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

* 'for-linus' of git://neil.brown.name/md: (27 commits)
  md: add 'recovery_start' per-device sysfs attribute
  md: rcu_read_lock() walk of mddev->disks in md_do_sync()
  md: integrate spares into array at earliest opportunity.
  md: move compat_ioctl handling into md.c
  md: revise Kconfig help for MD_MULTIPATH
  md: add MODULE_DESCRIPTION for all md related modules.
  raid: improve MD/raid10 handling of correctable read errors.
  md/raid10: print more useful messages on device failure.
  md/bitmap: update dirty flag when bitmap bits are explicitly set.
  md: Support write-intent bitmaps with externally managed metadata.
  md/bitmap: move setting of daemon_lastrun out of bitmap_read_sb
  md: support updating bitmap parameters via sysfs.
  md: factor out parsing of fixed-point numbers
  md: support bitmap offset appropriate for external-metadata arrays.
  md: remove needless setting of thread->timeout in raid10_quiesce
  md: change daemon_sleep to be in 'jiffies' rather than 'seconds'.
  md: move offset, daemon_sleep and chunksize out of bitmap structure
  md: collect bitmap-specific fields into one structure.
  md/raid1: add takeover support for raid5->raid1
  md: add honouring of suspend_{lo,hi} to raid1.
  ...

17 files changed, 1146 insertions, 315 deletions

diff --git a/Documentation/md.txt b/Documentation/md.txt
index 4edd39ec7db..188f4768f1d 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -233,9 +233,9 @@ All md devices contain:
 
   resync_start
      The point at which resync should start.  If no resync is needed,
-     this will be a very large number.  At array creation it will
-     default to 0, though starting the array as 'clean' will
-     set it much larger.
+     this will be a very large number (or 'none' since 2.6.30-rc1).  At
+     array creation it will default to 0, though starting the array as
+     'clean' will set it much larger.
 
    new_dev
      This file can be written but not read.  The value written should
@@ -296,6 +296,51 @@ All md devices contain:
      active-idle
          like active, but no writes have been seen for a while (safe_mode_delay).
 
+  bitmap/location
+     This indicates where the write-intent bitmap for the array is
+     stored.
+     It can be one of "none", "file" or "[+-]N".
+     "file" may later be extended to "file:/file/name"
+     "[+-]N" means that many sectors from the start of the metadata.
+       This is replicated on all devices.  For arrays with externally
+       managed metadata, the offset is from the beginning of the
+       device.
+  bitmap/chunksize
+     The size, in bytes, of the chunk which will be represented by a
+     single bit.  For RAID456, it is a portion of an individual
+     device. For RAID10, it is a portion of the array.  For RAID1, it
+     is both (they come to the same thing).
+  bitmap/time_base
+     The time, in seconds, between looking for bits in the bitmap to
+     be cleared. In the current implementation, a bit will be cleared
+     between 2 and 3 times "time_base" after all the covered blocks
+     are known to be in-sync.
+  bitmap/backlog
+     When write-mostly devices are active in a RAID1, write requests
+     to those devices proceed in the background - the filesystem (or
+     other user of the device) does not have to wait for them.
+     'backlog' sets a limit on the number of concurrent background
+     writes.  If there are more than this, new writes will by
+     synchronous.
+  bitmap/metadata
+     This can be either 'internal' or 'external'.
+     'internal' is the default and means the metadata for the bitmap
+     is stored in the first 256 bytes of the allocated space and is
+     managed by the md module.
+     'external' means that bitmap metadata is managed externally to
+     the kernel (i.e. by some userspace program)
+  bitmap/can_clear
+     This is either 'true' or 'false'.  If 'true', then bits in the
+     bitmap will be cleared when the corresponding blocks are thought
+     to be in-sync.  If 'false', bits will never be cleared.
+     This is automatically set to 'false' if a write happens on a
+     degraded array, or if the array becomes degraded during a write.
+     When metadata is managed externally, it should be set to true
+     once the array becomes non-degraded, and this fact has been
+     recorded in the metadata.
+     
+     
+     
 
 As component devices are added to an md array, they appear in the 'md'
 directory as new directories named
@@ -334,8 +379,9 @@ Each directory contains:
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
 	Writing "blocked" sets the "blocked" flag.
-	Writing "-blocked" clear the "blocked" flag and allows writes
+	Writing "-blocked" clears the "blocked" flag and allows writes
 		to complete.
+	Writing "in_sync" sets the in_sync flag.
 
 	This file responds to select/poll. Any change to 'faulty'
 	or 'blocked' causes an event.
@@ -372,6 +418,24 @@ Each directory contains:
         array.  If a value less than the current component_size is
         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
+	operation is will steadily increase, and if the recovery is
+	interrupted, restoring this value can cause recovery to
+	avoid repeating the earlier blocks.  With v1.x metadata, this
+	value is saved and restored automatically.
+
+	This can be set whenever the device is not an active member of
+	the array, either before the array is activated, or before
+	the 'slot' is set.
+
+	Setting this to 'none' is equivalent to setting 'in_sync'.
+	Setting to any other value also clears the 'in_sync' flag.
+	
+
 
 An active md device will also contain and entry for each active device
 in the array.  These are named
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2158377a135..acb3a4e404f 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -185,11 +185,10 @@ config MD_MULTIPATH
 	tristate "Multipath I/O support"
 	depends on BLK_DEV_MD
 	help
-	  Multipath-IO is the ability of certain devices to address the same
-	  physical disk over multiple 'IO paths'. The code ensures that such
-	  paths can be defined and handled at runtime, and ensures that a
-	  transparent failover to the backup path(s) happens if a IO errors
-	  arrives on the primary path.
+	  MD_MULTIPATH provides a simple multi-path personality for use
+	  the MD framework.  It is not under active development.  New
+	  projects should consider using DM_MULTIPATH which has more
+	  features and more testing.
 
 	  If unsure, say N.
 
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 60e2b322db1..26ac8aad0b1 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -212,7 +212,7 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
  */
 
 /* IO operations when bitmap is stored near all superblocks */
-static struct page *read_sb_page(mddev_t *mddev, long offset,
+static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
 				 struct page *page,
 				 unsigned long index, int size)
 {
@@ -287,27 +287,36 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
 			int size = PAGE_SIZE;
+			loff_t offset = mddev->bitmap_info.offset;
 			if (page->index == bitmap->file_pages-1)
 				size = roundup(bitmap->last_page_size,
 					       bdev_logical_block_size(rdev->bdev));
 			/* Just make sure we aren't corrupting data or
 			 * metadata
 			 */
-			if (bitmap->offset < 0) {
+			if (mddev->external) {
+				/* Bitmap could be anywhere. */
+				if (rdev->sb_start + offset + (page->index *(PAGE_SIZE/512)) >
+				    rdev->data_offset &&
+				    rdev->sb_start + offset < 
+				    rdev->data_offset + mddev->dev_sectors +
+				    (PAGE_SIZE/512))
+					goto bad_alignment;
+			} else if (offset < 0) {
 				/* DATA  BITMAP METADATA  */
-				if (bitmap->offset
+				if (offset
 				    + (long)(page->index * (PAGE_SIZE/512))
 				    + size/512 > 0)
 					/* bitmap runs in to metadata */
 					goto bad_alignment;
 				if (rdev->data_offset + mddev->dev_sectors
-				    > rdev->sb_start + bitmap->offset)
+				    > rdev->sb_start + offset)
 					/* data runs in to bitmap */
 					goto bad_alignment;
 			} else if (rdev->sb_start < rdev->data_offset) {
 				/* METADATA BITMAP DATA */
 				if (rdev->sb_start
-				    + bitmap->offset
+				    + offset
 				    + page->index*(PAGE_SIZE/512) + size/512
 				    > rdev->data_offset)
 					/* bitmap runs in to data */
@@ -316,7 +325,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 				/* DATA METADATA BITMAP - no problems */
 			}
 			md_super_write(mddev, rdev,
-				       rdev->sb_start + bitmap->offset
+				       rdev->sb_start + offset
 				       + page->index * (PAGE_SIZE/512),
 				       size,
 				       page);
@@ -488,6 +497,8 @@ void bitmap_update_sb(struct bitmap *bitmap)
 
 	if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
 		return;
+	if (bitmap->mddev->bitmap_info.external)
+		return;
 	spin_lock_irqsave(&bitmap->lock, flags);
 	if (!bitmap->sb_page) { /* no superblock */
 		spin_unlock_irqrestore(&bitmap->lock, flags);
@@ -501,6 +512,9 @@ void bitmap_update_sb(struct bitmap *bitmap)
 		bitmap->events_cleared = bitmap->mddev->events;
 		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
 	}
+	/* Just in case these have been changed via sysfs: */
+	sb->daemon_sleep = cpu_to_le32(bitmap->mddev->bitmap_info.daemon_sleep/HZ);
+	sb->write_behind = cpu_to_le32(bitmap->mddev->bitmap_info.max_write_behind);
 	kunmap_atomic(sb, KM_USER0);
 	write_page(bitmap, bitmap->sb_page, 1);
 }
@@ -550,7 +564,8 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 
 		bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
 	} else {
-		bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset,
+		bitmap->sb_page = read_sb_page(bitmap->mddev,
+					       bitmap->mddev->bitmap_info.offset,
 					       NULL,
 					       0, sizeof(bitmap_super_t));
 	}
@@ -563,7 +578,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
 
 	chunksize = le32_to_cpu(sb->chunksize);
-	daemon_sleep = le32_to_cpu(sb->daemon_sleep);
+	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 
 	/* verify that the bitmap-specific fields are valid */
@@ -576,7 +591,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		reason = "bitmap chunksize too small";
 	else if ((1 << ffz(~chunksize)) != chunksize)
 		reason = "bitmap chunksize not a power of 2";
-	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ)
+	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT)
 		reason = "daemon sleep period out of range";
 	else if (write_behind > COUNTER_MAX)
 		reason = "write-behind limit out of range (0 - 16383)";
@@ -610,10 +625,9 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	}
 success:
 	/* assign fields using values from superblock */
-	bitmap->chunksize = chunksize;
-	bitmap->daemon_sleep = daemon_sleep;
-	bitmap->daemon_lastrun = jiffies;
-	bitmap->max_write_behind = write_behind;
+	bitmap->mddev->bitmap_info.chunksize = chunksize;
+	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
 	bitmap->flags |= le32_to_cpu(sb->state);
 	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
 		bitmap->flags |= BITMAP_HOSTENDIAN;
@@ -664,16 +678,26 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
  * general bitmap file operations
  */
 
+/*
+ * on-disk bitmap:
+ *
+ * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap
+ * file a page at a time. There's a superblock at the start of the file.
+ */
 /* calculate the index of the page that contains this bit */
-static inline unsigned long file_page_index(unsigned long chunk)
+static inline unsigned long file_page_index(struct bitmap *bitmap, unsigned long chunk)
 {
-	return CHUNK_BIT_OFFSET(chunk) >> PAGE_BIT_SHIFT;
+	if (!bitmap->mddev->bitmap_info.external)
+		chunk += sizeof(bitmap_super_t) << 3;
+	return chunk >> PAGE_BIT_SHIFT;
 }
 
 /* calculate the (bit) offset of this bit within a page */
-static inline unsigned long file_page_offset(unsigned long chunk)
+static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned long chunk)
 {
-	return CHUNK_BIT_OFFSET(chunk) & (PAGE_BITS - 1);
+	if (!bitmap->mddev->bitmap_info.external)
+		chunk += sizeof(bitmap_super_t) << 3;
+	return chunk & (PAGE_BITS - 1);
 }
 
 /*
@@ -686,8 +710,9 @@ static inline unsigned long file_page_offset(unsigned long chunk)
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					unsigned long chunk)
 {
-	if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
-	return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
+	if (file_page_index(bitmap, chunk) >= bitmap->file_pages) return NULL;
+	return bitmap->filemap[file_page_index(bitmap, chunk)
+			       - file_page_index(bitmap, 0)];
 }
 
 
@@ -710,7 +735,7 @@ static void bitmap_file_unmap(struct bitmap *bitmap)
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 
 	while (pages--)
-		if (map[pages]->index != 0) /* 0 is sb_page, release it below */
+		if (map[pages] != sb_page) /* 0 is sb_page, release it below */
 			free_buffers(map[pages]);
 	kfree(map);
 	kfree(attr);
@@ -821,7 +846,7 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 
 	page = filemap_get_page(bitmap, chunk);
 	if (!page) return;
-	bit = file_page_offset(chunk);
+	bit = file_page_offset(bitmap, chunk);
 
  	/* set the bit */
 	kaddr = kmap_atomic(page, KM_USER0);
@@ -907,7 +932,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	chunks = bitmap->chunks;
 	file = bitmap->file;
 
-	BUG_ON(!file && !bitmap->offset);
+	BUG_ON(!file && !bitmap->mddev->bitmap_info.offset);
 
 #ifdef INJECT_FAULTS_3
 	outofdate = 1;
@@ -919,14 +944,17 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 			"recovery\n", bmname(bitmap));
 
 	bytes = (chunks + 7) / 8;
+	if (!bitmap->mddev->bitmap_info.external)
+		bytes += sizeof(bitmap_super_t);
 
-	num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;
+	
+	num_pages = (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
 
-	if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
+	if (file && i_size_read(file->f_mapping->host) < bytes) {
 		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
 			bmname(bitmap),
 			(unsigned long) i_size_read(file->f_mapping->host),
-			bytes + sizeof(bitmap_super_t));
+			bytes);
 		goto err;
 	}
 
@@ -947,17 +975,16 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 
 	for (i = 0; i < chunks; i++) {
 		int b;
-		index = file_page_index(i);
-		bit = file_page_offset(i);
+		index = file_page_index(bitmap, i);
+		bit = file_page_offset(bitmap, i);
 		if (index != oldindex) { /* this is a new page, read it in */
 			int count;
 			/* unmap the old page, we're done with it */
 			if (index == num_pages-1)
-				count = bytes + sizeof(bitmap_super_t)
-					- index * PAGE_SIZE;
+				count = bytes - index * PAGE_SIZE;
 			else
 				count = PAGE_SIZE;
-			if (index == 0) {
+			if (index == 0 && bitmap->sb_page) {
 				/*
 				 * if we're here then the superblock page
 				 * contains some bits (PAGE_SIZE != sizeof sb)
@@ -967,14 +994,15 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 				offset = sizeof(bitmap_super_t);
 				if (!file)
 					read_sb_page(bitmap->mddev,
-						     bitmap->offset,
+						     bitmap->mddev->bitmap_info.offset,
 						     page,
 						     index, count);
 			} else if (file) {
 				page = read_page(file, index, bitmap, count);
 				offset = 0;
 			} else {
-				page = read_sb_page(bitmap->mddev, bitmap->offset,
+				page = read_sb_page(bitmap->mddev,
+						    bitmap->mddev->bitmap_info.offset,
 						    NULL,
 						    index, count);
 				offset = 0;
@@ -1078,23 +1106,32 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
  *			out to disk
  */
 
-void bitmap_daemon_work(struct bitmap *bitmap)
+void bitmap_daemon_work(mddev_t *mddev)
 {
+	struct bitmap *bitmap;
 	unsigned long j;
 	unsigned long flags;
 	struct page *page = NULL, *lastpage = NULL;
 	int blocks;
 	void *paddr;
 
-	if (bitmap == NULL)
+	/* Use a mutex to guard daemon_work against
+	 * bitmap_destroy.
+	 */
+	mutex_lock(&mddev->bitmap_info.mutex);
+	bitmap = mddev->bitmap;
+	if (bitmap == NULL) {
+		mutex_unlock(&mddev->bitmap_info.mutex);
 		return;
-	if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
+	}
+	if (time_before(jiffies, bitmap->daemon_lastrun
+			+ bitmap->mddev->bitmap_info.daemon_sleep))
 		goto done;
 
 	bitmap->daemon_lastrun = jiffies;
 	if (bitmap->allclean) {
 		bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
-		return;
+		goto done;
 	}
 	bitmap->allclean = 1;
 
@@ -1142,7 +1179,8 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			/* We are possibly going to clear some bits, so make
 			 * sure that events_cleared is up-to-date.
 			 */
-			if (bitmap->need_sync) {
+			if (bitmap->need_sync &&
+			    bitmap->mddev->bitmap_info.external == 0) {
 				bitmap_super_t *sb;
 				bitmap->need_sync = 0;
 				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
@@ -1152,7 +1190,8 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 				write_page(bitmap, bitmap->sb_page, 1);
 			}
 			spin_lock_irqsave(&bitmap->lock, flags);
-			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
+			if (!bitmap->need_sync)
+				clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
 		bmc = bitmap_get_counter(bitmap,
 					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
@@ -1167,7 +1206,7 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			if (*bmc == 2) {
 				*bmc=1; /* maybe clear the bit next time */
 				set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
-			} else if (*bmc == 1) {
+			} else if (*bmc == 1 && !bitmap->need_sync) {
 				/* we can clear the bit */
 				*bmc = 0;
 				bitmap_count_page(bitmap,
@@ -1177,9 +1216,11 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 				/* clear the bit */
 				paddr = kmap_atomic(page, KM_USER0);
 				if (bitmap->flags & BITMAP_HOSTENDIAN)
-					clear_bit(file_page_offset(j), paddr);
+					clear_bit(file_page_offset(bitmap, j),
+						  paddr);
 				else
-					ext2_clear_bit(file_page_offset(j), paddr);
+					ext2_clear_bit(file_page_offset(bitmap, j),
+						       paddr);
 				kunmap_atomic(paddr, KM_USER0);
 			}
 		} else
@@ -1202,7 +1243,9 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 
  done:
 	if (bitmap->allclean == 0)
-		bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ;
+		bitmap->mddev->thread->timeout = 
+			bitmap->mddev->bitmap_info.daemon_sleep;
+	mutex_unlock(&mddev->bitmap_info.mutex);
 }
 
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
@@ -1332,6 +1375,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 		    bitmap->events_cleared < bitmap->mddev->events) {
 			bitmap->events_cleared = bitmap->mddev->events;
 			bitmap->need_sync = 1;
+			sysfs_notify_dirent(bitmap->sysfs_can_clear);
 		}
 
 		if (!success && ! (*bmc & NEEDED_MASK))
@@ -1470,7 +1514,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 		return;
 	}
 	if (time_before(jiffies, (bitmap->last_end_sync
-				  + bitmap->daemon_sleep * HZ)))
+				  + bitmap->mddev->bitmap_info.daemon_sleep)))
 		return;
 	wait_event(bitmap->mddev->recovery_wait,
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
@@ -1522,6 +1566,12 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
 		sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
 		bitmap_set_memory_bits(bitmap, sec, 1);
 		bitmap_file_set_bit(bitmap, sec);
+		if (sec < bitmap->mddev->recovery_cp)
+			/* We are asserting that the array is dirty,
+			 * so move the recovery_cp address back so
+			 * that it is obvious that it is dirty
+			 */
+			bitmap->mddev->recovery_cp = sec;
 	}
 }
 
@@ -1531,7 +1581,7 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
 void bitmap_flush(mddev_t *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
-	int sleep;
+	long sleep;
 
 	if (!bitmap) /* there was no bitmap */
 		return;
@@ -1539,12 +1589,13 @@ void bitmap_flush(mddev_t *mddev)
 	/* run the daemon_work three time to ensure everything is flushed
 	 * that can be
 	 */
-	sleep = bitmap->daemon_sleep;
-	bitmap->daemon_sleep = 0;
-	bitmap_daemon_work(bitmap);
-	bitmap_daemon_work(bitmap);
-	bitmap_daemon_work(bitmap);
-	bitmap->daemon_sleep = sleep;
+	sleep = mddev->bitmap_info.daemon_sleep * 2;
+	bitmap->daemon_lastrun -= sleep;
+	bitmap_daemon_work(mddev);
+	bitmap->daemon_lastrun -= sleep;
+	bitmap_daemon_work(mddev);
+	bitmap->daemon_lastrun -= sleep;
+	bitmap_daemon_work(mddev);
 	bitmap_update_sb(bitmap);
 }
 
@@ -1574,6 +1625,7 @@ static void bitmap_free(struct bitmap *bitmap)
 	kfree(bp);
 	kfree(bitmap);
 }
+
 void bitmap_destroy(mddev_t *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -1581,10 +1633,15 @@ void bitmap_destroy(mddev_t *mddev)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
+	mutex_lock(&mddev->bitmap_info.mutex);
 	mddev->bitmap = NULL; /* disconnect from the md device */
+	mutex_unlock(&mddev->bitmap_info.mutex);
 	if (mddev->thread)
 		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
 
+	if (bitmap->sysfs_can_clear)
+		sysfs_put(bitmap->sysfs_can_clear);
+
 	bitmap_free(bitmap);
 }
 
@@ -1598,16 +1655,17 @@ int bitmap_create(mddev_t *mddev)
 	sector_t blocks = mddev->resync_max_sectors;
 	unsigned long chunks;
 	unsigned long pages;
-	struct file *file = mddev->bitmap_file;
+	struct file *file = mddev->bitmap_info.file;
 	int err;
 	sector_t start;
+	struct sysfs_dirent *bm;
 
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 
-	if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
+	if (!file && !mddev->bitmap_info.offset) /* bitmap disabled, nothing to do */
 		return 0;
 
-	BUG_ON(file && mddev->bitmap_offset);
+	BUG_ON(file && mddev->bitmap_info.offset);
 
 	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
 	if (!bitmap)
@@ -1620,8 +1678,14 @@ int bitmap_create(mddev_t *mddev)
 
 	bitmap->mddev = mddev;
 
+	bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap");
+	if (bm) {
+		bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "can_clear");
+		sysfs_put(bm);
+	} else
+		bitmap->sysfs_can_clear = NULL;
+
 	bitmap->file = file;
-	bitmap->offset = mddev->bitmap_offset;
 	if (file) {
 		get_file(file);
 		/* As future accesses to this file will use bmap,
@@ -1630,12 +1694,22 @@ int bitmap_create(mddev_t *mddev)
 		 */
 		vfs_fsync(file, file->f_dentry, 1);
 	}
-	/* read superblock from bitmap file (this sets bitmap->chunksize) */
-	err = bitmap_read_sb(bitmap);
+	/* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */
+	if (!mddev->bitmap_info.external)
+		err = bitmap_read_sb(bitmap);
+	else {
+		err = 0;
+		if (mddev->bitmap_info.chunksize == 0 ||
+		    mddev->bitmap_info.daemon_sleep == 0)
+			/* chunksize and time_base need to be
+			 * set first. */
+			err = -EINVAL;
+	}
 	if (err)
 		goto error;
 
-	bitmap->chunkshift = ffz(~bitmap->chunksize);
+	bitmap->daemon_lastrun = jiffies;
+	bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize);
 
 	/* now that chunksize and chunkshift are set, we can use these macros */
  	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
@@ -1677,7 +1751,8 @@ int bitmap_create(mddev_t *mddev)
 
 	mddev->bitmap = bitmap;
 
-	mddev->thread->timeout = bitmap->daemon_sleep * HZ;
+	mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
+	md_wakeup_thread(mddev->thread);
 
 	bitmap_update_sb(bitmap);
 
@@ -1688,6 +1763,264 @@ int bitmap_create(mddev_t *mddev)
 	return err;
 }
 
+static ssize_t
+location_show(mddev_t *mddev, char *page)
+{
+	ssize_t len;
+	if (mddev->bitmap_info.file) {
+		len = sprintf(page, "file");
+	} else if (mddev->bitmap_info.offset) {
+		len = sprintf(page, "%+lld", (long long)mddev->bitmap_info.offset);
+	} else
+		len = sprintf(page, "none");
+	len += sprintf(page+len, "\n");
+	return len;
+}
+
+static ssize_t
+location_store(mddev_t *mddev, const char *buf, size_t len)
+{
+
+	if (mddev->pers) {
+		if (!mddev->pers->quiesce)
+			return -EBUSY;
+		if (mddev->recovery || mddev->sync_thread)
+			return -EBUSY;
+	}
+
+	if (mddev->bitmap || mddev->bitmap_info.file ||
+	    mddev->bitmap_info.offset) {
+		/* bitmap already configured.  Only option is to clear it */
+		if (strncmp(buf, "none", 4) != 0)
+			return -EBUSY;
+		if (mddev->pers) {
+			mddev->pers->quiesce(mddev, 1);
+			bitmap_destroy(mddev);
+			mddev->pers->quiesce(mddev, 0);
+		}
+		mddev->bitmap_info.offset = 0;
+		if (mddev->bitmap_info.file) {
+			struct file *f = mddev->bitmap_info.file;
+			mddev->bitmap_info.file = NULL;
+			restore_bitmap_write_access(f);
+			fput(f);
+		}
+	} else {
+		/* No bitmap, OK to set a location */
+		long long offset;
+		if (strncmp(buf, "none", 4) == 0)
+			/* nothing to be done */;
+		else if (strncmp(buf, "file:", 5) == 0) {
+			/* Not supported yet */
+			return -EINVAL;
+		} else {
+			int rv;
+			if (buf[0] == '+')
+				rv = strict_strtoll(buf+1, 10, &offset);
+			else
+				rv = strict_strtoll(buf, 10, &offset);
+			if (rv)
+				return rv;
+			if (offset == 0)
+				return -EINVAL;
+			if (mddev->bitmap_info.external == 0 &&
+			    mddev->major_version == 0 &&
+			    offset != mddev->bitmap_info.default_offset)
+				return -EINVAL;
+			mddev->bitmap_info.offset = offset;
+			if (mddev->pers) {
+				mddev->pers->quiesce(mddev, 1);
+				rv = bitmap_create(mddev);
+				if (rv) {
+					bitmap_destroy(mddev);
+					mddev->bitmap_info.offset = 0;
+				}
+				mddev->pers->quiesce(mddev, 0);
+				if (rv)
+					return rv;
+			}
+		}
+	}
+	if (!mddev->external) {
+		/* Ensure new bitmap info is stored in
+		 * metadata promptly.
+		 */
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		md_wakeup_thread(mddev->thread);
+	}
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_location =
+__ATTR(location, S_IRUGO|S_IWUSR, location_show, location_store);
+
+static ssize_t
+timeout_show(mddev_t *mddev, char *page)
+{
+	ssize_t len;
+	unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ;
+	unsigned long jifs = mddev->bitmap_info.daemon_sleep % HZ;
+	
+	len = sprintf(page, "%lu", secs);
+	if (jifs)
+		len += sprintf(page+len, ".%03u", jiffies_to_msecs(jifs));
+	len += sprintf(page+len, "\n");
+	return len;
+}
+
+static ssize_t
+timeout_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	/* timeout can be set at any time */
+	unsigned long timeout;
+	int rv = strict_strtoul_scaled(buf, &timeout, 4);
+	if (rv)
+		return rv;
+
+	/* just to make sure we don't overflow... */
+	if (timeout >= LONG_MAX / HZ)
+		return -EINVAL;
+
+	timeout = timeout * HZ / 10000;
+
+	if (timeout >= MAX_SCHEDULE_TIMEOUT)
+		timeout = MAX_SCHEDULE_TIMEOUT-1;
+	if (timeout < 1)
+		timeout = 1;
+	mddev->bitmap_info.daemon_sleep = timeout;
+	if (mddev->thread) {
+		/* if thread->timeout is MAX_SCHEDULE_TIMEOUT, then
+		 * the bitmap is all clean and we don't need to
+		 * adjust the timeout right now
+		 */
+		if (mddev->thread->timeout < MAX_SCHEDULE_TIMEOUT) {
+			mddev->thread->timeout = timeout;
+			md_wakeup_thread(mddev->thread);
+		}
+	}
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_timeout =
+__ATTR(time_base, S_IRUGO|S_IWUSR, timeout_show, timeout_store);
+
+static ssize_t
+backlog_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%lu\n", mddev->bitmap_info.max_write_behind);
+}
+
+static ssize_t
+backlog_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	unsigned long backlog;
+	int rv = strict_strtoul(buf, 10, &backlog);
+	if (rv)
+		return rv;
+	if (backlog > COUNTER_MAX)
+		return -EINVAL;
+	mddev->bitmap_info.max_write_behind = backlog;
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_backlog =
+__ATTR(backlog, S_IRUGO|S_IWUSR, backlog_show, backlog_store);
+
+static ssize_t
+chunksize_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%lu\n", mddev->bitmap_info.chunksize);
+}
+
+static ssize_t
+chunksize_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	/* Can only be changed when no bitmap is active */
+	int rv;
+	unsigned long csize;
+	if (mddev->bitmap)
+		return -EBUSY;
+	rv = strict_strtoul(buf, 10, &csize);
+	if (rv)
+		return rv;
+	if (csize < 512 ||
+	    !is_power_of_2(csize))
+		return -EINVAL;
+	mddev->bitmap_info.chunksize = csize;
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_chunksize =
+__ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store);
+
+static ssize_t metadata_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%s\n", (mddev->bitmap_info.external
+				      ? "external" : "internal"));
+}
+
+static ssize_t metadata_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	if (mddev->bitmap ||
+	    mddev->bitmap_info.file ||
+	    mddev->bitmap_info.offset)
+		return -EBUSY;
+	if (strncmp(buf, "external", 8) == 0)
+		mddev->bitmap_info.external = 1;
+	else if (strncmp(buf, "internal", 8) == 0)
+		mddev->bitmap_info.external = 0;
+	else
+		return -EINVAL;
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_metadata =
+__ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
+
+static ssize_t can_clear_show(mddev_t *mddev, char *page)
+{
+	int len;
+	if (mddev->bitmap)
+		len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ?
+					     "false" : "true"));
+	else
+		len = sprintf(page, "\n");
+	return len;
+}
+
+static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	if (mddev->bitmap == NULL)
+		return -ENOENT;
+	if (strncmp(buf, "false", 5) == 0)
+		mddev->bitmap->need_sync = 1;
+	else if (strncmp(buf, "true", 4) == 0) {
+		if (mddev->degraded)
+			return -EBUSY;
+		mddev->bitmap->need_sync = 0;
+	} else
+		return -EINVAL;
+	return len;
+}
+
+static struct md_sysfs_entry bitmap_can_clear =
+__ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
+
+static struct attribute *md_bitmap_attrs[] = {
+	&bitmap_location.attr,
+	&bitmap_timeout.attr,
+	&bitmap_backlog.attr,
+	&bitmap_chunksize.attr,
+	&bitmap_metadata.attr,
+	&bitmap_can_clear.attr,
+	NULL
+};
+struct attribute_group md_bitmap_group = {
+	.name = "bitmap",
+	.attrs = md_bitmap_attrs,
+};
+
+
 /* the bitmap API -- for raid personalities */
 EXPORT_SYMBOL(bitmap_startwrite);
 EXPORT_SYMBOL(bitmap_endwrite);
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index e98900671ca..cb821d76d1b 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -106,7 +106,7 @@ typedef __u16 bitmap_counter_t;
 #define BITMAP_BLOCK_SHIFT 9
 
 /* how many blocks per chunk? (this is variable) */
-#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT)
+#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->m