Merge branch 'timers/urgent' into timers/core

Reason: Get upstream fixes and kfree_rcu which is necessary for a
follow up patch.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 96 insertions, 22 deletions

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 0d74b9ba90c8..c027d4f602f1 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -194,6 +194,70 @@ void clockevents_register_device(struct clock_event_device *dev)
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
+static void clockevents_config(struct clock_event_device *dev,
+                               u32 freq)
+{
+        u64 sec;
+
+        if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+                return;
+
+        /*
+         * Calculate the maximum number of seconds we can sleep. Limit
+         * to 10 minutes for hardware which can program more than
+         * 32bit ticks so we still get reasonable conversion values.
+         */
+        sec = dev->max_delta_ticks;
+        do_div(sec, freq);
+        if (!sec)
+                sec = 1;
+        else if (sec > 600 && dev->max_delta_ticks > UINT_MAX)
+                sec = 600;
+
+        clockevents_calc_mult_shift(dev, freq, sec);
+        dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
+        dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+}
+
+/**
+ * clockevents_config_and_register - Configure and register a clock event device
+ * @dev:        device to register
+ * @freq:       The clock frequency
+ * @min_delta:  The minimum clock ticks to program in oneshot mode
+ * @max_delta:  The maximum clock ticks to program in oneshot mode
+ *
+ * min/max_delta can be 0 for devices which do not support oneshot mode.
+ */
+void clockevents_config_and_register(struct clock_event_device *dev,
+                                     u32 freq, unsigned long min_delta,
+                                     unsigned long max_delta)
+{
+        dev->min_delta_ticks = min_delta;
+        dev->max_delta_ticks = max_delta;
+        clockevents_config(dev, freq);
+        clockevents_register_device(dev);
+}
+
+/**
+ * clockevents_update_freq - Update frequency and reprogram a clock event device.
+ * @dev:        device to modify
+ * @freq:       new device frequency
+ *
+ * Reconfigure and reprogram a clock event device in oneshot
+ * mode. Must be called on the cpu for which the device delivers per
+ * cpu timer events with interrupts disabled!  Returns 0 on success,
+ * -ETIME when the event is in the past.
+ */
+int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+        clockevents_config(dev, freq);
+
+        if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
+                return 0;
+
+        return clockevents_program_event(dev, dev->next_event, ktime_get());
+}
+
 /*
  * Noop handler when we shut down an event device
  */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 6519cf62d9cd..1c95fd677328 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -626,19 +626,6 @@ static void clocksource_enqueue(struct clocksource *cs)
         list_add(&cs->list, entry);
 }
 
-
-/*
- * Maximum time we expect to go between ticks. This includes idle
- * tickless time. It provides the trade off between selecting a
- * mult/shift pair that is very precise but can only handle a short
- * period of time, vs. a mult/shift pair that can handle long periods
- * of time but isn't as precise.
- *
- * This is a subsystem constant, and actual hardware limitations
- * may override it (ie: clocksources that wrap every 3 seconds).
- */
-#define MAX_UPDATE_LENGTH 5 /* Seconds */
-
 /**
  * __clocksource_updatefreq_scale - Used update clocksource with new freq
  * @t:          clocksource to be registered
@@ -652,15 +639,28 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
+        u64 sec;
+
         /*
-         * Ideally we want to use  some of the limits used in
-         * clocksource_max_deferment, to provide a more informed
-         * MAX_UPDATE_LENGTH. But for now this just gets the
-         * register interface working properly.
+         * Calc the maximum number of seconds which we can run before
+         * wrapping around. For clocksources which have a mask > 32bit
+         * we need to limit the max sleep time to have a good
+         * conversion precision. 10 minutes is still a reasonable
+         * amount. That results in a shift value of 24 for a
+         * clocksource with mask >= 40bit and f >= 4GHz. That maps to
+         * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
+         * margin as we do in clocksource_max_deferment()
          */
+        sec = (cs->mask - (cs->mask >> 5));
+        do_div(sec, freq);
+        do_div(sec, scale);
+        if (!sec)
+                sec = 1;
+        else if (sec > 600 && cs->mask > UINT_MAX)
+                sec = 600;
+
         clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-                                      NSEC_PER_SEC/scale,
-                                      MAX_UPDATE_LENGTH*scale);
+                               NSEC_PER_SEC / scale, sec * scale);
         cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -685,8 +685,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
         /* Add clocksource to the clcoksource list */
         mutex_lock(&clocksource_mutex);
         clocksource_enqueue(cs);
-        clocksource_select();
         clocksource_enqueue_watchdog(cs);
+        clocksource_select();
         mutex_unlock(&clocksource_mutex);
         return 0;
 }
@@ -706,8 +706,8 @@ int clocksource_register(struct clocksource *cs)
 
         mutex_lock(&clocksource_mutex);
         clocksource_enqueue(cs);
-        clocksource_select();
         clocksource_enqueue_watchdog(cs);
+        clocksource_select();
         mutex_unlock(&clocksource_mutex);
         return 0;
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 827e0f862da4..c7218d132738 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -524,10 +524,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask,
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
+        int cpu = smp_processor_id();
+
         /* Set it up only once ! */
         if (bc->event_handler != tick_handle_oneshot_broadcast) {
                 int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
-                int cpu = smp_processor_id();
 
                 bc->event_handler = tick_handle_oneshot_broadcast;
                 clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -553,6 +554,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
                         tick_broadcast_set_event(tick_next_period, 1);
                 } else
                         bc->next_event.tv64 = KTIME_MAX;
+        } else {
+                /*
+                 * The first cpu which switches to oneshot mode sets
+                 * the bit for all other cpus which are in the general
+                 * (periodic) broadcast mask. So the bit is set and
+                 * would prevent the first broadcast enter after this
+                 * to program the bc device.
+                 */
+                tick_broadcast_clear_oneshot(cpu);
         }
 }