Store the pmu in event->pmu_private, so we can get rid of the per cpu data
storage. We keep it after converting to per package data, because a cpu to
package lookup will be 3 loads versus one and these usage sites are the perf
fast pathes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/perf_event_intel_uncore.c     |   15 +--------------
 arch/x86/kernel/cpu/perf_event_intel_uncore.h     |   12 ++++++++++--
 arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c |    1 +
 3 files changed, 12 insertions(+), 16 deletions(-)

--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -92,11 +92,6 @@ ssize_t uncore_event_show(struct kobject
 	return sprintf(buf, "%s", event->config);
 }
 
-struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
-	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
-
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
 	struct intel_uncore_box *box;
@@ -122,15 +117,6 @@ struct intel_uncore_box *uncore_pmu_to_b
 	return *per_cpu_ptr(pmu->box, cpu);
 }
 
-struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
-	/*
-	 * perf core schedules event on the basis of cpu, uncore events are
-	 * collected by one of the cpus inside a physical package.
-	 */
-	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
-}
-
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 count;
@@ -690,6 +676,7 @@ static int uncore_pmu_event_init(struct
 	if (!box || box->cpu < 0)
 		return -EINVAL;
 	event->cpu = box->cpu;
+	event->pmu_private = box;
 
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -319,9 +319,17 @@ static inline bool uncore_box_is_fake(st
 	return (box->phys_id < 0);
 }
 
-struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event);
+static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+	return event->pmu_private;
+}
+
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
-struct intel_uncore_box *uncore_event_to_box(struct perf_event *event);
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -313,6 +313,7 @@ static int snb_uncore_imc_event_init(str
 		return -EINVAL;
 
 	event->cpu = box->cpu;
+	event->pmu_private = box;
 
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;