[v2,2/2] perf/arm-ccn: Remove broken race mitigation

Commit Message

Robin Murphy April 3, 2019, 5:10 p.m. UTC

Like arm-cci, arm-ccn has the same issue of disabling preemption around
operations which can take mutexes. Again, remove the definite bug by
simply not trying to fight the theoretical races. And since we are
touching the hotplug handling code, take the opportunity to streamline
it, as there's really no need to store a full-sized cpumask to keep
track of a single CPU ID.

Signed-off-by: Robin Murphy <[e-mail]>
---
 drivers/perf/arm-ccn.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

Comments

Suzuki K Poulose April 4, 2019, 10:46 a.m. UTC | #1

Hi Robin,

On 03/04/2019 18:10, Robin Murphy wrote:
> Like arm-cci, arm-ccn has the same issue of disabling preemption around
> operations which can take mutexes. Again, remove the definite bug by
> simply not trying to fight the theoretical races. And since we are
> touching the hotplug handling code, take the opportunity to streamline
> it, as there's really no need to store a full-sized cpumask to keep
> track of a single CPU ID.
> 
> Signed-off-by: Robin Murphy <[e-mail]>
> ---
>   drivers/perf/arm-ccn.c | 23 +++++++++++------------
>   1 file changed, 11 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
> index 2ae76026e947..a0214308b0cd 100644
> --- a/drivers/perf/arm-ccn.c
> +++ b/drivers/perf/arm-ccn.c

>   	/* Pick one CPU which we will use to collect data from CCN... */
> -	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
> +	ccn->dt.cpu = raw_smp_processor_id();
>   
>   	/* Also make sure that the overflow interrupt is handled by this CPU */
>   	if (ccn->irq) {
> -		err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
> +		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
>   		if (err) {
>   			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
>   			goto error_set_affinity;
>   		}
>   	}
>   
> +	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
> +					 &ccn->dt.node);
> +
>   	err = perf_pmu_register(&ccn->dt.pmu, name, -1);
>   	if (err)
>   		goto error_pmu_register;

Should we not remove the above instance, in case we fail to register
the PMU ? Similarly for the CCI driver, we may have to reset the g_cci_pmu
if we fail.

Cheers
Suzuki


>   
> -	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
> -					 &ccn->dt.node);
> -	put_cpu();
>   	return 0;
>   
>   error_pmu_register:
>   error_set_affinity:
> -	put_cpu();
>   error_choose_name:
>   	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
>   	for (i = 0; i < ccn->num_xps; i++)
>

Patch

diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae76026e947..a0214308b0cd 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -167,7 +167,7 @@  struct arm_ccn_dt {
 
 	struct hrtimer hrtimer;
 
-	cpumask_t cpu;
+	unsigned int cpu;
 	struct hlist_node node;
 
 	struct pmu pmu;
@@ -559,7 +559,7 @@  static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
 {
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
 }
 
 static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +759,7 @@  static int arm_ccn_pmu_event_init(struct perf_event *event)
 	 * mitigate this, we enforce CPU assignment to one, selected
 	 * processor (the one described in the "cpumask" attribute).
 	 */
-	event->cpu = cpumask_first(&ccn->dt.cpu);
+	event->cpu = ccn->dt.cpu;
 
 	node_xp = CCN_CONFIG_NODE(event->attr.config);
 	type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1215,15 @@  static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
 	unsigned int target;
 
-	if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+	if (cpu != dt->cpu)
 		return 0;
 	target = cpumask_any_but(cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
-	cpumask_set_cpu(target, &dt->cpu);
+	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1299,29 +1299,28 @@  static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
-	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+	ccn->dt.cpu = raw_smp_processor_id();
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
 		}
 	}
 
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					 &ccn->dt.node);
+
 	err = perf_pmu_register(&ccn->dt.pmu, name, -1);
 	if (err)
 		goto error_pmu_register;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-					 &ccn->dt.node);
-	put_cpu();
 	return 0;
 
 error_pmu_register:
 error_set_affinity:
-	put_cpu();
 error_choose_name:
 	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)