cpuset: fix possible races in cpu/memory hotplug

Change to cpuset->cpus_allowed and cpuset->mems_allowed should be protected
by callback_mutex, otherwise the reader may read wrong cpus/mems. This is
cpuset's lock rule.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ee5ec386aa8b548dc07758789d54da17be241174..31737957cb6207be7459225c6fa7b4083f6330c7 100644 (file)
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2070,7 +2070,9 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
        }
 
        cgroup_lock();
+       mutex_lock(&callback_mutex);
        cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+       mutex_unlock(&callback_mutex);
        scan_for_empty_cpusets(&top_cpuset);
        ndoms = generate_sched_domains(&doms, &attr);
        cgroup_unlock();
@@ -2093,11 +2095,12 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
        cgroup_lock();
        switch (action) {
        case MEM_ONLINE:
-               top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-               break;
        case MEM_OFFLINE:
+               mutex_lock(&callback_mutex);
                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-               scan_for_empty_cpusets(&top_cpuset);
+               mutex_unlock(&callback_mutex);
+               if (action == MEM_OFFLINE)
+                       scan_for_empty_cpusets(&top_cpuset);
                break;
        default:
                break;