Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S936847Ab3DIHQs (ORCPT ); Tue, 9 Apr 2013 03:16:48 -0400 Received: from mail-bk0-f46.google.com ([209.85.214.46]:55616 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S935220Ab3DIHQq (ORCPT ); Tue, 9 Apr 2013 03:16:46 -0400 MIME-Version: 1.0 In-Reply-To: References: <1364996263-12198-1-git-send-email-vincent.guittot@linaro.org> Date: Tue, 9 Apr 2013 09:16:45 +0200 Message-ID: Subject: Re: [PATCH Resend v5] sched: fix init NOHZ_IDLE flag From: Vincent Guittot To: Frederic Weisbecker Cc: LKML , "linaro-kernel@lists.linaro.org" , Peter Zijlstra , Ingo Molnar , Steven Rostedt , Mike Galbraith Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7470 Lines: 187 On 4 April 2013 19:30, Vincent Guittot wrote: > On 4 April 2013 19:07, Frederic Weisbecker wrote: >> 2013/4/3 Vincent Guittot : >>> On my smp platform which is made of 5 cores in 2 clusters, I have the >>> nr_busy_cpu field of sched_group_power struct that is not null when the >>> platform is fully idle. The root cause is: >>> During the boot sequence, some CPUs reach the idle loop and set their >>> NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus >>> field is initialized later with the assumption that all CPUs are in the busy >>> state whereas some CPUs have already set their NOHZ_IDLE flag. >>> >>> More generally, the NOHZ_IDLE flag must be initialized when new sched_domains >>> are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. >>> >>> This condition can be ensured by adding a synchronize_rcu between the >>> destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE >>> flag will not be updated with old sched_domain once it has been initialized. >>> But this solution introduces a additionnal latency in the rebuild sequence >>> that is called during cpu hotplug. >>> >>> As suggested by Frederic Weisbecker, another solution is to have the same >>> rcu lifecycle for both NOHZ_IDLE and sched_domain struct. I have introduce >>> a new sched_domain_rq struct that is the entry point for both sched_domains >>> and objects that must follow the same lifecycle like NOHZ_IDLE flags. They >>> will share the same RCU lifecycle and will be always synchronized. >>> >>> The synchronization is done at the cost of : >>> - an additional indirection for accessing the first sched_domain level >>> - an additional indirection and a rcu_dereference before accessing to the >>> NOHZ_IDLE flag. >>> >>> Change since v4: >>> - link both sched_domain and NOHZ_IDLE flag in one RCU object so >>> their states are always synchronized. >>> >>> Change since V3; >>> - NOHZ flag is not cleared if a NULL domain is attached to the CPU >>> - Remove patch 2/2 which becomes useless with latest modifications >>> >>> Change since V2: >>> - change the initialization to idle state instead of busy state so a CPU that >>> enters idle during the build of the sched_domain will not corrupt the >>> initialization state >>> >>> Change since V1: >>> - remove the patch for SCHED softirq on an idle core use case as it was >>> a side effect of the other use cases. >>> >>> Signed-off-by: Vincent Guittot >>> --- >>> include/linux/sched.h | 6 +++ >>> kernel/sched/core.c | 105 ++++++++++++++++++++++++++++++++++++++++++++----- >>> kernel/sched/fair.c | 35 +++++++++++------ >>> kernel/sched/sched.h | 24 +++++++++-- >>> 4 files changed, 145 insertions(+), 25 deletions(-) >>> >>> diff --git a/include/linux/sched.h b/include/linux/sched.h >>> index d35d2b6..2a52188 100644 >>> --- a/include/linux/sched.h >>> +++ b/include/linux/sched.h >>> @@ -959,6 +959,12 @@ struct sched_domain { >>> unsigned long span[0]; >>> }; >>> >>> +struct sched_domain_rq { >>> + struct sched_domain *sd; >>> + unsigned long flags; >>> + struct rcu_head rcu; /* used during destruction */ >>> +}; >>> + >>> static inline struct cpumask *sched_domain_span(struct sched_domain *sd) >>> { >>> return to_cpumask(sd->span); >>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c >>> index 7f12624..69e2313 100644 >>> --- a/kernel/sched/core.c >>> +++ b/kernel/sched/core.c >>> @@ -5602,6 +5602,15 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) >>> destroy_sched_domain(sd, cpu); >>> } >>> >>> +static void destroy_sched_domain_rq(struct sched_domain_rq *sd_rq, int cpu) >>> +{ >>> + if (!sd_rq) >>> + return; >>> + >>> + destroy_sched_domains(sd_rq->sd, cpu); >>> + kfree_rcu(sd_rq, rcu); >>> +} >>> + >>> /* >>> * Keep a special pointer to the highest sched_domain that has >>> * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this >>> @@ -5632,10 +5641,23 @@ static void update_top_cache_domain(int cpu) >>> * hold the hotplug lock. >>> */ >>> static void >>> -cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) >>> +cpu_attach_domain(struct sched_domain_rq *sd_rq, struct root_domain *rd, >>> + int cpu) >>> { >>> struct rq *rq = cpu_rq(cpu); >>> - struct sched_domain *tmp; >>> + struct sched_domain_rq *tmp_rq; >>> + struct sched_domain *tmp, *sd = NULL; >>> + >>> + /* >>> + * If we don't have any sched_domain and associated object, we can >>> + * directly jump to the attach sequence otherwise we try to degenerate >>> + * the sched_domain >>> + */ >>> + if (!sd_rq) >>> + goto attach; >>> + >>> + /* Get a pointer to the 1st sched_domain */ >>> + sd = sd_rq->sd; >>> >>> /* Remove the sched domains which do not contribute to scheduling. */ >>> for (tmp = sd; tmp; ) { >>> @@ -5658,14 +5680,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) >>> destroy_sched_domain(tmp, cpu); >>> if (sd) >>> sd->child = NULL; >>> + /* update sched_domain_rq */ >>> + sd_rq->sd = sd; >>> } >>> >>> +attach: >>> sched_domain_debug(sd, cpu); >>> >>> rq_attach_root(rq, rd); >>> - tmp = rq->sd; >>> - rcu_assign_pointer(rq->sd, sd); >>> - destroy_sched_domains(tmp, cpu); >>> + tmp_rq = rq->sd_rq; >>> + rcu_assign_pointer(rq->sd_rq, sd_rq); >>> + destroy_sched_domain_rq(tmp_rq, cpu); >>> >>> update_top_cache_domain(cpu); >>> } >>> @@ -5695,12 +5720,14 @@ struct sd_data { >>> }; >>> >>> struct s_data { >>> + struct sched_domain_rq ** __percpu sd_rq; >>> struct sched_domain ** __percpu sd; >>> struct root_domain *rd; >>> }; >>> >>> enum s_alloc { >>> sa_rootdomain, >>> + sa_sd_rq, >>> sa_sd, >>> sa_sd_storage, >>> sa_none, >>> @@ -5935,7 +5962,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) >>> return; >>> >>> update_group_power(sd, cpu); >>> - atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); >>> + atomic_set(&sg->sgp->nr_busy_cpus, 0); >> >> Is it possible that we can be dealing here with a >> sched_group/sched_group_power that is used on another CPU (from that >> CPU's rq->rq_sd->sd) concurrently? >> When we call build_sched_groups(), we might reuse an exisiting struct >> sched_group used elsewhere right? If so, is there a race with the >> above initialization? > > No we are not reusing an existing struct, the > sched_group/sched_group_power that is initialized here, has just been > created by __visit_domain_allocation_hell in build_sched_domains. The > sched_group/sched_group_power is not already attached to any CPU > Hi Frederic, Does it answer your concern and do you have more comments about the patch? Vincent > Vincent -- 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/