powerpc/powernv: Detect and create IMC device

Code to create platform device for the In-Memory Collection (IMC)
counters. Platform devices are created based on the IMC compatibility.
New header file created to contain the data structures and macros
needed for In-Memory Collection (IMC) counter pmu devices.

The device tree for IMC counters starts at the node "imc-counters".
This node contains all the IMC PMU nodes and event nodes for these IMC
PMUs. Device probe() parses the device to locate three possible IMC
device types (Nest/Core/Thread). Function then branch to parse each
unit nodes to populate vital information such as device memory sizes,
event nodes information, base address for reserve memory access (if
any) and so on. Simple bare-minimum shutdown function added which only
"stops" the engines.

Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
[mpe: Fix build with CONFIG_PERF_EVENTS=n]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 364 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
new file mode 100644
index 000000000000..7f74c282710f
--- /dev/null
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -0,0 +1,128 @@
+#ifndef __ASM_POWERPC_IMC_PMU_H
+#define __ASM_POWERPC_IMC_PMU_H
+
+/*
+ * IMC 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
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or later version.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/io.h>
+#include <asm/opal.h>
+
+/*
+ * For static allocation of some of the structures.
+ */
+#define IMC_MAX_PMUS			32
+
+/*
+ * Compatibility macros for IMC devices
+ */
+#define IMC_DTB_COMPAT			"ibm,opal-in-memory-counters"
+#define IMC_DTB_UNIT_COMPAT		"ibm,imc-counters"
+
+
+/*
+ * LDBAR: Counter address and Enable/Disable macro.
+ * perf/imc-pmu.c has the LDBAR layout information.
+ */
+#define THREAD_IMC_LDBAR_MASK           0x0003ffffffffe000ULL
+#define THREAD_IMC_ENABLE               0x8000000000000000ULL
+
+/*
+ * Structure to hold memory address information for imc units.
+ */
+struct imc_mem_info {
+	u64 *vbase;
+	u32 id;
+};
+
+/*
+ * Place holder for nest pmu events and values.
+ */
+struct imc_events {
+	u32 value;
+	char *name;
+	char *unit;
+	char *scale;
+};
+
+/* Event attribute array index */
+#define IMC_FORMAT_ATTR		0
+#define IMC_EVENT_ATTR		1
+#define IMC_CPUMASK_ATTR	2
+#define IMC_NULL_ATTR		3
+
+/* PMU Format attribute macros */
+#define IMC_EVENT_OFFSET_MASK	0xffffffffULL
+
+/*
+ * Device tree parser code detects IMC pmu support and
+ * registers new IMC pmus. This structure will hold the
+ * pmu functions, events, counter memory information
+ * and attrs for each imc pmu and will be referenced at
+ * the time of pmu registration.
+ */
+struct imc_pmu {
+	struct pmu pmu;
+	struct imc_mem_info *mem_info;
+	struct imc_events **events;
+	/*
+	 * Attribute groups for the PMU. Slot 0 used for
+	 * format attribute, slot 1 used for cpusmask attribute,
+	 * slot 2 used for event attribute. Slot 3 keep as
+	 * NULL.
+	 */
+	const struct attribute_group *attr_groups[4];
+	u32 counter_mem_size;
+	int domain;
+	/*
+	 * flag to notify whether the memory is mmaped
+	 * or allocated by kernel.
+	 */
+	bool imc_counter_mmaped;
+};
+
+/*
+ * Structure to hold id, lock and reference count for the imc events which
+ * are inited.
+ */
+struct imc_pmu_ref {
+	struct mutex lock;
+	unsigned int id;
+	int refc;
+};
+
+/*
+ * In-Memory Collection Counters type.
+ * Data comes from Device tree.
+ * Three device type are supported.
+ */
+
+enum {
+	IMC_TYPE_THREAD		= 0x1,
+	IMC_TYPE_CORE		= 0x4,
+	IMC_TYPE_CHIP           = 0x10,
+};
+
+/*
+ * Domains for IMC PMUs
+ */
+#define IMC_DOMAIN_NEST		1
+#define IMC_DOMAIN_CORE		2
+#define IMC_DOMAIN_THREAD	3
+
+extern int init_imc_pmu(struct device_node *parent,
+				struct imc_pmu *pmu_ptr, int pmu_id);
+extern void thread_imc_disable(void);
+#endif /* __ASM_POWERPC_IMC_PMU_H */
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b5d98cb3f482..a0d4353a17c9 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
+obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
new file mode 100644
index 000000000000..f57a6fbd3f57
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -0,0 +1,221 @@
+/*
+ * OPAL IMC interface detection driver
+ * Supported on POWERNV platform
+ *
+ * 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
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or later version.
+ */
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/crash_dump.h>
+#include <asm/opal.h>
+#include <asm/io.h>
+#include <asm/imc-pmu.h>
+#include <asm/cputhreads.h>
+
+/*
+ * imc_get_mem_addr_nest: Function to get nest counter memory region
+ * for each chip
+ */
+static int imc_get_mem_addr_nest(struct device_node *node,
+				 struct imc_pmu *pmu_ptr,
+				 u32 offset)
+{
+	int nr_chips = 0, i;
+	u64 *base_addr_arr, baddr;
+	u32 *chipid_arr;
+
+	nr_chips = of_property_count_u32_elems(node, "chip-id");
+	if (nr_chips <= 0)
+		return -ENODEV;
+
+	base_addr_arr = kcalloc(nr_chips, sizeof(u64), GFP_KERNEL);
+	if (!base_addr_arr)
+		return -ENOMEM;
+
+	chipid_arr = kcalloc(nr_chips, sizeof(u32), GFP_KERNEL);
+	if (!chipid_arr)
+		return -ENOMEM;
+
+	if (of_property_read_u32_array(node, "chip-id", chipid_arr, nr_chips))
+		goto error;
+
+	if (of_property_read_u64_array(node, "base-addr", base_addr_arr,
+								nr_chips))
+		goto error;
+
+	pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(struct imc_mem_info),
+								GFP_KERNEL);
+	if (!pmu_ptr->mem_info)
+		goto error;
+
+	for (i = 0; i < nr_chips; i++) {
+		pmu_ptr->mem_info[i].id = chipid_arr[i];
+		baddr = base_addr_arr[i] + offset;
+		pmu_ptr->mem_info[i].vbase = phys_to_virt(baddr);
+	}
+
+	pmu_ptr->imc_counter_mmaped = true;
+	kfree(base_addr_arr);
+	kfree(chipid_arr);
+	return 0;
+
+error:
+	kfree(pmu_ptr->mem_info);
+	kfree(base_addr_arr);
+	kfree(chipid_arr);
+	return -1;
+}
+
+/*
+ * imc_pmu_create : Takes the parent device which is the pmu unit, pmu_index
+ *		    and domain as the inputs.
+ * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets
+ */
+static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
+{
+	int ret = 0;
+	struct imc_pmu *pmu_ptr;
+	u32 offset;
+
+	/* memory for pmu */
+	pmu_ptr = kzalloc(sizeof(struct imc_pmu), GFP_KERNEL);
+	if (!pmu_ptr)
+		return -ENOMEM;
+
+	/* Set the domain */
+	pmu_ptr->domain = domain;
+
+	ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size);
+	if (ret) {
+		ret = -EINVAL;
+		goto free_pmu;
+	}
+
+	if (!of_property_read_u32(parent, "offset", &offset)) {
+		if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) {
+			ret = -EINVAL;
+			goto free_pmu;
+		}
+	}
+
+	return 0;
+
+free_pmu:
+	kfree(pmu_ptr);
+	return ret;
+}
+
+static void disable_nest_pmu_counters(void)
+{
+	int nid, cpu;
+	struct cpumask *l_cpumask;
+
+	get_online_cpus();
+	for_each_online_node(nid) {
+		l_cpumask = cpumask_of_node(nid);
+		cpu = cpumask_first(l_cpumask);
+		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
+				       get_hard_smp_processor_id(cpu));
+	}
+	put_online_cpus();
+}
+
+static void disable_core_pmu_counters(void)
+{
+	cpumask_t cores_map;
+	int cpu, rc;
+
+	get_online_cpus();
+	/* Disable the IMC Core functions */
+	cores_map = cpu_online_cores_map();
+	for_each_cpu(cpu, &cores_map) {
+		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
+					    get_hard_smp_processor_id(cpu));
+		if (rc)
+			pr_err("%s: Failed to stop Core (cpu = %d)\n",
+				__FUNCTION__, cpu);
+	}
+	put_online_cpus();
+}
+
+static int opal_imc_counters_probe(struct platform_device *pdev)
+{
+	struct device_node *imc_dev = pdev->dev.of_node;
+	int pmu_count = 0, domain;
+	u32 type;
+
+	/*
+	 * Check whether this is kdump kernel. If yes, force the engines to
+	 * stop and return.
+	 */
+	if (is_kdump_kernel()) {
+		disable_nest_pmu_counters();
+		disable_core_pmu_counters();
+		return -ENODEV;
+	}
+
+	for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) {
+		if (of_property_read_u32(imc_dev, "type", &type)) {
+			pr_warn("IMC Device without type property\n");
+			continue;
+		}
+
+		switch (type) {
+		case IMC_TYPE_CHIP:
+			domain = IMC_DOMAIN_NEST;
+			break;
+		case IMC_TYPE_CORE:
+			domain =IMC_DOMAIN_CORE;
+			break;
+		case IMC_TYPE_THREAD:
+			domain = IMC_DOMAIN_THREAD;
+			break;
+		default:
+			pr_warn("IMC Unknown Device type \n");
+			domain = -1;
+			break;
+		}
+
+		if (!imc_pmu_create(imc_dev, pmu_count, domain))
+			pmu_count++;
+	}
+
+	return 0;
+}
+
+static void opal_imc_counters_shutdown(struct platform_device *pdev)
+{
+	/*
+	 * Function only stops the engines which is bare minimum.
+	 * TODO: Need to handle proper memory cleanup and pmu
+	 * unregister.
+	 */
+	disable_nest_pmu_counters();
+	disable_core_pmu_counters();
+}
+
+static const struct of_device_id opal_imc_match[] = {
+	{ .compatible = IMC_DTB_COMPAT },
+	{},
+};
+
+static struct platform_driver opal_imc_driver = {
+	.driver = {
+		.name = "opal-imc-counters",
+		.of_match_table = opal_imc_match,
+	},
+	.probe = opal_imc_counters_probe,
+	.shutdown = opal_imc_counters_shutdown,
+};
+
+builtin_platform_driver(opal_imc_driver);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cad6b57ce494..946158e6fc1d 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
+#include <linux/of_address.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
@@ -30,6 +31,7 @@
 #include <asm/opal.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
+#include <asm/imc-pmu.h>
 
 #include "powernv.h"
 
@@ -720,6 +722,15 @@ static void opal_pdev_init(const char *compatible)
 		of_platform_device_create(np, NULL, NULL);
 }
 
+static void __init opal_imc_init_dev(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT);
+	if (np)
+		of_platform_device_create(np, NULL, NULL);
+}
+
 static int kopald(void *unused)
 {
 	unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1;
@@ -793,6 +804,9 @@ static int __init opal_init(void)
 	/* Setup a heatbeat thread if requested by OPAL */
 	opal_init_heartbeat();
 
+	/* Detect In-Memory Collection counters and create devices*/
+	opal_imc_init_dev();
+
 	/* Create leds platform devices */
 	leds = of_find_node_by_path("/ibm,opal/leds");
 	if (leds) {