Preparation for the addition of per-core RAPL energy counter support for
AMD CPUs. Post which, one cpu might be mapped to more than one rapl_pmu
(package/die one or per-core one), also makes sense to use the
get_rapl_pmu_idx macro which is anyway used to index into the
rapl_pmus->pmus[] array.
Signed-off-by: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
---
arch/x86/events/rapl.c | 29 +++++++++++++----------------
1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index ce04dc5844c4..b997899233c3 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -162,17 +162,6 @@ static inline unsigned int get_rapl_pmu_idx(int cpu)
topology_logical_die_id(cpu);
}
-static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
-{
- unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
-
- /*
- * The unsigned check also catches the '-1' return value for non
- * existent mappings in the topology map.
- */
- return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL;
-}
-
static inline u64 rapl_read_counter(struct perf_event *event)
{
u64 raw;
@@ -348,7 +337,7 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags)
static int rapl_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config & RAPL_EVENT_MASK;
- int bit, ret = 0;
+ int bit, rapl_pmu_idx, ret = 0;
struct rapl_pmu *pmu;
/* only look at RAPL events */
@@ -376,8 +365,12 @@ static int rapl_pmu_event_init(struct perf_event *event)
if (event->attr.sample_period) /* no sampling */
return -EINVAL;
+ rapl_pmu_idx = get_rapl_pmu_idx(event->cpu);
+ if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu)
+ return -EINVAL;
+
/* must be done before validate_group */
- pmu = cpu_to_rapl_pmu(event->cpu);
+ pmu = rapl_pmus->pmus[rapl_pmu_idx];
if (!pmu)
return -EINVAL;
event->pmu_private = pmu;
@@ -623,12 +616,16 @@ static const struct attribute_group *rapl_attr_update[] = {
static void __init init_rapl_pmu(void)
{
struct rapl_pmu *pmu;
- int cpu;
+ int cpu, rapl_pmu_idx;
cpus_read_lock();
for_each_cpu(cpu, cpu_online_mask) {
- pmu = cpu_to_rapl_pmu(cpu);
+ rapl_pmu_idx = get_rapl_pmu_idx(cpu);
+ if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu)
+ continue;
+
+ pmu = rapl_pmus->pmus[rapl_pmu_idx];
if (pmu)
continue;
pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
@@ -640,7 +637,7 @@ static void __init init_rapl_pmu(void)
pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
rapl_hrtimer_init(pmu);
- rapl_pmus->pmus[get_rapl_pmu_idx(cpu)] = pmu;
+ rapl_pmus->pmus[rapl_pmu_idx] = pmu;
}
cpus_read_unlock();
--
2.34.1