[PATCH v12 9/9] timers: Exclude isolated cpus from timer migration

[Gabriele Monaco <gmonaco@redhat.com>]

The timer migration mechanism allows active CPUs to pull timers from
idle ones to improve the overall idle time. This is however undesired
when CPU intensive workloads run on isolated cores, as the algorithm
would move the timers from housekeeping to isolated cores, negatively
affecting the isolation.

Exclude isolated cores from the timer migration algorithm, extend the
concept of unavailable cores, currently used for offline ones, to
isolated ones:
* A core is unavailable if isolated or offline;
* A core is available if non isolated and online;

A core is considered unavailable as isolated if it belongs to:
* the isolcpus (domain) list
* an isolated cpuset
Except if it is:
* in the nohz_full list (already idle for the hierarchy)
* the nohz timekeeper core (must be available to handle global timers)

CPUs are added to the hierarchy during late boot, excluding isolated
ones, the hierarchy is also adapted when the cpuset isolation changes.

Due to how the timer migration algorithm works, any CPU part of the
hierarchy can have their global timers pulled by remote CPUs and have to
pull remote timers, only skipping pulling remote timers would break the
logic.
For this reason, prevent isolated CPUs from pulling remote global
timers, but also the other way around: any global timer started on an
isolated CPU will run there. This does not break the concept of
isolation (global timers don't come from outside the CPU) and, if
considered inappropriate, can usually be mitigated with other isolation
techniques (e.g. IRQ pinning).

This effect was noticed on a 128 cores machine running oslat on the
isolated cores (1-31,33-63,65-95,97-127). The tool monopolises CPUs,
and the CPU with lowest count in a timer migration hierarchy (here 1
and 65) appears as always active and continuously pulls global timers,
from the housekeeping CPUs. This ends up moving driver work (e.g.
delayed work) to isolated CPUs and causes latency spikes:

before the change:

 # oslat -c 1-31,33-63,65-95,97-127 -D 62s
 ...
  Maximum:     1203 10 3 4 ... 5 (us)

after the change:

 # oslat -c 1-31,33-63,65-95,97-127 -D 62s
 ...
  Maximum:      10 4 3 4 3 ... 5 (us)

Tested-by: John B. Wyatt IV <jwyatt@redhat.com>
Tested-by: John B. Wyatt IV <sageofredondo@gmail.com>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
 include/linux/timer.h         |   9 +++
 kernel/cgroup/cpuset.c        |   3 +
 kernel/time/timer_migration.c | 108 +++++++++++++++++++++++++++++++++-
 3 files changed, 119 insertions(+), 1 deletion(-)

diff --git a/include/linux/timer.h b/include/linux/timer.h
index 0414d9e6b4fc..62e1cea71125 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -188,4 +188,13 @@ int timers_dead_cpu(unsigned int cpu);
 #define timers_dead_cpu		NULL
 #endif
 
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask);
+#else
+static inline int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3cedc3580373..6e9d86fab27e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1399,6 +1399,9 @@ static void update_exclusion_cpumasks(bool isolcpus_updated)
 
 	ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
 	WARN_ON_ONCE(ret < 0);
+
+	ret = tmigr_isolated_exclude_cpumask(isolated_cpus);
+	WARN_ON_ONCE(ret < 0);
 }
 
 /**
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 0a3a26e766d0..08e29fc01479 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/timerqueue.h>
 #include <trace/events/ipi.h>
+#include <linux/sched/isolation.h>
 
 #include "timer_migration.h"
 #include "tick-internal.h"
@@ -436,6 +437,29 @@ static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc)
 	return !(tmc->tmgroup && tmc->available);
 }
 
+/*
+ * Returns true if @cpu should be excluded from the hierarchy as isolated.
+ * Domain isolated CPUs don't participate in timer migration, nohz_full CPUs
+ * are still part of the hierarchy but become idle (from a tick and timer
+ * migration perspective) when they stop their tick. This lets the timekeeping
+ * CPU handle their global timers. Marking also isolated CPUs as idle would be
+ * too costly, hence they are completely excluded from the hierarchy.
+ * This check is necessary, for instance, to prevent offline isolated CPUs from
+ * being incorrectly marked as available once getting back online.
+ *
+ * Additionally, the tick CPU can be isolated at boot, however
+ * we cannot mark it as unavailable to avoid having no global migrator
+ * for the nohz_full CPUs. This check is only necessary at boot time.
+ */
+static inline bool tmigr_is_isolated(int cpu)
+{
+	if (!tick_nohz_cpu_hotpluggable(cpu))
+		return false;
+	return (!housekeeping_cpu(cpu, HK_TYPE_DOMAIN) ||
+		cpuset_cpu_is_isolated(cpu)) &&
+	       housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE);
+}
+
 /*
  * Returns true, when @childmask corresponds to the group migrator or when the
  * group is not active - so no migrator is set.
@@ -1451,6 +1475,8 @@ static int tmigr_clear_cpu_available(unsigned int cpu)
 
 	cpumask_clear_cpu(cpu, tmigr_available_cpumask);
 	scoped_guard(raw_spinlock_irq, &tmc->lock) {
+		if (!tmc->available)
+			return 0;
 		tmc->available = false;
 		WRITE_ONCE(tmc->wakeup, KTIME_MAX);
 
@@ -1478,8 +1504,12 @@ static int tmigr_set_cpu_available(unsigned int cpu)
 	if (WARN_ON_ONCE(!tmc->tmgroup))
 		return -EINVAL;
 
+	if (tmigr_is_isolated(cpu))
+		return 0;
 	cpumask_set_cpu(cpu, tmigr_available_cpumask);
 	scoped_guard(raw_spinlock_irq, &tmc->lock) {
+		if (tmc->available)
+			return 0;
 		trace_tmigr_cpu_available(tmc);
 		tmc->idle = timer_base_is_idle();
 		if (!tmc->idle)
@@ -1489,6 +1519,81 @@ static int tmigr_set_cpu_available(unsigned int cpu)
 	return 0;
 }
 
+static void tmigr_cpu_isolate(struct work_struct *ignored)
+{
+	tmigr_clear_cpu_available(smp_processor_id());
+}
+
+static void tmigr_cpu_unisolate(struct work_struct *ignored)
+{
+	tmigr_set_cpu_available(smp_processor_id());
+}
+
+/**
+ * tmigr_isolated_exclude_cpumask - Exclude given CPUs from hierarchy
+ * @exclude_cpumask: the cpumask to be excluded from timer migration hierarchy
+ *
+ * This function can be called from cpuset code to provide the new set of
+ * isolated CPUs that should be excluded from the hierarchy.
+ * Online CPUs not present in exclude_cpumask but already excluded are brought
+ * back to the hierarchy.
+ * Functions to isolate/unisolate need to be called locally and can sleep.
+ */
+int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
+{
+	struct work_struct __percpu *works __free(free_percpu) =
+		alloc_percpu(struct work_struct);
+	cpumask_var_t cpumask_unisol __free(free_cpumask_var) = CPUMASK_NULL;
+	cpumask_var_t cpumask_isol __free(free_cpumask_var) = CPUMASK_NULL;
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!alloc_cpumask_var(&cpumask_isol, GFP_KERNEL))
+		return -ENOMEM;
+	if (!alloc_cpumask_var(&cpumask_unisol, GFP_KERNEL))
+		return -ENOMEM;
+	if (!works)
+		return -ENOMEM;
+
+	cpumask_andnot(cpumask_unisol, cpu_online_mask, exclude_cpumask);
+	cpumask_andnot(cpumask_unisol, cpumask_unisol, tmigr_available_cpumask);
+	/* Set up the mask earlier to avoid races with the migrator CPU */
+	cpumask_or(tmigr_available_cpumask, tmigr_available_cpumask, cpumask_unisol);
+	for_each_cpu(cpu, cpumask_unisol) {
+		struct work_struct *work = per_cpu_ptr(works, cpu);
+
+		INIT_WORK(work, tmigr_cpu_unisolate);
+		schedule_work_on(cpu, work);
+	}
+
+	cpumask_and(cpumask_isol, exclude_cpumask, tmigr_available_cpumask);
+	cpumask_and(cpumask_isol, cpumask_isol, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE));
+	/*
+	 * Handle this here and not in the cpuset code because exclude_cpumask
+	 * might include also the tick CPU if included in isolcpus.
+	 */
+	for_each_cpu(cpu, cpumask_isol) {
+		if (!tick_nohz_cpu_hotpluggable(cpu)) {
+			cpumask_clear_cpu(cpu, cpumask_isol);
+			break;
+		}
+	}
+	/* Set up the mask earlier to avoid races with the migrator CPU */
+	cpumask_andnot(tmigr_available_cpumask, tmigr_available_cpumask, cpumask_isol);
+	for_each_cpu(cpu, cpumask_isol) {
+		struct work_struct *work = per_cpu_ptr(works, cpu);
+
+		INIT_WORK(work, tmigr_cpu_isolate);
+		schedule_work_on(cpu, work);
+	}
+
+	for_each_cpu_or(cpu, cpumask_isol, cpumask_unisol)
+		flush_work(per_cpu_ptr(works, cpu));
+
+	return 0;
+}
+
 /*
  * NOHZ can only be enabled after clocksource_done_booting(). Don't
  * bother trashing the cache in the tree before.
@@ -1496,7 +1601,8 @@ static int tmigr_set_cpu_available(unsigned int cpu)
 static int __init tmigr_late_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online",
-				 tmigr_set_cpu_available, tmigr_clear_cpu_available);
+				 tmigr_set_cpu_available,
+				 tmigr_clear_cpu_available);
 }
 
 static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
-- 
2.51.0