[PATCH v4 08/11] powerpc/perf: add support for the hv gpci (get performance counter info) interface

[Cody P Schafer <cody@linux.vnet.ibm.com>]

This provides a basic link between perf and hv_gpci. Notably, it does
not yet support transactions and does not list any events (they can
still be manually composed).

Example usage via perf tool:

	perf stat -e 'hv_gpci/counter_info_version=3,offset=0,length=8,secondary_index=0,starting_index=0xffffffff,request=0x10/' -r 0 -C 0 -x ' ' sleep 0.1

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
---
 arch/powerpc/perf/hv-gpci.c | 277 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 277 insertions(+)
 create mode 100644 arch/powerpc/perf/hv-gpci.c

diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
new file mode 100644
index 0000000..cc308fc
--- /dev/null
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -0,0 +1,277 @@
+/*
+ * Hypervisor supplied "gpci" ("get performance counter info") performance
+ * counter support
+ *
+ * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
+ * Copyright 2014 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 (at your option) any later version.
+ */
+#define pr_fmt(fmt) "hv-gpci: " fmt
+
+#include <linux/init.h>
+#include <linux/perf_event.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/io.h>
+
+#include "hv-gpci.h"
+#include "hv-common.h"
+
+PMU_FORMAT_RANGE(request, config, 0, 31); /* u32 */
+PMU_FORMAT_RANGE(starting_index, config, 32, 63); /* u32 */
+PMU_FORMAT_RANGE(secondary_index, config1, 0, 15); /* u16 */
+PMU_FORMAT_RANGE(counter_info_version, config1, 16, 23); /* u8 */
+PMU_FORMAT_RANGE(length, config1, 24, 31); /* u8, bytes of data (1-8) */
+PMU_FORMAT_RANGE(offset, config1, 32, 63); /* u32, byte offset */
+
+static struct attribute *format_attrs[] = {
+	&format_attr_request.attr,
+	&format_attr_starting_index.attr,
+	&format_attr_secondary_index.attr,
+	&format_attr_counter_info_version.attr,
+
+	&format_attr_offset.attr,
+	&format_attr_length.attr,
+	NULL,
+};
+
+static struct attribute_group format_group = {
+	.name = "format",
+	.attrs = format_attrs,
+};
+
+#define HV_CAPS_ATTR(_name, _format)				\
+static ssize_t _name##_show(struct device *dev,			\
+			    struct device_attribute *attr,	\
+			    char *page)				\
+{								\
+	struct hv_perf_caps caps;				\
+	unsigned long hret = hv_perf_caps_get(&caps);		\
+	if (hret)						\
+		return -EIO;					\
+								\
+	return sprintf(page, _format, caps._name);		\
+}								\
+static struct device_attribute hv_caps_attr_##_name = __ATTR_RO(_name)
+
+static ssize_t kernel_version_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *page)
+{
+	return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
+}
+
+DEVICE_ATTR_RO(kernel_version);
+HV_CAPS_ATTR(version, "0x%x\n");
+HV_CAPS_ATTR(ga, "%d\n");
+HV_CAPS_ATTR(expanded, "%d\n");
+HV_CAPS_ATTR(lab, "%d\n");
+HV_CAPS_ATTR(collect_privileged, "%d\n");
+
+static struct attribute *interface_attrs[] = {
+	&dev_attr_kernel_version.attr,
+	&hv_caps_attr_version.attr,
+	&hv_caps_attr_ga.attr,
+	&hv_caps_attr_expanded.attr,
+	&hv_caps_attr_lab.attr,
+	&hv_caps_attr_collect_privileged.attr,
+	NULL,
+};
+
+static struct attribute_group interface_group = {
+	.name = "interface",
+	.attrs = interface_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&format_group,
+	&interface_group,
+	NULL,
+};
+
+#define GPCI_MAX_DATA_BYTES \
+	(1024 - sizeof(struct hv_get_perf_counter_info_params))
+
+static unsigned long single_gpci_request(u32 req, u32 starting_index,
+		u16 secondary_index, u8 version_in, u32 offset, u8 length,
+		u64 *value)
+{
+	unsigned long ret;
+	size_t i;
+	u64 count;
+
+	struct {
+		struct hv_get_perf_counter_info_params params;
+		uint8_t bytes[GPCI_MAX_DATA_BYTES];
+	} __packed __aligned(sizeof(uint64_t)) arg = {
+		.params = {
+			.counter_request = cpu_to_be32(req),
+			.starting_index = cpu_to_be32(starting_index),
+			.secondary_index = cpu_to_be16(secondary_index),
+			.counter_info_version_in = version_in,
+		}
+	};
+
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+			virt_to_phys(&arg), sizeof(arg));
+	if (ret) {
+		pr_devel("hcall failed: 0x%lx\n", ret);
+		return ret;
+	}
+
+	/*
+	 * we verify offset and length are within the zeroed buffer at event
+	 * init.
+	 */
+	count = 0;
+	for (i = offset; i < offset + length; i++)
+		count |= arg.bytes[i] << (i - offset);
+
+	*value = count;
+	return ret;
+}
+
+static u64 h_gpci_get_value(struct perf_event *event)
+{
+	u64 count;
+	unsigned long ret = single_gpci_request(format_get(request, event),
+					format_get(starting_index, event),
+					format_get(secondary_index, event),
+					format_get(counter_info_version, event),
+					format_get(offset, event),
+					format_get(length, event),
+					&count);
+	if (ret)
+		return 0;
+	return count;
+}
+
+static void h_gpci_event_update(struct perf_event *event)
+{
+	s64 prev;
+	u64 now = h_gpci_get_value(event);
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
+}
+
+static void h_gpci_event_start(struct perf_event *event, int flags)
+{
+	local64_set(&event->hw.prev_count, h_gpci_get_value(event));
+}
+
+static void h_gpci_event_stop(struct perf_event *event, int flags)
+{
+	h_gpci_event_update(event);
+}
+
+static int h_gpci_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		h_gpci_event_start(event, flags);
+
+	return 0;
+}
+
+static int h_gpci_event_init(struct perf_event *event)
+{
+	u64 count;
+	u8 length;
+
+	/* Not our event */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* config2 is unused */
+	if (event->attr.config2) {
+		pr_devel("config2 set when reserved\n");
+		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  ||
+	    is_sampling_event(event)) /* no sampling */
+		return -EINVAL;
+
+	/* no branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	length = format_get(length, event);
+	if (length < 1 || length > 8) {
+		pr_devel("length invalid\n");
+		return -EINVAL;
+	}
+
+	/* last byte within the buffer? */
+	if ((format_get(offset, event) + length) > GPCI_MAX_DATA_BYTES) {
+		pr_devel("request outside of buffer: %zu > %zu\n",
+				(size_t)format_get(offset, event) + length,
+				GPCI_MAX_DATA_BYTES);
+		return -EINVAL;
+	}
+
+	/* check if the request works... */
+	if (single_gpci_request(format_get(request, event),
+				format_get(starting_index, event),
+				format_get(secondary_index, event),
+				format_get(counter_info_version, event),
+				format_get(offset, event),
+				length,
+				&count)) {
+		pr_devel("gpci hcall failed\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct pmu h_gpci_pmu = {
+	.task_ctx_nr = perf_invalid_context,
+
+	.name = "hv_gpci",
+	.attr_groups = attr_groups,
+	.event_init  = h_gpci_event_init,
+	.add         = h_gpci_event_add,
+	.del         = h_gpci_event_stop,
+	.start       = h_gpci_event_start,
+	.stop        = h_gpci_event_stop,
+	.read        = h_gpci_event_update,
+
+	.event_idx = perf_event_nop_0,
+};
+
+static int hv_gpci_init(void)
+{
+	int r;
+	unsigned long hret;
+	struct hv_perf_caps caps;
+
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		pr_info("not a virtualized system, not enabling\n");
+		return -ENODEV;
+	}
+
+	hret = hv_perf_caps_get(&caps);
+	if (hret) {
+		pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+				hret);
+		return -ENODEV;
+	}
+
+	r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+device_initcall(hv_gpci_init);
-- 
1.9.0