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>

tools/include/linux/compiler-gcc.h

@@ -21,6 +21,9 @@
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
+#ifndef __pure
+#define  __pure		__attribute__((pure))
+#endif
 #define  noinline	__attribute__((noinline))
 #ifndef __packed
 #define __packed	__attribute__((packed))

tools/lib/api/fs/tracing_path.c

@@ -13,11 +13,9 @@
 
 #include "tracing_path.h"
 
-
-char tracing_mnt[PATH_MAX]         = "/sys/kernel/debug";
-char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
-
+static char tracing_mnt[PATH_MAX]  = "/sys/kernel/debug";
+static char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
+static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
 
 static void __tracing_path_set(const char *tracing, const char *mountpoint)
 {
@@ -76,7 +74,7 @@ char *get_tracing_file(const char *name)
 {
 	char *file;
 
-	if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
+	if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0)
 		return NULL;
 
 	return file;
@@ -87,6 +85,34 @@ void put_tracing_file(char *file)
 	free(file);
 }
 
+char *get_events_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+		return NULL;
+
+	return file;
+}
+
+void put_events_file(char *file)
+{
+	free(file);
+}
+
+DIR *tracing_events__opendir(void)
+{
+	DIR *dir = NULL;
+	char *path = get_tracing_file("events");
+
+	if (path) {
+		dir = opendir(path);
+		put_events_file(path);
+	}
+
+	return dir;
+}
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 				   const char *sys, const char *name)
 {
@@ -129,7 +155,7 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 		snprintf(buf, size,
 			 "Error:\tNo permissions to read %s/%s\n"
 			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
-			 tracing_events_path, filename, tracing_mnt);
+			 tracing_events_path, filename, tracing_path_mount());
 	}
 		break;
 	default:

tools/lib/api/fs/tracing_path.h

@@ -3,15 +3,20 @@
 #define __API_FS_TRACING_PATH_H
 
 #include <linux/types.h>
+#include <dirent.h>
 
-extern char tracing_path[];
-extern char tracing_events_path[];
+DIR *tracing_events__opendir(void);
 
 void tracing_path_set(const char *mountpoint);
 const char *tracing_path_mount(void);
 
 char *get_tracing_file(const char *name);
 void put_tracing_file(char *file);
 
+char *get_events_file(const char *name);
+void put_events_file(char *file);
+
+#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; })
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
 #endif /* __API_FS_TRACING_PATH_H */

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) \

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;

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,
 	};

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;
 	}
 

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")) {
@@ -421,52 +421,30 @@ 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);
 	pager_init(PERF_PAGER_ENVIRONMENT);
 
 	/* 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)
 		cmd = "perf-help";
 
 	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:
 	 *

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);

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
 

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 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				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':