linux-kernel - Re: [PATCH v12 10/11] sched: early boot clock

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20180625085543.GT2494@hirez.programming.kicks-ass.net>
Date:   Mon, 25 Jun 2018 10:55:43 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Pavel Tatashin <pasha.tatashin@...cle.com>
Cc:     steven.sistare@...cle.com, daniel.m.jordan@...cle.com,
        linux@...linux.org.uk, schwidefsky@...ibm.com,
        heiko.carstens@...ibm.com, john.stultz@...aro.org,
        sboyd@...eaurora.org, x86@...nel.org, linux-kernel@...r.kernel.org,
        mingo@...hat.com, tglx@...utronix.de, hpa@...or.com,
        douly.fnst@...fujitsu.com, prarit@...hat.com, feng.tang@...el.com,
        pmladek@...e.com, gnomes@...rguk.ukuu.org.uk,
        linux-s390@...r.kernel.org
Subject: Re: [PATCH v12 10/11] sched: early boot clock

On Thu, Jun 21, 2018 at 05:25:17PM -0400, Pavel Tatashin wrote:
> Allow sched_clock() to be used before schec_clock_init() and
> sched_clock_init_late() are called. This provides us with a way to get
> early boot timestamps on machines with unstable clocks.

There are !x86 architectures that use this code and might not expect to
have their sched_clock() called quite that early. Please verify.

> Signed-off-by: Pavel Tatashin <pasha.tatashin@...cle.com>
> ---
>  kernel/sched/clock.c | 10 ++++++++--
>  1 file changed, 8 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
> index 10c83e73837a..f034392b0f6c 100644
> --- a/kernel/sched/clock.c
> +++ b/kernel/sched/clock.c
> @@ -205,6 +205,11 @@ void clear_sched_clock_stable(void)
>   */
>  static int __init sched_clock_init_late(void)
>  {
> +	/* Transition to unstable clock from early clock */

This is wrong... or at least it smells horribly.

This is not the point where we transition from early to unstable, that
is in fact in sched_clock_init.

This function, sched_clock_init_late(), is where we attempt to
transition from unstable to stable. And this is _waaaay_ after SMP init.

> +	local_irq_disable();
> +	__gtod_offset = sched_clock() + __sched_clock_offset - ktime_get_ns();
> +	local_irq_enable();

This might work in sched_clock_init(), which is pre-SMP.

>  	sched_clock_running = 2;
>  	/*
>  	 * Ensure that it is impossible to not do a static_key update.
> @@ -350,8 +355,9 @@ u64 sched_clock_cpu(int cpu)
>  	if (sched_clock_stable())
>  		return sched_clock() + __sched_clock_offset;
>  
> -	if (unlikely(!sched_clock_running))
> -		return 0ull;
> +	/* Use early clock until sched_clock_init_late() */
> +	if (unlikely(sched_clock_running < 2))
> +		return sched_clock() + __sched_clock_offset;

And then this remains !sched_clock_running, except instead of 0, you
then return sched_clock() + __sched_clock_offset;

>  	preempt_disable_notrace();
>  	scd = cpu_sdc(cpu);