linux-kernel - Re: [PATCH] locking/rwsem: simplify the is-owner-spinnable checks

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]

Date:   Fri, 18 May 2018 13:00:11 -0400
From:   Waiman Long <longman@...hat.com>
To:     Oleg Nesterov <oleg@...hat.com>, Ingo Molnar <mingo@...nel.org>
Cc:     Matthew Wilcox <willy@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
        Davidlohr Bueso <dave@...olabs.net>,
        "Theodore Y. Ts'o" <tytso@....edu>,
        Amir Goldstein <amir73il@...il.com>, Jan Kara <jack@...e.cz>
Subject: Re: [PATCH] locking/rwsem: simplify the is-owner-spinnable checks

On 05/18/2018 12:55 PM, Oleg Nesterov wrote:
> Add the trivial owner_on_cpu() helper for rwsem_can_spin_on_owner() and
> rwsem_spin_on_owner(), it also allows to make rwsem_can_spin_on_owner()
> a bit more clear.
>
> Signed-off-by: Oleg Nesterov <oleg@...hat.com>
> ---
>  kernel/locking/rwsem-xadd.c | 25 +++++++++++++------------
>  1 file changed, 13 insertions(+), 12 deletions(-)
>
> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> index a903367..3064c50 100644
> --- a/kernel/locking/rwsem-xadd.c
> +++ b/kernel/locking/rwsem-xadd.c
> @@ -347,6 +347,15 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
>  	}
>  }
>  
> +static inline bool owner_on_cpu(struct task_struct *owner)
> +{
> +	/*
> +	 * As lock holder preemption issue, we both skip spinning if
> +	 * task is not on cpu or its cpu is preempted
> +	 */
> +	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
> +}
> +
>  static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
>  {
>  	struct task_struct *owner;
> @@ -359,17 +368,10 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
>  
>  	rcu_read_lock();
>  	owner = READ_ONCE(sem->owner);
> -	if (!owner || !is_rwsem_owner_spinnable(owner)) {
> -		ret = !owner;	/* !owner is spinnable */
> -		goto done;
> +	if (owner) {
> +		ret = is_rwsem_owner_spinnable(owner) &&
> +		      owner_on_cpu(owner);
>  	}
> -
> -	/*
> -	 * As lock holder preemption issue, we both skip spinning if task is not
> -	 * on cpu or its cpu is preempted
> -	 */
> -	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
> -done:
>  	rcu_read_unlock();
>  	return ret;
>  }
> @@ -398,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
>  		 * abort spinning when need_resched or owner is not running or
>  		 * owner's cpu is preempted.
>  		 */
> -		if (!owner->on_cpu || need_resched() ||
> -				vcpu_is_preempted(task_cpu(owner))) {
> +		if (need_resched() || !owner_on_cpu(owner)) {
>  			rcu_read_unlock();
>  			return false;
>  		}

Acked-by: Waiman Long <longman@...hat.com>