cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node

commit 5ab116c9349ef52d6fbd2e2917a53f13194b048e upstream.

cpuset_mem_spread_node() returns an offline node, and causes an oops.

This patch fixes it by initializing task->mems_allowed to
node_states[N_HIGH_MEMORY], and updating task->mems_allowed when doing
memory hotplug.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Reported-by: Nick Piggin <npiggin@suse.de>
Tested-by: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/init/main.c b/init/main.c
index 4be7de2a78b69fc92d184b46ed035ff32cce413d..bc109c70648677829584ce702d6d32d9e7953996 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -846,7 +846,7 @@ static int __init kernel_init(void * unused)
        /*
         * init can allocate pages on any node
         */
-       set_mems_allowed(node_possible_map);
+       set_mems_allowed(node_states[N_HIGH_MEMORY]);
        /*
         * init can run on any cpu.
         */

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 39e5121a78a6933d469e0207ff175dbae44afa18..a81a91010c9f91da7c55f8068146949f53925de5 100644 (file)
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -921,9 +921,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
  *    call to guarantee_online_mems(), as we know no one is changing
  *    our task's cpuset.
  *
- *    Hold callback_mutex around the two modifications of our tasks
- *    mems_allowed to synchronize with cpuset_mems_allowed().
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -1392,11 +1389,10 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
 
        if (cs == &top_cpuset) {
                cpumask_copy(cpus_attach, cpu_possible_mask);
-               to = node_possible_map;
        } else {
                guarantee_online_cpus(cs, cpus_attach);
-               guarantee_online_mems(cs, &to);
        }
+       guarantee_online_mems(cs, &to);
 
        /* do per-task migration stuff possibly for each in the threadgroup */
        cpuset_attach_task(tsk, &to, cs);
@@ -2091,15 +2087,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 static int cpuset_track_online_nodes(struct notifier_block *self,
                                unsigned long action, void *arg)
 {
+       nodemask_t oldmems;
+
        cgroup_lock();
        switch (action) {
        case MEM_ONLINE:
-       case MEM_OFFLINE:
+               oldmems = top_cpuset.mems_allowed;
                mutex_lock(&callback_mutex);
                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
                mutex_unlock(&callback_mutex);
-               if (action == MEM_OFFLINE)
-                       scan_for_empty_cpusets(&top_cpuset);
+               update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
+               break;
+       case MEM_OFFLINE:
+               /*
+                * needn't update top_cpuset.mems_allowed explicitly because
+                * scan_for_empty_cpusets() will update it.
+                */
+               scan_for_empty_cpusets(&top_cpuset);
                break;
        default:
                break;

diff --git a/kernel/kthread.c b/kernel/kthread.c
index ab7ae57773e1b41f263407eb4a3bad1c95b41289..84027cfffccf05b412fe8261351e7dee28dc23a2 100644 (file)
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -196,7 +196,7 @@ int kthreadd(void *unused)
        set_task_comm(tsk, "kthreadd");
        ignore_signals(tsk);
        set_cpus_allowed_ptr(tsk, cpu_all_mask);
-       set_mems_allowed(node_possible_map);
+       set_mems_allowed(node_states[N_HIGH_MEMORY]);
 
        current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;