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

* 'for-linus' of git://neil.brown.name/md:
  md: Fix removal of extra drives when converting RAID6 to RAID5
  md: range check slot number when manually adding a spare.
  md/raid5: handle manually-added spares in start_reshape.
  md: fix sync_completed reporting for very large drives (>2TB)
  md: allow suspend_lo and suspend_hi to decrease as well as increase.
  md: Don't let implementation detail of curr_resync leak out through sysfs.
  md: separate meta and data devs
  md-new-param-to_sync_page_io
  md-new-param-to-calc_dev_sboffset
  md: Be more careful about clearing flags bit in ->recovery
  md: md_stop_writes requires mddev_lock.
  md/raid5: use sysfs_notify_dirent_safe to avoid NULL pointer
  md: Ensure no IO request to get md device before it is properly initialised.
  md: Fix single printks with multiple KERN_<level>s
  md: fix regression resulting in delays in clearing bits in a bitmap
  md: fix regression with re-adding devices to arrays with no metadata

drivers/md/bitmap.c

@@ -210,11 +210,11 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 
-		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);
+		target = offset + index * (PAGE_SIZE/512);
 
 		if (sync_page_io(rdev, target,
 				 roundup(size, bdev_logical_block_size(rdev->bdev)),
-				 page, READ)) {
+				 page, READ, true)) {
 			page->index = index;
 			attach_page_buffers(page, NULL); /* so that free_buffer will
 							  * quietly no-op */
@@ -264,14 +264,18 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
 	mdk_rdev_t *rdev = NULL;
+	struct block_device *bdev;
 	mddev_t *mddev = bitmap->mddev;
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
 		int size = PAGE_SIZE;
 		loff_t offset = mddev->bitmap_info.offset;
+
+		bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
+
 		if (page->index == bitmap->file_pages-1)
 			size = roundup(bitmap->last_page_size,
-				       bdev_logical_block_size(rdev->bdev));
+				       bdev_logical_block_size(bdev));
 		/* Just make sure we aren't corrupting data or
 		 * metadata
 		 */
@@ -1542,7 +1546,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 	wait_event(bitmap->mddev->recovery_wait,
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
-	bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
+	bitmap->mddev->curr_resync_completed = sector;
 	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
 	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
 	s = 0;

drivers/md/md.h

@@ -60,6 +60,12 @@ struct mdk_rdev_s
 	mddev_t *mddev;			/* RAID array if running */
 	int last_events;		/* IO event timestamp */
 
+	/*
+	 * If meta_bdev is non-NULL, it means that a separate device is
+	 * being used to store the metadata (superblock/bitmap) which
+	 * would otherwise be contained on the same device as the data (bdev).
+	 */
+	struct block_device *meta_bdev;
 	struct block_device *bdev;	/* block device handle */
 
 	struct page	*sb_page;
@@ -148,7 +154,8 @@ struct mddev_s
 						       * are happening, so run/
 						       * takeover/stop are not safe
 						       */
-
+	int				ready; /* See when safe to pass 
+						* IO requests down */
 	struct gendisk			*gendisk;
 
 	struct kobject			kobj;
@@ -497,8 +504,8 @@ extern void md_flush_request(mddev_t *mddev, struct bio *bio);
 extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 			   sector_t sector, int size, struct page *page);
 extern void md_super_wait(mddev_t *mddev);
-extern int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size,
-			struct page *page, int rw);
+extern int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, 
+			struct page *page, int rw, bool metadata_op);
 extern void md_do_sync(mddev_t *mddev);
 extern void md_new_event(mddev_t *mddev);
 extern int md_allow_write(mddev_t *mddev);

drivers/md/raid1.c

@@ -1027,8 +1027,9 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	} else
 		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n"
-	       KERN_ALERT "md/raid1:%s: Operation continuing on %d devices.\n",
+	printk(KERN_ALERT
+	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
+	       "md/raid1:%s: Operation continuing on %d devices.\n",
 	       mdname(mddev), bdevname(rdev->bdev, b),
 	       mdname(mddev), conf->raid_disks - mddev->degraded);
 }
@@ -1364,10 +1365,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 					 */
 					rdev = conf->mirrors[d].rdev;
 					if (sync_page_io(rdev,
-							 sect + rdev->data_offset,
+							 sect,
 							 s<<9,
 							 bio->bi_io_vec[idx].bv_page,
-							 READ)) {
+							 READ, false)) {
 						success = 1;
 						break;
 					}
@@ -1390,10 +1391,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 					rdev = conf->mirrors[d].rdev;
 					atomic_add(s, &rdev->corrected_errors);
 					if (sync_page_io(rdev,
-							 sect + rdev->data_offset,
+							 sect,
 							 s<<9,
 							 bio->bi_io_vec[idx].bv_page,
-							 WRITE) == 0)
+							 WRITE, false) == 0)
 						md_error(mddev, rdev);
 				}
 				d = start;
@@ -1405,10 +1406,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 						continue;
 					rdev = conf->mirrors[d].rdev;
 					if (sync_page_io(rdev,
-							 sect + rdev->data_offset,
+							 sect,
 							 s<<9,
 							 bio->bi_io_vec[idx].bv_page,
-							 READ) == 0)
+							 READ, false) == 0)
 						md_error(mddev, rdev);
 				}
 			} else {
@@ -1488,10 +1489,8 @@ static void fix_read_error(conf_t *conf, int read_disk,
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
-			    sync_page_io(rdev,
-					 sect + rdev->data_offset,
-					 s<<9,
-					 conf->tmppage, READ))
+			    sync_page_io(rdev, sect, s<<9,
+					 conf->tmppage, READ, false))
 				success = 1;
 			else {
 				d++;
@@ -1514,9 +1513,8 @@ static void fix_read_error(conf_t *conf, int read_disk,
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags)) {
-				if (sync_page_io(rdev,
-						 sect + rdev->data_offset,
-						 s<<9, conf->tmppage, WRITE)
+				if (sync_page_io(rdev, sect, s<<9,
+						 conf->tmppage, WRITE, false)
 				    == 0)
 					/* Well, this device is dead */
 					md_error(mddev, rdev);
@@ -1531,9 +1529,8 @@ static void fix_read_error(conf_t *conf, int read_disk,
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags)) {
-				if (sync_page_io(rdev,
-						 sect + rdev->data_offset,
-						 s<<9, conf->tmppage, READ)
+				if (sync_page_io(rdev, sect, s<<9,
+						 conf->tmppage, READ, false)
 				    == 0)
 					/* Well, this device is dead */
 					md_error(mddev, rdev);

drivers/md/raid10.c

@@ -1051,8 +1051,9 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "md/raid10:%s: Disk failure on %s, disabling device.\n"
-	       KERN_ALERT "md/raid10:%s: Operation continuing on %d devices.\n",
+	printk(KERN_ALERT
+	       "md/raid10:%s: Disk failure on %s, disabling device.\n"
+	       "md/raid10:%s: Operation continuing on %d devices.\n",
 	       mdname(mddev), bdevname(rdev->bdev, b),
 	       mdname(mddev), conf->raid_disks - mddev->degraded);
 }
@@ -1559,9 +1560,9 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 				rcu_read_unlock();
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
-						       sect + rdev->data_offset,
+						       sect,
 						       s<<9,
-						       conf->tmppage, READ);
+						       conf->tmppage, READ, false);
 				rdev_dec_pending(rdev, mddev);
 				rcu_read_lock();
 				if (success)
@@ -1598,8 +1599,8 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 				atomic_add(s, &rdev->corrected_errors);
 				if (sync_page_io(rdev,
 						 r10_bio->devs[sl].addr +
-						 sect + rdev->data_offset,
-						 s<<9, conf->tmppage, WRITE)
+						 sect,
+						 s<<9, conf->tmppage, WRITE, false)
 				    == 0) {
 					/* Well, this device is dead */
 					printk(KERN_NOTICE
@@ -1635,9 +1636,9 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 				rcu_read_unlock();
 				if (sync_page_io(rdev,
 						 r10_bio->devs[sl].addr +
-						 sect + rdev->data_offset,
+						 sect,
 						 s<<9, conf->tmppage,
-						 READ) == 0) {
+						 READ, false) == 0) {
 					/* Well, this device is dead */
 					printk(KERN_NOTICE
 					       "md/raid10:%s: unable to read back "

drivers/md/raid5.c

@@ -1721,7 +1721,6 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		set_bit(Faulty, &rdev->flags);
 		printk(KERN_ALERT
 		       "md/raid:%s: Disk failure on %s, disabling device.\n"
-		       KERN_ALERT
 		       "md/raid:%s: Operation continuing on %d devices.\n",
 		       mdname(mddev),
 		       bdevname(rdev->bdev, b),
@@ -4237,7 +4236,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 		wait_event(conf->wait_for_overlap,
 			   atomic_read(&conf->reshape_stripes)==0);
 		mddev->reshape_position = conf->reshape_progress;
-		mddev->curr_resync_completed = mddev->curr_resync;
+		mddev->curr_resync_completed = sector_nr;
 		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
@@ -4338,7 +4337,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 		wait_event(conf->wait_for_overlap,
 			   atomic_read(&conf->reshape_stripes) == 0);
 		mddev->reshape_position = conf->reshape_progress;
-		mddev->curr_resync_completed = mddev->curr_resync + reshape_sectors;
+		mddev->curr_resync_completed = sector_nr;
 		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
@@ -5339,7 +5338,7 @@ static int raid5_spare_active(mddev_t *mddev)
 		    && !test_bit(Faulty, &tmp->rdev->flags)
 		    && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
 			count++;
-			sysfs_notify_dirent(tmp->rdev->sysfs_state);
+			sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
 		}
 	}
 	spin_lock_irqsave(&conf->device_lock, flags);
@@ -5528,8 +5527,8 @@ static int raid5_start_reshape(mddev_t *mddev)
 		return -ENOSPC;
 
 	list_for_each_entry(rdev, &mddev->disks, same_set)
-		if (rdev->raid_disk < 0 &&
-		    !test_bit(Faulty, &rdev->flags))
+		if ((rdev->raid_disk < 0 || rdev->raid_disk >= conf->raid_disks)
+		     && !test_bit(Faulty, &rdev->flags))
 			spares++;
 
 	if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded)
@@ -5589,6 +5588,11 @@ static int raid5_start_reshape(mddev_t *mddev)
 					/* Failure here is OK */;
 			} else
 				break;
+		} else if (rdev->raid_disk >= conf->previous_raid_disks
+			   && !test_bit(Faulty, &rdev->flags)) {
+			/* This is a spare that was manually added */
+			set_bit(In_sync, &rdev->flags);
+			added_devices++;
 		}
 
 	/* When a reshape changes the number of devices, ->degraded