sched/fair: Move record_wakee()

Since I want to make ->task_woken() conditional on the task getting
migrated, we cannot use it to call record_wakee().

Move it to select_task_rq_fair(), which gets called in almost all the
same conditions. The only exception is if the woken task (@p) is
CPU-bound (as per the nr_cpus_allowed test in select_task_rq()).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Hunter <ahh@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Pavan Kondeti <pkondeti@codeaurora.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: byungchul.park@lge.com
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -4810,24 +4810,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	return 0;
 }
 
-static void record_wakee(struct task_struct *p)
-{
-	/*
-	 * Rough decay (wiping) for cost saving, don't worry
-	 * about the boundary, really active task won't care
-	 * about the loss.
-	 */
-	if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
-		current->wakee_flips >>= 1;
-		current->wakee_flip_decay_ts = jiffies;
-	}
-
-	if (current->last_wakee != p) {
-		current->last_wakee = p;
-		current->wakee_flips++;
-	}
-}
-
 static void task_waking_fair(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
@@ -4847,7 +4829,6 @@ static void task_waking_fair(struct task_struct *p)
 #endif
 
 	se->vruntime -= min_vruntime;
-	record_wakee(p);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -4965,17 +4946,39 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 
 #endif
 
+static void record_wakee(struct task_struct *p)
+{
+	/*
+	 * Only decay a single time; tasks that have less then 1 wakeup per
+	 * jiffy will not have built up many flips.
+	 */
+	if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
+		current->wakee_flips >>= 1;
+		current->wakee_flip_decay_ts = jiffies;
+	}
+
+	if (current->last_wakee != p) {
+		current->last_wakee = p;
+		current->wakee_flips++;
+	}
+}
+
 /*
  * Detect M:N waker/wakee relationships via a switching-frequency heuristic.
+ *
  * A waker of many should wake a different task than the one last awakened
- * at a frequency roughly N times higher than one of its wakees.  In order
- * to determine whether we should let the load spread vs consolodating to
- * shared cache, we look for a minimum 'flip' frequency of llc_size in one
- * partner, and a factor of lls_size higher frequency in the other.  With
- * both conditions met, we can be relatively sure that the relationship is
- * non-monogamous, with partner count exceeding socket size.  Waker/wakee
- * being client/server, worker/dispatcher, interrupt source or whatever is
- * irrelevant, spread criteria is apparent partner count exceeds socket size.
+ * at a frequency roughly N times higher than one of its wakees.
+ *
+ * In order to determine whether we should let the load spread vs consolidating
+ * to shared cache, we look for a minimum 'flip' frequency of llc_size in one
+ * partner, and a factor of lls_size higher frequency in the other.
+ *
+ * With both conditions met, we can be relatively sure that the relationship is
+ * non-monogamous, with partner count exceeding socket size.
+ *
+ * Waker/wakee being client/server, worker/dispatcher, interrupt source or
+ * whatever is irrelevant, spread criteria is apparent partner count exceeds
+ * socket size.
  */
 static int wake_wide(struct task_struct *p)
 {
@@ -5280,8 +5283,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	int want_affine = 0;
 	int sync = wake_flags & WF_SYNC;
 
-	if (sd_flag & SD_BALANCE_WAKE)
+	if (sd_flag & SD_BALANCE_WAKE) {
+		record_wakee(p);
 		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, tmp) {