1 files changed, 74 insertions, 44 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44999505e1bf..89e7283015a6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2475,44 +2475,6 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
 
 /*
- * Return any ns on the sched_clock that have not yet been accounted in
- * @p in case that task is currently running.
- *
- * Called with task_rq_lock() held on @rq.
- */
-static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
-{
-        u64 ns = 0;
-
-        /*
-         * Must be ->curr _and_ ->on_rq.  If dequeued, we would
-         * project cycles that may never be accounted to this
-         * thread, breaking clock_gettime().
-         */
-        if (task_current(rq, p) && task_on_rq_queued(p)) {
-                update_rq_clock(rq);
-                ns = rq_clock_task(rq) - p->se.exec_start;
-                if ((s64)ns < 0)
-                        ns = 0;
-        }
-
-        return ns;
-}
-
-unsigned long long task_delta_exec(struct task_struct *p)
-{
-        unsigned long flags;
-        struct rq *rq;
-        u64 ns = 0;
-
-        rq = task_rq_lock(p, &flags);
-        ns = do_task_delta_exec(p, rq);
-        task_rq_unlock(rq, p, &flags);
-
-        return ns;
-}
-
-/*
  * Return accounted runtime for the task.
  * In case the task is currently running, return the runtime plus current's
  * pending runtime that have not been accounted yet.
@@ -2521,7 +2483,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 {
         unsigned long flags;
         struct rq *rq;
-        u64 ns = 0;
+        u64 ns;
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
         /*
@@ -2540,7 +2502,16 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 #endif
 
         rq = task_rq_lock(p, &flags);
-        ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+        /*
+         * Must be ->curr _and_ ->on_rq.  If dequeued, we would
+         * project cycles that may never be accounted to this
+         * thread, breaking clock_gettime().
+         */
+        if (task_current(rq, p) && task_on_rq_queued(p)) {
+                update_rq_clock(rq);
+                p->sched_class->update_curr(rq);
+        }
+        ns = p->se.sum_exec_runtime;
         task_rq_unlock(rq, p, &flags);
 
         return ns;
@@ -2903,10 +2874,14 @@ asmlinkage __visible void __sched schedule_user(void)
          * or we have been woken up remotely but the IPI has not yet arrived,
          * we haven't yet exited the RCU idle mode. Do it here manually until
          * we find a better solution.
+         *
+         * NB: There are buggy callers of this function.  Ideally we
+         * should warn if prev_state != IN_USER, but that will trigger
+         * too frequently to make sense yet.
          */
-        user_exit();
+        enum ctx_state prev_state = exception_enter();
         schedule();
-        user_enter();
+        exception_exit(prev_state);
 }
 #endif
 
@@ -2951,6 +2926,47 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 }
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+{
+        enum ctx_state prev_ctx;
+
+        if (likely(!preemptible()))
+                return;
+
+        do {
+                __preempt_count_add(PREEMPT_ACTIVE);
+                /*
+                 * Needs preempt disabled in case user_exit() is traced
+                 * and the tracer calls preempt_enable_notrace() causing
+                 * an infinite recursion.
+                 */
+                prev_ctx = exception_enter();
+                __schedule();
+                exception_exit(prev_ctx);
+
+                __preempt_count_sub(PREEMPT_ACTIVE);
+                barrier();
+        } while (need_resched());
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #endif /* CONFIG_PREEMPT */
 
 /*
@@ -6327,6 +6343,10 @@ static void sched_init_numa(void)
                 if (!sched_debug())
                         break;
         }
+
+        if (!level)
+                return;
+
         /*
          * 'level' contains the number of unique distances, excluding the
          * identity distance node_distance(i,i).
@@ -7403,8 +7423,12 @@ void sched_move_task(struct task_struct *tsk)
         if (unlikely(running))
                 put_prev_task(rq, tsk);
 
-        tg = container_of(task_css_check(tsk, cpu_cgrp_id,
-                                lockdep_is_held(&tsk->sighand->siglock)),
+        /*
+         * All callers are synchronized by task_rq_lock(); we do not use RCU
+         * which is pointless here. Thus, we pass "true" to task_css_check()
+         * to prevent lockdep warnings.
+         */
+        tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
                           struct task_group, css);
         tg = autogroup_task_group(tsk, tg);
         tsk->sched_task_group = tg;
@@ -7833,6 +7857,11 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
         sched_offline_group(tg);
 }
 
+static void cpu_cgroup_fork(struct task_struct *task)
+{
+        sched_move_task(task);
+}
+
 static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
                                  struct cgroup_taskset *tset)
 {
@@ -8205,6 +8234,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
         .css_free       = cpu_cgroup_css_free,
         .css_online     = cpu_cgroup_css_online,
         .css_offline    = cpu_cgroup_css_offline,
+        .fork           = cpu_cgroup_fork,
         .can_attach     = cpu_cgroup_can_attach,
         .attach         = cpu_cgroup_attach,
         .exit           = cpu_cgroup_exit,