From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755800Ab1EOIdX (ORCPT ); Sun, 15 May 2011 04:33:23 -0400 Received: from e1.ny.us.ibm.com ([32.97.182.141]:44600 "EHLO e1.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755330Ab1EOIdV (ORCPT ); Sun, 15 May 2011 04:33:21 -0400 Date: Sun, 15 May 2011 01:33:18 -0700 From: "Paul E. McKenney" To: Cheng Xu Cc: Peter Zijlstra , Ingo Molnar , LKML Subject: Re: [PATCH v2] sched: rt_rq runtime leakage bug fix Message-ID: <20110515083318.GJ2258@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <4DCE1F12.6040609@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4DCE1F12.6040609@linux.vnet.ibm.com> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, May 14, 2011 at 02:20:02PM +0800, Cheng Xu wrote: > This patch is to fix the real-time scheduler bug reported at > https://lkml.org/lkml/2011/4/26/13. That is, when running multiple real-time > threads on every logical CPUs and then turning off one CPU, the kernel will > bug at function __disable_runtime(). > > Function __disable_runtime() bugs and reports leakage of rt_rq runtime. The > root cause is __disable_runtime() assumes it iterates through all the existing > rt_rq's while walking rq->leaf_rt_rq_list, which actually contains only > runnable rt_rq's. This problem also applies to __enable_runtime() and > print_rt_stats(). > > The patch is based on above analysis, appears to fix the problem, but is only > lightly tested. > > Reported-by: Paul E. McKenney > Signed-off-by: Cheng Xu Works for me! Tested-by: Paul E. McKenney > --- > kernel/sched_rt.c | 22 +++++++++++++++++++--- > 1 files changed, 19 insertions(+), 3 deletions(-) > > diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c > index e7cebdc..f8fcf82 100644 > --- a/kernel/sched_rt.c > +++ b/kernel/sched_rt.c > @@ -183,6 +183,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) > return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); > } > > +typedef struct task_group *rt_rq_iter_t; > + > +#define for_each_rt_rq(rt_rq, iter, rq) \ > + for (iter = list_entry_rcu(task_groups.next, typeof(*iter), list); \ > + (&iter->list != &task_groups) && \ > + (rt_rq = iter->rt_rq[cpu_of(rq)]); \ > + iter = list_entry_rcu(iter->list.next, typeof(*iter), list)) > + > static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) > { > list_add_rcu(&rt_rq->leaf_rt_rq_list, > @@ -288,6 +296,11 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) > return ktime_to_ns(def_rt_bandwidth.rt_period); > } > > +typedef struct rt_rq *rt_rq_iter_t; > + > +#define for_each_rt_rq(rt_rq, iter, rq) \ > + for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL) > + > static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) > { > } > @@ -402,12 +415,13 @@ next: > static void __disable_runtime(struct rq *rq) > { > struct root_domain *rd = rq->rd; > + rt_rq_iter_t iter; > struct rt_rq *rt_rq; > > if (unlikely(!scheduler_running)) > return; > > - for_each_leaf_rt_rq(rt_rq, rq) { > + for_each_rt_rq(rt_rq, iter, rq) { > struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); > s64 want; > int i; > @@ -487,6 +501,7 @@ static void disable_runtime(struct rq *rq) > > static void __enable_runtime(struct rq *rq) > { > + rt_rq_iter_t iter; > struct rt_rq *rt_rq; > > if (unlikely(!scheduler_running)) > @@ -495,7 +510,7 @@ static void __enable_runtime(struct rq *rq) > /* > * Reset each runqueue's bandwidth settings > */ > - for_each_leaf_rt_rq(rt_rq, rq) { > + for_each_rt_rq(rt_rq, iter, rq) { > struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); > > raw_spin_lock(&rt_b->rt_runtime_lock); > @@ -1796,10 +1811,11 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); > > static void print_rt_stats(struct seq_file *m, int cpu) > { > + rt_rq_iter_t iter; > struct rt_rq *rt_rq; > > rcu_read_lock(); > - for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu)) > + for_each_rt_rq(rt_rq, iter, cpu_rq(cpu)) > print_rt_rq(m, cpu, rt_rq); > rcu_read_unlock(); > } > -- > 1.7.1 >