Merge tag 'md-3.7' of git://neil.brown.name/md

Pull md updates from NeilBrown:
 - "discard" support, some dm-raid improvements and other assorted bits
   and pieces.

* tag 'md-3.7' of git://neil.brown.name/md: (29 commits)
  md: refine reporting of resync/reshape delays.
  md/raid5: be careful not to resize_stripes too big.
  md: make sure manual changes to recovery checkpoint are saved.
  md/raid10: use correct limit variable
  md: writing to sync_action should clear the read-auto state.
  Subject: [PATCH] md:change resync_mismatches to atomic64_t to avoid races
  md/raid5: make sure to_read and to_write never go negative.
  md: When RAID5 is dirty, force reconstruct-write instead of read-modify-write.
  md/raid5: protect debug message against NULL derefernce.
  md/raid5: add some missing locking in handle_failed_stripe.
  MD: raid5 avoid unnecessary zero page for trim
  MD: raid5 trim support
  md/bitmap:Don't use IS_ERR to judge alloc_page().
  md/raid1: Don't release reference to device while handling read error.
  raid: replace list_for_each_continue_rcu with new interface
  add further __init annotations to crypto/xor.c
  DM RAID: Fix for "sync" directive ineffectiveness
  DM RAID: Fix comparison of index and quantity for "rebuild" parameter
  DM RAID: Add rebuild capability for RAID10
  DM RAID: Move 'rebuild' checking code to its own function
  ...

1 files changed, 84 insertions, 11 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0138a727c1f3..906ccbd0f7dc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -911,7 +911,12 @@ static void flush_pending_writes(struct r10conf *conf)
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
 			bio->bi_next = NULL;
-			generic_make_request(bio);
+			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+				/* Just ignore it */
+				bio_endio(bio, 0);
+			else
+				generic_make_request(bio);
 			bio = next;
 		}
 	} else
@@ -1050,6 +1055,44 @@ static sector_t choose_data_offset(struct r10bio *r10_bio,
 		return rdev->new_data_offset;
 }
 
+struct raid10_plug_cb {
+	struct blk_plug_cb	cb;
+	struct bio_list		pending;
+	int			pending_cnt;
+};
+
+static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb,
+						   cb);
+	struct mddev *mddev = plug->cb.data;
+	struct r10conf *conf = mddev->private;
+	struct bio *bio;
+
+	if (from_schedule) {
+		spin_lock_irq(&conf->device_lock);
+		bio_list_merge(&conf->pending_bio_list, &plug->pending);
+		conf->pending_count += plug->pending_cnt;
+		spin_unlock_irq(&conf->device_lock);
+		md_wakeup_thread(mddev->thread);
+		kfree(plug);
+		return;
+	}
+
+	/* we aren't scheduling, so we can do the write-out directly. */
+	bio = bio_list_get(&plug->pending);
+	bitmap_unplug(mddev->bitmap);
+	wake_up(&conf->wait_barrier);
+
+	while (bio) { /* submit pending writes */
+		struct bio *next = bio->bi_next;
+		bio->bi_next = NULL;
+		generic_make_request(bio);
+		bio = next;
+	}
+	kfree(plug);
+}
+
 static void make_request(struct mddev *mddev, struct bio * bio)
 {
 	struct r10conf *conf = mddev->private;
@@ -1061,8 +1104,12 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
+	const unsigned long do_discard = (bio->bi_rw
+					  & (REQ_DISCARD | REQ_SECURE));
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
+	struct blk_plug_cb *cb;
+	struct raid10_plug_cb *plug = NULL;
 	int sectors_handled;
 	int max_sectors;
 	int sectors;
@@ -1081,7 +1128,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 			 || conf->prev.near_copies < conf->prev.raid_disks))) {
 		struct bio_pair *bp;
 		/* Sanity check -- queue functions should prevent this happening */
-		if (bio->bi_vcnt != 1 ||
+		if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
 		    bio->bi_idx != 0)
 			goto bad_map;
 		/* This is a one page bio that upper layers
@@ -1410,15 +1457,26 @@ retry_write:
 						      conf->mirrors[d].rdev));
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua;
+		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
+
+		cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
+		if (cb)
+			plug = container_of(cb, struct raid10_plug_cb, cb);
+		else
+			plug = NULL;
 		spin_lock_irqsave(&conf->device_lock, flags);
-		bio_list_add(&conf->pending_bio_list, mbio);
-		conf->pending_count++;
+		if (plug) {
+			bio_list_add(&plug->pending, mbio);
+			plug->pending_cnt++;
+		} else {
+			bio_list_add(&conf->pending_bio_list, mbio);
+			conf->pending_count++;
+		}
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!mddev_check_plugged(mddev))
+		if (!plug)
 			md_wakeup_thread(mddev->thread);
 
 		if (!r10_bio->devs[i].repl_bio)
@@ -1439,7 +1497,7 @@ retry_write:
 					   conf->mirrors[d].replacement));
 		mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua;
+		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
@@ -1638,7 +1696,7 @@ static int raid10_spare_active(struct mddev *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);
@@ -1725,6 +1783,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(Unmerged, &rdev->flags);
 	}
 	md_integrity_add_rdev(rdev, mddev);
+	if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
 	print_conf(conf);
 	return err;
 }
@@ -1952,7 +2013,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 					break;
 			if (j == vcnt)
 				continue;
-			mddev->resync_mismatches += r10_bio->sectors;
+			atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
 			if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
 				/* Don't fix anything. */
 				continue;
@@ -2673,8 +2734,9 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
 	}
 }
 
-static void raid10d(struct mddev *mddev)
+static void raid10d(struct md_thread *thread)
 {
+	struct mddev *mddev = thread->mddev;
 	struct r10bio *r10_bio;
 	unsigned long flags;
 	struct r10conf *conf = mddev->private;
@@ -3158,7 +3220,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				else {
 					bad_sectors -= (sector - first_bad);
 					if (max_sync > bad_sectors)
-						max_sync = max_sync;
+						max_sync = bad_sectors;
 					continue;
 				}
 			}
@@ -3482,6 +3544,7 @@ static int run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	bool discard_supported = false;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -3498,6 +3561,8 @@ static int run(struct mddev *mddev)
 
 	chunk_size = mddev->chunk_sectors << 9;
 	if (mddev->queue) {
+		blk_queue_max_discard_sectors(mddev->queue,
+					      mddev->chunk_sectors);
 		blk_queue_io_min(mddev->queue, chunk_size);
 		if (conf->geo.raid_disks % conf->geo.near_copies)
 			blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
@@ -3543,8 +3608,16 @@ static int run(struct mddev *mddev)
 					  rdev->data_offset << 9);
 
 		disk->head_position = 0;
+
+		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+			discard_supported = true;
 	}
 
+	if (discard_supported)
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	else
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",