Resguardo inicial

linux-7.2.3/tools/perf/arch/x86/util/Build

@@ -0,0 +1,13 @@
+perf-util-y += header.o
+perf-util-y += tsc.o
+perf-util-y += pmu.o
+perf-util-y += topdown.o
+perf-util-y += machine.o
+perf-util-y += event.o
+perf-util-y += evlist.o
+perf-util-y += mem-events.o
+perf-util-y += evsel.o
+perf-util-y += iostat.o
+perf-util-y += auxtrace.o
+perf-util-y += intel-pt.o
+perf-util-y += intel-bts.o

linux-7.2.3/tools/perf/arch/x86/util/auxtrace.c

@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * auxtrace.c: AUX area tracing support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ */
+
+#include <errno.h>
+#include <stdbool.h>
+
+#include "../../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/evlist.h"
+
+static
+struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
+						    int *err)
+{
+	struct perf_pmu *intel_pt_pmu;
+	struct perf_pmu *intel_bts_pmu;
+	struct evsel *evsel;
+	bool found_pt = false;
+	bool found_bts = false;
+
+	intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
+	intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->core.attr.type == intel_bts_pmu->type)
+			found_bts = true;
+	}
+
+	if (found_pt && found_bts) {
+		pr_err("intel_pt and intel_bts may not be used together\n");
+		*err = -EINVAL;
+		return NULL;
+	}
+
+	if (found_pt)
+		return intel_pt_recording_init(err);
+
+	if (found_bts)
+		return intel_bts_recording_init(err);
+
+	return NULL;
+}
+
+struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
+					      int *err)
+{
+	char buffer[64];
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
+	int ret;
+
+	*err = 0;
+
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
+	if (ret) {
+		*err = ret;
+		return NULL;
+	}
+
+	if (!strncmp(buffer, "GenuineIntel,", 13))
+		return auxtrace_record__init_intel(evlist, err);
+
+	return NULL;
+}

linux-7.2.3/tools/perf/arch/x86/util/cpuid.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CPUID_H
+#define PERF_CPUID_H 1
+
+
+static inline void
+cpuid(unsigned int op, unsigned int op2, unsigned int *a, unsigned int *b,
+	unsigned int *c, unsigned int *d)
+{
+	/*
+	 * Preserve %ebx/%rbx register by either placing it in %rdi or saving it
+	 * on the stack - x86-64 needs to avoid the stack red zone. In PIC
+	 * compilations %ebx contains the address of the global offset
+	 * table. %rbx is occasionally used to address stack variables in
+	 * presence of dynamic allocas.
+	 */
+	asm(
+#if defined(__x86_64__)
+		"mov %%rbx, %%rdi\n"
+		"cpuid\n"
+		"xchg %%rdi, %%rbx\n"
+#else
+		"pushl %%ebx\n"
+		"cpuid\n"
+		"movl %%ebx, %%edi\n"
+		"popl %%ebx\n"
+#endif
+		: "=a"(*a), "=D"(*b), "=c"(*c), "=d"(*d)
+		: "a"(op), "2"(op2));
+}
+
+void get_cpuid_0(char *vendor, unsigned int *lvl);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/event.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
+
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
+#include "../../../util/machine.h"
+#include "../../../util/tool.h"
+#include "../../../util/map.h"
+#include "../../../util/debug.h"
+#include "util/sample.h"
+
+#if defined(__x86_64__)
+
+struct perf_event__synthesize_extra_kmaps_cb_args {
+	const struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
+{
+	struct perf_event__synthesize_extra_kmaps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct kmap *kmap;
+	size_t size;
+
+	if (!__map__is_extra_kernel_map(map))
+		return 0;
+
+	kmap = map__kmap(map);
+
+	size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		      PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		      args->machine->id_hdr_size;
+
+	memset(event, 0, size);
+
+	event->mmap.header.type = PERF_RECORD_MMAP;
+
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(args->machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	event->mmap.header.size = size;
+
+	event->mmap.start = map__start(map);
+	event->mmap.len   = map__size(map);
+	event->mmap.pgoff = map__pgoff(map);
+	event->mmap.pid   = args->machine->pid;
+
+	strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
+
+	return 0;
+}
+
+int perf_event__synthesize_extra_kmaps(const struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc;
+	struct maps *kmaps = machine__kernel_maps(machine);
+	struct perf_event__synthesize_extra_kmaps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+		.event = zalloc(sizeof(args.event->mmap) + machine->id_hdr_size),
+	};
+
+	if (!args.event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
+	}
+
+	rc = maps__for_each_map(kmaps, perf_event__synthesize_extra_kmaps_cb, &args);
+
+	free(args.event);
+	return rc;
+}
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/evlist.c

@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "topdown.h"
+#include "evsel.h"
+
+int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
+{
+	/*
+	 * Currently the following topdown events sequence are supported to
+	 * move and regroup correctly.
+	 *
+	 * a. all events in a group
+	 *    perf stat -e "{instructions,topdown-retiring,slots}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          15,066,240     slots
+	 *          1,899,760      instructions
+	 *          2,126,998      topdown-retiring
+	 * b. all events not in a group
+	 *    perf stat -e "instructions,topdown-retiring,slots" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          2,045,561      instructions
+	 *          17,108,370     slots
+	 *          2,281,116      topdown-retiring
+	 * c. slots event in a group but topdown metrics events outside the group
+	 *    perf stat -e "{instructions,slots},topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         20,323,878      slots
+	 *          2,634,884      instructions
+	 *          3,028,656      topdown-retiring
+	 * d. slots event and topdown metrics events in two groups
+	 *    perf stat -e "{instructions,slots},{topdown-retiring}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         26,319,024      slots
+	 *          2,427,791      instructions
+	 *          2,683,508      topdown-retiring
+	 * e. slots event and metrics event are not in a group and not adjacent
+	 *    perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *         68,433,522      slots
+	 *          8,856,102      topdown-retiring
+	 *          7,791,494      instructions
+	 *         11,469,513      cycles
+	 */
+	if (topdown_sys_has_perf_metrics() &&
+	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
+		/* Ensure the topdown slots comes first. */
+		if (arch_is_topdown_slots(lhs))
+			return -1;
+		if (arch_is_topdown_slots(rhs))
+			return 1;
+
+		/*
+		 * Move topdown metrics events forward only when topdown metrics
+		 * events are not in same group with previous slots event. If
+		 * topdown metrics events are already in same group with slots
+		 * event, do nothing.
+		 */
+		if (lhs->core.leader != rhs->core.leader) {
+			bool lhs_topdown = arch_is_topdown_metrics(lhs);
+			bool rhs_topdown = arch_is_topdown_metrics(rhs);
+
+			if (lhs_topdown && !rhs_topdown)
+				return -1;
+			if (!lhs_topdown && rhs_topdown)
+				return 1;
+		}
+	}
+
+	/* Retire latency event should not be group leader*/
+	if (lhs->retire_lat && !rhs->retire_lat)
+		return 1;
+	if (!lhs->retire_lat && rhs->retire_lat)
+		return -1;
+
+	/* Default ordering by insertion index. */
+	return lhs->core.idx - rhs->core.idx;
+}
+
+int arch_evlist__add_required_events(struct list_head *list)
+{
+	struct evsel *pos, *metric_event = NULL;
+	int idx = 0;
+
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	list_for_each_entry(pos, list, core.node) {
+		if (arch_is_topdown_slots(pos)) {
+			/* Slots event already present, nothing to do. */
+			return 0;
+		}
+		if (metric_event == NULL && arch_is_topdown_metrics(pos))
+			metric_event = pos;
+		idx++;
+	}
+	if (metric_event == NULL) {
+		/* No topdown metric events, nothing to do. */
+		return 0;
+	}
+	return topdown_insert_slots_event(list, idx + 1, metric_event);
+}

linux-7.2.3/tools/perf/arch/x86/util/evsel.c

@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/evsel_config.h"
+#include "util/env.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
+#include "util/stat.h"
+#include "util/strbuf.h"
+#include "linux/string.h"
+#include "topdown.h"
+#include "evsel.h"
+#include "util/debug.h"
+#include "env.h"
+
+#define IBS_FETCH_L3MISSONLY   (1ULL << 59)
+#define IBS_OP_L3MISSONLY      (1ULL << 16)
+
+void arch_evsel__set_sample_weight(struct evsel *evsel)
+{
+	evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
+}
+
+/* Check whether the evsel's PMU supports the perf metrics */
+bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu;
+
+	if (!topdown_sys_has_perf_metrics())
+		return false;
+
+	/*
+	 * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU on a
+	 * non-hybrid machine, "cpu_core" PMU on a hybrid machine.  The
+	 * topdown_sys_has_perf_metrics checks the slots event is only available
+	 * for the core PMU, which supports the perf metrics feature. Checking
+	 * both the PERF_TYPE_RAW type and the slots event should be good enough
+	 * to detect the perf metrics feature.
+	 */
+	pmu = evsel__find_pmu(evsel);
+	return pmu && pmu->type == PERF_TYPE_RAW;
+}
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel)
+{
+	if (!evsel__sys_has_perf_metrics(evsel))
+		return false;
+
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
+}
+
+int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+{
+	u64 event = evsel->core.attr.config & PERF_HW_EVENT_MASK;
+	u64 pmu = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+	const char *event_name;
+
+	if (event < PERF_COUNT_HW_MAX && evsel__hw_names[event])
+		event_name = evsel__hw_names[event];
+	else
+		event_name = "unknown-hardware";
+
+	/* The PMU type is not required for the non-hybrid platform. */
+	if (!pmu)
+		return  scnprintf(bf, size, "%s", event_name);
+
+	return scnprintf(bf, size, "%s/%s/",
+			 evsel->pmu ? evsel->pmu->name : "cpu",
+			 event_name);
+}
+
+void arch_evsel__apply_ratio_to_prev(struct evsel *evsel,
+				struct perf_event_attr *attr)
+{
+	struct perf_event_attr *prev_attr = NULL;
+	struct evsel *evsel_prev = NULL;
+	const char *name = "acr_mask";
+	int evsel_idx = 0;
+	__u64 ev_mask, pr_ev_mask;
+
+	if (!perf_pmu__has_format(evsel->pmu, name)) {
+		pr_err("'%s' does not have acr_mask format support\n", evsel->pmu->name);
+		return;
+	}
+	if (perf_pmu__format_type(evsel->pmu, name) !=
+			PERF_PMU_FORMAT_VALUE_CONFIG2) {
+		pr_err("'%s' does not have config2 format support\n", evsel->pmu->name);
+		return;
+	}
+
+	evsel_prev = evsel__prev(evsel);
+	if (!evsel_prev) {
+		pr_err("Previous event does not exist.\n");
+		return;
+	}
+
+	prev_attr = &evsel_prev->core.attr;
+
+	if (prev_attr->config2) {
+		pr_err("'%s' has set config2 (acr_mask?) already, configuration not supported\n", evsel_prev->name);
+		return;
+	}
+
+	/*
+	 * acr_mask (config2) is calculated using the event's index in
+	 * the event group. The first event will use the index of the
+	 * second event as its mask (e.g., 0x2), indicating that the
+	 * second event counter will be reset and a sample taken for
+	 * the first event if its counter overflows. The second event
+	 * will use the mask consisting of the first and second bits
+	 * (e.g., 0x3), meaning both counters will be reset if the
+	 * second event counter overflows.
+	 */
+
+	evsel_idx = evsel__group_idx(evsel);
+	ev_mask = 1ull << evsel_idx;
+	pr_ev_mask = 1ull << (evsel_idx - 1);
+
+	prev_attr->config2 = ev_mask;
+	attr->config2 = ev_mask | pr_ev_mask;
+}
+
+static void ibs_l3miss_warn(void)
+{
+	pr_warning(
+"WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled\n"
+"and tagged operation does not cause L3 Miss. This causes sampling period skew.\n");
+}
+
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
+{
+	struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
+	static int warned_once;
+
+	if (warned_once || !x86__is_amd_cpu())
+		return;
+
+	evsel_pmu = evsel__find_pmu(evsel);
+	if (!evsel_pmu)
+		return;
+
+	ibs_fetch_pmu = perf_pmus__find("ibs_fetch");
+	ibs_op_pmu = perf_pmus__find("ibs_op");
+
+	if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_FETCH_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	} else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_OP_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	}
+}
+
+static int amd_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
+{
+	struct perf_pmu *pmu;
+
+	if (evsel->core.attr.precise_ip == 0)
+		return 0;
+
+	pmu = evsel__find_pmu(evsel);
+	if (!pmu || strncmp(pmu->name, "ibs", 3))
+		return 0;
+
+	/* More verbose IBS errors. */
+	if (evsel->core.attr.exclude_kernel || evsel->core.attr.exclude_user ||
+	    evsel->core.attr.exclude_hv || evsel->core.attr.exclude_idle ||
+	    evsel->core.attr.exclude_host || evsel->core.attr.exclude_guest) {
+		return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try "
+				 "again without the privilege modifiers (like 'k') at the end.");
+	}
+	return 0;
+}
+
+static int intel_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int ret;
+
+	if (err != EINVAL)
+		return 0;
+
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	if (arch_is_topdown_slots(evsel)) {
+		if (!evsel__is_group_leader(evsel)) {
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Topdown slots event can only be group leader "
+					"in '%s'.", sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	} else if (arch_is_topdown_metrics(evsel)) {
+		struct evsel *pos;
+
+		evlist__for_each_entry(evsel->evlist, pos) {
+			if (pos == evsel || !arch_is_topdown_metrics(pos))
+				continue;
+
+			if (pos->core.attr.config != evsel->core.attr.config)
+				continue;
+
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Perf metric event '%s' is duplicated "
+					"in the same group (only one event is allowed) in '%s'.",
+					evsel__name(evsel), sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+int arch_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	return x86__is_amd_cpu()
+		? amd_evsel__open_strerror(evsel, msg, size)
+		: intel_evsel__open_strerror(evsel, err, msg, size);
+}

linux-7.2.3/tools/perf/arch/x86/util/evsel.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EVSEL_H
+#define _EVSEL_H 1
+
+bool evsel__sys_has_perf_metrics(const struct evsel *evsel);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/header.c

@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/types.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <regex.h>
+
+#include "../../../util/debug.h"
+#include "../../../util/header.h"
+#include "cpuid.h"
+
+void get_cpuid_0(char *vendor, unsigned int *lvl)
+{
+	unsigned int b, c, d;
+
+	cpuid(0, 0, lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
+}
+
+static int
+__get_cpuid(char *buffer, size_t sz, const char *fmt)
+{
+	unsigned int a, b, c, d, lvl;
+	int family = -1, model = -1, step = -1;
+	int nb;
+	char vendor[16];
+
+	get_cpuid_0(vendor, &lvl);
+
+	if (lvl >= 1) {
+		cpuid(1, 0, &a, &b, &c, &d);
+
+		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
+		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
+		step   = a & 0xf;
+
+		/* extended family */
+		if (family == 0xf)
+			family += (a >> 20) & 0xff;
+
+		/* extended model */
+		if (family >= 0x6)
+			model += ((a >> 16) & 0xf) << 4;
+	}
+	nb = scnprintf(buffer, sz, fmt, vendor, family, model, step);
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return ENOBUFS;
+}
+
+int
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
+{
+	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
+}
+
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
+{
+	char *buf = malloc(128);
+
+	if (buf && __get_cpuid(buf, 128, "%s-%u-%X-%X$") < 0) {
+		free(buf);
+		return NULL;
+	}
+	return buf;
+}
+
+/* Full CPUID format for x86 is vendor-family-model-stepping */
+static bool is_full_cpuid(const char *id)
+{
+	const char *tmp = id;
+	int count = 0;
+
+	while ((tmp = strchr(tmp, '-')) != NULL) {
+		count++;
+		tmp++;
+	}
+
+	if (count == 3)
+		return true;
+
+	return false;
+}
+
+int strcmp_cpuid_str(const char *mapcpuid, const char *id)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+	bool full_mapcpuid = is_full_cpuid(mapcpuid);
+	bool full_cpuid = is_full_cpuid(id);
+
+	/*
+	 * Full CPUID format is required to identify a platform.
+	 * Error out if the cpuid string is incomplete.
+	 */
+	if (full_mapcpuid && !full_cpuid) {
+		pr_info("Invalid CPUID %s. Full CPUID is required, "
+			"vendor-family-model-stepping\n", id);
+		return 1;
+	}
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, id, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+		size_t cpuid_len;
+
+		/* If the full CPUID format isn't required,
+		 * ignoring the stepping.
+		 */
+		if (!full_mapcpuid && full_cpuid)
+			cpuid_len = strrchr(id, '-') - id;
+		else
+			cpuid_len = strlen(id);
+
+		/* Verify the entire string matched. */
+		if (match_len == cpuid_len)
+			return 0;
+	}
+
+	return 1;
+}

linux-7.2.3/tools/perf/arch/x86/util/intel-bts.c

@@ -0,0 +1,453 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * intel-bts.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ */
+
+#include "../../../util/intel-bts.h"
+
+#include <errno.h>
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+#include <linux/zalloc.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/mmap.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
+#include "../../../util/record.h"
+#include "../../../util/session.h"
+#include "../../../util/tsc.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+struct intel_bts_snapshot_ref {
+	void	*ref_buf;
+	size_t	ref_offset;
+	bool	wrapped;
+};
+
+struct intel_bts_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*intel_bts_pmu;
+	struct evlist		*evlist;
+	bool				snapshot_mode;
+	size_t				snapshot_size;
+	int				snapshot_ref_cnt;
+	struct intel_bts_snapshot_ref	*snapshot_refs;
+};
+
+struct branch {
+	u64 from;
+	u64 to;
+	u64 misc;
+};
+
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			 struct evlist *evlist __maybe_unused)
+{
+	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
+}
+
+static int intel_bts_info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct perf_record_auxtrace_info *auxtrace_info,
+			       size_t priv_size)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct perf_event_mmap_page *pc;
+	struct perf_tsc_conversion tc = { .time_mult = 0, };
+	bool cap_user_time_zero = false;
+	int err;
+
+	if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->core.nr_mmaps)
+		return -EINVAL;
+
+	pc = session->evlist->mmap[0].core.base;
+	if (pc) {
+		err = perf_read_tsc_conversion(pc, &tc);
+		if (err) {
+			if (err != -EOPNOTSUPP)
+				return err;
+		} else {
+			cap_user_time_zero = tc.time_mult != 0;
+		}
+		if (!cap_user_time_zero)
+			ui__warning("Intel BTS: TSC not available\n");
+	}
+
+	auxtrace_info->type = PERF_AUXTRACE_INTEL_BTS;
+	auxtrace_info->priv[INTEL_BTS_PMU_TYPE] = intel_bts_pmu->type;
+	auxtrace_info->priv[INTEL_BTS_TIME_SHIFT] = tc.time_shift;
+	auxtrace_info->priv[INTEL_BTS_TIME_MULT] = tc.time_mult;
+	auxtrace_info->priv[INTEL_BTS_TIME_ZERO] = tc.time_zero;
+	auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+	auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE] = btsr->snapshot_mode;
+
+	return 0;
+}
+
+static int intel_bts_recording_options(struct auxtrace_record *itr,
+				       struct evlist *evlist,
+				       struct record_opts *opts)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct evsel *evsel, *intel_bts_evsel = NULL;
+	const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
+	bool privileged = perf_event_paranoid_check(-1);
+
+	if (opts->auxtrace_sample_mode) {
+		pr_err("Intel BTS does not support AUX area sampling\n");
+		return -EINVAL;
+	}
+
+	btsr->evlist = evlist;
+	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == intel_bts_pmu->type) {
+			if (intel_bts_evsel) {
+				pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
+				return -EINVAL;
+			}
+			evsel->core.attr.freq = 0;
+			evsel->core.attr.sample_period = 1;
+			evsel->needs_auxtrace_mmap = true;
+			intel_bts_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+		pr_err("Snapshot mode (-S option) requires " INTEL_BTS_PMU_NAME " PMU event (-e " INTEL_BTS_PMU_NAME ")\n");
+		return -EINVAL;
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	if (opts->full_auxtrace && !perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
+		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
+		return -EINVAL;
+	}
+
+	/* Set default sizes for snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages = KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+			   opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+		if (!opts->auxtrace_snapshot_size)
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+		pr_debug2("Intel BTS snapshot size: %zu\n",
+			  opts->auxtrace_snapshot_size);
+	}
+
+	/* Set default sizes for full trace mode */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / 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;
+
+		if (opts->auxtrace_snapshot_mode)
+			min_sz = KiB(4);
+		else
+			min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for Intel BTS: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+	if (intel_bts_evsel) {
+		/*
+		 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+		 * must come first.
+		 */
+		evlist__to_front(evlist, intel_bts_evsel);
+		/*
+		 * In the case of per-cpu mmaps, we need the CPU on the
+		 * AUX event.
+		 */
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
+			evsel__set_sample_bit(intel_bts_evsel, CPU);
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct evsel *tracking_evsel;
+		int err;
+
+		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;
+	}
+
+	return 0;
+}
+
+static int intel_bts_parse_snapshot_options(struct auxtrace_record *itr,
+					    struct record_opts *opts,
+					    const char *str)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	btsr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static u64 intel_bts_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return rdtsc();
+}
+
+static int intel_bts_alloc_snapshot_refs(struct intel_bts_recording *btsr,
+					 int idx)
+{
+	const size_t sz = sizeof(struct intel_bts_snapshot_ref);
+	int cnt = btsr->snapshot_ref_cnt, new_cnt = cnt * 2;
+	struct intel_bts_snapshot_ref *refs;
+
+	if (!new_cnt)
+		new_cnt = 16;
+
+	while (new_cnt <= idx)
+		new_cnt *= 2;
+
+	refs = calloc(new_cnt, sz);
+	if (!refs)
+		return -ENOMEM;
+
+	memcpy(refs, btsr->snapshot_refs, cnt * sz);
+
+	btsr->snapshot_refs = refs;
+	btsr->snapshot_ref_cnt = new_cnt;
+
+	return 0;
+}
+
+static void intel_bts_free_snapshot_refs(struct intel_bts_recording *btsr)
+{
+	int i;
+
+	for (i = 0; i < btsr->snapshot_ref_cnt; i++)
+		zfree(&btsr->snapshot_refs[i].ref_buf);
+	zfree(&btsr->snapshot_refs);
+}
+
+static void intel_bts_recording_free(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+
+	intel_bts_free_snapshot_refs(btsr);
+	free(btsr);
+}
+
+static int intel_bts_snapshot_start(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(btsr->evlist, evsel) {
+		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
+			return evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(btsr->evlist, evsel) {
+		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
+			return evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static bool intel_bts_first_wrap(u64 *data, size_t buf_size)
+{
+	int i, a, b;
+
+	b = buf_size >> 3;
+	a = b - 512;
+	if (a < 0)
+		a = 0;
+
+	for (i = a; i < b; i++) {
+		if (data[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm, unsigned char *data,
+				   u64 *head, u64 *old)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	bool wrapped;
+	int err;
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head);
+
+	if (idx >= btsr->snapshot_ref_cnt) {
+		err = intel_bts_alloc_snapshot_refs(btsr, idx);
+		if (err)
+			goto out_err;
+	}
+
+	wrapped = btsr->snapshot_refs[idx].wrapped;
+	if (!wrapped && intel_bts_first_wrap((u64 *)data, mm->len)) {
+		btsr->snapshot_refs[idx].wrapped = true;
+		wrapped = true;
+	}
+
+	/*
+	 * In full trace mode 'head' continually increases.  However in snapshot
+	 * mode 'head' is an offset within the buffer.  Here 'old' and 'head'
+	 * are adjusted to match the full trace case which expects that 'old' is
+	 * always less than 'head'.
+	 */
+	if (wrapped) {
+		*old = *head;
+		*head += mm->len;
+	} else {
+		if (mm->mask)
+			*old &= mm->mask;
+		else
+			*old %= mm->len;
+		if (*old > *head)
+			*head += mm->len;
+	}
+
+	pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+		  __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+	return 0;
+
+out_err:
+	pr_err("%s: failed, error %d\n", __func__, err);
+	return err;
+}
+
+struct auxtrace_record *intel_bts_recording_init(int *err)
+{
+	struct perf_pmu *intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
+	struct intel_bts_recording *btsr;
+
+	if (!intel_bts_pmu)
+		return NULL;
+
+	if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) {
+		*err = -errno;
+		return NULL;
+	}
+
+	btsr = zalloc(sizeof(struct intel_bts_recording));
+	if (!btsr) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.recording_options = intel_bts_recording_options;
+	btsr->itr.info_priv_size = intel_bts_info_priv_size;
+	btsr->itr.info_fill = intel_bts_info_fill;
+	btsr->itr.free = intel_bts_recording_free;
+	btsr->itr.snapshot_start = intel_bts_snapshot_start;
+	btsr->itr.snapshot_finish = intel_bts_snapshot_finish;
+	btsr->itr.find_snapshot = intel_bts_find_snapshot;
+	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
+	btsr->itr.reference = intel_bts_reference;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
+	btsr->itr.alignment = sizeof(struct branch);
+	return &btsr->itr;
+}

linux-7.2.3/tools/perf/arch/x86/util/iostat.c

@@ -0,0 +1,475 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * perf iostat
+ *
+ * Copyright (C) 2020, Intel Corporation
+ *
+ * Authors: Alexander Antonov <alexander.antonov@linux.intel.com>
+ */
+
+#include <api/fs/fs.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/zalloc.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <regex.h>
+#include "util/cpumap.h"
+#include "util/debug.h"
+#include "util/iostat.h"
+#include "util/counts.h"
+#include "path.h"
+
+#ifndef MAX_PATH
+#define MAX_PATH 1024
+#endif
+
+#define UNCORE_IIO_PMU_PATH	"bus/event_source/devices/uncore_iio_%d"
+#define SYSFS_UNCORE_PMU_PATH	"%s/"UNCORE_IIO_PMU_PATH
+#define PLATFORM_MAPPING_PATH	UNCORE_IIO_PMU_PATH"/die%d"
+
+/*
+ * Each metric requiries one IIO event which increments at every 4B transfer
+ * in corresponding direction. The formulas to compute metrics are generic:
+ *     #EventCount * 4B / (1024 * 1024)
+ */
+static const char * const iostat_metrics[] = {
+	"Inbound Read(MB)",
+	"Inbound Write(MB)",
+	"Outbound Read(MB)",
+	"Outbound Write(MB)",
+};
+
+static inline int iostat_metrics_count(void)
+{
+	return sizeof(iostat_metrics) / sizeof(char *);
+}
+
+static const char *iostat_metric_by_idx(int idx)
+{
+	return *(iostat_metrics + idx % iostat_metrics_count());
+}
+
+struct iio_root_port {
+	u32 domain;
+	u8 bus;
+	u8 die;
+	u8 pmu_idx;
+	int idx;
+};
+
+struct iio_root_ports_list {
+	struct iio_root_port **rps;
+	int nr_entries;
+};
+
+static struct iio_root_ports_list *root_ports;
+
+static void iio_root_port_show(FILE *output,
+			       const struct iio_root_port * const rp)
+{
+	if (output && rp)
+		fprintf(output, "S%d-uncore_iio_%d<%04x:%02x>\n",
+			rp->die, rp->pmu_idx, rp->domain, rp->bus);
+}
+
+static struct iio_root_port *iio_root_port_new(u32 domain, u8 bus,
+					       u8 die, u8 pmu_idx)
+{
+	struct iio_root_port *p = calloc(1, sizeof(*p));
+
+	if (p) {
+		p->domain = domain;
+		p->bus = bus;
+		p->die = die;
+		p->pmu_idx = pmu_idx;
+	}
+	return p;
+}
+
+static void iio_root_ports_list_free(struct iio_root_ports_list *list)
+{
+	int idx;
+
+	if (list) {
+		for (idx = 0; idx < list->nr_entries; idx++)
+			zfree(&list->rps[idx]);
+		zfree(&list->rps);
+		free(list);
+	}
+}
+
+static struct iio_root_port *iio_root_port_find_by_notation(
+	const struct iio_root_ports_list * const list, u32 domain, u8 bus)
+{
+	int idx;
+	struct iio_root_port *rp;
+
+	if (list) {
+		for (idx = 0; idx < list->nr_entries; idx++) {
+			rp = list->rps[idx];
+			if (rp && rp->domain == domain && rp->bus == bus)
+				return rp;
+		}
+	}
+	return NULL;
+}
+
+static int iio_root_ports_list_insert(struct iio_root_ports_list *list,
+				      struct iio_root_port * const rp)
+{
+	struct iio_root_port **tmp_buf;
+
+	if (list && rp) {
+		rp->idx = list->nr_entries++;
+		tmp_buf = realloc(list->rps,
+				  list->nr_entries * sizeof(*list->rps));
+		if (!tmp_buf) {
+			pr_err("Failed to realloc memory\n");
+			return -ENOMEM;
+		}
+		tmp_buf[rp->idx] = rp;
+		list->rps = tmp_buf;
+	}
+	return 0;
+}
+
+static int iio_mapping(u8 pmu_idx, struct iio_root_ports_list * const list)
+{
+	char *buf;
+	char path[MAX_PATH];
+	u32 domain;
+	u8 bus;
+	struct iio_root_port *rp;
+	size_t size;
+	int ret;
+
+	for (int die = 0; die < cpu__max_node(); die++) {
+		scnprintf(path, MAX_PATH, PLATFORM_MAPPING_PATH, pmu_idx, die);
+		if (sysfs__read_str(path, &buf, &size) < 0) {
+			if (pmu_idx)
+				goto out;
+			pr_err("Mode iostat is not supported\n");
+			return -1;
+		}
+		ret = sscanf(buf, "%04x:%02hhx", &domain, &bus);
+		free(buf);
+		if (ret != 2) {
+			pr_err("Invalid mapping data: iio_%d; die%d\n",
+			       pmu_idx, die);
+			return -1;
+		}
+		rp = iio_root_port_new(domain, bus, die, pmu_idx);
+		if (!rp || iio_root_ports_list_insert(list, rp)) {
+			free(rp);
+			return -ENOMEM;
+		}
+	}
+out:
+	return 0;
+}
+
+static u8 iio_pmu_count(void)
+{
+	u8 pmu_idx = 0;
+	char path[MAX_PATH];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (sysfs) {
+		for (;; pmu_idx++) {
+			snprintf(path, sizeof(path), SYSFS_UNCORE_PMU_PATH,
+				 sysfs, pmu_idx);
+			if (access(path, F_OK) != 0)
+				break;
+		}
+	}
+	return pmu_idx;
+}
+
+static int iio_root_ports_scan(struct iio_root_ports_list **list)
+{
+	int ret = -ENOMEM;
+	struct iio_root_ports_list *tmp_list;
+	u8 pmu_count = iio_pmu_count();
+
+	if (!pmu_count) {
+		pr_err("Unsupported uncore pmu configuration\n");
+		return -1;
+	}
+
+	tmp_list = calloc(1, sizeof(*tmp_list));
+	if (!tmp_list)
+		goto err;
+
+	for (u8 pmu_idx = 0; pmu_idx < pmu_count; pmu_idx++) {
+		ret = iio_mapping(pmu_idx, tmp_list);
+		if (ret)
+			break;
+	}
+err:
+	if (!ret)
+		*list = tmp_list;
+	else
+		iio_root_ports_list_free(tmp_list);
+
+	return ret;
+}
+
+static int iio_root_port_parse_str(u32 *domain, u8 *bus, char *str)
+{
+	int ret;
+	regex_t regex;
+	/*
+	 * Expected format domain:bus:
+	 * Valid domain range [0:ffff]
+	 * Valid bus range [0:ff]
+	 * Example: 0000:af, 0:3d, 01:7
+	 */
+	regcomp(&regex, "^([a-f0-9A-F]{1,}):([a-f0-9A-F]{1,2})", REG_EXTENDED);
+	ret = regexec(&regex, str, 0, NULL, 0);
+	if (ret || sscanf(str, "%08x:%02hhx", domain, bus) != 2)
+		pr_warning("Unrecognized root port format: %s\n"
+			   "Please use the following format:\n"
+			   "\t [domain]:[bus]\n"
+			   "\t for example: 0000:3d\n", str);
+
+	regfree(&regex);
+	return ret;
+}
+
+static int iio_root_ports_list_filter(struct iio_root_ports_list **list,
+				      const char *filter)
+{
+	char *tok, *tmp, *filter_copy = NULL;
+	struct iio_root_port *rp;
+	u32 domain;
+	u8 bus;
+	int ret = -ENOMEM;
+	struct iio_root_ports_list *tmp_list = calloc(1, sizeof(*tmp_list));
+
+	if (!tmp_list)
+		goto err;
+
+	filter_copy = strdup(filter);
+	if (!filter_copy)
+		goto err;
+
+	for (tok = strtok_r(filter_copy, ",", &tmp); tok;
+	     tok = strtok_r(NULL, ",", &tmp)) {
+		if (!iio_root_port_parse_str(&domain, &bus, tok)) {
+			rp = iio_root_port_find_by_notation(*list, domain, bus);
+			if (rp) {
+				(*list)->rps[rp->idx] = NULL;
+				ret = iio_root_ports_list_insert(tmp_list, rp);
+				if (ret) {
+					free(rp);
+					goto err;
+				}
+			} else if (!iio_root_port_find_by_notation(tmp_list,
+								   domain, bus))
+				pr_warning("Root port %04x:%02x were not found\n",
+					   domain, bus);
+		}
+	}
+
+	if (tmp_list->nr_entries == 0) {
+		pr_err("Requested root ports were not found\n");
+		ret = -EINVAL;
+	}
+err:
+	iio_root_ports_list_free(*list);
+	if (ret)
+		iio_root_ports_list_free(tmp_list);
+	else
+		*list = tmp_list;
+
+	free(filter_copy);
+	return ret;
+}
+
+static int iostat_event_group(struct evlist *evl,
+			      struct iio_root_ports_list *list)
+{
+	int ret;
+	int idx;
+	const char *iostat_cmd_template =
+	"{uncore_iio_%x/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0x83,umask=0x01,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0xc0,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0xc0,umask=0x01,ch_mask=0xF,fc_mask=0x07/}";
+	const int len_template = strlen(iostat_cmd_template) + 1;
+	struct evsel *evsel = NULL;
+	int metrics_count = iostat_metrics_count();
+	char *iostat_cmd = calloc(len_template, 1);
+
+	if (!iostat_cmd)
+		return -ENOMEM;
+
+	for (idx = 0; idx < list->nr_entries; idx++) {
+		sprintf(iostat_cmd, iostat_cmd_template,
+			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx,
+			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx);
+		ret = parse_event(evl, iostat_cmd);
+		if (ret)
+			goto err;
+	}
+
+	evlist__for_each_entry(evl, evsel) {
+		evsel->priv = list->rps[evsel->core.idx / metrics_count];
+	}
+	list->nr_entries = 0;
+err:
+	iio_root_ports_list_free(list);
+	free(iostat_cmd);
+	return ret;
+}
+
+int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config)
+{
+	if (evlist->core.nr_entries > 0) {
+		pr_warning("The -e and -M options are not supported."
+			   "All chosen events/metrics will be dropped\n");
+		evlist__delete(evlist);
+		evlist = evlist__new();
+		if (!evlist)
+			return -ENOMEM;
+	}
+
+	config->metric_only = true;
+	config->aggr_mode = AGGR_GLOBAL;
+
+	return iostat_event_group(evlist, root_ports);
+}
+
+int iostat_parse(const struct option *opt, const char *str,
+		 int unset __maybe_unused)
+{
+	int ret;
+	struct perf_stat_config *config = (struct perf_stat_config *)opt->data;
+
+	ret = iio_root_ports_scan(&root_ports);
+	if (!ret) {
+		config->iostat_run = true;
+		if (!str)
+			iostat_mode = IOSTAT_RUN;
+		else if (!strcmp(str, "list"))
+			iostat_mode = IOSTAT_LIST;
+		else {
+			iostat_mode = IOSTAT_RUN;
+			ret = iio_root_ports_list_filter(&root_ports, str);
+		}
+	}
+	return ret;
+}
+
+void iostat_list(struct evlist *evlist, struct perf_stat_config *config)
+{
+	struct evsel *evsel;
+	struct iio_root_port *rp = NULL;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (rp != evsel->priv) {
+			rp = evsel->priv;
+			iio_root_port_show(config->output, rp);
+		}
+	}
+}
+
+void iostat_release(struct evlist *evlist)
+{
+	struct evsel *evsel;
+	struct iio_root_port *rp = NULL;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (rp != evsel->priv) {
+			rp = evsel->priv;
+			zfree(&evsel->priv);
+		}
+	}
+}
+
+void iostat_prefix(struct evlist *evlist,
+		   struct perf_stat_config *config,
+		   char *prefix, struct timespec *ts)
+{
+	struct iio_root_port *rp = evlist->selected->priv;
+
+	if (rp) {
+		/*
+		 * TODO: This is the incorrect format in JSON mode.
+		 *       See prepare_timestamp()
+		 */
+		if (ts)
+			sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s",
+				ts->tv_sec, ts->tv_nsec,
+				config->csv_sep, rp->domain, rp->bus,
+				config->csv_sep);
+		else
+			sprintf(prefix, "%04x:%02x%s", rp->domain, rp->bus,
+				config->csv_sep);
+	}
+}
+
+void iostat_print_header_prefix(struct perf_stat_config *config)
+{
+	if (config->csv_output)
+		fputs("port,", config->output);
+	else if (config->interval)
+		fprintf(config->output, "#          time    port         ");
+	else
+		fprintf(config->output, "   port         ");
+}
+
+void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
+			 struct perf_stat_output_ctx *out)
+{
+	double iostat_value = 0;
+	u64 prev_count_val = 0;
+	const char *iostat_metric = iostat_metric_by_idx(evsel->core.idx);
+	u8 die = ((struct iio_root_port *)evsel->priv)->die;
+	struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
+
+	if (count && count->run && count->ena) {
+		if (evsel->prev_raw_counts && !out->force_header) {
+			struct perf_counts_values *prev_count =
+				perf_counts(evsel->prev_raw_counts, die, 0);
+
+			prev_count_val = prev_count->val;
+			prev_count->val = count->val;
+		}
+		iostat_value = (count->val - prev_count_val) /
+			       ((double) count->run / count->ena);
+	}
+	out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.0f", iostat_metric,
+			  iostat_value / (256 * 1024));
+}
+
+void iostat_print_counters(struct evlist *evlist,
+			   struct perf_stat_config *config, struct timespec *ts,
+			   char *prefix, iostat_print_counter_t print_cnt_cb, void *arg)
+{
+	void *perf_device = NULL;
+	struct evsel *counter = evlist__first(evlist);
+
+	evlist__set_selected(evlist, counter);
+	iostat_prefix(evlist, config, prefix, ts);
+	fprintf(config->output, "%s", prefix);
+	evlist__for_each_entry(evlist, counter) {
+		perf_device = evlist->selected->priv;
+		if (perf_device && perf_device != counter->priv) {
+			evlist__set_selected(evlist, counter);
+			iostat_prefix(evlist, config, prefix, ts);
+			fprintf(config->output, "\n%s", prefix);
+		}
+		print_cnt_cb(config, counter, arg);
+	}
+	fputc('\n', config->output);
+}

linux-7.2.3/tools/perf/arch/x86/util/machine.c

@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <limits.h>
+#include <stdlib.h>
+
+#include <internal/lib.h> // page_size
+#include "../../../util/machine.h"
+#include "../../../util/map.h"
+#include "../../../util/symbol.h"
+#include <linux/ctype.h>
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+	int cnt;
+	int max_cnt;
+	struct extra_kernel_map *maps;
+	bool get_entry_trampolines;
+	u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+				u64 end, u64 pgoff, const char *name)
+{
+	if (mi->cnt >= mi->max_cnt) {
+		void *buf;
+		size_t sz;
+
+		mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+		sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+		buf = realloc(mi->maps, sz);
+		if (!buf)
+			return -1;
+		mi->maps = buf;
+	}
+
+	mi->maps[mi->cnt].start = start;
+	mi->maps[mi->cnt].end   = end;
+	mi->maps[mi->cnt].pgoff = pgoff;
+	strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+	mi->cnt += 1;
+
+	return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+				  u64 start)
+{
+	struct extra_kernel_map_info *mi = arg;
+
+	if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+	    !strcmp(name, "_entry_trampoline")) {
+		mi->entry_trampoline = start;
+		return 0;
+	}
+
+	if (is_entry_trampoline(name)) {
+		u64 end = start + page_size;
+
+		return add_extra_kernel_map(mi, start, end, 0, name);
+	}
+
+	return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel)
+{
+	struct extra_kernel_map_info mi = { .cnt = 0, };
+	char filename[PATH_MAX];
+	int ret;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+	if (ret)
+		goto out_free;
+
+	if (!mi.entry_trampoline)
+		goto out_free;
+
+	for (i = 0; i < mi.cnt; i++) {
+		struct extra_kernel_map *xm = &mi.maps[i];
+
+		xm->pgoff = mi.entry_trampoline;
+		ret = machine__create_extra_kernel_map(machine, kernel, xm);
+		if (ret)
+			goto out_free;
+	}
+
+	machine->trampolines_mapped = mi.cnt;
+out_free:
+	free(mi.maps);
+	return ret;
+}
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/mem-events.c

@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "linux/string.h"
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
+#include "mem-events.h"
+
+
+#define MEM_LOADS_AUX		0x8203
+
+#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a }
+
+struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"mem-loads",	true,	0),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
+};
+
+struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P",	"mem-loads",	true,	MEM_LOADS_AUX),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
+};
+
+struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s//",		NULL,	false,	0),
+};
+
+struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
+};

linux-7.2.3/tools/perf/arch/x86/util/mem-events.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_MEM_EVENTS_H
+#define _X86_MEM_EVENTS_H
+
+extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
+
+extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
+
+#endif /* _X86_MEM_EVENTS_H */

linux-7.2.3/tools/perf/arch/x86/util/pmu.c

@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/perf_event.h>
+#include <api/fs/fs.h>
+#include <api/io_dir.h>
+#include <internal/cpumap.h>
+#include <errno.h>
+
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/pmu.h"
+#include "../../../util/fncache.h"
+#include "../../../util/pmus.h"
+#include "mem-events.h"
+#include "util/debug.h"
+#include "util/env.h"
+#include "util/header.h"
+
+static bool x86__is_intel_graniterapids(void)
+{
+	static bool checked_if_graniterapids;
+	static bool is_graniterapids;
+
+	if (!checked_if_graniterapids) {
+		const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]";
+		char *cpuid = get_cpuid_str((struct perf_cpu){0});
+
+		is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0;
+		free(cpuid);
+		checked_if_graniterapids = true;
+	}
+	return is_graniterapids;
+}
+
+static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path)
+{
+	struct perf_cpu_map *cpus;
+	char *buf = NULL;
+	size_t buf_len;
+
+	if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0)
+		return NULL;
+
+	cpus = perf_cpu_map__new(buf);
+	free(buf);
+	return cpus;
+}
+
+static int snc_nodes_per_l3_cache(void)
+{
+	static bool checked_snc;
+	static int snc_nodes;
+
+	if (!checked_snc) {
+		struct perf_cpu_map *node_cpus =
+			read_sysfs_cpu_map("devices/system/node/node0/cpulist");
+		struct perf_cpu_map *cache_cpus =
+			read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list");
+
+		snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus);
+		perf_cpu_map__put(cache_cpus);
+		perf_cpu_map__put(node_cpus);
+		checked_snc = true;
+	}
+	return snc_nodes;
+}
+
+static int num_chas(void)
+{
+	static bool checked_chas;
+	static int num_chas;
+
+	if (!checked_chas) {
+		int fd = perf_pmu__event_source_devices_fd();
+		struct io_dir dir;
+		struct io_dirent64 *dent;
+
+		if (fd < 0)
+			return -1;
+
+		io_dir__init(&dir, fd);
+
+		while ((dent = io_dir__readdir(&dir)) != NULL) {
+			/* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */
+			if (strstarts(dent->d_name, "uncore_cha_"))
+				num_chas++;
+		}
+		close(fd);
+		checked_chas = true;
+	}
+	return num_chas;
+}
+
+#define MAX_SNCS 6
+
+static int uncore_cha_snc(struct perf_pmu *pmu)
+{
+	// CHA SNC numbers are ordered correspond to the CHAs number.
+	unsigned int cha_num;
+	int num_cha, chas_per_node, cha_snc;
+	int snc_nodes = snc_nodes_per_l3_cache();
+
+	if (snc_nodes <= 1)
+		return 0;
+
+	num_cha = num_chas();
+	if (num_cha <= 0) {
+		pr_warning("Unexpected: no CHAs found\n");
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) {
+		pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name);
+		return 0;
+	}
+	chas_per_node = num_cha / snc_nodes;
+	cha_snc = cha_num / chas_per_node;
+
+	/* Range check cha_snc. for unexpected out of bounds. */
+	return cha_snc >= MAX_SNCS ? 0 : cha_snc;
+}
+
+static int uncore_imc_snc(struct perf_pmu *pmu)
+{
+	// Compute the IMC SNC using lookup tables.
+	unsigned int imc_num;
+	int snc_nodes = snc_nodes_per_l3_cache();
+	const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0};
+	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2};
+	const u8 *snc_map;
+	size_t snc_map_len;
+
+	switch (snc_nodes) {
+	case 2:
+		snc_map = snc2_map;
+		snc_map_len = ARRAY_SIZE(snc2_map);
+		break;
+	case 3:
+		snc_map = snc3_map;
+		snc_map_len = ARRAY_SIZE(snc3_map);
+		break;
+	default:
+		/* Error or no lookup support for SNC with >3 nodes. */
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) {
+		pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name);
+		return 0;
+	}
+	if (imc_num >= snc_map_len) {
+		pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes);
+		return 0;
+	}
+	return snc_map[imc_num];
+}
+
+static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc)
+{
+	static bool checked_cpu_adjust[MAX_SNCS];
+	static int cpu_adjust[MAX_SNCS];
+	struct perf_cpu_map *node_cpus;
+	char node_path[] = "devices/system/node/node0/cpulist";
+
+	/* Was adjust already computed? */
+	if (checked_cpu_adjust[pmu_snc])
+		return cpu_adjust[pmu_snc];
+
+	/* SNC0 doesn't need an adjust. */
+	if (pmu_snc == 0) {
+		cpu_adjust[0] = 0;
+		checked_cpu_adjust[0] = true;
+		return 0;
+	}
+
+	/*
+	 * Use NUMA topology to compute first CPU of the NUMA node, we want to
+	 * adjust CPU 0 to be this and similarly for other CPUs if there is >1
+	 * socket.
+	 */
+	assert(pmu_snc >= 0 && pmu_snc <= 9);
+	node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>.
+	node_cpus = read_sysfs_cpu_map(node_path);
+	cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu;
+	if (cpu_adjust[pmu_snc] < 0) {
+		pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path);
+		cpu_adjust[pmu_snc] = 0;
+	} else {
+		checked_cpu_adjust[pmu_snc] = true;
+	}
+	perf_cpu_map__put(node_cpus);
+	return cpu_adjust[pmu_snc];
+}
+
+static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha)
+{
+	// With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the
+	// topology. For example, a two socket graniterapids machine may be set
+	// up with 3-way SNC meaning there are 6 NUMA nodes that should be
+	// displayed with --per-node. The cpumask of the CHA and IMC PMUs
+	// reflects per-socket information meaning, for example, uncore_cha_60
+	// on a two socket graniterapids machine with 120 cores per socket will
+	// have a cpumask of "0,120". This cpumask needs adjusting to "40,160"
+	// to reflect that uncore_cha_60 is used for the 2nd SNC of each
+	// socket. Without the adjustment events on uncore_cha_60 will appear in
+	// node 0 and node 3 (in our example 2 socket 3-way set up), but with
+	// the adjustment they will appear in node 1 and node 4. The number of
+	// CHAs is typically larger than the number of cores. The CHA numbers
+	// are assumed to split evenly and inorder wrt core numbers. There are
+	// fewer memory IMC PMUs than cores and mapping is handled using lookup
+	// tables.
+	static struct perf_cpu_map *cha_adjusted[MAX_SNCS];
+	static struct perf_cpu_map *imc_adjusted[MAX_SNCS];
+	struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted;
+	unsigned int idx;
+	int pmu_snc, cpu_adjust;
+	struct perf_cpu cpu;
+	bool alloc;
+
+	// Cpus from the kernel holds first CPU of each socket. e.g. 0,120.
+	if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) {
+		pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name);
+		return;
+	}
+
+	pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu);
+	if (pmu_snc == 0) {
+		// No adjustment necessary for the first SNC.
+		return;
+	}
+
+	alloc = adjusted[pmu_snc] == NULL;
+	if (alloc) {
+		// Hold onto the perf_cpu_map globally to avoid recomputation.
+		cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc);
+		adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus));
+		if (!adjusted[pmu_snc])
+			return;
+	}
+
+	perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) {
+		// Compute the new cpu map values or if not allocating, assert
+		// that they match expectations. asserts will be removed to
+		// avoid overhead in NDEBUG builds.
+		if (alloc) {
+			RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust;
+		} else if (idx == 0) {
+			cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu;
+			assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust);
+		} else {
+			assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu ==
+			       cpu.cpu + cpu_adjust);
+		}
+	}
+
+	perf_cpu_map__put(pmu->cpus);
+	pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]);
+}
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	struct perf_pmu_caps *ldlat_cap;
+
+	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
+		pmu->auxtrace = true;
+		pmu->selectable = true;
+		pmu->perf_event_attr_init_default = intel_pt_pmu_default_config;
+	}
+	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) {
+		pmu->auxtrace = true;
+		pmu->selectable = true;
+	}
+
+	if (x86__is_amd_cpu()) {
+		if (strcmp(pmu->name, "ibs_op"))
+			return;
+
+		pmu->mem_events = perf_mem_events_amd;
+
+		if (!perf_pmu__caps_parse(pmu))
+			return;
+
+		ldlat_cap = perf_pmu__get_cap(pmu, "ldlat");
+		if (!ldlat_cap || strcmp(ldlat_cap->value, "1"))
+			return;
+
+		perf_mem_events__loads_ldlat = 0;
+		pmu->mem_events = perf_mem_events_amd_ldlat;
+	} else {
+		if (pmu->is_core) {
+			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+				pmu->mem_events = perf_mem_events_intel_aux;
+			else
+				pmu->mem_events = perf_mem_events_intel;
+		} else if (x86__is_intel_graniterapids()) {
+			if (strstarts(pmu->name, "uncore_cha_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true);
+			else if (strstarts(pmu->name, "uncore_imc_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false);
+		}
+	}
+}

linux-7.2.3/tools/perf/arch/x86/util/topdown.c

@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include "util/evlist.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
+#include "util/topdown.h"
+#include "topdown.h"
+#include "evsel.h"
+
+// cmask=0, inv=0, pc=0, edge=0, umask=4, event=0
+#define TOPDOWN_SLOTS		0x0400
+
+/* Check whether there is a PMU which supports the perf metrics. */
+bool topdown_sys_has_perf_metrics(void)
+{
+	static bool has_perf_metrics;
+	static bool cached;
+	struct perf_pmu *pmu;
+
+	if (cached)
+		return has_perf_metrics;
+
+	/*
+	 * The perf metrics feature is a core PMU feature.
+	 * The PERF_TYPE_RAW type is the type of a core PMU.
+	 * The slots event is only available when the core PMU
+	 * supports the perf metrics feature.
+	 */
+	pmu = perf_pmus__find_by_type(PERF_TYPE_RAW);
+	if (pmu && perf_pmu__have_event(pmu, "slots"))
+		has_perf_metrics = true;
+
+	cached = true;
+	return has_perf_metrics;
+}
+
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	return evsel->core.attr.type == PERF_TYPE_RAW &&
+	       evsel->core.attr.config == TOPDOWN_SLOTS &&
+	       evsel->core.attr.config1 == 0;
+}
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	// cmask=0, inv=0, pc=0, edge=0, umask=0x80-0x87, event=0
+	return evsel->core.attr.type == PERF_TYPE_RAW &&
+		(evsel->core.attr.config & 0xFFFFF8FF) == 0x8000 &&
+		evsel->core.attr.config1 == 0;
+}
+
+/*
+ * Check whether a topdown group supports sample-read.
+ *
+ * Only Topdown metric supports sample-read. The slots
+ * event must be the leader of the topdown group.
+ */
+bool arch_topdown_sample_read(struct evsel *leader)
+{
+	struct evsel *evsel;
+
+	if (!evsel__sys_has_perf_metrics(leader))
+		return false;
+
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel->core.leader != leader->core.leader)
+			continue;
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Make a copy of the topdown metric event metric_event with the given index but
+ * change its configuration to be a topdown slots event. Copying from
+ * metric_event ensures modifiers are the same.
+ */
+int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event)
+{
+	struct evsel *evsel = evsel__new_idx(&metric_event->core.attr, idx);
+
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->core.attr.config = TOPDOWN_SLOTS;
+	evsel->core.cpus = perf_cpu_map__get(metric_event->core.cpus);
+	evsel->core.pmu_cpus = perf_cpu_map__get(metric_event->core.pmu_cpus);
+	evsel->core.is_pmu_core = true;
+	evsel->pmu = metric_event->pmu;
+	evsel->name = strdup("slots");
+	evsel->precise_max = metric_event->precise_max;
+	evsel->sample_read = metric_event->sample_read;
+	evsel->weak_group = metric_event->weak_group;
+	evsel->bpf_counter = metric_event->bpf_counter;
+	evsel->retire_lat = metric_event->retire_lat;
+	evsel__set_leader(evsel, evsel__leader(metric_event));
+	list_add_tail(&evsel->core.node, list);
+	return 0;
+}

linux-7.2.3/tools/perf/arch/x86/util/topdown.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOPDOWN_H
+#define _TOPDOWN_H 1
+
+#include <stdbool.h>
+
+struct evsel;
+struct list_head;
+
+bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
+int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/tsc.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <math.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "../../../util/debug.h"
+#include "../../../util/tsc.h"
+#include "cpuid.h"
+
+u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+/*
+ * Derive the TSC frequency in Hz from the /proc/cpuinfo, for example:
+ * ...
+ * model name      : Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
+ * ...
+ * will return 3000000000.
+ */
+static u64 cpuinfo_tsc_freq(void)
+{
+	u64 result = 0;
+	FILE *cpuinfo;
+	char *line = NULL;
+	size_t len = 0;
+
+	cpuinfo = fopen("/proc/cpuinfo", "r");
+	if (!cpuinfo) {
+		pr_err("Failed to read /proc/cpuinfo for TSC frequency\n");
+		return 0;
+	}
+	while (getline(&line, &len, cpuinfo) > 0) {
+		if (!strncmp(line, "model name", 10)) {
+			char *pos = strstr(line + 11, " @ ");
+			double float_result;
+
+			if (pos && sscanf(pos, " @ %lfGHz", &float_result) == 1) {
+				float_result *= 1000000000;
+				result = (u64)float_result;
+				goto out;
+			}
+		}
+	}
+out:
+	if (result == 0)
+		pr_err("Failed to find TSC frequency in /proc/cpuinfo\n");
+
+	free(line);
+	fclose(cpuinfo);
+	return result;
+}
+
+u64 arch_get_tsc_freq(void)
+{
+	unsigned int a, b, c, d, lvl;
+	static bool cached;
+	static double tsc;
+	char vendor[16];
+
+	if (cached)
+		return tsc;
+
+	cached = true;
+	get_cpuid_0(vendor, &lvl);
+	if (!strstr(vendor, "Intel"))
+		return 0;
+
+	/*
+	 * Don't support Time Stamp Counter and
+	 * Nominal Core Crystal Clock Information Leaf.
+	 */
+	if (lvl < 0x15) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	cpuid(0x15, 0, &a, &b, &c, &d);
+	/* TSC frequency is not enumerated */
+	if (!a || !b || !c) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	tsc = (u64)c * (u64)b / (u64)a;
+	return tsc;
+}