sched/uclamp: Add CPU's clamp buckets refcounting

Utilization clamping allows to clamp the CPU's utilization within a
[util_min, util_max] range, depending on the set of RUNNABLE tasks on
that CPU. Each task references two "clamp buckets" defining its minimum
and maximum (util_{min,max}) utilization "clamp values". A CPU's clamp
bucket is active if there is at least one RUNNABLE tasks enqueued on
that CPU and refcounting that bucket.

When a task is {en,de}queued {on,from} a rq, the set of active clamp
buckets on that CPU can change. If the set of active clamp buckets
changes for a CPU a new "aggregated" clamp value is computed for that
CPU. This is because each clamp bucket enforces a different utilization
clamp value.

Clamp values are always MAX aggregated for both util_min and util_max.
This ensures that no task can affect the performance of other
co-scheduled tasks which are more boosted (i.e. with higher util_min
clamp) or less capped (i.e. with higher util_max clamp).

A task has:
   task_struct::uclamp[clamp_id]::bucket_id
to track the "bucket index" of the CPU's clamp bucket it refcounts while
enqueued, for each clamp index (clamp_id).

A runqueue has:
   rq::uclamp[clamp_id]::bucket[bucket_id].tasks
to track how many RUNNABLE tasks on that CPU refcount each
clamp bucket (bucket_id) of a clamp index (clamp_id).
It also has a:
   rq::uclamp[clamp_id]::bucket[bucket_id].value
to track the clamp value of each clamp bucket (bucket_id) of a clamp
index (clamp_id).

The rq::uclamp::bucket[clamp_id][] array is scanned every time it's
needed to find a new MAX aggregated clamp value for a clamp_id. This
operation is required only when it's dequeued the last task of a clamp
bucket tracking the current MAX aggregated clamp value. In this case,
the CPU is either entering IDLE or going to schedule a less boosted or
more clamped task.
The expected number of different clamp values configured at build time
is small enough to fit the full unordered array into a single cache
line, for configurations of up to 7 buckets.

Add to struct rq the basic data structures required to refcount the
number of RUNNABLE tasks for each clamp bucket. Add also the max
aggregation required to update the rq's clamp value at each
enqueue/dequeue event.

Use a simple linear mapping of clamp values into clamp buckets.
Pre-compute and cache bucket_id to avoid integer divisions at
enqueue/dequeue time.

Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alessio Balsini <balsini@android.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Perret <quentin.perret@arm.com>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Steve Muckle <smuckle@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Todd Kjos <tkjos@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lkml.kernel.org/r/20190621084217.8167-2-patrick.bellasi@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 73 insertions, 6 deletions

diff --git a/include/linux/log2.h b/include/linux/log2.h
index 1aec01365ed4..83a4a3ca3e8a 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -220,4 +220,38 @@ int __order_base_2(unsigned long n)
 		ilog2((n) - 1) + 1) :		\
 	__order_base_2(n)			\
 )
+
+static inline __attribute__((const))
+int __bits_per(unsigned long n)
+{
+	if (n < 2)
+		return 1;
+	if (is_power_of_2(n))
+		return order_base_2(n) + 1;
+	return order_base_2(n);
+}
+
+/**
+ * bits_per - calculate the number of bits required for the argument
+ * @n: parameter
+ *
+ * This is constant-capable and can be used for compile time
+ * initializations, e.g bitfields.
+ *
+ * The first few values calculated by this routine:
+ * bf(0) = 1
+ * bf(1) = 1
+ * bf(2) = 2
+ * bf(3) = 2
+ * bf(4) = 3
+ * ... and so on.
+ */
+#define bits_per(n)				\
+(						\
+	__builtin_constant_p(n) ? (		\
+		((n) == 0 || (n) == 1)		\
+			? 1 : ilog2(n) + 1	\
+	) :					\
+	__bits_per(n)				\
+)
 #endif /* _LINUX_LOG2_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 044c023875e8..80235bcd05f2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -283,6 +283,18 @@ struct vtime {
 	u64			gtime;
 };
 
+/*
+ * Utilization clamp constraints.
+ * @UCLAMP_MIN:	Minimum utilization
+ * @UCLAMP_MAX:	Maximum utilization
+ * @UCLAMP_CNT:	Utilization clamp constraints count
+ */
+enum uclamp_id {
+	UCLAMP_MIN = 0,
+	UCLAMP_MAX,
+	UCLAMP_CNT
+};
+
 struct sched_info {
 #ifdef CONFIG_SCHED_INFO
 	/* Cumulative counters: */
@@ -314,6 +326,10 @@ struct sched_info {
 # define SCHED_FIXEDPOINT_SHIFT		10
 # define SCHED_FIXEDPOINT_SCALE		(1L << SCHED_FIXEDPOINT_SHIFT)
 
+/* Increase resolution of cpu_capacity calculations */
+# define SCHED_CAPACITY_SHIFT		SCHED_FIXEDPOINT_SHIFT
+# define SCHED_CAPACITY_SCALE		(1L << SCHED_CAPACITY_SHIFT)
+
 struct load_weight {
 	unsigned long			weight;
 	u32				inv_weight;
@@ -562,6 +578,25 @@ struct sched_dl_entity {
 	struct hrtimer inactive_timer;
 };
 
+#ifdef CONFIG_UCLAMP_TASK
+/* Number of utilization clamp buckets (shorter alias) */
+#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT
+
+/*
+ * Utilization clamp for a scheduling entity
+ * @value:		clamp value "assigned" to a se
+ * @bucket_id:		bucket index corresponding to the "assigned" value
+ *
+ * The bucket_id is the index of the clamp bucket matching the clamp value
+ * which is pre-computed and stored to avoid expensive integer divisions from
+ * the fast path.
+ */
+struct uclamp_se {
+	unsigned int value		: bits_per(SCHED_CAPACITY_SCALE);
+	unsigned int bucket_id		: bits_per(UCLAMP_BUCKETS);
+};
+#endif /* CONFIG_UCLAMP_TASK */
+
 union rcu_special {
 	struct {
 		u8			blocked;
@@ -642,6 +677,10 @@ struct task_struct {
 #endif
 	struct sched_dl_entity		dl;
 
+#ifdef CONFIG_UCLAMP_TASK
+	struct uclamp_se		uclamp[UCLAMP_CNT];
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* List of struct preempt_notifier: */
 	struct hlist_head		preempt_notifiers;
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index e445d3767cdd..7863bb62d2ab 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -7,12 +7,6 @@
 #include <linux/sched/idle.h>
 
 /*
- * Increase resolution of cpu_capacity calculations
- */
-#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
-#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
-
-/*
  * sched-domains (multiprocessor balancing) declarations:
  */
 #ifdef CONFIG_SMP