From mboxrd@z Thu Jan  1 00:00:00 1970
From: keith.busch@intel.com (Keith Busch)
Date: Wed, 18 Nov 2015 23:02:27 +0000
Subject: Drives with MDTS set to zero
In-Reply-To: <20151118225820.GB24252@localhost.localdomain>
References: <564B9366.1090904@ranbarg.com>
 <20151118225820.GB24252@localhost.localdomain>
Message-ID: <20151118230226.GC24252@localhost.localdomain>

On Wed, Nov 18, 2015@10:58:20PM +0000, Keith Busch wrote:
> We can fix this by reordering the math instead of artificially reducing
> the transfer size.

Resend with an actually compilable patch.

---
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5aca81c..f17e3d3 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2266,7 +2266,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	if (dev->max_hw_sectors) {
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
 		blk_queue_max_segments(ns->queue,
-			((dev->max_hw_sectors << 9) / dev->page_size) + 1);
+			(dev->max_hw_sectors / (dev->page_size >> 9) + 1);
 	}
 	if (dev->stripe_size)
 		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
--