[RFC v2 1/4] drivers/nvdimm: Add perf interface to expose nvdimm performance stats

[Kajol Jain <kjain@linux.ibm.com>]

Patch adds performance stats reporting support for nvdimm.
Added interface includes support for pmu register/unregister
functions. A structure is added called nvdimm_pmu to be used for
adding arch/platform specific data such as supported events and pmu
event functions like event_init/add/read/del.
User could use the standard perf tool to access perf
events exposed via pmu.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
---
 drivers/nvdimm/Makefile  |  1 +
 drivers/nvdimm/nd_perf.c | 58 ++++++++++++++++++++++++++++++++++++++++
 include/linux/nd.h       | 35 ++++++++++++++++++++++++
 3 files changed, 94 insertions(+)
 create mode 100644 drivers/nvdimm/nd_perf.c

diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 29203f3d3069..25dba6095612 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -18,6 +18,7 @@ nd_e820-y := e820.o
 libnvdimm-y := core.o
 libnvdimm-y += bus.o
 libnvdimm-y += dimm_devs.o
+libnvdimm-y += nd_perf.o
 libnvdimm-y += dimm.o
 libnvdimm-y += region_devs.o
 libnvdimm-y += region.o
diff --git a/drivers/nvdimm/nd_perf.c b/drivers/nvdimm/nd_perf.c
new file mode 100644
index 000000000000..96280c1ff799
--- /dev/null
+++ b/drivers/nvdimm/nd_perf.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * nd_perf.c: NVDIMM Device Performance Monitoring Unit support
+ *
+ * Perf interface to expose nvdimm performance stats.
+ *
+ * Copyright (C) 2021 IBM Corporation
+ */
+
+#define pr_fmt(fmt) "nvdimm_pmu: " fmt
+
+#include <linux/nd.h>
+
+int register_nvdimm_pmu(struct nvdimm_pmu *nd_pmu, struct platform_device *pdev)
+{
+	int rc;
+
+	if (!nd_pmu || !pdev)
+		return -EINVAL;
+
+	/* event functions like add/del/read/event_init should not be NULL */
+	if (WARN_ON_ONCE(!(nd_pmu->event_init && nd_pmu->add && nd_pmu->del && nd_pmu->read)))
+		return -EINVAL;
+
+	nd_pmu->pmu.task_ctx_nr = perf_invalid_context;
+	nd_pmu->pmu.name = nd_pmu->name;
+	nd_pmu->pmu.event_init = nd_pmu->event_init;
+	nd_pmu->pmu.add = nd_pmu->add;
+	nd_pmu->pmu.del = nd_pmu->del;
+	nd_pmu->pmu.read = nd_pmu->read;
+
+	nd_pmu->pmu.attr_groups = nd_pmu->attr_groups;
+	nd_pmu->pmu.capabilities = PERF_PMU_CAP_NO_INTERRUPT |
+				PERF_PMU_CAP_NO_EXCLUDE;
+
+	/*
+	 * Add platform_device->dev pointer to nvdimm_pmu to access
+	 * device data in events functions.
+	 */
+	nd_pmu->dev = &pdev->dev;
+
+	rc = perf_pmu_register(&nd_pmu->pmu, nd_pmu->name, -1);
+	if (rc)
+		return rc;
+
+	pr_info("%s NVDIMM performance monitor support registered\n",
+		nd_pmu->name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_nvdimm_pmu);
+
+void unregister_nvdimm_pmu(struct pmu *nd_pmu)
+{
+	/* handle freeing of memory in arch specific code */
+	perf_pmu_unregister(nd_pmu);
+}
+EXPORT_SYMBOL_GPL(unregister_nvdimm_pmu);
diff --git a/include/linux/nd.h b/include/linux/nd.h
index ee9ad76afbba..a0e0619256be 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -8,6 +8,8 @@
 #include <linux/ndctl.h>
 #include <linux/device.h>
 #include <linux/badblocks.h>
+#include <linux/platform_device.h>
+#include <linux/perf_event.h>
 
 enum nvdimm_event {
 	NVDIMM_REVALIDATE_POISON,
@@ -23,6 +25,39 @@ enum nvdimm_claim_class {
 	NVDIMM_CCLASS_UNKNOWN,
 };
 
+/* Event attribute array index */
+#define NVDIMM_PMU_FORMAT_ATTR		0
+#define NVDIMM_PMU_EVENT_ATTR		1
+#define NVDIMM_PMU_NULL_ATTR		2
+
+/**
+ * struct nvdimm_pmu - data structure for nvdimm perf driver
+ *
+ * @name: name of the nvdimm pmu device.
+ * @pmu: pmu data structure for nvdimm performance stats.
+ * @dev: nvdimm device pointer.
+ * @functions(event_init/add/del/read): platform specific pmu functions.
+ * @attr_groups: data structure for events and formats.
+ */
+struct nvdimm_pmu {
+	const char *name;
+	struct pmu pmu;
+	struct device *dev;
+	int (*event_init)(struct perf_event *event);
+	int  (*add)(struct perf_event *event, int flags);
+	void (*del)(struct perf_event *event, int flags);
+	void (*read)(struct perf_event *event);
+	/*
+	 * Attribute groups for the nvdimm pmu. Index 0 used for
+	 * format attribute, index 1 used for event attribute and
+	 * index 2 kept as NULL.
+	 */
+	const struct attribute_group *attr_groups[3];
+};
+
+int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev);
+void unregister_nvdimm_pmu(struct pmu *pmu);
+
 struct nd_device_driver {
 	struct device_driver drv;
 	unsigned long type;
-- 
2.27.0