From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752949AbZHBNOJ (ORCPT ); Sun, 2 Aug 2009 09:14:09 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752951AbZHBNOI (ORCPT ); Sun, 2 Aug 2009 09:14:08 -0400 Received: from hera.kernel.org ([140.211.167.34]:33857 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752687AbZHBNOF (ORCPT ); Sun, 2 Aug 2009 09:14:05 -0400 Date: Sun, 2 Aug 2009 13:13:25 GMT From: tip-bot for Gregory Haskins To: linux-tip-commits@vger.kernel.org Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com, a.p.zijlstra@chello.nl, peterz@infradead.org, maxk@qualcomm.com, tglx@linutronix.de, ghaskins@novell.com, mingo@elte.hu Reply-To: mingo@redhat.com, hpa@zytor.com, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl, peterz@infradead.org, maxk@qualcomm.com, tglx@linutronix.de, ghaskins@novell.com, mingo@elte.hu In-Reply-To: <20090730145723.25226.24493.stgit@dev.haskins.net> References: <20090730145723.25226.24493.stgit@dev.haskins.net> Subject: [tip:sched/core] sched: Fully integrate cpus_active_map and root-domain code Message-ID: Git-Commit-ID: 00aec93d10a051ea64f83eff75d4065a19508ea6 X-Mailer: tip-git-log-daemon MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.0 (hera.kernel.org [127.0.0.1]); Sun, 02 Aug 2009 13:13:26 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 00aec93d10a051ea64f83eff75d4065a19508ea6 Gitweb: http://git.kernel.org/tip/00aec93d10a051ea64f83eff75d4065a19508ea6 Author: Gregory Haskins AuthorDate: Thu, 30 Jul 2009 10:57:23 -0400 Committer: Ingo Molnar CommitDate: Sun, 2 Aug 2009 14:26:12 +0200 sched: Fully integrate cpus_active_map and root-domain code Reflect "active" cpus in the rq->rd->online field, instead of the online_map. The motivation is that things that use the root-domain code (such as cpupri) only care about cpus classified as "active" anyway. By synchronizing the root-domain state with the active map, we allow several optimizations. For instance, we can remove an extra cpumask_and from the scheduler hotpath by utilizing rq->rd->online (since it is now a cached version of cpu_active_map & rq->rd->span). Signed-off-by: Gregory Haskins Acked-by: Peter Zijlstra Acked-by: Max Krasnyansky Signed-off-by: Peter Zijlstra LKML-Reference: <20090730145723.25226.24493.stgit@dev.haskins.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- kernel/sched_fair.c | 10 +++++++--- kernel/sched_rt.c | 7 ------- 3 files changed, 8 insertions(+), 11 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 613fee5..475138c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7927,7 +7927,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) rq->rd = rd; cpumask_set_cpu(rq->cpu, rd->span); - if (cpumask_test_cpu(rq->cpu, cpu_online_mask)) + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) set_rq_online(rq); spin_unlock_irqrestore(&rq->lock, flags); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 652e8bd..4934729 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1046,17 +1046,21 @@ static void yield_task_fair(struct rq *rq) * search starts with cpus closest then further out as needed, * so we always favor a closer, idle cpu. * Domains may include CPUs that are not usable for migration, - * hence we need to mask them out (cpu_active_mask) + * hence we need to mask them out (rq->rd->online) * * Returns the CPU we should wake onto. */ #if defined(ARCH_HAS_SCHED_WAKE_IDLE) + +#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online) + static int wake_idle(int cpu, struct task_struct *p) { struct sched_domain *sd; int i; unsigned int chosen_wakeup_cpu; int this_cpu; + struct rq *task_rq = task_rq(p); /* * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu @@ -1089,10 +1093,10 @@ static int wake_idle(int cpu, struct task_struct *p) for_each_domain(cpu, sd) { if ((sd->flags & SD_WAKE_IDLE) || ((sd->flags & SD_WAKE_IDLE_FAR) - && !task_hot(p, task_rq(p)->clock, sd))) { + && !task_hot(p, task_rq->clock, sd))) { for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) { - if (cpu_active(i) && idle_cpu(i)) { + if (cpu_rd_active(i, task_rq) && idle_cpu(i)) { if (i != task_cpu(p)) { schedstat_inc(p, se.nr_wakeups_idle); diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index a8f89bc..13f728e 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1173,13 +1173,6 @@ static int find_lowest_rq(struct task_struct *task) return -1; /* No targets found */ /* - * Only consider CPUs that are usable for migration. - * I guess we might want to change cpupri_find() to ignore those - * in the first place. - */ - cpumask_and(lowest_mask, lowest_mask, cpu_active_mask); - - /* * At this point we have built a mask of cpus representing the * lowest priority tasks in the system. Now we want to elect * the best one based on our affinity and topology.