summaryrefslogtreecommitdiff
path: root/kernel/sched.c
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@redhat.com>2010-03-15 10:10:19 +0100
committerIngo Molnar <mingo@elte.hu>2010-04-02 20:12:02 +0200
commit30da688ef6b76e01969b00608202fff1eed2accc (patch)
treef4068cb8cf29f1d93d8489b162f41b7ac15a3d0c /kernel/sched.c
parentc1804d547dc098363443667609c272d1e4d15ee8 (diff)
sched: sched_exec(): Remove the select_fallback_rq() logic
sched_exec()->select_task_rq() reads/updates ->cpus_allowed lockless. This can race with other CPUs updating our ->cpus_allowed, and this looks meaningless to me. The task is current and running, it must have online cpus in ->cpus_allowed, the fallback mode is bogus. And, if ->sched_class returns the "wrong" cpu, this likely means we raced with set_cpus_allowed() which was called for reason, why should sched_exec() retry and call ->select_task_rq() again? Change the code to call sched_class->select_task_rq() directly and do nothing if the returned cpu is wrong after re-checking under rq->lock. From now task_struct->cpus_allowed is always stable under TASK_WAKING, select_fallback_rq() is always called under rq-lock or the caller or the caller owns TASK_WAKING (select_task_rq). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20100315091019.GA9141@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/sched.c')
-rw-r--r--kernel/sched.c25
1 files changed, 8 insertions, 17 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index f475c608b073..165b532dd8c2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2280,6 +2280,9 @@ void task_oncpu_function_call(struct task_struct *p,
}
#ifdef CONFIG_SMP
+/*
+ * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ */
static int select_fallback_rq(int cpu, struct task_struct *p)
{
int dest_cpu;
@@ -2316,12 +2319,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
}
/*
- * Gets called from 3 sites (exec, fork, wakeup), since it is called without
- * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
- * by:
- *
- * exec: is unstable, retry loop
- * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
*/
static inline
int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
@@ -3076,9 +3074,8 @@ void sched_exec(void)
unsigned long flags;
struct rq *rq;
-again:
this_cpu = get_cpu();
- dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
+ dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
if (dest_cpu == this_cpu) {
put_cpu();
return;
@@ -3086,18 +3083,12 @@ again:
rq = task_rq_lock(p, &flags);
put_cpu();
-
/*
* select_task_rq() can race against ->cpus_allowed
*/
- if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
- || unlikely(!cpu_active(dest_cpu))) {
- task_rq_unlock(rq, &flags);
- goto again;
- }
-
- /* force the process onto the specified CPU */
- if (migrate_task(p, dest_cpu, &req)) {
+ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
+ likely(cpu_active(dest_cpu)) &&
+ migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
struct task_struct *mt = rq->migration_thread;