sched: Add yield_to(task, preempt) functionality

Currently only implemented for fair class tasks.

Add a yield_to_task method() to the fair scheduling class. allowing the
caller of yield_to() to accelerate another thread in it's thread group,
task group.

Implemented via a scheduler hint, using cfs_rq->next to encourage the
target being selected.  We can rely on pick_next_entity to keep things
fair, so noone can accelerate a thread that has already used its fair
share of CPU time.

This also means callers should only call yield_to when they really
mean it.  Calling it too often can result in the scheduler just
ignoring the hint.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110201095051.4ddb7738@annuminas.surriel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4e9fad271c30606847664c368a398bce194797d7..c88b3bfbd09e9e05920e033d7d3bce88d44a3068 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1058,6 +1058,7 @@ struct sched_class {
        void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
        void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
        void (*yield_task) (struct rq *rq);
+       bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
 
        void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
@@ -1972,6 +1973,7 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 # define rt_mutex_adjust_pi(p)         do { } while (0)
 #endif
 
+extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);

diff --git a/kernel/sched.c b/kernel/sched.c
index ae5e1a19b9d6ba4f6796b892cc5a204d82b3dbfd..2effcb71a47849224a9dcd58c78a769bd498740b 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1686,6 +1686,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
                __release(rq2->lock);
 }
 
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+       __acquires(rq1->lock)
+       __acquires(rq2->lock)
+{
+       BUG_ON(!irqs_disabled());
+       BUG_ON(rq1 != rq2);
+       raw_spin_lock(&rq1->lock);
+       __acquire(rq2->lock);   /* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+       __releases(rq1->lock)
+       __releases(rq2->lock)
+{
+       BUG_ON(rq1 != rq2);
+       raw_spin_unlock(&rq1->lock);
+       __release(rq2->lock);
+}
+
 #endif
 
 static void calc_load_account_idle(struct rq *this_rq);
@@ -5448,6 +5481,58 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+       struct task_struct *curr = current;
+       struct rq *rq, *p_rq;
+       unsigned long flags;
+       bool yielded = 0;
+
+       local_irq_save(flags);
+       rq = this_rq();
+
+again:
+       p_rq = task_rq(p);
+       double_rq_lock(rq, p_rq);
+       while (task_rq(p) != p_rq) {
+               double_rq_unlock(rq, p_rq);
+               goto again;
+       }
+
+       if (!curr->sched_class->yield_to_task)
+               goto out;
+
+       if (curr->sched_class != p->sched_class)
+               goto out;
+
+       if (task_running(p_rq, p) || p->state)
+               goto out;
+
+       yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+       if (yielded)
+               schedstat_inc(rq, yld_count);
+
+out:
+       double_rq_unlock(rq, p_rq);
+       local_irq_restore(flags);
+
+       if (yielded)
+               schedule();
+
+       return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c0fbeb992833a356ea3e42a68a429b11accd39e2..0270246940432f9adc0d0e72f9f60353e229a0e7 100644 (file)
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1975,6 +1975,25 @@ static void yield_task_fair(struct rq *rq)
        set_skip_buddy(se);
 }
 
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+       struct sched_entity *se = &p->se;
+
+       if (!se->on_rq)
+               return false;
+
+       /* Tell the scheduler that we'd really like pse to run next. */
+       set_next_buddy(se);
+
+       /* Make p's CPU reschedule; pick_next_entity takes care of fairness. */
+       if (preempt)
+               resched_task(rq->curr);
+
+       yield_task_fair(rq);
+
+       return true;
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
@@ -4243,6 +4262,7 @@ static const struct sched_class fair_sched_class = {
        .enqueue_task           = enqueue_task_fair,
        .dequeue_task           = dequeue_task_fair,
        .yield_task             = yield_task_fair,
+       .yield_to_task          = yield_to_task_fair,
 
        .check_preempt_curr     = check_preempt_wakeup,