LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Robin Getz <rgetz@blackfin.uclinux.org>
To: "Paul Mundt" <lethal@linux-sh.org>
Cc: "Bernd Schmidt" <bernds_cb1@t-online.de>,
	"Wu, Bryan" <bryan.wu@analog.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH -mm 1/5] Blackfin: blackfin architecture patch update
Date: Mon, 5 Mar 2007 08:26:56 -0500	[thread overview]
Message-ID: <200703050826.56966.rgetz@blackfin.uclinux.org> (raw)
In-Reply-To: <20070305123910.GA13684@linux-sh.org>

On Mon 5 Mar 2007 07:39, Paul Mundt pondered:
> On Mon, Mar 05, 2007 at 01:32:07PM +0100, Bernd Schmidt wrote:
>  > Paul Mundt wrote:
>  > >>+comment "Memory Optimizations"
>  > >>+
>  > >>+config I_ENTRY_L1
>  > >>+   bool "Locate interrupt entry code in L1 Memory"
>  > >>+   default y
>  > >>+   help
>  > >>+     If enabled interrupt entry code (STORE/RESTORE CONTEXT) is
>  > >> linked +     into L1 instruction memory.(less latency)
>  > >>+
>  > >
>  > >Wow, this is really crying out for a special linker section with
>  > > slightly more intelligent relocation logic. You should flag the
>  > > performance critical parts to be located in L1 memory directly with a
>  > > section attribute, rather than making everything selectable. If you
>  > > overflow you can simply spill in to main memory.
>  >
>  > This is done intentionally, because it's also possible for user code to
>  > be loaded into L1 memory.  We want to give users the option to avoid
>  > filling it all up with kernel code.
>
>  So then why not make the userspace component of it optional and allow a
> size cap for kernel usage that's configurable if it's enabled? This degree
> of abstraction is almost worse than no abstraction.

I don't understand why you think lots of options are a bad thing??

For most embedded targets, people want/need easy knobs to turn to try and 
optimise the system level performance. I would guess that SH users want to do 
the same thing?

That is what this does - it is just a easy to use knob.

-Robin

  reply	other threads:[~2007-03-05 13:26 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-03-01  4:14 Wu, Bryan
2007-03-03 20:38 ` Arnd Bergmann
2007-03-05  7:13   ` Wu, Bryan
2007-03-03 22:30 ` Arnd Bergmann
2007-03-03 22:50   ` bert hubert
2007-03-03 23:05     ` Arnd Bergmann
2007-03-05  6:54   ` Aubrey Li
2007-03-05  8:47     ` Arnd Bergmann
2007-03-05  9:19       ` Wu, Bryan
2007-03-05 16:43         ` Arnd Bergmann
2007-03-05  7:34   ` Wu, Bryan
2007-03-05  8:10     ` Arnd Bergmann
2007-03-06  2:09   ` Mike Frysinger
2007-03-05  9:23 ` Paul Mundt
2007-03-05 12:32   ` Bernd Schmidt
2007-03-05 12:39     ` Paul Mundt
2007-03-05 13:26       ` Robin Getz [this message]
2007-03-05 14:00         ` Paul Mundt
2007-03-05 16:29           ` Robin Getz
2007-03-05 17:32             ` Paul Mundt
2007-03-05 22:06               ` Robin Getz
2007-03-06  2:04   ` Mike Frysinger
2007-03-21 15:44   ` Mike Frysinger
2007-03-21 23:42     ` Paul Mundt

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=200703050826.56966.rgetz@blackfin.uclinux.org \
    --to=rgetz@blackfin.uclinux.org \
    --cc=akpm@linux-foundation.org \
    --cc=bernds_cb1@t-online.de \
    --cc=bryan.wu@analog.com \
    --cc=lethal@linux-sh.org \
    --cc=linux-kernel@vger.kernel.org \
    --subject='Re: [PATCH -mm 1/5] Blackfin: blackfin architecture patch update' \
    /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

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).