[RFC PATCH v2 1/2] tick/nohz: Add a policy dependency for full dynticks

[Peng Wang <peng_wang@linux.alibaba.com>]

Cloud hosts may pin vCPU threads one-to-one to host CPUs. At full
allocation this includes the housekeeping CPUs, which always retain
their non-idle tick. Operators want comparable performance for otherwise
equivalent vCPUs. Retaining the non-idle tick on nohz_full CPUs as well
avoids one placement-dependent difference in host tick interference.
With spare capacity, selected CPUs may stop the tick to reduce host
scheduler-tick interference with vCPUs.

Allocation changes as VMs are created or destroyed while other VMs
remain running. A vCPU thread may be the only runnable task in either
state, so existing tick dependencies do not express this policy.

Add a per-CPU POLICY dependency within the boot-time nohz_full set.
Permission defaults to enabled. The policy can be changed without
taking CPUs offline. Revoking permission uses the existing asynchronous
kick; granting it leaves all other dependencies effective. Preserve
POLICY across CPU hotplug and report it in tick_stop tracing.

Idle tick suppression, nohz_full membership, context tracking, RCU
offloading and housekeeping configuration are unchanged.

Co-developed-by: He Rongguang <herongguang@linux.alibaba.com>
Signed-off-by: He Rongguang <herongguang@linux.alibaba.com>
Signed-off-by: Peng Wang <peng_wang@linux.alibaba.com>
---
 include/linux/tick.h         |  8 +++++--
 include/trace/events/timer.h |  3 ++-
 kernel/time/tick-sched.c     | 42 ++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index b121c5d53e308..8b250f245ff31 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -111,9 +111,10 @@ enum tick_dep_bits {
 	TICK_DEP_BIT_SCHED		= 2,
 	TICK_DEP_BIT_CLOCK_UNSTABLE	= 3,
 	TICK_DEP_BIT_RCU		= 4,
-	TICK_DEP_BIT_RCU_EXP		= 5
+	TICK_DEP_BIT_RCU_EXP		= 5,
+	TICK_DEP_BIT_POLICY		= 6
 };
-#define TICK_DEP_BIT_MAX TICK_DEP_BIT_RCU_EXP
+#define TICK_DEP_BIT_MAX TICK_DEP_BIT_POLICY
 
 #define TICK_DEP_MASK_NONE		0
 #define TICK_DEP_MASK_POSIX_TIMER	(1 << TICK_DEP_BIT_POSIX_TIMER)
@@ -122,6 +123,7 @@ enum tick_dep_bits {
 #define TICK_DEP_MASK_CLOCK_UNSTABLE	(1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
 #define TICK_DEP_MASK_RCU		(1 << TICK_DEP_BIT_RCU)
 #define TICK_DEP_MASK_RCU_EXP		(1 << TICK_DEP_BIT_RCU_EXP)
+#define TICK_DEP_MASK_POLICY		(1 << TICK_DEP_BIT_POLICY)
 
 #ifdef CONFIG_NO_HZ_COMMON
 extern bool tick_nohz_enabled;
@@ -205,6 +207,8 @@ extern void tick_nohz_dep_set_signal(struct task_struct *tsk,
 extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
 				       enum tick_dep_bits bit);
 extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu);
+extern bool tick_nohz_full_get_allowed(unsigned int cpu);
+extern int tick_nohz_full_set_allowed(unsigned int cpu, bool allowed);
 
 /*
  * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 3aa0608c63611..dff9579cd90eb 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -435,7 +435,8 @@ TRACE_EVENT(itimer_expire,
 		tick_dep_name(SCHED)			\
 		tick_dep_name(CLOCK_UNSTABLE)		\
 		tick_dep_name(RCU)			\
-		tick_dep_name_end(RCU_EXP)
+		tick_dep_name(RCU_EXP)			\
+		tick_dep_name_end(POLICY)
 
 #undef tick_dep_name
 #undef tick_dep_mask_name
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 87e2a7a875265..0d6fcc3736bae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -375,6 +375,11 @@ static bool check_tick_dependency(atomic_t *dep)
 		return true;
 	}
 
+	if (val & TICK_DEP_MASK_POLICY) {
+		trace_tick_stop(0, TICK_DEP_MASK_POLICY);
+		return true;
+	}
+
 	return false;
 }
 
@@ -561,6 +566,39 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 }
 EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
+/* Read policy, not whether a CPU currently has its tick stopped. */
+bool tick_nohz_full_get_allowed(unsigned int cpu)
+{
+	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	/* CPU teardown resets and restores this bit under stop_machine(). */
+	return !(atomic_read(&ts->tick_dep_mask) & TICK_DEP_MASK_POLICY);
+}
+
+int tick_nohz_full_set_allowed(unsigned int cpu, bool allowed)
+{
+	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	if (!tick_nohz_full_cpu(cpu))
+		return -EINVAL;
+
+	/* CPU device removal may wait for an active sysfs callback. */
+	if (!cpus_read_trylock())
+		return -EBUSY;
+
+	if (allowed) {
+		tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_POLICY);
+	} else if (cpu_online(cpu)) {
+		/* The existing kick requests an asynchronous restart. */
+		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_POLICY);
+	} else {
+		/* Record policy without queuing irq_work on an offline CPU. */
+		atomic_or(TICK_DEP_MASK_POLICY, &ts->tick_dep_mask);
+	}
+	cpus_read_unlock();
+	return 0;
+}
+
 /*
  * Set a per-task tick dependency. RCU needs this. Also posix CPU timers
  * in order to elapse per task timers.
@@ -1533,6 +1571,7 @@ void tick_sched_timer_dying(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long idle_calls, idle_sleeps;
+	int policy;
 
 	/* This must happen before hrtimers are migrated! */
 	if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES))
@@ -1540,7 +1579,10 @@ void tick_sched_timer_dying(int cpu)
 
 	idle_calls = ts->idle_calls;
 	idle_sleeps = ts->idle_sleeps;
+	/* Preserve only the policy dependency across CPU offline/online. */
+	policy = atomic_read(&ts->tick_dep_mask) & TICK_DEP_MASK_POLICY;
 	memset(ts, 0, sizeof(*ts));
+	atomic_set(&ts->tick_dep_mask, policy);
 	ts->idle_calls = idle_calls;
 	ts->idle_sleeps = idle_sleeps;
 }
-- 
2.47.0