md: Skip cluster setup for dm-raid

There is a bug that the bitmap superblock isn't initialised properly for
dm-raid, so a new field can have garbage in new fields.
(dm-raid does initialisation in the kernel - md initialised the
 superblock in mdadm).

This means that for dm-raid we cannot currently trust the new ->nodes
field. So:
 - use __GFP_ZERO to initialise the superblock properly for all new
    arrays
 - initialise all fields in bitmap_info in bitmap_new_disk_sb
 - ignore ->nodes for dm arrays (yes, this is a hack)

This bug exposes dm-raid to bug in the (still experimental) md-cluster
code, so it is suitable for -stable.  It does cause crashes.

References: https://bugzilla.kernel.org/show_bug.cgi?id=100491
Cc: stable@vger.kernel.org (v4.1)
Signed-off-By: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.com>

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 135a090..c90118e 100644 (file)
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -494,7 +494,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
        bitmap_super_t *sb;
        unsigned long chunksize, daemon_sleep, write_behind;
 
        bitmap_super_t *sb;
        unsigned long chunksize, daemon_sleep, write_behind;
 

-       bitmap->storage.sb_page = alloc_page(GFP_KERNEL);
+       bitmap->storage.sb_page = alloc_page(GFP_KERNEL | __GFP_ZERO);

        if (bitmap->storage.sb_page == NULL)
                return -ENOMEM;
        bitmap->storage.sb_page->index = 0;
        if (bitmap->storage.sb_page == NULL)
                return -ENOMEM;
        bitmap->storage.sb_page->index = 0;


@@ -541,6 +541,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
        sb->state = cpu_to_le32(bitmap->flags);
        bitmap->events_cleared = bitmap->mddev->events;
        sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
        sb->state = cpu_to_le32(bitmap->flags);
        bitmap->events_cleared = bitmap->mddev->events;
        sb->events_cleared = cpu_to_le64(bitmap->mddev->events);

+       bitmap->mddev->bitmap_info.nodes = 0;

 
        kunmap_atomic(sb);
 
 
        kunmap_atomic(sb);
 


@@ -611,8 +612,16 @@ re_read:
        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);
        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);

-       nodes = le32_to_cpu(sb->nodes);
-       strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
+       /* XXX: This is a hack to ensure that we don't use clustering
+        *  in case:
+        *      - dm-raid is in use and
+        *      - the nodes written in bitmap_sb is erroneous.
+        */
+       if (!bitmap->mddev->sync_super) {
+               nodes = le32_to_cpu(sb->nodes);
+               strlcpy(bitmap->mddev->bitmap_info.cluster_name,
+                               sb->cluster_name, 64);
+       }

 
        /* verify that the bitmap-specific fields are valid */
        if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
 
        /* verify that the bitmap-specific fields are valid */
        if (sb->magic != cpu_to_le32(BITMAP_MAGIC))