From: Salman Qazi <[email protected]>

commit f13d4f979c518119bba5439dd2364d76d31dcd3f upstream.

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 ca109491f (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 <[email protected]>
Cc: [email protected]
Cc: Peter Zijlstra <[email protected]>
LKML-Reference: <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Signed-off-by: Paul Gortmaker <[email protected]>
---
 kernel/hrtimer.c |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0086628..3c727aa 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -936,6 +936,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
        if (hrtimer_is_queued(timer)) {
+               unsigned long state;
                int reprogram;
 
                /*
@@ -949,8 +950,13 @@ 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;
@@ -1237,6 +1243,9 @@ 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;
 }
 
-- 
1.7.3.3

_______________________________________________
stable mailing list
[email protected]
http://linux.kernel.org/mailman/listinfo/stable

Reply via email to