From: Frederic Weisbecker <frederic@kernel.org>
Date: Fri, 17 Jul 2020 14:05:48 +0000 (+0200)
Subject: timers: Expand clk forward logic beyond nohz
X-Git-Tag: block-5.9-2020-08-14~26^2~5
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=1f8a4212dc83f8353843fabf6465fd918372fbbf;p=linux-block.git

timers: Expand clk forward logic beyond nohz

As for next_expiry, the base->clk catch up logic will be expanded beyond
NOHZ in order to avoid triggering useless softirqs.

If softirqs should only fire to expire pending timers, periodic base->clk
increments must be skippable for random amounts of time.  Therefore prepare
to catch-up with missing updates whenever an up-to-date base clock is
needed.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/20200717140551.29076-10-frederic@kernel.org
---

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 13f48ee708aa..1be92b53b75f 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -888,19 +888,12 @@ get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-#ifdef CONFIG_NO_HZ_COMMON
 	unsigned long jnow;
 
-	/*
-	 * We only forward the base when we are idle or have just come out of
-	 * idle (must_forward_clk logic), and have a delta between base clock
-	 * and jiffies. In the common case, run_timers will take care of it.
-	 */
-	if (likely(!base->must_forward_clk))
+	if (!base->must_forward_clk)
 		return;
 
 	jnow = READ_ONCE(jiffies);
-	base->must_forward_clk = base->is_idle;
 	if ((long)(jnow - base->clk) < 2)
 		return;
 
@@ -915,7 +908,6 @@ static inline void forward_timer_base(struct timer_base *base)
 			return;
 		base->clk = base->next_expiry;
 	}
-#endif
 }
 
 
@@ -1667,10 +1659,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		 * logic is only maintained for the BASE_STD base, deferrable
 		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC) {
-			base->must_forward_clk = true;
+		if ((expires - basem) > TICK_NSEC)
 			base->is_idle = true;
-		}
 	}
 	raw_spin_unlock(&base->lock);
 
@@ -1769,16 +1759,7 @@ static inline void __run_timers(struct timer_base *base)
 	/*
 	 * timer_base::must_forward_clk must be cleared before running
 	 * timers so that any timer functions that call mod_timer() will
-	 * not try to forward the base. Idle tracking / clock forwarding
-	 * logic is only used with BASE_STD timers.
-	 *
-	 * The must_forward_clk flag is cleared unconditionally also for
-	 * the deferrable base. The deferrable base is not affected by idle
-	 * tracking and never forwarded, so clearing the flag is a NOOP.
-	 *
-	 * The fact that the deferrable base is never forwarded can cause
-	 * large variations in granularity for deferrable timers, but they
-	 * can be deferred for long periods due to idle anyway.
+	 * not try to forward the base.
 	 */
 	base->must_forward_clk = false;
 
@@ -1791,6 +1772,7 @@ static inline void __run_timers(struct timer_base *base)
 		while (levels--)
 			expire_timers(base, heads + levels);
 	}
+	base->must_forward_clk = true;
 	raw_spin_unlock_irq(&base->lock);
 	timer_base_unlock_expiry(base);
 }