In order to avoid reading partial updated min_vruntime values on 32bit implement a seqcount like solution. Signed-off-by: Peter Zijlstra Reviewed-by: Frank Rowand --- kernel/sched.c | 3 +++ kernel/sched_fair.c | 19 +++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) Index: linux-2.6/kernel/sched.c =================================================================== --- linux-2.6.orig/kernel/sched.c +++ linux-2.6/kernel/sched.c @@ -313,6 +313,9 @@ 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; Index: linux-2.6/kernel/sched_fair.c =================================================================== --- linux-2.6.orig/kernel/sched_fair.c +++ linux-2.6/kernel/sched_fair.c @@ -365,6 +365,10 @@ static void update_min_vruntime(struct c } 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 } /* @@ -1342,10 +1346,21 @@ static void task_waking_fair(struct task { 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