From: Catalin Marinas <catalin.marinas@arm.com>
To: Russell King - ARM Linux <linux@arm.linux.org.uk>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH v7 16/16] ARM: LPAE: Add the Kconfig entries
Date: Wed, 2 Nov 2011 18:07:58 +0000 [thread overview]
Message-ID: <20111102180758.GK29782@arm.com> (raw)
In-Reply-To: <20111102172142.GB12913@n2100.arm.linux.org.uk>
On Wed, Nov 02, 2011 at 05:21:42PM +0000, Russell King - ARM Linux wrote:
> On Wed, Aug 10, 2011 at 04:03:39PM +0100, Catalin Marinas wrote:
> > +config ARCH_DMA_ADDR_T_64BIT
> > + def_bool ARM_LPAE
> > +
>
> I think this should be selected only when we have a DMA engine supporting
> 64-bit addresses. Technically LPAE itself doesn't give us that assurance.
>
> If you have this kind of a setup:
>
> CPU <==++==> RAM
> ||
> IOMMU
> |
> DMA device
>
> where == and || means >32-bit addressing, and | means 32-bit addressing.
That's one configuration but there are other configurations with PCI
devices that can access 64-bit addresses without requiring an IOMMU.
> In such a setup, having dma_addr_t be 64-bit is pointless because it
> should never see 64-bit addresses (the DMA API should deal with the
> IOMMU and provide a list of DMA addresses to be placed into RAM for
> the DMA device which takes account of the mappings setup in the IOMMU.)
>
> So, I think 64-bit dma_addr_t should be a property of the DMA devices
> present in the system rather than whether the CPUs MMU can deal with
> >32-bit addresses or not.
I agree, that's a property of the device but it doesn't mean that we
can't have a dma_addr_t as u64.
The current DMA allocator uses pages that can be placed anywhere if the
mask is 0xffffffff, so just making this type u32 does not change such
allocation, just ignoring the top bits of the bus address. What I think
we need for this case is GFP_DMA32, assuming that ZONE_DMA32 is set up:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e4e7f6c..a51026b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -81,6 +81,8 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
if (mask < 0xffffffffULL)
gfp |= GFP_DMA;
+ else if (mask == 0xffffffffULL)
+ gfp |= GFP_DMA32;
page = alloc_pages(gfp, order);
if (!page)
--
Catalin
prev parent reply other threads:[~2011-11-02 18:08 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-10 15:03 [PATCH v7 00/16] ARM: Add support for the Large Physical Address Extensions Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 01/16] ARM: LPAE: add ISBs around MMU enabling code Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 02/16] ARM: LPAE: Cast the dma_addr_t argument to unsigned long in dma_to_virt Catalin Marinas
2011-08-13 14:33 ` Russell King - ARM Linux
2011-08-23 11:15 ` Russell King - ARM Linux
2011-08-10 15:03 ` [PATCH v7 03/16] ARM: LPAE: Use PMD_(SHIFT|SIZE|MASK) instead of PGDIR_* Catalin Marinas
2011-08-13 14:34 ` Russell King - ARM Linux
2011-08-15 16:48 ` Catalin Marinas
2011-08-23 11:15 ` Russell King - ARM Linux
2011-08-23 13:09 ` Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 04/16] ARM: LPAE: Factor out 2-level page table definitions into separate files Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 05/16] ARM: LPAE: Add (pte|pmd)val_t type definitions as u32 Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 06/16] ARM: LPAE: Use a mask for physical addresses in page table entries Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 07/16] ARM: LPAE: Introduce the 3-level page table format definitions Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 08/16] ARM: LPAE: Page table maintenance for the 3-level format Catalin Marinas
2011-10-23 11:56 ` Russell King - ARM Linux
2011-10-23 12:49 ` Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 09/16] ARM: LPAE: MMU setup for the 3-level page table format Catalin Marinas
2011-08-13 11:49 ` Vasily Khoruzhick
2011-08-13 12:56 ` Vasily Khoruzhick
2011-08-13 12:58 ` [PATCH] Fix non-LPAE boot regression Vasily Khoruzhick
2011-08-13 14:14 ` Catalin Marinas
2011-08-13 14:39 ` Russell King - ARM Linux
2011-08-13 14:45 ` Catalin Marinas
2011-08-15 11:41 ` Catalin Marinas
2011-08-15 12:09 ` Catalin Marinas
2011-08-15 12:31 ` Vasily Khoruzhick
2011-08-24 8:16 ` Vasily Khoruzhick
2011-08-15 16:51 ` [PATCH v7 09/16] ARM: LPAE: MMU setup for the 3-level page table format Catalin Marinas
2011-08-19 10:25 ` Ian Campbell
2011-08-19 11:10 ` Catalin Marinas
2011-08-19 11:47 ` Ian Campbell
2011-08-10 15:03 ` [PATCH v7 10/16] ARM: LPAE: Invalidate the TLB before freeing the PMD Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 11/16] ARM: LPAE: Add fault handling support Catalin Marinas
2011-10-23 11:57 ` Russell King - ARM Linux
2011-11-02 17:02 ` Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 12/16] ARM: LPAE: Add context switching support Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 13/16] ARM: LPAE: Add identity mapping support for the 3-level page table format Catalin Marinas
2011-10-23 11:59 ` Russell King - ARM Linux
2011-08-10 15:03 ` [PATCH v7 14/16] ARM: LPAE: mark memory banks with start > ULONG_MAX as highmem Catalin Marinas
2011-08-10 15:03 ` [PATCH v7 15/16] ARM: LPAE: add support for ATAG_MEM64 Catalin Marinas
2011-10-23 11:59 ` Russell King - ARM Linux
2011-08-10 15:03 ` [PATCH v7 16/16] ARM: LPAE: Add the Kconfig entries Catalin Marinas
2011-10-23 12:00 ` Russell King - ARM Linux
2011-11-02 17:21 ` Russell King - ARM Linux
2011-11-02 18:07 ` Catalin Marinas [this message]
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=20111102180758.GK29782@arm.com \
--to=catalin.marinas@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
/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