Merge tag 'md-3.6' of git://neil.brown.name/md

Pull additional md update from NeilBrown:
 "This contains a few patches that depend on plugging changes in the
  block layer so needed to wait for those.

  It also contains a Kconfig fix for the new RAID10 support in dm-raid."

* tag 'md-3.6' of git://neil.brown.name/md:
  md/dm-raid: DM_RAID should select MD_RAID10
  md/raid1: submit IO from originating thread instead of md thread.
  raid5: raid5d handle stripe in batch way
  raid5: make_request use batch stripe release

5 files changed, 150 insertions, 22 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 1eee45b69b71..d949b781f6f8 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -268,13 +268,14 @@ config DM_MIRROR
          needed for live data migration tools such as 'pvmove'.
 
 config DM_RAID
-       tristate "RAID 1/4/5/6 target"
+       tristate "RAID 1/4/5/6/10 target"
        depends on BLK_DEV_DM
        select MD_RAID1
+       select MD_RAID10
        select MD_RAID456
        select BLK_DEV_MD
        ---help---
-	 A dm target that supports RAID1, RAID4, RAID5 and RAID6 mappings
+	 A dm target that supports RAID1, RAID10, RAID4, RAID5 and RAID6 mappings
 
 	 A RAID-5 set of N drives with a capacity of C MB per drive provides
 	 the capacity of C * (N - 1) MB, and protects against a failure
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 15dbe03117e4..94e7f6ba2e11 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1305,7 +1305,7 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 			prepare_to_wait(&bitmap->overflow_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock_irq(&bitmap->counts.lock);
-			io_schedule();
+			schedule();
 			finish_wait(&bitmap->overflow_wait, &__wait);
 			continue;
 		}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 9f7f8bee8442..611b5f797618 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -944,6 +944,44 @@ do_sync_io:
 	pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
 }
 
+struct raid1_plug_cb {
+	struct blk_plug_cb	cb;
+	struct bio_list		pending;
+	int			pending_cnt;
+};
+
+static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb,
+						  cb);
+	struct mddev *mddev = plug->cb.data;
+	struct r1conf *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 r1conf *conf = mddev->private;
@@ -957,6 +995,8 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
 	struct md_rdev *blocked_rdev;
+	struct blk_plug_cb *cb;
+	struct raid1_plug_cb *plug = NULL;
 	int first_clone;
 	int sectors_handled;
 	int max_sectors;
@@ -1259,11 +1299,22 @@ read_again:
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
+
+		cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
+		if (cb)
+			plug = container_of(cb, struct raid1_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);
 	}
 	/* Mustn't call r1_bio_write_done before this next test,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 87a2d0bdedd1..adda94df5eb2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -484,7 +484,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 		} else {
 			if (atomic_read(&sh->count)) {
 				BUG_ON(!list_empty(&sh->lru)
-				    && !test_bit(STRIPE_EXPANDING, &sh->state));
+				    && !test_bit(STRIPE_EXPANDING, &sh->state)
+				    && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state));
 			} else {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
@@ -4010,6 +4011,62 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf)
 	return sh;
 }
 
+struct raid5_plug_cb {
+	struct blk_plug_cb	cb;
+	struct list_head	list;
+};
+
+static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
+{
+	struct raid5_plug_cb *cb = container_of(
+		blk_cb, struct raid5_plug_cb, cb);
+	struct stripe_head *sh;
+	struct mddev *mddev = cb->cb.data;
+	struct r5conf *conf = mddev->private;
+
+	if (cb->list.next && !list_empty(&cb->list)) {
+		spin_lock_irq(&conf->device_lock);
+		while (!list_empty(&cb->list)) {
+			sh = list_first_entry(&cb->list, struct stripe_head, lru);
+			list_del_init(&sh->lru);
+			/*
+			 * avoid race release_stripe_plug() sees
+			 * STRIPE_ON_UNPLUG_LIST clear but the stripe
+			 * is still in our list
+			 */
+			smp_mb__before_clear_bit();
+			clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
+			__release_stripe(conf, sh);
+		}
+		spin_unlock_irq(&conf->device_lock);
+	}
+	kfree(cb);
+}
+
+static void release_stripe_plug(struct mddev *mddev,
+				struct stripe_head *sh)
+{
+	struct blk_plug_cb *blk_cb = blk_check_plugged(
+		raid5_unplug, mddev,
+		sizeof(struct raid5_plug_cb));
+	struct raid5_plug_cb *cb;
+
+	if (!blk_cb) {
+		release_stripe(sh);
+		return;
+	}
+
+	cb = container_of(blk_cb, struct raid5_plug_cb, cb);
+
+	if (cb->list.next == NULL)
+		INIT_LIST_HEAD(&cb->list);
+
+	if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state))
+		list_add_tail(&sh->lru, &cb->list);
+	else
+		release_stripe(sh);
+}
+
 static void make_request(struct mddev *mddev, struct bio * bi)
 {
 	struct r5conf *conf = mddev->private;
@@ -4138,8 +4195,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 			if ((bi->bi_rw & REQ_NOIDLE) &&
 			    !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
-			mddev_check_plugged(mddev);
-			release_stripe(sh);
+			release_stripe_plug(mddev, sh);
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -4537,6 +4593,30 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	return handled;
 }
 
+#define MAX_STRIPE_BATCH 8
+static int handle_active_stripes(struct r5conf *conf)
+{
+	struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
+	int i, batch_size = 0;
+
+	while (batch_size < MAX_STRIPE_BATCH &&
+			(sh = __get_priority_stripe(conf)) != NULL)
+		batch[batch_size++] = sh;
+
+	if (batch_size == 0)
+		return batch_size;
+	spin_unlock_irq(&conf->device_lock);
+
+	for (i = 0; i < batch_size; i++)
+		handle_stripe(batch[i]);
+
+	cond_resched();
+
+	spin_lock_irq(&conf->device_lock);
+	for (i = 0; i < batch_size; i++)
+		__release_stripe(conf, batch[i]);
+	return batch_size;
+}
 
 /*
  * This is our raid5 kernel thread.
@@ -4547,7 +4627,6 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
  */
 static void raid5d(struct mddev *mddev)
 {
-	struct stripe_head *sh;
 	struct r5conf *conf = mddev->private;
 	int handled;
 	struct blk_plug plug;
@@ -4561,6 +4640,7 @@ static void raid5d(struct mddev *mddev)
 	spin_lock_irq(&conf->device_lock);
 	while (1) {
 		struct bio *bio;
+		int batch_size;
 
 		if (
 		    !list_empty(&conf->bitmap_list)) {
@@ -4584,21 +4664,16 @@ static void raid5d(struct mddev *mddev)
 			handled++;
 		}
 
-		sh = __get_priority_stripe(conf);
-
-		if (!sh)
+		batch_size = handle_active_stripes(conf);
+		if (!batch_size)
 			break;
-		spin_unlock_irq(&conf->device_lock);
-		
-		handled++;
-		handle_stripe(sh);
-		release_stripe(sh);
-		cond_resched();
+		handled += batch_size;
 
-		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+		if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) {
+			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
-
-		spin_lock_irq(&conf->device_lock);
+			spin_lock_irq(&conf->device_lock);
+		}
 	}
 	pr_debug("%d stripes handled\n", handled);
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 61dbb615c30b..a9fc24901eda 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -321,6 +321,7 @@ enum {
 	STRIPE_BIOFILL_RUN,
 	STRIPE_COMPUTE_RUN,
 	STRIPE_OPS_REQ_PENDING,
+	STRIPE_ON_UNPLUG_LIST,
 };
 
 /*