[PATCH 3.4 08/92] md/raid0: update queue parameter in a safer location.

[lizf]

From: NeilBrown <neilb@xxxxxxxx>

3.4.112-rc1 review patch.  If anyone has any objections, please let me know.

------------------


commit 199dc6ed5179251fa6158a461499c24bdd99c836 upstream.

When a (e.g.) RAID5 array is reshaped to RAID0, the updating
of queue parameters (e.g. max number of sectors per bio) is
done in the wrong place.
It should be part of ->run, but it is actually part of ->takeover.
This means it happens before level_store() calls:

	blk_set_stacking_limits(&mddev->queue->limits);

and so it ineffective.  This can lead to errors from underlying
devices.

So move all the relevant settings out of create_stripe_zones()
and into raid0_run().

As this can lead to a bug-on it is suitable for any -stable
kernel which supports reshape to RAID0.  So 2.6.35 or later.
As the bug has been present for five years there is no urgency,
so no need to rush into -stable.

Fixes: 9af204cf720c ("md: Add support for Raid5->Raid0 and Raid10->Raid0 takeover")
Reported-by: Yi Zhang <yizhan@xxxxxxxxxx>
Signed-off-by: NeilBrown <neilb@xxxxxxxx>
[lizf: Backported to 3.4:
 - adjust context
 - remove changes to discard and write-same features]
Signed-off-by: Zefan Li <lizefan@xxxxxxxxxx>
---
 drivers/md/raid0.c | 55 ++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 37 insertions(+), 18 deletions(-)

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 06a0257..3e285e6 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -88,6 +88,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	char b[BDEVNAME_SIZE];
 	char b2[BDEVNAME_SIZE];
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
+	unsigned short blksize = 512;
 
 	if (!conf)
 		return -ENOMEM;
@@ -102,6 +103,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
+		blksize = max(blksize, queue_logical_block_size(
+				      rdev1->bdev->bd_disk->queue));
+
 		rdev_for_each(rdev2, mddev) {
 			pr_debug("md/raid0:%s:   comparing %s(%llu)"
 				 " with %s(%llu)\n",
@@ -138,6 +142,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	}
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
+	/*
+	 * now since we have the hard sector sizes, we can make sure
+	 * chunk size is a multiple of that sector size
+	 */
+	if ((mddev->chunk_sectors << 9) % blksize) {
+		printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n",
+		       mdname(mddev),
+		       mddev->chunk_sectors << 9, blksize);
+		err = -EINVAL;
+		goto abort;
+	}
+
 	err = -ENOMEM;
 	conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
 				conf->nr_strip_zones, GFP_KERNEL);
@@ -186,9 +202,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		}
 		dev[j] = rdev1;
 
-		disk_stack_limits(mddev->gendisk, rdev1->bdev,
-				  rdev1->data_offset << 9);
-
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
 			conf->has_merge_bvec = 1;
 
@@ -257,21 +270,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	mddev->queue->backing_dev_info.congested_fn = raid0_congested;
 	mddev->queue->backing_dev_info.congested_data = mddev;
 
-	/*
-	 * now since we have the hard sector sizes, we can make sure
-	 * chunk size is a multiple of that sector size
-	 */
-	if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
-		printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
-		       mdname(mddev),
-		       mddev->chunk_sectors << 9);
-		goto abort;
-	}
-
-	blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-	blk_queue_io_opt(mddev->queue,
-			 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 
@@ -432,6 +430,27 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
+	if (mddev->queue) {
+		struct md_rdev *rdev;
+		bool discard_supported = false;
+
+		rdev_for_each(rdev, mddev) {
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+				discard_supported = true;
+		}
+		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
+
+		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
+		blk_queue_io_opt(mddev->queue,
+				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
+
+		if (!discard_supported)
+			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+		else
+			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
-- 
1.9.1