sched/uclamp: Protect uclamp fast path code with static key

There is a report that when uclamp is enabled, a netperf UDP test
regresses compared to a kernel compiled without uclamp.

https://lore.kernel.org/lkml/20200529100806.GA3070@suse.de/

While investigating the root cause, there were no sign that the uclamp
code is doing anything particularly expensive but could suffer from bad
cache behavior under certain circumstances that are yet to be
understood.

https://lore.kernel.org/lkml/20200616110824.dgkkbyapn3io6wik@e107158-lin/

To reduce the pressure on the fast path anyway, add a static key that is
by default will skip executing uclamp logic in the
enqueue/dequeue_task() fast path until it's needed.

As soon as the user start using util clamp by:

	1. Changing uclamp value of a task with sched_setattr()
	2. Modifying the default sysctl_sched_util_clamp_{min, max}
	3. Modifying the default cpu.uclamp.{min, max} value in cgroup

We flip the static key now that the user has opted to use util clamp.
Effectively re-introducing uclamp logic in the enqueue/dequeue_task()
fast path. It stays on from that point forward until the next reboot.

This should help minimize the effect of util clamp on workloads that
don't need it but still allow distros to ship their kernels with uclamp
compiled in by default.

SCHED_WARN_ON() in uclamp_rq_dec_id() was removed since now we can end
up with unbalanced call to uclamp_rq_dec_id() if we flip the key while
a task is running in the rq. Since we know it is harmless we just
quietly return if we attempt a uclamp_rq_dec_id() when
rq->uclamp[].bucket[].tasks is 0.

In schedutil, we introduce a new uclamp_is_enabled() helper which takes
the static key into account to ensure RT boosting behavior is retained.

The following results demonstrates how this helps on 2 Sockets Xeon E5
2x10-Cores system.

                                   nouclamp                 uclamp      uclamp-static-key
Hmean     send-64         162.43 (   0.00%)      157.84 *  -2.82%*      163.39 *   0.59%*
Hmean     send-128        324.71 (   0.00%)      314.78 *  -3.06%*      326.18 *   0.45%*
Hmean     send-256        641.55 (   0.00%)      628.67 *  -2.01%*      648.12 *   1.02%*
Hmean     send-1024      2525.28 (   0.00%)     2448.26 *  -3.05%*     2543.73 *   0.73%*
Hmean     send-2048      4836.14 (   0.00%)     4712.08 *  -2.57%*     4867.69 *   0.65%*
Hmean     send-3312      7540.83 (   0.00%)     7425.45 *  -1.53%*     7621.06 *   1.06%*
Hmean     send-4096      9124.53 (   0.00%)     8948.82 *  -1.93%*     9276.25 *   1.66%*
Hmean     send-8192     15589.67 (   0.00%)    15486.35 *  -0.66%*    15819.98 *   1.48%*
Hmean     send-16384    26386.47 (   0.00%)    25752.25 *  -2.40%*    26773.74 *   1.47%*

The perf diff between nouclamp and uclamp-static-key when uclamp is
disabled in the fast path:

     8.73%     -1.55%  [kernel.kallsyms]        [k] try_to_wake_up
     0.07%     +0.04%  [kernel.kallsyms]        [k] deactivate_task
     0.13%     -0.02%  [kernel.kallsyms]        [k] activate_task

The diff between nouclamp and uclamp-static-key when uclamp is enabled
in the fast path:

     8.73%     -0.72%  [kernel.kallsyms]        [k] try_to_wake_up
     0.13%     +0.39%  [kernel.kallsyms]        [k] activate_task
     0.07%     +0.38%  [kernel.kallsyms]        [k] deactivate_task

Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcounting")
Reported-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20200630112123.12076-3-qais.yousef@arm.com

1 files changed, 45 insertions, 2 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9bef2dd01247..b1432f608061 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -878,6 +878,8 @@ struct uclamp_rq {
 	unsigned int value;
 	struct uclamp_bucket bucket[UCLAMP_BUCKETS];
 };
+
+DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
 /*
@@ -2365,12 +2367,35 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #ifdef CONFIG_UCLAMP_TASK
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq:		The rq to clamp against. Must not be NULL.
+ * @util:	The util value to clamp.
+ * @p:		The task to clamp against. Can be NULL if you want to clamp
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
 static __always_inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 				  struct task_struct *p)
 {
-	unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+	unsigned long min_util;
+	unsigned long max_util;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return util;
+
+	min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
 
 	if (p) {
 		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
@@ -2387,6 +2412,19 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 
 	return clamp(util, min_util, max_util);
 }
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	return static_branch_likely(&sched_uclamp_used);
+}
 #else /* CONFIG_UCLAMP_TASK */
 static inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
@@ -2394,6 +2432,11 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 {
 	return util;
 }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef arch_scale_freq_capacity