perf auxtrace arm64: Add support for HiSilicon PCIe Tune and Trace device driver

HiSilicon PCIe tune and trace device (PTT) could dynamically tune the
PCIe link's events, and trace the TLP headers).

This patch add support for PTT device in perf tool, so users could use
'perf record' to get TLP headers trace data.

Reviewed-by: Leo Yan <[e-mail]>
Signed-off-by: Qi Liu <[e-mail]>
Signed-off-by: Yicong Yang <[e-mail]>
Acked-by: John Garry <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Bjorn Helgaas <[e-mail]>
Cc: Greg Kroah-Hartman <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jonathan Cameron <[e-mail]>
Cc: Lorenzo Pieralisi <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Mathieu Poirier <[e-mail]>
Cc: Mike Leach <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Qi Liu <[e-mail]>
Cc: Shameerali Kolothum Thodi <[e-mail]>
Cc: Shaokun Zhang <[e-mail]>
Cc: Suzuki Poulouse <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Zeng Prime <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/arch/arm/util/auxtrace.c

···
  * Author: Mathieu Poirier <[e-mail]>
  */
 
+#include <dirent.h>
 #include <stdbool.h>
 #include <linux/coresight-pmu.h>
 #include <linux/zalloc.h>
+#include <api/fs/fs.h>
 
 #include "../../../util/auxtrace.h"
 #include "../../../util/debug.h"
···
 #include "../../../util/pmu.h"
 #include "cs-etm.h"
 #include "arm-spe.h"
+#include "hisi-ptt.h"
 
 static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err)
 {
···
 	return arm_spe_pmus;
 }
 
+static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err)
+{
+	const char *sysfs = sysfs__mountpoint();
+	struct perf_pmu **hisi_ptt_pmus = NULL;
+	struct dirent *dent;
+	char path[PATH_MAX];
+	DIR *dir = NULL;
+	int idx = 0;
+
+	snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH, sysfs);
+	dir = opendir(path);
+	if (!dir) {
+		pr_err("can't read directory '%s'\n", EVENT_SOURCE_DEVICE_PATH);
+		*err = -EINVAL;
+		return NULL;
+	}
+
+	while ((dent = readdir(dir))) {
+		if (strstr(dent->d_name, HISI_PTT_PMU_NAME))
+			(*nr_ptts)++;
+	}
+
+	if (!(*nr_ptts))
+		goto out;
+
+	hisi_ptt_pmus = zalloc(sizeof(struct perf_pmu *) * (*nr_ptts));
+	if (!hisi_ptt_pmus) {
+		pr_err("hisi_ptt alloc failed\n");
+		*err = -ENOMEM;
+		goto out;
+	}
+
+	rewinddir(dir);
+	while ((dent = readdir(dir))) {
+		if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) {
+			hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name);
+			if (hisi_ptt_pmus[idx])
+				idx++;
+		}
+	}
+
+out:
+	closedir(dir);
+	return hisi_ptt_pmus;
+}
+
 static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus,
 					   int pmu_nr, struct evsel *evsel)
 {
···
 {
 	struct perf_pmu	*cs_etm_pmu = NULL;
 	struct perf_pmu **arm_spe_pmus = NULL;
+	struct perf_pmu **hisi_ptt_pmus = NULL;
 	struct evsel *evsel;
 	struct perf_pmu *found_etm = NULL;
 	struct perf_pmu *found_spe = NULL;
+	struct perf_pmu *found_ptt = NULL;
 	int auxtrace_event_cnt = 0;
 	int nr_spes = 0;
+	int nr_ptts = 0;
 
 	if (!evlist)
 		return NULL;
 
 	cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME);
 	arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err);
+	hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err);
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (cs_etm_pmu && !found_etm)
···
 
 		if (arm_spe_pmus && !found_spe)
 			found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel);
+
+		if (hisi_ptt_pmus && !found_ptt)
+			found_ptt = find_pmu_for_event(hisi_ptt_pmus, nr_ptts, evsel);
 	}
 
 	free(arm_spe_pmus);
+	free(hisi_ptt_pmus);
 
 	if (found_etm)
 		auxtrace_event_cnt++;
 
 	if (found_spe)
+		auxtrace_event_cnt++;
+
+	if (found_ptt)
 		auxtrace_event_cnt++;
 
 	if (auxtrace_event_cnt > 1) {
···
 #if defined(__aarch64__)
 	if (found_spe)
 		return arm_spe_recording_init(err, found_spe);
+
+	if (found_ptt)
+		return hisi_ptt_recording_init(err, found_ptt);
 #endif
 
 	/*

tools/perf/arch/arm/util/pmu.c

···
 #include <linux/string.h>
 
 #include "arm-spe.h"
+#include "hisi-ptt.h"
 #include "../../../util/pmu.h"
 
 struct perf_event_attr
···
 #if defined(__aarch64__)
 	} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
 		return arm_spe_pmu_default_config(pmu);
+	} else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) {
+		pmu->selectable = true;
 #endif
 	}
 

tools/perf/arch/arm64/util/Build

···
 perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
 			      ../../arm/util/cs-etm.o \
-			      arm-spe.o mem-events.o
+			      arm-spe.o mem-events.o hisi-ptt.o

tools/perf/arch/arm64/util/hisi-ptt.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/zalloc.h>
+#include <time.h>
+
+#include <internal/lib.h> // page_size
+#include "../../../util/auxtrace.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/hisi-ptt.h"
+#include "../../../util/pmu.h"
+#include "../../../util/record.h"
+#include "../../../util/session.h"
+#include "../../../util/tsc.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+
+struct hisi_ptt_recording {
+	struct auxtrace_record	itr;
+	struct perf_pmu *hisi_ptt_pmu;
+	struct evlist *evlist;
+};
+
+static size_t
+hisi_ptt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			struct evlist *evlist __maybe_unused)
+{
+	return HISI_PTT_AUXTRACE_PRIV_SIZE;
+}
+
+static int hisi_ptt_info_fill(struct auxtrace_record *itr,
+			      struct perf_session *session,
+			      struct perf_record_auxtrace_info *auxtrace_info,
+			      size_t priv_size)
+{
+	struct hisi_ptt_recording *pttr =
+			container_of(itr, struct hisi_ptt_recording, itr);
+	struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu;
+
+	if (priv_size != HISI_PTT_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->core.nr_mmaps)
+		return -EINVAL;
+
+	auxtrace_info->type = PERF_AUXTRACE_HISI_PTT;
+	auxtrace_info->priv[0] = hisi_ptt_pmu->type;
+
+	return 0;
+}
+
+static int hisi_ptt_set_auxtrace_mmap_page(struct record_opts *opts)
+{
+	bool privileged = perf_event_paranoid_check(-1);
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(16) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for HISI PTT: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int hisi_ptt_recording_options(struct auxtrace_record *itr,
+				      struct evlist *evlist,
+				      struct record_opts *opts)
+{
+	struct hisi_ptt_recording *pttr =
+			container_of(itr, struct hisi_ptt_recording, itr);
+	struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu;
+	struct evsel *evsel, *hisi_ptt_evsel = NULL;
+	struct evsel *tracking_evsel;
+	int err;
+
+	pttr->evlist = evlist;
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == hisi_ptt_pmu->type) {
+			if (hisi_ptt_evsel) {
+				pr_err("There may be only one " HISI_PTT_PMU_NAME "x event\n");
+				return -EINVAL;
+			}
+			evsel->core.attr.freq = 0;
+			evsel->core.attr.sample_period = 1;
+			evsel->needs_auxtrace_mmap = true;
+			hisi_ptt_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	err = hisi_ptt_set_auxtrace_mmap_page(opts);
+	if (err)
+		return err;
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	evlist__to_front(evlist, hisi_ptt_evsel);
+	evsel__set_sample_bit(hisi_ptt_evsel, TIME);
+
+	/* Add dummy event to keep tracking */
+	err = parse_event(evlist, "dummy:u");
+	if (err)
+		return err;
+
+	tracking_evsel = evlist__last(evlist);
+	evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->core.attr.freq = 0;
+	tracking_evsel->core.attr.sample_period = 1;
+	evsel__set_sample_bit(tracking_evsel, TIME);
+
+	return 0;
+}
+
+static u64 hisi_ptt_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return rdtsc();
+}
+
+static void hisi_ptt_recording_free(struct auxtrace_record *itr)
+{
+	struct hisi_ptt_recording *pttr =
+			container_of(itr, struct hisi_ptt_recording, itr);
+
+	free(pttr);
+}
+
+struct auxtrace_record *hisi_ptt_recording_init(int *err,
+						struct perf_pmu *hisi_ptt_pmu)
+{
+	struct hisi_ptt_recording *pttr;
+
+	if (!hisi_ptt_pmu) {
+		*err = -ENODEV;
+		return NULL;
+	}
+
+	pttr = zalloc(sizeof(*pttr));
+	if (!pttr) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	pttr->hisi_ptt_pmu = hisi_ptt_pmu;
+	pttr->itr.pmu = hisi_ptt_pmu;
+	pttr->itr.recording_options = hisi_ptt_recording_options;
+	pttr->itr.info_priv_size = hisi_ptt_info_priv_size;
+	pttr->itr.info_fill = hisi_ptt_info_fill;
+	pttr->itr.free = hisi_ptt_recording_free;
+	pttr->itr.reference = hisi_ptt_reference;
+	pttr->itr.read_finish = auxtrace_record__read_finish;
+	pttr->itr.alignment = 0;
+
+	*err = 0;
+	return &pttr->itr;
+}

tools/perf/util/auxtrace.c

···
 	case PERF_AUXTRACE_S390_CPUMSF:
 		err = s390_cpumsf_process_auxtrace_info(event, session);
 		break;
+	case PERF_AUXTRACE_HISI_PTT:
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

tools/perf/util/auxtrace.h

···
 	PERF_AUXTRACE_CS_ETM,
 	PERF_AUXTRACE_ARM_SPE,
 	PERF_AUXTRACE_S390_CPUMSF,
+	PERF_AUXTRACE_HISI_PTT,
 };
 
 enum itrace_period_type {

tools/perf/util/hisi-ptt.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#ifndef INCLUDE__PERF_HISI_PTT_H__
+#define INCLUDE__PERF_HISI_PTT_H__
+
+#define HISI_PTT_PMU_NAME		"hisi_ptt"
+#define HISI_PTT_AUXTRACE_PRIV_SIZE	sizeof(u64)
+
+struct auxtrace_record *hisi_ptt_recording_init(int *err,
+						struct perf_pmu *hisi_ptt_pmu);
+
+#endif