[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20140813105618.GI9918@twins.programming.kicks-ass.net>
Date: Wed, 13 Aug 2014 12:56:18 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc: linux-kernel@...r.kernel.org, mingo@...nel.org,
laijs@...fujitsu.com, dipankar@...ibm.com,
akpm@...ux-foundation.org, mathieu.desnoyers@...icios.com,
josh@...htriplett.org, tglx@...utronix.de, rostedt@...dmis.org,
dhowells@...hat.com, edumazet@...gle.com, dvhart@...ux.intel.com,
fweisbec@...il.com, oleg@...hat.com, bobby.prani@...il.com
Subject: Re: [PATCH v5 tip/core/rcu 14/16] rcu: Remove redundant
preempt_disable() from rcu_note_voluntary_context_switch()
On Mon, Aug 11, 2014 at 03:49:03PM -0700, Paul E. McKenney wrote:
> From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
>
> In theory, synchronize_sched() requires a read-side critical section to
> order against. In practice, preemption can be thought of as being
> disabled across every machine instruction. So this commit removes
> the redundant preempt_disable() from rcu_note_voluntary_context_switch().
> #define rcu_note_voluntary_context_switch(t) \
> do { \
> - preempt_disable(); /* Exclude synchronize_sched(); */ \
> if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
> ACCESS_ONCE((t)->rcu_tasks_holdout) = 0; \
> - preempt_enable(); \
> } while (0)
But that's more than 1 instruction.
Content of type "application/pgp-signature" skipped
Powered by blists - more mailing lists