1 files changed, 68 insertions, 32 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 1b59e265273b..ce1056e9b02a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -693,6 +693,7 @@ static inline int cpu_of(struct rq *rq)
 #define this_rq()               (&__get_cpu_var(runqueues))
 #define task_rq(p)              cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
+#define raw_rq()                (&__raw_get_cpu_var(runqueues))
 
 inline void update_rq_clock(struct rq *rq)
 {
@@ -2637,9 +2638,32 @@ void sched_fork(struct task_struct *p, int clone_flags)
         set_task_cpu(p, cpu);
 
         /*
-         * Make sure we do not leak PI boosting priority to the child:
+         * Make sure we do not leak PI boosting priority to the child.
          */
         p->prio = current->normal_prio;
+
+        /*
+         * Revert to default priority/policy on fork if requested.
+         */
+        if (unlikely(p->sched_reset_on_fork)) {
+                if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+                        p->policy = SCHED_NORMAL;
+
+                if (p->normal_prio < DEFAULT_PRIO)
+                        p->prio = DEFAULT_PRIO;
+
+                if (PRIO_TO_NICE(p->static_prio) < 0) {
+                        p->static_prio = NICE_TO_PRIO(0);
+                        set_load_weight(p);
+                }
+
+                /*
+                 * We don't need the reset flag anymore after the fork. It has
+                 * fulfilled its duty:
+                 */
+                p->sched_reset_on_fork = 0;
+        }
+
         if (!rt_prio(p->prio))
                 p->sched_class = &fair_sched_class;
 
@@ -6123,17 +6147,25 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
         unsigned long flags;
         const struct sched_class *prev_class = p->sched_class;
         struct rq *rq;
+        int reset_on_fork;
 
         /* may grab non-irq protected spin_locks */
         BUG_ON(in_interrupt());
 recheck:
         /* double check policy once rq lock held */
-        if (policy < 0)
+        if (policy < 0) {
+                reset_on_fork = p->sched_reset_on_fork;
                 policy = oldpolicy = p->policy;
-        else if (policy != SCHED_FIFO && policy != SCHED_RR &&
-                        policy != SCHED_NORMAL && policy != SCHED_BATCH &&
-                        policy != SCHED_IDLE)
-                return -EINVAL;
+        } else {
+                reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+                policy &= ~SCHED_RESET_ON_FORK;
+
+                if (policy != SCHED_FIFO && policy != SCHED_RR &&
+                                policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+                                policy != SCHED_IDLE)
+                        return -EINVAL;
+        }
+
         /*
          * Valid priorities for SCHED_FIFO and SCHED_RR are
          * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -6177,6 +6209,10 @@ recheck:
                 /* can't change other user's priorities */
                 if (!check_same_owner(p))
                         return -EPERM;
+
+                /* Normal users shall not reset the sched_reset_on_fork flag */
+                if (p->sched_reset_on_fork && !reset_on_fork)
+                        return -EPERM;
         }
 
         if (user) {
@@ -6220,6 +6256,8 @@ recheck:
         if (running)
                 p->sched_class->put_prev_task(rq, p);
 
+        p->sched_reset_on_fork = reset_on_fork;
+
         oldprio = p->prio;
         __setscheduler(rq, p, policy, param->sched_priority);
 
@@ -6336,14 +6374,15 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
         if (p) {
                 retval = security_task_getscheduler(p);
                 if (!retval)
-                        retval = p->policy;
+                        retval = p->policy
+                                | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
         }
         read_unlock(&tasklist_lock);
         return retval;
 }
 
 /**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
@@ -6571,19 +6610,9 @@ static inline int should_resched(void)
 
 static void __cond_resched(void)
 {
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-        __might_sleep(__FILE__, __LINE__);
-#endif
-        /*
-         * The BKS might be reacquired before we have dropped
-         * PREEMPT_ACTIVE, which could trigger a second
-         * cond_resched() call.
-         */
-        do {
-                add_preempt_count(PREEMPT_ACTIVE);
-                schedule();
-                sub_preempt_count(PREEMPT_ACTIVE);
-        } while (need_resched());
+        add_preempt_count(PREEMPT_ACTIVE);
+        schedule();
+        sub_preempt_count(PREEMPT_ACTIVE);
 }
 
 int __sched _cond_resched(void)
@@ -6597,14 +6626,14 @@ int __sched _cond_resched(void)
 EXPORT_SYMBOL(_cond_resched);
 
 /*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
  * call schedule, and on return reacquire the lock.
  *
  * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
  * operations here to prevent schedule() from being called twice (once via
  * spin_unlock(), once by hand).
  */
-int cond_resched_lock(spinlock_t *lock)
+int __cond_resched_lock(spinlock_t *lock)
 {
         int resched = should_resched();
         int ret = 0;
@@ -6620,9 +6649,9 @@ int cond_resched_lock(spinlock_t *lock)
         }
         return ret;
 }
-EXPORT_SYMBOL(cond_resched_lock);
+EXPORT_SYMBOL(__cond_resched_lock);
 
-int __sched cond_resched_softirq(void)
+int __sched __cond_resched_softirq(void)
 {
         BUG_ON(!in_softirq());
 
@@ -6634,7 +6663,7 @@ int __sched cond_resched_softirq(void)
         }
         return 0;
 }
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
 
 /**
  * yield - yield the current processor to other threads.
@@ -6658,7 +6687,7 @@ EXPORT_SYMBOL(yield);
  */
 void __sched io_schedule(void)
 {
-        struct rq *rq = &__raw_get_cpu_var(runqueues);
+        struct rq *rq = raw_rq();
 
         delayacct_blkio_start();
         atomic_inc(&rq->nr_iowait);
@@ -6670,7 +6699,7 @@ EXPORT_SYMBOL(io_schedule);
 
 long __sched io_schedule_timeout(long timeout)
 {
-        struct rq *rq = &__raw_get_cpu_var(runqueues);
+        struct rq *rq = raw_rq();
         long ret;
 
         delayacct_blkio_start();
@@ -7625,7 +7654,7 @@ static int __init migration_init(void)
         migration_call(&migration_notifier, CPU_ONLINE, cpu);
         register_cpu_notifier(&migration_notifier);
 
-        return err;
+        return 0;
 }
 early_initcall(migration_init);
 #endif
@@ -9398,13 +9427,20 @@ void __init sched_init(void)
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-void __might_sleep(char *file, int line)
+static inline int preempt_count_equals(int preempt_offset)
+{
+        int nested = preempt_count() & ~PREEMPT_ACTIVE;
+
+        return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+}
+
+void __might_sleep(char *file, int line, int preempt_offset)
 {
 #ifdef in_atomic
         static unsigned long prev_jiffy;        /* ratelimiting */
 
-        if ((!in_atomic() && !irqs_disabled()) ||
-                    system_state != SYSTEM_RUNNING || oops_in_progress)
+        if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+            system_state != SYSTEM_RUNNING || oops_in_progress)
                 return;
         if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
                 return;