From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759699AbYFSMhl (ORCPT ); Thu, 19 Jun 2008 08:37:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758460AbYFSMfg (ORCPT ); Thu, 19 Jun 2008 08:35:36 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:44117 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758286AbYFSMfd (ORCPT ); Thu, 19 Jun 2008 08:35:33 -0400 Message-Id: <20080619123314.049253081@chello.nl> References: <20080619122218.971447669@chello.nl> User-Agent: quilt/0.46-1 Date: Thu, 19 Jun 2008 14:22:23 +0200 From: Peter Zijlstra To: LKML Cc: Ingo Molnar , "Daniel K." , Peter Zijlstra Subject: [PATCH 05/10] sched: rt-bandwidth: fix cpu-hotplug interaction Content-Disposition: inline; filename=sched-rt_bandwidth-vs-hotplug.patch X-Bad-Reply: References but no 'Re:' in Subject. Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Restore the bandwidth to offlining cpus so we don't leak/gain bandwidth. Signed-off-by: Peter Zijlstra --- kernel/sched.c | 15 +++++-- kernel/sched_rt.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 114 insertions(+), 9 deletions(-) Index: linux-2.6/kernel/sched_rt.c =================================================================== --- linux-2.6.orig/kernel/sched_rt.c +++ linux-2.6/kernel/sched_rt.c @@ -280,6 +280,9 @@ static int balance_runtime(struct rt_rq continue; spin_lock(&iter->rt_runtime_lock); + if (iter->rt_runtime == RUNTIME_INF) + goto next; + diff = iter->rt_runtime - iter->rt_time; if (diff > 0) { do_div(diff, weight); @@ -293,12 +296,104 @@ static int balance_runtime(struct rt_rq break; } } +next: spin_unlock(&iter->rt_runtime_lock); } spin_unlock(&rt_b->rt_runtime_lock); return more; } + +static void __disable_runtime(struct rq *rq) +{ + struct root_domain *rd = rq->rd; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_leaf_rt_rq(rt_rq, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + s64 want; + int i; + + spin_lock(&rt_b->rt_runtime_lock); + spin_lock(&rt_rq->rt_runtime_lock); + if (rt_rq->rt_runtime == RUNTIME_INF || + rt_rq->rt_runtime == rt_b->rt_runtime) + goto balanced; + spin_unlock(&rt_rq->rt_runtime_lock); + + want = rt_b->rt_runtime - rt_rq->rt_runtime; + + for_each_cpu_mask(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + if (iter == rt_rq) + continue; + + spin_lock(&iter->rt_runtime_lock); + if (want > 0) { + diff = min_t(s64, iter->rt_runtime, want); + iter->rt_runtime -= diff; + want -= diff; + } else { + iter->rt_runtime -= want; + want -= want; + } + spin_unlock(&iter->rt_runtime_lock); + + if (!want) + break; + } + + spin_lock(&rt_rq->rt_runtime_lock); + BUG_ON(want); +balanced: + rt_rq->rt_runtime = RUNTIME_INF; + spin_unlock(&rt_rq->rt_runtime_lock); + spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static void disable_runtime(struct rq *rq) +{ + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __disable_runtime(rq); + spin_unlock_irqrestore(&rq->lock, flags); +} + +static void __enable_runtime(struct rq *rq) +{ + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_leaf_rt_rq(rt_rq, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + spin_lock(&rt_b->rt_runtime_lock); + spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_b->rt_runtime; + rt_rq->rt_time = 0; + spin_unlock(&rt_rq->rt_runtime_lock); + spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static void enable_runtime(struct rq *rq) +{ + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __enable_runtime(rq); + spin_unlock_irqrestore(&rq->lock, flags); +} + #endif static inline int rt_se_prio(struct sched_rt_entity *rt_se) @@ -328,14 +423,13 @@ static int sched_rt_runtime_exceeded(str #ifdef CONFIG_SMP if (rt_rq->rt_time > runtime) { - int more; - spin_unlock(&rt_rq->rt_runtime_lock); - more = balance_runtime(rt_rq); + balance_runtime(rt_rq); spin_lock(&rt_rq->rt_runtime_lock); - if (more) - runtime = sched_rt_runtime(rt_rq); + runtime = sched_rt_runtime(rt_rq); + if (runtime == RUNTIME_INF) + return 0; } #endif @@ -1166,6 +1260,8 @@ static void join_domain_rt(struct rq *rq { if (rq->rt.overloaded) rt_set_overload(rq); + + __enable_runtime(rq); } /* Assumes rq->lock is held */ @@ -1173,6 +1269,8 @@ static void leave_domain_rt(struct rq *r { if (rq->rt.overloaded) rt_clear_overload(rq); + + __disable_runtime(rq); } /* Index: linux-2.6/kernel/sched.c =================================================================== --- linux-2.6.orig/kernel/sched.c +++ linux-2.6/kernel/sched.c @@ -7461,20 +7461,27 @@ int sched_create_sysfs_power_savings_ent static int update_sched_domains(struct notifier_block *nfb, unsigned long action, void *hcpu) { + int cpu = (int)(long)hcpu; + switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: + disable_runtime(cpu_rq(cpu)); + /* fall-through */ + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: detach_destroy_domains(&cpu_online_map); return NOTIFY_OK; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: case CPU_ONLINE: case CPU_ONLINE_FROZEN: + enable_runtime(cpu_rq(cpu)); + /* fall-through */ + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: /* --