Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

 - Apply a number of membarrier related fixes and cleanups, which fixes
   a use-after-free race in the membarrier code

 - Introduce proper RCU protection for tasks on the runqueue - to get
   rid of the subtle task_rcu_dereference() interface that was easy to
   get wrong

 - Misc fixes, but also an EAS speedup

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Avoid redundant EAS calculation
  sched/core: Remove double update_max_interval() call on CPU startup
  sched/core: Fix preempt_schedule() interrupt return comment
  sched/fair: Fix -Wunused-but-set-variable warnings
  sched/core: Fix migration to invalid CPU in __set_cpus_allowed_ptr()
  sched/membarrier: Return -ENOMEM to userspace on memory allocation failure
  sched/membarrier: Skip IPIs when mm->mm_users == 1
  selftests, sched/membarrier: Add multi-threaded test
  sched/membarrier: Fix p->mm->membarrier_state racy load
  sched/membarrier: Call sync_core only before usermode for same mm
  sched/membarrier: Remove redundant check
  sched/membarrier: Fix private expedited registration check
  tasks, sched/core: RCUify the assignment of rq->curr
  tasks, sched/core: With a grace period after finish_task_switch(), remove unnecessary code
  tasks, sched/core: Ensure tasks are available for a grace period after leaving the runqueue
  tasks: Add a count of task RCU users
  sched/core: Convert vcpu_is_preempted() from macro to an inline function
  sched/fair: Remove unused cfs_rq_clock_task() function

1 files changed, 15 insertions, 13 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9a1346a5fa9..7880f4f64d0e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1656,7 +1656,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_equal(p->cpus_ptr, new_mask))
 		goto out;
 
-	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
+	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+	if (dest_cpu >= nr_cpu_ids) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1677,7 +1678,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
 	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
@@ -3254,7 +3254,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		/* Task is done with its stack. */
 		put_task_stack(prev);
 
-		put_task_struct(prev);
+		put_task_struct_rcu_user(prev);
 	}
 
 	tick_nohz_task_switch();
@@ -3358,15 +3358,15 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		else
 			prev->active_mm = NULL;
 	} else {                                        // to user
+		membarrier_switch_mm(rq, prev->active_mm, next->mm);
 		/*
 		 * sys_membarrier() requires an smp_mb() between setting
-		 * rq->curr and returning to userspace.
+		 * rq->curr / membarrier_switch_mm() and returning to userspace.
 		 *
 		 * The below provides this either through switch_mm(), or in
 		 * case 'prev->active_mm == next->mm' through
 		 * finish_task_switch()'s mmdrop().
 		 */
-
 		switch_mm_irqs_off(prev->active_mm, next->mm, next);
 
 		if (!prev->mm) {                        // from kernel
@@ -4042,7 +4042,11 @@ static void __sched notrace __schedule(bool preempt)
 
 	if (likely(prev != next)) {
 		rq->nr_switches++;
-		rq->curr = next;
+		/*
+		 * RCU users of rcu_dereference(rq->curr) may not see
+		 * changes to task_struct made by pick_next_task().
+		 */
+		RCU_INIT_POINTER(rq->curr, next);
 		/*
 		 * The membarrier system call requires each architecture
 		 * to have a full memory barrier after updating
@@ -4223,9 +4227,8 @@ static void __sched notrace preempt_schedule_common(void)
 
 #ifdef CONFIG_PREEMPTION
 /*
- * this is the entry point to schedule() from in-kernel preemption
- * off of preempt_enable. Kernel preemptions off return from interrupt
- * occur there and call schedule directly.
+ * This is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable.
  */
 asmlinkage __visible void __sched notrace preempt_schedule(void)
 {
@@ -4296,7 +4299,7 @@ EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 #endif /* CONFIG_PREEMPTION */
 
 /*
- * this is the entry point to schedule() from kernel preemption
+ * This is the entry point to schedule() from kernel preemption
  * off of irq context.
  * Note, that this is called and return with irqs disabled. This will
  * protect us against recursive calling from irq.
@@ -6069,7 +6072,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	__set_task_cpu(idle, cpu);
 	rcu_read_unlock();
 
-	rq->curr = rq->idle = idle;
+	rq->idle = idle;
+	rcu_assign_pointer(rq->curr, idle);
 	idle->on_rq = TASK_ON_RQ_QUEUED;
 #ifdef CONFIG_SMP
 	idle->on_cpu = 1;
@@ -6430,8 +6434,6 @@ int sched_cpu_activate(unsigned int cpu)
 	}
 	rq_unlock_irqrestore(rq, &rf);
 
-	update_max_interval();
-
 	return 0;
 }