gpstate_timer_handler() uses synchronous smp_call to set the pstate
on the requested core. This causes the below hard lockup:
[c000003fe566b320] [c0000000001d5340] smp_call_function_single+0x110/0x180 (unreliable)
[c000003fe566b390] [c0000000001d55e0] smp_call_function_any+0x180/0x250
[c000003fe566b3f0] [c000000000acd3e8] gpstate_timer_handler+0x1e8/0x580
[c000003fe566b4a0] [c0000000001b46b0] call_timer_fn+0x50/0x1c0
[c000003fe566b520] [c0000000001b4958] expire_timers+0x138/0x1f0
[c000003fe566b590] [c0000000001b4bf8] run_timer_softirq+0x1e8/0x270
[c000003fe566b630] [c000000000d0d6c8] __do_softirq+0x158/0x3e4
[c000003fe566b710] [c000000000114be8] irq_exit+0xe8/0x120
[c000003fe566b730] [c000000000024d0c] timer_interrupt+0x9c/0xe0
[c000003fe566b760] [c000000000009014] decrementer_common+0x114/0x120
-- interrupt: 901 at doorbell_global_ipi+0x34/0x50
LR = arch_send_call_function_ipi_mask+0x120/0x130
[c000003fe566ba50] [c00000000004876c]
arch_send_call_function_ipi_mask+0x4c/0x130
[c000003fe566ba90] [c0000000001d59f0] smp_call_function_many+0x340/0x450
[c000003fe566bb00] [c000000000075f18] pmdp_invalidate+0x98/0xe0
[c000003fe566bb30] [c0000000003a1120] change_huge_pmd+0xe0/0x270
[c000003fe566bba0] [c000000000349278] change_protection_range+0xb88/0xe40
[c000003fe566bcf0] [c0000000003496c0] mprotect_fixup+0x140/0x340
[c000003fe566bdb0] [c000000000349a74] SyS_mprotect+0x1b4/0x350
[c000003fe566be30] [c00000000000b184] system_call+0x58/0x6c
One way to avoid this is removing the smp-call. We can ensure that the timer
always runs on one of the policy-cpus. If the timer gets migrated to a
cpu outside the policy then re-queue it back on the policy->cpus. This way
we can get rid of the smp-call which was being used to set the pstate
on the policy->cpus.
Fixes: 7bc54b652f13 (timers, cpufreq/powernv: Initialize the gpstate timer as pinned)
Cc: <stable@xxxxxxxxxxxxxxx> [4.8+]
Reported-by: Nicholas Piggin <npiggin@xxxxxxxxx>
Reported-by: Pridhiviraj Paidipeddi <ppaidipe@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Shilpasri G Bhat <shilpa.bhat@xxxxxxxxxxxxxxxxxx>
---
Changes from V1:
- Remove smp_call in the pstate handler.
drivers/cpufreq/powernv-cpufreq.c | 23 ++++++++++++++++++++---
1 file changed, 20 insertions(+), 3 deletions(-)
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 71f8682..dc8ffb5 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -679,6 +679,25 @@ void gpstate_timer_handler(struct timer_list *t)
if (!spin_trylock(&gpstates->gpstate_lock))
return;
+ /*
+ * If the timer has migrated to the different cpu then bring
+ * it back to one of the policy->cpus
+ */
+ if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
+ /*
+ * Timer should be deleted if policy is inactive.
+ * If policy is active then re-queue on one of the
+ * policy->cpus.
+ */
+ if (!cpumask_empty(policy->cpus)) {
+ gpstates->timer.expires = jiffies +
+ msecs_to_jiffies(1);
+ add_timer_on(&gpstates->timer,
+ cpumask_first(policy->cpus));
+ }
+ spin_unlock(&gpstates->gpstate_lock);
+ return;
+ }
/*
* If PMCR was last updated was using fast_swtich then
@@ -718,10 +737,8 @@ void gpstate_timer_handler(struct timer_list *t)
if (gpstate_idx != gpstates->last_lpstate_idx)
queue_gpstate_timer(gpstates);
+ set_pstate(&freq_data);
spin_unlock(&gpstates->gpstate_lock);
-
- /* Timer may get migrated to a different cpu on cpu hot unplug */
- smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
}
/*
--
1.8.3.1