Merge tag 'md-3.5' of git://neil.brown.name/md

Pull md updates from NeilBrown:
 "It's been a busy cycle for md - lots of fun stuff here..  if you like
  this kind of thing :-)

  Main features:
   - RAID10 arrays can be reshaped - adding and removing devices and
     changing chunks (not 'far' array though)
   - allow RAID5 arrays to be reshaped with a backup file (not tested
     yet, but the priciple works fine for RAID10).
   - arrays can be reshaped while a bitmap is present - you no longer
     need to remove it first
   - SSSE3 support for RAID6 syndrome calculations

  and of course a number of minor fixes etc."

* tag 'md-3.5' of git://neil.brown.name/md: (56 commits)
  md/bitmap: record the space available for the bitmap in the superblock.
  md/raid10: Remove extras after reshape to smaller number of devices.
  md/raid5: improve removal of extra devices after reshape.
  md: check the return of mddev_find()
  MD RAID1: Further conditionalize 'fullsync'
  DM RAID: Use md_error() in place of simply setting Faulty bit
  DM RAID: Record and handle missing devices
  DM RAID: Set recovery flags on resume
  md/raid5: Allow reshape while a bitmap is present.
  md/raid10: resize bitmap when required during reshape.
  md: allow array to be resized while bitmap is present.
  md/bitmap: make sure reshape request are reflected in superblock.
  md/bitmap: add bitmap_resize function to allow bitmap resizing.
  md/bitmap: use DIV_ROUND_UP instead of open-code
  md/bitmap: create a 'struct bitmap_counts' substructure of 'struct bitmap'
  md/bitmap: make bitmap bitops atomic.
  md/bitmap: make _page_attr bitops atomic.
  md/bitmap: merge bitmap_file_unmap and bitmap_file_put.
  md/bitmap: remove async freeing of bitmap file.
  md/bitmap: convert some spin_lock_irqsave to spin_lock_irq
  ...

10 files changed, 2365 insertions, 795 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 17e2b472e16..15dbe03117e 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -45,7 +45,7 @@ static inline char *bmname(struct bitmap *bitmap)
  * if we find our page, we increment the page's refcount so that it stays
  * allocated while we're using it
  */
-static int bitmap_checkpage(struct bitmap *bitmap,
+static int bitmap_checkpage(struct bitmap_counts *bitmap,
 			    unsigned long page, int create)
 __releases(bitmap->lock)
 __acquires(bitmap->lock)
@@ -76,8 +76,7 @@ __acquires(bitmap->lock)
 	spin_lock_irq(&bitmap->lock);
 
 	if (mappage == NULL) {
-		pr_debug("%s: bitmap map page allocation failed, hijacking\n",
-			 bmname(bitmap));
+		pr_debug("md/bitmap: map page allocation failed, hijacking\n");
 		/* failed - set the hijacked flag so that we can use the
 		 * pointer as a counter */
 		if (!bitmap->bp[page].map)
@@ -100,7 +99,7 @@ __acquires(bitmap->lock)
 /* if page is completely empty, put it back on the free list, or dealloc it */
 /* if page was hijacked, unmark the flag so it might get alloced next time */
 /* Note: lock should be held when calling this */
-static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
+static void bitmap_checkfree(struct bitmap_counts *bitmap, unsigned long page)
 {
 	char *ptr;
 
@@ -130,22 +129,14 @@ 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(struct mddev *mddev, loff_t offset,
-				 struct page *page,
-				 unsigned long index, int size)
+static int read_sb_page(struct mddev *mddev, loff_t offset,
+			struct page *page,
+			unsigned long index, int size)
 {
 	/* choose a good rdev and read the page from there */
 
 	struct md_rdev *rdev;
 	sector_t target;
-	int did_alloc = 0;
-
-	if (!page) {
-		page = alloc_page(GFP_KERNEL);
-		if (!page)
-			return ERR_PTR(-ENOMEM);
-		did_alloc = 1;
-	}
 
 	rdev_for_each(rdev, mddev) {
 		if (! test_bit(In_sync, &rdev->flags)
@@ -158,15 +149,10 @@ static struct page *read_sb_page(struct mddev *mddev, loff_t offset,
 				 roundup(size, bdev_logical_block_size(rdev->bdev)),
 				 page, READ, true)) {
 			page->index = index;
-			attach_page_buffers(page, NULL); /* so that free_buffer will
-							  * quietly no-op */
-			return page;
+			return 0;
 		}
 	}
-	if (did_alloc)
-		put_page(page);
-	return ERR_PTR(-EIO);
-
+	return -EIO;
 }
 
 static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *mddev)
@@ -208,6 +194,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 	struct md_rdev *rdev = NULL;
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
+	struct bitmap_storage *store = &bitmap->storage;
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
 		int size = PAGE_SIZE;
@@ -215,9 +202,13 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 
 		bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
 
-		if (page->index == bitmap->file_pages-1)
-			size = roundup(bitmap->last_page_size,
+		if (page->index == store->file_pages-1) {
+			int last_page_size = store->bytes & (PAGE_SIZE-1);
+			if (last_page_size == 0)
+				last_page_size = PAGE_SIZE;
+			size = roundup(last_page_size,
 				       bdev_logical_block_size(bdev));
+		}
 		/* Just make sure we aren't corrupting data or
 		 * metadata
 		 */
@@ -276,10 +267,10 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
 {
 	struct buffer_head *bh;
 
-	if (bitmap->file == NULL) {
+	if (bitmap->storage.file == NULL) {
 		switch (write_sb_page(bitmap, page, wait)) {
 		case -EINVAL:
-			bitmap->flags |= BITMAP_WRITE_ERROR;
+			set_bit(BITMAP_WRITE_ERROR, &bitmap->flags);
 		}
 	} else {
 
@@ -297,20 +288,16 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
 			wait_event(bitmap->write_wait,
 				   atomic_read(&bitmap->pending_writes)==0);
 	}
-	if (bitmap->flags & BITMAP_WRITE_ERROR)
+	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }
 
 static void end_bitmap_write(struct buffer_head *bh, int uptodate)
 {
 	struct bitmap *bitmap = bh->b_private;
-	unsigned long flags;
 
-	if (!uptodate) {
-		spin_lock_irqsave(&bitmap->lock, flags);
-		bitmap->flags |= BITMAP_WRITE_ERROR;
-		spin_unlock_irqrestore(&bitmap->lock, flags);
-	}
+	if (!uptodate)
+		set_bit(BITMAP_WRITE_ERROR, &bitmap->flags);
 	if (atomic_dec_and_test(&bitmap->pending_writes))
 		wake_up(&bitmap->write_wait);
 }
@@ -325,8 +312,12 @@ __clear_page_buffers(struct page *page)
 }
 static void free_buffers(struct page *page)
 {
-	struct buffer_head *bh = page_buffers(page);
+	struct buffer_head *bh;
 
+	if (!PagePrivate(page))
+		return;
+
+	bh = page_buffers(page);
 	while (bh) {
 		struct buffer_head *next = bh->b_this_page;
 		free_buffer_head(bh);
@@ -343,11 +334,12 @@ static void free_buffers(struct page *page)
  * This usage is similar to how swap files are handled, and allows us
  * to write to a file with no concerns of memory allocation failing.
  */
-static struct page *read_page(struct file *file, unsigned long index,
-			      struct bitmap *bitmap,
-			      unsigned long count)
+static int read_page(struct file *file, unsigned long index,
+		     struct bitmap *bitmap,
+		     unsigned long count,
+		     struct page *page)
 {
-	struct page *page = NULL;
+	int ret = 0;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct buffer_head *bh;
 	sector_t block;
@@ -355,16 +347,9 @@ static struct page *read_page(struct file *file, unsigned long index,
 	pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
 		 (unsigned long long)index << PAGE_SHIFT);
 
-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		page = ERR_PTR(-ENOMEM);
-	if (IS_ERR(page))
-		goto out;
-
 	bh = alloc_page_buffers(page, 1<<inode->i_blkbits, 0);
 	if (!bh) {
-		put_page(page);
-		page = ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
 		goto out;
 	}
 	attach_page_buffers(page, bh);
@@ -376,8 +361,7 @@ static struct page *read_page(struct file *file, unsigned long index,
 			bh->b_blocknr = bmap(inode, block);
 			if (bh->b_blocknr == 0) {
 				/* Cannot use this file! */
-				free_buffers(page);
-				page = ERR_PTR(-EINVAL);
+				ret = -EINVAL;
 				goto out;
 			}
 			bh->b_bdev = inode->i_sb->s_bdev;
@@ -400,17 +384,15 @@ static struct page *read_page(struct file *file, unsigned long index,
 
 	wait_event(bitmap->write_wait,
 		   atomic_read(&bitmap->pending_writes)==0);
-	if (bitmap->flags & BITMAP_WRITE_ERROR) {
-		free_buffers(page);
-		page = ERR_PTR(-EIO);
-	}
+	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
+		ret = -EIO;
 out:
-	if (IS_ERR(page))
-		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %ld\n",
+	if (ret)
+		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %d\n",
 			(int)PAGE_SIZE,
 			(unsigned long long)index << PAGE_SHIFT,
-			PTR_ERR(page));
-	return page;
+			ret);
+	return ret;
 }
 
 /*
@@ -426,9 +408,9 @@ void bitmap_update_sb(struct bitmap *bitmap)
 		return;
 	if (bitmap->mddev->bitmap_info.external)
 		return;
-	if (!bitmap->sb_page) /* no superblock */
+	if (!bitmap->storage.sb_page) /* no superblock */
 		return;
-	sb = kmap_atomic(bitmap->sb_page);
+	sb = kmap_atomic(bitmap->storage.sb_page);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared)
 		/* rocking back to read-only */
@@ -438,8 +420,13 @@ void bitmap_update_sb(struct bitmap *bitmap)
 	/* 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);
+	/* This might have been changed by a reshape */
+	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
+	sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize);
+	sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
+					   bitmap_info.space);
 	kunmap_atomic(sb);
-	write_page(bitmap, bitmap->sb_page, 1);
+	write_page(bitmap, bitmap->storage.sb_page, 1);
 }
 
 /* print out the bitmap file superblock */
@@ -447,9 +434,9 @@ void bitmap_print_sb(struct bitmap *bitmap)
 {
 	bitmap_super_t *sb;
 
-	if (!bitmap || !bitmap->sb_page)
+	if (!bitmap || !bitmap->storage.sb_page)
 		return;
-	sb = kmap_atomic(bitmap->sb_page);
+	sb = kmap_atomic(bitmap->storage.sb_page);
 	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
 	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
 	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
@@ -488,15 +475,15 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	unsigned long chunksize, daemon_sleep, write_behind;
 	int err = -EINVAL;
 
-	bitmap->sb_page = alloc_page(GFP_KERNEL);
-	if (IS_ERR(bitmap->sb_page)) {
-		err = PTR_ERR(bitmap->sb_page);
-		bitmap->sb_page = NULL;
+	bitmap->storage.sb_page = alloc_page(GFP_KERNEL);
+	if (IS_ERR(bitmap->storage.sb_page)) {
+		err = PTR_ERR(bitmap->storage.sb_page);
+		bitmap->storage.sb_page = NULL;
 		return err;
 	}
-	bitmap->sb_page->index = 0;
+	bitmap->storage.sb_page->index = 0;
 
-	sb = kmap_atomic(bitmap->sb_page);
+	sb = kmap_atomic(bitmap->storage.sb_page);
 
 	sb->magic = cpu_to_le32(BITMAP_MAGIC);
 	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
@@ -534,8 +521,8 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 
 	memcpy(sb->uuid, bitmap->mddev->uuid, 16);
 
-	bitmap->flags |= BITMAP_STALE;
-	sb->state |= cpu_to_le32(BITMAP_STALE);
+	set_bit(BITMAP_STALE, &bitmap->flags);
+	sb->state = cpu_to_le32(bitmap->flags);
 	bitmap->events_cleared = bitmap->mddev->events;
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
 
@@ -551,31 +538,45 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	bitmap_super_t *sb;
 	unsigned long chunksize, daemon_sleep, write_behind;
 	unsigned long long events;
+	unsigned long sectors_reserved = 0;
 	int err = -EINVAL;
+	struct page *sb_page;
 
+	if (!bitmap->storage.file && !bitmap->mddev->bitmap_info.offset) {
+		chunksize = 128 * 1024 * 1024;
+		daemon_sleep = 5 * HZ;
+		write_behind = 0;
+		set_bit(BITMAP_STALE, &bitmap->flags);
+		err = 0;
+		goto out_no_sb;
+	}
 	/* page 0 is the superblock, read it... */
-	if (bitmap->file) {
-		loff_t isize = i_size_read(bitmap->file->f_mapping->host);
+	sb_page = alloc_page(GFP_KERNEL);
+	if (!sb_page)
+		return -ENOMEM;
+	bitmap->storage.sb_page = sb_page;
+
+	if (bitmap->storage.file) {
+		loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host);
 		int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
 
-		bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
+		err = read_page(bitmap->storage.file, 0,
+				bitmap, bytes, sb_page);
 	} else {
-		bitmap->sb_page = read_sb_page(bitmap->mddev,
-					       bitmap->mddev->bitmap_info.offset,
-					       NULL,
-					       0, sizeof(bitmap_super_t));
+		err = read_sb_page(bitmap->mddev,
+				   bitmap->mddev->bitmap_info.offset,
+				   sb_page,
+				   0, sizeof(bitmap_super_t));
 	}
-	if (IS_ERR(bitmap->sb_page)) {
-		err = PTR_ERR(bitmap->sb_page);
-		bitmap->sb_page = NULL;
+	if (err)
 		return err;
-	}
 
-	sb = kmap_atomic(bitmap->sb_page);
+	sb = kmap_atomic(sb_page);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
+	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -618,60 +619,32 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 			       "-- forcing full recovery\n",
 			       bmname(bitmap), events,
 			       (unsigned long long) bitmap->mddev->events);
-			sb->state |= cpu_to_le32(BITMAP_STALE);
+			set_bit(BITMAP_STALE, &bitmap->flags);
 		}
 	}
 
 	/* assign fields using values from superblock */
-	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;
+		set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
 	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
-	if (bitmap->flags & BITMAP_STALE)
-		bitmap->events_cleared = bitmap->mddev->events;
 	err = 0;
 out:
 	kunmap_atomic(sb);
+out_no_sb:
+	if (test_bit(BITMAP_STALE, &bitmap->flags))
+		bitmap->events_cleared = bitmap->mddev->events;
+	bitmap->mddev->bitmap_info.chunksize = chunksize;
+	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+	if (bitmap->mddev->bitmap_info.space == 0 ||
+	    bitmap->mddev->bitmap_info.space > sectors_reserved)
+		bitmap->mddev->bitmap_info.space = sectors_reserved;
 	if (err)
 		bitmap_print_sb(bitmap);
 	return err;
 }
 
-enum bitmap_mask_op {
-	MASK_SET,
-	MASK_UNSET
-};
-
-/* record the state of the bitmap in the superblock.  Return the old value */
-static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
-			     enum bitmap_mask_op op)
-{
-	bitmap_super_t *sb;
-	int old;
-
-	if (!bitmap->sb_page) /* can't set the state */
-		return 0;
-	sb = kmap_atomic(bitmap->sb_page);
-	old = le32_to_cpu(sb->state) & bits;
-	switch (op) {
-	case MASK_SET:
-		sb->state |= cpu_to_le32(bits);
-		bitmap->flags |= bits;
-		break;
-	case MASK_UNSET:
-		sb->state &= cpu_to_le32(~bits);
-		bitmap->flags &= ~bits;
-		break;
-	default:
-		BUG();
-	}
-	kunmap_atomic(sb);
-	return old;
-}
-
 /*
  * general bitmap file operations
  */
@@ -683,17 +656,19 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
  * 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(struct bitmap *bitmap, unsigned long chunk)
+static inline unsigned long file_page_index(struct bitmap_storage *store,
+					    unsigned long chunk)
 {
-	if (!bitmap->mddev->bitmap_info.external)
+	if (store->sb_page)
 		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(struct bitmap *bitmap, unsigned long chunk)
+static inline unsigned long file_page_offset(struct bitmap_storage *store,
+					     unsigned long chunk)
 {
-	if (!bitmap->mddev->bitmap_info.external)
+	if (store->sb_page)
 		chunk += sizeof(bitmap_super_t) << 3;
 	return chunk & (PAGE_BITS - 1);
 }
@@ -705,57 +680,86 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
  * 1 page (e.g., x86) or less than 1 page -- so the bitmap might start on page
  * 0 or page 1
  */
-static inline struct page *filemap_get_page(struct bitmap *bitmap,
+static inline struct page *filemap_get_page(struct bitmap_storage *store,
 					    unsigned long chunk)
 {
-	if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
+	if (file_page_index(store, chunk) >= store->file_pages)
 		return NULL;
-	return bitmap->filemap[file_page_index(bitmap, chunk)
-			       - file_page_index(bitmap, 0)];
+	return store->filemap[file_page_index(store, chunk)
+			      - file_page_index(store, 0)];
 }
 
-static void bitmap_file_unmap(struct bitmap *bitmap)
+static int bitmap_storage_alloc(struct bitmap_storage *store,
+				unsigned long chunks, int with_super)
+{
+	int pnum;
+	unsigned long num_pages;
+	unsigned long bytes;
+
+	bytes = DIV_ROUND_UP(chunks, 8);
+	if (with_super)
+		bytes += sizeof(bitmap_super_t);
+
+	num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
+
+	store->filemap = kmalloc(sizeof(struct page *)
+				 * num_pages, GFP_KERNEL);
+	if (!store->filemap)
+		return -ENOMEM;
+
+	if (with_super && !store->sb_page) {
+		store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
+		if (store->sb_page == NULL)
+			return -ENOMEM;
+		store->sb_page->index = 0;
+	}
+	pnum = 0;
+	if (store->sb_page) {
+		store->filemap[0] = store->sb_page;
+		pnum = 1;
+	}
+	for ( ; pnum < num_pages; pnum++) {
+		store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+		if (!store->filemap[pnum]) {
+			store->file_pages = pnum;
+			return -ENOMEM;
+		}
+		store->filemap[pnum]->index = pnum;
+	}
+	store->file_pages = pnum;
+
+	/* We need 4 bits per page, rounded up to a multiple
+	 * of sizeof(unsigned long) */
+	store->filemap_attr = kzalloc(
+		roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
+		GFP_KERNEL);
+	if (!store->filemap_attr)
+		return -ENOMEM;
+
+	store->bytes = bytes;
+
+	return 0;
+}
+
+static void bitmap_file_unmap(struct bitmap_storage *store)
 {
 	struct page **map, *sb_page;
-	unsigned long *attr;
 	int pages;
-	unsigned long flags;
+	struct file *file;
 
-	spin_lock_irqsave(&bitmap->lock, flags);
-	map = bitmap->filemap;
-	bitmap->filemap = NULL;
-	attr = bitmap->filemap_attr;
-	bitmap->filemap_attr = NULL;
-	pages = bitmap->file_pages;
-	bitmap->file_pages = 0;
-	sb_page = bitmap->sb_page;
-	bitmap->sb_page = NULL;
-	spin_unlock_irqrestore(&bitmap->lock, flags);
+	file = store->file;
+	map = store->filemap;
+	pages = store->file_pages;
+	sb_page = store->sb_page;
 
 	while (pages--)
 		if (map[pages] != sb_page) /* 0 is sb_page, release it below */
 			free_buffers(map[pages]);
 	kfree(map);
-	kfree(attr);
+	kfree(store->filemap_attr);
 
 	if (sb_page)
 		free_buffers(sb_page);
-}
-
-static void bitmap_file_put(struct bitmap *bitmap)
-{
-	struct file *file;
-	unsigned long flags;
-
-	spin_lock_irqsave(&bitmap->lock, flags);
-	file = bitmap->file;
-	bitmap->file = NULL;
-	spin_unlock_irqrestore(&bitmap->lock, flags);
-
-	if (file)
-		wait_event(bitmap->write_wait,
-			   atomic_read(&bitmap->pending_writes)==0);
-	bitmap_file_unmap(bitmap);
 
 	if (file) {
 		struct inode *inode = file->f_path.dentry->d_inode;
@@ -773,14 +777,14 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 {
 	char *path, *ptr = NULL;
 
-	if (bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET) == 0) {
+	if (!test_and_set_bit(BITMAP_STALE, &bitmap->flags)) {
 		bitmap_update_sb(bitmap);
 
-		if (bitmap->file) {
+		if (bitmap->storage.file) {
 			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (path)
-				ptr = d_path(&bitmap->file->f_path, path,
-					     PAGE_SIZE);
+				ptr = d_path(&bitmap->storage.file->f_path,
+					     path, PAGE_SIZE);
 
 			printk(KERN_ALERT
 			      "%s: kicking failed bitmap file %s from array!\n",
@@ -792,10 +796,6 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 			       "%s: disabling internal bitmap due to errors\n",
 			       bmname(bitmap));
 	}
-
-	bitmap_file_put(bitmap);
-
-	return;
 }
 
 enum bitmap_page_attr {
@@ -805,24 +805,30 @@ enum bitmap_page_attr {
 	BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */
 };
 
-static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
-				enum bitmap_page_attr attr)
+static inline void set_page_attr(struct bitmap *bitmap, int pnum,
+				 enum bitmap_page_attr attr)
 {
-	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	set_bit((pnum<<2) + attr, bitmap->storage.filemap_attr);
 }
 
-static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
-				enum bitmap_page_attr attr)
+static inline void clear_page_attr(struct bitmap *bitmap, int pnum,
+				   enum bitmap_page_attr attr)
 {
-	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	clear_bit((pnum<<2) + attr, bitmap->storage.filemap_attr);
 }
 
-static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
-					   enum bitmap_page_attr attr)
+static inline int test_page_attr(struct bitmap *bitmap, int pnum,
+				 enum bitmap_page_attr attr)
 {
-	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	return test_bit((pnum<<2) + attr, bitmap->storage.filemap_attr);
 }
 
+static inline int test_and_clear_page_attr(struct bitmap *bitmap, int pnum,
+					   enum bitmap_page_attr attr)
+{
+	return test_and_clear_bit((pnum<<2) + attr,
+				  bitmap->storage.filemap_attr);
+}
 /*
  * bitmap_file_set_bit -- called before performing a write to the md device
  * to set (and eventually sync) a particular bit in the bitmap file
@@ -835,26 +841,46 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long bit;
 	struct page *page;
 	void *kaddr;
-	unsigned long chunk = block >> bitmap->chunkshift;
+	unsigned long chunk = block >> bitmap->counts.chunkshift;
 
-	if (!bitmap->filemap)
-		return;
-
-	page = filemap_get_page(bitmap, chunk);
+	page = filemap_get_page(&bitmap->storage, chunk);
 	if (!page)
 		return;
-	bit = file_page_offset(bitmap, chunk);
+	bit = file_page_offset(&bitmap->storage, chunk);
 
 	/* set the bit */
 	kaddr = kmap_atomic(page);
-	if (bitmap->flags & BITMAP_HOSTENDIAN)
+	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 		set_bit(bit, kaddr);
 	else
-		__set_bit_le(bit, kaddr);
+		test_and_set_bit_le(bit, kaddr);
 	kunmap_atomic(kaddr);
 	pr_debug("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);
+	set_page_attr(bitmap, page->index, BITMAP_PAGE_DIRTY);
+}
+
+static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
+{
+	unsigned long bit;
+	struct page *page;
+	void *paddr;
+	unsigned long chunk = block >> bitmap->counts.chunkshift;
+
+	page = filemap_get_page(&bitmap->storage, chunk);
+	if (!page)
+		return;
+	bit = file_page_offset(&bitmap->storage, chunk);
+	paddr = kmap_atomic(page);
+	if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
+		clear_bit(bit, paddr);
+	else
+		test_and_clear_bit_le(bit, paddr);
+	kunmap_atomic(paddr);
+	if (!test_page_attr(bitmap, page->index, BITMAP_PAGE_NEEDWRITE)) {
+		set_page_attr(bitmap, page->index, BITMAP_PAGE_PENDING);
+		bitmap->allclean = 0;
+	}
 }
 
 /* this gets called when the md device is ready to unplug its underlying
@@ -862,42 +888,37 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
  * sync the dirty pages of the bitmap file to disk */
 void bitmap_unplug(struct bitmap *bitmap)
 {
-	unsigned long i, flags;
+	unsigned long i;
 	int dirty, need_write;
-	struct page *page;
 	int wait = 0;
 
-	if (!bitmap)
+	if (!bitmap || !bitmap->storage.filemap ||
+	    test_bit(BITMAP_STALE, &bitmap->flags))
 		return;
 
 	/* look at each page to see if there are any set bits that need to be
 	 * flushed out to disk */
-	for (i = 0; i < bitmap->file_pages; i++) {
-		spin_lock_irqsave(&bitmap->lock, flags);
-		if (!bitmap->filemap) {
-			spin_unlock_irqrestore(&bitmap->lock, flags);
+	for (i = 0; i < bitmap->storage.file_pages; i++) {
+		if (!bitmap->storage.filemap)
 			return;
+		dirty = test_and_clear_page_attr(bitmap, i, BITMAP_PAGE_DIRTY);
+		need_write = test_and_clear_page_attr(bitmap, i,
+						      BITMAP_PAGE_NEEDWRITE);
+		if (dirty || need_write) {
+			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
+			write_page(bitmap, bitmap->storage.filemap[i], 0);
 		}
-		page = bitmap->filemap[i];
-		dirty = test_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
-		need_write = test_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
-		clear_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
-		clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
 		if (dirty)
 			wait = 1;
-		spin_unlock_irqrestore(&bitmap->lock, flags);
-
-		if (dirty || need_write)
-			write_page(bitmap, page, 0);
 	}
 	if (wait) { /* if any writes were performed, we need to wait on them */
-		if (bitmap->file)
+		if (bitmap->storage.file)
 			wait_event(bitmap->write_wait,
 				   atomic_read(&bitmap->pending_writes)==0);
 		else
 			md_super_wait(bitmap->mddev);
 	}
-	if (bitmap->flags & BITMAP_WRITE_ERROR)
+	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }
 EXPORT_SYMBOL(bitmap_unplug);
@@ -917,98 +938,77 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
 static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 {
 	unsigned long i, chunks, index, oldindex, bit;
-	struct page *page = NULL, *oldpage = NULL;
-	unsigned long num_pages, bit_cnt = 0;
+	struct page *page = NULL;
+	unsigned long bit_cnt = 0;
 	struct file *file;
-	unsigned long bytes, offset;
+	unsigned long offset;
 	int outofdate;
 	int ret = -ENOSPC;
 	void *paddr;
+	struct bitmap_storage *store = &bitmap->storage;
 
-	chunks = bitmap->chunks;
-	file = bitmap->file;
+	chunks = bitmap->counts.chunks;
+	file = store->file;
 
-	BUG_ON(!file && !bitmap->mddev->bitmap_info.offset);
+	if (!file && !bitmap->mddev->bitmap_info.offset) {
+		/* No permanent bitmap - fill with '1s'. */
+		store->filemap = NULL;
+		store->file_pages = 0;
+		for (i = 0; i < chunks ; i++) {
+			/* if the disk bit is set, set the memory bit */
+			int needed = ((sector_t)(i+1) << (bitmap->counts.chunkshift)
+				      >= start);
+			bitmap_set_memory_bits(bitmap,
+					       (sector_t)i << bitmap->counts.chunkshift,
+					       needed);
+		}
+		return 0;
+	}
 
-	outofdate = bitmap->flags & BITMAP_STALE;
+	outofdate = test_bit(BITMAP_STALE, &bitmap->flags);
 	if (outofdate)
 		printk(KERN_INFO "%s: bitmap file is out of date, doing full "
 			"recovery\n", bmname(bitmap));
 
-	bytes = DIV_ROUND_UP(bitmap->chunks, 8);
-	if (!bitmap->mddev->bitmap_info.external)
-		bytes += sizeof(bitmap_super_t);
-
-	num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
-
-	if (file && i_size_read(file->f_mapping->host) < bytes) {
+	if (file && i_size_read(file->f_mapping->host) < store->bytes) {
 		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
-			bmname(bitmap),
-			(unsigned long) i_size_read(file->f_mapping->host),
-			bytes);
+		       bmname(bitmap),
+		       (unsigned long) i_size_read(file->f_mapping->host),
+		       store->bytes);
 		goto err;
 	}
 
-	ret = -ENOMEM;
-
-	bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
-	if (!bitmap->filemap)
-		goto err;
-
-	/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
-	bitmap->filemap_attr = kzalloc(
-		roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
-		GFP_KERNEL);
-	if (!bitmap->filemap_attr)
-		goto err;
-
 	oldindex = ~0L;
+	offset = 0;
+	if (!bitmap->mddev->bitmap_info.external)
+		offset = sizeof(bitmap_super_t);
 
 	for (i = 0; i < chunks; i++) {
 		int b;
-		index = file_page_index(bitmap, i);
-		bit = file_page_offset(bitmap, i);
+		index = file_page_index(&bitmap->storage, i);
+		bit = file_page_offset(&bitmap->storage, 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 - index * PAGE_SIZE;
+			if (index == store->file_pages-1)
+				count = store->bytes - index * PAGE_SIZE;
 			else
 				count = PAGE_SIZE;
-			if (index == 0 && bitmap->sb_page) {
-				/*
-				 * if we're here then the superblock page
-				 * contains some bits (PAGE_SIZE != sizeof sb)
-				 * we've already read it in, so just use it
-				 */
-				page = bitmap->sb_page;
-				offset = sizeof(bitmap_super_t);
-				if (!file)
-					page = read_sb_page(
-						bitmap->mddev,
-						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->mddev->bitmap_info.offset,
-						    NULL,
-						    index, count);
-				offset = 0;
-			}
-			if (IS_ERR(page)) { /* read error */
-				ret = PTR_ERR(page);
+			page = store->filemap[index];
+			if (file)
+				ret = read_page(file, index, bitmap,
+						count, page);
+			else
+				ret = read_sb_page(
+					bitmap->mddev,
+					bitmap->mddev->bitmap_info.offset,
+					page,
+					index, count);
+
+			if (ret)
 				goto err;
-			}
 
 			oldindex = index;
-			oldpage = page;
-
-			bitmap->filemap[bitmap->file_pages++] = page;
-			bitmap->last_page_size = count;
 
 			if (outofdate) {
 				/*
@@ -1022,39 +1022,33 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 				write_page(bitmap, page, 1);
 
 				ret = -EIO;
-				if (bitmap->flags & BITMAP_WRITE_ERROR)
+				if (test_bit(BITMAP_WRITE_ERROR,
+					     &bitmap->flags))
 					goto err;
 			}
 		}
 		paddr = kmap_atomic(page);
-		if (bitmap->flags & BITMAP_HOSTENDIAN)
+		if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags))
 			b = test_bit(bit, paddr);
 		else
 			b = test_bit_le(bit, paddr);
 		kunmap_atomic(paddr);
 		if (b) {
 			/* if the disk bit is set, set the memory bit */
-			int needed = ((sector_t)(i+1) << bitmap->chunkshift
+			int needed = ((sector_t)(i+1) << bitmap->counts.chunkshift
 				      >= start);
 			bitmap_set_memory_bits(bitmap,
-					       (sector_t)i << bitmap->chunkshift,
+					       (sector_t)i << bitmap->counts.chunkshift,
 					       needed);
 			bit_cnt++;
 		}
-	}
-
-	/* everything went OK */
-	ret = 0;
-	bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
-
-	if (bit_cnt) { /* Kick recovery if any bits were set */
-		set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
-		md_wakeup_thread(bitmap->mddev->thread);
+		offset = 0;
 	}
 
 	printk(KERN_INFO "%s: bitmap initialized from disk: "
-	       "read %lu/%lu pages, set %lu of %lu bits\n",
-	       bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks);
+	       "read %lu pages, set %lu of %lu bits\n",
+	       bmname(bitmap), store->file_pages,
+	       bit_cnt, chunks);
 
 	return 0;
 
@@ -1071,22 +1065,38 @@ void bitmap_write_all(struct bitmap *bitmap)
 	 */
 	int i;
 
-	spin_lock_irq(&bitmap->lock);
-	for (i = 0; i < bitmap->file_pages; i++)
-		set_page_attr(bitmap, bitmap->filemap[i],
+	if (!bitmap || !bitmap->storage.filemap)
+		return;
+	if (bitmap->storage.file)
+		/* Only one copy, so nothing needed */
+		return;
+
+	for (i = 0; i < bitmap->storage.file_pages; i++)
+		set_page_attr(bitmap, i,
 			      BITMAP_PAGE_NEEDWRITE);
 	bitmap->allclean = 0;
-	spin_unlock_irq(&bitmap->lock);
 }
 
-static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
+static void bitmap_count_page(struct bitmap_counts *bitmap,
+			      sector_t offset, int inc)
 {
 	sector_t chunk = offset >> bitmap->chunkshift;