Merge branch 'master'

4 files changed, 72 insertions, 9 deletions

diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index b6e0bcad84e..66b44e5e0d6 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -92,7 +92,10 @@ extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 extern void md_super_wait(mddev_t *mddev);
 extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
 			struct page *page, int rw);
+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(); }
 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 617b9506c76..e2df61f5b09 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 */
@@ -143,6 +151,10 @@ struct mddev_s
 	sector_t			resync_mismatches; /* count of sectors where
 							    * parity/replica mismatch found
 							    */
+
+	/* allow user-space to request suspension of IO to regions of the array */
+	sector_t			suspend_lo;
+	sector_t			suspend_hi;
 	/* if zero, use the system-wide default */
 	int				sync_speed_min;
 	int				sync_speed_max;
@@ -157,6 +169,9 @@ struct mddev_s
 	 * DONE:     thread is done and is waiting to be reaped
 	 * REQUEST:  user-space has requested a sync (used with SYNC)
 	 * CHECK:    user-space request for for check-only, no repair
+	 * RESHAPE:  A reshape is happening
+	 *
+	 * If neither SYNC or RESHAPE are set, then it is a recovery.
 	 */
 #define	MD_RECOVERY_RUNNING	0
 #define	MD_RECOVERY_SYNC	1
@@ -166,10 +181,11 @@ struct mddev_s
 #define	MD_RECOVERY_NEEDED	5
 #define	MD_RECOVERY_REQUESTED	6
 #define	MD_RECOVERY_CHECK	7
+#define MD_RECOVERY_RESHAPE	8
 	unsigned long			recovery;
 
 	int				in_sync;	/* know to not need resync */
-	struct semaphore		reconfig_sem;
+	struct mutex			reconfig_mutex;
 	atomic_t			active;
 
 	int				changed;	/* true if we might need to reread partition info */
@@ -249,7 +265,8 @@ struct mdk_personality
 	int (*spare_active) (mddev_t *mddev);
 	sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
 	int (*resize) (mddev_t *mddev, sector_t sectors);
-	int (*reshape) (mddev_t *mddev, int raid_disks);
+	int (*check_reshape) (mddev_t *mddev);
+	int (*start_reshape) (mddev_t *mddev);
 	int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
 	/* quiesce moves between quiescence states
 	 * 0 - fully active
diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h
index c100fa5d4bf..774e1acfb8c 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 394da8207b3..914af667044 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -135,6 +135,7 @@ struct stripe_head {
 	atomic_t		count;			/* nr of active thread/requests */
 	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
+	int			disks;			/* disks in stripe */
 	struct r5dev {
 		struct bio	req;
 		struct bio_vec	vec;
@@ -156,6 +157,7 @@ struct stripe_head {
 #define	R5_ReadError	8	/* seen a read error here recently */
 #define	R5_ReWrite	9	/* have tried to over-write the readerror */
 
+#define	R5_Expanded	10	/* This block now has post-expand data */
 /*
  * Write method
  */
@@ -174,7 +176,9 @@ struct stripe_head {
 #define	STRIPE_DELAYED		6
 #define	STRIPE_DEGRADED		7
 #define	STRIPE_BIT_DELAY	8
-
+#define	STRIPE_EXPANDING	9
+#define	STRIPE_EXPAND_SOURCE	10
+#define	STRIPE_EXPAND_READY	11
 /*
  * Plugging:
  *
@@ -211,12 +215,24 @@ struct raid5_private_data {
 	int			raid_disks, working_disks, failed_disks;
 	int			max_nr_stripes;
 
+	/* used during an expand */
+	sector_t		expand_progress;	/* MaxSector when no expand happening */
+	sector_t		expand_lo; /* from here up to expand_progress it out-of-bounds
+					    * as we haven't flushed the metadata yet
+					    */
+	int			previous_raid_disks;
+
 	struct list_head	handle_list; /* stripes needing handling */
 	struct list_head	delayed_list; /* stripes that have plugged requests */
 	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */
 	atomic_t		preread_active_stripes; /* stripes with scheduled io */
 
-	char			cache_name[20];
+	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
+	/* unfortunately we need two cache names as we temporarily have
+	 * two caches.
+	 */
+	int			active_name;
+	char			cache_name[2][20];
 	kmem_cache_t		*slab_cache; /* for allocating stripes */
 
 	int			seq_flush, seq_write;
@@ -238,9 +254,10 @@ struct raid5_private_data {
 	wait_queue_head_t	wait_for_overlap;
 	int			inactive_blocked;	/* release of inactive stripes blocked,
 							 * waiting for 25% to be free
-							 */        
+							 */
+	int			pool_size; /* number of disks in stripeheads in pool */
 	spinlock_t		device_lock;
-	struct disk_info	disks[0];
+	struct disk_info	*disks;
 };
 
 typedef struct raid5_private_data raid5_conf_t;