Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (52 commits)
  md: Protect access to mddev->disks list using RCU
  md: only count actual openers as access which prevent a 'stop'
  md: linear: Make array_size sector-based and rename it to array_sectors.
  md: Make mddev->array_size sector-based.
  md: Make super_type->rdev_size_change() take sector-based sizes.
  md: Fix check for overlapping devices.
  md: Tidy up rdev_size_store a bit:
  md: Remove some unused macros.
  md: Turn rdev->sb_offset into a sector-based quantity.
  md: Make calc_dev_sboffset() return a sector count.
  md: Replace calc_dev_size() by calc_num_sectors().
  md: Make update_size() take the number of sectors.
  md: Better control of when do_md_stop is allowed to stop the array.
  md: get_disk_info(): Don't convert between signed and unsigned and back.
  md: Simplify restart_array().
  md: alloc_disk_sb(): Return proper error value.
  md: Simplify sb_equal().
  md: Simplify uuid_equal().
  md: sb_equal(): Fix misleading printk.
  md: Fix a typo in the comment to cmd_match().
  ...

include/linux/raid/bitmap.h

@@ -221,6 +221,7 @@ struct bitmap {
 	unsigned long syncchunk;
 
 	__u64	events_cleared;
+	int need_sync;
 
 	/* bitmap spinlock */
 	spinlock_t lock;

include/linux/raid/linear.h

@@ -16,7 +16,7 @@ struct linear_private_data
 	struct linear_private_data *prev;	/* earlier version */
 	dev_info_t		**hash_table;
 	sector_t		hash_spacing;
-	sector_t		array_size;
+	sector_t		array_sectors;
 	int			preshift; /* shift before dividing by hash_spacing */
 	dev_info_t		disks[0];
 };

include/linux/raid/md.h

@@ -95,7 +95,7 @@ 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_allow_write(mddev_t *mddev);
+extern int md_allow_write(mddev_t *mddev);
 extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 
 #endif /* CONFIG_MD */

include/linux/raid/md_k.h

@@ -59,7 +59,7 @@ struct mdk_rdev_s
 	int		sb_loaded;
 	__u64		sb_events;
 	sector_t	data_offset;	/* start of data in array */
-	sector_t	sb_offset;
+	sector_t 	sb_start;	/* offset of the super block (in 512byte sectors) */
 	int		sb_size;	/* bytes in the superblock */
 	int		preferred_minor;	/* autorun support */
 
@@ -87,6 +87,9 @@ struct mdk_rdev_s
 #define Blocked		8		/* An error occured on an externally
 					 * managed array, don't allow writes
 					 * until it is cleared */
+#define StateChanged	9		/* Faulty or Blocked has changed during
+					 * interrupt, so it needs to be
+					 * notified by the thread */
 	wait_queue_head_t blocked_wait;
 
 	int desc_nr;			/* descriptor index in the superblock */
@@ -147,7 +150,7 @@ struct mddev_s
 	int				raid_disks;
 	int				max_disks;
 	sector_t			size; /* used size of component devices */
-	sector_t			array_size; /* exported array size */
+	sector_t			array_sectors; /* exported array size */
 	__u64				events;
 
 	char				uuid[16];
@@ -188,6 +191,7 @@ struct mddev_s
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started
 	 * SYNC:     actually doing a resync, not a recovery
+	 * RECOVER:  doing recovery, or need to try it.
 	 * INTR:     resync needs to be aborted for some reason
 	 * DONE:     thread is done and is waiting to be reaped
 	 * REQUEST:  user-space has requested a sync (used with SYNC)
@@ -198,6 +202,7 @@ struct mddev_s
 	 */
 #define	MD_RECOVERY_RUNNING	0
 #define	MD_RECOVERY_SYNC	1
+#define	MD_RECOVERY_RECOVER	2
 #define	MD_RECOVERY_INTR	3
 #define	MD_RECOVERY_DONE	4
 #define	MD_RECOVERY_NEEDED	5
@@ -210,7 +215,8 @@ struct mddev_s
 
 	int				in_sync;	/* know to not need resync */
 	struct mutex			reconfig_mutex;
-	atomic_t			active;
+	atomic_t			active;		/* general refcount */
+	atomic_t			openers;	/* number of active opens */
 
 	int				changed;	/* true if we might need to reread partition info */
 	int				degraded;	/* whether md should consider
@@ -227,6 +233,8 @@ struct mddev_s
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
 	sector_t			recovery_cp;
+	sector_t			resync_min;	/* user requested sync
+							 * starts here */
 	sector_t			resync_max;	/* resync should pause
 							 * when it gets here */
 
@@ -331,6 +339,9 @@ static inline char * mdname (mddev_t * mddev)
 #define rdev_for_each(rdev, tmp, mddev)				\
 	rdev_for_each_list(rdev, tmp, (mddev)->disks)
 
+#define rdev_for_each_rcu(rdev, mddev)				\
+	list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
+
 typedef struct mdk_thread_s {
 	void			(*run) (mddev_t *mddev);
 	mddev_t			*mddev;

include/linux/raid/md_p.h

@@ -43,14 +43,11 @@
  */
 #define MD_RESERVED_BYTES		(64 * 1024)
 #define MD_RESERVED_SECTORS		(MD_RESERVED_BYTES / 512)
-#define MD_RESERVED_BLOCKS		(MD_RESERVED_BYTES / BLOCK_SIZE)
 
 #define MD_NEW_SIZE_SECTORS(x)		((x & ~(MD_RESERVED_SECTORS - 1)) - MD_RESERVED_SECTORS)
-#define MD_NEW_SIZE_BLOCKS(x)		((x & ~(MD_RESERVED_BLOCKS - 1)) - MD_RESERVED_BLOCKS)
 
 #define MD_SB_BYTES			4096
 #define MD_SB_WORDS			(MD_SB_BYTES / 4)
-#define MD_SB_BLOCKS			(MD_SB_BYTES / BLOCK_SIZE)
 #define MD_SB_SECTORS			(MD_SB_BYTES / 512)
 
 /*

include/linux/raid/raid5.h

@@ -158,6 +158,43 @@
  *    the compute block completes.
  */
 
+/*
+ * Operations state - intermediate states that are visible outside of sh->lock
+ * In general _idle indicates nothing is running, _run indicates a data
+ * processing operation is active, and _result means the data processing result
+ * is stable and can be acted upon.  For simple operations like biofill and
+ * compute that only have an _idle and _run state they are indicated with
+ * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
+ */
+/**
+ * enum check_states - handles syncing / repairing a stripe
+ * @check_state_idle - check operations are quiesced
+ * @check_state_run - check operation is running
+ * @check_state_result - set outside lock when check result is valid
+ * @check_state_compute_run - check failed and we are repairing
+ * @check_state_compute_result - set outside lock when compute result is valid
+ */
+enum check_states {
+	check_state_idle = 0,
+	check_state_run, /* parity check */
+	check_state_check_result,
+	check_state_compute_run, /* parity repair */
+	check_state_compute_result,
+};
+
+/**
+ * enum reconstruct_states - handles writing or expanding a stripe
+ */
+enum reconstruct_states {
+	reconstruct_state_idle = 0,
+	reconstruct_state_prexor_drain_run,	/* prexor-write */
+	reconstruct_state_drain_run,		/* write */
+	reconstruct_state_run,			/* expand */
+	reconstruct_state_prexor_drain_result,
+	reconstruct_state_drain_result,
+	reconstruct_state_result,
+};
+
 struct stripe_head {
 	struct hlist_node	hash;
 	struct list_head	lru;			/* inactive_list or handle_list */
@@ -169,19 +206,13 @@ struct stripe_head {
 	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
 	int			disks;			/* disks in stripe */
+	enum check_states	check_state;
+	enum reconstruct_states reconstruct_state;
 	/* stripe_operations
-	 * @pending - pending ops flags (set for request->issue->complete)
-	 * @ack - submitted ops flags (set for issue->complete)
-	 * @complete - completed ops flags (set for complete)
 	 * @target - STRIPE_OP_COMPUTE_BLK target
-	 * @count - raid5_runs_ops is set to run when this is non-zero
 	 */
 	struct stripe_operations {
-		unsigned long	   pending;
-		unsigned long	   ack;
-		unsigned long	   complete;
 		int		   target;
-		int		   count;
 		u32		   zero_sum_result;
 	} ops;
 	struct r5dev {
@@ -202,6 +233,7 @@ struct stripe_head_state {
 	int locked, uptodate, to_read, to_write, failed, written;
 	int to_fill, compute, req_compute, non_overwrite;
 	int failed_num;
+	unsigned long ops_request;
 };
 
 /* r6_state - extra state data only relevant to r6 */
@@ -228,9 +260,7 @@ struct r6_state {
 #define	R5_Wantfill	12 /* dev->toread contains a bio that needs
 				    * filling
 				    */
-#define	R5_Wantprexor	13 /* distinguish blocks ready for rmw from
-				    * other "towrites"
-				    */
+#define R5_Wantdrain	13 /* dev->towrite needs to be drained */
 /*
  * Write method
  */
@@ -254,8 +284,10 @@ struct r6_state {
 #define	STRIPE_EXPAND_READY	11
 #define	STRIPE_IO_STARTED	12 /* do not count towards 'bypass_count' */
 #define	STRIPE_FULL_WRITE	13 /* all blocks are set to be overwritten */
+#define	STRIPE_BIOFILL_RUN	14
+#define	STRIPE_COMPUTE_RUN	15
 /*
- * Operations flags (in issue order)
+ * Operation request flags
  */
 #define STRIPE_OP_BIOFILL	0
 #define STRIPE_OP_COMPUTE_BLK	1
@@ -263,14 +295,6 @@ struct r6_state {
 #define STRIPE_OP_BIODRAIN	3
 #define STRIPE_OP_POSTXOR	4
 #define STRIPE_OP_CHECK	5
-#define STRIPE_OP_IO		6
-
-/* modifiers to the base operations
- * STRIPE_OP_MOD_REPAIR_PD - compute the parity block and write it back
- * STRIPE_OP_MOD_DMA_CHECK - parity is not corrupted by the check
- */
-#define STRIPE_OP_MOD_REPAIR_PD 7
-#define STRIPE_OP_MOD_DMA_CHECK 8
 
 /*
  * Plugging: