 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -162,6 +162,7 @@ struct disk_part_tbl {
 };
 
 struct disk_events;
+struct badblocks;
 
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
@@ -201,6 +202,7 @@ struct gendisk {
 	struct blk_integrity *integrity;
 #endif
 	int node_id;
+	struct badblocks *bb;
 };
 
 static inline struct gendisk *part_to_disk(struct hd_struct *part)
@@ -421,6 +423,10 @@ extern void add_disk(struct gendisk *disk);
 extern void del_gendisk(struct gendisk *gp);
 extern struct gendisk *get_gendisk(dev_t dev, int *partno);
 extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
+extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors,
+		   sector_t *first_bad, int *bad_sectors);
+extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors);
+extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors);
 
 extern void set_device_ro(struct block_device *bdev, int flag);
 extern void set_disk_ro(struct gendisk *disk, int flag);
-- 
2.5.0

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Jeff Moyer]

Vishal Verma <vishal.l.verma@intel.com> writes:

> NVDIMM devices, which can behave more like DRAM rather than block
> devices, may develop bad cache lines, or 'poison'. A block device
> exposed by the pmem driver can then consume poison via a read (or
> write), and cause a machine check. On platforms without machine
> check recovery features, this would mean a crash.
>
> The block device maintaining a runtime list of all known sectors that
> have poison can directly avoid this, and also provide a path forward
> to enable proper handling/recovery for DAX faults on such a device.
>
> Use the new badblock management interfaces to add a badblocks list to
> gendisks.

Because disk_alloc_badblocks can fail, you need to check for a NULL
disk->bb in all of the utility functions you've defined.

Cheers,
Jeff

>
> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
> ---
>  block/genhd.c         | 64 +++++++++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/genhd.h |  6 +++++
>  2 files changed, 70 insertions(+)
>
> diff --git a/block/genhd.c b/block/genhd.c
> index 0c706f3..4209c32 100644
> --- a/block/genhd.c
> +++ b/block/genhd.c
> @@ -20,6 +20,7 @@
>  #include <linux/idr.h>
>  #include <linux/log2.h>
>  #include <linux/pm_runtime.h>
> +#include <linux/badblocks.h>
>  
>  #include "blk.h"
>  
> @@ -505,6 +506,20 @@ static int exact_lock(dev_t devt, void *data)
>  	return 0;
>  }
>  
> +static void disk_alloc_badblocks(struct gendisk *disk)
> +{
> +	disk->bb = kzalloc(sizeof(disk->bb), GFP_KERNEL);
> +	if (!disk->bb) {
> +		pr_warn("%s: failed to allocate space for badblocks\n",
> +			disk->disk_name);
> +		return;
> +	}
> +
> +	if (badblocks_init(disk->bb, 1))
> +		pr_warn("%s: failed to initialize badblocks\n",
> +			disk->disk_name);
> +}
> +
>  static void register_disk(struct gendisk *disk)
>  {
>  	struct device *ddev = disk_to_dev(disk);
> @@ -609,6 +624,7 @@ void add_disk(struct gendisk *disk)
>  	disk->first_minor = MINOR(devt);
>  
>  	disk_alloc_events(disk);
> +	disk_alloc_badblocks(disk);
>  
>  	/* Register BDI before referencing it from bdev */
>  	bdi = &disk->queue->backing_dev_info;
> @@ -657,6 +673,9 @@ void del_gendisk(struct gendisk *disk)
>  	blk_unregister_queue(disk);
>  	blk_unregister_region(disk_devt(disk), disk->minors);
>  
> +	badblocks_free(disk->bb);
> +	kfree(disk->bb);
> +
>  	part_stat_set_all(&disk->part0, 0);
>  	disk->part0.stamp = 0;
>  
> @@ -670,6 +689,48 @@ void del_gendisk(struct gendisk *disk)
>  }
>  EXPORT_SYMBOL(del_gendisk);
>  
> +/*
> + * The gendisk usage of badblocks does not track acknowledgements for
> + * badblocks. We always assume they are acknowledged.
> + */
> +int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors,
> +		   sector_t *first_bad, int *bad_sectors)
> +{
> +	return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors);
> +}
> +EXPORT_SYMBOL(disk_check_badblocks);
> +
> +int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors)
> +{
> +	return badblocks_set(disk->bb, s, sectors, 1);
> +}
> +EXPORT_SYMBOL(disk_set_badblocks);
> +
> +int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors)
> +{
> +	return badblocks_clear(disk->bb, s, sectors);
> +}
> +EXPORT_SYMBOL(disk_clear_badblocks);
> +
> +/* sysfs access to bad-blocks list. */
> +static ssize_t disk_badblocks_show(struct device *dev,
> +					struct device_attribute *attr,
> +					char *page)
> +{
> +	struct gendisk *disk = dev_to_disk(dev);
> +
> +	return badblocks_show(disk->bb, page, 0);
> +}
> +
> +static ssize_t disk_badblocks_store(struct device *dev,
> +					struct device_attribute *attr,
> +					const char *page, size_t len)
> +{
> +	struct gendisk *disk = dev_to_disk(dev);
> +
> +	return badblocks_store(disk->bb, page, len, 0);
> +}
> +
>  /**
>   * get_gendisk - get partitioning information for a given device
>   * @devt: device to get partitioning information for
> @@ -988,6 +1049,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
>  static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
>  static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
>  static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
> +static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
> +		disk_badblocks_store);
>  #ifdef CONFIG_FAIL_MAKE_REQUEST
>  static struct device_attribute dev_attr_fail =
>  	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
> @@ -1009,6 +1072,7 @@ static struct attribute *disk_attrs[] = {
>  	&dev_attr_capability.attr,
>  	&dev_attr_stat.attr,
>  	&dev_attr_inflight.attr,
> +	&dev_attr_badblocks.attr,
>  #ifdef CONFIG_FAIL_MAKE_REQUEST
>  	&dev_attr_fail.attr,
>  #endif
> diff --git a/include/linux/genhd.h b/include/linux/genhd.h
> index 2adbfa6..5563bde 100644
> --- a/include/linux/genhd.h
> +++ b/include/linux/genhd.h
> @@ -162,6 +162,7 @@ struct disk_part_tbl {
>  };
>  
>  struct disk_events;
> +struct badblocks;
>  
>  struct gendisk {
>  	/* major, first_minor and minors are input parameters only,
> @@ -201,6 +202,7 @@ struct gendisk {
>  	struct blk_integrity *integrity;
>  #endif
>  	int node_id;
> +	struct badblocks *bb;
>  };
>  
>  static inline struct gendisk *part_to_disk(struct hd_struct *part)
> @@ -421,6 +423,10 @@ extern void add_disk(struct gendisk *disk);
>  extern void del_gendisk(struct gendisk *gp);
>  extern struct gendisk *get_gendisk(dev_t dev, int *partno);
>  extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
> +extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors,
> +		   sector_t *first_bad, int *bad_sectors);
> +extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors);
> +extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors);
>  
>  extern void set_device_ro(struct block_device *bdev, int flag);
>  extern void set_disk_ro(struct gendisk *disk, int flag);

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Verma, Vishal L]

On Tue, 2015-11-24 at 10:34 -0500, Jeff Moyer wrote:
> Vishal Verma <vishal.l.verma@intel.com> writes:
> 
> > NVDIMM devices, which can behave more like DRAM rather than block
> > devices, may develop bad cache lines, or 'poison'. A block device
> > exposed by the pmem driver can then consume poison via a read (or
> > write), and cause a machine check. On platforms without machine
> > check recovery features, this would mean a crash.
> > 
> > The block device maintaining a runtime list of all known sectors
> > that
> > have poison can directly avoid this, and also provide a path forward
> > to enable proper handling/recovery for DAX faults on such a device.
> > 
> > Use the new badblock management interfaces to add a badblocks list
> > to
> > gendisks.
> 
> Because disk_alloc_badblocks can fail, you need to check for a NULL
> disk->bb in all of the utility functions you've defined.
> 

Thanks, Jeff - I'll fix this. I have a handful of other fixes queued up
too, will send out a v2 soon.

	-Vishal

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Jeff Moyer]

"Verma, Vishal L" <vishal.l.verma@intel.com> writes:

> On Tue, 2015-11-24 at 10:34 -0500, Jeff Moyer wrote:
>> Vishal Verma <vishal.l.verma@intel.com> writes:
>> 
>> > NVDIMM devices, which can behave more like DRAM rather than block
>> > devices, may develop bad cache lines, or 'poison'. A block device
>> > exposed by the pmem driver can then consume poison via a read (or
>> > write), and cause a machine check. On platforms without machine
>> > check recovery features, this would mean a crash.
>> > 
>> > The block device maintaining a runtime list of all known sectors
>> > that
>> > have poison can directly avoid this, and also provide a path forward
>> > to enable proper handling/recovery for DAX faults on such a device.
>> > 
>> > Use the new badblock management interfaces to add a badblocks list
>> > to
>> > gendisks.
>> 
>> Because disk_alloc_badblocks can fail, you need to check for a NULL
>> disk->bb in all of the utility functions you've defined.
>> 
>
> Thanks, Jeff - I'll fix this. I have a handful of other fixes queued up
> too, will send out a v2 soon.

I'm not sure whether it makes sense to continue without badblock
management for the RAID code.  I was hoping Neil would comment on that.

-Jeff

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Verma, Vishal L]

On Tue, 2015-11-24 at 14:14 -0500, Jeff Moyer wrote:
> 
> I'm not sure whether it makes sense to continue without badblock
> management for the RAID code.  I was hoping Neil would comment on
> that.
> 
> -Jeff

Not sure I follow? I believe I've kept all the badblocks functionality
RAID already had..


On a related note, something I observed when testing with md:

md's badblock list is per-device, and can be seen at:
	/sys/block/md0/md/dev-pmem0/bad_blocks

Now if we have badblocks in the gendisks too, there is also:
	/sys/block/pmem0/bad_blocks

The two are separate 'accounts' maintained by separate drivers (md for
the former, and pmem for the latter). This can potentially be
confusing..

Should we consolidate the two, i.e. make md (re)use the gendisk
badblocks for its purposes too?

	-Vishal

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Dan Williams]

On Tue, Nov 24, 2015 at 12:10 PM, Verma, Vishal L
<vishal.l.verma@intel.com> wrote:
> On Tue, 2015-11-24 at 14:14 -0500, Jeff Moyer wrote:
>>
>> I'm not sure whether it makes sense to continue without badblock
>> management for the RAID code.  I was hoping Neil would comment on
>> that.
>>
>> -Jeff
>
> Not sure I follow? I believe I've kept all the badblocks functionality
> RAID already had..
>
>
> On a related note, something I observed when testing with md:
>
> md's badblock list is per-device, and can be seen at:
>         /sys/block/md0/md/dev-pmem0/bad_blocks
>
> Now if we have badblocks in the gendisks too, there is also:
>         /sys/block/pmem0/bad_blocks
>
> The two are separate 'accounts' maintained by separate drivers (md for
> the former, and pmem for the latter). This can potentially be
> confusing..
>
> Should we consolidate the two, i.e. make md (re)use the gendisk
> badblocks for its purposes too?

If we get agreement that tracking bad blocks at the gendisk is useful
for more than just nvdimms then yes, I think it makes sense to move md
bad_blocks to the gendisk layer.  That is provided we can add a
symlink to make the move transparent to existing md userspace tooling.

The use cases I can envision being useful for other disks is:

1/ Bypassing / avoiding known bad blocks on disks / drivers that
inject long completion latency for error handling.

2/ Simulating bad blocks for disks that can't store them locally.
Similar to the md use case, if one encounters errors restoring a disk
image from a backup it's useful to have the option to record the error
in a bad block list and keep going.

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Jeff Moyer]

"Verma, Vishal L" <vishal.l.verma@intel.com> writes:

> On Tue, 2015-11-24 at 14:14 -0500, Jeff Moyer wrote:
>> 
>> I'm not sure whether it makes sense to continue without badblock
>> management for the RAID code.  I was hoping Neil would comment on
>> that.
>> 
>> -Jeff
>
> Not sure I follow? I believe I've kept all the badblocks functionality
> RAID already had..

What I mean to say is that the RAID code had previously embedded the
badblocks structure in one of its other data structures.  As a result,
you would never get an allocation failure for it.

> On a related note, something I observed when testing with md:
>
> md's badblock list is per-device, and can be seen at:
> 	/sys/block/md0/md/dev-pmem0/bad_blocks
>
> Now if we have badblocks in the gendisks too, there is also:
> 	/sys/block/pmem0/bad_blocks
>
> The two are separate 'accounts' maintained by separate drivers (md for
> the former, and pmem for the latter). This can potentially be
> confusing..
>
> Should we consolidate the two, i.e. make md (re)use the gendisk
> badblocks for its purposes too?

I agree with what Dan said.

Cheers,
Jeff
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Verma, Vishal L]

On Wed, 2015-11-25 at 10:37 -0500, Jeff Moyer wrote:
> "Verma, Vishal L" <vishal.l.verma@intel.com> writes:
> 
> > On Tue, 2015-11-24 at 14:14 -0500, Jeff Moyer wrote:
> > > 
> > > I'm not sure whether it makes sense to continue without badblock
> > > management for the RAID code.  I was hoping Neil would comment on
> > > that.
> > > 
> > > -Jeff
> > 
> > Not sure I follow? I believe I've kept all the badblocks
> > functionality
> > RAID already had..
> 
> What I mean to say is that the RAID code had previously embedded the
> badblocks structure in one of its other data structures.  As a result,
> you would never get an allocation failure for it.
> 
Ah I see - I don't think that has effectively changed. 'rdev' still
contains a statically allocated badblocks structure (as opposed to
gendisk, which just stores a pointer). md used to dynamically allocate
the storage space inside badblocks (bb->page), and that is still the
case using badblocks_init.

	-Vishal

Re: [PATCH 2/3] block: Add badblock management for gendisks

[Jeff Moyer]

"Verma, Vishal L" <vishal.l.verma@intel.com> writes:

> On Wed, 2015-11-25 at 10:37 -0500, Jeff Moyer wrote:
>> "Verma, Vishal L" <vishal.l.verma@intel.com> writes:
>> 
>> > On Tue, 2015-11-24 at 14:14 -0500, Jeff Moyer wrote:
>> > > 
>> > > I'm not sure whether it makes sense to continue without badblock
>> > > management for the RAID code.  I was hoping Neil would comment on
>> > > that.
>> > > 
>> > > -Jeff
>> > 
>> > Not sure I follow? I believe I've kept all the badblocks
>> > functionality
>> > RAID already had..
>> 
>> What I mean to say is that the RAID code had previously embedded the
>> badblocks structure in one of its other data structures.  As a result,
>> you would never get an allocation failure for it.
>> 
> Ah I see - I don't think that has effectively changed. 'rdev' still
> contains a statically allocated badblocks structure (as opposed to
> gendisk, which just stores a pointer). md used to dynamically allocate
> the storage space inside badblocks (bb->page), and that is still the
> case using badblocks_init.

Ah, ok.  Sorry I didn't dig into that further.

Thanks,
Jeff
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 3/3] md: convert to use the generic badblocks code

[Vishal Verma]

Retain badblocks as part of rdev, but use the accessor functions from
include/linux/badblocks for all manipulation.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 drivers/md/md.c | 495 +++-----------------------------------------------------
 drivers/md/md.h |  31 +---
 2 files changed, 21 insertions(+), 505 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index c702de1..82994d7 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>
@@ -1358,8 +1359,6 @@ 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;
@@ -1484,7 +1483,7 @@ 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,
+			if (badblocks_set(&rdev->badblocks,
 					     sector, count, 1) == 0)
 				return -EINVAL;
 		}
@@ -2226,7 +2225,7 @@ 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);
@@ -2352,7 +2351,7 @@ 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);
 	}
@@ -2944,11 +2943,17 @@ 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);
@@ -8348,253 +8353,7 @@ 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 */
 
 int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		       int is_new)
@@ -8604,8 +8363,7 @@ 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);
+	rv = badblocks_set(&rdev->badblocks, s, sectors, 0);
 	if (rv) {
 		/* Make sure they get written out promptly */
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
@@ -8617,101 +8375,6 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 }
 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)
 {
@@ -8719,133 +8382,11 @@ 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 ab33957..dd9fab8 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
  */
@@ -111,22 +105,7 @@ 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 */
@@ -183,13 +162,11 @@ enum flag_bits {
 #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)
@@ -202,8 +179,6 @@ 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 {
-- 
2.5.0