summaryrefslogtreecommitdiff
path: root/kernel/sched.c
diff options
context:
space:
mode:
authorSuresh Siddha <suresh.b.siddha@intel.com>2011-10-03 15:09:00 -0700
committerIngo Molnar <mingo@elte.hu>2011-10-06 12:46:23 +0200
commitca38062e57e97791c2f62e3dbd06caf3ebb5721c (patch)
treec022f6a3d3087cc8eaebbc5640ca145f7d9c50d8 /kernel/sched.c
parent9243a169acb9df9c63632fb7d5464359a107877a (diff)
sched: Use resched IPI to kick off the nohz idle balance
Current use of smp call function to kick the nohz idle balance can deadlock in this scenario. 1. cpu-A did a generic_exec_single() to cpu-B and after queuing its call single data (csd) to the call single queue, cpu-A took a timer interrupt. Actual IPI to cpu-B to process the call single queue is not yet sent. 2. As part of the timer interrupt handler, cpu-A decided to kick cpu-B for the idle load balancing (sets cpu-B's rq->nohz_balance_kick to 1) and __smp_call_function_single() with nowait will queue the csd to the cpu-B's queue. But the generic_exec_single() won't send an IPI to cpu-B as the call single queue was not empty. 3. cpu-A is busy with lot of interrupts 4. Meanwhile cpu-B is entering and exiting idle and noticed that it has it's rq->nohz_balance_kick set to '1'. So it will go ahead and do the idle load balancer and clear its rq->nohz_balance_kick. 5. At this point, csd queued as part of the step-2 above is still locked and waiting to be serviced on cpu-B. 6. cpu-A is still busy with interrupt load and now it got another timer interrupt and as part of it decided to kick cpu-B for another idle load balancing (as it finds cpu-B's rq->nohz_balance_kick cleared in step-4 above) and does __smp_call_function_single() with the same csd that is still locked. 7. And we get a deadlock waiting for the csd_lock() in the __smp_call_function_single(). Main issue here is that cpu-B can service the idle load balancer kick request from cpu-A even with out receiving the IPI and this lead to doing multiple __smp_call_function_single() on the same csd leading to deadlock. To kick a cpu, scheduler already has the reschedule vector reserved. Use that mechanism (kick_process()) instead of using the generic smp call function mechanism to kick off the nohz idle load balancing and avoid the deadlock. [ This issue is present from 2.6.35+ kernels, but marking it -stable only from v3.0+ as the proposed fix depends on the scheduler_ipi() that is introduced recently. ] Reported-by: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: stable@kernel.org # v3.0+ Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20111003220934.834943260@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/sched.c')
-rw-r--r--kernel/sched.c21
1 files changed, 19 insertions, 2 deletions
diff --git a/kernel/sched.c b/kernel/sched.c
index 4cdc91cf48f..9e49af00ae3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1404,6 +1404,18 @@ void wake_up_idle_cpu(int cpu)
smp_send_reschedule(cpu);
}
+static inline bool got_nohz_idle_kick(void)
+{
+ return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
+}
+
+#else /* CONFIG_NO_HZ */
+
+static inline bool got_nohz_idle_kick(void)
+{
+ return false;
+}
+
#endif /* CONFIG_NO_HZ */
static u64 sched_avg_period(void)
@@ -2717,7 +2729,7 @@ static void sched_ttwu_pending(void)
void scheduler_ipi(void)
{
- if (llist_empty(&this_rq()->wake_list))
+ if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
return;
/*
@@ -2735,6 +2747,12 @@ void scheduler_ipi(void)
*/
irq_enter();
sched_ttwu_pending();
+
+ /*
+ * Check if someone kicked us for doing the nohz idle load balance.
+ */
+ if (unlikely(got_nohz_idle_kick() && !need_resched()))
+ raise_softirq_irqoff(SCHED_SOFTIRQ);
irq_exit();
}
@@ -8288,7 +8306,6 @@ void __init sched_init(void)
rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ
rq->nohz_balance_kick = 0;
- init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
#endif
#endif
init_rq_hrtick(rq);