md: add explicit method to signal the end of a reshape.

Currently raid5 (the only module that supports restriping)
notices that the reshape has finished be sync_request being
given a large value, and handles any cleanup them.

This patch changes it so md_check_recovery calls into an
explicit finish_reshape method as well.

The clean-up from sync_request can do things that need to be
done promptly, typically things local to the raid5_conf_t
structure.

The "finish_reshape" method is called under the mddev_lock
so it can do things involving reconfiguring the device.

This allows us to get rid of md_set_array_sectors_locked, which
would have caused a deadlock if you tried to stop and array
while a reshape was happening.

Signed-off-by: NeilBrown <neilb@suse.de>

3 files changed, 34 insertions, 29 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 923d125..c509313 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5073,14 +5073,6 @@ void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors)
 }
 EXPORT_SYMBOL(md_set_array_sectors);
 
-void md_set_array_sectors_lock(mddev_t *mddev, sector_t array_sectors)
-{
-	mddev_lock(mddev);
-	md_set_array_sectors(mddev, array_sectors);
-	mddev_unlock(mddev);
-}
-EXPORT_SYMBOL(md_set_array_sectors_lock);
-
 static int update_size(mddev_t *mddev, sector_t num_sectors)
 {
 	mdk_rdev_t *rdev;
@@ -6641,6 +6633,9 @@ void md_check_recovery(mddev_t *mddev)
 					sysfs_notify(&mddev->kobj, NULL,
 						     "degraded");
 			}
+			if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+			    mddev->pers->finish_reshape)
+				mddev->pers->finish_reshape(mddev);
 			md_update_sb(mddev, 1);
 
 			/* if array is no-longer degraded, then any saved_raid_disk
diff --git a/drivers/md/md.h b/drivers/md/md.h
index d13e34f..e9b7f54 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -317,6 +317,7 @@ struct mdk_personality
 	sector_t (*size) (mddev_t *mddev, sector_t sectors, int raid_disks);
 	int (*check_reshape) (mddev_t *mddev);
 	int (*start_reshape) (mddev_t *mddev);
+	void (*finish_reshape) (mddev_t *mddev);
 	int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
 	/* quiesce moves between quiescence states
 	 * 0 - fully active
@@ -433,4 +434,3 @@ extern void md_new_event(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);
 extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors);
-extern void md_set_array_sectors_lock(mddev_t *mddev, sector_t array_sectors);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5694eb8..a0f22dd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3850,6 +3850,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	if (sector_nr >= max_sector) {
 		/* just being told to finish up .. nothing much to do */
 		unplug_slaves(mddev);
+
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
 			end_reshape(conf);
 			return 0;
@@ -4836,43 +4837,49 @@ static int raid5_start_reshape(mddev_t *mddev)
 
 static void end_reshape(raid5_conf_t *conf)
 {
-	struct block_device *bdev;
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		mddev_t *mddev = conf->mddev;
-
-		md_set_array_sectors_lock(mddev, raid5_size(mddev, 0,
-						       conf->raid_disks));
-		set_capacity(mddev->gendisk, mddev->array_sectors);
-		mddev->changed = 1;
-		conf->previous_raid_disks = conf->raid_disks;
 
-		bdev = bdget_disk(conf->mddev->gendisk, 0);
-		if (bdev) {
-			mutex_lock(&bdev->bd_inode->i_mutex);
-			i_size_write(bdev->bd_inode,
-				     (loff_t)conf->mddev->array_sectors << 9);
-			mutex_unlock(&bdev->bd_inode->i_mutex);
-			bdput(bdev);
-		}
 		spin_lock_irq(&conf->device_lock);
+		conf->previous_raid_disks = conf->raid_disks;
 		conf->expand_progress = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
-		conf->mddev->reshape_position = MaxSector;
 
 		/* read-ahead size must cover two whole stripes, which is
 		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
 		 */
 		{
-			int data_disks = conf->previous_raid_disks - conf->max_degraded;
-			int stripe = data_disks *
-				(conf->mddev->chunk_size / PAGE_SIZE);
+			int data_disks = conf->raid_disks - conf->max_degraded;
+			int stripe = data_disks * (conf->chunk_size
+						   / PAGE_SIZE);
 			if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 				conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 		}
 	}
 }
 
+static void raid5_finish_reshape(mddev_t *mddev)
+{
+	struct block_device *bdev;
+
+	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+
+		md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+		set_capacity(mddev->gendisk, mddev->array_sectors);
+		mddev->changed = 1;
+		mddev->reshape_position = MaxSector;
+
+		bdev = bdget_disk(mddev->gendisk, 0);
+		if (bdev) {
+			mutex_lock(&bdev->bd_inode->i_mutex);
+			i_size_write(bdev->bd_inode,
+				     (loff_t)mddev->array_sectors << 9);
+			mutex_unlock(&bdev->bd_inode->i_mutex);
+			bdput(bdev);
+		}
+	}
+}
+
 static void raid5_quiesce(mddev_t *mddev, int state)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
@@ -5098,6 +5105,7 @@ static struct mdk_personality raid6_personality =
 #ifdef CONFIG_MD_RAID5_RESHAPE
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
+	.finish_reshape = raid5_finish_reshape,
 #endif
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
@@ -5121,6 +5129,7 @@ static struct mdk_personality raid5_personality =
 #ifdef CONFIG_MD_RAID5_RESHAPE
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
+	.finish_reshape = raid5_finish_reshape,
 #endif
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
@@ -5146,6 +5155,7 @@ static struct mdk_personality raid4_personality =
 #ifdef CONFIG_MD_RAID5_RESHAPE
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
+	.finish_reshape = raid5_finish_reshape,
 #endif
 	.quiesce	= raid5_quiesce,
 };