clocksource: Move watchdog downgrade to a work queue thread

Move the downgrade of an unstable clocksource from the timer interrupt
context into the process context of a work queue thread. This is
needed to be able to do the clocksource switch with stop_machine.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: John Stultz <johnstul@us.ibm.com>
Cc: Daniel Walker <dwalker@fifo99.com>
LKML-Reference: <20090814134809.354926067@de.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f263b3abf46e319dfbd3e3e3215f9d6cd0637b8a..19ad43af62d07aad5bdcc55f311572bd66480cda 100644 (file)
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -213,6 +213,7 @@ extern struct clocksource *clock;   /* current clocksource */
 
 #define CLOCK_SOURCE_WATCHDOG                  0x10
 #define CLOCK_SOURCE_VALID_FOR_HRES            0x20
+#define CLOCK_SOURCE_UNSTABLE                  0x40
 
 /* simplify initialization of mask field */
 #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 56aaa749645d17cc08f61f10a05bec1b451d5461..f1508019bfb4735d86661d815727a51b671dd19c 100644 (file)
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -143,10 +143,13 @@ fs_initcall(clocksource_done_booting);
 static LIST_HEAD(watchdog_list);
 static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
+static struct work_struct watchdog_work;
 static DEFINE_SPINLOCK(watchdog_lock);
 static cycle_t watchdog_last;
 static int watchdog_running;
 
+static void clocksource_watchdog_work(struct work_struct *work);
+
 /*
  * Interval: 0.5sec Threshold: 0.0625s
  */
@@ -158,15 +161,16 @@ static void clocksource_unstable(struct clocksource *cs, int64_t delta)
        printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
               cs->name, delta);
        cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
-       clocksource_change_rating(cs, 0);
-       list_del(&cs->wd_list);
+       cs->flags |= CLOCK_SOURCE_UNSTABLE;
+       schedule_work(&watchdog_work);
 }
 
 static void clocksource_watchdog(unsigned long data)
 {
-       struct clocksource *cs, *tmp;
+       struct clocksource *cs;
        cycle_t csnow, wdnow;
        int64_t wd_nsec, cs_nsec;
+       int next_cpu;
 
        spin_lock(&watchdog_lock);
        if (!watchdog_running)
@@ -176,7 +180,12 @@ static void clocksource_watchdog(unsigned long data)
        wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
        watchdog_last = wdnow;
 
-       list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
+       list_for_each_entry(cs, &watchdog_list, wd_list) {
+
+               /* Clocksource already marked unstable? */
+               if (cs->flags & CLOCK_SOURCE_UNSTABLE)
+                       continue;
+
                csnow = cs->read(cs);
 
                /* Clocksource initialized ? */
@@ -207,19 +216,15 @@ static void clocksource_watchdog(unsigned long data)
                }
        }
 
-       if (!list_empty(&watchdog_list)) {
-               /*
-                * Cycle through CPUs to check if the CPUs stay
-                * synchronized to each other.
-                */
-               int next_cpu = cpumask_next(raw_smp_processor_id(),
-                                           cpu_online_mask);
-
-               if (next_cpu >= nr_cpu_ids)
-                       next_cpu = cpumask_first(cpu_online_mask);
-               watchdog_timer.expires += WATCHDOG_INTERVAL;
-               add_timer_on(&watchdog_timer, next_cpu);
-       }
+       /*
+        * Cycle through CPUs to check if the CPUs stay synchronized
+        * to each other.
+        */
+       next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+       if (next_cpu >= nr_cpu_ids)
+               next_cpu = cpumask_first(cpu_online_mask);
+       watchdog_timer.expires += WATCHDOG_INTERVAL;
+       add_timer_on(&watchdog_timer, next_cpu);
 out:
        spin_unlock(&watchdog_lock);
 }
@@ -228,6 +233,7 @@ static inline void clocksource_start_watchdog(void)
 {
        if (watchdog_running || !watchdog || list_empty(&watchdog_list))
                return;
+       INIT_WORK(&watchdog_work, clocksource_watchdog_work);
        init_timer(&watchdog_timer);
        watchdog_timer.function = clocksource_watchdog;
        watchdog_last = watchdog->read(watchdog);
@@ -313,6 +319,22 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs)
        spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
+static void clocksource_watchdog_work(struct work_struct *work)
+{
+       struct clocksource *cs, *tmp;
+       unsigned long flags;
+
+       spin_lock_irqsave(&watchdog_lock, flags);
+       list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list)
+               if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
+                       list_del_init(&cs->wd_list);
+                       clocksource_change_rating(cs, 0);
+               }
+       /* Check if the watchdog timer needs to be stopped. */
+       clocksource_stop_watchdog();
+       spin_unlock(&watchdog_lock);
+}
+
 #else /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)