From: Stephane Eranian <eranian@hpl.hp.com>
To: Arjan van de Ven <arjan@infradead.org>
Cc: linux-kernel@vger.kernel.org, ak@suse.de
Subject: Re: [PATCH 1/2] x86-64 TIF flags for debug regs and io bitmap in ctxsw
Date: Tue, 4 Jul 2006 01:10:55 -0700 [thread overview]
Message-ID: <20060704081055.GD5902@frankl.hpl.hp.com> (raw)
In-Reply-To: <1151999509.3109.6.camel@laptopd505.fenrus.org>
On Tue, Jul 04, 2006 at 09:51:49AM +0200, Arjan van de Ven wrote:
> > - }
> > - }
> > + if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW))
> > + || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))
> > + __switch_to_xtra(prev_p, next_p, tss);
>
> well isn't this replacing an if() (which isn't cheap but also not
> expensive, due to unlikely()) with an atomic operation (which *is*
> expensive) ?
>
> That to me doesn't make this sound like an actual win....
>
Although the two if were marked unlikely, you had to do the test anyway.
So you had to touch next->debugreg[7], next->io_bitmap_ptr, and prev->io_bitmap_ptr.
Now the first two are collapsed into one cache line in thread_info->flags.
Yet, I see your point about the test_tsk_thread_flag() and I am wondering if we
do need the atomicity in this case and whether we could simplify by using the
same expression as for next, i.e, task_thread_info(prev_p)->flags & TIF_IO_BITMAP?
--
-Stephane
next prev parent reply other threads:[~2006-07-04 8:19 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-04 7:28 [PATCH 1/2] x86-64 TIF flags for debug regs and io bitmap in ctxsw Stephane Eranian
2006-07-04 7:51 ` Arjan van de Ven
2006-07-04 8:09 ` Andi Kleen
2006-07-04 8:22 ` Arjan van de Ven
2006-07-04 8:10 ` Stephane Eranian [this message]
2006-07-04 8:14 ` Stephane Eranian
2006-07-04 8:14 ` Andi Kleen
2006-07-04 8:20 ` Stephane Eranian
-- strict thread matches above, loose matches on Subject: below --
2006-07-04 9:05 Mikael Pettersson
2006-07-04 10:22 ` Andi Kleen
2006-07-04 9:20 Mikael Pettersson
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=20060704081055.GD5902@frankl.hpl.hp.com \
--to=eranian@hpl.hp.com \
--cc=ak@suse.de \
--cc=arjan@infradead.org \
--cc=linux-kernel@vger.kernel.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.