UPSTREAM: sched/fair: Let asymmetric CPU configurations balance at wake-up

Currently, SD_WAKE_AFFINE always takes priority over wakeup balancing if
SD_BALANCE_WAKE is set on the sched_domains. For asymmetric
configurations SD_WAKE_AFFINE is only desirable if the waking task's
compute demand (utilization) is suitable for the waking CPU and the
previous CPU, and all CPUs within their respective
SD_SHARE_PKG_RESOURCES domains (sd_llc). If not, let wakeup balancing
take over (find_idlest_{group, cpu}()).

This patch makes affine wake-ups conditional on whether both the waker
CPU and the previous CPU has sufficient capacity for the waking task,
or not, assuming that the CPU capacities within an SD_SHARE_PKG_RESOURCES
domain (sd_llc) are homogeneous.

Change-Id: I6d5d0426713da9ef6198f574ad9afbe58dacc1f0
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: freedom.tan@mediatek.com
Cc: keita.kobayashi.ym@renesas.com
Cc: mgalbraith@suse.de
Cc: sgurrappadi@nvidia.com
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1469453670-2660-10-git-send-email-morten.rasmussen@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 3273163c6775c4c21823985304c2364b08ca6ea2)
[removed existing definition of capacity_margin]
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

1 files changed, 54 insertions, 3 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5294c5f47939..19edbc48b1bc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -128,6 +128,12 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
 unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
 #endif
 
+/*
+ * The margin used when comparing utilization with CPU capacity:
+ * util * 1024 < capacity * margin
+ */
+unsigned int capacity_margin = 1280; /* ~20% */
+
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
@@ -5358,8 +5364,6 @@ static inline unsigned long task_util(struct task_struct *p)
 	return p->se.avg.util_avg;
 }
 
-unsigned int capacity_margin = 1280; /* ~20% margin */
-
 static inline unsigned long boosted_task_util(struct task_struct *task);
 
 static inline bool __task_fits(struct task_struct *p, int cpu, int util)
@@ -5496,6 +5500,13 @@ boosted_task_util(struct task_struct *task)
 	return util + margin;
 }
 
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+	return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+}
+
 /*
  * find_idlest_group finds and returns the least busy CPU group within the
  * domain.
@@ -5900,6 +5911,45 @@ static int energy_aware_wake_cpu(struct task_struct *p, int target, int sync)
 }
 
 /*
+ * cpu_util_wake: Compute cpu utilization with any contributions from
+ * the waking task p removed.
+ */
+static int cpu_util_wake(int cpu, struct task_struct *p)
+{
+	unsigned long util, capacity;
+
+	/* Task has no contribution or is new */
+	if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
+		return cpu_util(cpu);
+
+	capacity = capacity_orig_of(cpu);
+	util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0);
+
+	return (util >= capacity) ? capacity : util;
+}
+
+/*
+ * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
+ * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
+ *
+ * In that case WAKE_AFFINE doesn't make sense and we'll let
+ * BALANCE_WAKE sort things out.
+ */
+static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
+{
+	long min_cap, max_cap;
+
+	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
+	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+	/* Minimum capacity is close to max, no need to abort wake_affine */
+	if (max_cap - min_cap < max_cap >> 3)
+		return 0;
+
+	return min_cap * 1024 < task_util(p) * capacity_margin;
+}
+
+/*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
  * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
  * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
@@ -5921,7 +5971,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	int sync = wake_flags & WF_SYNC;
 
 	if (sd_flag & SD_BALANCE_WAKE)
-		want_affine = (!wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) ||
+		want_affine = (!wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
+					&& cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) ||
 			      energy_aware();
 
 	rcu_read_lock();