From mboxrd@z Thu Jan  1 00:00:00 1970
From: Ingo Molnar <mingo@elte.hu>
Subject: Re: [PATCH 4/6] kvm tools: Add rwlock wrapper
Date: Sat, 28 May 2011 20:32:59 +0200
Message-ID: <20110528183259.GA15019@elte.hu>
References: <alpine.DEB.2.00.1105261901470.5480@tiger>
 <1306426743.3065.34.camel@lappy>
 <20110526180518.GA3572@elte.hu>
 <4DDE97CE.4000302@redhat.com>
 <BANLkTi=bMMr1zHWhwNsD=ah52n3ueoLbUg@mail.gmail.com>
 <20110526202531.GA2765@elte.hu>
 <20110526230508.GA15983@Krystal>
 <20110527102533.GA24608@elte.hu>
 <20110527110729.GA26920@elte.hu>
 <4DE13AF0.2080001@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Pekka Enberg <penberg@kernel.org>,
	Sasha Levin <levinsasha928@gmail.com>, john@jfloren.net,
	kvm@vger.kernel.org, asias.hejun@gmail.com, gorcunov@gmail.com,
	prasadjoshi124@gmail.com,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Avi Kivity <avi@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx2.mail.elte.hu ([157.181.151.9]:48836 "EHLO mx2.mail.elte.hu"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1754879Ab1E1SdP (ORCPT <rfc822;kvm@vger.kernel.org>);
	Sat, 28 May 2011 14:33:15 -0400
Content-Disposition: inline
In-Reply-To: <4DE13AF0.2080001@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>


* Avi Kivity <avi@redhat.com> wrote:

> > So if you set a notification signal via fcntl(F_SETOWN) on the 
> > scheduler context switch event fd, the user-space RCU code will 
> > get a signal on every context switch.
> 
> Context switches are completely uninteresting for userspace rcu:
> 
>   rcu_read_lock();
>   ---> context switch
> 
> have we learned anything from that?  no.  User code is always 
> preemptible and migratable.  If rcu_read_lock() prevented migration 
> somehow, then we'd know that a context switch means we've started a 
> grace period for this thread.  But it doesn't, so we don't.

Well, in the next mail i mentioned that we can do migration events as 
well, which would be useful: instead of having to keep track of 
nr_tasks RCU grace periods we could simplify it down to nr_cpus.

But if we indexed by the TID then we wouldnt need any scheduler 
bindings at all - this is the simpler approach.

> What's needed are explicit notifications about grace periods.  For 
> the vcpu threads, calling KVM_VCPU_RUN seems like a good point.  
> For I/O threads, completion of processing of an event is also a 
> good point.

Grace period notifications are needed too, obviously.

Thanks,

	Ingo