linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
To: Matthew Wilcox <willy@linux.intel.com>
Cc: Keith Busch <keith.busch@intel.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Paul Mackerras <paulus@samba.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Alexey Kardashevskiy <aik@ozlabs.ru>,
	David Gibson <david@gibson.dropbear.id.au>,
	Christoph Hellwig <hch@infradead.org>,
	"David S. Miller" <davem@davemloft.net>,
	linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
	linuxppc-dev@lists.ozlabs.org, sparclinux@vger.kernel.org
Subject: [PATCH 7/7 v2] drivers/nvme: default to the IOMMU page size
Date: Fri, 23 Oct 2015 14:02:23 -0700	[thread overview]
Message-ID: <20151023210223.GI10197@linux.vnet.ibm.com> (raw)
In-Reply-To: <20151023205420.GA10197@linux.vnet.ibm.com>

We received a bug report recently when DDW (64-bit direct DMA on Power)
is not enabled for NVMe devices. In that case, we fall back to 32-bit
DMA via the IOMMU, which is always done via 4K TCEs (Translation Control
Entries).

The NVMe device driver, though, assumes that the DMA alignment for the
PRP entries will match the device's page size, and that the DMA aligment
matches the kernel's page aligment. On Power, the the IOMMU page size,
as mentioned above, can be 4K, while the device can have a page size of
8K, while the kernel has a page size of 64K. This eventually trips the
BUG_ON in nvme_setup_prps(), as we have a 'dma_len' that is a multiple
of 4K but not 8K (e.g., 0xF000).

In this particular case of page sizes, we clearly want to use the
IOMMU's page size in the driver. And generally, the NVMe driver in this
function should be using the IOMMU's page size for the default device
page size, rather than the kernel's page size.

With this patch, a NVMe device survives our internal hardware
exerciser; the kernel BUGs within a few seconds without the patch.

Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>

---
v1 -> v2:
  Based upon feedback from Christoph Hellwig, implement the IOMMU page
  size lookup as a generic DMA API, rather than an architecture-specific
  hack.

 drivers/block/nvme-core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 6f04771..5a79106 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -18,6 +18,7 @@
 #include <linux/blk-mq.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
@@ -1711,7 +1712,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u32 aqa;
 	u64 cap = readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
-	unsigned page_shift = PAGE_SHIFT;
+	unsigned page_shift = dma_get_page_shift(dev->dev);
 	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
 	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
 
-- 
1.9.1


  parent reply	other threads:[~2015-10-23 21:02 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-10-23 20:54 [PATCH 0/5 v3] Fix NVMe driver support on Power with 32-bit DMA Nishanth Aravamudan
2015-10-23 20:56 ` [PATCH 1/7 v3] dma-mapping: add generic dma_get_page_shift API Nishanth Aravamudan
2015-10-23 20:57 ` [PATCH 2/7 v2] powerpc/dma-mapping: override dma_get_page_shift Nishanth Aravamudan
2015-10-27  6:02   ` Alexey Kardashevskiy
2015-10-27 14:06     ` Busch, Keith
2015-10-27 22:27     ` Nishanth Aravamudan
2015-10-28  1:00       ` Alexey Kardashevskiy
2015-10-28  1:54         ` Nishanth Aravamudan
2015-10-28  2:20           ` Benjamin Herrenschmidt
2015-10-28  2:30             ` Nishanth Aravamudan
2015-10-28  3:20               ` Benjamin Herrenschmidt
2015-10-23 20:57 ` [PATCH 0/5 v3] Fix NVMe driver support on Power with 32-bit DMA Nishanth Aravamudan
2015-10-23 20:58 ` [PATCH 3/7 v2] powerpc/dma: implement per-platform dma_get_page_shift Nishanth Aravamudan
2015-10-23 20:59 ` [PATCH 4/7 v2] pseries/iommu: implement DDW-aware dma_get_page_shift Nishanth Aravamudan
2015-10-27  5:56   ` Alexey Kardashevskiy
2015-10-27 22:22     ` Nishanth Aravamudan
2015-10-23 21:00 ` [PATCH 5/7] [RFC PATCH 5/7] sparc: rename kernel/iommu_common.h -> include/asm/iommu_common.h Nishanth Aravamudan
2015-10-23 21:02   ` Nishanth Aravamudan
2015-10-23 21:01 ` [RFC PATCH 6/7] sparc/dma-mapping: override dma_get_page_shift Nishanth Aravamudan
2015-10-23 21:02 ` Nishanth Aravamudan [this message]
2015-10-27  1:27 ` [PATCH 0/5 v3] Fix NVMe driver support on Power with 32-bit DMA David Miller
2015-10-27 22:20   ` Nishanth Aravamudan
2015-10-27 22:36     ` Busch, Keith
2015-10-28  0:54       ` David Miller
2015-10-28 13:59         ` Busch, Keith
2015-10-29 11:55           ` Christoph Hellwig
2015-10-29 15:57             ` Nishanth Aravamudan
2015-10-29 17:20               ` Busch, Keith
2015-10-30 21:35                 ` [PATCH 1/1 v3] drivers/nvme: default to 4k device page size Nishanth Aravamudan
2015-10-30 21:48                   ` Keith Busch
2015-10-30 22:13                     ` Nishanth Aravamudan
2015-11-03 13:18                   ` Christoph Hellwig
2015-11-03 13:46                     ` Keith Busch
2015-11-05 17:01                       ` [PATCH 1/1 v4] " Nishanth Aravamudan
2015-11-05 19:58                         ` Christoph Hellwig
2015-11-05 21:54                           ` Nishanth Aravamudan
2015-11-06 16:13                           ` Nishanth Aravamudan
2015-11-13  7:37                           ` Christoph Hellwig
2015-11-13 15:08                             ` Keith Busch
2015-11-18 14:42                               ` Christoph Hellwig
2015-10-30  1:49               ` [PATCH 0/5 v3] Fix NVMe driver support on Power with 32-bit DMA David Miller
2015-10-30 21:35                 ` Nishanth Aravamudan
2015-10-27 22:57     ` Julian Calaby
2015-10-27 23:40       ` Nishanth Aravamudan
2015-10-27 23:43         ` Julian Calaby
2015-10-28  0:29           ` Benjamin Herrenschmidt
2015-10-28  1:00           ` David Miller
2015-10-28  0:53     ` David Miller
2015-10-28  1:52       ` Nishanth Aravamudan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20151023210223.GI10197@linux.vnet.ibm.com \
    --to=nacc@linux.vnet.ibm.com \
    --cc=aik@ozlabs.ru \
    --cc=benh@kernel.crashing.org \
    --cc=davem@davemloft.net \
    --cc=david@gibson.dropbear.id.au \
    --cc=hch@infradead.org \
    --cc=keith.busch@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.org \
    --cc=sparclinux@vger.kernel.org \
    --cc=willy@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).