LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Steven Rostedt <email@example.com>
To: Peter Zijlstra <firstname.lastname@example.org>
Cc: LKML <email@example.com>,
"Ingo Molnar" <firstname.lastname@example.org>,
"Thomas Gleixner" <email@example.com>,
"Clark Williams" <firstname.lastname@example.org>,
"Mike Galbraith" <email@example.com>,
"Paul E. McKenney" <firstname.lastname@example.org>,
"Jörn Engel" <email@example.com>,
"Oleg Nesterov" <firstname.lastname@example.org>
Subject: Re: [RFC][PATCH v2] sched/rt: Use IPI to trigger RT task push migration instead of pulling
Date: Thu, 26 Feb 2015 09:00:55 -0500 [thread overview]
Message-ID: <email@example.com> (raw)
On Thu, 26 Feb 2015 14:47:54 +0100
Peter Zijlstra <firstname.lastname@example.org> wrote:
> > Thinking about this more, is it because a wmb just forces the CPU to
> > write everything before this before it writes anything after it. That
> > is, the writes themselves can happen at a much later time. Does a plain
> > mb() work the same way if there are no reads required?
> No, neither smp_wmb nor smp_mb are required to flush the store buffers.
Heh, that's what I said :-) "That is, the writes themselves can happen
at a much later time."
> The only thing barriers do is guarantee order, this can be done by
> flushing store buffers but it can also be done by making sure store
> buffers flush writes in the 'right' order.
> Nor does an rmb help anything with ordering against a possible store
> buffer flush. Again rmb only guarantees two loads are issued in that
> particular order, it doesn't disallow the CPU speculating the load at
> > What about using atomic_t?
> > Note, my latest code doesn't have any of this, but I just want to
> > understand the semantics of these operations a bit better.
> Nope, atomic_t doesn't help here either. Atomics only make sure the RmW
> cycle is atomic.
> Note that even if wmb or mb did flush the store buffer, you would still
> have a race here.
Oh, it wasn't that I meant to remove the race. I was just trying to
make that race smaller.
But this is all academic now, as my last version doesn't do any of this.
next prev parent reply other threads:[~2015-02-26 14:01 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-24 18:39 Steven Rostedt
2015-02-24 18:45 ` Steven Rostedt
2015-02-24 21:23 ` Steven Rostedt
2015-02-25 10:35 ` Peter Zijlstra
2015-02-25 15:51 ` Steven Rostedt
2015-02-25 17:11 ` Peter Zijlstra
2015-02-25 17:41 ` Peter Zijlstra
2015-02-25 17:50 ` Steven Rostedt
2015-02-26 7:45 ` Peter Zijlstra
2015-02-26 12:43 ` Steven Rostedt
2015-02-26 13:47 ` Peter Zijlstra
2015-02-26 14:00 ` Steven Rostedt [this message]
2015-02-26 7:49 ` Peter Zijlstra
2015-02-26 12:46 ` Steven Rostedt
2015-02-25 7:56 Hillf Danton
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:
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--subject='Re: [RFC][PATCH v2] sched/rt: Use IPI to trigger RT task push migration instead of pulling' \
* 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).