4 files changed, 132 insertions, 97 deletions

diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index 4085419283d0..99a06550e25d 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP	PERF_REG_ARM_PC
 #define PERF_REG_SP	PERF_REG_ARM_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM_R0:
-		return "r0";
-	case PERF_REG_ARM_R1:
-		return "r1";
-	case PERF_REG_ARM_R2:
-		return "r2";
-	case PERF_REG_ARM_R3:
-		return "r3";
-	case PERF_REG_ARM_R4:
-		return "r4";
-	case PERF_REG_ARM_R5:
-		return "r5";
-	case PERF_REG_ARM_R6:
-		return "r6";
-	case PERF_REG_ARM_R7:
-		return "r7";
-	case PERF_REG_ARM_R8:
-		return "r8";
-	case PERF_REG_ARM_R9:
-		return "r9";
-	case PERF_REG_ARM_R10:
-		return "r10";
-	case PERF_REG_ARM_FP:
-		return "fp";
-	case PERF_REG_ARM_IP:
-		return "ip";
-	case PERF_REG_ARM_SP:
-		return "sp";
-	case PERF_REG_ARM_LR:
-		return "lr";
-	case PERF_REG_ARM_PC:
-		return "pc";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
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 <mathieu.poirier@linaro.org>
  */
 
+#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/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 293a23bf8be3..a346d5f3dafa 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -199,13 +199,15 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
 			     struct evsel *evsel, u32 option)
 {
 	int i, err = -EINVAL;
-	struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* Set option of each CPU we have */
-	for (i = 0; i < cpu__max_cpu(); i++) {
-		if (!cpu_map__has(event_cpus, i) ||
-		    !cpu_map__has(online_cpus, i))
+	for (i = 0; i < cpu__max_cpu().cpu; i++) {
+		struct perf_cpu cpu = { .cpu = i, };
+
+		if (!perf_cpu_map__has(event_cpus, cpu) ||
+		    !perf_cpu_map__has(online_cpus, cpu))
 			continue;
 
 		if (option & BIT(ETM_OPT_CTXTID)) {
@@ -297,7 +299,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 				container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
 	struct evsel *evsel, *cs_etm_evsel = NULL;
-	struct perf_cpu_map *cpus = evlist->core.cpus;
+	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	int err = 0;
 
@@ -317,6 +319,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 			}
 			evsel->core.attr.freq = 0;
 			evsel->core.attr.sample_period = 1;
+			evsel->needs_auxtrace_mmap = true;
 			cs_etm_evsel = evsel;
 			opts->full_auxtrace = true;
 		}
@@ -407,25 +410,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 
 	}
 
-	/* Validate auxtrace_mmap_pages provided by user */
-	if (opts->auxtrace_mmap_pages) {
-		unsigned int max_page = (KiB(128) / page_size);
-		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
-
-		if (!privileged &&
-		    opts->auxtrace_mmap_pages > max_page) {
-			opts->auxtrace_mmap_pages = max_page;
-			pr_err("auxtrace too big, truncating to %d\n",
-			       max_page);
-		}
-
-		if (!is_power_of_2(sz)) {
-			pr_err("Invalid mmap size for %s: must be a power of 2\n",
-			       CORESIGHT_ETM_PMU_NAME);
-			return -EINVAL;
-		}
-	}
-
 	if (opts->auxtrace_snapshot_mode)
 		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
 			  opts->auxtrace_snapshot_size);
@@ -454,7 +438,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	if (opts->full_auxtrace) {
 		struct evsel *tracking_evsel;
 
-		err = parse_events(evlist, "dummy:u", NULL);
+		err = parse_event(evlist, "dummy:u");
 		if (err)
 			goto out;
 
@@ -527,6 +511,9 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
 	if (config_opts & BIT(ETM_OPT_CTXTID2))
 		config |= BIT(ETM4_CFG_BIT_VMID) |
 			  BIT(ETM4_CFG_BIT_VMID_OPT);
+	if (config_opts & BIT(ETM_OPT_BRANCH_BROADCAST))
+		config |= BIT(ETM4_CFG_BIT_BB);
+
 	return config;
 }
 
@@ -536,14 +523,16 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 {
 	int i;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
-	struct perf_cpu_map *event_cpus = evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* cpu map is not empty, we have specific CPUs to work with */
 	if (!perf_cpu_map__empty(event_cpus)) {
-		for (i = 0; i < cpu__max_cpu(); i++) {
-			if (!cpu_map__has(event_cpus, i) ||
-			    !cpu_map__has(online_cpus, i))
+		for (i = 0; i < cpu__max_cpu().cpu; i++) {
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (!perf_cpu_map__has(event_cpus, cpu) ||
+			    !perf_cpu_map__has(online_cpus, cpu))
 				continue;
 
 			if (cs_etm_is_ete(itr, i))
@@ -555,8 +544,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		}
 	} else {
 		/* get configuration for all CPUs in the system */
-		for (i = 0; i < cpu__max_cpu(); i++) {
-			if (!cpu_map__has(online_cpus, i))
+		for (i = 0; i < cpu__max_cpu().cpu; i++) {
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (!perf_cpu_map__has(online_cpus, cpu))
 				continue;
 
 			if (cs_etm_is_ete(itr, i))
@@ -723,7 +714,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	u32 offset;
 	u64 nr_cpu, type;
 	struct perf_cpu_map *cpu_map;
-	struct perf_cpu_map *event_cpus = session->evlist->core.cpus;
+	struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus;
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
@@ -741,8 +732,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	} else {
 		/* Make sure all specified CPUs are online */
 		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
-			if (cpu_map__has(event_cpus, i) &&
-			    !cpu_map__has(online_cpus, i))
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (perf_cpu_map__has(event_cpus, cpu) &&
+			    !perf_cpu_map__has(online_cpus, cpu))
 				return -EINVAL;
 		}
 
@@ -762,9 +755,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 
 	offset = CS_ETM_SNAPSHOT + 1;
 
-	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
-		if (cpu_map__has(cpu_map, i))
+	for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) {
+		struct perf_cpu cpu = { .cpu = i, };
+
+		if (perf_cpu_map__has(cpu_map, cpu))
 			cs_etm_get_metadata(i, &offset, itr, info);
+	}
 
 	perf_cpu_map__put(online_cpus);
 
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
 	}