From: Daniel Walker <dwalker@codeaurora.org>
To: Stepan Moskovchenko <stepanm@codeaurora.org>
Cc: davidb@codeaurora.org, bryanh@codeaurora.org,
linux-arm-msm@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 09/14] msm: iommu: Kconfig option for cacheable page tables
Date: Mon, 15 Nov 2010 10:20:36 -0800 [thread overview]
Message-ID: <1289845236.4050.25.camel@c-dwalke-linux.qualcomm.com> (raw)
In-Reply-To: <8bd62d321211c93af883cd2ad404e802.squirrel@www.codeaurora.org>
On Sun, 2010-11-14 at 18:56 -0800, Stepan Moskovchenko wrote:
> > On Fri, 2010-11-12 at 19:29 -0800, Stepan Moskovchenko wrote:
> >>
> >> +config IOMMU_PGTABLES_L2
> >> + depends on ARCH_MSM8X60
> >> + depends on MMU
> >> + depends on CPU_DCACHE_DISABLE=n
> >> + depends on SMP
> >> + bool "Cacheable IOMMU page tables"
> >> + default y
> >> + help
> >> + Allows the IOMMU page tables to be brought into the L2 cache. This
> >> + improves the TLB miss latency at the expense of potential pollution
> >> + of the L2 cache. This option has been shown to improve multimedia
> >> + performance in some cases.
> >> +
> >> + If unsure, say Y here.
> >
> > Why would someone want this off?
> >
> > The other thing is that you usually want this included with the code
> > that uses the option.
>
> The code that uses it had gone in during a previous patch series, but I
> didn't want to meddle in the Kconfig just yet, especially since the option
> only improves performance and does not add new functionality at a high
> level. This patch should be the last of what is needed for this feature.
>
> You would want to turn this off if you wanted more deterministic behavior
> from the multimedia subsystem, such as when trying to run benchmarks for
> the worst-case behavior in terms of memory latency and TLB misses. You
> might also want to turn it off if you are debugging memory problems that
> you suspect might be related to the cache maintenance code, in which case
> turning this off would give an idea as to whether that is the problem.
> Similarly, this needs to be off (and will be, due to the dependencies) if
> certain required things (like the Dcache, MMU, etc) have been disabled.
> Finally, if you are doing things with the MMSS that you know will not
> result in many TLB misses, (or if you know that you can tolerate high miss
> latency) you may as well turn this off to avoid the (small) bit of cache
> pollution.
It sounds like you don't really want it off unless your a developer (or
you turn one of the dependencies) .. I think this might be better as a
hidden option just cause of the developer centric nature of it.
Daniel
--
Sent by a consultant of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
next prev parent reply other threads:[~2010-11-15 18:20 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-13 3:29 [PATCH 00/14] Improvements to the MSM IOMMU driver Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 01/14] msm: iommu: Increase maximum MID size to 5 bits Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 02/14] msm: iomap: Addresses and IRQs for 2nd GFX core IOMMU Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 03/14] msm: iommu: Use more consistent naming in platform data Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 04/14] msm: iommu: Revise GFX3D IOMMU contexts and M2V mappings Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 05/14] msm: iommu: Revise GFX2D0 " Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 06/14] msm: iommu: Support for the 2nd GFX core's IOMMU Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 07/14] msm: iommu: Mark functions with the right section names Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 08/14] msm: iommu: Don't flush page tables if no devices attached Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 09/14] msm: iommu: Kconfig option for cacheable page tables Stepan Moskovchenko
2010-11-14 20:17 ` Daniel Walker
2010-11-15 2:56 ` Stepan Moskovchenko
2010-11-15 18:20 ` Daniel Walker [this message]
2010-11-16 1:47 ` Stepan Moskovchenko
2010-11-16 1:46 ` [PATCH 09/14 v2] msm: iommu: Kconfig item " Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 10/14] msm: iommu: Check if device is already attached Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 11/14] msm: iommu: Kconfig dependency for the IOMMU API Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 12/14] msm: iommu: Definitions for extended memory attributes Stepan Moskovchenko
2010-11-16 2:19 ` [PATCH 12/14 v2] " Stepan Moskovchenko
2010-11-13 3:29 ` [PATCH 13/14] msm: iommu: Support cache-coherent memory access Stepan Moskovchenko
2010-11-16 2:20 ` [PATCH 13/14 v2] " Stepan Moskovchenko
2010-11-13 3:30 ` [PATCH 14/14] msm: iommu: Miscellaneous code cleanup Stepan Moskovchenko
2010-11-16 0:25 ` Daniel Walker
2010-11-16 1:16 ` Stepan Moskovchenko
2010-11-16 20:45 ` Daniel Walker
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=1289845236.4050.25.camel@c-dwalke-linux.qualcomm.com \
--to=dwalker@codeaurora.org \
--cc=bryanh@codeaurora.org \
--cc=davidb@codeaurora.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stepanm@codeaurora.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).