From: Joerg Roedel <joerg.roedel@amd.com>
To: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: linux-kernel@vger.kernel.org, mingo@elte.hu
Subject: Re: [PATCH] x86: avoid unnecessary low zone allocation in AMD IOMMU's alloc_coherent
Date: Wed, 10 Sep 2008 15:53:47 +0200 [thread overview]
Message-ID: <20080910135347.GI6329@amd.com> (raw)
In-Reply-To: <20080910223735O.fujita.tomonori@lab.ntt.co.jp>
On Wed, Sep 10, 2008 at 10:37:45PM +0900, FUJITA Tomonori wrote:
> On Wed, 10 Sep 2008 15:10:32 +0200
> Joerg Roedel <joerg.roedel@amd.com> wrote:
> > Can't we simply make the gfp hacks depend on
> > dma_ops->is_phys and avoid further gfp hacks in the hardware iommu
> > implementations?
>
> I thought about it but adding a new dma_ops->we_don't_want_gfp_flag
> hook doesn't make the code simpler much. Currently, we have the gfp
> setting hack in just one place. It's not bad. Adding such new hook
> means adding more lines than we can remove.
The is_phys flas is already in place and its meaning is "the dma_ops
return bus addresses equal to physical addresses". This is exactly the
case when we need the gfp hacks. So I don't see a problem in just
skipping the gfp rewrite if is_phys is zero. I don't see a point in
adding gfp flags in dma_alloc_coherent and remove them again
dma_ops->alloc_coherent code. Specially in this case where we already
know in dma_alloc_coherent if we really need the flag rewrite.
> Yeah, I was against your patch to adding the gfp setting hack to
> swiotlb but it's because gfp is kinda architecture specific stuff and
> swiotlb should not. It's the bad design IMO. It's ok for me that
> architecture specific IOMMUs can do the architecture specific stuff
> (and it's about just clearing the gfp flag).
The generic swiotlb code already contained a gfp hack for IA64 and I
added another one for x86 which is ok in my opinion. But the #ifdef was
ugly, I agree with that now :-)
Your solution of removing the flag hacks from the generic code completly
was the other possible way.
Joerg
--
| AMD Saxony Limited Liability Company & Co. KG
Operating | Wilschdorfer Landstr. 101, 01109 Dresden, Germany
System | Register Court Dresden: HRA 4896
Research | General Partner authorized to represent:
Center | AMD Saxony LLC (Wilmington, Delaware, US)
| General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy
next prev parent reply other threads:[~2008-09-10 13:54 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-10 11:19 [PATCH] x86: avoid unnecessary low zone allocation in AMD IOMMU's alloc_coherent FUJITA Tomonori
2008-09-10 11:57 ` Ingo Molnar
2008-09-10 12:03 ` Joerg Roedel
2008-09-10 12:18 ` Ingo Molnar
2008-09-10 12:38 ` FUJITA Tomonori
2008-09-10 12:48 ` Joerg Roedel
2008-09-10 13:03 ` FUJITA Tomonori
2008-09-10 13:10 ` Joerg Roedel
2008-09-10 13:37 ` FUJITA Tomonori
2008-09-10 13:53 ` Joerg Roedel [this message]
2008-09-10 14:24 ` FUJITA Tomonori
2008-09-10 14:38 ` Joerg Roedel
2008-09-10 14:45 ` FUJITA Tomonori
2008-09-11 9:10 ` Joerg Roedel
2008-09-11 13:36 ` FUJITA Tomonori
2008-09-10 14:39 ` FUJITA Tomonori
2008-09-10 14:52 ` Joerg Roedel
2008-09-10 15:09 ` FUJITA Tomonori
2008-09-10 15:29 ` Joerg Roedel
2008-09-10 16:29 ` FUJITA Tomonori
2008-09-10 17:05 ` Joerg Roedel
2008-09-10 17:15 ` FUJITA Tomonori
2008-09-10 17:25 ` 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=20080910135347.GI6329@amd.com \
--to=joerg.roedel@amd.com \
--cc=fujita.tomonori@lab.ntt.co.jp \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
/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