linux-kernel - Re: [PATCH] percpu-refcount: Use normal instead of RCU-sched"

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20191107091319.6zf5tmdi54amtann@linutronix.de>
Date:   Thu, 7 Nov 2019 10:13:19 +0100
From:   Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To:     linux-kernel@...r.kernel.org
Cc:     Dennis Zhou <dennis@...nel.org>, Tejun Heo <tj@...nel.org>,
        Christoph Lameter <cl@...ux.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Peter Zijlstra <peterz@...radead.org>,
        "Paul E. McKenney" <paulmck@...nel.org>
Subject: Re: [PATCH] percpu-refcount: Use normal instead of RCU-sched"

On 2019-10-02 13:22:53 [+0200], To linux-kernel@...r.kernel.org wrote:
> This is a revert of commit
>    a4244454df129 ("percpu-refcount: use RCU-sched insted of normal RCU")
> 
> which claims the only reason for using RCU-sched is
>    "rcu_read_[un]lock() … are slightly more expensive than preempt_disable/enable()"
> 
> and
>     "As the RCU critical sections are extremely short, using sched-RCU
>     shouldn't have any latency implications."
> 
> The problem with using RCU-sched here is that it disables preemption and
> the callback must not acquire any sleeping locks like spinlock_t on
> PREEMPT_RT which is the case with some of the users.
> 
> Using rcu_read_lock() on PREEMPTION=n kernels is not any different
> compared to rcu_read_lock_sched(). On PREEMPTION=y kernels there are
> already performance issues due to additional preemption points.
> Looking at the code, the rcu_read_lock() is just an increment and unlock
> is almost just a decrement unless there is something special to do. Both
> are functions while disabling preemption is inlined.
> Doing a small benchmark, the minimal amount of time required was mostly
> the same. The average time required was higher due to the higher MAX
> value (which could be preemption). With DEBUG_PREEMPT=y it is
> rcu_read_lock_sched() that takes a little longer due to the additional
> debug code.
> 
> Convert back to normal RCU.

a gentle ping.

> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
> ---
> 
> Benchmark https://breakpoint.cc/percpu_test.patch


Sebastian