Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20200414150556.10920-1-qais.yousef@arm.com> <20200414150556.10920-3-qais.yousef@arm.com>
 <20200414121956.3687d6e9@gandalf.local.home> <20200415093617.GZ20730@hirez.programming.kicks-ass.net>
 <20200420154317.klwoztvdybmvykwe@e107158-lin.cambridge.arm.com>
In-Reply-To: <20200420154317.klwoztvdybmvykwe@e107158-lin.cambridge.arm.com>
From:   Josh Don <joshdon@google.com>
Date:   Mon, 20 Apr 2020 14:36:49 -0700
Message-ID: <CABk29NskBLS+s2J-FjzdmnrxvKR_+zQ1GxGkgiui=A1b-fvXtQ@mail.gmail.com>
Subject: Re: [PATCH 2/4] cpumask: Make cpumask_any() truly random
To:     Qais Yousef <qais.yousef@arm.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Andrew Morton <akpm@linux-foundation.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Yury Norov <yury.norov@gmail.com>,
        Paul Turner <pjt@google.com>,
        Alexey Dobriyan <adobriyan@gmail.com>,
        Pavan Kondeti <pkondeti@codeaurora.org>,
        linux-kernel <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Apr 20, 2020 at 8:43 AM Qais Yousef <qais.yousef@arm.com> wrote:
>
> On 04/15/20 11:36, Peter Zijlstra wrote:
> > On Tue, Apr 14, 2020 at 12:19:56PM -0400, Steven Rostedt wrote:
> > > Do we care if this gets preempted and migrated to a new CPU where we read
> > > "prev" from one distribute_cpu_mask_prev on one CPU and write it to another
> > > CPU?
> >
> > I don't think we do; that just adds to the randomness ;-), but you do
>
> Yep we don't care and it should enhance the randomness.
>
> > raise a good point in that __this_cpu_*() ops assume preemption is
> > already disabled, which is true of the one exiting
> > cpumask_any_and_distribute() caller, but is no longer true after patch
> > 1, and this patch repeats the mistake.
> >
> > So either we need to disable preemption across the function or
> > transition to this_cpu_*() ops.
>
> Sorry wasn't aware about the preemption check in __this_cpu_write().
>
> Transitioning to this_cpu_write() makes sense. Unless Josh comes back it'll
> break something he noticed.

Yep, this_cpu_* makes sense to me.  Preemption is ok, since prev must
always be a valid cpu id, thus we just get a little more _random_ from
this pseudorandom implementation.