From: Hillf Danton <dhillf@xxxxxxxxx>
Without coments, the following three hunks, I guess,
======
@@ -2788,6 +2801,7 @@ select_task_rq_fair(struct task_struct *p,
goto unlock;
}
+ prev_cpu = new_cpu;
while (sd) {
int load_idx = sd->forkexec_idx;
struct sched_group *group;
@@ -2811,6 +2825,7 @@ select_task_rq_fair(struct task_struct *p,
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
+ new_cpu = prev_cpu;
continue;
}
@@ -2826,6 +2841,7 @@ select_task_rq_fair(struct task_struct *p,
}
/* while loop will break here if sd == NULL */
}
+ BUG_ON(new_cpu < 0);
unlock:
rcu_read_unlock();
======
were added for certain that selected cpu is valid, based on BUG_ON.
But question raised, why prev_cpu is changed?
Andrea's answer: yes the BUG_ON was introduced to verify the function
wouldn't return -1. This patch fixes the problem too.
Signed-off-by: Hillf Danton <dhillf@xxxxxxxxx>
Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
---
kernel/sched/fair.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 25e9e5b..a8498e0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2769,7 +2769,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
goto unlock;
}
- prev_cpu = new_cpu;
while (sd) {
int load_idx = sd->forkexec_idx;
struct sched_group *group;
@@ -2793,7 +2792,10 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
- new_cpu = prev_cpu;
+ if (new_cpu == -1) {
+ /* Only for certain that new cpu is valid */
+ new_cpu = prev_cpu;
+ }
continue;
}
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>