From mboxrd@z Thu Jan  1 00:00:00 1970
From: will.deacon@arm.com (Will Deacon)
Date: Thu, 19 Mar 2015 16:00:09 +0000
Subject: [PATCH] arm64: percpu: Make this_cpu accessors pre-empt safe
In-Reply-To: <20150319154435.GC25967@leverpostej>
References: <1426776751-20526-1-git-send-email-steve.capper@linaro.org>
 <20150319154435.GC25967@leverpostej>
Message-ID: <20150319160008.GA4751@arm.com>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

On Thu, Mar 19, 2015 at 03:44:36PM +0000, Mark Rutland wrote:
> On Thu, Mar 19, 2015 at 02:52:31PM +0000, Steve Capper wrote:
> > this_cpu operations were implemented for arm64 in:
> >  5284e1b arm64: xchg: Implement cmpxchg_double
> >  f97fc81 arm64: percpu: Implement this_cpu operations
> > 
> > Unfortunately, it is possible for pre-emption to take place between
> > address generation and data access. This can lead to cases where data
> > is being manipulated by this_cpu for a different CPU than it was
> > called on. Which effectively breaks the spec.
> > 
> > This patch disables pre-emption for the this_cpu operations
> > guaranteeing that address generation and data manipulation.
> 
> Shouldn't that last sentence end with "occur on the same CPU", or
> something like that?
> 
> [...]
> 
> > +/*
> > + * Modules aren't allowed to use preempt_enable_no_resched, and it is
> > + * undef'ed. If we are unable to use preempt_enable_no_resched, then
> > + * fallback to the standard preempt_enable.
> > + */
> > +#ifdef preempt_enable_no_resched
> > +#define __pcp_preempt_enable()	preempt_enable_no_resched()
> > +#else
> > +#define __pcp_preempt_enable()	preempt_enable()
> > +#endif /* preempt_enable_no_resched */
> 
> I think it would be worth mentioning in the comment why we want to use
> preempt_enable_no_resched where possible (e.g. read-modify-cmpxchg
> sequences where we want to have as few retries as possible).

Hmm, I'm not sure I agree with that. In the interest of throughput, I can
understand that you want to minimise the retries but since preempt kernels
are all about minimising latency then actually scheduling when a cmpxchg
loop fail sounds pretty ideal to me.

Why can't we just use preempt_enable?

Will