sched: add /proc/sys/kernel/sched_compat_yield

add /proc/sys/kernel/sched_compat_yield to make sys_sched_yield()
more agressive, by moving the yielding task to the last position
in the rbtree.

with sched_compat_yield=0:

   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
  2539 mingo     20   0  1576  252  204 R   50  0.0   0:02.03 loop_yield
  2541 mingo     20   0  1576  244  196 R   50  0.0   0:02.05 loop

with sched_compat_yield=1:

   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
  2584 mingo     20   0  1576  248  196 R   99  0.0   0:52.45 loop
  2582 mingo     20   0  1576  256  204 R    0  0.0   0:00.00 loop_yield

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

4 files changed, 67 insertions, 10 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5445eaec6908..3de79016f2a6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1406,6 +1406,7 @@ extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_batch_wakeup_granularity;
 extern unsigned int sysctl_sched_stat_granularity;
 extern unsigned int sysctl_sched_runtime_limit;
+extern unsigned int sysctl_sched_compat_yield;
 extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index deeb1f8e0c30..63e0971c8fbb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4550,10 +4550,7 @@ asmlinkage long sys_sched_yield(void)
         struct rq *rq = this_rq_lock();
 
         schedstat_inc(rq, yld_cnt);
-        if (unlikely(rq->nr_running == 1))
-                schedstat_inc(rq, yld_act_empty);
-        else
-                current->sched_class->yield_task(rq, current);
+        current->sched_class->yield_task(rq, current);
 
         /*
          * Since we are going to call schedule() anyway, there's
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 892616bf2c77..c9fbe8e73a45 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -43,6 +43,14 @@ unsigned int sysctl_sched_latency __read_mostly = 20000000ULL;
 unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
 
 /*
+ * sys_sched_yield() compat mode
+ *
+ * This option switches the agressive yield implementation of the
+ * old scheduler back on.
+ */
+unsigned int __read_mostly sysctl_sched_compat_yield;
+
+/*
  * SCHED_BATCH wake-up granularity.
  * (default: 25 msec, units: nanoseconds)
  *
@@ -897,19 +905,62 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 }
 
 /*
- * sched_yield() support is very simple - we dequeue and enqueue
+ * sched_yield() support is very simple - we dequeue and enqueue.
+ *
+ * If compat_yield is turned on then we requeue to the end of the tree.
  */
 static void yield_task_fair(struct rq *rq, struct task_struct *p)
 {
         struct cfs_rq *cfs_rq = task_cfs_rq(p);
+        struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+        struct sched_entity *rightmost, *se = &p->se;
+        struct rb_node *parent;
 
-        __update_rq_clock(rq);
         /*
-         * Dequeue and enqueue the task to update its
-         * position within the tree:
+         * Are we the only task in the tree?
+         */
+        if (unlikely(cfs_rq->nr_running == 1))
+                return;
+
+        if (likely(!sysctl_sched_compat_yield)) {
+                __update_rq_clock(rq);
+                /*
+                 * Dequeue and enqueue the task to update its
+                 * position within the tree:
+                 */
+                dequeue_entity(cfs_rq, &p->se, 0);
+                enqueue_entity(cfs_rq, &p->se, 0);
+
+                return;
+        }
+        /*
+         * Find the rightmost entry in the rbtree:
          */
-        dequeue_entity(cfs_rq, &p->se, 0);
-        enqueue_entity(cfs_rq, &p->se, 0);
+        do {
+                parent = *link;
+                link = &parent->rb_right;
+        } while (*link);
+
+        rightmost = rb_entry(parent, struct sched_entity, run_node);
+        /*
+         * Already in the rightmost position?
+         */
+        if (unlikely(rightmost == se))
+                return;
+
+        /*
+         * Minimally necessary key value to be last in the tree:
+         */
+        se->fair_key = rightmost->fair_key + 1;
+
+        if (cfs_rq->rb_leftmost == &se->run_node)
+                cfs_rq->rb_leftmost = rb_next(&se->run_node);
+        /*
+         * Relink the task to the rightmost position:
+         */
+        rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+        rb_link_node(&se->run_node, parent, link);
+        rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6ace893c17c9..53a456ebf6d5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -303,6 +303,14 @@ static ctl_table kern_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
 #endif
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "sched_compat_yield",
+                .data           = &sysctl_sched_compat_yield,
+                .maxlen         = sizeof(unsigned int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec,
+        },
 #ifdef CONFIG_PROVE_LOCKING
         {
                 .ctl_name       = CTL_UNNUMBERED,