[PATCH v8 04/10] powerpc/perf: Add generic IMC pmu groupand event functions

[Anju T Sudhakar]

From: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>

Device tree IMC driver code parses the IMC units and their events. It
passes the information to IMC pmu code which is placed in powerpc/perf
as "imc-pmu.c".

Patch adds a set of generic imc pmu related event functions to be
used  by each imc pmu unit. Add code to setup format attribute and to
register imc pmus. Add a event_init function for nest_imc events.

Since, the IMC counters' data are periodically fed to a memory location,
the functions to read/update, start/stop, add/del can be generic and can
be used by all IMC PMU units.

Signed-off-by: Anju T Sudhakar <anju@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Madhavan Srinivasan <maddy@xxxxxxxxxxxxxxxxxx>
---
 arch/powerpc/include/asm/imc-pmu.h        |   3 +
 arch/powerpc/perf/Makefile                |   3 +
 arch/powerpc/perf/imc-pmu.c               | 269 ++++++++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal-imc.c |  10 +-
 4 files changed, 283 insertions(+), 2 deletions(-)
 create mode 100644 arch/powerpc/perf/imc-pmu.c

diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index d0193c8..6bbe184 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -92,4 +92,7 @@ struct imc_pmu {
 #define IMC_DOMAIN_NEST		1
 #define IMC_DOMAIN_UNKNOWN	-1
 
+extern struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS];
+extern struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS];
+extern int __init init_imc_pmu(struct imc_events *events,int idx, struct imc_pmu *pmu_ptr);
 #endif /* PPC_POWERNV_IMC_PMU_DEF_H */
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 4d606b9..b29d918 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -6,6 +6,9 @@ obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
 				   isa207-common.o power8-pmu.o power9-pmu.o
+
+obj-$(CONFIG_HV_PERF_IMC_CTRS)	+= imc-pmu.o
+
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
new file mode 100644
index 0000000..f09a37a
--- /dev/null
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -0,0 +1,269 @@
+/*
+ * Nest Performance Monitor counter support.
+ *
+ * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation.
+ *           (C) 2017 Anju T Sudhakar, IBM Corporation.
+ *           (C) 2017 Hemant K Shaw, IBM Corporation.
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include <asm/opal.h>
+#include <asm/imc-pmu.h>
+#include <asm/cputhreads.h>
+#include <asm/smp.h>
+#include <linux/string.h>
+
+struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS];
+struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS];
+
+/* Needed for sanity check */
+extern u64 nest_max_offset;
+
+PMU_FORMAT_ATTR(event, "config:0-20");
+static struct attribute *imc_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group imc_format_group = {
+	.name = "format",
+	.attrs = imc_format_attrs,
+};
+
+static int nest_imc_event_init(struct perf_event *event)
+{
+	int chip_id;
+	u32 config = event->attr.config;
+	struct perchip_nest_info *pcni;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* Sampling not supported */
+	if (event->hw.sample_period)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest)
+		return -EINVAL;
+
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	/* Sanity check for config (event offset) */
+	if (config > nest_max_offset)
+		return -EINVAL;
+
+	chip_id = topology_physical_package_id(event->cpu);
+	pcni = &nest_perchip_info[chip_id];
+
+	/*
+	 * Memory for Nest HW counter data could be in multiple pages.
+	 * Hence check and pick the right event base page for chip with
+	 * "chip_id" and add "config" to it".
+	 */
+	event->hw.event_base = pcni->vbase[config/PAGE_SIZE] +
+							(config & ~PAGE_MASK);
+
+	return 0;
+}
+
+static void imc_read_counter(struct perf_event *event)
+{
+	u64 *addr, data;
+
+	/*
+	 * In-Memory Collection (IMC) counters are free flowing counters.
+	 * So we take a snapshot of the counter value on enable and save it
+	 * to calculate the delta at later stage to present the event counter
+	 * value.
+	 */
+	addr = (u64 *)event->hw.event_base;
+	data = __be64_to_cpu(READ_ONCE(*addr));
+	local64_set(&event->hw.prev_count, data);
+}
+
+static void imc_perf_event_update(struct perf_event *event)
+{
+	u64 counter_prev, counter_new, final_count, *addr;
+
+	addr = (u64 *)event->hw.event_base;
+	counter_prev = local64_read(&event->hw.prev_count);
+	counter_new = __be64_to_cpu(READ_ONCE(*addr));
+	final_count = counter_new - counter_prev;
+
+	/*
+	 * Need to update prev_count is that, counter could be
+	 * read in a periodic interval from the tool side.
+	 */
+	local64_set(&event->hw.prev_count, counter_new);
+	/* Update the delta to the event count */
+	local64_add(final_count, &event->count);
+}
+
+static void imc_event_start(struct perf_event *event, int flags)
+{
+	/*
+	 * In Memory Counters are free flowing counters. HW or the microcode
+	 * keeps adding to the counter offset in memory. To get event
+	 * counter value, we snapshot the value here and we calculate
+	 * delta at later point.
+	 */
+	imc_read_counter(event);
+}
+
+static void imc_event_stop(struct perf_event *event, int flags)
+{
+	/*
+	 * Take a snapshot and calculate the delta and update
+	 * the event counter values.
+	 */
+	imc_perf_event_update(event);
+}
+
+/*
+ * The wrapper function is provided here, since we will have reserve
+ * and release lock for imc_event_start() in the following patch.
+ * Same in case of imc_event_stop().
+ */
+static void nest_imc_event_start(struct perf_event *event, int flags)
+{
+	imc_event_start(event, flags);
+}
+
+static void nest_imc_event_stop(struct perf_event *event, int flags)
+{
+	imc_event_stop(event, flags);
+}
+
+static int nest_imc_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		nest_imc_event_start(event, flags);
+
+	return 0;
+}
+
+/* update_pmu_ops : Populate the appropriate operations for "pmu" */
+static int update_pmu_ops(struct imc_pmu *pmu)
+{
+	if (!pmu)
+		return -EINVAL;
+
+	pmu->pmu.task_ctx_nr = perf_invalid_context;
+	pmu->pmu.event_init = nest_imc_event_init;
+	pmu->pmu.add = nest_imc_event_add;
+	pmu->pmu.del = nest_imc_event_stop;
+	pmu->pmu.start = nest_imc_event_start;
+	pmu->pmu.stop = nest_imc_event_stop;
+	pmu->pmu.read = imc_perf_event_update;
+	pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group;
+	pmu->pmu.attr_groups = pmu->attr_groups;
+
+	return 0;
+}
+
+/* dev_str_attr : Populate event "name" and string "str" in attribute */
+static struct attribute *dev_str_attr(const char *name, const char *str)
+{
+	struct perf_pmu_events_attr *attr;
+
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	if (!attr)
+		return NULL;
+	sysfs_attr_init(&attr->attr.attr);
+
+	attr->event_str = str;
+	attr->attr.attr.name = name;
+	attr->attr.attr.mode = 0444;
+	attr->attr.show = perf_event_sysfs_show;
+
+	return &attr->attr.attr;
+}
+
+/*
+ * update_events_in_group: Update the "events" information in an attr_group
+ *                         and assign the attr_group to the pmu "pmu".
+ */
+static int update_events_in_group(struct imc_events *events,
+				  int idx, struct imc_pmu *pmu)
+{
+	struct attribute_group *attr_group;
+	struct attribute **attrs;
+	int i;
+
+	/* If there is no events for this pmu, just return zero */
+	if (!events)
+		return 0;
+
+	/* Allocate memory for attribute group */
+	attr_group = kzalloc(sizeof(*attr_group), GFP_KERNEL);
+	if (!attr_group)
+		return -ENOMEM;
+
+	/* Allocate memory for attributes */
+	attrs = kzalloc((sizeof(struct attribute *) * (idx + 1)), GFP_KERNEL);
+	if (!attrs) {
+		kfree(attr_group);
+		return -ENOMEM;
+	}
+
+	attr_group->name = "events";
+	attr_group->attrs = attrs;
+	for (i = 0; i < idx; i++, events++) {
+		attrs[i] = dev_str_attr((char *)events->ev_name,
+					(char *)events->ev_value);
+	}
+
+	/* Save the event attribute */
+	pmu->attr_groups[IMC_EVENT_ATTR] = attr_group;
+	return 0;
+}
+
+/*
+ * init_imc_pmu : Setup and register the IMC pmu device.
+ *
+ * @events:	events memory for this pmu.
+ * @idx:	number of event entries created.
+ * @pmu_ptr:	memory allocated for this pmu.
+ */
+int __init init_imc_pmu(struct imc_events *events, int idx,
+		 struct imc_pmu *pmu_ptr)
+{
+	int ret = -ENODEV;
+
+	ret = update_events_in_group(events, idx, pmu_ptr);
+	if (ret)
+		goto err_free;
+
+	ret = update_pmu_ops(pmu_ptr);
+	if (ret)
+		goto err_free;
+
+	ret = perf_pmu_register(&pmu_ptr->pmu, pmu_ptr->pmu.name, -1);
+	if (ret)
+		goto err_free;
+
+	pr_info("%s performance monitor hardware support registered\n",
+		pmu_ptr->pmu.name);
+
+	return 0;
+
+err_free:
+	/* Only free the attr_groups which are dynamically allocated  */
+	if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]) {
+		if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs)
+			kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
+		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
+	}
+
+	return ret;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 0ddaf7d..61f6d67 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -34,8 +34,6 @@
 #include <asm/imc-pmu.h>
 
 u64 nest_max_offset;
-struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS];
-struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS];
 
 static int imc_event_prop_update(char *name, struct imc_events *events)
 {
@@ -423,8 +421,16 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
 	if (prop)
 		events = imc_events_setup(parent, pmu_index, pmu_ptr,
 					  prop, &idx);
+	/* Function to register IMC pmu */
+	ret = init_imc_pmu(events, idx, pmu_ptr);
+	if (ret) {
+		pr_err("IMC PMU %s Register failed\n", pmu_ptr->pmu.name);
+		goto free_events;
+	}
 	return 0;
 
+free_events:
+	imc_free_events(events, idx);
 free_pmu:
 	kfree(pmu_ptr);
 	return ret;
-- 
2.7.4