rcu: Simplify curing of load woes

[sfrench/cifs-2.6.git] / kernel / rcutree.c

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 77a7671dd1472b10567fcaba0fd0d308565215cc..0a8ec5b2e208eebe7eafb3c86f5cc8cd8f837539 100644 (file)
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1635,6 +1635,20 @@ static int rcu_cpu_kthread(void *arg)
  * to manipulate rcu_cpu_kthread_task.  There might be another CPU
  * attempting to access it during boot, but the locking in kthread_bind()
  * will enforce sufficient ordering.
+ *
+ * Please note that we cannot simply refuse to wake up the per-CPU
+ * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
+ * which can result in softlockup complaints if the task ends up being
+ * idle for more than a couple of minutes.
+ *
+ * However, please note also that we cannot bind the per-CPU kthread to its
+ * CPU until that CPU is fully online.  We also cannot wait until the
+ * CPU is fully online before we create its per-CPU kthread, as this would
+ * deadlock the system when CPU notifiers tried waiting for grace
+ * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
+ * is online.  If its CPU is not yet fully online, then the code in
+ * rcu_cpu_kthread() will wait until it is fully online, and then do
+ * the binding.
  */
 static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 {
@@ -1647,13 +1661,14 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
        t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
        if (IS_ERR(t))
                return PTR_ERR(t);
-       kthread_bind(t, cpu);
-       set_task_state(t, TASK_INTERRUPTIBLE);
+       if (cpu_online(cpu))
+               kthread_bind(t, cpu);
        per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
        WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
-       per_cpu(rcu_cpu_kthread_task, cpu) = t;
        sp.sched_priority = RCU_KTHREAD_PRIO;
        sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+       per_cpu(rcu_cpu_kthread_task, cpu) = t;
+       wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
        return 0;
 }
 
@@ -1756,11 +1771,11 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
                if (IS_ERR(t))
                        return PTR_ERR(t);
                raw_spin_lock_irqsave(&rnp->lock, flags);
-               set_task_state(t, TASK_INTERRUPTIBLE);
                rnp->node_kthread_task = t;
                raw_spin_unlock_irqrestore(&rnp->lock, flags);
                sp.sched_priority = 99;
                sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+               wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
        }
        return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
@@ -2188,14 +2203,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
        raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
        rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
        rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
        rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
        struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
        struct rcu_node *rnp = rdp->mynode;
@@ -2221,8 +2236,8 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
        switch (action) {
        case CPU_UP_PREPARE:
        case CPU_UP_PREPARE_FROZEN:
-               rcu_online_cpu(cpu);
-               rcu_online_kthreads(cpu);
+               rcu_prepare_cpu(cpu);
+               rcu_prepare_kthreads(cpu);
                break;
        case CPU_ONLINE:
        case CPU_DOWN_FAILED: