Merge tag 'perf-tools-for-v6.1-2-2022-10-16' of...

Merge tag 'perf-tools-for-v6.1-2-2022-10-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:

 - Use BPF CO-RE (Compile Once, Run Everywhere) to support old kernels
   when using bperf (perf BPF based counters) with cgroups.

 - Support HiSilicon PCIe Performance Monitoring Unit (PMU), that
   monitors bandwidth, latency, bus utilization and buffer occupancy.

   Documented in Documentation/admin-guide/perf/hisi-pcie-pmu.rst.

 - User space tasks can migrate between CPUs, so when tracing selected
   CPUs, system-wide sideband is still needed, fix it in the setup of
   Intel PT on hybrid systems.

 - Fix metricgroups title message in 'perf list', it should state that
   the metrics groups are to be used with the '-M' option, not '-e'.

 - Sync the msr-index.h copy with the kernel sources, adding support for
   using "AMD64_TSC_RATIO" in filter expressions in 'perf trace' as well
   as decoding it when printing the MSR tracepoint arguments.

 - Fix program header size and alignment when generating a JIT ELF in
   'perf inject'.

 - Add multiple new Intel PT 'perf test' entries, including a jitdump
   one.

 - Fix the 'perf test' entries for 'perf stat' CSV and JSON output when
   running on PowerPC due to an invalid topology number in that arch.

 - Fix the 'perf test' for arm_coresight failures on the ARM Juno
   system.

 - Fix the 'perf test' attr entry for PERF_FORMAT_LOST, adding this
   option to the or expression expected in the intercepted
   perf_event_open() syscall.

 - Add missing condition flags ('hs', 'lo', 'vc', 'vs') for arm64 in the
   'perf annotate' asm parser.

 - Fix 'perf mem record -C' option processing, it was being chopped up
   when preparing the underlying 'perf record -e mem-events' and thus
   being ignored, requiring using '-- -C CPUs' as a workaround.

 - Improvements and tidy ups for 'perf test' shell infra.

 - Fix Intel PT information printing segfault in uClibc, where a NULL
   format was being passed to fprintf.

* tag 'perf-tools-for-v6.1-2-2022-10-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (23 commits)
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf auxtrace arm64: Add support for parsing HiSilicon PCIe Trace packet
  perf auxtrace arm64: Add support for HiSilicon PCIe Tune and Trace device driver
  perf auxtrace arm: Refactor event list iteration in auxtrace_record__init()
  perf tests stat+json_output: Include sanity check for topology
  perf tests stat+csv_output: Include sanity check for topology
  perf intel-pt: Fix system_wide dummy event for hybrid
  perf intel-pt: Fix segfault in intel_pt_print_info() with uClibc
  perf test: Fix attr tests for PERF_FORMAT_LOST
  perf test: test_intel_pt.sh: Add 9 tests
  perf inject: Fix GEN_ELF_TEXT_OFFSET for jit
  perf test: test_intel_pt.sh: Add jitdump test
  perf test: test_intel_pt.sh: Tidy some alignment
  perf test: test_intel_pt.sh: Print a message when skipping kernel tracing
  perf test: test_intel_pt.sh: Tidy some perf record options
  perf test: test_intel_pt.sh: Fix return checking again
  perf: Skip and warn on unknown format 'configN' attrs
  perf list: Fix metricgroups title message
  perf mem: Fix -C option behavior for perf mem record
  perf annotate: Add missing condition flags for arm64
  ...

tools/arch/x86/include/asm/msr-index.h

@@ -155,6 +155,11 @@
 						 * Return Stack Buffer Predictions.
 						 */
 
+#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
+						 * IA32_XAPIC_DISABLE_STATUS MSR
+						 * supported
+						 */
+
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
 						 * Writeback and invalidate the
@@ -585,6 +590,9 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
 
+/* AMD Last Branch Record MSRs */
+#define MSR_AMD64_LBR_SELECT			0xc000010e
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
@@ -756,6 +764,8 @@
 #define MSR_AMD_DBG_EXTN_CFG		0xc000010f
 #define MSR_AMD_SAMP_BR_FROM		0xc0010300
 
+#define DBG_EXTN_CFG_LBRV2EN		BIT_ULL(6)
+
 #define MSR_IA32_MPERF			0x000000e7
 #define MSR_IA32_APERF			0x000000e8
 
@@ -1054,4 +1064,12 @@
 #define MSR_IA32_HW_FEEDBACK_PTR        0x17d0
 #define MSR_IA32_HW_FEEDBACK_CONFIG     0x17d1
 
+/* x2APIC locked status */
+#define MSR_IA32_XAPIC_DISABLE_STATUS	0xBD
+#define LEGACY_XAPIC_DISABLED		BIT(0) /*
+						* x2APIC mode is locked and
+						* disabling x2APIC will cause
+						* a #GP
+						*/
+
 #endif /* _ASM_X86_MSR_INDEX_H */

tools/lib/perf/include/perf/event.h

@@ -6,7 +6,6 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/bpf.h>
-#include <linux/compiler.h>
 #include <sys/types.h> /* pid_t */
 
 #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
@@ -207,7 +206,7 @@ struct perf_record_range_cpu_map {
 	__u16 end_cpu;
 };
 
-struct __packed perf_record_cpu_map_data {
+struct perf_record_cpu_map_data {
 	__u16			 type;
 	union {
 		/* Used when type == PERF_CPU_MAP__CPUS. */
@@ -219,7 +218,7 @@ struct __packed perf_record_cpu_map_data {
 		/* Used when type == PERF_CPU_MAP__RANGE_CPUS. */
 		struct perf_record_range_cpu_map range_cpu_data;
 	};
-};
+} __attribute__((packed));
 
 #pragma GCC diagnostic pop
 

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 (cs_etm_pmu && !found_etm)
+			found_etm = find_pmu_for_event(&cs_etm_pmu, 1, evsel);
 
-		if (!nr_spes || found_spe)
-			continue;
+		if (arm_spe_pmus && !found_spe)
+			found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel);
 
-		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 (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
 
 	/*

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
 	}
 

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;

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

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/arch/x86/util/intel-pt.c

@@ -866,7 +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);

tools/perf/builtin-list.c

@@ -60,7 +60,7 @@ int cmd_list(int argc, const char **argv)
 	setup_pager();
 
 	if (!raw_dump && pager_in_use())
-		printf("\nList of pre-defined events (to be used in -e):\n\n");
+		printf("\nList of pre-defined events (to be used in -e or -M):\n\n");
 
 	if (hybrid_type) {
 		pmu_name = perf_pmu__hybrid_type_to_pmu(hybrid_type);

tools/perf/builtin-mem.c

@@ -97,6 +97,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	else
 		rec_argc = argc + 9 * perf_pmu__hybrid_pmu_num();
 
+	if (mem->cpu_list)
+		rec_argc += 2;
+
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
@@ -159,6 +162,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (all_kernel)
 		rec_argv[i++] = "--all-kernel";
 
+	if (mem->cpu_list) {
+		rec_argv[i++] = "-C";
+		rec_argv[i++] = mem->cpu_list;
+	}
+
 	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 

tools/perf/tests/attr/base-record

@@ -9,7 +9,7 @@ size=128
 config=0
 sample_period=*
 sample_type=263
-read_format=0|4
+read_format=0|4|20
 disabled=1
 inherit=1
 pinned=0

tools/perf/tests/attr/system-wide-dummy

@@ -11,7 +11,7 @@ size=128
 config=9
 sample_period=4000
 sample_type=455
-read_format=4
+read_format=4|20
 # Event will be enabled right away.
 disabled=0
 inherit=1

tools/perf/tests/attr/test-record-group

@@ -7,14 +7,14 @@ ret     = 1
 fd=1
 group_fd=-1
 sample_type=327
-read_format=4
+read_format=4|20
 
 [event-2:base-record]
 fd=2
 group_fd=1
 config=1
 sample_type=327
-read_format=4
+read_format=4|20
 mmap=0
 comm=0
 task=0

tools/perf/tests/attr/test-record-group-sampling

@@ -7,7 +7,7 @@ ret     = 1
 fd=1
 group_fd=-1
 sample_type=343
-read_format=12
+read_format=12|28
 inherit=0
 
 [event-2:base-record]
@@ -21,8 +21,8 @@ config=3
 # default | PERF_SAMPLE_READ
 sample_type=343
 
-# PERF_FORMAT_ID | PERF_FORMAT_GROUP
-read_format=12
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP  | PERF_FORMAT_LOST
+read_format=12|28
 task=0
 mmap=0
 comm=0

tools/perf/tests/attr/test-record-group1

@@ -7,7 +7,7 @@ ret     = 1
 fd=1
 group_fd=-1
 sample_type=327
-read_format=4
+read_format=4|20
 
 [event-2:base-record]
 fd=2
@@ -15,7 +15,7 @@ group_fd=1
 type=0
 config=1
 sample_type=327
-read_format=4
+read_format=4|20
 mmap=0
 comm=0
 task=0

tools/perf/tests/attr/test-record-group2

@@ -9,7 +9,7 @@ group_fd=-1
 config=0|1
 sample_period=1234000
 sample_type=87
-read_format=12
+read_format=12|28
 inherit=0
 freq=0
 
@@ -19,7 +19,7 @@ group_fd=1
 config=0|1
 sample_period=6789000
 sample_type=87
-read_format=12
+read_format=12|28
 disabled=0
 inherit=0
 mmap=0

tools/perf/tests/shell/stat+csv_output.sh

@@ -6,6 +6,8 @@
 
 set -e
 
+skip_test=0
+
 function commachecker()
 {
 	local -i cnt=0
@@ -156,14 +158,47 @@ check_per_socket()
 	echo "[Success]"
 }
 
+# The perf stat options for per-socket, per-core, per-die
+# and -A ( no_aggr mode ) uses the info fetched from this
+# directory: "/sys/devices/system/cpu/cpu*/topology". For
+# example, socket value is fetched from "physical_package_id"
+# file in topology directory.
+# Reference: cpu__get_topology_int in util/cpumap.c
+# If the platform doesn't expose topology information, values
+# will be set to -1. For example, incase of pSeries platform
+# of powerpc, value for  "physical_package_id" is restricted
+# and set to -1. Check here validates the socket-id read from
+# topology file before proceeding further
+
+FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
+FILE_NAME="physical_package_id"
+
+check_for_topology()
+{
+	if ! ParanoidAndNotRoot 0
+	then
+		socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
+		[ -z $socket_file ] && return 0
+		socket_id=`cat $socket_file`
+		[ $socket_id == -1 ] && skip_test=1
+		return 0
+	fi
+}
+
+check_for_topology
 check_no_args
 check_system_wide
-check_system_wide_no_aggr
 check_interval
 check_event
-check_per_core
 check_per_thread
-check_per_die
 check_per_node
-check_per_socket
+if [ $skip_test -ne 1 ]
+then
+	check_system_wide_no_aggr
+	check_per_core
+	check_per_die
+	check_per_socket
+else
+	echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
+fi
 exit 0

tools/perf/tests/shell/stat+json_output.sh

@@ -6,6 +6,8 @@
 
 set -e
 
+skip_test=0
+
 pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
 if [ "x$PYTHON" == "x" ]
 then
@@ -134,14 +136,47 @@ check_per_socket()
 	echo "[Success]"
 }
 
+# The perf stat options for per-socket, per-core, per-die
+# and -A ( no_aggr mode ) uses the info fetched from this
+# directory: "/sys/devices/system/cpu/cpu*/topology". For
+# example, socket value is fetched from "physical_package_id"
+# file in topology directory.
+# Reference: cpu__get_topology_int in util/cpumap.c
+# If the platform doesn't expose topology information, values
+# will be set to -1. For example, incase of pSeries platform
+# of powerpc, value for  "physical_package_id" is restricted
+# and set to -1. Check here validates the socket-id read from
+# topology file before proceeding further
+
+FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
+FILE_NAME="physical_package_id"
+
+check_for_topology()
+{
+	if ! ParanoidAndNotRoot 0
+	then
+		socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
+		[ -z $socket_file ] && return 0
+		socket_id=`cat $socket_file`
+		[ $socket_id == -1 ] && skip_test=1
+		return 0
+	fi
+}
+
+check_for_topology
 check_no_args
 check_system_wide
-check_system_wide_no_aggr
 check_interval
 check_event
-check_per_core
 check_per_thread
-check_per_die
 check_per_node
-check_per_socket
+if [ $skip_test -ne 1 ]
+then
+	check_system_wide_no_aggr
+	check_per_core
+	check_per_die
+	check_per_socket
+else
+	echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
+fi
 exit 0

tools/perf/tests/shell/test_arm_coresight.sh

@@ -70,7 +70,7 @@ perf_report_instruction_samples() {
 	#   68.12%  touch    libc-2.27.so   [.] _dl_addr
 	#    5.80%  touch    libc-2.27.so   [.] getenv
 	#    4.35%  touch    ld-2.27.so     [.] _dl_fixup
-	perf report --itrace=i1000i --stdio -i ${perfdata} 2>&1 | \
+	perf report --itrace=i20i --stdio -i ${perfdata} 2>&1 | \
 		egrep " +[0-9]+\.[0-9]+% +$1" > /dev/null 2>&1
 }
 

tools/perf/tests/shell/test_intel_pt.sh

@@ -22,6 +22,8 @@ outfile="${temp_dir}/test-out.txt"
 errfile="${temp_dir}/test-err.txt"
 workload="${temp_dir}/workload"
 awkscript="${temp_dir}/awkscript"
+jitdump_workload="${temp_dir}/jitdump_workload"
+maxbrstack="${temp_dir}/maxbrstack.py"
 
 cleanup()
 {
@@ -42,6 +44,21 @@ trap_cleanup()
 
 trap trap_cleanup EXIT TERM INT
 
+# perf record for testing without decoding
+perf_record_no_decode()
+{
+	# Options to speed up recording: no post-processing, no build-id cache update,
+	# and no BPF events.
+	perf record -B -N --no-bpf-event "$@"
+}
+
+# perf record for testing should not need BPF events
+perf_record_no_bpf()
+{
+	# Options for no BPF events
+	perf record --no-bpf-event "$@"
+}
+
 have_workload=false
 cat << _end_of_file_ | /usr/bin/cc -o "${workload}" -xc - -pthread && have_workload=true
 #include <time.h>
@@ -76,7 +93,7 @@ _end_of_file_
 can_cpu_wide()
 {
 	echo "Checking for CPU-wide recording on CPU $1"
-	if ! perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:u -C "$1" true >/dev/null 2>&1 ; then
+	if ! perf_record_no_decode -o "${tmpfile}" -e dummy:u -C "$1" true >/dev/null 2>&1 ; then
 		echo "No so skipping"
 		return 2
 	fi
@@ -93,7 +110,7 @@ test_system_wide_side_band()
 	can_cpu_wide 1 || return $?
 
 	# Record on CPU 0 a task running on CPU 1
-	perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname
 
 	# Should get MMAP events from CPU 1 because they can be needed to decode
 	mmap_cnt=$(perf script -i "${perfdatafile}" --no-itrace --show-mmap-events -C 1 2>/dev/null | grep -c MMAP)
@@ -109,7 +126,14 @@ test_system_wide_side_band()
 
 can_kernel()
 {
-	perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:k true >/dev/null 2>&1 || return 2
+	if [ -z "${can_kernel_trace}" ] ; then
+		can_kernel_trace=0
+		perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 && can_kernel_trace=1
+	fi
+	if [ ${can_kernel_trace} -eq 0 ] ; then
+		echo "SKIP: no kernel tracing"
+		return 2
+	fi
 	return 0
 }
 
@@ -235,7 +259,7 @@ test_per_thread()
 	wait_for_threads ${w1} 2
 	wait_for_threads ${w2} 2
 
-	perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" &
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" &
 	ppid=$!
 	echo "perf PID is $ppid"
 	wait_for_perf_to_start ${ppid} "${errfile}" || return 1
@@ -254,6 +278,342 @@ test_per_thread()
 	return 0
 }
 
+test_jitdump()
+{
+	echo "--- Test tracing self-modifying code that uses jitdump ---"
+
+	script_path=$(realpath "$0")
+	script_dir=$(dirname "$script_path")
+	jitdump_incl_dir="${script_dir}/../../util"
+	jitdump_h="${jitdump_incl_dir}/jitdump.h"
+
+	if [ ! -e "${jitdump_h}" ] ; then
+		echo "SKIP: Include file jitdump.h not found"
+		return 2
+	fi
+
+	if [ -z "${have_jitdump_workload}" ] ; then
+		have_jitdump_workload=false
+		# Create a workload that uses self-modifying code and generates its own jitdump file
+		cat <<- "_end_of_file_" | /usr/bin/cc -o "${jitdump_workload}" -I "${jitdump_incl_dir}" -xc - -pthread && have_jitdump_workload=true
+		#define _GNU_SOURCE
+		#include <sys/mman.h>
+		#include <sys/types.h>
+		#include <stddef.h>
+		#include <stdio.h>
+		#include <stdint.h>
+		#include <unistd.h>
+		#include <string.h>
+
+		#include "jitdump.h"
+
+		#define CHK_BYTE 0x5a
+
+		static inline uint64_t rdtsc(void)
+		{
+			unsigned int low, high;
+
+			asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+			return low | ((uint64_t)high) << 32;
+		}
+
+		static FILE *open_jitdump(void)
+		{
+			struct jitheader header = {
+				.magic      = JITHEADER_MAGIC,
+				.version    = JITHEADER_VERSION,
+				.total_size = sizeof(header),
+				.pid        = getpid(),
+				.timestamp  = rdtsc(),
+				.flags      = JITDUMP_FLAGS_ARCH_TIMESTAMP,
+			};
+			char filename[256];
+			FILE *f;
+			void *m;
+
+			snprintf(filename, sizeof(filename), "jit-%d.dump", getpid());
+			f = fopen(filename, "w+");
+			if (!f)
+				goto err;
+			/* Create an MMAP event for the jitdump file. That is how perf tool finds it. */
+			m = mmap(0, 4096, PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(f), 0);
+			if (m == MAP_FAILED)
+				goto err_close;
+			munmap(m, 4096);
+			if (fwrite(&header,sizeof(header),1,f) != 1)
+				goto err_close;
+			return f;
+
+		err_close:
+			fclose(f);
+		err:
+			return NULL;
+		}
+
+		static int write_jitdump(FILE *f, void *addr, const uint8_t *dat, size_t sz, uint64_t *idx)
+		{
+			struct jr_code_load rec = {
+				.p.id          = JIT_CODE_LOAD,
+				.p.total_size  = sizeof(rec) + sz,
+				.p.timestamp   = rdtsc(),
+				.pid	       = getpid(),
+				.tid	       = gettid(),
+				.vma           = (unsigned long)addr,
+				.code_addr     = (unsigned long)addr,
+				.code_size     = sz,
+				.code_index    = ++*idx,
+			};
+
+			if (fwrite(&rec,sizeof(rec),1,f) != 1 ||
+			fwrite(dat, sz, 1, f) != 1)
+				return -1;
+			return 0;
+		}
+
+		static void close_jitdump(FILE *f)
+		{
+			fclose(f);
+		}
+
+		int main()
+		{
+			/* Get a memory page to store executable code */
+			void *addr = mmap(0, 4096, PROT_WRITE | PROT_EXEC, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+			/* Code to execute: mov CHK_BYTE, %eax ; ret */
+			uint8_t dat[] = {0xb8, CHK_BYTE, 0x00, 0x00, 0x00, 0xc3};
+			FILE *f = open_jitdump();
+			uint64_t idx = 0;
+			int ret = 1;
+
+			if (!f)
+				return 1;
+			/* Copy executable code to executable memory page */
+			memcpy(addr, dat, sizeof(dat));
+			/* Record it in the jitdump file */
+			if (write_jitdump(f, addr, dat, sizeof(dat), &idx))
+				goto out_close;
+			/* Call it */
+			ret = ((int (*)(void))addr)() - CHK_BYTE;
+		out_close:
+			close_jitdump(f);
+			return ret;
+		}
+		_end_of_file_
+	fi
+
+	if ! $have_jitdump_workload ; then
+		echo "SKIP: No jitdump workload"
+		return 2
+	fi
+
+	# Change to temp_dir so jitdump collateral files go there
+	cd "${temp_dir}"
+	perf_record_no_bpf -o "${tmpfile}" -e intel_pt//u "${jitdump_workload}"
+	perf inject -i "${tmpfile}" -o "${perfdatafile}" --jit
+	decode_br_cnt=$(perf script -i "${perfdatafile}" --itrace=b | wc -l)
+	# Note that overflow and lost errors are suppressed for the error count
+	decode_err_cnt=$(perf script -i "${perfdatafile}" --itrace=e-o-l | grep -ci error)
+	cd -
+	# Should be thousands of branches
+	if [ "${decode_br_cnt}" -lt 1000 ] ; then
+		echo "Decode failed, only ${decode_br_cnt} branches"
+		return 1
+	fi
+	# Should be no errors
+	if [ "${decode_err_cnt}" -ne 0 ] ; then
+		echo "Decode failed, ${decode_err_cnt} errors"
+		perf script -i "${perfdatafile}" --itrace=e-o-l --show-mmap-events | cat
+		return 1
+	fi
+
+	echo OK
+	return 0
+}
+
+test_packet_filter()
+{
+	echo "--- Test with MTC and TSC disabled ---"
+	# Disable MTC and TSC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/mtc=0,tsc=0/u uname
+	# Should not get MTC packet
+	mtc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "MTC 0x")
+	if [ "${mtc_cnt}" -ne 0 ] ; then
+		echo "Failed to filter with mtc=0"
+		return 1
+	fi
+	# Should not get TSC package
+	tsc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TSC 0x")
+	if [ "${tsc_cnt}" -ne 0 ] ; then
+		echo "Failed to filter with tsc=0"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_disable_branch()
+{
+	echo "--- Test with branches disabled ---"
+	# Disable branch
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/branch=0/u uname
+	# Should not get branch related packets
+	tnt_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TNT 0x")
+	tip_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TIP 0x")
+	fup_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "FUP 0x")
+	if [ "${tnt_cnt}" -ne 0 ] || [ "${tip_cnt}" -ne 0 ] || [ "${fup_cnt}" -ne 0 ] ; then
+		echo "Failed to disable branches"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_time_cyc()
+{
+	echo "--- Test with/without CYC ---"
+	# Check if CYC is supported
+	cyc=$(cat /sys/bus/event_source/devices/intel_pt/caps/psb_cyc)
+	if [ "${cyc}" != "1" ] ; then
+		echo "SKIP: CYC is not supported"
+		return 2
+	fi
+	# Enable CYC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/cyc/u uname
+	# should get CYC packets
+	cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x")
+	if [ "${cyc_cnt}" = "0" ] ; then
+		echo "Failed to get CYC packet"
+		return 1
+	fi
+	# Without CYC
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u uname
+	# Should not get CYC packets
+	cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x")
+	if [ "${cyc_cnt}" -gt 0 ] ; then
+		echo "Still get CYC packet without cyc"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_sample()
+{
+	echo "--- Test recording with sample mode ---"
+	# Check if recording with sample mode is working
+	if ! perf_record_no_decode -o "${perfdatafile}" --aux-sample=8192 -e '{intel_pt//u,branch-misses:u}' uname ; then
+		echo "perf record failed with --aux-sample"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_kernel_trace()
+{
+	echo "--- Test with kernel trace ---"
+	# Check if recording with kernel trace is working
+	can_kernel || return 2
+	if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt//k -m1,128 uname ; then
+		echo "perf record failed with intel_pt//k"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_virtual_lbr()
+{
+	echo "--- Test virtual LBR ---"
+
+	# Python script to determine the maximum size of branch stacks
+	cat << "_end_of_file_" > "${maxbrstack}"
+from __future__ import print_function
+
+bmax = 0
+
+def process_event(param_dict):
+	if "brstack" in param_dict:
+		brstack = param_dict["brstack"]
+		n = len(brstack)
+		global bmax
+		if n > bmax:
+			bmax = n
+
+def trace_end():
+	print("max brstack", bmax)
+_end_of_file_
+
+	# Check if virtual lbr is working
+	perf_record_no_bpf -o "${perfdatafile}" --aux-sample -e '{intel_pt//,cycles}:u' uname
+	times_val=$(perf script -i "${perfdatafile}" --itrace=L -s "${maxbrstack}" 2>/dev/null | grep "max brstack " | cut -d " " -f 3)
+	case "${times_val}" in
+		[0-9]*)	;;
+		*)	times_val=0;;
+	esac
+	if [ "${times_val}" -lt 2 ] ; then
+		echo "Failed with virtual lbr"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_power_event()
+{
+	echo "--- Test power events ---"
+	# Check if power events are supported
+	power_event=$(cat /sys/bus/event_source/devices/intel_pt/caps/power_event_trace)
+	if [ "${power_event}" != "1" ] ; then
+		echo "SKIP: power_event_trace is not supported"
+		return 2
+	fi
+	if ! perf_record_no_decode -o "${perfdatafile}" -a -e intel_pt/pwr_evt/u uname ; then
+		echo "perf record failed with pwr_evt"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_no_tnt()
+{
+	echo "--- Test with TNT packets disabled  ---"
+	# Check if TNT disable is supported
+	notnt=$(cat /sys/bus/event_source/devices/intel_pt/caps/tnt_disable)
+	if [ "${notnt}" != "1" ] ; then
+		echo "SKIP: tnt_disable is not supported"
+		return 2
+	fi
+	perf_record_no_decode -o "${perfdatafile}" -e intel_pt/notnt/u uname
+	# Should be no TNT packets
+	tnt_cnt=$(perf script -i "${perfdatafile}" -D | grep -c TNT)
+	if [ "${tnt_cnt}" -ne 0 ] ; then
+		echo "TNT packets still there after notnt"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
+test_event_trace()
+{
+	echo "--- Test with event_trace ---"
+	# Check if event_trace is supported
+	event_trace=$(cat /sys/bus/event_source/devices/intel_pt/caps/event_trace)
+	if [ "${event_trace}" != 1 ] ; then
+		echo "SKIP: event_trace is not supported"
+		return 2
+	fi
+	if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/event/u uname ; then
+		echo "perf record failed with event trace"
+		return 1
+	fi
+	echo OK
+	return 0
+}
+
 count_result()
 {
 	if [ "$1" -eq 2 ] ; then
@@ -265,13 +625,22 @@ count_result()
 		return
 	fi
 	err_cnt=$((err_cnt + 1))
-	ret=0
 }
 
 ret=0
-test_system_wide_side_band || ret=$? ; count_result $ret
-test_per_thread "" "" || ret=$? ; count_result $ret
-test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret
+test_system_wide_side_band		|| ret=$? ; count_result $ret ; ret=0
+test_per_thread "" ""			|| ret=$? ; count_result $ret ; ret=0
+test_per_thread "k" "(incl. kernel) "	|| ret=$? ; count_result $ret ; ret=0
+test_jitdump				|| ret=$? ; count_result $ret ; ret=0
+test_packet_filter			|| ret=$? ; count_result $ret ; ret=0
+test_disable_branch			|| ret=$? ; count_result $ret ; ret=0
+test_time_cyc				|| ret=$? ; count_result $ret ; ret=0
+test_sample				|| ret=$? ; count_result $ret ; ret=0
+test_kernel_trace			|| ret=$? ; count_result $ret ; ret=0
+test_virtual_lbr			|| ret=$? ; count_result $ret ; ret=0
+test_power_event			|| ret=$? ; count_result $ret ; ret=0
+test_no_tnt				|| ret=$? ; count_result $ret ; ret=0
+test_event_trace			|| ret=$? ; count_result $ret ; ret=0
 
 cleanup
 

tools/perf/util/Build

@@ -118,6 +118,8 @@ perf-$(CONFIG_AUXTRACE) += intel-pt.o
 perf-$(CONFIG_AUXTRACE) += intel-bts.o
 perf-$(CONFIG_AUXTRACE) += arm-spe.o
 perf-$(CONFIG_AUXTRACE) += arm-spe-decoder/
+perf-$(CONFIG_AUXTRACE) += hisi-ptt.o
+perf-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/
 perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
 
 ifdef CONFIG_LIBOPENCSD

tools/perf/util/auxtrace.c

@@ -52,6 +52,7 @@
 #include "intel-pt.h"
 #include "intel-bts.h"
 #include "arm-spe.h"
+#include "hisi-ptt.h"
 #include "s390-cpumsf.h"
 #include "util/mmap.h"
 
@@ -1320,6 +1321,9 @@ int perf_event__process_auxtrace_info(struct perf_session *session,
 	case PERF_AUXTRACE_S390_CPUMSF:
 		err = s390_cpumsf_process_auxtrace_info(event, session);
 		break;
+	case PERF_AUXTRACE_HISI_PTT:
+		err = hisi_ptt_process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

tools/perf/util/auxtrace.h

@@ -48,6 +48,7 @@ enum auxtrace_type {
 	PERF_AUXTRACE_CS_ETM,
 	PERF_AUXTRACE_ARM_SPE,
 	PERF_AUXTRACE_S390_CPUMSF,
+	PERF_AUXTRACE_HISI_PTT,
 };
 
 enum itrace_period_type {

tools/perf/util/bpf_skel/bperf_cgroup.bpf.c

@@ -43,6 +43,18 @@ struct {
 	__uint(value_size, sizeof(struct bpf_perf_event_value));
 } cgrp_readings SEC(".maps");
 
+/* new kernel cgroup definition */
+struct cgroup___new {
+	int level;
+	struct cgroup *ancestors[];
+} __attribute__((preserve_access_index));
+
+/* old kernel cgroup definition */
+struct cgroup___old {
+	int level;
+	u64 ancestor_ids[];
+} __attribute__((preserve_access_index));
+
 const volatile __u32 num_events = 1;
 const volatile __u32 num_cpus = 1;
 
@@ -50,6 +62,21 @@ int enabled = 0;
 int use_cgroup_v2 = 0;
 int perf_subsys_id = -1;
 
+static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level)
+{
+	/* recast pointer to capture new type for compiler */
+	struct cgroup___new *cgrp_new = (void *)cgrp;
+
+	if (bpf_core_field_exists(cgrp_new->ancestors)) {
+		return BPF_CORE_READ(cgrp_new, ancestors[level], kn, id);
+	} else {
+		/* recast pointer to capture old type for compiler */
+		struct cgroup___old *cgrp_old = (void *)cgrp;
+
+		return BPF_CORE_READ(cgrp_old, ancestor_ids[level]);
+	}
+}
+
 static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 {
 	struct task_struct *p = (void *)bpf_get_current_task();
@@ -77,7 +104,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 			break;
 
 		// convert cgroup-id to a map index
-		cgrp_id = BPF_CORE_READ(cgrp, ancestors[i], kn, id);
+		cgrp_id = get_cgroup_v1_ancestor_id(cgrp, i);
 		elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id);
 		if (!elem)
 			continue;

tools/perf/util/genelf.h

@@ -2,6 +2,8 @@
 #ifndef __GENELF_H__
 #define __GENELF_H__
 
+#include <linux/math.h>
+
 /* genelf.c */
 int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
 		  const void *code, int csize, void *debug, int nr_debug_entries,
@@ -76,6 +78,6 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #endif
 
 /* The .text section is directly after the ELF header */
-#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr)
+#define GEN_ELF_TEXT_OFFSET round_up(sizeof(Elf_Ehdr) + sizeof(Elf_Phdr), 16)
 
 #endif

tools/perf/util/hisi-ptt-decoder/Build

+perf-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o

tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+#include <linux/bitops.h>
+#include <stdarg.h>
+
+#include "../color.h"
+#include "hisi-ptt-pkt-decoder.h"
+
+/*
+ * For 8DW format, the bit[31:11] of DW0 is always 0x1fffff, which can be
+ * used to distinguish the data format.
+ * 8DW format is like:
+ *   bits [                 31:11                 ][       10:0       ]
+ *        |---------------------------------------|-------------------|
+ *    DW0 [                0x1fffff               ][ Reserved (0x7ff) ]
+ *    DW1 [                       Prefix                              ]
+ *    DW2 [                     Header DW0                            ]
+ *    DW3 [                     Header DW1                            ]
+ *    DW4 [                     Header DW2                            ]
+ *    DW5 [                     Header DW3                            ]
+ *    DW6 [                   Reserved (0x0)                          ]
+ *    DW7 [                        Time                               ]
+ *
+ * 4DW format is like:
+ *   bits [31:30] [ 29:25 ][24][23][22][21][    20:11   ][    10:0    ]
+ *        |-----|---------|---|---|---|---|-------------|-------------|
+ *    DW0 [ Fmt ][  Type  ][T9][T8][TH][SO][   Length   ][    Time    ]
+ *    DW1 [                     Header DW1                            ]
+ *    DW2 [                     Header DW2                            ]
+ *    DW3 [                     Header DW3                            ]
+ */
+
+enum hisi_ptt_8dw_pkt_field_type {
+	HISI_PTT_8DW_CHK_AND_RSV0,
+	HISI_PTT_8DW_PREFIX,
+	HISI_PTT_8DW_HEAD0,
+	HISI_PTT_8DW_HEAD1,
+	HISI_PTT_8DW_HEAD2,
+	HISI_PTT_8DW_HEAD3,
+	HISI_PTT_8DW_RSV1,
+	HISI_PTT_8DW_TIME,
+	HISI_PTT_8DW_TYPE_MAX
+};
+
+enum hisi_ptt_4dw_pkt_field_type {
+	HISI_PTT_4DW_HEAD1,
+	HISI_PTT_4DW_HEAD2,
+	HISI_PTT_4DW_HEAD3,
+	HISI_PTT_4DW_TYPE_MAX
+};
+
+static const char * const hisi_ptt_8dw_pkt_field_name[] = {
+	[HISI_PTT_8DW_PREFIX]	= "Prefix",
+	[HISI_PTT_8DW_HEAD0]	= "Header DW0",
+	[HISI_PTT_8DW_HEAD1]	= "Header DW1",
+	[HISI_PTT_8DW_HEAD2]	= "Header DW2",
+	[HISI_PTT_8DW_HEAD3]	= "Header DW3",
+	[HISI_PTT_8DW_TIME]	= "Time"
+};
+
+static const char * const hisi_ptt_4dw_pkt_field_name[] = {
+	[HISI_PTT_4DW_HEAD1]	= "Header DW1",
+	[HISI_PTT_4DW_HEAD2]	= "Header DW2",
+	[HISI_PTT_4DW_HEAD3]	= "Header DW3",
+};
+
+union hisi_ptt_4dw {
+	struct {
+		uint32_t format : 2;
+		uint32_t type : 5;
+		uint32_t t9 : 1;
+		uint32_t t8 : 1;
+		uint32_t th : 1;
+		uint32_t so : 1;
+		uint32_t len : 10;
+		uint32_t time : 11;
+	};
+	uint32_t value;
+};
+
+static void hisi_ptt_print_pkt(const unsigned char *buf, int pos, const char *desc)
+{
+	const char *color = PERF_COLOR_BLUE;
+	int i;
+
+	printf(".");
+	color_fprintf(stdout, color, "  %08x: ", pos);
+	for (i = 0; i < HISI_PTT_FIELD_LENTH; i++)
+		color_fprintf(stdout, color, "%02x ", buf[pos + i]);
+	for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++)
+		color_fprintf(stdout, color, "   ");
+	color_fprintf(stdout, color, "  %s\n", desc);
+}
+
+static int hisi_ptt_8dw_kpt_desc(const unsigned char *buf, int pos)
+{
+	int i;
+
+	for (i = 0; i < HISI_PTT_8DW_TYPE_MAX; i++) {
+		/* Do not show 8DW check field and reserved fields */
+		if (i == HISI_PTT_8DW_CHK_AND_RSV0 || i == HISI_PTT_8DW_RSV1) {
+			pos += HISI_PTT_FIELD_LENTH;
+			continue;
+		}
+
+		hisi_ptt_print_pkt(buf, pos, hisi_ptt_8dw_pkt_field_name[i]);
+		pos += HISI_PTT_FIELD_LENTH;
+	}
+
+	return hisi_ptt_pkt_size[HISI_PTT_8DW_PKT];
+}
+
+static void hisi_ptt_4dw_print_dw0(const unsigned char *buf, int pos)
+{
+	const char *color = PERF_COLOR_BLUE;
+	union hisi_ptt_4dw dw0;
+	int i;
+
+	dw0.value = *(uint32_t *)(buf + pos);
+	printf(".");
+	color_fprintf(stdout, color, "  %08x: ", pos);
+	for (i = 0; i < HISI_PTT_FIELD_LENTH; i++)
+		color_fprintf(stdout, color, "%02x ", buf[pos + i]);
+	for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++)
+		color_fprintf(stdout, color, "   ");
+
+	color_fprintf(stdout, color,
+		      "  %s %x %s %x %s %x %s %x %s %x %s %x %s %x %s %x\n",
+		      "Format", dw0.format, "Type", dw0.type, "T9", dw0.t9,
+		      "T8", dw0.t8, "TH", dw0.th, "SO", dw0.so, "Length",
+		      dw0.len, "Time", dw0.time);
+}
+
+static int hisi_ptt_4dw_kpt_desc(const unsigned char *buf, int pos)
+{
+	int i;
+
+	hisi_ptt_4dw_print_dw0(buf, pos);
+	pos += HISI_PTT_FIELD_LENTH;
+
+	for (i = 0; i < HISI_PTT_4DW_TYPE_MAX; i++) {
+		hisi_ptt_print_pkt(buf, pos, hisi_ptt_4dw_pkt_field_name[i]);
+		pos += HISI_PTT_FIELD_LENTH;
+	}
+
+	return hisi_ptt_pkt_size[HISI_PTT_4DW_PKT];
+}
+
+int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type)
+{
+	if (type == HISI_PTT_8DW_PKT)
+		return hisi_ptt_8dw_kpt_desc(buf, pos);
+
+	return hisi_ptt_4dw_kpt_desc(buf, pos);
+}

tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#ifndef INCLUDE__HISI_PTT_PKT_DECODER_H__
+#define INCLUDE__HISI_PTT_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define HISI_PTT_8DW_CHECK_MASK		GENMASK(31, 11)
+#define HISI_PTT_IS_8DW_PKT		GENMASK(31, 11)
+#define HISI_PTT_MAX_SPACE_LEN		10
+#define HISI_PTT_FIELD_LENTH		4
+
+enum hisi_ptt_pkt_type {
+	HISI_PTT_4DW_PKT,
+	HISI_PTT_8DW_PKT,
+	HISI_PTT_PKT_MAX
+};
+
+static int hisi_ptt_pkt_size[] = {
+	[HISI_PTT_4DW_PKT]	= 16,
+	[HISI_PTT_8DW_PKT]	= 32,
+};
+
+int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type);
+
+#endif

tools/perf/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 <byteswap.h>
+#include <endian.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "auxtrace.h"
+#include "color.h"
+#include "debug.h"
+#include "evsel.h"
+#include "hisi-ptt.h"
+#include "hisi-ptt-decoder/hisi-ptt-pkt-decoder.h"
+#include "machine.h"
+#include "session.h"
+#include "tool.h"
+#include <internal/lib.h>
+
+struct hisi_ptt {
+	struct auxtrace auxtrace;
+	u32 auxtrace_type;
+	struct perf_session *session;
+	struct machine *machine;
+	u32 pmu_type;
+};
+
+struct hisi_ptt_queue {
+	struct hisi_ptt *ptt;
+	struct auxtrace_buffer *buffer;
+};
+
+static enum hisi_ptt_pkt_type hisi_ptt_check_packet_type(unsigned char *buf)
+{
+	uint32_t head = *(uint32_t *)buf;
+
+	if ((HISI_PTT_8DW_CHECK_MASK & head) == HISI_PTT_IS_8DW_PKT)
+		return HISI_PTT_8DW_PKT;
+
+	return HISI_PTT_4DW_PKT;
+}
+
+static void hisi_ptt_dump(struct hisi_ptt *ptt __maybe_unused,
+			  unsigned char *buf, size_t len)
+{
+	const char *color = PERF_COLOR_BLUE;
+	enum hisi_ptt_pkt_type type;
+	size_t pos = 0;
+	int pkt_len;
+
+	type = hisi_ptt_check_packet_type(buf);
+	len = round_down(len, hisi_ptt_pkt_size[type]);
+	color_fprintf(stdout, color, ". ... HISI PTT data: size %zu bytes\n",
+		      len);
+
+	while (len > 0) {
+		pkt_len = hisi_ptt_pkt_desc(buf, pos, type);
+		if (!pkt_len)
+			color_fprintf(stdout, color, " Bad packet!\n");
+
+		pos += pkt_len;
+		len -= pkt_len;
+	}
+}
+
+static void hisi_ptt_dump_event(struct hisi_ptt *ptt, unsigned char *buf,
+				size_t len)
+{
+	printf(".\n");
+
+	hisi_ptt_dump(ptt, buf, len);
+}
+
+static int hisi_ptt_process_event(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_sample *sample __maybe_unused,
+				  struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
+					   union perf_event *event,
+					   struct perf_tool *tool __maybe_unused)
+{
+	struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt,
+					    auxtrace);
+	int fd = perf_data__fd(session->data);
+	int size = event->auxtrace.size;
+	void *data = malloc(size);
+	off_t data_offset;
+	int err;
+
+	if (!data)
+		return -errno;
+
+	if (perf_data__is_pipe(session->data)) {
+		data_offset = 0;
+	} else {
+		data_offset = lseek(fd, 0, SEEK_CUR);
+		if (data_offset == -1)
+			return -errno;
+	}
+
+	err = readn(fd, data, size);
+	if (err != (ssize_t)size) {
+		free(data);
+		return -errno;
+	}
+
+	if (dump_trace)
+		hisi_ptt_dump_event(ptt, data, size);
+
+	return 0;
+}
+
+static int hisi_ptt_flush(struct perf_session *session __maybe_unused,
+			  struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static void hisi_ptt_free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static void hisi_ptt_free(struct perf_session *session)
+{
+	struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt,
+					    auxtrace);
+
+	session->auxtrace = NULL;
+	free(ptt);
+}
+
+static bool hisi_ptt_evsel_is_auxtrace(struct perf_session *session,
+				       struct evsel *evsel)
+{
+	struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, auxtrace);
+
+	return evsel->core.attr.type == ptt->pmu_type;
+}
+
+static void hisi_ptt_print_info(__u64 type)
+{
+	if (!dump_trace)
+		return;
+
+	fprintf(stdout, "  PMU Type           %" PRId64 "\n", (s64) type);
+}
+
+int hisi_ptt_process_auxtrace_info(union perf_event *event,
+				   struct perf_session *session)
+{
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
+	struct hisi_ptt *ptt;
+
+	if (auxtrace_info->header.size < HISI_PTT_AUXTRACE_PRIV_SIZE +
+				sizeof(struct perf_record_auxtrace_info))
+		return -EINVAL;
+
+	ptt = zalloc(sizeof(*ptt));
+	if (!ptt)
+		return -ENOMEM;
+
+	ptt->session = session;
+	ptt->machine = &session->machines.host; /* No kvm support */
+	ptt->auxtrace_type = auxtrace_info->type;
+	ptt->pmu_type = auxtrace_info->priv[0];
+
+	ptt->auxtrace.process_event = hisi_ptt_process_event;
+	ptt->auxtrace.process_auxtrace_event = hisi_ptt_process_auxtrace_event;
+	ptt->auxtrace.flush_events = hisi_ptt_flush;
+	ptt->auxtrace.free_events = hisi_ptt_free_events;
+	ptt->auxtrace.free = hisi_ptt_free;
+	ptt->auxtrace.evsel_is_auxtrace = hisi_ptt_evsel_is_auxtrace;
+	session->auxtrace = &ptt->auxtrace;
+
+	hisi_ptt_print_info(auxtrace_info->priv[0]);
+
+	return 0;
+}

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);
+
+int hisi_ptt_process_auxtrace_info(union perf_event *event,
+				   struct perf_session *session);
+
+#endif

tools/perf/util/intel-pt.c

@@ -4046,6 +4046,7 @@ static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_SNAPSHOT_MODE]	= "  Snapshot mode       %"PRId64"\n",
 	[INTEL_PT_PER_CPU_MMAPS]	= "  Per-cpu maps        %"PRId64"\n",
 	[INTEL_PT_MTC_BIT]		= "  MTC bit             %#"PRIx64"\n",
+	[INTEL_PT_MTC_FREQ_BITS]	= "  MTC freq bits       %#"PRIx64"\n",
 	[INTEL_PT_TSC_CTC_N]		= "  TSC:CTC numerator   %"PRIu64"\n",
 	[INTEL_PT_TSC_CTC_D]		= "  TSC:CTC denominator %"PRIu64"\n",
 	[INTEL_PT_CYC_BIT]		= "  CYC bit             %#"PRIx64"\n",
@@ -4060,8 +4061,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish)
 	if (!dump_trace)
 		return;
 
-	for (i = start; i <= finish; i++)
-		fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
+	for (i = start; i <= finish; i++) {
+		const char *fmt = intel_pt_info_fmts[i];
+
+		if (fmt)
+			fprintf(stdout, fmt, arr[i]);
+	}
 }
 
 static void intel_pt_print_info_str(const char *name, const char *str)

tools/perf/util/parse-events.c

@@ -246,6 +246,9 @@ __add_event(struct list_head *list, int *idx,
 	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
+	if (pmu)
+		perf_pmu__warn_invalid_formats(pmu);
+
 	if (pmu && attr->type == PERF_TYPE_RAW)
 		perf_pmu__warn_invalid_config(pmu, attr->config, name);
 

tools/perf/util/pmu.c

@@ -1005,6 +1005,23 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name)
 	return NULL;
 }
 
+void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
+{
+	struct perf_pmu_format *format;
+
+	/* fake pmu doesn't have format list */
+	if (pmu == &perf_pmu__fake)
+		return;
+
+	list_for_each_entry(format, &pmu->format, list)
+		if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) {
+			pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'"
+				   "which is not supported by this version of perf!\n",
+				   pmu->name, format->name, format->value);
+			return;
+		}
+}
+
 static struct perf_pmu *pmu_find(const char *name)
 {
 	struct perf_pmu *pmu;

tools/perf/util/pmu.h

@@ -17,6 +17,7 @@ enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
 	PERF_PMU_FORMAT_VALUE_CONFIG1,
 	PERF_PMU_FORMAT_VALUE_CONFIG2,
+	PERF_PMU_FORMAT_VALUE_CONFIG_END,
 };
 
 #define PERF_PMU_FORMAT_BITS 64
@@ -139,6 +140,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu);
 
 void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *name);
+void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
 bool perf_pmu__has_hybrid(void);
 int perf_pmu__match(char *pattern, char *name, char *tok);

tools/perf/util/pmu.l

@@ -27,8 +27,6 @@ num_dec         [0-9]+
 
 {num_dec}	{ return value(10); }
 config		{ return PP_CONFIG; }
-config1		{ return PP_CONFIG1; }
-config2		{ return PP_CONFIG2; }
 -		{ return '-'; }
 :		{ return ':'; }
 ,		{ return ','; }

tools/perf/util/pmu.y

@@ -18,7 +18,7 @@ do { \
 
 %}
 
-%token PP_CONFIG PP_CONFIG1 PP_CONFIG2
+%token PP_CONFIG
 %token PP_VALUE PP_ERROR
 %type <num> PP_VALUE
 %type <bits> bit_term
@@ -45,18 +45,11 @@ PP_CONFIG ':' bits
 				      $3));
 }
 |
-PP_CONFIG1 ':' bits
+PP_CONFIG PP_VALUE ':' bits
 {
 	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG1,
-				      $3));
-}
-|
-PP_CONFIG2 ':' bits
-{
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG2,
-				      $3));
+				      $2,
+				      $4));
 }
 
 bits: