Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753203Ab3IQOaZ (ORCPT ); Tue, 17 Sep 2013 10:30:25 -0400 Received: from merlin.infradead.org ([205.233.59.134]:48990 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752790Ab3IQOaY (ORCPT ); Tue, 17 Sep 2013 10:30:24 -0400 Date: Tue, 17 Sep 2013 16:30:03 +0200 From: Peter Zijlstra To: Mel Gorman Cc: Rik van Riel , Srikar Dronamraju , Ingo Molnar , Andrea Arcangeli , Johannes Weiner , Linux-MM , LKML , Oleg Nesterov , Paul McKenney , Thomas Gleixner , Steven Rostedt Subject: [PATCH] hotplug: Optimize {get,put}_online_cpus() Message-ID: <20130917143003.GA29354@twins.programming.kicks-ass.net> References: <1378805550-29949-1-git-send-email-mgorman@suse.de> <1378805550-29949-38-git-send-email-mgorman@suse.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1378805550-29949-38-git-send-email-mgorman@suse.de> User-Agent: Mutt/1.5.21 (2012-12-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5929 Lines: 220 Subject: hotplug: Optimize {get,put}_online_cpus() From: Peter Zijlstra Date: Tue Sep 17 16:17:11 CEST 2013 The cpu hotplug lock is a purely reader biased read-write lock. The current implementation uses global state, change it so the reader side uses per-cpu state in the uncontended fast-path. Cc: Oleg Nesterov Cc: Paul McKenney Cc: Thomas Gleixner Cc: Steven Rostedt Signed-off-by: Peter Zijlstra --- include/linux/cpu.h | 33 ++++++++++++++- kernel/cpu.c | 108 ++++++++++++++++++++++++++-------------------------- 2 files changed, 87 insertions(+), 54 deletions(-) --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -16,6 +16,7 @@ #include #include #include +#include struct device; @@ -175,8 +176,36 @@ extern struct bus_type cpu_subsys; extern void cpu_hotplug_begin(void); extern void cpu_hotplug_done(void); -extern void get_online_cpus(void); -extern void put_online_cpus(void); + +extern struct task_struct *__cpuhp_writer; +DECLARE_PER_CPU(unsigned int, __cpuhp_refcount); + +extern void __get_online_cpus(void); + +static inline void get_online_cpus(void) +{ + might_sleep(); + + this_cpu_inc(__cpuhp_refcount); + /* + * Order the refcount inc against the writer read; pairs with the full + * barrier in cpu_hotplug_begin(). + */ + smp_mb(); + if (unlikely(__cpuhp_writer)) + __get_online_cpus(); +} + +extern void __put_online_cpus(void); + +static inline void put_online_cpus(void) +{ + barrier(); + this_cpu_dec(__cpuhp_refcount); + if (unlikely(__cpuhp_writer)) + __put_online_cpus(); +} + extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -49,88 +49,92 @@ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU -static struct { - struct task_struct *active_writer; - struct mutex lock; /* Synchronizes accesses to refcount, */ - /* - * Also blocks the new readers during - * an ongoing cpu hotplug operation. - */ - int refcount; -} cpu_hotplug = { - .active_writer = NULL, - .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), - .refcount = 0, -}; +struct task_struct *__cpuhp_writer = NULL; +EXPORT_SYMBOL_GPL(__cpuhp_writer); + +DEFINE_PER_CPU(unsigned int, __cpuhp_refcount); +EXPORT_PER_CPU_SYMBOL_GPL(__cpuhp_refcount); -void get_online_cpus(void) +static DECLARE_WAIT_QUEUE_HEAD(cpuhp_wq); + +void __get_online_cpus(void) { - might_sleep(); - if (cpu_hotplug.active_writer == current) + if (__cpuhp_writer == current) return; - mutex_lock(&cpu_hotplug.lock); - cpu_hotplug.refcount++; - mutex_unlock(&cpu_hotplug.lock); +again: + /* + * Ensure a pending reading has a 0 refcount. + * + * Without this a new reader that comes in before cpu_hotplug_begin() + * reads the refcount will deadlock. + */ + this_cpu_dec(__cpuhp_refcount); + wait_event(cpuhp_wq, !__cpuhp_writer); + + this_cpu_inc(__cpuhp_refcount); + /* + * See get_online_cpu(). + */ + smp_mb(); + if (unlikely(__cpuhp_writer)) + goto again; } -EXPORT_SYMBOL_GPL(get_online_cpus); +EXPORT_SYMBOL_GPL(__get_online_cpus); -void put_online_cpus(void) +void __put_online_cpus(void) { - if (cpu_hotplug.active_writer == current) - return; - mutex_lock(&cpu_hotplug.lock); + unsigned int refcnt = 0; + int cpu; - if (WARN_ON(!cpu_hotplug.refcount)) - cpu_hotplug.refcount++; /* try to fix things up */ + if (__cpuhp_writer == current) + return; - if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) - wake_up_process(cpu_hotplug.active_writer); - mutex_unlock(&cpu_hotplug.lock); + for_each_possible_cpu(cpu) + refcnt += per_cpu(__cpuhp_refcount, cpu); + if (!refcnt) + wake_up_process(__cpuhp_writer); } -EXPORT_SYMBOL_GPL(put_online_cpus); +EXPORT_SYMBOL_GPL(__put_online_cpus); /* * This ensures that the hotplug operation can begin only when the * refcount goes to zero. * - * Note that during a cpu-hotplug operation, the new readers, if any, - * will be blocked by the cpu_hotplug.lock - * * Since cpu_hotplug_begin() is always called after invoking * cpu_maps_update_begin(), we can be sure that only one writer is active. - * - * Note that theoretically, there is a possibility of a livelock: - * - Refcount goes to zero, last reader wakes up the sleeping - * writer. - * - Last reader unlocks the cpu_hotplug.lock. - * - A new reader arrives at this moment, bumps up the refcount. - * - The writer acquires the cpu_hotplug.lock finds the refcount - * non zero and goes to sleep again. - * - * However, this is very difficult to achieve in practice since - * get_online_cpus() not an api which is called all that often. - * */ void cpu_hotplug_begin(void) { - cpu_hotplug.active_writer = current; + __cpuhp_writer = current; for (;;) { - mutex_lock(&cpu_hotplug.lock); - if (likely(!cpu_hotplug.refcount)) + unsigned int refcnt = 0; + int cpu; + + /* + * Order the setting of writer against the reading of refcount; + * pairs with the full barrier in get_online_cpus(). + */ + + set_current_state(TASK_UNINTERRUPTIBLE); + + for_each_possible_cpu(cpu) + refcnt += per_cpu(__cpuhp_refcount, cpu); + + if (!refcnt) break; - __set_current_state(TASK_UNINTERRUPTIBLE); - mutex_unlock(&cpu_hotplug.lock); + schedule(); } + __set_current_state(TASK_RUNNING); } void cpu_hotplug_done(void) { - cpu_hotplug.active_writer = NULL; - mutex_unlock(&cpu_hotplug.lock); + __cpuhp_writer = NULL; + wake_up_all(&cpuhp_wq); } /* -- 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/