md: Fix handling for devices from 2TB to 4TB in 0.90 metadata.

commit 27a7b260f71439c40546b43588448faac01adb93 upstream.

0.90 metadata uses an unsigned 32bit number to count the number of
kilobytes used from each device.
This should allow up to 4TB per device.
However we multiply this by 2 (to get sectors) before casting to a
larger type, so sizes above 2TB get truncated.

Also we allow rdev->sectors to be larger than 4TB, so it is possible
for the array to be resized larger than the metadata can handle.
So make sure rdev->sectors never exceeds 4TB when 0.90 metadata is in
used.

Also the sanity check at the end of super_90_load should include level
1 as it used ->size too. (RAID0 and Linear don't use ->size at all).

Reported-by: Pim Zandbergen <P.Zandbergen@macroscoop.nl>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index d26df7f1b5abff65626429922452778f6ffe9062..4788c82182049341081ecdd6949e403adc0c7333 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -985,8 +985,11 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
                        ret = 0;
        }
        rdev->sectors = rdev->sb_start;
+       /* Limit to 4TB as metadata cannot record more than that */
+       if (rdev->sectors >= (2ULL << 32))
+               rdev->sectors = (2ULL << 32) - 2;
 
-       if (rdev->sectors < sb->size * 2 && sb->level > 1)
+       if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
                /* "this cannot possibly happen" ... */
                ret = -EINVAL;
 
@@ -1021,7 +1024,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
                mddev->clevel[0] = 0;
                mddev->layout = sb->layout;
                mddev->raid_disks = sb->raid_disks;
-               mddev->dev_sectors = sb->size * 2;
+               mddev->dev_sectors = ((sector_t)sb->size) * 2;
                mddev->events = ev1;
                mddev->bitmap_info.offset = 0;
                mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
@@ -1260,6 +1263,11 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
        rdev->sb_start = calc_dev_sboffset(rdev->bdev);
        if (!num_sectors || num_sectors > rdev->sb_start)
                num_sectors = rdev->sb_start;
+       /* Limit to 4TB as metadata cannot record more than that.
+        * 4TB == 2^32 KB, or 2*2^32 sectors.
+        */
+       if (num_sectors >= (2ULL << 32))
+               num_sectors = (2ULL << 32) - 2;
        md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
                       rdev->sb_page);
        md_super_wait(rdev->mddev);