Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 75 insertions, 22 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 64d48249c03..77b562d18a9 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -38,21 +38,36 @@
  *    near_copies (stored in low byte of layout)
  *    far_copies (stored in second byte of layout)
  *    far_offset (stored in bit 16 of layout )
+ *    use_far_sets (stored in bit 17 of layout )
  *
- * The data to be stored is divided into chunks using chunksize.
- * Each device is divided into far_copies sections.
- * In each section, chunks are laid out in a style similar to raid0, but
- * near_copies copies of each chunk is stored (each on a different drive).
- * The starting device for each section is offset near_copies from the starting
- * device of the previous section.
- * Thus they are (near_copies*far_copies) of each chunk, and each is on a different
- * drive.
- * near_copies and far_copies must be at least one, and their product is at most
- * raid_disks.
+ * The data to be stored is divided into chunks using chunksize.  Each device
+ * is divided into far_copies sections.   In each section, chunks are laid out
+ * in a style similar to raid0, but near_copies copies of each chunk is stored
+ * (each on a different drive).  The starting device for each section is offset
+ * near_copies from the starting device of the previous section.  Thus there
+ * are (near_copies * far_copies) of each chunk, and each is on a different
+ * drive.  near_copies and far_copies must be at least one, and their product
+ * is at most raid_disks.
  *
  * If far_offset is true, then the far_copies are handled a bit differently.
- * The copies are still in different stripes, but instead of be very far apart
- * on disk, there are adjacent stripes.
+ * The copies are still in different stripes, but instead of being very far
+ * apart on disk, there are adjacent stripes.
+ *
+ * The far and offset algorithms are handled slightly differently if
+ * 'use_far_sets' is true.  In this case, the array's devices are grouped into
+ * sets that are (near_copies * far_copies) in size.  The far copied stripes
+ * are still shifted by 'near_copies' devices, but this shifting stays confined
+ * to the set rather than the entire array.  This is done to improve the number
+ * of device combinations that can fail without causing the array to fail.
+ * Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk
+ * on a device):
+ *    A B C D    A B C D E
+ *      ...         ...
+ *    D A B C    E A B C D
+ * Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s):
+ *    [A B] [C D]    [A B] [C D E]
+ *    |...| |...|    |...| | ... |
+ *    [B A] [D C]    [B A] [E C D]
  */
 
 /*
@@ -535,6 +550,13 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio)
 	sector_t stripe;
 	int dev;
 	int slot = 0;
+	int last_far_set_start, last_far_set_size;
+
+	last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
+	last_far_set_start *= geo->far_set_size;
+
+	last_far_set_size = geo->far_set_size;
+	last_far_set_size += (geo->raid_disks % geo->far_set_size);
 
 	/* now calculate first sector/dev */
 	chunk = r10bio->sector >> geo->chunk_shift;
@@ -551,15 +573,25 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio)
 	/* and calculate all the others */
 	for (n = 0; n < geo->near_copies; n++) {
 		int d = dev;
+		int set;
 		sector_t s = sector;
-		r10bio->devs[slot].addr = sector;
 		r10bio->devs[slot].devnum = d;
+		r10bio->devs[slot].addr = s;
 		slot++;
 
 		for (f = 1; f < geo->far_copies; f++) {
+			set = d / geo->far_set_size;
 			d += geo->near_copies;
-			if (d >= geo->raid_disks)
-				d -= geo->raid_disks;
+
+			if ((geo->raid_disks % geo->far_set_size) &&
+			    (d > last_far_set_start)) {
+				d -= last_far_set_start;
+				d %= last_far_set_size;
+				d += last_far_set_start;
+			} else {
+				d %= geo->far_set_size;
+				d += geo->far_set_size * set;
+			}
 			s += geo->stride;
 			r10bio->devs[slot].devnum = d;
 			r10bio->devs[slot].addr = s;
@@ -595,6 +627,20 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 	 * or recovery, so reshape isn't happening
 	 */
 	struct geom *geo = &conf->geo;
+	int far_set_start = (dev / geo->far_set_size) * geo->far_set_size;
+	int far_set_size = geo->far_set_size;
+	int last_far_set_start;
+
+	if (geo->raid_disks % geo->far_set_size) {
+		last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
+		last_far_set_start *= geo->far_set_size;
+
+		if (dev >= last_far_set_start) {
+			far_set_size = geo->far_set_size;
+			far_set_size += (geo->raid_disks % geo->far_set_size);
+			far_set_start = last_far_set_start;
+		}
+	}
 
 	offset = sector & geo->chunk_mask;
 	if (geo->far_offset) {
@@ -602,13 +648,13 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
 		chunk = sector >> geo->chunk_shift;
 		fc = sector_div(chunk, geo->far_copies);
 		dev -= fc * geo->near_copies;
-		if (dev < 0)
-			dev += geo->raid_disks;
+		if (dev < far_set_start)
+			dev += far_set_size;
 	} else {
 		while (sector >= geo->stride) {
 			sector -= geo->stride;
-			if (dev < geo->near_copies)
-				dev += geo->raid_disks - geo->near_copies;
+			if (dev < (geo->near_copies + far_set_start))
+				dev += far_set_size - geo->near_copies;
 			else
 				dev -= geo->near_copies;
 		}
@@ -1073,6 +1119,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		bio_list_merge(&conf->pending_bio_list, &plug->pending);
 		conf->pending_count += plug->pending_cnt;
 		spin_unlock_irq(&conf->device_lock);
+		wake_up(&conf->wait_barrier);
 		md_wakeup_thread(mddev->thread);
 		kfree(plug);
 		return;
@@ -1105,6 +1152,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
 	const unsigned long do_discard = (bio->bi_rw
 					  & (REQ_DISCARD | REQ_SECURE));
+	const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
@@ -1460,7 +1508,8 @@ retry_write:
 							      rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_rw =
+				WRITE | do_sync | do_fua | do_discard | do_same;
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
@@ -1502,7 +1551,8 @@ retry_write:
 						   r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_rw =
+				WRITE | do_sync | do_fua | do_discard | do_same;
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
@@ -3436,7 +3486,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
 		disks = mddev->raid_disks + mddev->delta_disks;
 		break;
 	}
-	if (layout >> 17)
+	if (layout >> 18)
 		return -1;
 	if (chunk < (PAGE_SIZE >> 9) ||
 	    !is_power_of_2(chunk))
@@ -3448,6 +3498,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
 	geo->near_copies = nc;
 	geo->far_copies = fc;
 	geo->far_offset = fo;
+	geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks;
 	geo->chunk_mask = chunk - 1;
 	geo->chunk_shift = ffz(~chunk);
 	return nc*fc;
@@ -3569,6 +3620,8 @@ static int run(struct mddev *mddev)
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
 					      mddev->chunk_sectors);
+		blk_queue_max_write_same_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);