sched/numa: Prevent parallel updates to group stats during placement

Having multiple tasks in a group go through task_numa_placement
simultaneously can lead to a task picking a wrong node to run on, because
the group stats may be in the middle of an update. This patch avoids
parallel updates by holding the numa_group lock during placement
decisions.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-52-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c4df2de..1473499 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1233,6 +1233,7 @@ static void task_numa_placement(struct task_struct *p)
 {
        int seq, nid, max_nid = -1, max_group_nid = -1;
        unsigned long max_faults = 0, max_group_faults = 0;
+       spinlock_t *group_lock = NULL;
 
        seq = ACCESS_ONCE(p->mm->numa_scan_seq);
        if (p->numa_scan_seq == seq)
@@ -1241,6 +1242,12 @@ static void task_numa_placement(struct task_struct *p)
        p->numa_migrate_seq++;
        p->numa_scan_period_max = task_scan_max(p);
 
+       /* If the task is part of a group prevent parallel updates to group stats */
+       if (p->numa_group) {
+               group_lock = &p->numa_group->lock;
+               spin_lock(group_lock);
+       }
+
        /* Find the node with the highest number of faults */
        for_each_online_node(nid) {
                unsigned long faults = 0, group_faults = 0;
@@ -1279,20 +1286,24 @@ static void task_numa_placement(struct task_struct *p)
                }
        }
 
-       /*
-        * If the preferred task and group nids are different,
-        * iterate over the nodes again to find the best place.
-        */
-       if (p->numa_group && max_nid != max_group_nid) {
-               unsigned long weight, max_weight = 0;
-
-               for_each_online_node(nid) {
-                       weight = task_weight(p, nid) + group_weight(p, nid);
-                       if (weight > max_weight) {
-                               max_weight = weight;
-                               max_nid = nid;
+       if (p->numa_group) {
+               /*
+                * If the preferred task and group nids are different,
+                * iterate over the nodes again to find the best place.
+                */
+               if (max_nid != max_group_nid) {
+                       unsigned long weight, max_weight = 0;
+
+                       for_each_online_node(nid) {
+                               weight = task_weight(p, nid) + group_weight(p, nid);
+                               if (weight > max_weight) {
+                                       max_weight = weight;
+                                       max_nid = nid;
+                               }
                        }
                }
+
+               spin_unlock(group_lock);
        }
 
        /* Preferred node as the node with the most faults */