Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (75 commits)
  md/raid10: handle further errors during fix_read_error better.
  md/raid10: Handle read errors during recovery better.
  md/raid10: simplify read error handling during recovery.
  md/raid10: record bad blocks due to write errors during resync/recovery.
  md/raid10:  attempt to fix read errors during resync/check
  md/raid10:  Handle write errors by updating badblock log.
  md/raid10: clear bad-block record when write succeeds.
  md/raid10: avoid writing to known bad blocks on known bad drives.
  md/raid10 record bad blocks as needed during recovery.
  md/raid10: avoid reading known bad blocks during resync/recovery.
  md/raid10 - avoid reading from known bad blocks - part 3
  md/raid10: avoid reading from known bad blocks - part 2
  md/raid10: avoid reading from known bad blocks - part 1
  md/raid10: Split handle_read_error out from raid10d.
  md/raid10: simplify/reindent some loops.
  md/raid5: Clear bad blocks on successful write.
  md/raid5.  Don't write to known bad block on doubtful devices.
  md/raid5: write errors should be recorded as bad blocks if possible.
  md/raid5: use bad-block log to improve handling of uncorrectable read errors.
  md/raid5: avoid reading from known bad blocks.
  ...

12 files changed, 3093 insertions, 1379 deletions

diff --git a/Documentation/md.txt b/Documentation/md.txt
index f0eee83ff78..fc94770f44a 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -360,18 +360,20 @@ Each directory contains:
         A file recording the current state of the device in the array
 	which can be a comma separated list of
 	      faulty   - device has been kicked from active use due to
-                         a detected fault
+                         a detected fault or it has unacknowledged bad
+                         blocks
 	      in_sync  - device is a fully in-sync member of the array
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
-	      blocked  - device has failed, metadata is "external",
-	                 and the failure hasn't been acknowledged yet.
+	      blocked  - device has failed, and the failure hasn't been
+			 acknowledged yet by the metadata handler.
 			 Writes that would write to this device if
 			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
+	      write_error - device has ever seen a write error.
 	This list may grow in future.
 	This can be written to.
 	Writing "faulty"  simulates a failure on the device.
@@ -379,9 +381,11 @@ Each directory contains:
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
 	Writing "blocked" sets the "blocked" flag.
-	Writing "-blocked" clears the "blocked" flag and allows writes
-		to complete.
+	Writing "-blocked" clears the "blocked" flags and allows writes
+		to complete and possibly simulates an error.
 	Writing "in_sync" sets the in_sync flag.
+	Writing "write_error" sets writeerrorseen flag.
+	Writing "-write_error" clears writeerrorseen flag.
 
 	This file responds to select/poll. Any change to 'faulty'
 	or 'blocked' causes an event.
@@ -419,7 +423,6 @@ Each directory contains:
         written, it will be rejected.
 
       recovery_start
-
         When the device is not 'in_sync', this records the number of
 	sectors from the start of the device which are known to be
 	correct.  This is normally zero, but during a recovery
@@ -435,6 +438,20 @@ Each directory contains:
 	Setting this to 'none' is equivalent to setting 'in_sync'.
 	Setting to any other value also clears the 'in_sync' flag.
 	
+      bad_blocks
+	This gives the list of all known bad blocks in the form of
+	start address and length (in sectors respectively). If output
+	is too big to fit in a page, it will be truncated. Writing
+	"sector length" to this file adds new acknowledged (i.e.
+	recorded to disk safely) bad blocks.
+
+      unacknowledged_bad_blocks
+	This gives the list of known-but-not-yet-saved-to-disk bad
+	blocks in the same form of 'bad_blocks'. If output is too big
+	to fit in a page, it will be truncated. Writing to this file
+	adds bad blocks without acknowledging them. This is largely
+	for testing.
+
 
 
 An active md device will also contain and entry for each active device
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 574b09afedd..0dc6546b77a 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -29,7 +29,6 @@
 #include "md.h"
 #include "bitmap.h"
 
-#include <linux/dm-dirty-log.h>
 /* debug macros */
 
 #define DEBUG 0
@@ -775,10 +774,8 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
  * 0 or page 1
  */
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
-					unsigned long chunk)
+					    unsigned long chunk)
 {
-	if (bitmap->filemap == NULL)
-		return NULL;
 	if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
 		return NULL;
 	return bitmap->filemap[file_page_index(bitmap, chunk)
@@ -878,28 +875,19 @@ enum bitmap_page_attr {
 static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	if (page)
-		__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
-	else
-		__set_bit(attr, &bitmap->logattrs);
+	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
 }
 
 static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	if (page)
-		__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
-	else
-		__clear_bit(attr, &bitmap->logattrs);
+	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
 }
 
 static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
 					   enum bitmap_page_attr attr)
 {
-	if (page)
-		return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
-	else
-		return test_bit(attr, &bitmap->logattrs);
+	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
 }
 
 /*
@@ -912,30 +900,26 @@ static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *p
 static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 {
 	unsigned long bit;
-	struct page *page = NULL;
+	struct page *page;
 	void *kaddr;
 	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
 
-	if (!bitmap->filemap) {
-		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
-		if (log)
-			log->type->mark_region(log, chunk);
-	} else {
+	if (!bitmap->filemap)
+		return;
 
-		page = filemap_get_page(bitmap, chunk);
-		if (!page)
-			return;
-		bit = file_page_offset(bitmap, chunk);
+	page = filemap_get_page(bitmap, chunk);
+	if (!page)
+		return;
+	bit = file_page_offset(bitmap, chunk);
 
-		/* set the bit */
-		kaddr = kmap_atomic(page, KM_USER0);
-		if (bitmap->flags & BITMAP_HOSTENDIAN)
-			set_bit(bit, kaddr);
-		else
-			__test_and_set_bit_le(bit, kaddr);
-		kunmap_atomic(kaddr, KM_USER0);
-		PRINTK("set file bit %lu page %lu\n", bit, page->index);
-	}
+	/* set the bit */
+	kaddr = kmap_atomic(page, KM_USER0);
+	if (bitmap->flags & BITMAP_HOSTENDIAN)
+		set_bit(bit, kaddr);
+	else
+		__set_bit_le(bit, kaddr);
+	kunmap_atomic(kaddr, KM_USER0);
+	PRINTK("set file bit %lu page %lu\n", bit, page->index);
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
 }
@@ -952,16 +936,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 
 	if (!bitmap)
 		return;
-	if (!bitmap->filemap) {
-		/* Must be using a dirty_log */
-		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
-		dirty = test_and_clear_bit(BITMAP_PAGE_DIRTY, &bitmap->logattrs);
-		need_write = test_and_clear_bit(BITMAP_PAGE_NEEDWRITE, &bitmap->logattrs);
-		if (dirty || need_write)
-			if (log->type->flush(log))
-				bitmap->flags |= BITMAP_WRITE_ERROR;
-		goto out;
-	}
 
 	/* look at each page to see if there are any set bits that need to be
 	 * flushed out to disk */
@@ -990,7 +964,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 		else
 			md_super_wait(bitmap->mddev);
 	}
-out:
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);
 }
@@ -1199,7 +1172,6 @@ void bitmap_daemon_work(mddev_t *mddev)
 	struct page *page = NULL, *lastpage = NULL;
 	sector_t blocks;
 	void *paddr;
-	struct dm_dirty_log *log = mddev->bitmap_info.log;
 
 	/* Use a mutex to guard daemon_work against
 	 * bitmap_destroy.
@@ -1224,12 +1196,11 @@ void bitmap_daemon_work(mddev_t *mddev)
 	spin_lock_irqsave(&bitmap->lock, flags);
 	for (j = 0; j < bitmap->chunks; j++) {
 		bitmap_counter_t *bmc;
-		if (!bitmap->filemap) {
-			if (!log)
-				/* error or shutdown */
-				break;
-		} else
-			page = filemap_get_page(bitmap, j);
+		if (!bitmap->filemap)
+			/* error or shutdown */
+			break;
+
+		page = filemap_get_page(bitmap, j);
 
 		if (page != lastpage) {
 			/* skip this page unless it's marked as needing cleaning */
@@ -1298,17 +1269,16 @@ void bitmap_daemon_work(mddev_t *mddev)
 						  -1);
 
 				/* clear the bit */
-				if (page) {
-					paddr = kmap_atomic(page, KM_USER0);
-					if (bitmap->flags & BITMAP_HOSTENDIAN)
-						clear_bit(file_page_offset(bitmap, j),
-							  paddr);
-					else
-						__test_and_clear_bit_le(file_page_offset(bitmap, j),
-							       paddr);
-					kunmap_atomic(paddr, KM_USER0);
-				} else
-					log->type->clear_region(log, j);
+				paddr = kmap_atomic(page, KM_USER0);
+				if (bitmap->flags & BITMAP_HOSTENDIAN)
+					clear_bit(file_page_offset(bitmap, j),
+						  paddr);
+				else
+					__clear_bit_le(
+							file_page_offset(bitmap,
+									 j),
+							paddr);
+				kunmap_atomic(paddr, KM_USER0);
 			}
 		} else
 			j |= PAGE_COUNTER_MASK;
@@ -1316,16 +1286,12 @@ void bitmap_daemon_work(mddev_t *mddev)
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 
 	/* now sync the final page */
-	if (lastpage != NULL || log != NULL) {
+	if (lastpage != NULL) {
 		spin_lock_irqsave(&bitmap->lock, flags);
 		if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
 			clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
 			spin_unlock_irqrestore(&bitmap->lock, flags);
-			if (lastpage)
-				write_page(bitmap, lastpage, 0);
-			else
-				if (log->type->flush(log))
-					bitmap->flags |= BITMAP_WRITE_ERROR;
+			write_page(bitmap, lastpage, 0);
 		} else {
 			set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
 			spin_unlock_irqrestore(&bitmap->lock, flags);
@@ -1767,12 +1733,10 @@ int bitmap_create(mddev_t *mddev)
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 
 	if (!file
-	    && !mddev->bitmap_info.offset
-	    && !mddev->bitmap_info.log) /* bitmap disabled, nothing to do */
+	    && !mddev->bitmap_info.offset) /* bitmap disabled, nothing to do */
 		return 0;
 
 	BUG_ON(file && mddev->bitmap_info.offset);
-	BUG_ON(mddev->bitmap_info.offset && mddev->bitmap_info.log);
 
 	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
 	if (!bitmap)
@@ -1863,6 +1827,7 @@ int bitmap_create(mddev_t *mddev)
 int bitmap_load(mddev_t *mddev)
 {
 	int err = 0;
+	sector_t start = 0;
 	sector_t sector = 0;
 	struct bitmap *bitmap = mddev->bitmap;
 
@@ -1881,24 +1846,14 @@ int bitmap_load(mddev_t *mddev)
 	}
 	bitmap_close_sync(bitmap);
 
-	if (mddev->bitmap_info.log) {
-		unsigned long i;
-		struct dm_dirty_log *log = mddev->bitmap_info.log;
-		for (i = 0; i < bitmap->chunks; i++)
-			if (!log->type->in_sync(log, i, 1))
-				bitmap_set_memory_bits(bitmap,
-						       (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
-						       1);
-	} else {
-		sector_t start = 0;
-		if (mddev->degraded == 0
-		    || bitmap->events_cleared == mddev->events)
-			/* no need to keep dirty bits to optimise a
-			 * re-add of a missing device */
-			start = mddev->recovery_cp;
-
-		err = bitmap_init_from_disk(bitmap, start);
-	}
+	if (mddev->degraded == 0
+	    || bitmap->events_cleared == mddev->events)
+		/* no need to keep dirty bits to optimise a
+		 * re-add of a missing device */
+		start = mddev->recovery_cp;
+
+	err = bitmap_init_from_disk(bitmap, start);
+
 	if (err)
 		goto out;
 
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index b2a127e891a..a28f2e5588c 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -212,10 +212,6 @@ struct bitmap {
 	unsigned long file_pages; /* number of pages in the file */
 	int last_page_size; /* bytes in the last page */
 
-	unsigned long logattrs; /* used when filemap_attr doesn't exist
-				 * because we are working with a dirty_log
-				 */
-
 	unsigned long flags;
 
 	int allclean;
@@ -237,7 +233,6 @@ struct bitmap {
 	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
-
 };
 
 /* the bitmap API */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index dfc9425db70..8e221a20f5d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -215,6 +215,55 @@ struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
 }
 EXPORT_SYMBOL_GPL(bio_clone_mddev);
 
+void md_trim_bio(struct bio *bio, int offset, int size)
+{
+	/* 'bio' is a cloned bio which we need to trim to match
+	 * the given offset and size.
+	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
+	 */
+	int i;
+	struct bio_vec *bvec;
+	int sofar = 0;
+
+	size <<= 9;
+	if (offset == 0 && size == bio->bi_size)
+		return;
+
+	bio->bi_sector += offset;
+	bio->bi_size = size;
+	offset <<= 9;
+	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+
+	while (bio->bi_idx < bio->bi_vcnt &&
+	       bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
+		/* remove this whole bio_vec */
+		offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
+		bio->bi_idx++;
+	}
+	if (bio->bi_idx < bio->bi_vcnt) {
+		bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
+		bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
+	}
+	/* avoid any complications with bi_idx being non-zero*/
+	if (bio->bi_idx) {
+		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
+			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
+		bio->bi_vcnt -= bio->bi_idx;
+		bio->bi_idx = 0;
+	}
+	/* Make sure vcnt and last bv are not too big */
+	bio_for_each_segment(bvec, bio, i) {
+		if (sofar + bvec->bv_len > size)
+			bvec->bv_len = size - sofar;
+		if (bvec->bv_len == 0) {
+			bio->bi_vcnt = i;
+			break;
+		}
+		sofar += bvec->bv_len;
+	}
+}
+EXPORT_SYMBOL_GPL(md_trim_bio);
+
 /*
  * We have a system wide 'event count' that is incremented
  * on any 'interesting' event, and readers of /proc/mdstat
@@ -757,6 +806,10 @@ static void free_disk_sb(mdk_rdev_t * rdev)
 		rdev->sb_start = 0;
 		rdev->sectors = 0;
 	}
+	if (rdev->bb_page) {
+		put_page(rdev->bb_page);
+		rdev->bb_page = NULL;
+	}
 }
 
 
@@ -1025,7 +1078,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 	ret = -EINVAL;
 
 	bdevname(rdev->bdev, b);
-	sb = (mdp_super_t*)page_address(rdev->sb_page);
+	sb = page_address(rdev->sb_page);
 
 	if (sb->md_magic != MD_SB_MAGIC) {
 		printk(KERN_ERR "md: invalid raid superblock magic on %s\n",
@@ -1054,6 +1107,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 	rdev->preferred_minor = sb->md_minor;
 	rdev->data_offset = 0;
 	rdev->sb_size = MD_SB_BYTES;
+	rdev->badblocks.shift = -1;
 
 	if (sb->level == LEVEL_MULTIPATH)
 		rdev->desc_nr = -1;
@@ -1064,7 +1118,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 		ret = 1;
 	} else {
 		__u64 ev1, ev2;
-		mdp_super_t *refsb = (mdp_super_t*)page_address(refdev->sb_page);
+		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",
 				b, bdevname(refdev->bdev,b2));
@@ -1099,7 +1153,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	mdp_disk_t *desc;
-	mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
+	mdp_super_t *sb = page_address(rdev->sb_page);
 	__u64 ev1 = md_event(sb);
 
 	rdev->raid_disk = -1;
@@ -1230,7 +1284,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 
 	rdev->sb_size = MD_SB_BYTES;
 
-	sb = (mdp_super_t*)page_address(rdev->sb_page);
+	sb = page_address(rdev->sb_page);
 
 	memset(sb, 0, sizeof(*sb));
 
@@ -1395,6 +1449,8 @@ 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(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 {
 	struct mdp_superblock_1 *sb;
@@ -1435,7 +1491,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	if (ret) return ret;
 
 
-	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+	sb = page_address(rdev->sb_page);
 
 	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
 	    sb->major_version != cpu_to_le32(1) ||
@@ -1473,12 +1529,52 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	else
 		rdev->desc_nr = le32_to_cpu(sb->dev_number);
 
+	if (!rdev->bb_page) {
+		rdev->bb_page = alloc_page(GFP_KERNEL);
+		if (!rdev->bb_page)
+			return -ENOMEM;
+	}
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BAD_BLOCKS) &&
+	    rdev->badblocks.count == 0) {
+		/* need to load the bad block list.
+		 * Currently we limit it to one page.
+		 */
+		s32 offset;
+		sector_t bb_sector;
+		u64 *bbp;
+		int i;
+		int sectors = le16_to_cpu(sb->bblog_size);
+		if (sectors > (PAGE_SIZE / 512))
+			return -EINVAL;
+		offset = le32_to_cpu(sb->bblog_offset);
+		if (offset == 0)
+			return -EINVAL;
+		bb_sector = (long long)offset;
+		if (!sync_page_io(rdev, bb_sector, sectors << 9,
+				  rdev->bb_page, READ, true))
+			return -EIO;
+		bbp = (u64 *)page_address(rdev->bb_page);
+		rdev->badblocks.shift = sb->bblog_shift;
+		for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) {
+			u64 bb = le64_to_cpu(*bbp);
+			int count = bb & (0x3ff);
+			u64 sector = bb >> 10;
+			sector <<= sb->bblog_shift;
+			count <<= sb->bblog_shift;
+			if (bb + 1 == 0)
+				break;
+			if (md_set_badblocks(&rdev->badblocks,
+					     sector, count, 1) == 0)
+				return -EINVAL;
+		}
+	} else if (sb->bblog_offset == 0)
+		rdev->badblocks.shift = -1;
+
 	if (!refdev) {
 		ret = 1;
 	} else {
 		__u64 ev1, ev2;
-		struct mdp_superblock_1 *refsb = 
-			(struct mdp_superblock_1*)page_address(refdev->sb_page);
+		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);
 
 		if (memcmp(sb->set_uuid, refsb->set_uuid, 16) != 0 ||
 		    sb->level != refsb->level ||
@@ -1513,7 +1609,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 
 static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 {
-	struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
 	__u64 ev1 = le64_to_cpu(sb->events);
 
 	rdev->raid_disk = -1;
@@ -1619,13 +1715,12 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 	int max_dev, i;
 	/* make rdev->sb match mddev and rdev data. */
 
-	sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+	sb = page_address(rdev->sb_page);
 
 	sb->feature_map = 0;
 	sb->pad0 = 0;
 	sb->recovery_offset = cpu_to_le64(0);
 	memset(sb->pad1, 0, sizeof(sb->pad1));
-	memset(sb->pad2, 0, sizeof(sb->pad2));
 	memset(sb->pad3, 0, sizeof(sb->pad3));
 
 	sb->utime = cpu_to_le64((__u64)mddev->utime);
@@ -1665,6 +1760,40 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 		sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors);
 	}
 
+	if (rdev->badblocks.count == 0)
+		/* Nothing to do for bad blocks*/ ;
+	else if (sb->bblog_offset == 0)
+		/* Cannot record bad blocks on this device */
+		md_error(mddev, rdev);
+	else {
+		struct badblocks *bb = &rdev->badblocks;
+		u64 *bbp = (u64 *)page_address(rdev->bb_page);
+		u64 *p = bb->page;
+		sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
+		if (bb->changed) {
+			unsigned seq;
+
+retry:
+			seq = read_seqbegin(&bb->lock);
+
+			memset(bbp, 0xff, PAGE_SIZE);
+
+			for (i = 0 ; i < bb->count ; i++) {
+				u64 internal_bb = *p++;
+				u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
+						| BB_LEN(internal_bb));
+				*bbp++ = cpu_to_le64(store_bb);
+			}
+			if (read_seqretry(&bb->lock, seq))
+				goto retry;
+
+			bb->sector = (rdev->sb_start +
+				      (int)le32_to_cpu(sb->bblog_offset));
+			bb->size = le16_to_cpu(sb->bblog_size);
+			bb->changed = 0;
+		}
+	}
+
 	max_dev = 0;
 	list_for_each_entry(rdev2, &mddev->disks, same_set)
 		if (rdev2->desc_nr+1 > max_dev)
@@ -1724,7 +1853,7 @@ super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 			num_sectors = max_sectors;
 		rdev->sb_start = sb_start;
 	}
-	sb = (struct mdp_superblock_1 *) page_address(rdev->sb_page);
+	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
 	sb->super_offset = rdev->sb_start;
 	sb->sb_csum = calc_sb_1_csum(sb);
@@ -1922,7 +2051,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 	bd_link_disk_holder(rdev->bdev, mddev->gendisk);
 
 	/* May as well allow recovery to be retried once */
-	mddev->recovery_disabled = 0;
+	mddev->recovery_disabled++;
 
 	return 0;
 
@@ -1953,6 +2082,9 @@ static void unbind_rdev_from_array(mdk_rdev_t * rdev)
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
 	rdev->sysfs_state = NULL;
+	kfree(rdev->badblocks.page);
+	rdev->badblocks.count = 0;
+	rdev->badblocks.page = NULL;
 	/* We need to delay this, otherwise we can deadlock when
 	 * writing to 'remove' to "dev/state".  We also need
 	 * to delay it due to rcu usage.
@@ -2127,10 +2259,10 @@ static void print_rdev(mdk_rdev_t *rdev, int major_version)
 		printk(KERN_INFO "md: rdev superblock (MJ:%d):\n", major_version);
 		switch (major_version) {
 		case 0:
-			print_sb_90((mdp_super_t*)page_address(rdev->sb_page));
+			print_sb_90(page_address(rdev->sb_page));
 			break;
 		case 1:
-			print_sb_1((struct mdp_superblock_1 *)page_address(rdev->sb_page));
+			print_sb_1(page_address(rdev->sb_page));
 			break;
 		}
 	} else
@@ -2194,6 +2326,7 @@ static void md_update_sb(mddev_t * mddev, int force_change)
 	mdk_rdev_t *rdev;
 	int sync_req;
 	int nospares = 0;
+	int any_badblocks_changed = 0;
 
 repeat:
 	/* First make sure individual recovery_offsets are correct */
@@ -2208,8 +2341,18 @@ repeat:
 	if (!mddev->persistent) {
 		clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
 		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
-		if (!mddev->external)
+		if (!mddev->external) {
 			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+			list_for_each_entry(rdev, &mddev->disks, same_set) {
+				if (rdev->badblocks.changed) {
+					md_ack_all_badblocks(&rdev->badblocks);
+					md_error(mddev, rdev);
+				}
+				clear_bit(Blocked, &rdev->flags);
+				clear_bit(BlockedBadBlocks, &rdev->flags);
+				wake_up(&rdev->blocked_wait);
+			}
+		}
 		wake_up(&mddev->sb_wait);
 		return;
 	}
@@ -2265,6 +2408,14 @@ repeat:
 		MD_BUG();
 		mddev->events --;
 	}
+
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (rdev->badblocks.changed)
+			any_badblocks_changed++;
+		if (test_bit(Faulty, &rdev->flags))
+			set_bit(FaultRecorded, &rdev->flags);
+	}
+
 	sync_sbs(mddev, nospares);
 	spin_unlock_irq(&mddev->write_lock);
 
@@ -2290,6 +2441,13 @@ repeat:
 				bdevname(rdev->bdev,b),
 				(unsigned long long)rdev->sb_start);
 			rdev->sb_events = mddev->events;
+			if (rdev->badblocks.size) {
+				md_super_write(mddev, rdev,
+					       rdev->badblocks.sector,
+					       rdev->badblocks.size << 9,
+					       rdev->bb_page);
+				rdev->badblocks.size = 0;
+			}
 
 		} else
 			dprintk(")\n");
@@ -2313,6 +2471,15 @@ repeat:
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (test_and_clear_bit(FaultRecorded, &rdev->flags))
+			clear_bit(Blocked, &rdev->flags);
+
+		if (any_badblocks_changed)
+			md_ack_all_badblocks(&rdev->badblocks);
+		clear_bit(BlockedBadBlocks, &rdev->flags);
+		wake_up(&rdev->blocked_wait);
+	}
 }
 
 /* words written to sysfs files may, or may not, be \n terminated.
@@ -2347,7 +2514,8 @@ state_show(mdk_rdev_t *rdev, char *page)
 	char *sep = "";
 	size_t len = 0;
 
-	if (test_bit(Faulty, &rdev->flags)) {
+	if (test_bit(Faulty, &rdev->flags) ||
+	    rdev->badblocks.unacked_exist) {
 		len+= sprintf(page+len, "%sfaulty",sep);
 		sep = ",";
 	}
@@ -2359,7 +2527,8 @@ state_show(mdk_rdev_t *rdev, char *page)
 		len += sprintf(page+len, "%swrite_mostly",sep);
 		sep = ",";
 	}
-	if (test_bit(Blocked, &rdev->flags)) {
+	if (test_bit(Blocked, &rdev->flags) ||
+	    rdev->badblocks.unacked_exist) {
 		len += sprintf(page+len, "%sblocked", sep);
 		sep = ",";
 	}
@@ -2368,6 +2537,10 @@ state_show(mdk_rdev_t *rdev, char *page)
 		len += sprintf(page+len, "%sspare", sep);
 		sep = ",";
 	}
+	if (test_bit(WriteErrorSeen, &rdev->flags)) {
+		len += sprintf(page+len, "%swrite_error", sep);
+		sep = ",";
+	}
 	return len+sprintf(page+len, "\n");
 }
 
@@ -2375,13 +2548,15 @@ static ssize_t
 state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 {
 	/* can write
-	 *  faulty  - simulates and error
+	 *  faulty  - simulates an error
 	 *  remove  - disconnects the device
 	 *  writemostly - sets write_mostly
 	 *  -writemostly - clears write_mostly
-	 *  blocked - sets the Blocked flag
-	 *  -blocked - clears the Blocked flag
+	 *  blocked - sets the Blocked flags
+	 *  -blocked - clears the Blocked and possibly simulates an error
 	 *  insync - sets Insync providing device isn't active
+	 *  write_error - sets WriteErrorSeen
+	 *  -write_error - clears WriteErrorSeen
 	 */
 	int err = -EINVAL;
 	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
@@ -2408,7 +2583,15 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		set_bit(Blocked, &rdev->flags);
 		err = 0;
 	} else if (cmd_match(buf, "-blocked")) {
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    test_bit(BlockedBadBlocks, &rdev->flags)) {
+			/* metadata handler doesn't understand badblocks,
+			 * so we need to fail the device
+			 */
+			md_error(rdev->mddev, rdev);
+		}
 		clear_bit(Blocked, &rdev->flags);
+		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
@@ -2417,6 +2600,12 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
+	} else if (cmd_match(buf, "write_error")) {
+		set_bit(WriteErrorSeen, &rdev->flags);
+		err = 0;
+	} else if (cmd_match(buf, "-write_error")) {
+		clear_bit(WriteErrorSeen, &rdev->flags);
+		err = 0;
 	}
 	if (!err)
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
@@ -2459,7 +2648,6 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 {
 	char *e;
 	int err;
-	char nm[20];
 	int slot = simple_strtoul(buf, &e, 10);
 	if (strncmp(buf, "none", 4)==0)
 		slot = -1;
@@ -2482,8 +2670,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 			hot_remove_disk(rdev->mddev, rdev->raid_disk);
 		if (err)
 			return err;
-		sprintf(nm, "rd%d", rdev->raid_disk);
-		sysfs_remove_link(&rdev->mddev->kobj, nm);
+		sysfs_unlink_rdev(rdev->mddev, rdev);
 		rdev->raid_disk = -1;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
@@ -2522,8 +2709,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 			return err;
 		} else
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
-		sprintf(nm, "rd%d", rdev->raid_disk);
-		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
+		if (sysfs_link_rdev(rdev->mddev, rdev))
 			/* failure here is OK */;
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
@@ -2712,6 +2898,39 @@ static ssize_t recovery_start_store(mdk_rdev_t *rdev, const char *buf, size_t le
 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);
+
+static ssize_t bb_show(mdk_rdev_t *rdev, char *page)
+{
+	return badblocks_show(&rdev->badblocks, page, 0);
+}
+static ssize_t bb_store(mdk_rdev_t *rdev, const char *page, size_t len)
+{
+	int rv = badblocks_store(&rdev->badblocks, page, len, 0);
+	/* Maybe that ack was all we needed */
+	if (test_and_clear_bit(BlockedBadBlocks, &rdev->flags))
+		wake_up(&rdev->blocked_wait);
+	return rv;
+}
+static struct rdev_sysfs_entry rdev_bad_blocks =
+__ATTR(bad_blocks, S_IRUGO|S_IWUSR, bb_show, bb_store);
+
+
+static ssize_t ubb_show(mdk_rdev_t *rdev, char *page)
+{
+	return badblocks_show(&rdev->badblocks, page, 1);
+}
+static ssize_t ubb_store(mdk_rdev_t *rdev, const char *page, size_t len)
+{
+	return badblocks_store(&rdev->badblocks, page, len, 1);
+}
+static struct rdev_sysfs_entry rdev_unack_bad_blocks =
+__ATTR(unacknowledged_bad_blocks, S_IRUGO|S_IWUSR, ubb_show, ubb_store);
+
 static struct attribute *rdev_default_attrs[] = {
 	&rdev_state.attr,
 	&rdev_errors.attr,
@@ -2719,6 +2938,8 @@ static struct attribute *rdev_default_attrs[] = {
 	&rdev_offset.attr,
 	&rdev_size.attr,
 	&rdev_recovery_start.attr,
+	&rdev_bad_blocks.attr,
+	&rdev_unack_bad_blocks.attr,
 	NULL,
 };
 static ssize_t
@@ -2782,7 +3003,7 @@ static struct kobj_type rdev_ktype = {
 	.default_attrs	= rdev_default_attrs,
 };
 
-void md_rdev_init(mdk_rdev_t *rdev)
+int md_rdev_init(mdk_rdev_t *rdev)
 {
 	rdev->desc_nr = -1;
 	rdev->saved_raid_disk = -1;
@@ -2792,12 +3013,27 @@ void md_rdev_init(mdk_rdev_t *rdev)
 	rdev->sb_events = 0;
 	rdev->last_read_error.tv_sec  = 0;
 	rdev->last_read_error.tv_nsec = 0;
+	rdev->sb_loaded = 0;
+	rdev->bb_page = NULL;
 	atomic_set(&rdev->nr_pending, 0);
 	atomic_set(&rdev->read_errors, 0);
 	atomic_set(&rdev->corrected_errors, 0);
 
 	INIT_LIST_HEAD(&rdev->same_set);
 	init_waitqueue_head(&rdev->blocked_wait);
+
+	/* Add space to store bad block list.
+	 * This reserves the space even on arrays where it cannot
+	 * be used - I wonder if that matters
+	 */
+	rdev->badblocks.count = 0;
+	rdev->badblocks.shift = 0;
+	rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	seqlock_init(&rdev->badblocks.lock);
+	if (rdev->badblocks.page == NULL)
+		return -ENOMEM;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(md_rdev_init);
 /*
@@ -2823,8 +3059,11 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 		return ERR_PTR(-ENOMEM);
 	}
 
-	md_rdev_init(rdev);
-	if ((err = alloc_disk_sb(rdev)))
+	err = md_rdev_init(rdev);
+	if (err)
+		goto abort_free;
+	err = alloc_disk_sb(rdev);
+	if (err)
 		goto abort_free;
 
 	err = lock_rdev(rdev, newdev, super_format == -2);
@@ -2860,15 +3099,17 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
 			goto abort_free;
 		}
 	}
+	if (super_format == -1)
+		/* hot-add for 0.90, or non-persistent: so no badblocks */
+		rdev->badblocks.shift = -1;
 
 	return rdev;
 
 abort_free:
-	if (rdev->sb_page) {
-		if (rdev->bdev)
-			unlock_rdev(rdev);
-		free_disk_sb(rdev);
-	}
+	if (rdev->bdev)
+		unlock_rdev(rdev);
+	free_disk_sb(rdev);
+	kfree(rdev->badblocks.page);
 	kfree(rdev);
 	return ERR_PTR(err);
 }
@@ -3149,15 +3390,13 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
 	}
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
-		char nm[20];
 		if (rdev->raid_disk < 0)