Merge tag 'perf-core-for-mingo-4.18-20180519' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Record min/max LBR cycles (>= Skylake) and add 'perf annotate' TUI
  hotkey to show it (c) (Jin Yao)

- Fix machine->kernel_start for PTI on x86 (Adrian Hunter)

- Make machine->env->arch always available, e.g. in 'perf top', not
  just when reading that info from perf.data files (Adrian Hunter)

- Reduce the number of files read at 'perf' start, leaving information such as
  cacheline size, tracefs mount point determination, max_stack, etc, to be
  lazily read as tools needs then (Arnaldo Carvalho de Melo)

- Fix up BPF include and examples install messages (Arnaldo Carvalho de Melo)

- Fix up callchain addresses and symbol offsets in 'perf script', to help
  correlating with objdump output (Sandipan Das)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

25 files changed, 236 insertions, 111 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c63a3971d719..ecc9fc952655 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -770,9 +770,11 @@ endif
 ifndef NO_LIBBPF
 	$(call QUIET_INSTALL, lib) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, include/bpf) \
 		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
 	$(call QUIET_INSTALL, lib) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, examples/bpf) \
 		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index fa2c7a288750..cefc8813e91e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -153,8 +153,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -165,8 +165,9 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -185,10 +186,10 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
-			      PERF_OUTPUT_PHYS_ADDR,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
+			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -199,8 +200,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -211,8 +212,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_SYNTH,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -544,6 +545,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 			if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
 				output[j].fields |= PERF_OUTPUT_IP;
 				output[j].fields |= PERF_OUTPUT_SYM;
+				output[j].fields |= PERF_OUTPUT_SYMOFFSET;
 				output[j].fields |= PERF_OUTPUT_DSO;
 				set_print_ip_opts(attr);
 				goto out;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3c061c57afb6..7a349fcd3864 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1264,7 +1264,7 @@ int cmd_top(int argc, const char **argv)
 			.proc_map_timeout    = 500,
 			.overwrite	= 1,
 		},
-		.max_stack	     = sysctl_perf_event_max_stack,
+		.max_stack	     = sysctl__max_stack(),
 		.sym_pcnt_filter     = 5,
 		.nr_threads_synthesize = UINT_MAX,
 	};
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c7effcfc40ed..560aed7da36a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3162,7 +3162,7 @@ int cmd_trace(int argc, const char **argv)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
 		max_stack_user_set = false;
 	}
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 20a08cb32332..51c81509a315 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -238,7 +238,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			(*argc)--;
 		} else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
 			tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
-			fprintf(stderr, "dir: %s\n", tracing_path);
+			fprintf(stderr, "dir: %s\n", tracing_path_mount());
 			if (envchanged)
 				*envchanged = 1;
 		} else if (!strcmp(cmd, "--list-cmds")) {
@@ -421,22 +421,11 @@ void pthread__unblock_sigwinch(void)
 	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
-	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-		pr_debug("cannot determine cache line size");
-}
-#endif
-
 int main(int argc, const char **argv)
 {
 	int err;
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
-	int value;
 
 	/* libsubcmd init */
 	exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
@@ -444,13 +433,6 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
-	cache_line_size(&cacheline_size);
-
-	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
-		sysctl_perf_event_max_stack = value;
-
-	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
-		sysctl_perf_event_max_contexts_per_stack = value;
 
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
@@ -458,15 +440,11 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
-	perf_config__init();
 	err = perf_config(perf_default_config, NULL);
 	if (err)
 		return err;
 	set_buildid_dir(NULL);
 
-	/* get debugfs/tracefs mount point from /proc/mounts */
-	tracing_path_mount();
-
 	/*
 	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
 	 *
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 6829dd416a99..b9ebe15afb13 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1323,12 +1323,12 @@ static int count_tracepoints(void)
 	DIR *events_dir;
 	int cnt = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 
 	TEST_ASSERT_VAL("Can't open events dir", events_dir);
 
 	while ((events_ent = readdir(events_dir))) {
-		char sys_path[PATH_MAX];
+		char *sys_path;
 		struct dirent *sys_ent;
 		DIR *sys_dir;
 
@@ -1339,8 +1339,8 @@ static int count_tracepoints(void)
 		    || !strcmp(events_ent->d_name, "header_page"))
 			continue;
 
-		scnprintf(sys_path, PATH_MAX, "%s/%s",
-			  tracing_events_path, events_ent->d_name);
+		sys_path = get_events_file(events_ent->d_name);
+		TEST_ASSERT_VAL("Can't get sys path", sys_path);
 
 		sys_dir = opendir(sys_path);
 		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
@@ -1356,6 +1356,7 @@ static int count_tracepoints(void)
 		}
 
 		closedir(sys_dir);
+		put_events_file(sys_path);
 	}
 
 	closedir(events_dir);
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index ee86473643be..650b208f700f 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -16,18 +16,18 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$"
+	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$"
-		expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
+		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo[[:space:]]\($libc\)$"
-		expected[3]=".*\(.*/bin/ping.*\)$"
+		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
+		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	esac
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 3781d74088a7..8be40fa903aa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -695,6 +695,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"O             Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
 		"s             Toggle source code view\n"
 		"t             Circulate percent, total period, samples view\n"
+		"c             Show min/max cycle\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
 		"P             Print to [symbol_name].annotation file.\n"
@@ -791,6 +792,13 @@ show_sup_ins:
 				notes->options->show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'c':
+			if (notes->options->show_minmax_cycle)
+				notes->options->show_minmax_cycle = false;
+			else
+				notes->options->show_minmax_cycle = true;
+			annotation__update_column_widths(notes);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 5d74a30fe00f..6612c7f90af4 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -760,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes,
 	ch[offset].num_aggr++;
 	ch[offset].cycles_aggr += cycles;
 
+	if (cycles > ch[offset].cycles_max)
+		ch[offset].cycles_max = cycles;
+
+	if (ch[offset].cycles_min) {
+		if (cycles && cycles < ch[offset].cycles_min)
+			ch[offset].cycles_min = cycles;
+	} else
+		ch[offset].cycles_min = cycles;
+
 	if (!have_start && ch[offset].have_start)
 		return 0;
 	if (ch[offset].num) {
@@ -953,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
 			al = notes->offsets[offset];
-			if (al && ch->num_aggr)
+			if (al && ch->num_aggr) {
 				al->cycles = ch->cycles_aggr / ch->num_aggr;
+				al->cycles_max = ch->cycles_max;
+				al->cycles_min = ch->cycles_min;
+			}
 			notes->have_cycles = true;
 		}
 	}
@@ -2486,13 +2498,38 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (al->cycles)
-			obj__printf(obj, "%*" PRIu64 " ",
+		if (!notes->options->show_minmax_cycle) {
+			if (al->cycles)
+				obj__printf(obj, "%*" PRIu64 " ",
 					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
-		else if (!show_title)
-			obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " ");
-		else
-			obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle");
+			else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__CYCLES_WIDTH, " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__CYCLES_WIDTH - 1,
+					    "Cycle");
+		} else {
+			if (al->cycles) {
+				char str[32];
+
+				scnprintf(str, sizeof(str),
+					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
+					al->cycles, al->cycles_min,
+					al->cycles_max);
+
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    str);
+			} else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH,
+					    " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    "Cycle(min/max)");
+		}
 	}
 
 	obj__printf(obj, " ");
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f28a9e43421d..5080b6dd98b8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -61,6 +61,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
+#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
 
 struct annotation_options {
 	bool hide_src_code,
@@ -69,7 +70,8 @@ struct annotation_options {
 	     show_linenr,
 	     show_nr_jumps,
 	     show_nr_samples,
-	     show_total_period;
+	     show_total_period,
+	     show_minmax_cycle;
 	u8   offset_level;
 };
 
@@ -105,6 +107,8 @@ struct annotation_line {
 	int			 jump_sources;
 	float			 ipc;
 	u64			 cycles;
+	u64			 cycles_max;
+	u64			 cycles_min;
 	size_t			 privsize;
 	char			*path;
 	u32			 idx;
@@ -186,6 +190,8 @@ struct cyc_hist {
 	u64	start;
 	u64	cycles;
 	u64	cycles_aggr;
+	u64	cycles_max;
+	u64	cycles_min;
 	u32	num;
 	u32	num_aggr;
 	u8	have_start;
@@ -239,6 +245,9 @@ struct annotation {
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
+	if (notes->have_cycles && notes->options->show_minmax_cycle)
+		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
+
 	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 84eb9393c7db..5ac157056cdf 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void)
 	return set;
 }
 
+static int perf_config__init(void)
+{
+	if (config_set == NULL)
+		config_set = perf_config_set__new();
+
+	return config_set == NULL;
+}
+
 int perf_config(config_fn_t fn, void *data)
 {
 	int ret = 0;
@@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data)
 	struct perf_config_section *section;
 	struct perf_config_item *item;
 
-	if (config_set == NULL)
+	if (config_set == NULL && perf_config__init())
 		return -1;
 
 	perf_config_set__for_each_entry(config_set, section, item) {
@@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data)
 	return ret;
 }
 
-void perf_config__init(void)
-{
-	if (config_set == NULL)
-		config_set = perf_config_set__new();
-}
-
 void perf_config__exit(void)
 {
 	perf_config_set__delete(config_set);
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index baf82bf227ac..bd0a5897c76a 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
 			     const char *var, const char *value);
-void perf_config__init(void);
 void perf_config__exit(void);
 void perf_config__refresh(void);
 
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c842762e3f2..319fb0a0d05e 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -93,6 +93,24 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	return 0;
 }
 
+static int perf_env__read_arch(struct perf_env *env)
+{
+	struct utsname uts;
+
+	if (env->arch)
+		return 0;
+
+	if (!uname(&uts))
+		env->arch = strdup(uts.machine);
+
+	return env->arch ? 0 : -ENOMEM;
+}
+
+const char *perf_env__raw_arch(struct perf_env *env)
+{
+	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index c4ef2e523367..62e193948608 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -76,4 +76,6 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__raw_arch(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4cd2cf93f726..150db5ed7400 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2862,7 +2862,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			return scnprintf(msg, size,
 					 "Not enough memory to setup event with callchain.\n"
 					 "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
-					 "Hint: Current value: %d", sysctl_perf_event_max_stack);
+					 "Hint: Current value: %d", sysctl__max_stack());
 		break;
 	case ENODEV:
 		if (target->cpu_list)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 72a351613d85..e011a7160380 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1764,7 +1764,7 @@ static int add_callchain_ip(struct thread *thread,
 	}
 
 	srcline = callchain_srcline(al.map, al.sym, al.addr);
-	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
+	return callchain_cursor_append(cursor, ip, al.map, al.sym,
 				       branch, flags, nr_loop_iter,
 				       iter_cycles, branch_from, srcline);
 }
@@ -2296,6 +2296,15 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	return 0;
 }
 
+/*
+ * Compares the raw arch string. N.B. see instead perf_env__arch() if a
+ * normalized arch is needed.
+ */
+bool machine__is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);
@@ -2312,7 +2321,12 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (!err)
+		/*
+		 * On x86_64, PTI entry trampolines are less than the
+		 * start of kernel text, but still above 2^63. So leave
+		 * kernel_start = 1ULL << 63 for x86_64.
+		 */
+		if (!err && !machine__is(machine, "x86_64"))
 			machine->kernel_start = map->start;
 	}
 	return err;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 388fb4741c54..b31d33b5aa2a 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -188,6 +188,8 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
+bool machine__is(struct machine *machine, const char *arch);
+
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fc4ee8b86c1..15eec49e71a1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		    (strcmp(sys_dirent->d_name, ".")) &&	\
 		    (strcmp(sys_dirent->d_name, "..")))
 
-static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
+static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 {
 	char evt_path[MAXPATHLEN];
 	int fd;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
-			sys_dir->d_name, evt_dir->d_name);
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
 		return -EINVAL;
@@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+#define for_each_event(dir_path, evt_dir, evt_dirent)		\
 	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
 		if (evt_dirent->d_type == DT_DIR &&		\
 		    (strcmp(evt_dirent->d_name, ".")) &&	\
 		    (strcmp(evt_dirent->d_name, "..")) &&	\
-		    (!tp_event_has_id(sys_dirent, evt_dirent)))
+		    (!tp_event_has_id(dir_path, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -190,21 +189,21 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	int fd;
 	u64 id;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return NULL;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 
 			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
 				  evt_dirent->d_name);
@@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			close(fd);
 			id = atoll(id_buf);
 			if (id == config) {
+				put_events_file(dir_path);
 				closedir(evt_dir);
 				closedir(sys_dir);
 				path = zalloc(sizeof(*path));
@@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 
 	closedir(sys_dir);
@@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      struct parse_events_error *err,
 				      struct list_head *head_config)
 {
-	char evt_path[MAXPATHLEN];
+	char *evt_path;
 	struct dirent *evt_ent;
 	DIR *evt_dir;
 	int ret = 0, found = 0;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
+	evt_path = get_events_file(sys_name);
+	if (!evt_path) {
+		tracepoint_error(err, errno, sys_name, evt_name);
+		return -1;
+	}
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
+		put_events_file(evt_path);
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
 	}
@@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		ret = -1;
 	}
 
+	put_events_file(evt_path);
 	closedir(evt_dir);
 	return ret;
 }
@@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 	DIR *events_dir;
 	int ret = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 	if (!events_dir) {
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
@@ -2092,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 	char **evt_list = NULL;
 	unsigned int evt_i = 0, evt_num = 0;
 	bool evt_num_known = false;
 
 restart:
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return;
 
@@ -2113,13 +2121,14 @@ restart:
 		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
 			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
@@ -2133,11 +2142,15 @@ restart:
 				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
-			if (evt_list[evt_i] == NULL)
+			if (evt_list[evt_i] == NULL) {
+				put_events_file(dir_path);
 				goto out_close_evt_dir;
+			}
 			evt_i++;
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 
@@ -2185,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string)
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return 0;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
@@ -2209,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 	return 0;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 4ae1123c6794..b76088fadf3d 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite)
 	char buf[PATH_MAX];
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/%s",
-			 tracing_path, trace_file);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index e65903a695a6..4058ade352a5 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2582,7 +2582,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
-		if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+		if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0)
 			return -EINVAL;
 
 		if (sd->entry == &sort_mem_daddr_sym)
@@ -2628,7 +2628,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 		if (*tok) {
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
-				if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+				if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
 					pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
 				else
 					pr_err("Invalid --sort key: `%s'", tok);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 035b62e2c60b..9e6896293bbd 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -186,13 +186,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 static inline u64 cl_address(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
+	return (address & ~(cacheline_size() - 1));
 }
 
 static inline u64 cl_offset(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & (cacheline_size - 1));
+	return (address & (cacheline_size() - 1));
 }
 
 enum sort_mode {
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d7f2113462fb..c85d0d1a65ed 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -103,11 +103,10 @@ out:
 
 static int record_header_files(void)
 {
-	char *path;
+	char *path = get_events_file("header_page");
 	struct stat st;
 	int err = -EIO;
 
-	path = get_tracing_file("events/header_page");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_page");
 		return -ENOMEM;
@@ -128,9 +127,9 @@ static int record_header_files(void)
 		goto out;
 	}
 
-	put_tracing_file(path);
+	put_events_file(path);
 
-	path = get_tracing_file("events/header_event");
+	path = get_events_file("header_event");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_event");
 		err = -ENOMEM;
@@ -154,7 +153,7 @@ static int record_header_files(void)
 
 	err = 0;
 out:
-	put_tracing_file(path);
+	put_events_file(path);
 	return err;
 }
 
@@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps)
 	char *path;
 	int ret;
 
-	path = get_tracing_file("events/ftrace");
+	path = get_events_file("ftrace");
 	if (!path) {
 		pr_debug("can't get tracing/events/ftrace");
 		return -ENOMEM;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 16a776371d03..1aa368603268 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -75,6 +75,7 @@ void trace_event__cleanup(struct trace_event *t)
 static struct event_format*
 tp_format(const char *sys, const char *name)
 {
+	char *tp_dir = get_events_file(sys);
 	struct pevent *pevent = tevent.pevent;
 	struct event_format *event = NULL;
 	char path[PATH_MAX];
@@ -82,8 +83,11 @@ tp_format(const char *sys, const char *name)
 	char *data;
 	int err;
 
-	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
-		  tracing_events_path, sys, name);
+	if (!tp_dir)
+		return ERR_PTR(-errno);
+
+	scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name);
+	put_events_file(tp_dir);
 
 	err = filename__read_str(path, &data, &size);
 	if (err)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 1019bbc5dbd8..eac5b858a371 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -38,11 +38,43 @@ void perf_set_multithreaded(void)
 }
 
 unsigned int page_size;
-int cacheline_size;
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+	static int size;
+
+	if (!size)
+		cache_line_size(&size);
+
+	return size;
+}
 
 int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
+int sysctl__max_stack(void)
+{
+	int value;
+
+	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+		sysctl_perf_event_max_stack = value;
+
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
+	return sysctl_perf_event_max_stack;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c9626c206208..dc58254a2b69 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -43,7 +43,9 @@ size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
 extern unsigned int page_size;
-extern int cacheline_size;
+int __pure cacheline_size(void);
+
+int sysctl__max_stack(void);
 
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);