md: separate meta and data devs

Allow the metadata to be on a separate device from the
data.

This doesn't mean the data and metadata will by on separate
physical devices - it simply gives device-mapper and userspace
tools more flexibility.

Signed-off-by: NeilBrown <neilb@suse.de>

3 files changed, 17 insertions, 5 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1977765ff964..6cf587196b99 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -264,14 +264,18 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
         mdk_rdev_t *rdev = NULL;
+        struct block_device *bdev;
         mddev_t *mddev = bitmap->mddev;
 
         while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
                 int size = PAGE_SIZE;
                 loff_t offset = mddev->bitmap_info.offset;
+
+                bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
+
                 if (page->index == bitmap->file_pages-1)
                         size = roundup(bitmap->last_page_size,
-                                       bdev_logical_block_size(rdev->bdev));
+                                       bdev_logical_block_size(bdev));
                 /* Just make sure we aren't corrupting data or
                  * metadata
                  */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0bc10cc4b961..b98a85fd10b6 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -765,7 +765,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
          */
         struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);
 
-        bio->bi_bdev = rdev->bdev;
+        bio->bi_bdev = rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev;
         bio->bi_sector = sector;
         bio_add_page(bio, page, size, 0);
         bio->bi_private = rdev;
@@ -803,7 +803,8 @@ int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size,
 
         rw |= REQ_SYNC | REQ_UNPLUG;
 
-        bio->bi_bdev = rdev->bdev;
+        bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
+                rdev->meta_bdev : rdev->bdev;
         if (metadata_op)
                 bio->bi_sector = sector + rdev->sb_start;
         else
@@ -4435,7 +4436,9 @@ int md_run(mddev_t *mddev)
                  * We don't want the data to overlap the metadata,
                  * Internal Bitmap issues have been handled elsewhere.
                  */
-                if (rdev->data_offset < rdev->sb_start) {
+                if (rdev->meta_bdev) {
+                        /* Nothing to check */;
+                } else if (rdev->data_offset < rdev->sb_start) {
                         if (mddev->dev_sectors &&
                             rdev->data_offset + mddev->dev_sectors
                             > rdev->sb_start) {
@@ -5532,7 +5535,6 @@ static int update_size(mddev_t *mddev, sector_t num_sectors)
          * sb_start or, if that is <data_offset, it must fit before the size
          * of each device.  If num_sectors is zero, we find the largest size
          * that fits.
-
          */
         if (mddev->sync_thread)
                 return -EBUSY;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 7e4f358a26a6..eec517ced31a 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -60,6 +60,12 @@ struct mdk_rdev_s
         mddev_t *mddev;                 /* RAID array if running */
         int last_events;                /* IO event timestamp */
 
+        /*
+         * If meta_bdev is non-NULL, it means that a separate device is
+         * being used to store the metadata (superblock/bitmap) which
+         * would otherwise be contained on the same device as the data (bdev).
+         */
+        struct block_device *meta_bdev;
         struct block_device *bdev;      /* block device handle */
 
         struct page     *sb_page;