From: Scott Wood <scottwood@freescale.com>
To: benh@kernel.crashing.org
Cc: Dominik Bozek <domino@mikroswiat.pl>,
linuxppc-embedded@ozlabs.org, Paul Mackerras <paulus@samba.org>,
linuxppc-dev@ozlabs.org
Subject: Re: performance: memcpy vs. __copy_tofrom_user
Date: Mon, 13 Oct 2008 16:03:30 -0500 [thread overview]
Message-ID: <48F3B7A2.3010004@freescale.com> (raw)
In-Reply-To: <1223931027.8157.272.camel@pasglop>
Benjamin Herrenschmidt wrote:
>> It doesn't need to be done in non-preemptible sections, if you have a
>> separate per-thread save area for kernel fp/altivec use (and appropriate
>> flags so an FP unavailable handler knows which regs to restore), and you
>> can avoid using it in a preempting context.
>
> Yuck.
Hmm? It's simple and achieves the desired result (avoiding
non-preemptible regions without unduly restricting the ability to
extract performance from the hardware).
Would it be nicer to avoid FP/Altivec in the kernel altogether? Sure.
If the benchmarking says that we're better off with it, though, then so
be it.
-Scott
next prev parent reply other threads:[~2008-10-13 21:03 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-08 14:39 performance: memcpy vs. __copy_tofrom_user Dominik Bozek
2008-10-08 15:31 ` Minh Tuan Duong
2008-10-08 15:39 ` Bill Gatliff
2008-10-08 15:42 ` Grant Likely
2008-10-09 2:34 ` Paul Mackerras
2008-10-09 10:12 ` Dominik Bozek
2008-10-09 11:06 ` Paul Mackerras
2008-10-09 11:41 ` Dominik Bozek
2008-10-09 12:04 ` Leon Woestenberg
2008-10-09 15:37 ` Matt Sealey
2008-10-11 22:30 ` Benjamin Herrenschmidt
2008-10-12 2:05 ` Matt Sealey
2008-10-12 4:05 ` Benjamin Herrenschmidt
2008-10-13 15:20 ` Scott Wood
2008-10-13 20:50 ` Benjamin Herrenschmidt
2008-10-13 21:03 ` Scott Wood [this message]
2008-10-14 2:14 ` Matt Sealey
2008-10-14 2:39 ` Benjamin Herrenschmidt
2008-10-14 15:10 ` Scott Wood
2008-10-15 1:37 ` Matt Sealey
2008-10-10 17:17 ` Dominik Bozek
2008-10-08 17:40 ` Scott Wood
2008-10-09 2:36 ` Paul Mackerras
2008-10-11 22:32 ` Benjamin Herrenschmidt
2008-10-13 15:06 ` Scott Wood
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=48F3B7A2.3010004@freescale.com \
--to=scottwood@freescale.com \
--cc=benh@kernel.crashing.org \
--cc=domino@mikroswiat.pl \
--cc=linuxppc-dev@ozlabs.org \
--cc=linuxppc-embedded@ozlabs.org \
--cc=paulus@samba.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.