powercap: intel_rapl: Introduce APIs for PMU support

Introduce two new APIs rapl_package_add_pmu()/rapl_package_remove_pmu().

RAPL driver can invoke these APIs to expose its supported energy
counters via perf PMU. The new RAPL PMU is fully compatible with current
MSR RAPL PMU, including using the same PMU name and events
name/id/unit/scale, etc.

For example, use below command
 perf stat -e power/energy-pkg/ -e power/energy-ram/ FOO
to get the energy consumption if power/energy-pkg/ and power/energy-ram/
events are available in the "perf list" output.

This does not introduce any conflict because TPMI RAPL is the only user
of these APIs currently, and it never co-exists with MSR RAPL.

Note that RAPL Packages can be probed/removed dynamically, and the
events supported by each TPMI RAPL device can be different. Thus the
RAPL PMU support is done on demand, which means
1. PMU is registered only if it is needed by a RAPL Package. PMU events
   for unsupported counters are not exposed.
2. PMU is unregistered and registered when a new RAPL Package is probed
   and supports new counters that are not supported by current PMU.
   For example, on a dual-package system using TPMI RAPL, it is possible
   that Package 1 behaves as TPMI domain root and supports Psys domain.
   In this case, register PMU without Psys event when probing Package 0,
   and re-register the PMU with Psys event when probing Package 1.
3. PMU is unregistered when all registered RAPL Packages don't need PMU.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

include/linux/intel_rapl.h

@@ -158,6 +158,26 @@ struct rapl_if_priv {
 	void *rpi;
 };
 
+#ifdef CONFIG_PERF_EVENTS
+/**
+ * struct rapl_package_pmu_data: Per package data for PMU support
+ * @scale:		Scale of 2^-32 Joules for each energy counter increase.
+ * @lock:		Lock to protect n_active and active_list.
+ * @n_active:		Number of active events.
+ * @active_list:	List of active events.
+ * @timer_interval:	Maximum timer expiration time before counter overflow.
+ * @hrtimer:		Periodically update the counter to prevent overflow.
+ */
+struct rapl_package_pmu_data {
+	u64 scale[RAPL_DOMAIN_MAX];
+	raw_spinlock_t lock;
+	int n_active;
+	struct list_head active_list;
+	ktime_t timer_interval;
+	struct hrtimer hrtimer;
+};
+#endif
+
 /* maximum rapl package domain name: package-%d-die-%d */
 #define PACKAGE_DOMAIN_NAME_LENGTH 30
 
@@ -176,6 +196,10 @@ struct rapl_package {
 	struct cpumask cpumask;
 	char name[PACKAGE_DOMAIN_NAME_LENGTH];
 	struct rapl_if_priv *priv;
+#ifdef CONFIG_PERF_EVENTS
+	bool has_pmu;
+	struct rapl_package_pmu_data pmu_data;
+#endif
 };
 
 struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv,
@@ -188,4 +212,12 @@ struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv,
 struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu);
 void rapl_remove_package(struct rapl_package *rp);
 
+#ifdef CONFIG_PERF_EVENTS
+int rapl_package_add_pmu(struct rapl_package *rp);
+void rapl_package_remove_pmu(struct rapl_package *rp);
+#else
+static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; }
+static inline void rapl_package_remove_pmu(struct rapl_package *rp) { }
+#endif
+
 #endif /* __INTEL_RAPL_H__ */