From: "Niklas Söderlund" <niklas.soderlund@ragnatech.se>
To: Christoph Hellwig <hch@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>,
Vinod Koul <vinod.koul@intel.com>,
linux-renesas-soc@vger.kernel.org,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"dmaengine@vger.kernel.org" <dmaengine@vger.kernel.org>,
iommu@lists.linux-foundation.org, robin.murphy@arm.com,
Laurent Pinchart <laurent.pinchart@ideasonboard.com>,
geert+renesas@glider.be, Linus Walleij <linus.walleij@linaro.org>,
Arnd Bergmann <arnd@arndb.de>,
linux-arch@vger.kernel.org
Subject: Re: [PATCH v5 3/9] dma-mapping: add dma_{map,unmap}_resource
Date: Fri, 11 Mar 2016 13:58:46 +0100 [thread overview]
Message-ID: <20160311125846.GF1111@bigcity.dyn.berto.se> (raw)
In-Reply-To: <20160311111522.GA3450@infradead.org>
Hi all,
Thanks for your comments.
On 2016-03-11 03:15:22 -0800, Christoph Hellwig wrote:
> On Thu, Mar 10, 2016 at 10:47:10PM -0800, Dan Williams wrote:
> > I think it is confusing to use the dma_ prefix for this peer-to-peer
> > mmio functionality. dma_addr_t is a device's view of host memory.
> > Something like bus_addr_t bus_map_resource(). Doesn't this routine
> > also need the source device in addition to the target device? The
> > resource address is from the perspective of the host cpu, it may be a
> > different address space in the view of two devices relative to each
> > other.
>
> Is it supposed to be per-mmio? It's in dma-mapping ops, and has dma
> in the name, so I suspected it's for some form of peer dma. But given
> that our dma APIs reuqire a struct page backing I have no idea how this
> even supposed to work, and this little documentation blurb still doesn't
> clear that up.
>
> So for now I'd like to NAK this patch until the use case can be
> explained clearly, and actually works.
I can explain the use case and maybe we can figure out if this approach
is the correct one to solve it.
The problem is that I have devices behind an IOMMU which I would like to
use with DMA. Vinod recently moved forward with his and Linus Walleij
patch '[PATCH] dmaengine: use phys_addr_t for slave configuration' which
clarifies that the DMA slave address provided by a client is the
physical address. This puts the task of mapping the DMA slave address
from a phys_addr_t to a dma_addr_t on the DMA engine.
Without an IOMMU this is easy since the phys_addr_t and dma_addr_t are
the same and no special care is needed. However if you have a IOMMU you
need to map the DMA slave phys_addr_t to a dma_addr_t using something
like this. Is it not very similar to dma_map_single() where one maps
processor virtual memory (instead if MMIO) so that it can be used with
DMA slaves?
--
Regards,
Niklas Söderlund
WARNING: multiple messages have this Message-ID (diff)
From: "Niklas Söderlund" <niklas.soderlund@ragnatech.se>
To: Christoph Hellwig <hch@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>,
Vinod Koul <vinod.koul@intel.com>,
linux-renesas-soc@vger.kernel.org,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"dmaengine@vger.kernel.org" <dmaengine@vger.kernel.org>,
iommu@lists.linux-foundation.org, robin.murphy@arm.com,
Laurent Pinchart <laurent.pinchart@ideasonboard.com>,
geert+renesas@glider.be, Linus Walleij <linus.walleij@linaro.org>,
Arnd Bergmann <arnd@arndb.de>,
linux-arch@vger.kernel.org
Subject: Re: [PATCH v5 3/9] dma-mapping: add dma_{map,unmap}_resource
Date: Fri, 11 Mar 2016 13:58:46 +0100 [thread overview]
Message-ID: <20160311125846.GF1111@bigcity.dyn.berto.se> (raw)
In-Reply-To: <20160311111522.GA3450@infradead.org>
Hi all,
Thanks for your comments.
On 2016-03-11 03:15:22 -0800, Christoph Hellwig wrote:
> On Thu, Mar 10, 2016 at 10:47:10PM -0800, Dan Williams wrote:
> > I think it is confusing to use the dma_ prefix for this peer-to-peer
> > mmio functionality. dma_addr_t is a device's view of host memory.
> > Something like bus_addr_t bus_map_resource(). Doesn't this routine
> > also need the source device in addition to the target device? The
> > resource address is from the perspective of the host cpu, it may be a
> > different address space in the view of two devices relative to each
> > other.
>
> Is it supposed to be per-mmio? It's in dma-mapping ops, and has dma
> in the name, so I suspected it's for some form of peer dma. But given
> that our dma APIs reuqire a struct page backing I have no idea how this
> even supposed to work, and this little documentation blurb still doesn't
> clear that up.
>
> So for now I'd like to NAK this patch until the use case can be
> explained clearly, and actually works.
I can explain the use case and maybe we can figure out if this approach
is the correct one to solve it.
The problem is that I have devices behind an IOMMU which I would like to
use with DMA. Vinod recently moved forward with his and Linus Walleij
patch '[PATCH] dmaengine: use phys_addr_t for slave configuration' which
clarifies that the DMA slave address provided by a client is the
physical address. This puts the task of mapping the DMA slave address
from a phys_addr_t to a dma_addr_t on the DMA engine.
Without an IOMMU this is easy since the phys_addr_t and dma_addr_t are
the same and no special care is needed. However if you have a IOMMU you
need to map the DMA slave phys_addr_t to a dma_addr_t using something
like this. Is it not very similar to dma_map_single() where one maps
processor virtual memory (instead if MMIO) so that it can be used with
DMA slaves?
--
Regards,
Niklas S�derlund
WARNING: multiple messages have this Message-ID (diff)
From: niklas.soderlund@ragnatech.se (Niklas Söderlund)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v5 3/9] dma-mapping: add dma_{map,unmap}_resource
Date: Fri, 11 Mar 2016 13:58:46 +0100 [thread overview]
Message-ID: <20160311125846.GF1111@bigcity.dyn.berto.se> (raw)
In-Reply-To: <20160311111522.GA3450@infradead.org>
Hi all,
Thanks for your comments.
On 2016-03-11 03:15:22 -0800, Christoph Hellwig wrote:
> On Thu, Mar 10, 2016 at 10:47:10PM -0800, Dan Williams wrote:
> > I think it is confusing to use the dma_ prefix for this peer-to-peer
> > mmio functionality. dma_addr_t is a device's view of host memory.
> > Something like bus_addr_t bus_map_resource(). Doesn't this routine
> > also need the source device in addition to the target device? The
> > resource address is from the perspective of the host cpu, it may be a
> > different address space in the view of two devices relative to each
> > other.
>
> Is it supposed to be per-mmio? It's in dma-mapping ops, and has dma
> in the name, so I suspected it's for some form of peer dma. But given
> that our dma APIs reuqire a struct page backing I have no idea how this
> even supposed to work, and this little documentation blurb still doesn't
> clear that up.
>
> So for now I'd like to NAK this patch until the use case can be
> explained clearly, and actually works.
I can explain the use case and maybe we can figure out if this approach
is the correct one to solve it.
The problem is that I have devices behind an IOMMU which I would like to
use with DMA. Vinod recently moved forward with his and Linus Walleij
patch '[PATCH] dmaengine: use phys_addr_t for slave configuration' which
clarifies that the DMA slave address provided by a client is the
physical address. This puts the task of mapping the DMA slave address
from a phys_addr_t to a dma_addr_t on the DMA engine.
Without an IOMMU this is easy since the phys_addr_t and dma_addr_t are
the same and no special care is needed. However if you have a IOMMU you
need to map the DMA slave phys_addr_t to a dma_addr_t using something
like this. Is it not very similar to dma_map_single() where one maps
processor virtual memory (instead if MMIO) so that it can be used with
DMA slaves?
--
Regards,
Niklas S?derlund
next prev parent reply other threads:[~2016-03-11 12:59 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-08 2:42 [PATCH v5 0/9] dmaengine: rcar-dmac: add iommu support for slave transfers Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 1/9] iommu: Add MMIO mapping type Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-17 11:18 ` Laurent Pinchart
2016-03-17 11:18 ` Laurent Pinchart
2016-03-17 11:18 ` Laurent Pinchart
2016-03-17 11:18 ` Laurent Pinchart
2016-03-08 2:42 ` [PATCH v5 2/9] dma-mapping: add {map,unmap}_resource to dma_map_ops Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 3/9] dma-mapping: add dma_{map,unmap}_resource Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 7:38 ` Christoph Hellwig
2016-03-08 7:38 ` Christoph Hellwig
2016-03-10 16:05 ` Niklas S??derlund
2016-03-10 16:05 ` Niklas S??derlund
2016-03-10 16:05 ` Niklas S??derlund
2016-03-11 6:19 ` Vinod Koul
2016-03-11 6:19 ` Vinod Koul
2016-03-11 6:19 ` Vinod Koul
2016-03-11 6:47 ` Dan Williams
2016-03-11 6:47 ` Dan Williams
2016-03-11 6:47 ` Dan Williams
2016-03-11 11:15 ` Christoph Hellwig
2016-03-11 11:15 ` Christoph Hellwig
2016-03-11 11:15 ` Christoph Hellwig
2016-03-11 12:58 ` Niklas Söderlund [this message]
2016-03-11 12:58 ` Niklas Söderlund
2016-03-11 12:58 ` Niklas Söderlund
2016-03-11 12:58 ` Niklas Söderlund
2016-03-15 8:22 ` Christoph Hellwig
2016-03-15 8:22 ` Christoph Hellwig
2016-03-15 8:22 ` Christoph Hellwig
2016-03-17 11:33 ` Laurent Pinchart
2016-03-17 11:33 ` Laurent Pinchart
2016-03-17 11:33 ` Laurent Pinchart
2016-03-17 11:33 ` Laurent Pinchart
2016-03-21 15:26 ` Christoph Hellwig
2016-03-21 15:26 ` Christoph Hellwig
2016-03-21 15:26 ` Christoph Hellwig
2016-04-13 13:29 ` Niklas Söderlund
2016-04-13 13:29 ` Niklas Söderlund
2016-04-13 13:29 ` Niklas Söderlund
2016-04-13 13:29 ` Niklas Söderlund
2016-04-13 13:29 ` Niklas Söderlund
2016-04-21 9:48 ` Niklas Söderlund
2016-04-21 9:48 ` Niklas Söderlund
2016-04-21 9:48 ` Niklas Söderlund
2016-04-21 9:48 ` Niklas Söderlund
2016-04-21 13:49 ` Christoph Hellwig
2016-04-21 13:49 ` Christoph Hellwig
2016-04-21 13:49 ` Christoph Hellwig
2016-04-25 14:26 ` Niklas Söderlund
2016-04-25 14:26 ` Niklas Söderlund
2016-04-25 14:26 ` Niklas Söderlund
2016-04-25 14:26 ` Niklas Söderlund
2016-04-25 19:10 ` Christoph Hellwig
2016-04-25 19:10 ` Christoph Hellwig
2016-04-25 19:10 ` Christoph Hellwig
2016-04-26 13:29 ` Niklas Söderlund
2016-04-26 13:29 ` Niklas Söderlund
2016-04-26 13:29 ` Niklas Söderlund
2016-04-26 13:29 ` Niklas Söderlund
2016-04-26 13:29 ` Niklas Söderlund
2016-03-11 13:46 ` Robin Murphy
2016-03-11 13:46 ` Robin Murphy
2016-03-11 13:46 ` Robin Murphy
2016-03-11 13:46 ` Robin Murphy
2016-03-11 17:51 ` Dan Williams
2016-03-11 17:51 ` Dan Williams
2016-03-11 17:51 ` Dan Williams
2016-03-08 2:42 ` [PATCH v5 4/9] arm: dma-mapping: add {map,unmap}_resource for iommu ops Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 4/9] arm: dma-mapping: add {map, unmap}_resource " Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 5/9] dmaengine: rcar-dmac: slave address are physical Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-17 11:30 ` Laurent Pinchart
2016-03-17 11:30 ` Laurent Pinchart
2016-03-17 11:30 ` Laurent Pinchart
2016-03-17 11:30 ` Laurent Pinchart
2016-03-08 2:42 ` [PATCH v5 6/9] dmaengine: rcar-dmac: group slave configuration Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-17 11:28 ` Laurent Pinchart
2016-03-17 11:28 ` Laurent Pinchart
2016-03-17 11:28 ` Laurent Pinchart
2016-03-17 11:28 ` Laurent Pinchart
2016-03-08 2:42 ` [PATCH v5 7/9] dmaengine: rcar-dmac: add iommu support for slave transfers Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 8/9] ARM: dts: r8a7790: add iommus to dmac0 and dmac1 Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
2016-03-08 2:42 ` [PATCH v5 9/9] ARM: dts: r8a7791: " Niklas Söderlund
2016-03-08 2:42 ` Niklas Söderlund
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=20160311125846.GF1111@bigcity.dyn.berto.se \
--to=niklas.soderlund@ragnatech.se \
--cc=arnd@arndb.de \
--cc=dan.j.williams@intel.com \
--cc=dmaengine@vger.kernel.org \
--cc=geert+renesas@glider.be \
--cc=hch@infradead.org \
--cc=iommu@lists.linux-foundation.org \
--cc=laurent.pinchart@ideasonboard.com \
--cc=linus.walleij@linaro.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-renesas-soc@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=vinod.koul@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.