Upgrade to 4.4.50-rt62

[kvmfornfv.git] / kernel / kernel / sched / core.c

diff --git a/kernel/kernel/sched/core.c b/kernel/kernel/sched/core.c
index 94827a5..e9b8d51 100644 (file)
--- a/kernel/kernel/sched/core.c
+++ b/kernel/kernel/sched/core.c
@@ -670,7 +670,10 @@ int get_nohz_timer_target(void)
        rcu_read_lock();
        for_each_domain(cpu, sd) {
                for_each_cpu(i, sched_domain_span(sd)) {
-                       if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
+                       if (cpu == i)
+                               continue;
+
+                       if (!idle_cpu(i) && is_housekeeping_cpu(i)) {
                                cpu = i;
                                goto unlock;
                        }
@@ -2098,6 +2101,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
        success = 1; /* we're going to change ->state */
        cpu = task_cpu(p);
 
+       /*
+        * Ensure we load p->on_rq _after_ p->state, otherwise it would
+        * be possible to, falsely, observe p->on_rq == 0 and get stuck
+        * in smp_cond_load_acquire() below.
+        *
+        * sched_ttwu_pending()                 try_to_wake_up()
+        *   [S] p->on_rq = 1;                  [L] P->state
+        *       UNLOCK rq->lock  -----.
+        *                              \
+        *                               +---   RMB
+        * schedule()                   /
+        *       LOCK rq->lock    -----'
+        *       UNLOCK rq->lock
+        *
+        * [task p]
+        *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+        *
+        * Pairs with the UNLOCK+LOCK on rq->lock from the
+        * last wakeup of our task and the schedule that got our task
+        * current.
+        */
+       smp_rmb();
        if (p->on_rq && ttwu_remote(p, wake_flags))
                goto stat;
 
@@ -3127,7 +3152,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
 static inline void schedule_debug(struct task_struct *prev)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
-       BUG_ON(task_stack_end_corrupted(prev));
+       if (task_stack_end_corrupted(prev))
+               panic("corrupted stack end detected inside scheduler\n");
 #endif
 
        if (unlikely(in_atomic_preempt_off())) {
@@ -3470,7 +3496,7 @@ static __always_inline int preemptible_lazy(void)
 
 #else
 
-static int preemptible_lazy(void)
+static inline int preemptible_lazy(void)
 {
        return 1;
 }
@@ -5185,14 +5211,16 @@ void show_state_filter(unsigned long state_filter)
                /*
                 * reset the NMI-timeout, listing all files on a slow
                 * console might take a lot of time:
+                * Also, reset softlockup watchdogs on all CPUs, because
+                * another CPU might be blocked waiting for us to process
+                * an IPI.
                 */
                touch_nmi_watchdog();
+               touch_all_softlockup_watchdogs();
                if (!state_filter || (p->state & state_filter))
                        sched_show_task(p);
        }
 
-       touch_all_softlockup_watchdogs();
-
 #ifdef CONFIG_SCHED_DEBUG
        sysrq_sched_debug_show();
 #endif
@@ -5768,6 +5796,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
        case CPU_UP_PREPARE:
                rq->calc_load_update = calc_load_update;
+               account_reset_rq(rq);
                break;
 
        case CPU_ONLINE:
@@ -7939,7 +7968,7 @@ void set_curr_task(int cpu, struct task_struct *p)
 /* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
-static void free_sched_group(struct task_group *tg)
+static void sched_free_group(struct task_group *tg)
 {
        free_fair_sched_group(tg);
        free_rt_sched_group(tg);
@@ -7965,7 +7994,7 @@ struct task_group *sched_create_group(struct task_group *parent)
        return tg;
 
 err:
-       free_sched_group(tg);
+       sched_free_group(tg);
        return ERR_PTR(-ENOMEM);
 }
 
@@ -7985,17 +8014,16 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 }
 
 /* rcu callback to free various structures associated with a task group */
-static void free_sched_group_rcu(struct rcu_head *rhp)
+static void sched_free_group_rcu(struct rcu_head *rhp)
 {
        /* now it should be safe to free those cfs_rqs */
-       free_sched_group(container_of(rhp, struct task_group, rcu));
+       sched_free_group(container_of(rhp, struct task_group, rcu));
 }
 
-/* Destroy runqueue etc associated with a task group */
 void sched_destroy_group(struct task_group *tg)
 {
        /* wait for possible concurrent references to cfs_rqs complete */
-       call_rcu(&tg->rcu, free_sched_group_rcu);
+       call_rcu(&tg->rcu, sched_free_group_rcu);
 }
 
 void sched_offline_group(struct task_group *tg)
@@ -8456,31 +8484,26 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
        if (IS_ERR(tg))
                return ERR_PTR(-ENOMEM);
 
+       sched_online_group(tg, parent);
+
        return &tg->css;
 }
 
-static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
        struct task_group *tg = css_tg(css);
-       struct task_group *parent = css_tg(css->parent);
 
-       if (parent)
-               sched_online_group(tg, parent);
-       return 0;
+       sched_offline_group(tg);
 }
 
 static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 {
        struct task_group *tg = css_tg(css);
 
-       sched_destroy_group(tg);
-}
-
-static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
-{
-       struct task_group *tg = css_tg(css);
-
-       sched_offline_group(tg);
+       /*
+        * Relies on the RCU grace period between css_released() and this.
+        */
+       sched_free_group(tg);
 }
 
 static void cpu_cgroup_fork(struct task_struct *task, void *private)
@@ -8840,9 +8863,8 @@ static struct cftype cpu_files[] = {
 
 struct cgroup_subsys cpu_cgrp_subsys = {
        .css_alloc      = cpu_cgroup_css_alloc,
+       .css_released   = cpu_cgroup_css_released,
        .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,