perf/core improvements and fixes:

User visible:
 
 - Print callchains asked for events requested via 'perf trace --event' too:
   (Arnaldo Carvalho de Melo)
 
   # trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
    0.346 (0.005 ms): usleep/24428 nanosleep(rqtp: 0x7fffa15a0540) ...
    0.346 (        ): sched:sched_switch:usleep:24428 [120] S ==> swapper/3:0 [120])
                                     __schedule+0xfe200402 ([kernel.kallsyms])
                                     schedule+0xfe200035 ([kernel.kallsyms])
                                     do_nanosleep+0xfe20006f ([kernel.kallsyms])
                                     hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
                                     sys_nanosleep+0xfe20007a ([kernel.kallsyms])
                                     do_syscall_64+0xfe200062 ([kernel.kallsyms])
                                     return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
                                     __nanosleep+0xffff005b8d602010 (/usr/lib64/libc-2.22.so)
    0.400 (0.059 ms): usleep/24428  ... [continued]: nanosleep()) = 0
                                     __nanosleep+0x10 (/usr/lib64/libc-2.22.so)
                                     usleep+0x34 (/usr/lib64/libc-2.22.so)
                                     main+0x1eb (/usr/bin/usleep)
                                     __libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
                                     _start+0x29 (/usr/bin/usleep)
 
 - Allow requesting that some CPUs or PIDs be highlighted in 'perf sched map' (Jiri Olsa)
 
 - Compact 'perf sched map' to show just CPUs with activity, improving the output
   in high core count systems (Jiri Olsa)
 
 - Fix segfault with 'perf trace --no-syscalls -e syscall-names' by bailing out
   such request, doesn't make sense to ask for no syscalls and then specify which
   ones should be printed (Arnaldo Carvalho de Melo)
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABCAAGBQJXDljhAAoJENZQFvNTUqpARMwQAK+pwzNfcx4BJXA4RuPfb2cL
 rvlZKXvJuhdYtH+mEYjkqW24CDTMObXGzJHX/ESkADnhHqBz15/aCCYYcN6Ib6TC
 b4hYKR8VfGe1oWFyKavFEl2iHeTZHJKqR//CV6ujmcC9/q9CV8FFjiYptyswqIiI
 qS1clOTVh/xhKEZqhTfCq2CgJcX0G/N9iTJJ4nm5JAb4wAUeQeTyX5Tbw7CrKOOQ
 D21EYviHxDQM3urG8eEB7FXVRbrjGHI4V0MUEth8Arkx64fvC7UTwTb+tsWjVVji
 MHLi0yylLH8mdDpzEnjRcj1z8/FjiNh9Cc5arC12cBREy98Sy7J50fLiSyR6UWyY
 UUB1qTwYe4cqi0bPGt50nMzizH/lOcYcbgyWEiKxsH6pfuNWvOJReFJt+Ovpg/wc
 Xr/0mhUOhy/aIMfUvvSST/+f/01BFzIx49PpDquKU/XAnB1PSHTnERV2BdY3D9Jr
 s9JaaKahj5P333wqxgQfOS9d+eu259kQcSvgHcsKAzZv4hUGsdAMMYaUOIfx1jBH
 qMOdD5aW1kzhzN9rm7saUCKZtplM48ZFM7cXKduxHpMhDCiQnUAEp+faM+uQm+n7
 9TGMLIA7by0TohG/jRQqObq5a/d8oDtwNwlZvOMf+BoJrG6ZXYii5KZ0vSiBVfIJ
 e7PhQIBfsJaeb+98EGgv
 =VzVp
 -----END PGP SIGNATURE-----

Merge tag 'perf-core-for-mingo-20160413' 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:

User visible changes:

- Print callchains asked for events requested via 'perf trace --event' too:
  (Arnaldo Carvalho de Melo)

  # trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
   0.346 (0.005 ms): usleep/24428 nanosleep(rqtp: 0x7fffa15a0540) ...
   0.346 (        ): sched:sched_switch:usleep:24428 [120] S ==> swapper/3:0 [120])
                                    __schedule+0xfe200402 ([kernel.kallsyms])
                                    schedule+0xfe200035 ([kernel.kallsyms])
                                    do_nanosleep+0xfe20006f ([kernel.kallsyms])
                                    hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
                                    sys_nanosleep+0xfe20007a ([kernel.kallsyms])
                                    do_syscall_64+0xfe200062 ([kernel.kallsyms])
                                    return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
                                    __nanosleep+0xffff005b8d602010 (/usr/lib64/libc-2.22.so)
   0.400 (0.059 ms): usleep/24428  ... [continued]: nanosleep()) = 0
                                    __nanosleep+0x10 (/usr/lib64/libc-2.22.so)
                                    usleep+0x34 (/usr/lib64/libc-2.22.so)
                                    main+0x1eb (/usr/bin/usleep)
                                    __libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
                                    _start+0x29 (/usr/bin/usleep)

- Allow requesting that some CPUs or PIDs be highlighted in 'perf sched map' (Jiri Olsa)

- Compact 'perf sched map' to show just CPUs with activity, improving the output
  in high core count systems (Jiri Olsa)

- Fix segfault with 'perf trace --no-syscalls -e syscall-names' by bailing out
  such request, doesn't make sense to ask for no syscalls and then specify which
  ones should be printed (Arnaldo Carvalho de Melo)

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

tools/perf/Documentation/perf-sched.txt

@@ -50,6 +50,22 @@ OPTIONS
 --dump-raw-trace=::
         Display verbose dump of the sched data.
 
+OPTIONS for 'perf sched map'
+----------------------------
+
+--compact::
+	Show only CPUs with activity. Helps visualizing on high core
+	count systems.
+
+--cpus::
+	Show just entries with activities for the given CPUs.
+
+--color-cpus::
+	Highlight the given cpus.
+
+--color-pids::
+	Highlight the given pids.
+
 SEE ALSO
 --------
 linkperf:perf-record[1]

tools/perf/builtin-sched.c

@@ -11,6 +11,8 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/cloexec.h"
+#include "util/thread_map.h"
+#include "util/color.h"
 
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
@@ -122,6 +124,21 @@ struct trace_sched_handler {
 				  struct machine *machine);
 };
 
+#define COLOR_PIDS PERF_COLOR_BLUE
+#define COLOR_CPUS PERF_COLOR_BG_RED
+
+struct perf_sched_map {
+	DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS);
+	int			*comp_cpus;
+	bool			 comp;
+	struct thread_map	*color_pids;
+	const char		*color_pids_str;
+	struct cpu_map		*color_cpus;
+	const char		*color_cpus_str;
+	struct cpu_map		*cpus;
+	const char		*cpus_str;
+};
+
 struct perf_sched {
 	struct perf_tool tool;
 	const char	 *sort_order;
@@ -173,6 +190,7 @@ struct perf_sched {
 	struct list_head sort_list, cmp_pid;
 	bool force;
 	bool skip_merge;
+	struct perf_sched_map map;
 };
 
 static u64 get_nsecs(void)
@@ -1339,6 +1357,38 @@ static int process_sched_wakeup_event(struct perf_tool *tool,
 	return 0;
 }
 
+union map_priv {
+	void	*ptr;
+	bool	 color;
+};
+
+static bool thread__has_color(struct thread *thread)
+{
+	union map_priv priv = {
+		.ptr = thread__priv(thread),
+	};
+
+	return priv.color;
+}
+
+static struct thread*
+map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid)
+{
+	struct thread *thread = machine__findnew_thread(machine, pid, tid);
+	union map_priv priv = {
+		.color = false,
+	};
+
+	if (!sched->map.color_pids || !thread || thread__priv(thread))
+		return thread;
+
+	if (thread_map__has(sched->map.color_pids, tid))
+		priv.color = true;
+
+	thread__set_priv(thread, priv.ptr);
+	return thread;
+}
+
 static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine)
 {
@@ -1347,13 +1397,25 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
-	int cpu, this_cpu = sample->cpu;
+	int i, this_cpu = sample->cpu;
+	int cpus_nr;
+	bool new_cpu = false;
+	const char *color = PERF_COLOR_NORMAL;
 
 	BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
 
 	if (this_cpu > sched->max_cpu)
 		sched->max_cpu = this_cpu;
 
+	if (sched->map.comp) {
+		cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS);
+		if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) {
+			sched->map.comp_cpus[cpus_nr++] = this_cpu;
+			new_cpu = true;
+		}
+	} else
+		cpus_nr = sched->max_cpu;
+
 	timestamp0 = sched->cpu_last_switched[this_cpu];
 	sched->cpu_last_switched[this_cpu] = timestamp;
 	if (timestamp0)
@@ -1366,7 +1428,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		return -1;
 	}
 
-	sched_in = machine__findnew_thread(machine, -1, next_pid);
+	sched_in = map__findnew_thread(sched, machine, -1, next_pid);
 	if (sched_in == NULL)
 		return -1;
 
@@ -1400,26 +1462,52 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		new_shortname = 1;
 	}
 
-	for (cpu = 0; cpu <= sched->max_cpu; cpu++) {
+	for (i = 0; i < cpus_nr; i++) {
+		int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
+		struct thread *curr_thread = sched->curr_thread[cpu];
+		const char *pid_color = color;
+		const char *cpu_color = color;
+
+		if (curr_thread && thread__has_color(curr_thread))
+			pid_color = COLOR_PIDS;
+
+		if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu))
+			continue;
+
+		if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu))
+			cpu_color = COLOR_CPUS;
+
 		if (cpu != this_cpu)
-			printf(" ");
+			color_fprintf(stdout, cpu_color, " ");
 		else
-			printf("*");
+			color_fprintf(stdout, cpu_color, "*");
 
 		if (sched->curr_thread[cpu])
-			printf("%2s ", sched->curr_thread[cpu]->shortname);
+			color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname);
 		else
-			printf("   ");
+			color_fprintf(stdout, color, "   ");
 	}
 
-	printf("  %12.6f secs ", (double)timestamp/1e9);
+	if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
+		goto out;
+
+	color_fprintf(stdout, color, "  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
-		printf("%s => %s:%d\n",
+		const char *pid_color = color;
+
+		if (thread__has_color(sched_in))
+			pid_color = COLOR_PIDS;
+
+		color_fprintf(stdout, pid_color, "%s => %s:%d",
 		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
-	} else {
-		printf("\n");
 	}
 
+	if (sched->map.comp && new_cpu)
+		color_fprintf(stdout, color, " (CPU %d)", this_cpu);
+
+out:
+	color_fprintf(stdout, color, "\n");
+
 	thread__put(sched_in);
 
 	return 0;
@@ -1675,9 +1763,75 @@ static int perf_sched__lat(struct perf_sched *sched)
 	return 0;
 }
 
+static int setup_map_cpus(struct perf_sched *sched)
+{
+	struct cpu_map *map;
+
+	sched->max_cpu  = sysconf(_SC_NPROCESSORS_CONF);
+
+	if (sched->map.comp) {
+		sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int));
+		if (!sched->map.comp_cpus)
+			return -1;
+	}
+
+	if (!sched->map.cpus_str)
+		return 0;
+
+	map = cpu_map__new(sched->map.cpus_str);
+	if (!map) {
+		pr_err("failed to get cpus map from %s\n", sched->map.cpus_str);
+		return -1;
+	}
+
+	sched->map.cpus = map;
+	return 0;
+}
+
+static int setup_color_pids(struct perf_sched *sched)
+{
+	struct thread_map *map;
+
+	if (!sched->map.color_pids_str)
+		return 0;
+
+	map = thread_map__new_by_tid_str(sched->map.color_pids_str);
+	if (!map) {
+		pr_err("failed to get thread map from %s\n", sched->map.color_pids_str);
+		return -1;
+	}
+
+	sched->map.color_pids = map;
+	return 0;
+}
+
+static int setup_color_cpus(struct perf_sched *sched)
+{
+	struct cpu_map *map;
+
+	if (!sched->map.color_cpus_str)
+		return 0;
+
+	map = cpu_map__new(sched->map.color_cpus_str);
+	if (!map) {
+		pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str);
+		return -1;
+	}
+
+	sched->map.color_cpus = map;
+	return 0;
+}
+
 static int perf_sched__map(struct perf_sched *sched)
 {
-	sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
+	if (setup_map_cpus(sched))
+		return -1;
+
+	if (setup_color_pids(sched))
+		return -1;
+
+	if (setup_color_cpus(sched))
+		return -1;
 
 	setup_pager();
 	if (perf_sched__read_events(sched))
@@ -1831,6 +1985,17 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "dump raw trace in ASCII"),
 	OPT_END()
 	};
+	const struct option map_options[] = {
+	OPT_BOOLEAN(0, "compact", &sched.map.comp,
+		    "map output in compact mode"),
+	OPT_STRING(0, "color-pids", &sched.map.color_pids_str, "pids",
+		   "highlight given pids in map"),
+	OPT_STRING(0, "color-cpus", &sched.map.color_cpus_str, "cpus",
+                    "highlight given CPUs in map"),
+	OPT_STRING(0, "cpus", &sched.map.cpus_str, "cpus",
+                    "display given CPUs in map"),
+	OPT_END()
+	};
 	const char * const latency_usage[] = {
 		"perf sched latency [<options>]",
 		NULL
@@ -1839,6 +2004,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf sched replay [<options>]",
 		NULL
 	};
+	const char * const map_usage[] = {
+		"perf sched map [<options>]",
+		NULL
+	};
 	const char *const sched_subcommands[] = { "record", "latency", "map",
 						  "replay", "script", NULL };
 	const char *sched_usage[] = {
@@ -1887,6 +2056,11 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		setup_sorting(&sched, latency_options, latency_usage);
 		return perf_sched__lat(&sched);
 	} else if (!strcmp(argv[0], "map")) {
+		if (argc) {
+			argc = parse_options(argc, argv, map_options, map_usage, 0);
+			if (argc)
+				usage_with_options(map_usage, map_options);
+		}
 		sched.tp_handler = &map_ops;
 		setup_sorting(&sched, latency_options, latency_usage);
 		return perf_sched__map(&sched);

tools/perf/builtin-script.c

@@ -317,19 +317,19 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
 
 	output[type].print_ip_opts = 0;
 	if (PRINT_FIELD(IP))
-		output[type].print_ip_opts |= PRINT_IP_OPT_IP;
+		output[type].print_ip_opts |= EVSEL__PRINT_IP;
 
 	if (PRINT_FIELD(SYM))
-		output[type].print_ip_opts |= PRINT_IP_OPT_SYM;
+		output[type].print_ip_opts |= EVSEL__PRINT_SYM;
 
 	if (PRINT_FIELD(DSO))
-		output[type].print_ip_opts |= PRINT_IP_OPT_DSO;
+		output[type].print_ip_opts |= EVSEL__PRINT_DSO;
 
 	if (PRINT_FIELD(SYMOFFSET))
-		output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+		output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET;
 
 	if (PRINT_FIELD(SRCLINE))
-		output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE;
+		output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE;
 }
 
 /*
@@ -574,9 +574,9 @@ static void print_sample_bts(struct perf_sample *sample,
 			printf("\n");
 		} else {
 			printf(" ");
-			if (print_opts & PRINT_IP_OPT_SRCLINE) {
+			if (print_opts & EVSEL__PRINT_SRCLINE) {
 				print_srcline_last = true;
-				print_opts &= ~PRINT_IP_OPT_SRCLINE;
+				print_opts &= ~EVSEL__PRINT_SRCLINE;
 			}
 		}
 		perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts,

tools/perf/builtin-trace.c

@@ -2114,6 +2114,28 @@ out_put:
 	return err;
 }
 
+static int trace__fprintf_callchain(struct trace *trace, struct perf_evsel *evsel,
+				    struct perf_sample *sample)
+{
+	struct addr_location al;
+	/* TODO: user-configurable print_opts */
+	const unsigned int print_opts = EVSEL__PRINT_SYM |
+				        EVSEL__PRINT_DSO |
+				        EVSEL__PRINT_UNKNOWN_AS_ADDR;
+
+	if (sample->callchain == NULL)
+		return 0;
+
+	if (machine__resolve(trace->host, &al, sample) < 0) {
+		pr_err("Problem processing %s callchain, skipping...\n",
+			perf_evsel__name(evsel));
+		return 0;
+	}
+
+	return perf_evsel__fprintf_callchain(evsel, sample, &al, 38, print_opts,
+					     scripting_max_stack, trace->output);
+}
+
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
@@ -2193,21 +2215,7 @@ signed_print:
 
 	fputc('\n', trace->output);
 
-	if (sample->callchain) {
-		struct addr_location al;
-		/* TODO: user-configurable print_opts */
-		const unsigned int print_opts = PRINT_IP_OPT_SYM |
-					        PRINT_IP_OPT_DSO |
-					        PRINT_IP_OPT_UNKNOWN_AS_ADDR;
-
-		if (machine__resolve(trace->host, &al, sample) < 0) {
-			pr_err("problem processing %d event, skipping it.\n",
-			       event->header.type);
-			goto out_put;
-		}
-		perf_evsel__fprintf_callchain(evsel, sample, &al, 38, print_opts,
-					      scripting_max_stack, trace->output);
-	}
+	trace__fprintf_callchain(trace, evsel, sample);
 out:
 	ttrace->entry_pending = false;
 	err = 0;
@@ -2355,6 +2363,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	}
 
 	fprintf(trace->output, ")\n");
+
+	trace__fprintf_callchain(trace, evsel, sample);
+
 	return 0;
 }
 
@@ -3333,6 +3344,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	err = -1;
+
 	if (trace.trace_pgfaults) {
 		trace.opts.sample_address = true;
 		trace.opts.sample_time = true;
@@ -3357,6 +3370,11 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
+	if (!trace.trace_syscalls && ev_qualifier_str) {
+		pr_err("The -e option can't be used with --no-syscalls.\n");
+		goto out;
+	}
+
 	if (output_name != NULL) {
 		err = trace__open_output(&trace, output_name);
 		if (err < 0) {

tools/perf/util/cpumap.c

@@ -587,3 +587,15 @@ int cpu__setup_cpunode_map(void)
 	closedir(dir1);
 	return 0;
 }
+
+bool cpu_map__has(struct cpu_map *cpus, int cpu)
+{
+	int i;
+
+	for (i = 0; i < cpus->nr; ++i) {
+		if (cpus->map[i] == cpu)
+			return true;
+	}
+
+	return false;
+}

tools/perf/util/cpumap.h

@@ -66,4 +66,6 @@ int cpu__get_node(int cpu);
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
 		       void *data);
+
+bool cpu_map__has(struct cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */

tools/perf/util/evsel.c

@@ -2343,6 +2343,137 @@ out:
 	return ++printed;
 }
 
+int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample *sample,
+				  struct addr_location *al, int left_alignment,
+				  unsigned int print_opts, unsigned int stack_depth,
+				  FILE *fp)
+{
+	int printed = 0;
+	struct callchain_cursor_node *node;
+	int print_ip = print_opts & EVSEL__PRINT_IP;
+	int print_sym = print_opts & EVSEL__PRINT_SYM;
+	int print_dso = print_opts & EVSEL__PRINT_DSO;
+	int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET;
+	int print_oneline = print_opts & EVSEL__PRINT_ONELINE;
+	int print_srcline = print_opts & EVSEL__PRINT_SRCLINE;
+	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
+	char s = print_oneline ? ' ' : '\t';
+
+	if (sample->callchain) {
+		struct addr_location node_al;
+
+		if (thread__resolve_callchain(al->thread, evsel,
+					      sample, NULL, NULL,
+					      stack_depth) != 0) {
+			if (verbose)
+				error("Failed to resolve callchain. Skipping\n");
+			return printed;
+		}
+		callchain_cursor_commit(&callchain_cursor);
+
+		if (print_symoffset)
+			node_al = *al;
+
+		while (stack_depth) {
+			u64 addr = 0;
+
+			node = callchain_cursor_current(&callchain_cursor);
+			if (!node)
+				break;
+
+			if (node->sym && node->sym->ignore)
+				goto next;
+
+			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
+
+			if (print_ip)
+				printed += fprintf(fp, "%c%16" PRIx64, s, node->ip);
+
+			if (node->map)
+				addr = node->map->map_ip(node->map, node->ip);
+
+			if (print_sym) {
+				printed += fprintf(fp, " ");
+				node_al.addr = addr;
+				node_al.map  = node->map;
+
+				if (print_symoffset) {
+					printed += __symbol__fprintf_symname_offs(node->sym, &node_al,
+										  print_unknown_as_addr, fp);
+				} else {
+					printed += __symbol__fprintf_symname(node->sym, &node_al,
+									     print_unknown_as_addr, fp);
+				}
+			}
+
+			if (print_dso) {
+				printed += fprintf(fp, " (");
+				printed += map__fprintf_dsoname(node->map, fp);
+				printed += fprintf(fp, ")");
+			}
+
+			if (print_srcline)
+				printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
+
+			if (!print_oneline)
+				printed += fprintf(fp, "\n");
+
+			stack_depth--;
+next:
+			callchain_cursor_advance(&callchain_cursor);
+		}
+	}
+
+	return printed;
+}
+
+int perf_evsel__fprintf_sym(struct perf_evsel *evsel, struct perf_sample *sample,
+			    struct addr_location *al, int left_alignment,
+			    unsigned int print_opts, unsigned int stack_depth,
+			    FILE *fp)
+{
+	int printed = 0;
+	int print_ip = print_opts & EVSEL__PRINT_IP;
+	int print_sym = print_opts & EVSEL__PRINT_SYM;
+	int print_dso = print_opts & EVSEL__PRINT_DSO;
+	int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET;
+	int print_srcline = print_opts & EVSEL__PRINT_SRCLINE;
+	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
+
+	if (symbol_conf.use_callchain && sample->callchain) {
+		printed += perf_evsel__fprintf_callchain(evsel, sample, al, left_alignment,
+							 print_opts, stack_depth, fp);
+	} else if (!(al->sym && al->sym->ignore)) {
+		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
+
+		if (print_ip)
+			printed += fprintf(fp, "%16" PRIx64, sample->ip);
+
+		if (print_sym) {
+			printed += fprintf(fp, " ");
+			if (print_symoffset) {
+				printed += __symbol__fprintf_symname_offs(al->sym, al,
+									  print_unknown_as_addr, fp);
+			} else {
+				printed += __symbol__fprintf_symname(al->sym, al,
+								     print_unknown_as_addr, fp);
+			}
+		}
+
+		if (print_dso) {
+			printed += fprintf(fp, " (");
+			printed += map__fprintf_dsoname(al->map, fp);
+			printed += fprintf(fp, ")");
+		}
+
+		if (print_srcline)
+			printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
+	}
+
+	return printed;
+}
+
+
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {

tools/perf/util/evsel.h

@@ -387,12 +387,25 @@ struct perf_attr_details {
 int perf_evsel__fprintf(struct perf_evsel *evsel,
 			struct perf_attr_details *details, FILE *fp);
 
+#define EVSEL__PRINT_IP			(1<<0)
+#define EVSEL__PRINT_SYM		(1<<1)
+#define EVSEL__PRINT_DSO		(1<<2)
+#define EVSEL__PRINT_SYMOFFSET		(1<<3)
+#define EVSEL__PRINT_ONELINE		(1<<4)
+#define EVSEL__PRINT_SRCLINE		(1<<5)
+#define EVSEL__PRINT_UNKNOWN_AS_ADDR	(1<<6)
+
 int perf_evsel__fprintf_callchain(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al, int left_alignment,
 				  unsigned int print_opts,
 				  unsigned int stack_depth, FILE *fp);
 
+int perf_evsel__fprintf_sym(struct perf_evsel *evsel, struct perf_sample *sample,
+			    struct addr_location *al, int left_alignment,
+			    unsigned int print_opts, unsigned int stack_depth,
+			    FILE *fp);
+
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize);
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,

tools/perf/util/session.c

@@ -1953,136 +1953,6 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-int perf_evsel__fprintf_callchain(struct perf_evsel *evsel, struct perf_sample *sample,
-				  struct addr_location *al, int left_alignment,
-				  unsigned int print_opts, unsigned int stack_depth,
-				  FILE *fp)
-{
-	int printed = 0;
-	struct callchain_cursor_node *node;
-	int print_ip = print_opts & PRINT_IP_OPT_IP;
-	int print_sym = print_opts & PRINT_IP_OPT_SYM;
-	int print_dso = print_opts & PRINT_IP_OPT_DSO;
-	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
-	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
-	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
-	int print_unknown_as_addr = print_opts & PRINT_IP_OPT_UNKNOWN_AS_ADDR;
-	char s = print_oneline ? ' ' : '\t';
-
-	if (sample->callchain) {
-		struct addr_location node_al;
-
-		if (thread__resolve_callchain(al->thread, evsel,
-					      sample, NULL, NULL,
-					      stack_depth) != 0) {
-			if (verbose)
-				error("Failed to resolve callchain. Skipping\n");
-			return printed;
-		}
-		callchain_cursor_commit(&callchain_cursor);
-
-		if (print_symoffset)
-			node_al = *al;
-
-		while (stack_depth) {
-			u64 addr = 0;
-
-			node = callchain_cursor_current(&callchain_cursor);
-			if (!node)
-				break;
-
-			if (node->sym && node->sym->ignore)
-				goto next;
-
-			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
-
-			if (print_ip)
-				printed += fprintf(fp, "%c%16" PRIx64, s, node->ip);
-
-			if (node->map)
-				addr = node->map->map_ip(node->map, node->ip);
-
-			if (print_sym) {
-				printed += fprintf(fp, " ");
-				node_al.addr = addr;
-				node_al.map  = node->map;
-
-				if (print_symoffset) {
-					printed += __symbol__fprintf_symname_offs(node->sym, &node_al,
-										  print_unknown_as_addr, fp);
-				} else {
-					printed += __symbol__fprintf_symname(node->sym, &node_al,
-									     print_unknown_as_addr, fp);
-				}
-			}
-
-			if (print_dso) {
-				printed += fprintf(fp, " (");
-				printed += map__fprintf_dsoname(node->map, fp);
-				printed += fprintf(fp, ")");
-			}
-
-			if (print_srcline)
-				printed += map__fprintf_srcline(node->map, addr, "\n  ", fp);
-
-			if (!print_oneline)
-				printed += fprintf(fp, "\n");
-
-			stack_depth--;
-next:
-			callchain_cursor_advance(&callchain_cursor);
-		}
-	}
-
-	return printed;
-}
-
-int perf_evsel__fprintf_sym(struct perf_evsel *evsel, struct perf_sample *sample,
-			    struct addr_location *al, int left_alignment,
-			    unsigned int print_opts, unsigned int stack_depth,
-			    FILE *fp)
-{
-	int printed = 0;
-	int print_ip = print_opts & PRINT_IP_OPT_IP;
-	int print_sym = print_opts & PRINT_IP_OPT_SYM;
-	int print_dso = print_opts & PRINT_IP_OPT_DSO;
-	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
-	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
-	int print_unknown_as_addr = print_opts & PRINT_IP_OPT_UNKNOWN_AS_ADDR;
-
-	if (symbol_conf.use_callchain && sample->callchain) {
-		printed += perf_evsel__fprintf_callchain(evsel, sample, al, left_alignment,
-							 print_opts, stack_depth, fp);
-	} else if (!(al->sym && al->sym->ignore)) {
-		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
-
-		if (print_ip)
-			printed += fprintf(fp, "%16" PRIx64, sample->ip);
-
-		if (print_sym) {
-			printed += fprintf(fp, " ");
-			if (print_symoffset) {
-				printed += __symbol__fprintf_symname_offs(al->sym, al,
-									  print_unknown_as_addr, fp);
-			} else {
-				printed += __symbol__fprintf_symname(al->sym, al,
-								     print_unknown_as_addr, fp);
-			}
-		}
-
-		if (print_dso) {
-			printed += fprintf(fp, " (");
-			printed += map__fprintf_dsoname(al->map, fp);
-			printed += fprintf(fp, ")");
-		}
-
-		if (print_srcline)
-			printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
-	}
-
-	return printed;
-}
-
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap)
 {

tools/perf/util/session.h

@@ -36,14 +36,6 @@ struct perf_session {
 	struct perf_tool	*tool;
 };
 
-#define PRINT_IP_OPT_IP		(1<<0)
-#define PRINT_IP_OPT_SYM		(1<<1)
-#define PRINT_IP_OPT_DSO		(1<<2)
-#define PRINT_IP_OPT_SYMOFFSET	(1<<3)
-#define PRINT_IP_OPT_ONELINE	(1<<4)
-#define PRINT_IP_OPT_SRCLINE	(1<<5)
-#define PRINT_IP_OPT_UNKNOWN_AS_ADDR (1<<6)
-
 struct perf_tool;
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -105,11 +97,6 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-int perf_evsel__fprintf_sym(struct perf_evsel *evsel, struct perf_sample *sample,
-			    struct addr_location *al, int left_alignment,
-			    unsigned int print_opts, unsigned int stack_depth,
-			    FILE *fp);
-
 int perf_session__cpu_bitmap(struct perf_session *session,
 			     const char *cpu_list, unsigned long *cpu_bitmap);
 

tools/perf/util/thread_map.c

@@ -260,7 +260,7 @@ struct thread_map *thread_map__new_dummy(void)
 	return threads;
 }
 
-static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
+struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
 	struct thread_map *threads = NULL, *nt;
 	int ntasks = 0;
@@ -436,3 +436,15 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event)
 
 	return threads;
 }
+
+bool thread_map__has(struct thread_map *threads, pid_t pid)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i) {
+		if (threads->map[i].pid == pid)
+			return true;
+	}
+
+	return false;
+}

tools/perf/util/thread_map.h

@@ -31,6 +31,8 @@ void thread_map__put(struct thread_map *map);
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
+struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
+
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
@@ -55,4 +57,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread)
 }
 
 void thread_map__read_comms(struct thread_map *threads);
+bool thread_map__has(struct thread_map *threads, pid_t pid);
 #endif	/* __PERF_THREAD_MAP_H */