7 files changed, 325 insertions, 34 deletions

diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 5fc6a2a3dbc5..deeb163999ce 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -4,9 +4,11 @@
  * Author: Mathieu Poirier <[email protected]>
  */
 
+#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"
@@ -14,6 +16,7 @@
 #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)
 {
@@ -50,42 +53,114 @@ 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)
+{
+	int i;
+
+	if (!pmus)
+		return NULL;
+
+	for (i = 0; i < pmu_nr; i++) {
+		if (evsel->core.attr.type == pmus[i]->type)
+			return pmus[i];
+	}
+
+	return NULL;
+}
+
 struct auxtrace_record
 *auxtrace_record__init(struct evlist *evlist, int *err)
 {
-	struct perf_pmu	*cs_etm_pmu;
+	struct perf_pmu	*cs_etm_pmu = NULL;
+	struct perf_pmu **arm_spe_pmus = NULL;
+	struct perf_pmu **hisi_ptt_pmus = NULL;
 	struct evsel *evsel;
-	bool found_etm = false;
+	struct perf_pmu *found_etm = NULL;
 	struct perf_pmu *found_spe = NULL;
-	struct perf_pmu **arm_spe_pmus = NULL;
+	struct perf_pmu *found_ptt = NULL;
+	int auxtrace_event_cnt = 0;
 	int nr_spes = 0;
-	int i = 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 &&
-		    evsel->core.attr.type == cs_etm_pmu->type)
-			found_etm = true;
-
-		if (!nr_spes || found_spe)
-			continue;
-
-		for (i = 0; i < nr_spes; i++) {
-			if (evsel->core.attr.type == arm_spe_pmus[i]->type) {
-				found_spe = arm_spe_pmus[i];
-				break;
-			}
-		}
+		if (cs_etm_pmu && !found_etm)
+			found_etm = find_pmu_for_event(&cs_etm_pmu, 1, evsel);
+
+		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_etm && found_spe) {
-		pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n");
+	if (found_spe)
+		auxtrace_event_cnt++;
+
+	if (found_ptt)
+		auxtrace_event_cnt++;
+
+	if (auxtrace_event_cnt > 1) {
+		pr_err("Concurrent AUX trace operation not currently supported\n");
 		*err = -EOPNOTSUPP;
 		return NULL;
 	}
@@ -96,6 +171,9 @@ struct auxtrace_record
 #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
 
 	/*
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index b8b23b9dc598..887c8addc491 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -10,6 +10,7 @@
 #include <linux/string.h>
 
 #include "arm-spe.h"
+#include "hisi-ptt.h"
 #include "../../../util/pmu.h"
 
 struct perf_event_attr
@@ -22,6 +23,8 @@ 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
 	}
 
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 037e292ecd8e..4af0c3a0f86e 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -102,7 +102,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	if (err)
 		goto out_free_arm;
 	/* b, b.cond, br, cbz/cbnz, tbz/tbnz */
-	err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$",
+	err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|hs|le|lo|ls|lt|mi|ne|pl|vc|vs)?n?z?$",
 		      REG_EXTENDED);
 	if (err)
 		goto out_free_call;
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index 9fcb4e68add9..337aa9bdf905 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -11,4 +11,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(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
diff --git a/tools/perf/arch/arm64/util/hisi-ptt.c b/tools/perf/arch/arm64/util/hisi-ptt.c
new file mode 100644
index 000000000000..ba97c8a562a0
--- /dev/null
+++ b/tools/perf/arch/arm64/util/hisi-ptt.c
@@ -0,0 +1,188 @@
+// 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;
+}
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 13933020a79e..af102f471e9f 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -11,6 +11,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/zalloc.h>
+#include <linux/err.h>
 #include <cpuid.h>
 
 #include "../../../util/session.h"
@@ -426,20 +427,14 @@ static int intel_pt_track_switches(struct evlist *evlist)
 	if (!evlist__can_select_event(evlist, sched_switch))
 		return -EPERM;
 
-	err = parse_event(evlist, sched_switch);
-	if (err) {
-		pr_debug2("%s: failed to parse %s, error %d\n",
+	evsel = evlist__add_sched_switch(evlist, true);
+	if (IS_ERR(evsel)) {
+		err = PTR_ERR(evsel);
+		pr_debug2("%s: failed to create %s, error = %d\n",
 			  __func__, sched_switch, err);
 		return err;
 	}
 
-	evsel = evlist__last(evlist);
-
-	evsel__set_sample_bit(evsel, CPU);
-	evsel__set_sample_bit(evsel, TIME);
-
-	evsel->core.system_wide = true;
-	evsel->no_aux_samples = true;
 	evsel->immediate = true;
 
 	return 0;
@@ -871,7 +866,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * User space tasks can migrate between CPUs, so when tracing
 		 * selected CPUs, sideband for all CPUs is still needed.
 		 */
-		need_system_wide_tracking = evlist->core.has_user_cpus &&
+		need_system_wide_tracking = opts->target.cpu_list &&
 					    !intel_pt_evsel->core.attr.exclude_user;
 
 		tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking);
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 5214370ca4e4..f683ac702247 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "util/pmu.h"
+#include "util/env.h"
 #include "map_symbol.h"
 #include "mem-events.h"
+#include "linux/string.h"
 
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
@@ -12,18 +14,43 @@ static char mem_stores_name[100];
 
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
-static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+static struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
 	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
 	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
 	E(NULL,			NULL,				NULL),
 };
 
+static struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL),
+	E(NULL,		NULL,		NULL),
+	E("mem-ldst",	"ibs_op//",	"ibs_op"),
+};
+
+static int perf_mem_is_amd_cpu(void)
+{
+	struct perf_env env = { .total_mem = 0, };
+
+	perf_env__cpuid(&env);
+	if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
+		return 1;
+	return -1;
+}
+
 struct perf_mem_event *perf_mem_events__ptr(int i)
 {
+	/* 0: Uninitialized, 1: Yes, -1: No */
+	static int is_amd;
+
 	if (i >= PERF_MEM_EVENTS__MAX)
 		return NULL;
 
-	return &perf_mem_events[i];
+	if (!is_amd)
+		is_amd = perf_mem_is_amd_cpu();
+
+	if (is_amd == 1)
+		return &perf_mem_events_amd[i];
+
+	return &perf_mem_events_intel[i];
 }
 
 bool is_mem_loads_aux_event(struct evsel *leader)