[PATCH] md: limit size of sb read/written to appropriate amount

version-1 superblocks are not (normally) 4K long, and can be of variable size.
 Writing the full 4K can cause corruption (but only in non-default
configurations).

With this patch the super-block-flavour can choose a size to read, and set a
size to write based on what it finds.

Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1be3f2de396b4aca3cc2c20493ea58dd91a28f2b..be7873c61b3cc08c89c8a3cfbcd5e20b29f6f162 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -393,7 +393,7 @@ int sync_page_io(struct block_device *bdev, sector_t sector, int size,
        return ret;
 }
 
-static int read_disk_sb(mdk_rdev_t * rdev)
+static int read_disk_sb(mdk_rdev_t * rdev, int size)
 {
        char b[BDEVNAME_SIZE];
        if (!rdev->sb_page) {
@@ -404,7 +404,7 @@ static int read_disk_sb(mdk_rdev_t * rdev)
                return 0;
 
 
-       if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, READ))
+       if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
                goto fail;
        rdev->sb_loaded = 1;
        return 0;
@@ -531,7 +531,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
        sb_offset = calc_dev_sboffset(rdev->bdev);
        rdev->sb_offset = sb_offset;
 
-       ret = read_disk_sb(rdev);
+       ret = read_disk_sb(rdev, MD_SB_BYTES);
        if (ret) return ret;
 
        ret = -EINVAL;
@@ -564,6 +564,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 
        rdev->preferred_minor = sb->md_minor;
        rdev->data_offset = 0;
+       rdev->sb_size = MD_SB_BYTES;
 
        if (sb->level == LEVEL_MULTIPATH)
                rdev->desc_nr = -1;
@@ -837,6 +838,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
        int ret;
        sector_t sb_offset;
        char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+       int bmask;
 
        /*
         * Calculate the position of the superblock.
@@ -865,7 +867,10 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
        }
        rdev->sb_offset = sb_offset;
 
-       ret = read_disk_sb(rdev);
+       /* superblock is rarely larger than 1K, but it can be larger,
+        * and it is safe to read 4k, so we do that
+        */
+       ret = read_disk_sb(rdev, 4096);
        if (ret) return ret;
 
 
@@ -891,6 +896,11 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
        rdev->preferred_minor = 0xffff;
        rdev->data_offset = le64_to_cpu(sb->data_offset);
 
+       rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
+       bmask = block_size(rdev->bdev)-1;
+       if (rdev->sb_size & bmask)
+               rdev-> sb_size = (rdev->sb_size | bmask)+1;
+
        if (refdev == 0)
                return 1;
        else {
@@ -1375,7 +1385,7 @@ repeat:
                dprintk("%s ", bdevname(rdev->bdev,b));
                if (!rdev->faulty) {
                        md_super_write(mddev,rdev,
-                                      rdev->sb_offset<<1, MD_SB_BYTES,
+                                      rdev->sb_offset<<1, rdev->sb_size,
                                       rdev->sb_page);
                        dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
                                bdevname(rdev->bdev,b),

diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 8042f55dd3237438c58003bc220bc484ad339456..ebce949b14432c4e3e157da8c32d74336e9de5e1 100644 (file)
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -102,6 +102,7 @@ struct mdk_rdev_s
        int             sb_loaded;
        sector_t        data_offset;    /* start of data in array */
        sector_t        sb_offset;
+       int             sb_size;        /* bytes in the superblock */
        int             preferred_minor;        /* autorun support */
 
        /* A device can be in one of three states based on two flags: