Re: [PATCH 2/2] locking/percpu-rwsem: Introduce bias knob

From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: oleg@redhat.com, tj@kernel.org, paulmck@linux.vnet.ibm.com,
	john.stultz@linaro.org, dimitrysh@google.com, romlem@google.com,
	ccross@google.com, tkjos@google.com
Subject: Re: [PATCH 2/2] locking/percpu-rwsem: Introduce bias knob
Date: Thu, 14 Jul 2016 20:37:43 +0200	[thread overview]
Message-ID: <20160714183743.GK30154@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20160714183022.336211504@infradead.org>

On Thu, Jul 14, 2016 at 08:25:47PM +0200, Peter Zijlstra wrote:
> @@ -19,6 +20,13 @@ int __percpu_init_rwsem(struct percpu_rw
>  
>  	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
>  	rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
> +	if (bias == PERCPU_RWSEM_WRITER) {
> +		/*
> +		 * Disable rcu_sync() and force slow path.
> +		 */
> +		sem->rss.gp_count++;
> +		sem->rss.gp_state = !0;
> +	}
>  	__init_rwsem(&sem->rw_sem, name, rwsem_key);
>  	init_waitqueue_head(&sem->writer);
>  	sem->state = readers_slow;

So this seemed like a better deal than calling rcu_sync_enter(), because
that would still incur a (pointless) synchronize_sched() at init time
and people do tend to complain about things like that.