From: "Kevin D. Kissell" <kevink@mips.com>
To: "Dominic Sweetman" <dom@algor.co.uk>, "H . J . Lu" <hjl@lucon.org>
Cc: "Ulrich Drepper" <drepper@redhat.com>,
"GNU libc hacker" <libc-hacker@sources.redhat.com>,
<linux-mips@oss.sgi.com>
Subject: Re: thread-ready ABIs
Date: Sat, 19 Jan 2002 23:21:21 +0100 [thread overview]
Message-ID: <002a01c1a137$a35340a0$0deca8c0@Ulysses> (raw)
In-Reply-To: 15433.26184.411289.161787@gladsmuir.algor.co.uk
> > > It would, in principle, be possible to save/restore k0
> > > or k1 (but not both) if no other clever solution can be found.
> > > There are other VM OSes that manage to do so for MIPS,
> > > for other outside-the-old-ABI reasons. It does, of course,
> > > add some instructions and some memory traffic to the
> > > low-level exception handling , and we would have to look
> > > at whether we would want to make such a feature standard
> > > or specific to a "thread-ready" kernel build.
> >
> > I like the read-only k0 idea. We just need to make a system call to
> > tell kernel what value to put in k0 before returning to the user space.
> > It shouldn't be too hard to implement. I will try it next week.
>
> You could, I guess, wire a TLB entry to map the thread register into
> the highest virtual memory region of the machine (the top of 'kseg2'),
> which is accessible in a single instruction as a negative offset from
> $0.
Funny you should mention this. I was thinking about it
yesterday in this context as something else that I've seen
done in some non-Linux MIPS OSes, and something that
I think would be a better solution for CPU-specific fast
storage in SMP configurations than some of the hacks that
I've seen proposed for SMP MIPS/Linux so far.
WARNING: multiple messages have this Message-ID (diff)
From: "Kevin D. Kissell" <kevink@mips.com>
To: Dominic Sweetman <dom@algor.co.uk>, "H . J . Lu" <hjl@lucon.org>
Cc: Ulrich Drepper <drepper@redhat.com>,
GNU libc hacker <libc-hacker@sources.redhat.com>,
linux-mips@oss.sgi.com
Subject: Re: thread-ready ABIs
Date: Sat, 19 Jan 2002 23:21:21 +0100 [thread overview]
Message-ID: <002a01c1a137$a35340a0$0deca8c0@Ulysses> (raw)
Message-ID: <20020119222121.YZmr4tt4-Nqn2ah4BG75cTR0b1tr-aBxVUlwg9PhjUM@z> (raw)
In-Reply-To: 15433.26184.411289.161787@gladsmuir.algor.co.uk
> > > It would, in principle, be possible to save/restore k0
> > > or k1 (but not both) if no other clever solution can be found.
> > > There are other VM OSes that manage to do so for MIPS,
> > > for other outside-the-old-ABI reasons. It does, of course,
> > > add some instructions and some memory traffic to the
> > > low-level exception handling , and we would have to look
> > > at whether we would want to make such a feature standard
> > > or specific to a "thread-ready" kernel build.
> >
> > I like the read-only k0 idea. We just need to make a system call to
> > tell kernel what value to put in k0 before returning to the user space.
> > It shouldn't be too hard to implement. I will try it next week.
>
> You could, I guess, wire a TLB entry to map the thread register into
> the highest virtual memory region of the machine (the top of 'kseg2'),
> which is accessible in a single instruction as a negative offset from
> $0.
Funny you should mention this. I was thinking about it
yesterday in this context as something else that I've seen
done in some non-Linux MIPS OSes, and something that
I think would be a better solution for CPU-specific fast
storage in SMP configurations than some of the hacks that
I've seen proposed for SMP MIPS/Linux so far.
next prev parent reply other threads:[~2002-01-19 23:20 UTC|newest]
Thread overview: 94+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <m3elkoa5dw.fsf@myware.mynet>
2002-01-18 18:19 ` thread-ready ABIs H . J . Lu
2002-01-18 18:31 ` Ulrich Drepper
2002-01-18 19:08 ` H . J . Lu
2002-01-18 19:20 ` Ulrich Drepper
2002-01-19 12:14 ` Dominic Sweetman
2002-01-19 12:14 ` Dominic Sweetman
2002-01-20 0:14 ` Ralf Baechle
2002-01-18 20:03 ` Maciej W. Rozycki
2002-01-18 20:20 ` Ulrich Drepper
2002-01-18 20:50 ` Maciej W. Rozycki
2002-01-18 21:02 ` Ulrich Drepper
2002-01-18 21:35 ` Maciej W. Rozycki
2002-01-18 21:44 ` Ulrich Drepper
2002-01-18 22:17 ` Maciej W. Rozycki
2002-01-18 21:23 ` Daniel Jacobowitz
2002-01-19 0:35 ` Kevin D. Kissell
2002-01-19 0:35 ` Kevin D. Kissell
2002-01-19 4:11 ` H . J . Lu
2002-01-19 12:27 ` Dominic Sweetman
2002-01-19 19:42 ` H . J . Lu
2002-01-21 13:27 ` Maciej W. Rozycki
2002-01-19 22:21 ` Kevin D. Kissell [this message]
2002-01-19 22:21 ` Kevin D. Kissell
2002-01-20 10:38 ` Machida Hiroyuki
2002-01-20 11:58 ` Kevin D. Kissell
2002-01-20 11:58 ` Kevin D. Kissell
2002-01-20 13:16 ` Machida Hiroyuki
2002-01-22 6:27 ` patches for test-and-set without ll/sc (Re: thread-ready ABIs) Machida Hiroyuki
2002-01-22 6:37 ` Ulrich Drepper
2002-01-22 6:46 ` Machida Hiroyuki
2002-01-22 6:56 ` Ulrich Drepper
2002-01-24 9:56 ` Andreas Jaeger
2002-01-24 9:56 ` Andreas Jaeger
2002-01-20 19:19 ` thread-ready ABIs H . J . Lu
2002-01-21 9:39 ` Kevin D. Kissell
2002-01-21 9:39 ` Kevin D. Kissell
2002-01-21 13:56 ` Maciej W. Rozycki
2002-01-21 18:24 ` H . J . Lu
2002-01-21 18:36 ` Ulrich Drepper
2002-01-21 18:52 ` H . J . Lu
2002-01-21 18:58 ` H . J . Lu
2002-01-21 18:59 ` Daniel Jacobowitz
2002-01-21 19:05 ` H . J . Lu
2002-01-21 19:09 ` Daniel Jacobowitz
2002-01-21 19:18 ` H . J . Lu
2002-01-21 21:04 ` Kevin D. Kissell
2002-01-21 21:04 ` Kevin D. Kissell
2002-01-21 19:30 ` Geoff Keating
2002-01-21 21:07 ` Ulrich Drepper
2002-01-21 13:43 ` Maciej W. Rozycki
2002-01-20 0:24 ` Ralf Baechle
2002-01-21 23:22 ` Ulrich Drepper
2002-01-21 23:57 ` Kevin D. Kissell
2002-01-21 23:57 ` Kevin D. Kissell
2002-01-22 0:16 ` Ulrich Drepper
2002-01-22 0:16 ` Ulrich Drepper
2002-01-22 9:37 ` Dominic Sweetman
2002-01-22 9:37 ` Dominic Sweetman
2002-01-22 17:41 ` Ulrich Drepper
2002-01-22 17:41 ` Ulrich Drepper
2002-01-22 9:59 ` Dominic Sweetman
2002-01-22 9:59 ` Dominic Sweetman
2002-01-22 12:18 ` Kevin D. Kissell
2002-01-22 12:18 ` Kevin D. Kissell
2002-01-22 15:21 ` Daniel Jacobowitz
2002-01-22 15:44 ` Dominic Sweetman
2002-01-22 21:44 ` Tommy S. Christensen
2002-01-22 21:53 ` Kevin D. Kissell
2002-01-22 21:53 ` Kevin D. Kissell
2002-01-22 23:13 ` Kevin D. Kissell
2002-01-22 23:13 ` Kevin D. Kissell
2002-01-23 1:12 ` Jason Gunthorpe
2002-01-22 16:05 ` Kevin D. Kissell
2002-01-22 16:05 ` Kevin D. Kissell
2002-01-22 16:34 ` Daniel Jacobowitz
2002-01-22 17:08 ` Kevin D. Kissell
2002-01-22 17:08 ` Kevin D. Kissell
2002-01-22 17:13 ` Daniel Jacobowitz
2002-01-22 17:34 ` Kevin D. Kissell
2002-01-22 17:34 ` Kevin D. Kissell
2002-01-22 17:37 ` Daniel Jacobowitz
2002-01-22 17:47 ` Kevin D. Kissell
2002-01-22 17:47 ` Kevin D. Kissell
2002-01-22 17:57 ` Daniel Jacobowitz
2002-01-22 18:18 ` Kevin D. Kissell
2002-01-22 18:18 ` Kevin D. Kissell
2002-01-27 20:24 ` Alan Cox
2002-01-27 20:24 ` Alan Cox
2002-01-28 8:50 ` Kevin D. Kissell
2002-01-28 8:50 ` Kevin D. Kissell
2002-01-22 1:39 ` Richard Henderson
2002-01-18 21:24 Justin Carlson
2002-01-18 21:31 ` Ulrich Drepper
2002-01-18 21:42 ` Maciej W. Rozycki
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='002a01c1a137$a35340a0$0deca8c0@Ulysses' \
--to=kevink@mips.com \
--cc=dom@algor.co.uk \
--cc=drepper@redhat.com \
--cc=hjl@lucon.org \
--cc=libc-hacker@sources.redhat.com \
--cc=linux-mips@oss.sgi.com \
/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