Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Thomas Gleixner:
 "A pile of fixes for long standing issues with the timer wheel and the
  NOHZ code:

   - Prevent timer base confusion accross the nohz switch, which can
     cause unlocked access and data corruption

   - Reinitialize the stale base clock on cpu hotplug to prevent subtle
     side effects including rollovers on 32bit

   - Prevent an interrupt storm when the timer softirq is already
     pending caused by tick_nohz_stop_sched_tick()

   - Move the timer start tracepoint to a place where it actually makes
     sense

   - Add documentation to timerqueue functions as they caused confusion
     several times now"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timerqueue: Document return values of timerqueue_add/del()
  timers: Invoke timer_start_debug() where it makes sense
  nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick()
  timers: Reinitialize per cpu bases on hotplug
  timers: Use deferrable base independent of base::nohz_active

6 files changed, 52 insertions, 20 deletions

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 201ab7267986..1a32e558eb11 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -86,7 +86,7 @@ enum cpuhp_state {
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
-	CPUHP_TIMERS_DEAD,
+	CPUHP_TIMERS_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 04af640ea95b..2448f9cc48a3 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -207,9 +207,11 @@ unsigned long round_jiffies_up(unsigned long j);
 unsigned long round_jiffies_up_relative(unsigned long j);
 
 #ifdef CONFIG_HOTPLUG_CPU
+int timers_prepare_cpu(unsigned int cpu);
 int timers_dead_cpu(unsigned int cpu);
 #else
-#define timers_dead_cpu NULL
+#define timers_prepare_cpu	NULL
+#define timers_dead_cpu		NULL
 #endif
 
 #endif
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3d002a6f216e..53f7dc65f9a3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
 	 */
-	[CPUHP_TIMERS_DEAD] = {
+	[CPUHP_TIMERS_PREPARE] = {
 		.name			= "timers:dead",
-		.startup.single		= NULL,
+		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
 	/* Kicks the plugged cpu into life */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 77555faf6fbc..f7cc7abfcf25 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -650,6 +650,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	ts->next_tick = 0;
 }
 
+static inline bool local_timer_softirq_pending(void)
+{
+	return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 					 ktime_t now, int cpu)
 {
@@ -666,8 +671,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	} while (read_seqretry(&jiffies_lock, seq));
 	ts->last_jiffies = basejiff;
 
-	if (rcu_needs_cpu(basemono, &next_rcu) ||
-	    arch_needs_cpu() || irq_work_needs_cpu()) {
+	/*
+	 * Keep the periodic tick, when RCU, architecture or irq_work
+	 * requests it.
+	 * Aside of that check whether the local timer softirq is
+	 * pending. If so its a bad idea to call get_next_timer_interrupt()
+	 * because there is an already expired timer, so it will request
+	 * immeditate expiry, which rearms the hardware timer with a
+	 * minimal delta which brings us back to this place
+	 * immediately. Lather, rinse and repeat...
+	 */
+	if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+	    irq_work_needs_cpu() || local_timer_softirq_pending()) {
 		next_tick = basemono + TICK_NSEC;
 	} else {
 		/*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ffebcf878fba..89a9e1b4264a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -823,11 +823,10 @@ 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);
 
 	/*
-	 * If the timer is deferrable and nohz is active then we need to use
-	 * the deferrable base.
+	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
+	 * to use the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
-	    (tflags & TIMER_DEFERRABLE))
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
 		base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
 	return base;
 }
@@ -837,11 +836,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
 	/*
-	 * If the timer is deferrable and nohz is active then we need to use
-	 * the deferrable base.
+	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
+	 * to use the deferrable base.
 	 */
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
-	    (tflags & TIMER_DEFERRABLE))
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
 		base = this_cpu_ptr(&timer_bases[BASE_DEF]);
 	return base;
 }
@@ -1009,8 +1007,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	if (!ret && (options & MOD_TIMER_PENDING_ONLY))
 		goto out_unlock;
 
-	debug_activate(timer, expires);
-
 	new_base = get_target_base(base, timer->flags);
 
 	if (base != new_base) {
@@ -1034,6 +1030,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 	}
 
+	debug_activate(timer, expires);
+
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
@@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 	base->must_forward_clk = false;
 
 	__run_timers(base);
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
 }
 
@@ -1855,6 +1853,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
 	}
 }
 
+int timers_prepare_cpu(unsigned int cpu)
+{
+	struct timer_base *base;
+	int b;
+
+	for (b = 0; b < NR_BASES; b++) {
+		base = per_cpu_ptr(&timer_bases[b], cpu);
+		base->clk = jiffies;
+		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+		base->is_idle = false;
+		base->must_forward_clk = true;
+	}
+	return 0;
+}
+
 int timers_dead_cpu(unsigned int cpu)
 {
 	struct timer_base *old_base;
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 4a720ed4fdaf..0d54bcbc8170 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -33,8 +33,9 @@
  * @head: head of timerqueue
  * @node: timer node to be added
  *
- * Adds the timer node to the timerqueue, sorted by the
- * node's expires value.
+ * Adds the timer node to the timerqueue, sorted by the node's expires
+ * value. Returns true if the newly added timer is the first expiring timer in
+ * the queue.
  */
 bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 {
@@ -70,7 +71,8 @@ EXPORT_SYMBOL_GPL(timerqueue_add);
  * @head: head of timerqueue
  * @node: timer node to be removed
  *
- * Removes the timer node from the timerqueue.
+ * Removes the timer node from the timerqueue. Returns true if the queue is
+ * not empty after the remove.
  */
 bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 {