sched: add new API sched_setscheduler_nocheck: add a flag to control access checks
Hidehiro Kawai noticed that sched_setscheduler() can fail in
stop_machine: it calls sched_setscheduler() from insmod, which can
have CAP_SYS_MODULE without CAP_SYS_NICE.
Two cases could have failed, so are changed to sched_setscheduler_nocheck:
kernel/softirq.c:cpu_callback()
- CPU hotplug callback
kernel/stop_machine.c:__stop_machine_run()
- Called from various places, including modprobe()
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: sugita <yumiko.sugita.yf@hitachi.com>
Cc: Satoshi OSHIMA <satoshi.oshima.fk@hitachi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index b048ad8..8d7c246 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4746,16 +4746,8 @@
set_load_weight(p);
}
-/**
- * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
- * @p: the task in question.
- * @policy: new policy.
- * @param: structure containing the new RT priority.
- *
- * NOTE that the task may be already dead.
- */
-int sched_setscheduler(struct task_struct *p, int policy,
- struct sched_param *param)
+static int __sched_setscheduler(struct task_struct *p, int policy,
+ struct sched_param *param, bool user)
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
@@ -4787,7 +4779,7 @@
/*
* Allow unprivileged RT tasks to decrease priority:
*/
- if (!capable(CAP_SYS_NICE)) {
+ if (user && !capable(CAP_SYS_NICE)) {
if (rt_policy(policy)) {
unsigned long rlim_rtprio;
@@ -4823,7 +4815,8 @@
* Do not allow realtime tasks into groups that have no runtime
* assigned.
*/
- if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+ if (user
+ && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
return -EPERM;
#endif
@@ -4872,8 +4865,39 @@
return 0;
}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+ struct sched_param *param)
+{
+ return __sched_setscheduler(p, policy, param, true);
+}
EXPORT_SYMBOL_GPL(sched_setscheduler);
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission. For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+ struct sched_param *param)
+{
+ return __sched_setscheduler(p, policy, param, false);
+}
+
static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{