Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Aaron Tomlin <atomlin@redhat.com>
To:     frederic@kernel.org, mtosatti@redhat.com
Cc:     cl@linux.com, tglx@linutronix.de, mingo@kernel.org,
        peterz@infradead.org, pauld@redhat.com, neelx@redhat.com,
        oleksandr@natalenko.name, atomlin@atomlin.com,
        akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org
Subject: [PATCH v8 4/5] tick/nohz_full: Ensure quiet_vmstat() is called on exit to user-mode when the idle tick is stopped
Date:   Sat, 24 Sep 2022 16:22:26 +0100
Message-Id: <20220924152227.819815-5-atomlin@redhat.com>
In-Reply-To: <20220924152227.819815-1-atomlin@redhat.com>
References: <20220924152227.819815-1-atomlin@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patch ensures CPU-specific vmstat differentials do not remain
when the scheduling-tick is stopped and before exiting to user-mode
in the context of nohz_full only.

A trivial test program was used to determine the impact of the proposed
changes and under vanilla. The mlock(2) and munlock(2) system calls was
used solely to modify vmstat item 'NR_MLOCK'. The following is an average
count of CPU-cycles across the aforementioned system calls:

				  Vanilla                 Modified

  Cycles per syscall              8461                    8690    (+2.6%)

Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
---
 include/linux/tick.h     |  5 +++--
 kernel/time/tick-sched.c | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/include/linux/tick.h b/include/linux/tick.h
index bfd571f18cfd..a2bbd6d32e33 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -11,7 +11,6 @@
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
 #include <linux/sched.h>
-#include <linux/rcupdate.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void __init tick_init(void);
@@ -272,6 +271,7 @@ 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);
+void __tick_nohz_user_enter_prepare(void);
 extern void __init tick_nohz_full_setup(cpumask_var_t cpumask);
 #else
 static inline bool tick_nohz_full_enabled(void) { return false; }
@@ -296,6 +296,7 @@ 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_user_enter_prepare(void) { }
 static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { }
 #endif
 
@@ -308,7 +309,7 @@ static inline void tick_nohz_task_switch(void)
 static inline void tick_nohz_user_enter_prepare(void)
 {
 	if (tick_nohz_full_cpu(smp_processor_id()))
-		rcu_nocb_flush_deferred_wakeup();
+		__tick_nohz_user_enter_prepare();
 }
 
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b0e3c9205946..634cd0fac267 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -26,6 +26,7 @@
 #include <linux/posix-timers.h>
 #include <linux/context_tracking.h>
 #include <linux/mm.h>
+#include <linux/rcupdate.h>
 
 #include <asm/irq_regs.h>
 
@@ -519,6 +520,20 @@ void __tick_nohz_task_switch(void)
 	}
 }
 
+void __tick_nohz_user_enter_prepare(void)
+{
+	struct tick_sched *ts;
+
+	if (tick_nohz_full_cpu(smp_processor_id())) {
+		ts = this_cpu_ptr(&tick_cpu_sched);
+
+		if (ts->tick_stopped)
+			quiet_vmstat();
+		rcu_nocb_flush_deferred_wakeup();
+	}
+}
+EXPORT_SYMBOL_GPL(__tick_nohz_user_enter_prepare);
+
 /* Get the boot-time nohz CPU list from the kernel parameters. */
 void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 {
-- 
2.37.1