3 files changed, 60 insertions, 17 deletions

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 9ba04aa..d67ef56 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -629,7 +629,8 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 	 * Rate limit to the tick as a hot fix to prevent DOS. Will be
 	 * mopped up later.
 	 */
-	if (ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC)
+	if (timr->it.alarm.interval.tv64 &&
+			ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC)
 		timr->it.alarm.interval = ktime_set(0, TICK_NSEC);
 
 	exp = timespec_to_ktime(new_setting->it_value);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index bb5ec42..eeb7f2f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,17 +94,15 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	/* Make sure we catch unsupported clockids */
+	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
+
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
 	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
-static inline int hrtimer_clockid_to_base(clockid_t clock_id)
-{
-	return hrtimer_clock_to_base_table[clock_id];
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -1112,6 +1110,18 @@ u64 hrtimer_get_next_event(void)
 }
 #endif
 
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	if (likely(clock_id < MAX_CLOCKS)) {
+		int base = hrtimer_clock_to_base_table[clock_id];
+
+		if (likely(base != HRTIMER_MAX_CLOCK_BASES))
+			return base;
+	}
+	WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
+	return HRTIMER_BASE_MONOTONIC;
+}
+
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index c611c47..7d67036 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -201,6 +201,7 @@ struct timer_base {
 	bool			migration_enabled;
 	bool			nohz_active;
 	bool			is_idle;
+	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
 } ____cacheline_aligned;
@@ -239,7 +240,7 @@ int timer_migration_handler(struct ctl_table *table, int write,
 	int ret;
 
 	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write)
 		timers_update_migration(false);
 	mutex_unlock(&mutex);
@@ -891,13 +892,19 @@ get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
+	unsigned long jnow;
 
 	/*
-	 * We only forward the base when it's idle and we have a delta between
-	 * base clock and jiffies.
+	 * 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 (!base->is_idle || (long) (jnow - base->clk) < 2)
+	if (likely(!base->must_forward_clk))
+		return;
+
+	jnow = READ_ONCE(jiffies);
+	base->must_forward_clk = base->is_idle;
+	if ((long)(jnow - base->clk) < 2)
 		return;
 
 	/*
@@ -973,6 +980,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	 * same array bucket then just return:
 	 */
 	if (timer_pending(timer)) {
+		/*
+		 * The downside of this optimization is that it can result in
+		 * larger granularity than you would get from adding a new
+		 * timer with this expiry.
+		 */
 		if (timer->expires == expires)
 			return 1;
 
@@ -983,6 +995,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * dequeue/enqueue dance.
 		 */
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
@@ -999,6 +1012,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		}
 	} else {
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 	}
 
 	timer_stats_timer_set_start_info(timer);
@@ -1028,12 +1042,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 			spin_lock(&base->lock);
 			WRITE_ONCE(timer->flags,
 				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
+			forward_timer_base(base);
 		}
 	}
 
-	/* Try to forward a stale timer base clock */
-	forward_timer_base(base);
-
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
@@ -1150,6 +1162,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 		WRITE_ONCE(timer->flags,
 			   (timer->flags & ~TIMER_BASEMASK) | cpu);
 	}
+	forward_timer_base(base);
 
 	debug_activate(timer, timer->expires);
 	internal_add_timer(base, timer);
@@ -1536,12 +1549,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		base->is_idle = false;
 	} else {
 		if (!is_max_delta)
-			expires = basem + (nextevt - basej) * TICK_NSEC;
+			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle:
+		 * If we expect to sleep more than a tick, mark the base idle.
+		 * 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).
 		 */
-		if ((expires - basem) > TICK_NSEC)
+		if ((expires - basem) > TICK_NSEC) {
+			base->must_forward_clk = true;
 			base->is_idle = true;
+		}
 	}
 	spin_unlock(&base->lock);
 
@@ -1651,6 +1670,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
+	/*
+	 * 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 trcking / clock forwarding logic is only used with
+	 * BASE_STD timers.
+	 *
+	 * The deferrable base does not do idle tracking at all, so we do
+	 * not forward it. This can result in very large variations in
+	 * granularity for deferrable timers, but they can be deferred for
+	 * long periods due to idle.
+	 */
+	base->must_forward_clk = false;
+
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));