sched: Deal with non-atomic min_vruntime reads on 32bits

In order to avoid reading partial updated min_vruntime values on 32bit
implement a seqcount like solution.

Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20110405152729.111378493@chello.nl
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 46f42ca..7a5eb26 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -312,6 +312,9 @@ struct cfs_rq {
 
        u64 exec_clock;
        u64 min_vruntime;
+#ifndef CONFIG_64BIT
+       u64 min_vruntime_copy;
+#endif
 
        struct rb_root tasks_timeline;
        struct rb_node *rb_leftmost;

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ad4c414..054cebb 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -358,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
        }
 
        cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+#ifndef CONFIG_64BIT
+       smp_wmb();
+       cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
+#endif
 }
 
 /*
@@ -1376,10 +1380,21 @@ static void task_waking_fair(struct task_struct *p)
 {
        struct sched_entity *se = &p->se;
        struct cfs_rq *cfs_rq = cfs_rq_of(se);
+       u64 min_vruntime;
 
-       lockdep_assert_held(&task_rq(p)->lock);
+#ifndef CONFIG_64BIT
+       u64 min_vruntime_copy;
 
-       se->vruntime -= cfs_rq->min_vruntime;
+       do {
+               min_vruntime_copy = cfs_rq->min_vruntime_copy;
+               smp_rmb();
+               min_vruntime = cfs_rq->min_vruntime;
+       } while (min_vruntime != min_vruntime_copy);
+#else
+       min_vruntime = cfs_rq->min_vruntime;
+#endif
+
+       se->vruntime -= min_vruntime;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED