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().
  ...

Documentation/md.txt

@@ -236,6 +236,11 @@ All md devices contain:
      writing the word for the desired state, however some states
      cannot be explicitly set, and some transitions are not allowed.
 
+     Select/poll works on this file.  All changes except between
+     	active_idle and active (which can be frequent and are not
+	very interesting) are notified.  active->active_idle is
+	reported if the metadata is externally managed.
+
      clear
          No devices, no size, no level
          Writing is equivalent to STOP_ARRAY ioctl
@@ -292,6 +297,10 @@ Each directory contains:
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
+	      blocked  - device has failed, metadata is "external",
+	                 and the failure hasn't been acknowledged yet.
+			 Writes that would write to this device if
+			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
@@ -301,6 +310,12 @@ Each directory contains:
 	Writing "remove" removes the device from the array.
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
+	Writing "blocked" sets the "blocked" flag.
+	Writing "-blocked" clear the "blocked" flag and allows writes
+		to complete.
+
+	This file responds to select/poll. Any change to 'faulty'
+	or 'blocked' causes an event.
 
       errors
 	An approximate count of read errors that have been detected on
@@ -332,7 +347,7 @@ Each directory contains:
         for storage of data.  This will normally be the same as the
 	component_size.  This can be written while assembling an
         array.  If a value less than the current component_size is
-        written, component_size will be reduced to this value.
+        written, it will be rejected.
 
 
 An active md device will also contain and entry for each active device
@@ -381,6 +396,19 @@ also have
 	'check' and 'repair' will start the appropriate process
            providing the current state is 'idle'.
 
+      This file responds to select/poll.  Any important change in the value
+      triggers a poll event.  Sometimes the value will briefly be
+      "recover" if a recovery seems to be needed, but cannot be
+      achieved. In that case, the transition to "recover" isn't
+      notified, but the transition away is.
+
+   degraded
+      This contains a count of the number of devices by which the
+      arrays is degraded.  So an optimal array with show '0'.  A
+      single failed/missing drive will show '1', etc.
+      This file responds to select/poll, any increase or decrease
+      in the count of missing devices will trigger an event.
+
    mismatch_count
       When performing 'check' and 'repair', and possibly when
       performing 'resync', md will count the number of errors that are

drivers/md/bitmap.c

@@ -225,7 +225,7 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 
-		target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
+		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
 			page->index = index;
@@ -241,10 +241,10 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
 	mdk_rdev_t *rdev;
-	struct list_head *tmp;
 	mddev_t *mddev = bitmap->mddev;
 
-	rdev_for_each(rdev, tmp, mddev)
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev)
 		if (test_bit(In_sync, &rdev->flags)
 		    && !test_bit(Faulty, &rdev->flags)) {
 			int size = PAGE_SIZE;
@@ -260,32 +260,37 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 				    + (long)(page->index * (PAGE_SIZE/512))
 				    + size/512 > 0)
 					/* bitmap runs in to metadata */
-					return -EINVAL;
+					goto bad_alignment;
 				if (rdev->data_offset + mddev->size*2
-				    > rdev->sb_offset*2 + bitmap->offset)
+				    > rdev->sb_start + bitmap->offset)
 					/* data runs in to bitmap */
-					return -EINVAL;
-			} else if (rdev->sb_offset*2 < rdev->data_offset) {
+					goto bad_alignment;
+			} else if (rdev->sb_start < rdev->data_offset) {
 				/* METADATA BITMAP DATA */
-				if (rdev->sb_offset*2
+				if (rdev->sb_start
 				    + bitmap->offset
 				    + page->index*(PAGE_SIZE/512) + size/512
 				    > rdev->data_offset)
 					/* bitmap runs in to data */
-					return -EINVAL;
+					goto bad_alignment;
 			} else {
 				/* DATA METADATA BITMAP - no problems */
 			}
 			md_super_write(mddev, rdev,
-				       (rdev->sb_offset<<1) + bitmap->offset
+				       rdev->sb_start + bitmap->offset
 				       + page->index * (PAGE_SIZE/512),
 				       size,
 				       page);
 		}
+	rcu_read_unlock();
 
 	if (wait)
 		md_super_wait(mddev);
 	return 0;
+
+ bad_alignment:
+	rcu_read_unlock();
+	return -EINVAL;
 }
 
 static void bitmap_file_kick(struct bitmap *bitmap);
@@ -454,8 +459,11 @@ void bitmap_update_sb(struct bitmap *bitmap)
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
-	if (!bitmap->mddev->degraded)
-		sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	if (bitmap->mddev->events < bitmap->events_cleared) {
+		/* rocking back to read-only */
+		bitmap->events_cleared = bitmap->mddev->events;
+		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+	}
 	kunmap_atomic(sb, KM_USER0);
 	write_page(bitmap, bitmap->sb_page, 1);
 }
@@ -1085,9 +1093,19 @@ void bitmap_daemon_work(struct bitmap *bitmap)
 			} else
 				spin_unlock_irqrestore(&bitmap->lock, flags);
 			lastpage = page;
-/*
-			printk("bitmap clean at page %lu\n", j);
-*/
+
+			/* We are possibly going to clear some bits, so make
+			 * sure that events_cleared is up-to-date.
+			 */
+			if (bitmap->need_sync) {
+				bitmap_super_t *sb;
+				bitmap->need_sync = 0;
+				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+				sb->events_cleared =
+					cpu_to_le64(bitmap->events_cleared);
+				kunmap_atomic(sb, KM_USER0);
+				write_page(bitmap, bitmap->sb_page, 1);
+			}
 			spin_lock_irqsave(&bitmap->lock, flags);
 			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
@@ -1257,6 +1275,12 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			return;
 		}
 
+		if (success &&
+		    bitmap->events_cleared < bitmap->mddev->events) {
+			bitmap->events_cleared = bitmap->mddev->events;
+			bitmap->need_sync = 1;
+		}
+
 		if (!success && ! (*bmc & NEEDED_MASK))
 			*bmc |= NEEDED_MASK;
 

drivers/md/faulty.c

@@ -297,7 +297,7 @@ static int run(mddev_t *mddev)
 	rdev_for_each(rdev, tmp, mddev)
 		conf->rdev = rdev;
 
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 	mddev->private = conf;
 
 	reconfig(mddev, mddev->layout, -1);

drivers/md/linear.c

@@ -122,13 +122,13 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		return NULL;
 
 	cnt = 0;
-	conf->array_size = 0;
+	conf->array_sectors = 0;
 
 	rdev_for_each(rdev, tmp, mddev) {
 		int j = rdev->raid_disk;
 		dev_info_t *disk = conf->disks + j;
 
-		if (j < 0 || j > raid_disks || disk->rdev) {
+		if (j < 0 || j >= raid_disks || disk->rdev) {
 			printk("linear: disk numbering problem. Aborting!\n");
 			goto out;
 		}
@@ -146,7 +146,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->size = rdev->size;
-		conf->array_size += rdev->size;
+		conf->array_sectors += rdev->size * 2;
 
 		cnt++;
 	}
@@ -155,7 +155,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		goto out;
 	}
 
-	min_spacing = conf->array_size;
+	min_spacing = conf->array_sectors / 2;
 	sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
 
 	/* min_spacing is the minimum spacing that will fit the hash
@@ -164,7 +164,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 	 * that is larger than min_spacing as use the size of that as
 	 * the actual spacing
 	 */
-	conf->hash_spacing = conf->array_size;
+	conf->hash_spacing = conf->array_sectors / 2;
 	for (i=0; i < cnt-1 ; i++) {
 		sector_t sz = 0;
 		int j;
@@ -194,7 +194,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		unsigned round;
 		unsigned long base;
 
-		sz = conf->array_size >> conf->preshift;
+		sz = conf->array_sectors >> (conf->preshift + 1);
 		sz += 1; /* force round-up */
 		base = conf->hash_spacing >> conf->preshift;
 		round = sector_div(sz, base);
@@ -221,7 +221,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 	curr_offset = 0;
 	i = 0;
 	for (curr_offset = 0;
-	     curr_offset < conf->array_size;
+	     curr_offset < conf->array_sectors / 2;
 	     curr_offset += conf->hash_spacing) {
 
 		while (i < raid_disks-1 &&
@@ -258,7 +258,7 @@ static int linear_run (mddev_t *mddev)
 	if (!conf)
 		return 1;
 	mddev->private = conf;
-	mddev->array_size = conf->array_size;
+	mddev->array_sectors = conf->array_sectors;
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->unplug_fn = linear_unplug;
@@ -292,8 +292,8 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
 	newconf->prev = mddev_to_conf(mddev);
 	mddev->private = newconf;
 	mddev->raid_disks++;
-	mddev->array_size = newconf->array_size;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = newconf->array_sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	return 0;
 }
 

drivers/md/multipath.c

@@ -281,13 +281,18 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	multipath_conf_t *conf = mddev->private;
 	struct request_queue *q;
-	int found = 0;
+	int err = -EEXIST;
 	int path;
 	struct multipath_info *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	print_multipath_conf(conf);
 
-	for (path=0; path<mddev->raid_disks; path++) 
+	for (path = first; path <= last; path++)
 		if ((p=conf->multipaths+path)->rdev == NULL) {
 			q = rdev->bdev->bd_disk->queue;
 			blk_queue_stack_limits(mddev->queue, q);
@@ -307,11 +312,13 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			rdev->raid_disk = path;
 			set_bit(In_sync, &rdev->flags);
 			rcu_assign_pointer(p->rdev, rdev);
-			found = 1;
+			err = 0;
+			break;
 		}
 
 	print_multipath_conf(conf);
-	return found;
+
+	return err;
 }
 
 static int multipath_remove_disk(mddev_t *mddev, int number)
@@ -497,7 +504,7 @@ static int multipath_run (mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 
 	mddev->queue->unplug_fn = multipath_unplug;
 	mddev->queue->backing_dev_info.congested_fn = multipath_congested;

drivers/md/raid0.c

@@ -295,16 +295,16 @@ static int raid0_run (mddev_t *mddev)
 		goto out_free_conf;
 
 	/* calculate array device size */
-	mddev->array_size = 0;
+	mddev->array_sectors = 0;
 	rdev_for_each(rdev, tmp, mddev)
-		mddev->array_size += rdev->size;
+		mddev->array_sectors += rdev->size * 2;
 
 	printk("raid0 : md_size is %llu blocks.\n", 
-		(unsigned long long)mddev->array_size);
+		(unsigned long long)mddev->array_sectors / 2);
 	printk("raid0 : conf->hash_spacing is %llu blocks.\n",
 		(unsigned long long)conf->hash_spacing);
 	{
-		sector_t s = mddev->array_size;
+		sector_t s = mddev->array_sectors / 2;
 		sector_t space = conf->hash_spacing;
 		int round;
 		conf->preshift = 0;

drivers/md/raid1.c

@@ -1100,11 +1100,16 @@ static int raid1_spare_active(mddev_t *mddev)
 static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror = 0;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
+
+	for (mirror = first; mirror <= last; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
@@ -1119,7 +1124,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
@@ -1130,7 +1135,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid1_remove_disk(mddev_t *mddev, int number)
@@ -2038,7 +2043,7 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 
 	mddev->queue->unplug_fn = raid1_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
@@ -2100,14 +2105,15 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	mddev->array_size = sectors>>1;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (mddev->array_size > mddev->size && mddev->recovery_cp == MaxSector) {
+	if (mddev->array_sectors / 2 > mddev->size &&
+	    mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->size << 1;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = mddev->array_size;
+	mddev->size = mddev->array_sectors / 2;
 	mddev->resync_max_sectors = sectors;
 	return 0;
 }
@@ -2131,7 +2137,7 @@ static int raid1_reshape(mddev_t *mddev)
 	conf_t *conf = mddev_to_conf(mddev);
 	int cnt, raid_disks;
 	unsigned long flags;
-	int d, d2;
+	int d, d2, err;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_size != mddev->new_chunk ||
@@ -2143,7 +2149,9 @@ static int raid1_reshape(mddev_t *mddev)
 		return -EINVAL;
 	}
 
-	md_allow_write(mddev);
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 

drivers/md/raid10.c

@@ -1114,24 +1114,30 @@ static int raid10_spare_active(mddev_t *mddev)
 static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
-		return 0;
+		return -EBUSY;
 	if (!enough(conf))
-		return 0;
+		return -EINVAL;
+
+	if (rdev->raid_disk)
+		first = last = rdev->raid_disk;
 
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
 	else
-		mirror = 0;
-	for ( ; mirror < mddev->raid_disks; mirror++)
+		mirror = first;
+	for ( ; mirror <= last ; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
@@ -1146,7 +1152,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != mirror)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
@@ -1154,7 +1160,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid10_remove_disk(mddev_t *mddev, int number)
@@ -2159,7 +2165,7 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = size << (conf->chunk_shift-1);
+	mddev->array_sectors = size << conf->chunk_shift;
 	mddev->resync_max_sectors = size << conf->chunk_shift;
 
 	mddev->queue->unplug_fn = raid10_unplug;

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: