Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751496AbaG0Bep (ORCPT ); Sat, 26 Jul 2014 21:34:45 -0400 Received: from mail-la0-f47.google.com ([209.85.215.47]:50165 "EHLO mail-la0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751309AbaG0Beo (ORCPT ); Sat, 26 Jul 2014 21:34:44 -0400 MIME-Version: 1.0 In-Reply-To: <20140725233623.GA18537@linux.vnet.ibm.com> References: <20140725233623.GA18537@linux.vnet.ibm.com> From: Pranith Kumar Date: Sat, 26 Jul 2014 21:34:11 -0400 Message-ID: Subject: Re: [PATCH RFC tip/core/rcu] Fix attempt to avoid offloading callbacks unless requested To: Paul McKenney Cc: LKML , Ingo Molnar , Lai Jiangshan , Dipankar Sarma , Andrew Morton , Mathieu Desnoyers , Josh Triplett , tglx@linutronix.de, Peter Zijlstra , Steven Rostedt , David Howells , Eric Dumazet , dvhart@linux.intel.com, =?UTF-8?B?RnLDqWTDqXJpYyBXZWlzYmVja2Vy?= , Oleg Nesterov , Sasha Levin Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jul 25, 2014 at 7:36 PM, Paul E. McKenney wrote: > [ Note: This applies on top of commit 187497fa5e9e (rcu: Allow for NULL > tick_nohz_full_mask when nohz_full= missing) in -tip > or -rcu. To make this work on top of rcu/next, move the > call to rcu_organize_nocb_kthreads(rsp) to the end of the > for_each_rcu_flavor(rsp) loop in rcu_init_nohz(). ] > > Commit b58cc46c5f6b (rcu: Don't offload callbacks unless specifically > requested) failed to adjust the callback lists of the CPUs that are > known to be no-CBs CPUs only because they are also nohz_full= CPUs. > This failure can result in callbacks that are posted during early boot > getting stranded on nxtlist for CPUs whose no-CBs property becomes > apparent late, and there can also be spurious warnings about offline > CPUs posting callbacks. > > This commit fixes these problems by adding an early-boot rcu_init_nohz() > that properly initializes the no-CBs CPUs. > > Note that kernels built with CONFIG_RCU_NOCB_CPU_ALL=y or with > CONFIG_RCU_NOCB_CPU=n do not exhibit this bug. Neither do kernels > booted without the nohz_full= boot parameter. > > Signed-off-by: Paul E. McKenney Please note one change below, with that Reviewed-by: Pranith Kumar > > diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h > index d231aa17b1d7..cc7bed1c90dc 100644 > --- a/include/linux/rcupdate.h > +++ b/include/linux/rcupdate.h > @@ -269,6 +269,14 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev, > struct task_struct *next) { } > #endif /* CONFIG_RCU_USER_QS */ > > +#ifdef CONFIG_RCU_NOCB_CPU > +void rcu_init_nohz(void); > +#else /* #ifdef CONFIG_RCU_NOCB_CPU */ > +static inline void rcu_init_nohz(void) > +{ > +} > +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ > + > /** > * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers > * @a: Code that RCU needs to pay attention to. > diff --git a/init/main.c b/init/main.c > index e8ae1fef0908..5d8c83ae6c55 100644 > --- a/init/main.c > +++ b/init/main.c > @@ -577,6 +577,7 @@ asmlinkage __visible void __init start_kernel(void) > idr_init_cache(); > rcu_init(); > tick_nohz_init(); > + rcu_init_nohz(); > context_tracking_init(); > radix_tree_init(); > /* init some links before init_ISA_irqs() */ > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h > index 00dc411e9676..095d6e4d2fd7 100644 > --- a/kernel/rcu/tree_plugin.h > +++ b/kernel/rcu/tree_plugin.h > @@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void) > pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); > if (nr_cpu_ids != NR_CPUS) > pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); > -#ifdef CONFIG_RCU_NOCB_CPU > -#ifndef CONFIG_RCU_NOCB_CPU_NONE > - if (!have_rcu_nocb_mask) { > - zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); > - have_rcu_nocb_mask = true; > - } > -#ifdef CONFIG_RCU_NOCB_CPU_ZERO > - pr_info("\tOffload RCU callbacks from CPU 0\n"); > - cpumask_set_cpu(0, rcu_nocb_mask); > -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ > -#ifdef CONFIG_RCU_NOCB_CPU_ALL > - pr_info("\tOffload RCU callbacks from all CPUs\n"); > - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); > -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ > -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ > - if (have_rcu_nocb_mask) { > - if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { > - pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); > - cpumask_and(rcu_nocb_mask, cpu_possible_mask, > - rcu_nocb_mask); > - } > - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); > - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); > - if (rcu_nocb_poll) > - pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); > - } > -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ > } > > #ifdef CONFIG_TREE_PREEMPT_RCU > @@ -2451,6 +2424,66 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) > trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty")); > } > > +void rcu_init_nohz(void) > +{ > + int cpu; > + bool need_rcu_nocb_mask = true; > + struct rcu_state *rsp; > + > +#ifdef CONFIG_RCU_NOCB_CPU_NONE > + need_rcu_nocb_mask = false; > +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ > + > +#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) > + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) > + need_rcu_nocb_mask = true; > +#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ > + > + if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { > + zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); > + have_rcu_nocb_mask = true; > + } > + if (!have_rcu_nocb_mask) > + return; > + > +#ifdef CONFIG_RCU_NOCB_CPU_ZERO > + pr_info("\tOffload RCU callbacks from CPU 0\n"); > + cpumask_set_cpu(0, rcu_nocb_mask); > +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ > +#ifdef CONFIG_RCU_NOCB_CPU_ALL > + pr_info("\tOffload RCU callbacks from all CPUs\n"); > + cpumask_copy(rcu_nocb_mask, cpu_possible_mask); > +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ > +#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) > + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); > +#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ I think we can still come here when there is garbage in tick_nohz_full_mask. So checking again for tick_nohz_full_running is necessary before cpumask_or(). > + > + if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { > + pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); > + cpumask_and(rcu_nocb_mask, cpu_possible_mask, > + rcu_nocb_mask); > + } > + cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); > + pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); > + if (rcu_nocb_poll) > + pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); > + > + for_each_rcu_flavor(rsp) { > + for_each_cpu(cpu, rcu_nocb_mask) { > + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); > + > + /* > + * If there are early callbacks, they will need > + * to be moved to the nocb lists. > + */ > + WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] != > + &rdp->nxtlist && > + rdp->nxttail[RCU_NEXT_TAIL] != NULL); > + init_nocb_callback_list(rdp); > + } > + } > +} > + > /* Initialize per-rcu_data variables for no-CBs CPUs. */ > static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) > { > @@ -2479,10 +2512,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) > > if (rcu_nocb_mask == NULL) > return; > -#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) > - if (tick_nohz_full_running) > - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); > -#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ > if (ls == -1) { > ls = int_sqrt(nr_cpu_ids); > rcu_nocb_leader_stride = ls; > -- Pranith -- 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/