Merge remote-tracking branch 'tip/smp/hotplug' into next.2012.09.25b

The conflicts between kernel/rcutree.h and kernel/rcutree_plugin.h
were due to adjacent insertions and deletions, which were resolved
by simply accepting the changes on both branches.

1 files changed, 71 insertions, 332 deletions

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 46d7d6cf16db..9c71c1b18e03 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -26,6 +26,7 @@
 
 #include <linux/delay.h>
 #include <linux/oom.h>
+#include <linux/smpboot.h>
 
 #define RCU_KTHREAD_PRIO 1
 
@@ -1090,6 +1091,16 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+        /*
+         * If the thread is yielding, only wake it when this
+         * is invoked from idle
+         */
+        if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
+                wake_up_process(t);
+}
+
 /*
  * Carry out RCU priority boosting on the task indicated by ->exp_tasks
  * or ->boost_tasks, advancing the pointer to the next task in the
@@ -1162,17 +1173,6 @@ static int rcu_boost(struct rcu_node *rnp)
 }
 
 /*
- * Timer handler to initiate waking up of boost kthreads that
- * have yielded the CPU due to excessive numbers of tasks to
- * boost.  We wake up the per-rcu_node kthread, which in turn
- * will wake up the booster kthread.
- */
-static void rcu_boost_kthread_timer(unsigned long arg)
-{
-        invoke_rcu_node_kthread((struct rcu_node *)arg);
-}
-
-/*
  * Priority-boosting kthread.  One per leaf rcu_node and one for the
  * root rcu_node.
  */
@@ -1195,8 +1195,9 @@ static int rcu_boost_kthread(void *arg)
                 else
                         spincnt = 0;
                 if (spincnt > 10) {
+                        rnp->boost_kthread_status = RCU_KTHREAD_YIELDING;
                         trace_rcu_utilization("End boost kthread@rcu_yield");
-                        rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
+                        schedule_timeout_interruptible(2);
                         trace_rcu_utilization("Start boost kthread@rcu_yield");
                         spincnt = 0;
                 }
@@ -1234,8 +1235,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
                         rnp->boost_tasks = rnp->gp_tasks;
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
                 t = rnp->boost_kthread_task;
-                if (t != NULL)
-                        wake_up_process(t);
+                if (t)
+                        rcu_wake_cond(t, rnp->boost_kthread_status);
         } else {
                 rcu_initiate_boost_trace(rnp);
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1252,8 +1253,10 @@ static void invoke_rcu_callbacks_kthread(void)
         local_irq_save(flags);
         __this_cpu_write(rcu_cpu_has_work, 1);
         if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
-            current != __this_cpu_read(rcu_cpu_kthread_task))
-                wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+            current != __this_cpu_read(rcu_cpu_kthread_task)) {
+                rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
+                              __this_cpu_read(rcu_cpu_kthread_status));
+        }
         local_irq_restore(flags);
 }
 
@@ -1266,21 +1269,6 @@ static bool rcu_is_callbacks_kthread(void)
         return __get_cpu_var(rcu_cpu_kthread_task) == current;
 }
 
-/*
- * Set the affinity of the boost kthread.  The CPU-hotplug locks are
- * held, so no one should be messing with the existence of the boost
- * kthread.
- */
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
-                                          cpumask_var_t cm)
-{
-        struct task_struct *t;
-
-        t = rnp->boost_kthread_task;
-        if (t != NULL)
-                set_cpus_allowed_ptr(rnp->boost_kthread_task, cm);
-}
-
 #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
 
 /*
@@ -1297,15 +1285,19 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
  * Returns zero if all is well, a negated errno otherwise.
  */
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
-                                                 struct rcu_node *rnp,
-                                                 int rnp_index)
+                                                 struct rcu_node *rnp)
 {
+        int rnp_index = rnp - &rsp->node[0];
         unsigned long flags;
         struct sched_param sp;
         struct task_struct *t;
 
         if (&rcu_preempt_state != rsp)
                 return 0;
+
+        if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0)
+                return 0;
+
         rsp->boost = 1;
         if (rnp->boost_kthread_task != NULL)
                 return 0;
@@ -1322,25 +1314,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
         return 0;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Stop the RCU's per-CPU kthread when its CPU goes offline,.
- */
-static void rcu_stop_cpu_kthread(int cpu)
-{
-        struct task_struct *t;
-
-        /* Stop the CPU's kthread. */
-        t = per_cpu(rcu_cpu_kthread_task, cpu);
-        if (t != NULL) {
-                per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
-                kthread_stop(t);
-        }
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
 static void rcu_kthread_do_work(void)
 {
         rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
@@ -1348,112 +1321,22 @@ static void rcu_kthread_do_work(void)
         rcu_preempt_do_callbacks();
 }
 
-/*
- * Wake up the specified per-rcu_node-structure kthread.
- * Because the per-rcu_node kthreads are immortal, we don't need
- * to do anything to keep them alive.
- */
-static void invoke_rcu_node_kthread(struct rcu_node *rnp)
-{
-        struct task_struct *t;
-
-        t = rnp->node_kthread_task;
-        if (t != NULL)
-                wake_up_process(t);
-}
-
-/*
- * Set the specified CPU's kthread to run RT or not, as specified by
- * the to_rt argument.  The CPU-hotplug locks are held, so the task
- * is not going away.
- */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+static void rcu_cpu_kthread_setup(unsigned int cpu)
 {
-        int policy;
         struct sched_param sp;
-        struct task_struct *t;
-
-        t = per_cpu(rcu_cpu_kthread_task, cpu);
-        if (t == NULL)
-                return;
-        if (to_rt) {
-                policy = SCHED_FIFO;
-                sp.sched_priority = RCU_KTHREAD_PRIO;
-        } else {
-                policy = SCHED_NORMAL;
-                sp.sched_priority = 0;
-        }
-        sched_setscheduler_nocheck(t, policy, &sp);
-}
-
-/*
- * Timer handler to initiate the waking up of per-CPU kthreads that
- * have yielded the CPU due to excess numbers of RCU callbacks.
- * We wake up the per-rcu_node kthread, which in turn will wake up
- * the booster kthread.
- */
-static void rcu_cpu_kthread_timer(unsigned long arg)
-{
-        struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
-        struct rcu_node *rnp = rdp->mynode;
 
-        atomic_or(rdp->grpmask, &rnp->wakemask);
-        invoke_rcu_node_kthread(rnp);
+        sp.sched_priority = RCU_KTHREAD_PRIO;
+        sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
 }
 
-/*
- * Drop to non-real-time priority and yield, but only after posting a
- * timer that will cause us to regain our real-time priority if we
- * remain preempted.  Either way, we restore our real-time priority
- * before returning.
- */
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+static void rcu_cpu_kthread_park(unsigned int cpu)
 {
-        struct sched_param sp;
-        struct timer_list yield_timer;
-        int prio = current->rt_priority;
-
-        setup_timer_on_stack(&yield_timer, f, arg);
-        mod_timer(&yield_timer, jiffies + 2);
-        sp.sched_priority = 0;
-        sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
-        set_user_nice(current, 19);
-        schedule();
-        set_user_nice(current, 0);
-        sp.sched_priority = prio;
-        sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-        del_timer(&yield_timer);
+        per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
 }
 
-/*
- * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
- * This can happen while the corresponding CPU is either coming online
- * or going offline.  We cannot wait until the CPU is fully online
- * before starting the kthread, because the various notifier functions
- * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
- * the corresponding CPU is online.
- *
- * Return 1 if the kthread needs to stop, 0 otherwise.
- *
- * Caller must disable bh.  This function can momentarily enable it.
- */
-static int rcu_cpu_kthread_should_stop(int cpu)
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
 {
-        while (cpu_is_offline(cpu) ||
-               !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
-               smp_processor_id() != cpu) {
-                if (kthread_should_stop())
-                        return 1;
-                per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
-                per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
-                local_bh_enable();
-                schedule_timeout_uninterruptible(1);
-                if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
-                        set_cpus_allowed_ptr(current, cpumask_of(cpu));
-                local_bh_disable();
-        }
-        per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
-        return 0;
+        return __get_cpu_var(rcu_cpu_has_work);
 }
 
 /*
@@ -1461,138 +1344,35 @@ static int rcu_cpu_kthread_should_stop(int cpu)
  * RCU softirq used in flavors and configurations of RCU that do not
  * support RCU priority boosting.
  */
-static int rcu_cpu_kthread(void *arg)
+static void rcu_cpu_kthread(unsigned int cpu)
 {
-        int cpu = (int)(long)arg;
-        unsigned long flags;
-        int spincnt = 0;
-        unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-        char work;
-        char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+        unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status);
+        char work, *workp = &__get_cpu_var(rcu_cpu_has_work);
+        int spincnt;
 
-        trace_rcu_utilization("Start CPU kthread@init");
-        for (;;) {
-                *statusp = RCU_KTHREAD_WAITING;
-                trace_rcu_utilization("End CPU kthread@rcu_wait");
-                rcu_wait(*workp != 0 || kthread_should_stop());
+        for (spincnt = 0; spincnt < 10; spincnt++) {
                 trace_rcu_utilization("Start CPU kthread@rcu_wait");
                 local_bh_disable();
-                if (rcu_cpu_kthread_should_stop(cpu)) {
-                        local_bh_enable();
-                        break;
-                }
                 *statusp = RCU_KTHREAD_RUNNING;
-                per_cpu(rcu_cpu_kthread_loops, cpu)++;
-                local_irq_save(flags);
+                this_cpu_inc(rcu_cpu_kthread_loops);
+                local_irq_disable();
                 work = *workp;
                 *workp = 0;
-                local_irq_restore(flags);
+                local_irq_enable();
                 if (work)
                         rcu_kthread_do_work();
                 local_bh_enable();
-                if (*workp != 0)
-                        spincnt++;
-                else
-                        spincnt = 0;
-                if (spincnt > 10) {
-                        *statusp = RCU_KTHREAD_YIELDING;
-                        trace_rcu_utilization("End CPU kthread@rcu_yield");
-                        rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
-                        trace_rcu_utilization("Start CPU kthread@rcu_yield");
-                        spincnt = 0;
-                }
-        }
-        *statusp = RCU_KTHREAD_STOPPED;
-        trace_rcu_utilization("End CPU kthread@term");
-        return 0;
-}
-
-/*
- * Spawn a per-CPU kthread, setting up affinity and priority.
- * Because the CPU hotplug lock is held, no other CPU will be attempting
- * 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)
-{
-        struct sched_param sp;
-        struct task_struct *t;
-
-        if (!rcu_scheduler_fully_active ||
-            per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
-                return 0;
-        t = kthread_create_on_node(rcu_cpu_kthread,
-                                   (void *)(long)cpu,
-                                   cpu_to_node(cpu),
-                                   "rcuc/%d", cpu);
-        if (IS_ERR(t))
-                return PTR_ERR(t);
-        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);
-        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;
-}
-
-/*
- * Per-rcu_node kthread, which is in charge of waking up the per-CPU
- * kthreads when needed.  We ignore requests to wake up kthreads
- * for offline CPUs, which is OK because force_quiescent_state()
- * takes care of this case.
- */
-static int rcu_node_kthread(void *arg)
-{
-        int cpu;
-        unsigned long flags;
-        unsigned long mask;
-        struct rcu_node *rnp = (struct rcu_node *)arg;
-        struct sched_param sp;
-        struct task_struct *t;
-
-        for (;;) {
-                rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-                rcu_wait(atomic_read(&rnp->wakemask) != 0);
-                rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
-                raw_spin_lock_irqsave(&rnp->lock, flags);
-                mask = atomic_xchg(&rnp->wakemask, 0);
-                rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
-                for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
-                        if ((mask & 0x1) == 0)
-                                continue;
-                        preempt_disable();
-                        t = per_cpu(rcu_cpu_kthread_task, cpu);
-                        if (!cpu_online(cpu) || t == NULL) {
-                                preempt_enable();
-                                continue;
-                        }
-                        per_cpu(rcu_cpu_has_work, cpu) = 1;
-                        sp.sched_priority = RCU_KTHREAD_PRIO;
-                        sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
-                        preempt_enable();
+                if (*workp == 0) {
+                        trace_rcu_utilization("End CPU kthread@rcu_wait");
+                        *statusp = RCU_KTHREAD_WAITING;
+                        return;
                 }
         }
-        /* NOTREACHED */
-        rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
-        return 0;
+        *statusp = RCU_KTHREAD_YIELDING;
+        trace_rcu_utilization("Start CPU kthread@rcu_yield");
+        schedule_timeout_interruptible(2);
+        trace_rcu_utilization("End CPU kthread@rcu_yield");
+        *statusp = RCU_KTHREAD_WAITING;
 }
 
 /*
@@ -1604,17 +1384,17 @@ static int rcu_node_kthread(void *arg)
  * no outgoing CPU.  If there are no CPUs left in the affinity set,
  * this function allows the kthread to execute on any CPU.
  */
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
+        struct task_struct *t = rnp->boost_kthread_task;
+        unsigned long mask = rnp->qsmaskinit;
         cpumask_var_t cm;
         int cpu;
-        unsigned long mask = rnp->qsmaskinit;
 
-        if (rnp->node_kthread_task == NULL)
+        if (!t)
                 return;
-        if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
                 return;
-        cpumask_clear(cm);
         for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
                 if ((mask & 0x1) && cpu != outgoingcpu)
                         cpumask_set_cpu(cpu, cm);
@@ -1624,62 +1404,36 @@ static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
                         cpumask_clear_cpu(cpu, cm);
                 WARN_ON_ONCE(cpumask_weight(cm) == 0);
         }
-        set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
-        rcu_boost_kthread_setaffinity(rnp, cm);
+        set_cpus_allowed_ptr(t, cm);
         free_cpumask_var(cm);
 }
 
-/*
- * Spawn a per-rcu_node kthread, setting priority and affinity.
- * Called during boot before online/offline can happen, or, if
- * during runtime, with the main CPU-hotplug locks held.  So only
- * one of these can be executing at a time.
- */
-static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
-                                                struct rcu_node *rnp)
-{
-        unsigned long flags;
-        int rnp_index = rnp - &rsp->node[0];
-        struct sched_param sp;
-        struct task_struct *t;
-
-        if (!rcu_scheduler_fully_active ||
-            rnp->qsmaskinit == 0)
-                return 0;
-        if (rnp->node_kthread_task == NULL) {
-                t = kthread_create(rcu_node_kthread, (void *)rnp,
-                                   "rcun/%d", rnp_index);
-                if (IS_ERR(t))
-                        return PTR_ERR(t);
-                raw_spin_lock_irqsave(&rnp->lock, flags);
-                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);
-}
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+        .store                  = &rcu_cpu_kthread_task,
+        .thread_should_run      = rcu_cpu_kthread_should_run,
+        .thread_fn              = rcu_cpu_kthread,
+        .thread_comm            = "rcuc/%u",
+        .setup                  = rcu_cpu_kthread_setup,
+        .park                   = rcu_cpu_kthread_park,
+};
 
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
 static int __init rcu_spawn_kthreads(void)
 {
-        int cpu;
         struct rcu_node *rnp;
+        int cpu;
 
         rcu_scheduler_fully_active = 1;
-        for_each_possible_cpu(cpu) {
+        for_each_possible_cpu(cpu)
                 per_cpu(rcu_cpu_has_work, cpu) = 0;
-                if (cpu_online(cpu))
-                        (void)rcu_spawn_one_cpu_kthread(cpu);
-        }
+        BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
         rnp = rcu_get_root(rcu_state);
-        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+        (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
         if (NUM_RCU_NODES > 1) {
                 rcu_for_each_leaf_node(rcu_state, rnp)
-                        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+                        (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
         }
         return 0;
 }
@@ -1691,11 +1445,8 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
         struct rcu_node *rnp = rdp->mynode;
 
         /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
-        if (rcu_scheduler_fully_active) {
-                (void)rcu_spawn_one_cpu_kthread(cpu);
-                if (rnp->node_kthread_task == NULL)
-                        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-        }
+        if (rcu_scheduler_fully_active)
+                (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
@@ -1719,19 +1470,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void rcu_stop_cpu_kthread(int cpu)
-{
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
-{
-}
-
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 }