Messages in this thread Patch in this message | | | Date | Mon, 16 May 2011 20:55:51 +0800 | Subject | [PATCH] sched: fix priority leakage in pick_next_highest_task_rt() | From | Hillf Danton <> |
| |
When picking the second highest RT task for a given runqueue, if no task found after scanning the queue of priority == idx, the next idx should also be checked even in case that next is already existing, or the window of priority leakage could be opened.
Signed-off-by: Hillf Danton <dhillf@gmail.com> ---
--- a/kernel/sched_rt.c 2011-04-27 11:48:50.000000000 +0800 +++ b/kernel/sched_rt.c 2011-05-16 19:58:42.000000000 +0800 @@ -1166,6 +1166,8 @@ static struct task_struct *pick_next_hig int idx;
for_each_leaf_rt_rq(rt_rq, rq) { + struct task_struct *this; + array = &rt_rq->active; idx = sched_find_first_bit(array->bitmap); next_idx: @@ -1173,6 +1175,7 @@ next_idx: continue; if (next && next->prio < idx) continue; + this = NULL; list_for_each_entry(rt_se, array->queue + idx, run_list) { struct task_struct *p;
@@ -1181,11 +1184,15 @@ next_idx:
p = rt_task_of(rt_se); if (pick_rt_task(rq, p, cpu)) { - next = p; + this = p; break; } } - if (!next) { + if (this != NULL) + next = this; + else { /* + * we have to check next idx even if next != NULL + */ idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1); goto next_idx; }
| |