1 files changed, 179 insertions, 2 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f4d4b077eba0..575da76a3874 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -6,6 +6,7 @@
 #include "sched.h"
 
 #include <linux/slab.h>
+#include <linux/irq_work.h>
 
 int sched_rr_timeslice = RR_TIMESLICE;
 
@@ -59,7 +60,11 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
         raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
+#ifdef CONFIG_SMP
+static void push_irq_work_func(struct irq_work *work);
+#endif
+
+void init_rt_rq(struct rt_rq *rt_rq)
 {
         struct rt_prio_array *array;
         int i;
@@ -78,7 +83,14 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
         rt_rq->rt_nr_migratory = 0;
         rt_rq->overloaded = 0;
         plist_head_init(&rt_rq->pushable_tasks);
+
+#ifdef HAVE_RT_PUSH_IPI
+        rt_rq->push_flags = 0;
+        rt_rq->push_cpu = nr_cpu_ids;
+        raw_spin_lock_init(&rt_rq->push_lock);
+        init_irq_work(&rt_rq->push_work, push_irq_work_func);
 #endif
+#endif /* CONFIG_SMP */
         /* We start is dequeued state, because no RT tasks are queued */
         rt_rq->rt_queued = 0;
 
@@ -193,7 +205,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
                 if (!rt_se)
                         goto err_free_rq;
 
-                init_rt_rq(rt_rq, cpu_rq(i));
+                init_rt_rq(rt_rq);
                 rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
                 init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
         }
@@ -1778,6 +1790,164 @@ static void push_rt_tasks(struct rq *rq)
                 ;
 }
 
+#ifdef HAVE_RT_PUSH_IPI
+/*
+ * The search for the next cpu always starts at rq->cpu and ends
+ * when we reach rq->cpu again. It will never return rq->cpu.
+ * This returns the next cpu to check, or nr_cpu_ids if the loop
+ * is complete.
+ *
+ * rq->rt.push_cpu holds the last cpu returned by this function,
+ * or if this is the first instance, it must hold rq->cpu.
+ */
+static int rto_next_cpu(struct rq *rq)
+{
+        int prev_cpu = rq->rt.push_cpu;
+        int cpu;
+
+        cpu = cpumask_next(prev_cpu, rq->rd->rto_mask);
+
+        /*
+         * If the previous cpu is less than the rq's CPU, then it already
+         * passed the end of the mask, and has started from the beginning.
+         * We end if the next CPU is greater or equal to rq's CPU.
+         */
+        if (prev_cpu < rq->cpu) {
+                if (cpu >= rq->cpu)
+                        return nr_cpu_ids;
+
+        } else if (cpu >= nr_cpu_ids) {
+                /*
+                 * We passed the end of the mask, start at the beginning.
+                 * If the result is greater or equal to the rq's CPU, then
+                 * the loop is finished.
+                 */
+                cpu = cpumask_first(rq->rd->rto_mask);
+                if (cpu >= rq->cpu)
+                        return nr_cpu_ids;
+        }
+        rq->rt.push_cpu = cpu;
+
+        /* Return cpu to let the caller know if the loop is finished or not */
+        return cpu;
+}
+
+static int find_next_push_cpu(struct rq *rq)
+{
+        struct rq *next_rq;
+        int cpu;
+
+        while (1) {
+                cpu = rto_next_cpu(rq);
+                if (cpu >= nr_cpu_ids)
+                        break;
+                next_rq = cpu_rq(cpu);
+
+                /* Make sure the next rq can push to this rq */
+                if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr)
+                        break;
+        }
+
+        return cpu;
+}
+
+#define RT_PUSH_IPI_EXECUTING           1
+#define RT_PUSH_IPI_RESTART             2
+
+static void tell_cpu_to_push(struct rq *rq)
+{
+        int cpu;
+
+        if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+                raw_spin_lock(&rq->rt.push_lock);
+                /* Make sure it's still executing */
+                if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+                        /*
+                         * Tell the IPI to restart the loop as things have
+                         * changed since it started.
+                         */
+                        rq->rt.push_flags |= RT_PUSH_IPI_RESTART;
+                        raw_spin_unlock(&rq->rt.push_lock);
+                        return;
+                }
+                raw_spin_unlock(&rq->rt.push_lock);
+        }
+
+        /* When here, there's no IPI going around */
+
+        rq->rt.push_cpu = rq->cpu;
+        cpu = find_next_push_cpu(rq);
+        if (cpu >= nr_cpu_ids)
+                return;
+
+        rq->rt.push_flags = RT_PUSH_IPI_EXECUTING;
+
+        irq_work_queue_on(&rq->rt.push_work, cpu);
+}
+
+/* Called from hardirq context */
+static void try_to_push_tasks(void *arg)
+{
+        struct rt_rq *rt_rq = arg;
+        struct rq *rq, *src_rq;
+        int this_cpu;
+        int cpu;
+
+        this_cpu = rt_rq->push_cpu;
+
+        /* Paranoid check */
+        BUG_ON(this_cpu != smp_processor_id());
+
+        rq = cpu_rq(this_cpu);
+        src_rq = rq_of_rt_rq(rt_rq);
+
+again:
+        if (has_pushable_tasks(rq)) {
+                raw_spin_lock(&rq->lock);
+                push_rt_task(rq);
+                raw_spin_unlock(&rq->lock);
+        }
+
+        /* Pass the IPI to the next rt overloaded queue */
+        raw_spin_lock(&rt_rq->push_lock);
+        /*
+         * If the source queue changed since the IPI went out,
+         * we need to restart the search from that CPU again.
+         */
+        if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) {
+                rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART;
+                rt_rq->push_cpu = src_rq->cpu;
+        }
+
+        cpu = find_next_push_cpu(src_rq);
+
+        if (cpu >= nr_cpu_ids)
+                rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING;
+        raw_spin_unlock(&rt_rq->push_lock);
+
+        if (cpu >= nr_cpu_ids)
+                return;
+
+        /*
+         * It is possible that a restart caused this CPU to be
+         * chosen again. Don't bother with an IPI, just see if we
+         * have more to push.
+         */
+        if (unlikely(cpu == rq->cpu))
+                goto again;
+
+        /* Try the next RT overloaded CPU */
+        irq_work_queue_on(&rt_rq->push_work, cpu);
+}
+
+static void push_irq_work_func(struct irq_work *work)
+{
+        struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work);
+
+        try_to_push_tasks(rt_rq);
+}
+#endif /* HAVE_RT_PUSH_IPI */
+
 static int pull_rt_task(struct rq *this_rq)
 {
         int this_cpu = this_rq->cpu, ret = 0, cpu;
@@ -1793,6 +1963,13 @@ static int pull_rt_task(struct rq *this_rq)
          */
         smp_rmb();
 
+#ifdef HAVE_RT_PUSH_IPI
+        if (sched_feat(RT_PUSH_IPI)) {
+                tell_cpu_to_push(this_rq);
+                return 0;
+        }
+#endif
+
         for_each_cpu(cpu, this_rq->rd->rto_mask) {
                 if (this_cpu == cpu)
                         continue;