[PATCH] sched: missing locking in sched_domains code

From: Heiko Carstens
Date: Sun Apr 27 2008 - 17:12:49 EST


From: Heiko Carstens <heiko.carstens@xxxxxxxxxx>

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 add a new sched_domains_mutex which protects these sections again.

Cc: Gautham R Shenoy <ego@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Paul Jackson <pj@xxxxxxx>
Signed-off-by: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
---
include/linux/sched.h | 2 ++
kernel/cpuset.c | 2 ++
kernel/sched.c | 11 +++++++++++
3 files changed, 15 insertions(+)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -7807,14 +7807,23 @@ match2:
unlock_doms_cur();
}

+/*
+ * Protects against concurrent calls to detach_destroy_domains
+ * and arch_init_sched_domains.
+ */
+DEFINE_MUTEX(sched_domains_mutex);
+
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
int arch_reinit_sched_domains(void)
{
+ static DEFINE_MUTEX(arch_reinit_sched_domains_mutex);
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;
@@ -7932,10 +7941,12 @@ 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);
Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -809,6 +809,8 @@ struct sched_domain {
#endif
};

+extern struct mutex sched_domains_mutex;
+
extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
struct sched_domain_attr *dattr_new);
extern int arch_reinit_sched_domains(void);
Index: linux-2.6/kernel/cpuset.c
===================================================================
--- linux-2.6.orig/kernel/cpuset.c
+++ linux-2.6/kernel/cpuset.c
@@ -684,7 +684,9 @@ restart:
rebuild:
/* Have scheduler rebuild sched domains */
get_online_cpus();
+ mutex_lock(&sched_domains_mutex);
partition_sched_domains(ndoms, doms, dattr);
+ mutex_unlock(&sched_domains_mutex);
put_online_cpus();

done:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/