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:   Anna-Maria Behnsen <anna-maria@linutronix.de>
To:     linux-kernel@vger.kernel.org
Cc:     Peter Zijlstra <peterz@infradead.org>,
        John Stultz <jstultz@google.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Eric Dumazet <edumazet@google.com>,
        "Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
        Arjan van de Ven <arjan@infradead.org>,
        "Paul E . McKenney" <paulmck@kernel.org>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Rik van Riel <riel@surriel.com>,
        Anna-Maria Behnsen <anna-maria@linutronix.de>,
        Richard Cochran <richardcochran@gmail.com>,
        Frederic Weisbecker <frederic@kernel.org>
Subject: [PATCH v4 06/16] timer: Keep the pinned timers separate from the others
Date:   Fri,  4 Nov 2022 15:57:27 +0100
Message-Id: <20221104145737.71236-7-anna-maria@linutronix.de>
In-Reply-To: <20221104145737.71236-1-anna-maria@linutronix.de>
References: <20221104145737.71236-1-anna-maria@linutronix.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Separate the storage space for pinned timers. Deferrable timers (doesn't
matter if pinned or non pinned) are still enqueued into their own base.

This is preparatory work for changing the NOHZ timer placement from a push
at enqueue time to a pull at expiry time model.

No functional change.

Originally-by: Richard Cochran (linutronix GmbH) <richardcochran@gmail.com>
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
---
v4:
  - split out logic to forward base clock into a helper function
    forward_base_clk() (Frederic)
  - ease the code in run_local_timers() and timer_clear_idle() (Frederic)
---
 kernel/time/timer.c | 122 ++++++++++++++++++++++++++++++--------------
 1 file changed, 84 insertions(+), 38 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 0e9f609f5a38..0e2abd906916 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -187,12 +187,18 @@ EXPORT_SYMBOL(jiffies_64);
 #define WHEEL_SIZE	(LVL_SIZE * LVL_DEPTH)
 
 #ifdef CONFIG_NO_HZ_COMMON
-# define NR_BASES	2
-# define BASE_STD	0
-# define BASE_DEF	1
+/*
+ * If multiple bases need to be locked, use the base ordering for lock
+ * nesting, i.e. lowest number first.
+ */
+# define NR_BASES	3
+# define BASE_LOCAL	0
+# define BASE_GLOBAL	1
+# define BASE_DEF	2
 #else
 # define NR_BASES	1
-# define BASE_STD	0
+# define BASE_LOCAL	0
+# define BASE_GLOBAL	0
 # define BASE_DEF	0
 #endif
 
@@ -902,7 +908,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
 
 static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 {
-	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
+	int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
+	struct timer_base *base;
+
+	base = per_cpu_ptr(&timer_bases[index], cpu);
 
 	/*
 	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
@@ -915,7 +924,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 
 static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
+	struct timer_base *base;
+
+	base = this_cpu_ptr(&timer_bases[index]);
 
 	/*
 	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
@@ -1690,6 +1702,21 @@ static unsigned long next_timer_interrupt(struct timer_base *base)
 	return base->next_expiry;
 }
 
+/*
+ * Forward base clock is done only when @basej is past base->clk, otherwise
+ * base-clk might be rewind.
+ */
+static void forward_base_clk(struct timer_base *base, unsigned long nextevt,
+			     unsigned long basej)
+{
+	if (time_after(basej, base->clk)) {
+		if (time_after(nextevt, basej))
+			base->clk = basej;
+		else if (time_after(nextevt, base->clk))
+			base->clk = nextevt;
+	}
+}
+
 /**
  * get_next_timer_interrupt - return the time (clock mono) of the next timer
  * @basej:	base time jiffies
@@ -1700,9 +1727,10 @@ static unsigned long next_timer_interrupt(struct timer_base *base)
  */
 u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	unsigned long nextevt, nextevt_local, nextevt_global;
+	struct timer_base *base_local, *base_global;
+	bool local_first, is_idle;
 	u64 expires = KTIME_MAX;
-	unsigned long nextevt;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1711,38 +1739,57 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 	if (cpu_is_offline(smp_processor_id()))
 		return expires;
 
-	raw_spin_lock(&base->lock);
+	base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
+	base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]);
+
+	raw_spin_lock(&base_local->lock);
+	raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
 
-	nextevt = next_timer_interrupt(base);
+	nextevt_local = next_timer_interrupt(base_local);
+	nextevt_global = next_timer_interrupt(base_global);
 
 	/*
 	 * We have a fresh next event. Check whether we can forward the
-	 * base. We can only do that when @basej is past base->clk
-	 * otherwise we might rewind base->clk.
+	 * base.
 	 */
-	if (time_after(basej, base->clk)) {
-		if (time_after(nextevt, basej))
-			base->clk = basej;
-		else if (time_after(nextevt, base->clk))
-			base->clk = nextevt;
-	}
+	forward_base_clk(base_local, nextevt_local, basej);
+	forward_base_clk(base_global, nextevt_global, basej);
+
+	/*
+	 * Check whether the local event is expiring before or at the same
+	 * time as the global event.
+	 *
+	 * Note, that nextevt_global and nextevt_local might be based on
+	 * different base->clk values. So it's not guaranteed that
+	 * comparing with empty bases results in a correct local_first.
+	 */
+	if (base_local->timers_pending && base_global->timers_pending)
+		local_first = time_before_eq(nextevt_local, nextevt_global);
+	else
+		local_first = base_local->timers_pending;
+
+	nextevt = local_first ? nextevt_local : nextevt_global;
 
 	/*
-	 * Base is idle if the next event is more than a tick away. Also
+	 * Bases are idle if the next event is more than a tick away. Also
 	 * the tick is stopped so any added timer must forward the base clk
 	 * itself to keep granularity small. This idle logic is only
-	 * maintained for the BASE_STD base, deferrable timers may still
-	 * see large granularity skew (by design).
+	 * maintained for the BASE_LOCAL and BASE_GLOBAL base, deferrable
+	 * timers may still see large granularity skew (by design).
 	 */
-	base->is_idle = time_after(nextevt, basej + 1);
+	is_idle = time_after(nextevt, basej + 1);
 
-	if (base->timers_pending) {
+	/* We need to mark both bases in sync */
+	base_local->is_idle = base_global->is_idle = is_idle;
+
+	if (base_local->timers_pending || base_global->timers_pending) {
 		/* If we missed a tick already, force 0 delta */
 		if (time_before(nextevt, basej))
 			nextevt = basej;
 		expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 	}
-	raw_spin_unlock(&base->lock);
+	raw_spin_unlock(&base_global->lock);
+	raw_spin_unlock(&base_local->lock);
 
 	return cmp_next_hrtimer_event(basem, expires);
 }
@@ -1754,15 +1801,14 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
  */
 void timer_clear_idle(void)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
-
 	/*
 	 * We do this unlocked. The worst outcome is a remote enqueue sending
 	 * a pointless IPI, but taking the lock would just make the window for
 	 * sending the IPI a few instructions smaller for the cost of taking
 	 * the lock in the exit from idle path.
 	 */
-	base->is_idle = false;
+	__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);
+	__this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false);
 }
 #endif
 
@@ -1808,11 +1854,13 @@ static inline void __run_timers(struct timer_base *base)
  */
 static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
 
 	__run_timers(base);
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) {
+		__run_timers(this_cpu_ptr(&timer_bases[BASE_GLOBAL]));
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
+	}
 }
 
 /*
@@ -1820,19 +1868,17 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
  */
 static void run_local_timers(void)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
 
 	hrtimer_run_queues();
-	/* Raise the softirq only if required. */
-	if (time_before(jiffies, base->next_expiry)) {
-		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
-			return;
-		/* CPU is awake, so check the deferrable base. */
-		base++;
-		if (time_before(jiffies, base->next_expiry))
+
+	for (int i = 0; i < NR_BASES; i++, base++) {
+		/* Raise the softirq only if required. */
+		if (time_after_eq(jiffies, base->next_expiry)) {
+			raise_softirq(TIMER_SOFTIRQ);
 			return;
+		}
 	}
-	raise_softirq(TIMER_SOFTIRQ);
 }
 
 /*
-- 
2.30.2