summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2009-07-09 13:52:32 +0200
committerThomas Gleixner <tglx@linutronix.de>2009-07-10 17:22:20 +0200
commit7e0c5086c172ecf8b0c2ad860b02a586967d17d0 (patch)
tree207e1975ea970279e5ad912a094361e2fa169d93 /kernel
parent507e123151149e578c9aae33eb876c49824da5f8 (diff)
hrtimer: migration: do not check expiry time on current CPU
The timer migration code needs to check whether the expiry time of the timer is before the programmed clock event expiry time when the timer is enqueued on another CPU because we can not reprogram the timer device on the other CPU. The current logic checks the expiry time even if we enqueue on the current CPU when nohz_get_load_balancer() returns current CPU. This might lead to an endless loop in the expiry check code when the expiry time of the timer is before the current programmed next event. Check whether nohz_get_load_balancer() returns current CPU and skip the expiry check if this is the case. The bug was triggered from the networking code. The patch fixes the regression http://bugzilla.kernel.org/show_bug.cgi?id=13738 (Soft-Lockup/Race in networking in 2.6.31-rc1+195) Cc: Arun Bharadwaj <arun@linux.vnet.ibm.com Tested-by: Joao Correia <joaomiguelcorreia@gmail.com> Tested-by: Andres Freund <andres@anarazel.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/hrtimer.c15
1 files changed, 13 insertions, 2 deletions
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9002958a96e7..126b9808f287 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -206,8 +206,19 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
preferred_cpu = get_nohz_load_balancer();
- if (preferred_cpu >= 0)
- cpu = preferred_cpu;
+ if (preferred_cpu >= 0) {
+ /*
+ * We must not check the expiry value when
+ * preferred_cpu is the current cpu. If base
+ * != new_base we would loop forever when the
+ * timer expires before the current programmed
+ * next timer event.
+ */
+ if (preferred_cpu != cpu)
+ cpu = preferred_cpu;
+ else
+ preferred_cpu = -1;
+ }
}
#endif