clocksource: Allow unregistering the watchdog

Hyper-V vmbus module registers TSC page clocksource when loaded. This is
the clocksource with the highest rating and thus it becomes the watchdog
making unloading of the vmbus module impossible.
Separate clocksource_select_watchdog() from clocksource_enqueue_watchdog()
and use it on clocksource register/rating change/unregister.

After all, lobotomized monkeys may need some love too.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Link: http://lkml.kernel.org/r/1453483913-25672-1-git-send-email-vkuznets@redhat.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
(cherry picked from commit bbf66d897adf2bb0c310db96c97e8db6369f39e1)

This commit changes the clocksource for the Hyper-V vmbus module to
provide superior performance for a VM

Orabug: 24746725
Signed-off-by: Jack Vogel <jack.vogel@oracle.com>

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 15facb1b9c606c7a5fa5ea3500ea7dd4bf523477..e1ad9a900a4a676bdd158697c67d2dfbdc9a912a 100644 (file)
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -320,13 +320,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
                /* cs is a watchdog. */
                if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
                        cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+       }
+       spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+       struct clocksource *cs, *old_wd;
+       unsigned long flags;
+
+       spin_lock_irqsave(&watchdog_lock, flags);
+       /* save current watchdog */
+       old_wd = watchdog;
+       if (fallback)
+               watchdog = NULL;
+
+       list_for_each_entry(cs, &clocksource_list, list) {
+               /* cs is a clocksource to be watched. */
+               if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+                       continue;
+
+               /* Skip current if we were requested for a fallback. */
+               if (fallback && cs == old_wd)
+                       continue;
+
                /* Pick the best watchdog. */
-               if (!watchdog || cs->rating > watchdog->rating) {
+               if (!watchdog || cs->rating > watchdog->rating)
                        watchdog = cs;
-                       /* Reset watchdog cycles */
-                       clocksource_reset_watchdog();
-               }
        }
+       /* If we failed to find a fallback restore the old one. */
+       if (!watchdog)
+               watchdog = old_wd;
+
+       /* If we changed the watchdog we need to reset cycles. */
+       if (watchdog != old_wd)
+               clocksource_reset_watchdog();
+
        /* Check if the watchdog timer needs to be started. */
        clocksource_start_watchdog();
        spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -401,6 +430,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
                cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -735,6 +765,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
        clocksource_enqueue(cs);
        clocksource_enqueue_watchdog(cs);
        clocksource_select();
+       clocksource_select_watchdog(false);
        mutex_unlock(&clocksource_mutex);
        return 0;
 }
@@ -757,6 +788,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
        mutex_lock(&clocksource_mutex);
        __clocksource_change_rating(cs, rating);
        clocksource_select();
+       clocksource_select_watchdog(false);
        mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -766,12 +798,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
-       /*
-        * I really can't convince myself to support this on hardware
-        * designed by lobotomized monkeys.
-        */
-       if (clocksource_is_watchdog(cs))
-               return -EBUSY;
+       if (clocksource_is_watchdog(cs)) {
+               /* Select and try to install a replacement watchdog. */
+               clocksource_select_watchdog(true);
+               if (clocksource_is_watchdog(cs))
+                       return -EBUSY;
+       }
 
        if (cs == curr_clocksource) {
                /* Select and try to install a replacement clock source */