From: Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
To: Hiroshi Doyu <hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
Cc: "linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
<linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
"linaro-mm-sig-cunTk1MwBs8s++Sfvej+rw@public.gmane.org"
<linaro-mm-sig-cunTk1MwBs8s++Sfvej+rw@public.gmane.org>,
"iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org"
<iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>,
"linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org"
<linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org>
Subject: Re: [RFC 0/3] How to pass IOMMU map attr via DMA API?
Date: Mon, 24 Jun 2013 09:21:28 +0200 [thread overview]
Message-ID: <20130624072128.GP11309@8bytes.org> (raw)
In-Reply-To: <20130624081759.76e66d42bbf7c2c54ed1975c-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
On Mon, Jun 24, 2013 at 08:17:59AM +0300, Hiroshi Doyu wrote:
> Ok, thanks. One more question, IOMMU H/W sometimes supports more
> platform specific attributes than READ/WRITE. For example, in OMAP,
>
> #define IOMMU_FLAG (IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
>
> Is there any way to deal with those platform specific attrs from DMA
> mapping API POV?
Depends on the kind of flag and whether you want to make it changeable
from the DMA-API. The AMD IOMMU for example has a flag in the
page-tables to force PCI DMA coherency. This is always set by the
driver.
For other parameters that should be changeable and don't fit into the
dma_direction parameter in some way the use of dma_attr would make
sense.
Joerg
WARNING: multiple messages have this Message-ID (diff)
From: joro@8bytes.org (Joerg Roedel)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC 0/3] How to pass IOMMU map attr via DMA API?
Date: Mon, 24 Jun 2013 09:21:28 +0200 [thread overview]
Message-ID: <20130624072128.GP11309@8bytes.org> (raw)
In-Reply-To: <20130624081759.76e66d42bbf7c2c54ed1975c@nvidia.com>
On Mon, Jun 24, 2013 at 08:17:59AM +0300, Hiroshi Doyu wrote:
> Ok, thanks. One more question, IOMMU H/W sometimes supports more
> platform specific attributes than READ/WRITE. For example, in OMAP,
>
> #define IOMMU_FLAG (IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
>
> Is there any way to deal with those platform specific attrs from DMA
> mapping API POV?
Depends on the kind of flag and whether you want to make it changeable
from the DMA-API. The AMD IOMMU for example has a flag in the
page-tables to force PCI DMA coherency. This is always set by the
driver.
For other parameters that should be changeable and don't fit into the
dma_direction parameter in some way the use of dma_attr would make
sense.
Joerg
next prev parent reply other threads:[~2013-06-24 7:21 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-20 5:49 [RFC 0/3] How to pass IOMMU map attr via DMA API? Hiroshi Doyu
2013-06-20 5:49 ` Hiroshi Doyu
[not found] ` <1371707384-30037-1-git-send-email-hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 5:49 ` [RFC 1/3] common: DMA-mapping: add DMA_ATTR_READ_ONLY attribute Hiroshi Doyu
2013-06-20 5:49 ` [RFC 2/3] ARM: dma-mapping: Pass DMA attrs as IOMMU prot Hiroshi Doyu
[not found] ` <1371707384-30037-3-git-send-email-hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 8:07 ` [Linaro-mm-sig] " Nishanth Peethambaran
2013-06-20 8:07 ` Nishanth Peethambaran
[not found] ` <CAMcxFTRnnCnPnvMi89r7rUsN4xeYzZGqy9s5v5ukm_fJ_d_RGg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-06-20 8:24 ` Hiroshi Doyu
2013-06-20 8:24 ` Hiroshi Doyu
[not found] ` <20130620.112439.1330557591655135630.hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 8:55 ` Nishanth Peethambaran
2013-06-20 8:55 ` Nishanth Peethambaran
[not found] ` <CAMcxFTS0dUUEfGj-=-cb_rdfy+qWvtsaoR6Tv+-x05XX0mZmmw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-06-20 9:54 ` Hiroshi Doyu
2013-06-20 9:54 ` Hiroshi Doyu
[not found] ` <20130620.125431.1161068035083905855.hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 10:13 ` Arnd Bergmann
2013-06-20 10:13 ` Arnd Bergmann
[not found] ` <201306201213.13644.arnd-r2nGTMty4D4@public.gmane.org>
2013-06-20 10:34 ` Hiroshi Doyu
2013-06-20 10:34 ` Hiroshi Doyu
[not found] ` <20130620.133407.798194318297047071.hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 10:57 ` Arnd Bergmann
2013-06-20 10:57 ` Arnd Bergmann
[not found] ` <201306201257.58419.arnd-r2nGTMty4D4@public.gmane.org>
2013-06-20 12:49 ` Nishanth Peethambaran
2013-06-20 12:49 ` Nishanth Peethambaran
2013-06-20 5:49 ` [RFC 3/3] iommu/tegra: smmu: Support read-only mapping Hiroshi Doyu
[not found] ` <1371707384-30037-4-git-send-email-hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 6:50 ` [Linaro-mm-sig] " Kyungmin Park
2013-06-20 6:50 ` Kyungmin Park
[not found] ` <CAH9JG2VUCJErBNwT0_u_9niaSWUza5gJ-+q8OOJhrrdw5D-hUg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-06-20 7:27 ` Hiroshi Doyu
2013-06-20 7:27 ` Hiroshi Doyu
2013-06-20 9:31 ` [RFC 0/3] How to pass IOMMU map attr via DMA API? Will Deacon
2013-06-20 9:31 ` Will Deacon
[not found] ` <20130620093152.GE2842-MRww78TxoiP5vMa5CHWGZ34zcgK1vI+I0E9HWUfgJXw@public.gmane.org>
2013-06-20 9:59 ` Hiroshi Doyu
2013-06-20 9:59 ` Hiroshi Doyu
[not found] ` <20130620.125929.2250094502232662356.hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-20 10:11 ` Catalin Marinas
2013-06-20 10:11 ` Catalin Marinas
[not found] ` <20130620101110.GB18536-5wv7dgnIgG8@public.gmane.org>
2013-06-20 11:00 ` Hiroshi Doyu
2013-06-20 11:00 ` Hiroshi Doyu
2013-06-20 10:12 ` Will Deacon
2013-06-20 10:12 ` Will Deacon
2013-06-21 7:17 ` Marek Szyprowski
2013-06-21 7:17 ` Marek Szyprowski
[not found] ` <51C3FE27.5070702-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
2013-06-21 16:03 ` Joerg Roedel
2013-06-21 16:03 ` Joerg Roedel
[not found] ` <20130621160344.GM11309-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2013-06-24 5:17 ` Hiroshi Doyu
2013-06-24 5:17 ` Hiroshi Doyu
[not found] ` <20130624081759.76e66d42bbf7c2c54ed1975c-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2013-06-24 7:21 ` Joerg Roedel [this message]
2013-06-24 7:21 ` Joerg Roedel
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=20130624072128.GP11309@8bytes.org \
--to=joro-zlv9swrftaidnm+yrofe0a@public.gmane.org \
--cc=hdoyu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=linaro-mm-sig-cunTk1MwBs8s++Sfvej+rw@public.gmane.org \
--cc=linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/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.