3.0.x: hrtimer: Fix clock_was_set so it is safe to call from irq context

NOTE:This is a prerequisite patch that's required to
address the widely observed leap-second related futex/hrtimer
issues.

Currently clock_was_set() is unsafe to be called from irq
context, as it calls on_each_cpu(). This causes problems when
we need to adjust the time from update_wall_time().

To fix this, if clock_was_set is called when irqs are
disabled, we schedule a timer to fire for immedately after
we're out of interrupt context to then notify the hrtimer
subsystem.

CC: Prarit Bhargava <prarit@redhat.com>
CC: stable@vger.kernel.org
CC: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Reported-by: Jan Engelhardt <jengelh@inai.de>
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Backported-by: Joe Jin <joe.jin@oracle.com>

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2043c08d36c89d44731fb70ff01679816704f3a0..250b2b5205a3e05c53d31abe9f1a8ef9a663bbff 100644 (file)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -746,7 +746,7 @@ static inline void retrigger_next_event(void *arg) { }
  * resolution timer interrupts. On UP we just disable interrupts and
  * call the high resolution interrupt code.
  */
-void clock_was_set(void)
+static void do_clock_was_set(unsigned long data)
 {
 #ifdef CONFIG_HIGH_RES_TIMERS
        /* Retrigger the CPU local events everywhere */
@@ -755,6 +755,21 @@ void clock_was_set(void)
        timerfd_clock_was_set();
 }
 
+static DEFINE_TIMER(clock_was_set_timer, do_clock_was_set , 0, 0);
+
+void clock_was_set(void)
+{
+       /*
+        * We can't call on_each_cpu() from irq context,
+        * so if irqs are disabled , schedule the clock_was_set
+        * via a timer_list timer for right after.
+        */
+       if (irqs_disabled())
+               mod_timer(&clock_was_set_timer, jiffies);
+       else
+               do_clock_was_set(0);
+}
+
 /*
  * During resume we might have to reprogram the high resolution timer
  * interrupt (on the local CPU):