[PATCH] md: Checkpoint and allow restart of raid5 reshape

We allow the superblock to record an 'old' and a 'new' geometry, and a
position where any conversion is up to.  The geometry allows for changing
chunksize, layout and level as well as number of devices.

When using verion-0.90 superblock, we convert the version to 0.91 while the
conversion is happening so that an old kernel will refuse the assemble the
array.  For version-1, we use a feature bit for the same effect.

When starting an array we check for an incomplete reshape and restart the
reshape process if needed.  If the reshape stopped at an awkward time (like
when updating the first stripe) we refuse to assemble the array, and let
user-space worry about it.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 40 insertions, 3 deletions

diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index 9c77cde5a795..66b44e5e0d6e 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -95,6 +95,8 @@ extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
 extern void md_do_sync(mddev_t *mddev);
 extern void md_new_event(mddev_t *mddev);
 
+extern void md_update_sb(mddev_t * mddev);
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 #endif 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 4e26ef2cacca..1a6f9f2f6282 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -132,6 +132,14 @@ struct mddev_s
 
         char                            uuid[16];
 
+        /* If the array is being reshaped, we need to record the
+         * new shape and an indication of where we are up to.
+         * This is written to the superblock.
+         * If reshape_position is MaxSector, then no reshape is happening (yet).
+         */
+        sector_t                        reshape_position;
+        int                             delta_disks, new_level, new_layout, new_chunk;
+
         struct mdk_thread_s             *thread;        /* management thread */
         struct mdk_thread_s             *sync_thread;   /* doing resync or reconstruct */
         sector_t                        curr_resync;    /* blocks scheduled */
diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h
index c100fa5d4bfa..774e1acfb8c4 100644
--- a/include/linux/raid/md_p.h
+++ b/include/linux/raid/md_p.h
@@ -102,6 +102,18 @@ typedef struct mdp_device_descriptor_s {
 #define MD_SB_ERRORS            1
 
 #define MD_SB_BITMAP_PRESENT    8 /* bitmap may be present nearby */
+
+/*
+ * Notes:
+ * - if an array is being reshaped (restriped) in order to change the
+ *   the number of active devices in the array, 'raid_disks' will be
+ *   the larger of the old and new numbers.  'delta_disks' will
+ *   be the "new - old".  So if +ve, raid_disks is the new value, and
+ *   "raid_disks-delta_disks" is the old.  If -ve, raid_disks is the
+ *   old value and "raid_disks+delta_disks" is the new (smaller) value.
+ */
+
+
 typedef struct mdp_superblock_s {
         /*
          * Constant generic information
@@ -146,7 +158,13 @@ typedef struct mdp_superblock_s {
         __u32 cp_events_hi;     /* 10 high-order of checkpoint update count   */
 #endif
         __u32 recovery_cp;      /* 11 recovery checkpoint sector count        */
-        __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 12];
+        /* There are only valid for minor_version > 90 */
+        __u64 reshape_position; /* 12,13 next address in array-space for reshape */
+        __u32 new_level;        /* 14 new level we are reshaping to           */
+        __u32 delta_disks;      /* 15 change in number of raid_disks          */
+        __u32 new_layout;       /* 16 new layout                              */
+        __u32 new_chunk;        /* 17 new chunk size (bytes)                  */
+        __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 18];
 
         /*
          * Personality information
@@ -207,7 +225,14 @@ struct mdp_superblock_1 {
                                  * NOTE: signed, so bitmap can be before superblock
                                  * only meaningful of feature_map[0] is set.
                                  */
-        __u8    pad1[128-100];  /* set to 0 when written */
+
+        /* These are only valid with feature bit '4' */
+        __u64   reshape_position;       /* next address in array-space for reshape */
+        __u32   new_level;      /* new level we are reshaping to                */
+        __u32   delta_disks;    /* change in number of raid_disks               */
+        __u32   new_layout;     /* new layout                                   */
+        __u32   new_chunk;      /* new chunk size (bytes)                       */
+        __u8    pad1[128-124];  /* set to 0 when written */
 
         /* constant this-device information - 64 bytes */
         __u64   data_offset;    /* sector start of data, often 0 */
@@ -240,8 +265,9 @@ struct mdp_superblock_1 {
 
 /* feature_map bits */
 #define MD_FEATURE_BITMAP_OFFSET        1
+#define MD_FEATURE_RESHAPE_ACTIVE       4
 
-#define MD_FEATURE_ALL                  1
+#define MD_FEATURE_ALL                  5
 
 #endif 
 
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index 55c738d50508..abcdf0d0658a 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -224,6 +224,7 @@ struct raid5_private_data {
         struct list_head        bitmap_list; /* stripes delaying awaiting bitmap update */
         atomic_t                preread_active_stripes; /* stripes with scheduled io */
 
+        atomic_t                reshape_stripes; /* stripes with pending writes for reshape */
         /* unfortunately we need two cache names as we temporarily have
          * two caches.
          */