1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * Hypervisor supplied "gpci" ("get performance counter info") performance
4 * counter support
5 *
6 * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
7 * Copyright 2014 IBM Corporation.
8 */
9
10#define pr_fmt(fmt) "hv-gpci: " fmt
11
12#include <linux/init.h>
13#include <linux/perf_event.h>
14#include <asm/firmware.h>
15#include <asm/hvcall.h>
16#include <asm/io.h>
17
18#include "hv-gpci.h"
19#include "hv-common.h"
20
21/*
22 * Example usage:
23 *  perf stat -e 'hv_gpci/counter_info_version=3,offset=0,length=8,
24 *		  secondary_index=0,starting_index=0xffffffff,request=0x10/' ...
25 */
26
27/* u32 */
28EVENT_DEFINE_RANGE_FORMAT(request, config, 0, 31);
29/* u32 */
30/*
31 * Note that starting_index, phys_processor_idx, sibling_part_id,
32 * hw_chip_id, partition_id all refer to the same bit range. They
33 * are basically aliases for the starting_index. The specific alias
34 * used depends on the event. See REQUEST_IDX_KIND in hv-gpci-requests.h
35 */
36EVENT_DEFINE_RANGE_FORMAT(starting_index, config, 32, 63);
37EVENT_DEFINE_RANGE_FORMAT_LITE(phys_processor_idx, config, 32, 63);
38EVENT_DEFINE_RANGE_FORMAT_LITE(sibling_part_id, config, 32, 63);
39EVENT_DEFINE_RANGE_FORMAT_LITE(hw_chip_id, config, 32, 63);
40EVENT_DEFINE_RANGE_FORMAT_LITE(partition_id, config, 32, 63);
41
42/* u16 */
43EVENT_DEFINE_RANGE_FORMAT(secondary_index, config1, 0, 15);
44/* u8 */
45EVENT_DEFINE_RANGE_FORMAT(counter_info_version, config1, 16, 23);
46/* u8, bytes of data (1-8) */
47EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31);
48/* u32, byte offset */
49EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
50
51static cpumask_t hv_gpci_cpumask;
52
53static struct attribute *format_attrs[] = {
54	&format_attr_request.attr,
55	&format_attr_starting_index.attr,
56	&format_attr_phys_processor_idx.attr,
57	&format_attr_sibling_part_id.attr,
58	&format_attr_hw_chip_id.attr,
59	&format_attr_partition_id.attr,
60	&format_attr_secondary_index.attr,
61	&format_attr_counter_info_version.attr,
62
63	&format_attr_offset.attr,
64	&format_attr_length.attr,
65	NULL,
66};
67
68static struct attribute_group format_group = {
69	.name = "format",
70	.attrs = format_attrs,
71};
72
73static struct attribute_group event_group = {
74	.name  = "events",
75	/* .attrs is set in init */
76};
77
78#define HV_CAPS_ATTR(_name, _format)				\
79static ssize_t _name##_show(struct device *dev,			\
80			    struct device_attribute *attr,	\
81			    char *page)				\
82{								\
83	struct hv_perf_caps caps;				\
84	unsigned long hret = hv_perf_caps_get(&caps);		\
85	if (hret)						\
86		return -EIO;					\
87								\
88	return sprintf(page, _format, caps._name);		\
89}								\
90static struct device_attribute hv_caps_attr_##_name = __ATTR_RO(_name)
91
92static ssize_t kernel_version_show(struct device *dev,
93				   struct device_attribute *attr,
94				   char *page)
95{
96	return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
97}
98
99static ssize_t cpumask_show(struct device *dev,
100			    struct device_attribute *attr, char *buf)
101{
102	return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask);
103}
104
105static DEVICE_ATTR_RO(kernel_version);
106static DEVICE_ATTR_RO(cpumask);
107
108HV_CAPS_ATTR(version, "0x%x\n");
109HV_CAPS_ATTR(ga, "%d\n");
110HV_CAPS_ATTR(expanded, "%d\n");
111HV_CAPS_ATTR(lab, "%d\n");
112HV_CAPS_ATTR(collect_privileged, "%d\n");
113
114static struct attribute *interface_attrs[] = {
115	&dev_attr_kernel_version.attr,
116	&hv_caps_attr_version.attr,
117	&hv_caps_attr_ga.attr,
118	&hv_caps_attr_expanded.attr,
119	&hv_caps_attr_lab.attr,
120	&hv_caps_attr_collect_privileged.attr,
121	NULL,
122};
123
124static struct attribute *cpumask_attrs[] = {
125	&dev_attr_cpumask.attr,
126	NULL,
127};
128
129static struct attribute_group cpumask_attr_group = {
130	.attrs = cpumask_attrs,
131};
132
133static struct attribute_group interface_group = {
134	.name = "interface",
135	.attrs = interface_attrs,
136};
137
138static const struct attribute_group *attr_groups[] = {
139	&format_group,
140	&event_group,
141	&interface_group,
142	&cpumask_attr_group,
143	NULL,
144};
145
146static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t));
147
148static unsigned long single_gpci_request(u32 req, u32 starting_index,
149		u16 secondary_index, u8 version_in, u32 offset, u8 length,
150		u64 *value)
151{
152	unsigned long ret;
153	size_t i;
154	u64 count;
155	struct hv_gpci_request_buffer *arg;
156
157	arg = (void *)get_cpu_var(hv_gpci_reqb);
158	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
159
160	arg->params.counter_request = cpu_to_be32(req);
161	arg->params.starting_index = cpu_to_be32(starting_index);
162	arg->params.secondary_index = cpu_to_be16(secondary_index);
163	arg->params.counter_info_version_in = version_in;
164
165	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
166			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
167	if (ret) {
168		pr_devel("hcall failed: 0x%lx\n", ret);
169		goto out;
170	}
171
172	/*
173	 * we verify offset and length are within the zeroed buffer at event
174	 * init.
175	 */
176	count = 0;
177	for (i = offset; i < offset + length; i++)
178		count |= (u64)(arg->bytes[i]) << ((length - 1 - (i - offset)) * 8);
179
180	*value = count;
181out:
182	put_cpu_var(hv_gpci_reqb);
183	return ret;
184}
185
186static u64 h_gpci_get_value(struct perf_event *event)
187{
188	u64 count;
189	unsigned long ret = single_gpci_request(event_get_request(event),
190					event_get_starting_index(event),
191					event_get_secondary_index(event),
192					event_get_counter_info_version(event),
193					event_get_offset(event),
194					event_get_length(event),
195					&count);
196	if (ret)
197		return 0;
198	return count;
199}
200
201static void h_gpci_event_update(struct perf_event *event)
202{
203	s64 prev;
204	u64 now = h_gpci_get_value(event);
205	prev = local64_xchg(&event->hw.prev_count, now);
206	local64_add(now - prev, &event->count);
207}
208
209static void h_gpci_event_start(struct perf_event *event, int flags)
210{
211	local64_set(&event->hw.prev_count, h_gpci_get_value(event));
212}
213
214static void h_gpci_event_stop(struct perf_event *event, int flags)
215{
216	h_gpci_event_update(event);
217}
218
219static int h_gpci_event_add(struct perf_event *event, int flags)
220{
221	if (flags & PERF_EF_START)
222		h_gpci_event_start(event, flags);
223
224	return 0;
225}
226
227static int h_gpci_event_init(struct perf_event *event)
228{
229	u64 count;
230	u8 length;
231
232	/* Not our event */
233	if (event->attr.type != event->pmu->type)
234		return -ENOENT;
235
236	/* config2 is unused */
237	if (event->attr.config2) {
238		pr_devel("config2 set when reserved\n");
239		return -EINVAL;
240	}
241
242	/* no branch sampling */
243	if (has_branch_stack(event))
244		return -EOPNOTSUPP;
245
246	length = event_get_length(event);
247	if (length < 1 || length > 8) {
248		pr_devel("length invalid\n");
249		return -EINVAL;
250	}
251
252	/* last byte within the buffer? */
253	if ((event_get_offset(event) + length) > HGPCI_MAX_DATA_BYTES) {
254		pr_devel("request outside of buffer: %zu > %zu\n",
255				(size_t)event_get_offset(event) + length,
256				HGPCI_MAX_DATA_BYTES);
257		return -EINVAL;
258	}
259
260	/* check if the request works... */
261	if (single_gpci_request(event_get_request(event),
262				event_get_starting_index(event),
263				event_get_secondary_index(event),
264				event_get_counter_info_version(event),
265				event_get_offset(event),
266				length,
267				&count)) {
268		pr_devel("gpci hcall failed\n");
269		return -EINVAL;
270	}
271
272	return 0;
273}
274
275static struct pmu h_gpci_pmu = {
276	.task_ctx_nr = perf_invalid_context,
277
278	.name = "hv_gpci",
279	.attr_groups = attr_groups,
280	.event_init  = h_gpci_event_init,
281	.add         = h_gpci_event_add,
282	.del         = h_gpci_event_stop,
283	.start       = h_gpci_event_start,
284	.stop        = h_gpci_event_stop,
285	.read        = h_gpci_event_update,
286	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
287};
288
289static int ppc_hv_gpci_cpu_online(unsigned int cpu)
290{
291	if (cpumask_empty(&hv_gpci_cpumask))
292		cpumask_set_cpu(cpu, &hv_gpci_cpumask);
293
294	return 0;
295}
296
297static int ppc_hv_gpci_cpu_offline(unsigned int cpu)
298{
299	int target;
300
301	/* Check if exiting cpu is used for collecting gpci events */
302	if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask))
303		return 0;
304
305	/* Find a new cpu to collect gpci events */
306	target = cpumask_last(cpu_active_mask);
307
308	if (target < 0 || target >= nr_cpu_ids) {
309		pr_err("hv_gpci: CPU hotplug init failed\n");
310		return -1;
311	}
312
313	/* Migrate gpci events to the new target */
314	cpumask_set_cpu(target, &hv_gpci_cpumask);
315	perf_pmu_migrate_context(&h_gpci_pmu, cpu, target);
316
317	return 0;
318}
319
320static int hv_gpci_cpu_hotplug_init(void)
321{
322	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
323			  "perf/powerpc/hv_gcpi:online",
324			  ppc_hv_gpci_cpu_online,
325			  ppc_hv_gpci_cpu_offline);
326}
327
328static int hv_gpci_init(void)
329{
330	int r;
331	unsigned long hret;
332	struct hv_perf_caps caps;
333	struct hv_gpci_request_buffer *arg;
334
335	hv_gpci_assert_offsets_correct();
336
337	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
338		pr_debug("not a virtualized system, not enabling\n");
339		return -ENODEV;
340	}
341
342	hret = hv_perf_caps_get(&caps);
343	if (hret) {
344		pr_debug("could not obtain capabilities, not enabling, rc=%ld\n",
345				hret);
346		return -ENODEV;
347	}
348
349	/* init cpuhotplug */
350	r = hv_gpci_cpu_hotplug_init();
351	if (r)
352		return r;
353
354	/* sampling not supported */
355	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
356
357	arg = (void *)get_cpu_var(hv_gpci_reqb);
358	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
359
360	/*
361	 * hcall H_GET_PERF_COUNTER_INFO populates the output
362	 * counter_info_version value based on the system hypervisor.
363	 * Pass the counter request 0x10 corresponds to request type
364	 * 'Dispatch_timebase_by_processor', to get the supported
365	 * counter_info_version.
366	 */
367	arg->params.counter_request = cpu_to_be32(0x10);
368
369	r = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
370			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
371	if (r) {
372		pr_devel("hcall failed, can't get supported counter_info_version: 0x%x\n", r);
373		arg->params.counter_info_version_out = 0x8;
374	}
375
376	/*
377	 * Use counter_info_version_out value to assign
378	 * required hv-gpci event list.
379	 */
380	if (arg->params.counter_info_version_out >= 0x8)
381		event_group.attrs = hv_gpci_event_attrs;
382	else
383		event_group.attrs = hv_gpci_event_attrs_v6;
384
385	put_cpu_var(hv_gpci_reqb);
386
387	r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
388	if (r)
389		return r;
390
391	return 0;
392}
393
394device_initcall(hv_gpci_init);
395