hrtimer: Preserve timer state in remove_hrtimer()

The race is described as follows:

CPU X                                 CPU Y
remove_hrtimer
// state & QUEUED == 0
timer->state = CALLBACK
unlock timer base
timer->f(n) //very long
                                  hrtimer_start
                                    lock timer base
                                    remove_hrtimer // no effect
                                    hrtimer_enqueue
                                    timer->state = CALLBACK |
                                                   QUEUED
                                    unlock timer base
                                  hrtimer_start
                                    lock timer base
                                    remove_hrtimer
                                        mode = INACTIVE
                                        // CALLBACK bit lost!
                                    switch_hrtimer_base
                                            CALLBACK bit not set:
                                                    timer->base
                                                    changes to a
                                                    different CPU.
lock this CPU's timer base

The bug was introduced with commit ca109491 (hrtimer: removing all ur
callback modes) in 2.6.29

[ tglx: Feed new state via local variable and add a comment. ]
Signed-off-by: Salman Qazi <sqazi@google.com>
Cc: akpm@linux-foundation.org
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20101012142351.8485.21823.stgit@dungbeetle.mtv.corp.google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org

kernel/hrtimer.c

@@ -931,6 +931,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
 	if (hrtimer_is_queued(timer)) {
+		unsigned long state;
 		int reprogram;
 
 		/*
@@ -944,8 +945,13 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
-		__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
-				 reprogram);
+		/*
+		 * We must preserve the CALLBACK state flag here,
+		 * otherwise we could move the timer base in
+		 * switch_hrtimer_base.
+		 */
+		state = timer->state & HRTIMER_STATE_CALLBACK;
+		__remove_hrtimer(timer, base, state, reprogram);
 		return 1;
 	}
 	return 0;
@@ -1231,6 +1237,9 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
 		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
 		enqueue_hrtimer(timer, base);
 	}
+
+	WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+
 	timer->state &= ~HRTIMER_STATE_CALLBACK;
 }