From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756609AbZETRT3 (ORCPT ); Wed, 20 May 2009 13:19:29 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752132AbZETRTV (ORCPT ); Wed, 20 May 2009 13:19:21 -0400 Received: from hera.kernel.org ([140.211.167.34]:48358 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753970AbZETRTU (ORCPT ); Wed, 20 May 2009 13:19:20 -0400 Date: Wed, 20 May 2009 17:18:46 GMT From: tip-bot for Peter Zijlstra To: linux-tip-commits@vger.kernel.org Cc: linux-kernel@vger.kernel.org, acme@redhat.com, paulus@samba.org, hpa@zytor.com, mingo@redhat.com, jkacur@redhat.com, a.p.zijlstra@chello.nl, mtosatti@redhat.com, tglx@linutronix.de, cjashfor@linux.vnet.ibm.com, mingo@elte.hu Reply-To: mingo@redhat.com, hpa@zytor.com, paulus@samba.org, acme@redhat.com, linux-kernel@vger.kernel.org, jkacur@redhat.com, a.p.zijlstra@chello.nl, mtosatti@redhat.com, tglx@linutronix.de, cjashfor@linux.vnet.ibm.com, mingo@elte.hu In-Reply-To: <20090520102553.237504544@chello.nl> References: <20090520102553.237504544@chello.nl> Subject: [tip:perfcounters/core] perf_counter: Solve the rotate_ctx vs inherit race differently Message-ID: Git-Commit-ID: d7b629a34fc4134a43c730b5f0197855dc4948d0 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]); Wed, 20 May 2009 17:18:47 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: d7b629a34fc4134a43c730b5f0197855dc4948d0 Gitweb: http://git.kernel.org/tip/d7b629a34fc4134a43c730b5f0197855dc4948d0 Author: Peter Zijlstra AuthorDate: Wed, 20 May 2009 12:21:19 +0200 Committer: Ingo Molnar CommitDate: Wed, 20 May 2009 12:43:32 +0200 perf_counter: Solve the rotate_ctx vs inherit race differently Instead of disabling RR scheduling of the counters, use a different list that does not get rotated to iterate the counters on inheritance. [ Impact: cleanup, optimization ] Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Corey Ashford Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Marcelo Tosatti Cc: John Kacur LKML-Reference: <20090520102553.237504544@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 1 - kernel/perf_counter.c | 15 +++++---------- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 13cb2fb..c8c1dfc 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -508,7 +508,6 @@ struct perf_counter_context { int nr_counters; int nr_active; int is_active; - int rr_allowed; struct task_struct *task; /* diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 4d8f973..64113e6 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -1120,8 +1120,7 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu) __perf_counter_task_sched_out(ctx); rotate_ctx(&cpuctx->ctx); - if (ctx->rr_allowed) - rotate_ctx(ctx); + rotate_ctx(ctx); perf_counter_cpu_sched_in(cpuctx, cpu); perf_counter_task_sched_in(curr, cpu); @@ -3109,7 +3108,6 @@ __perf_counter_init_context(struct perf_counter_context *ctx, mutex_init(&ctx->mutex); INIT_LIST_HEAD(&ctx->counter_list); INIT_LIST_HEAD(&ctx->event_list); - ctx->rr_allowed = 1; ctx->task = task; } @@ -3350,14 +3348,14 @@ void perf_counter_init_task(struct task_struct *child) */ mutex_lock(&parent_ctx->mutex); - parent_ctx->rr_allowed = 0; - barrier(); /* irqs */ - /* * We dont have to disable NMIs - we are only looking at * the list, not manipulating it: */ - list_for_each_entry(counter, &parent_ctx->counter_list, list_entry) { + list_for_each_entry_rcu(counter, &parent_ctx->event_list, event_entry) { + if (counter != counter->group_leader) + continue; + if (!counter->hw_event.inherit) continue; @@ -3366,9 +3364,6 @@ void perf_counter_init_task(struct task_struct *child) break; } - barrier(); /* irqs */ - parent_ctx->rr_allowed = 1; - mutex_unlock(&parent_ctx->mutex); }