Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760255Ab3EBPxn (ORCPT ); Thu, 2 May 2013 11:53:43 -0400 Received: from ja.ssi.bg ([178.16.129.10]:44353 "EHLO ja.ssi.bg" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1759204Ab3EBPxl (ORCPT ); Thu, 2 May 2013 11:53:41 -0400 Date: Thu, 2 May 2013 18:54:05 +0300 (EEST) From: Julian Anastasov To: Peter Zijlstra cc: Simon Horman , Eric Dumazet , Ingo Molnar , "Paul E. McKenney" , lvs-devel@vger.kernel.org, netdev@vger.kernel.org, netfilter-devel@vger.kernel.org, linux-kernel@vger.kernel.org, Pablo Neira Ayuso , Dipankar Sarma Subject: Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper In-Reply-To: <20130502072623.GE7521@dyad.programming.kicks-ass.net> Message-ID: References: <1367290378-29224-1-git-send-email-horms@verge.net.au> <1367290378-29224-2-git-send-email-horms@verge.net.au> <20130430072944.GA13959@verge.net.au> <20130501091012.GB28253@dyad.programming.kicks-ass.net> <20130501155501.GB7521@dyad.programming.kicks-ass.net> <20130502072623.GE7521@dyad.programming.kicks-ass.net> User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4606 Lines: 156 Hello, On Thu, 2 May 2013, Peter Zijlstra wrote: > On Wed, May 01, 2013 at 09:22:08PM +0300, Julian Anastasov wrote: > > > +extern int __cond_resched_rcu(void); > > > + > > > +#define cond_resched_rcu() ({ \ > > > + __might_sleep(__FILE__, __LINE__, 0); \ > > > > I see your goal. But digging into __might_sleep() > > I see that rcu_sleep_check() will scream for the non-preempt > > case because we are under rcu_read_lock. > > > #ifdef CONFIG_PREEMPT_RCU > #define PREEMPT_RCU_OFFSET 0 > #else > #define PREEMPT_RCU_OFFSET 1 > #endif > > #define cond_resched_rcu() ({ \ > __might_sleep(__FILE__, __LINE__, PREEMPT_RCU_OFFSET); \ > __cond_resched_rcu(); \ > }) > > Should work I think.. I implemented your idea. I tested the following patch in 2 variants, TINY_RCU and CONFIG_TREE_PREEMPT_RCU. I see the error if extra rcu_read_lock is added for testing. I'm using the PREEMPT_ACTIVE flag to indicate that we are already under lock. It should work because __might_sleep is not called with such bit. I also tried to add new flag in include/linux/hardirq.h but PREEMPT_ACTIVE depends on the arch, so this alternative looked difficult to implement. include/linux/rcupdate.h | 7 ++++--- include/linux/sched.h | 14 ++++++++++++++ kernel/sched/core.c | 20 ++++++++++++++++++-- 3 files changed, 36 insertions(+), 5 deletions(-) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b758ce1..b594759 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -480,9 +480,10 @@ static inline void rcu_preempt_sleep_check(void) } #endif /* #else #ifdef CONFIG_PROVE_RCU */ -#define rcu_sleep_check() \ +#define rcu_sleep_check(locked) \ do { \ - rcu_preempt_sleep_check(); \ + if (!(locked)) \ + rcu_preempt_sleep_check(); \ rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh" \ " read-side critical section"); \ @@ -494,7 +495,7 @@ static inline void rcu_preempt_sleep_check(void) #else /* #ifdef CONFIG_PROVE_RCU */ #define rcu_lockdep_assert(c, s) do { } while (0) -#define rcu_sleep_check() do { } while (0) +#define rcu_sleep_check(locked) do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ diff --git a/include/linux/sched.h b/include/linux/sched.h index e692a02..027deea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2608,6 +2608,20 @@ extern int __cond_resched_softirq(void); __cond_resched_softirq(); \ }) +#ifdef CONFIG_PREEMPT_RCU +#define PREEMPT_RCU_OFFSET 1 +#else +#define PREEMPT_RCU_OFFSET PREEMPT_CHECK_OFFSET +#endif + +extern int __cond_resched_rcu(void); + +#define cond_resched_rcu() ({ \ + __might_sleep(__FILE__, __LINE__, PREEMPT_ACTIVE | \ + PREEMPT_RCU_OFFSET); \ + __cond_resched_rcu(); \ +}) + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPT, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 67d0465..2724be7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2793,7 +2793,7 @@ static inline void schedule_debug(struct task_struct *prev) */ if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) __schedule_bug(prev); - rcu_sleep_check(); + rcu_sleep_check(0); profile_hit(SCHED_PROFILING, __builtin_return_address(0)); @@ -4364,6 +4364,20 @@ int __sched __cond_resched_softirq(void) } EXPORT_SYMBOL(__cond_resched_softirq); +int __sched __cond_resched_rcu(void) +{ +#ifndef CONFIG_PREEMPT_RCU + if (should_resched()) { + rcu_read_unlock(); + __cond_resched(); + rcu_read_lock(); + return 1; + } +#endif + return 0; +} +EXPORT_SYMBOL(__cond_resched_rcu); + /** * yield - yield the current processor to other threads. * @@ -7062,7 +7076,9 @@ void __might_sleep(const char *file, int line, int preempt_offset) { static unsigned long prev_jiffy; /* ratelimiting */ - rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + /* WARN_ON_ONCE() by default, no rate limit reqd. */ + rcu_sleep_check(preempt_offset & PREEMPT_ACTIVE); + preempt_offset &= ~PREEMPT_ACTIVE; if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || system_state != SYSTEM_RUNNING || oops_in_progress) return; -- 1.7.3.4 Regards -- Julian Anastasov -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/