md: override md superblock recovery_offset for journal device

Journal device stores data in a log structure. We need record the log
start. Here we override md superblock recovery_offset for this purpose.
This field of a journal device is meaningless otherwise.

Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: NeilBrown <neilb@suse.com>

3 files changed, 17 insertions, 2 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 391341a772c7..3592beb6931e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1646,6 +1646,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
                                 return -EINVAL;
                         }
                         set_bit(Journal, &rdev->flags);
+                        rdev->journal_tail = le64_to_cpu(sb->journal_tail);
                         break;
                 default:
                         rdev->saved_raid_disk = role;
@@ -1721,6 +1722,9 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
                         sb->feature_map |=
                                 cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP);
         }
+        /* Note: recovery_offset and journal_tail share space  */
+        if (test_bit(Journal, &rdev->flags))
+                sb->journal_tail = cpu_to_le64(rdev->journal_tail);
         if (test_bit(Replacement, &rdev->flags))
                 sb->feature_map |=
                         cpu_to_le32(MD_FEATURE_REPLACEMENT);
@@ -8097,6 +8101,8 @@ static int remove_and_add_spares(struct mddev *mddev,
                         continue;
                 if (test_bit(Faulty, &rdev->flags))
                         continue;
+                if (test_bit(Journal, &rdev->flags))
+                        continue;
                 if (mddev->ro &&
                     ! (rdev->saved_raid_disk >= 0 &&
                        !test_bit(Bitmap_sync, &rdev->flags)))
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 88dc6312f5d5..2b0f62fb6146 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -87,10 +87,16 @@ struct md_rdev {
                                          * array and could again if we did a partial
                                          * resync from the bitmap
                                          */
-        sector_t        recovery_offset;/* If this device has been partially
+        union {
+                sector_t recovery_offset;/* If this device has been partially
                                          * recovered, this is where we were
                                          * up to.
                                          */
+                sector_t journal_tail;  /* If this device is a journal device,
+                                         * this is the journal tail (journal
+                                         * recovery start point)
+                                         */
+        };
 
         atomic_t        nr_pending;     /* number of pending requests.
                                          * only maintained for arrays that
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index eaaab52077a3..a5f54ff26c20 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -258,7 +258,10 @@ struct mdp_superblock_1 {
         __le64  data_offset;    /* sector start of data, often 0 */
         __le64  data_size;      /* sectors in this device that can be used for data */
         __le64  super_offset;   /* sector start of this superblock */
-        __le64  recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+        union {
+                __le64  recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+                __le64  journal_tail;/* journal tail of journal device (from data_offset) */
+        };
         __le32  dev_number;     /* permanent identifier of this  device - not role in raid */
         __le32  cnt_corrected_read; /* number of read errors that were corrected by re-writing */
         __u8    device_uuid[16]; /* user-space setable, ignored by kernel */