[PATCH v2 1/4] tick/nohz: Re-evaluate the tick on return to user space

[Marco Crivellari <marco.crivellari@suse.com>]

On nohz_full CPUs the tick is re-evaluated on IRQ exit and on idle exit.

This is not enough on return to user space. If the tick is left running in
the kernel, for example because a tick dependency was cleared
(tick_nohz_dep_clear*() don't kick the CPU) or a timer that kept it
running was cancelled, it fires at least once in userspace before
tick_nohz_irq_exit() stops it.

Stop it from context tracking right before resuming userspace. When the
tick is already stopped, the common case, this costs a few flag tests on
each return to userspace.

Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Anna-Maria Behnsen <anna-maria@linutronix.de>
Cc: Thomas Gleixner <tglx@kernel.org>
Suggested-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
---
 include/linux/tick.h      |  8 ++++++++
 kernel/context_tracking.c |  8 ++++++++
 kernel/time/tick-sched.c  | 24 ++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index b121c5d53e30..8bfbb053f4fd 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -269,6 +269,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void __tick_nohz_task_switch(void);
 extern void __init tick_nohz_full_setup(cpumask_var_t cpumask);
+extern void __tick_nohz_user_enter(void);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
@@ -294,6 +295,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal,
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void __tick_nohz_task_switch(void) { }
 static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { }
+static inline void __tick_nohz_user_enter(void) { }
 #endif
 
 static inline void tick_nohz_task_switch(void)
@@ -302,6 +304,12 @@ static inline void tick_nohz_task_switch(void)
 		__tick_nohz_task_switch();
 }
 
+static inline void tick_nohz_user_enter(void)
+{
+	if (tick_nohz_full_enabled())
+		__tick_nohz_user_enter();
+}
+
 static inline void tick_nohz_user_enter_prepare(void)
 {
 	if (tick_nohz_full_cpu(smp_processor_id()))
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index a743e7ffa6c0..347f99e1880f 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 #include <linux/kprobes.h>
 #include <trace/events/rcu.h>
+#include <linux/tick.h>
 
 
 DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
@@ -466,6 +467,13 @@ void noinstr __ct_user_enter(enum ctx_state state)
 			 */
 			if (state == CT_STATE_USER) {
 				instrumentation_begin();
+				/*
+				 * On nohz_full CPUs the tick may have been left running in the
+				 * kernel, e.g. kept by a tick dependency that is now gone.
+				 * Stop it now rather than let it interrupt userspace once
+				 * more before the next IRQ exit notices.
+				 */
+				tick_nohz_user_enter();
 				trace_user_enter(0);
 				vtime_user_enter(current);
 				instrumentation_end();
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c6d86e4da8a9..645dba919386 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1071,6 +1071,30 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	__tick_nohz_full_update_tick(ts, ktime_get());
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+void __tick_nohz_user_enter(void)
+{
+	struct tick_sched *ts;
+	int cpu;
+
+	lockdep_assert_irqs_disabled();
+
+	cpu = smp_processor_id();
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	ts = this_cpu_ptr(&tick_cpu_sched);
+	if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ))
+		return;
+
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
+		return;
+
+	if (can_stop_full_tick(cpu, ts))
+		tick_nohz_full_stop_tick(ts, cpu);
+}
+#endif
+
 /*
  * A pending softirq outside an IRQ (or softirq disabled section) context
  * should be waiting for ksoftirqd to handle it. Therefore we shouldn't
-- 
2.56.0