hrtimer: Provide clock_was_set_delayed()

clock_was_set() cannot be called from hard interrupt context because
it calls on_each_cpu().

For fixing the widely reported leap seconds issue it is necessary to
call it from hard interrupt context, i.e. the timer tick code, which
does the timekeeping updates.

Provide a new function which denotes it in the hrtimer cpu base
structure of the cpu on which it is called and raise the hrtimer
softirq. We then execute the clock_was_set() notificiation from
softirq context in run_hrtimer_softirq(). The hrtimer softirq is
rarely used, so polling the flag there is not a performance issue.

[ tglx: Made it depend on CONFIG_HIGH_RES_TIMERS. We really should get
  rid of all this ifdeffery ASAP ]

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Reported-by: Jan Engelhardt <jengelh@inai.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1341960205-56738-2-git-send-email-johnstul@us.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index fd0dc30..c9ec940 100644 (file)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -165,6 +165,7 @@ enum  hrtimer_base_type {
  * @lock:              lock protecting the base and associated clock bases
  *                     and timers
  * @active_bases:      Bitfield to mark bases with active timers
+ * @clock_was_set:     Indicates that clock was set from irq context.
  * @expires_next:      absolute time of the next event which was scheduled
  *                     via clock_set_next_event()
  * @hres_active:       State of high resolution mode
@@ -177,7 +178,8 @@ enum  hrtimer_base_type {
  */
 struct hrtimer_cpu_base {
        raw_spinlock_t                  lock;
-       unsigned long                   active_bases;
+       unsigned int                    active_bases;
+       unsigned int                    clock_was_set;
 #ifdef CONFIG_HIGH_RES_TIMERS
        ktime_t                         expires_next;
        int                             hres_active;
@@ -286,6 +288,8 @@ extern void hrtimer_peek_ahead_timers(void);
 # define MONOTONIC_RES_NSEC    HIGH_RES_NSEC
 # define KTIME_MONOTONIC_RES   KTIME_HIGH_RES
 
+extern void clock_was_set_delayed(void);
+
 #else
 
 # define MONOTONIC_RES_NSEC    LOW_RES_NSEC
@@ -306,6 +310,9 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 {
        return 0;
 }
+
+static inline void clock_was_set_delayed(void) { }
+
 #endif
 
 extern void clock_was_set(void);

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae34bf5..3c24fb2 100644 (file)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -717,6 +717,19 @@ static int hrtimer_switch_to_hres(void)
        return 1;
 }
 
+/*
+ * Called from timekeeping code to reprogramm the hrtimer interrupt
+ * device. If called from the timer interrupt context we defer it to
+ * softirq context.
+ */
+void clock_was_set_delayed(void)
+{
+       struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+       cpu_base->clock_was_set = 1;
+       __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+}
+
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -1395,6 +1408,13 @@ void hrtimer_peek_ahead_timers(void)
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
+       struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+       if (cpu_base->clock_was_set) {
+               cpu_base->clock_was_set = 0;
+               clock_was_set();
+       }
+
        hrtimer_peek_ahead_timers();
 }