11 files changed, 63 insertions, 50 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2b02c9fda790..1cd5eef1fcdd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1562,8 +1562,10 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group
 
         if (!task) {
                 /*
-                 * Per cpu events are removed via an smp call and
-                 * the removal is always successful.
+                 * Per cpu events are removed via an smp call. The removal can
+                 * fail if the CPU is currently offline, but in that case we
+                 * already called __perf_remove_from_context from
+                 * perf_event_exit_cpu.
                  */
                 cpu_function_call(event->cpu, __perf_remove_from_context, &re);
                 return;
@@ -8117,7 +8119,7 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
-        struct remove_event re = { .detach_group = false };
+        struct remove_event re = { .detach_group = true };
         struct perf_event_context *ctx = __info;
 
         perf_pmu_rotate_stop(ctx->pmu);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 1d0af8a2c646..ed8f2cde34c5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1640,7 +1640,6 @@ bool uprobe_deny_signal(void)
                 if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
                         utask->state = UTASK_SSTEP_TRAPPED;
                         set_tsk_thread_flag(t, TIF_UPROBE);
-                        set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
                 }
         }
 
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index bbef57f5bdfd..1eb7da7bc8e8 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -308,4 +308,3 @@ config PM_GENERIC_DOMAINS_OF
 
 config CPU_PM
         bool
-        depends on SUSPEND || CPU_IDLE
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 240157c13ddc..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
 
@@ -6368,6 +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).
@@ -7444,8 +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;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5285332392d5..28fa9d9e9201 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1701,4 +1701,6 @@ const struct sched_class dl_sched_class = {
         .prio_changed           = prio_changed_dl,
         .switched_from          = switched_from_dl,
         .switched_to            = switched_to_dl,
+
+        .update_curr            = update_curr_dl,
 };
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 34baa60f8a7b..ef2b104b254c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -726,6 +726,11 @@ static void update_curr(struct cfs_rq *cfs_rq)
         account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
+static void update_curr_fair(struct rq *rq)
+{
+        update_curr(cfs_rq_of(&rq->curr->se));
+}
+
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -1180,6 +1185,13 @@ static void task_numa_compare(struct task_numa_env *env,
         raw_spin_unlock_irq(&dst_rq->lock);
 
         /*
+         * Because we have preemption enabled we can get migrated around and
+         * end try selecting ourselves (current == env->p) as a swap candidate.
+         */
+        if (cur == env->p)
+                goto unlock;
+
+        /*
          * "imp" is the fault differential for the source task between the
          * source and destination node. Calculate the total differential for
          * the source task and potential destination task. The more negative
@@ -7949,6 +7961,8 @@ const struct sched_class fair_sched_class = {
 
         .get_rr_interval        = get_rr_interval_fair,
 
+        .update_curr            = update_curr_fair,
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
         .task_move_group        = task_move_group_fair,
 #endif
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 67ad4e7f506a..c65dac8c97cd 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -75,6 +75,10 @@ static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task
         return 0;
 }
 
+static void update_curr_idle(struct rq *rq)
+{
+}
+
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
@@ -101,4 +105,5 @@ const struct sched_class idle_sched_class = {
 
         .prio_changed           = prio_changed_idle,
         .switched_to            = switched_to_idle,
+        .update_curr            = update_curr_idle,
 };
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d024e6ce30ba..20bca398084a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2128,6 +2128,8 @@ const struct sched_class rt_sched_class = {
 
         .prio_changed           = prio_changed_rt,
         .switched_to            = switched_to_rt,
+
+        .update_curr            = update_curr_rt,
 };
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24156c8434d1..2df8ef067cc5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1135,6 +1135,8 @@ struct sched_class {
         unsigned int (*get_rr_interval) (struct rq *rq,
                                          struct task_struct *task);
 
+        void (*update_curr) (struct rq *rq);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
         void (*task_move_group) (struct task_struct *p, int on_rq);
 #endif
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 67426e529f59..79ffec45a6ac 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -102,6 +102,10 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
         return 0;
 }
 
+static void update_curr_stop(struct rq *rq)
+{
+}
+
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
@@ -128,4 +132,5 @@ const struct sched_class stop_sched_class = {
 
         .prio_changed           = prio_changed_stop,
         .switched_to            = switched_to_stop,
+        .update_curr            = update_curr_stop,
 };
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 492b986195d5..a16b67859e2a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -553,7 +553,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
                 *sample = cputime_to_expires(cputime.utime);
                 break;
         case CPUCLOCK_SCHED:
-                *sample = cputime.sum_exec_runtime + task_delta_exec(p);
+                *sample = cputime.sum_exec_runtime;
                 break;
         }
         return 0;