sched: fix missing locking in sched_domains code

Concurrent calls to detach_destroy_domains and arch_init_sched_domains
were prevented by the old scheduler subsystem cpu hotplug mutex. When
this got converted to get_online_cpus() the locking got broken.
Unlike before now several processes can concurrently enter the critical
sections that were protected by the old lock.

So use the already present doms_cur_mutex to protect these sections again.

Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 12 insertions, 17 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 8f433fe..561b3b3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -242,6 +242,12 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 }
 #endif
 
+/*
+ * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
 #ifdef CONFIG_GROUP_SCHED
 
 #include <linux/cgroup.h>
@@ -308,9 +314,6 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
-/* doms_cur_mutex serializes access to doms_cur[] array */
-static DEFINE_MUTEX(doms_cur_mutex);
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
@@ -358,21 +361,9 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 }
 
-static inline void lock_doms_cur(void)
-{
-	mutex_lock(&doms_cur_mutex);
-}
-
-static inline void unlock_doms_cur(void)
-{
-	mutex_unlock(&doms_cur_mutex);
-}
-
 #else
 
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline void lock_doms_cur(void) { }
-static inline void unlock_doms_cur(void) { }
 
 #endif	/* CONFIG_GROUP_SCHED */
 
@@ -7822,7 +7813,7 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 {
 	int i, j;
 
-	lock_doms_cur();
+	mutex_lock(&sched_domains_mutex);
 
 	/* always unregister in case we don't destroy any domains */
 	unregister_sched_domain_sysctl();
@@ -7871,7 +7862,7 @@ match2:
 
 	register_sched_domain_sysctl();
 
-	unlock_doms_cur();
+	mutex_unlock(&sched_domains_mutex);
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -7880,8 +7871,10 @@ int arch_reinit_sched_domains(void)
 	int err;
 
 	get_online_cpus();
+	mutex_lock(&sched_domains_mutex);
 	detach_destroy_domains(&cpu_online_map);
 	err = arch_init_sched_domains(&cpu_online_map);
+	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
 
 	return err;
@@ -7999,10 +7992,12 @@ void __init sched_init_smp(void)
 	BUG_ON(sched_group_nodes_bycpu == NULL);
 #endif
 	get_online_cpus();
+	mutex_lock(&sched_domains_mutex);
 	arch_init_sched_domains(&cpu_online_map);
 	cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
 	if (cpus_empty(non_isolated_cpus))
 		cpu_set(smp_processor_id(), non_isolated_cpus);
+	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
 	/* XXX: Theoretical race here - CPU may be hotplugged now */
 	hotcpu_notifier(update_sched_domains, 0);