From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
To: hancockrwd@gmail.com
Cc: davem@davemloft.net, bzolnier@gmail.com,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
linux-usb@vger.kernel.org
Subject: Re: [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking drivers
Date: Sun, 28 Feb 2010 03:38:19 +0900 [thread overview]
Message-ID: <20100228033706G.fujita.tomonori@lab.ntt.co.jp> (raw)
In-Reply-To: <51f3faa71002271015i7c9ec45j18381b1269bfd799@mail.gmail.com>
On Sat, 27 Feb 2010 12:15:19 -0600
Robert Hancock <hancockrwd@gmail.com> wrote:
> On Sat, Feb 27, 2010 at 6:05 AM, David Miller <davem@davemloft.net> wrote:
> > From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
> > Date: Sat, 27 Feb 2010 12:59:31 +0100
> >
> >> Having IOMMU (even if it is only a software one, i.e. this would
> >> mean swiotlb for x86-32/highmem) always in place would simplify
> >> things greatly..
> >
> > I agree, things would be a lot simpler.
>
> Yeah, the situation kind of sucks on the platforms that don't have any
> IOMMU support, since it means that the DMA API can't handle anything
> over 4GB properly and you need all these hacks in the block layer,
> networking layer, etc. It would be nice if some kind of IOMMU support
> could be relied upon always.
When I proposed such approach (always use swiotlb) before, IIRC,
the objections were:
- better to make allocation respect dma_mask. (I don't think that this
approach is possible since we don't know which device handles data
later when we allocate memory).
- swiotlb is not good for small systems since it allocates too much
memory (we can fix this though).
There might be more.
WARNING: multiple messages have this Message-ID (diff)
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
To: hancockrwd@gmail.com
Cc: davem@davemloft.net, bzolnier@gmail.com,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
linux-usb@vger.kernel.org
Subject: Re: [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking drivers
Date: Sun, 28 Feb 2010 03:38:19 +0900 [thread overview]
Message-ID: <20100228033706G.fujita.tomonori@lab.ntt.co.jp> (raw)
In-Reply-To: <51f3faa71002271015i7c9ec45j18381b1269bfd799@mail.gmail.com>
On Sat, 27 Feb 2010 12:15:19 -0600
Robert Hancock <hancockrwd@gmail.com> wrote:
> On Sat, Feb 27, 2010 at 6:05 AM, David Miller <davem@davemloft.net> wrote:
> > From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
> > Date: Sat, 27 Feb 2010 12:59:31 +0100
> >
> >> Having IOMMU (even if it is only a software one, i.e. this would
> >> mean swiotlb for x86-32/highmem) always in place would simplify
> >> things greatly..
> >
> > I agree, things would be a lot simpler.
>
> Yeah, the situation kind of sucks on the platforms that don't have any
> IOMMU support, since it means that the DMA API can't handle anything
> over 4GB properly and you need all these hacks in the block layer,
> networking layer, etc. It would be nice if some kind of IOMMU support
> could be relied upon always.
When I proposed such approach (always use swiotlb) before, IIRC,
the objections were:
- better to make allocation respect dma_mask. (I don't think that this
approach is possible since we don't know which device handles data
later when we allocate memory).
- swiotlb is not good for small systems since it allocates too much
memory (we can fix this though).
There might be more.
next prev parent reply other threads:[~2010-02-27 18:38 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-23 2:45 [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking drivers Robert Hancock
2010-02-26 9:36 ` David Miller
2010-02-26 14:46 ` Robert Hancock
2010-02-26 14:46 ` Robert Hancock
2010-02-26 15:25 ` Bartlomiej Zolnierkiewicz
2010-02-27 3:08 ` Robert Hancock
2010-02-27 3:08 ` Robert Hancock
2010-02-27 9:53 ` David Miller
2010-02-27 11:59 ` Bartlomiej Zolnierkiewicz
2010-02-27 12:05 ` David Miller
2010-02-27 18:15 ` Robert Hancock
2010-02-27 18:15 ` Robert Hancock
2010-02-27 18:38 ` FUJITA Tomonori [this message]
2010-02-27 18:38 ` FUJITA Tomonori
2010-02-28 8:16 ` David Miller
2010-02-28 8:16 ` David Miller
2010-03-01 16:34 ` Was: Re: [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking, Now: SWIOTLB dynamic allocation Konrad Rzeszutek Wilk
2010-03-01 21:12 ` Robert Hancock
2010-03-01 21:12 ` Robert Hancock
2010-03-02 4:40 ` FUJITA Tomonori
2010-03-02 4:40 ` FUJITA Tomonori
2010-03-02 4:40 ` FUJITA Tomonori
2010-02-27 17:59 ` [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking drivers Robert Hancock
2010-02-27 17:59 ` Robert Hancock
2010-02-27 18:38 ` FUJITA Tomonori
2010-02-27 18:38 ` FUJITA Tomonori
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=20100228033706G.fujita.tomonori@lab.ntt.co.jp \
--to=fujita.tomonori@lab.ntt.co.jp \
--cc=bzolnier@gmail.com \
--cc=davem@davemloft.net \
--cc=hancockrwd@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-usb@vger.kernel.org \
--cc=netdev@vger.kernel.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.