Merge tag 'md-3.4' of git://neil.brown.name/md

Pull md updates for 3.4 from Neil Brown:
 "Mostly tidying up code in preparation for some bigger changes next
  time.

  A few bug fixes tagged for -stable.

  Main functionality change is that some RAID10 arrays can now grow to
  use extra space that may have been made available on the individual
  devices."

Fixed up trivial conflicts with the k[un]map_atomic() cleanups in
drivers/md/bitmap.c.

* tag 'md-3.4' of git://neil.brown.name/md: (22 commits)
  md: Add judgement bb->unacked_exist in function md_ack_all_badblocks().
  md: fix clearing of the 'changed' flags for the bad blocks list.
  md/bitmap: discard CHUNK_BLOCK_SHIFT macro
  md/bitmap: remove unnecessary indirection when allocating.
  md/bitmap: remove some pointless locking.
  md/bitmap: change a 'goto' to a normal 'if' construct.
  md/bitmap: move printing of bitmap status to bitmap.c
  md/bitmap: remove some unused noise from bitmap.h
  md/raid10 - support resizing some RAID10 arrays.
  md/raid1: handle merge_bvec_fn in member devices.
  md/raid10: handle merge_bvec_fn in member devices.
  md: add proper merge_bvec handling to RAID0 and Linear.
  md: tidy up rdev_for_each usage.
  md/raid1,raid10: avoid deadlock during resync/recovery.
  md/bitmap: ensure to load bitmap when creating via sysfs.
  md: don't set md arrays to readonly on shutdown.
  md: allow re-add to failed arrays.
  md/raid5: use atomic_dec_return() instead of atomic_dec() and atomic_read().
  md: Use existed macros instead of numbers
  md/raid5: removed unused 'added_devices' variable.
  ...

1 files changed, 138 insertions, 49 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 58c44d6453a0..3540316886f2 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -586,25 +586,68 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
- *      If near_copies == raid_disk, there are no striping issues,
- *      but in that case, the function isn't called at all.
+ *	This requires checking for end-of-chunk if near_copies != raid_disks,
+ *	and for subordinate merge_bvec_fns if merge_check_needed.
  */
 static int raid10_mergeable_bvec(struct request_queue *q,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
 	struct mddev *mddev = q->queuedata;
+	struct r10conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bvm->bi_size >> 9;
 
-	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
-	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	else
-		return max;
+	if (conf->near_copies < conf->raid_disks) {
+		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
+					+ bio_sectors)) << 9;
+		if (max < 0)
+			/* bio_add cannot handle a negative return */
+			max = 0;
+		if (max <= biovec->bv_len && bio_sectors == 0)
+			return biovec->bv_len;
+	} else
+		max = biovec->bv_len;
+
+	if (mddev->merge_check_needed) {
+		struct r10bio r10_bio;
+		int s;
+		r10_bio.sector = sector;
+		raid10_find_phys(conf, &r10_bio);
+		rcu_read_lock();
+		for (s = 0; s < conf->copies; s++) {
+			int disk = r10_bio.devs[s].devnum;
+			struct md_rdev *rdev = rcu_dereference(
+				conf->mirrors[disk].rdev);
+			if (rdev && !test_bit(Faulty, &rdev->flags)) {
+				struct request_queue *q =
+					bdev_get_queue(rdev->bdev);
+				if (q->merge_bvec_fn) {
+					bvm->bi_sector = r10_bio.devs[s].addr
+						+ rdev->data_offset;
+					bvm->bi_bdev = rdev->bdev;
+					max = min(max, q->merge_bvec_fn(
+							  q, bvm, biovec));
+				}
+			}
+			rdev = rcu_dereference(conf->mirrors[disk].replacement);
+			if (rdev && !test_bit(Faulty, &rdev->flags)) {
+				struct request_queue *q =
+					bdev_get_queue(rdev->bdev);
+				if (q->merge_bvec_fn) {
+					bvm->bi_sector = r10_bio.devs[s].addr
+						+ rdev->data_offset;
+					bvm->bi_bdev = rdev->bdev;
+					max = min(max, q->merge_bvec_fn(
+							  q, bvm, biovec));
+				}
+			}
+		}
+		rcu_read_unlock();
+	}
+	return max;
 }
 
 /*
@@ -668,11 +711,12 @@ retry:
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
-		if (rdev == NULL)
-			continue;
-		if (test_bit(Faulty, &rdev->flags))
+		if (rdev == NULL ||
+		    test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
@@ -863,9 +907,22 @@ static void wait_barrier(struct r10conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	if (conf->barrier) {
 		conf->nr_waiting++;
-		wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
+		/* Wait for the barrier to drop.
+		 * However if there are already pending
+		 * requests (preventing the barrier from
+		 * rising completely), and the
+		 * pre-process bio queue isn't empty,
+		 * then don't wait, as we need to empty
+		 * that queue to get the nr_pending
+		 * count down.
+		 */
+		wait_event_lock_irq(conf->wait_barrier,
+				    !conf->barrier ||
+				    (conf->nr_pending &&
+				     current->bio_list &&
+				     !bio_list_empty(current->bio_list)),
 				    conf->resync_lock,
-				    );
+			);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;
@@ -1121,12 +1178,14 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rrdev && test_bit(Faulty, &rrdev->flags))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)
+			      || test_bit(Unmerged, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags)) {
 			set_bit(R10BIO_Degraded, &r10_bio->state);
 			continue;
 		}
@@ -1477,18 +1536,24 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int mirror;
 	int first = 0;
 	int last = conf->raid_disks - 1;
+	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
 		return -EBUSY;
-	if (!enough(conf, -1))
+	if (rdev->saved_raid_disk < 0 && !enough(conf, -1))
 		return -EINVAL;
 
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
+	if (q->merge_bvec_fn) {
+		set_bit(Unmerged, &rdev->flags);
+		mddev->merge_check_needed = 1;
+	}
+
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
@@ -1508,11 +1573,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			err = 0;
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
-			if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-				blk_queue_max_segments(mddev->queue, 1);
-				blk_queue_segment_boundary(mddev->queue,
-							   PAGE_CACHE_SIZE - 1);
-			}
 			conf->fullsync = 1;
 			rcu_assign_pointer(p->replacement, rdev);
 			break;
@@ -1520,17 +1580,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
-		/* as we don't honour merge_bvec_fn, we must
-		 * never risk violating it, so limit
-		 * ->max_segments to one lying with a single
-		 * page, as a one page request is never in
-		 * violation.
-		 */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
 
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
@@ -1541,7 +1590,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-
+	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
+		/* Some requests might not have seen this new
+		 * merge_bvec_fn.  We must wait for them to complete
+		 * before merging the device fully.
+		 * First we make sure any code which has tested
+		 * our function has submitted the request, then
+		 * we wait for all outstanding requests to complete.
+		 */
+		synchronize_sched();
+		raise_barrier(conf, 0);
+		lower_barrier(conf);
+		clear_bit(Unmerged, &rdev->flags);
+	}
 	md_integrity_add_rdev(rdev, mddev);
 	print_conf(conf);
 	return err;
@@ -1682,10 +1743,8 @@ static void end_sync_write(struct bio *bio, int error)
 	d = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 	if (repl)
 		rdev = conf->mirrors[d].replacement;
-	if (!rdev) {
-		smp_mb();
+	else
 		rdev = conf->mirrors[d].rdev;
-	}
 
 	if (!uptodate) {
 		if (repl)
@@ -2087,6 +2146,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
+			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
@@ -2140,6 +2200,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
+			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -3242,7 +3303,7 @@ static int run(struct mddev *mddev)
 		blk_queue_io_opt(mddev->queue, chunk_size *
 				 (conf->raid_disks / conf->near_copies));
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 
 		disk_idx = rdev->raid_disk;
 		if (disk_idx >= conf->raid_disks
@@ -3262,15 +3323,6 @@ static int run(struct mddev *mddev)
 
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit max_segments to 1 lying
-		 * within a single page.
-		 */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
 
 		disk->head_position = 0;
 	}
@@ -3334,8 +3386,7 @@ static int run(struct mddev *mddev)
 			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
 	}
 
-	if (conf->near_copies < conf->raid_disks)
-		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
+	blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
@@ -3385,6 +3436,43 @@ static void raid10_quiesce(struct mddev *mddev, int state)
 	}
 }
 
+static int raid10_resize(struct mddev *mddev, sector_t sectors)
+{
+	/* Resize of 'far' arrays is not supported.
+	 * For 'near' and 'offset' arrays we can set the
+	 * number of sectors used to be an appropriate multiple
+	 * of the chunk size.
+	 * For 'offset', this is far_copies*chunksize.
+	 * For 'near' the multiplier is the LCM of
+	 * near_copies and raid_disks.
+	 * So if far_copies > 1 && !far_offset, fail.
+	 * Else find LCM(raid_disks, near_copy)*far_copies and
+	 * multiply by chunk_size.  Then round to this number.
+	 * This is mostly done by raid10_size()
+	 */
+	struct r10conf *conf = mddev->private;
+	sector_t oldsize, size;
+
+	if (conf->far_copies > 1 && !conf->far_offset)
+		return -EINVAL;
+
+	oldsize = raid10_size(mddev, 0, 0);
+	size = raid10_size(mddev, sectors, 0);
+	md_set_array_sectors(mddev, size);
+	if (mddev->array_sectors > size)
+		return -EINVAL;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
+	revalidate_disk(mddev->gendisk);
+	if (sectors > mddev->dev_sectors &&
+	    mddev->recovery_cp > oldsize) {
+		mddev->recovery_cp = oldsize;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	}
+	mddev->dev_sectors = sectors;
+	mddev->resync_max_sectors = size;
+	return 0;
+}
+
 static void *raid10_takeover_raid0(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
@@ -3408,7 +3496,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
 
 	conf = setup_conf(mddev);
 	if (!IS_ERR(conf)) {
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			if (rdev->raid_disk >= 0)
 				rdev->new_raid_disk = rdev->raid_disk * 2;
 		conf->barrier = 1;
@@ -3454,6 +3542,7 @@ static struct md_personality raid10_personality =
 	.sync_request	= sync_request,
 	.quiesce	= raid10_quiesce,
 	.size		= raid10_size,
+	.resize		= raid10_resize,
 	.takeover	= raid10_takeover,
 };