1 files changed, 179 insertions, 31 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e3ce2f34d3ad..c0783b4f7b6c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -21,8 +21,11 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/thread-stack.h"
+#include "util/time-utils.h"
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
+#include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 
@@ -63,6 +66,9 @@ enum perf_output_field {
 	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
+	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
+	PERF_OUTPUT_INSN	    = 1U << 21,
+	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 };
 
 struct output_option {
@@ -89,6 +95,9 @@ struct output_option {
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
+	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
+	{.str = "insn", .field = PERF_OUTPUT_INSN},
+	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 };
 
 /* default set to maintain compatibility with current format */
@@ -339,7 +348,7 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
  */
 static int perf_session__check_output_opt(struct perf_session *session)
 {
-	int j;
+	unsigned int j;
 	struct perf_evsel *evsel;
 
 	for (j = 0; j < PERF_TYPE_MAX; ++j) {
@@ -368,14 +377,16 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 	if (!no_callchain) {
 		bool use_callchain = false;
+		bool not_pipe = false;
 
-		evlist__for_each(session->evlist, evsel) {
+		evlist__for_each_entry(session->evlist, evsel) {
+			not_pipe = true;
 			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
 				use_callchain = true;
 				break;
 			}
 		}
-		if (!use_callchain)
+		if (not_pipe && !use_callchain)
 			symbol_conf.use_callchain = false;
 	}
 
@@ -388,17 +399,20 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		struct perf_event_attr *attr;
 
 		j = PERF_TYPE_TRACEPOINT;
-		evsel = perf_session__find_first_evtype(session, j);
-		if (evsel == NULL)
-			goto out;
 
-		attr = &evsel->attr;
+		evlist__for_each_entry(session->evlist, evsel) {
+			if (evsel->attr.type != j)
+				continue;
+
+			attr = &evsel->attr;
 
-		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
-			output[j].fields |= PERF_OUTPUT_IP;
-			output[j].fields |= PERF_OUTPUT_SYM;
-			output[j].fields |= PERF_OUTPUT_DSO;
-			set_print_ip_opts(attr);
+			if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+				output[j].fields |= PERF_OUTPUT_IP;
+				output[j].fields |= PERF_OUTPUT_SYM;
+				output[j].fields |= PERF_OUTPUT_DSO;
+				set_print_ip_opts(attr);
+				goto out;
+			}
 		}
 	}
 
@@ -428,7 +442,6 @@ static void print_sample_start(struct perf_sample *sample,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	unsigned long secs;
-	unsigned long usecs;
 	unsigned long long nsecs;
 
 	if (PRINT_FIELD(COMM)) {
@@ -456,13 +469,16 @@ static void print_sample_start(struct perf_sample *sample,
 
 	if (PRINT_FIELD(TIME)) {
 		nsecs = sample->time;
-		secs = nsecs / NSECS_PER_SEC;
-		nsecs -= secs * NSECS_PER_SEC;
-		usecs = nsecs / NSECS_PER_USEC;
+		secs = nsecs / NSEC_PER_SEC;
+		nsecs -= secs * NSEC_PER_SEC;
+
 		if (nanosecs)
 			printf("%5lu.%09llu: ", secs, nsecs);
-		else
-			printf("%5lu.%06lu: ", secs, usecs);
+		else {
+			char sample_time[32];
+			timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
+			printf("%12s: ", sample_time);
+		}
 	}
 }
 
@@ -513,11 +529,11 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
 		if (alf.map)
-			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
+			alf.sym = map__find_symbol(alf.map, alf.addr);
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		if (alt.map)
-			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
+			alt.sym = map__find_symbol(alt.map, alt.addr);
 
 		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
 		putchar('/');
@@ -559,6 +575,76 @@ static void print_sample_addr(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_callindent(struct perf_sample *sample,
+				    struct perf_evsel *evsel,
+				    struct thread *thread,
+				    struct addr_location *al)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	size_t depth = thread_stack__depth(thread);
+	struct addr_location addr_al;
+	const char *name = NULL;
+	static int spacing;
+	int len = 0;
+	u64 ip = 0;
+
+	/*
+	 * The 'return' has already been popped off the stack so the depth has
+	 * to be adjusted to match the 'call'.
+	 */
+	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
+		depth += 1;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				ip = sample->addr;
+		} else {
+			ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			ip = sample->ip;
+	}
+
+	if (name)
+		len = printf("%*s%s", (int)depth * 4, "", name);
+	else if (ip)
+		len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+
+	if (len < 0)
+		return;
+
+	/*
+	 * Try to keep the output length from changing frequently so that the
+	 * output lines up more nicely.
+	 */
+	if (len > spacing || (len && len < spacing - 52))
+		spacing = round_up(len + 4, 32);
+
+	if (len < spacing)
+		printf("%*s", spacing - len, "");
+}
+
+static void print_insn(struct perf_sample *sample,
+		       struct perf_event_attr *attr)
+{
+	if (PRINT_FIELD(INSNLEN))
+		printf(" ilen: %d", sample->insn_len);
+	if (PRINT_FIELD(INSN)) {
+		int i;
+
+		printf(" insn:");
+		for (i = 0; i < sample->insn_len; i++)
+			printf(" %02x", (unsigned char)sample->insn[i]);
+	}
+}
+
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
@@ -567,6 +653,9 @@ static void print_sample_bts(struct perf_sample *sample,
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
 
+	if (PRINT_FIELD(CALLINDENT))
+		print_sample_callindent(sample, evsel, thread, al);
+
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
 		unsigned int print_opts = output[attr->type].print_ip_opts;
@@ -600,16 +689,47 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
+	print_insn(sample, attr);
+
 	printf("\n");
 }
 
+static struct {
+	u32 flags;
+	const char *name;
+} sample_flags[] = {
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"},
+	{PERF_IP_FLAG_BRANCH, "jmp"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |	PERF_IP_FLAG_INTERRUPT, "hw int"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"},
+	{0, NULL}
+};
+
 static void print_sample_flags(u32 flags)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
 	const int n = strlen(PERF_IP_FLAG_CHARS);
+	bool in_tx = flags & PERF_IP_FLAG_IN_TX;
+	const char *name = NULL;
 	char str[33];
 	int i, pos = 0;
 
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
+			name = sample_flags[i].name;
+			break;
+		}
+	}
+
 	for (i = 0; i < n; i++, flags >>= 1) {
 		if (flags & 1)
 			str[pos++] = chars[i];
@@ -619,7 +739,11 @@ static void print_sample_flags(u32 flags)
 			str[pos++] = '?';
 	}
 	str[pos] = 0;
-	printf("  %-4s ", str);
+
+	if (name)
+		printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
+	else
+		printf("  %-11s ", str);
 }
 
 struct printer_data {
@@ -710,6 +834,8 @@ struct perf_script {
 	struct cpu_map		*cpus;
 	struct thread_map	*threads;
 	int			name_width;
+	const char              *time_str;
+	struct perf_time_interval ptime;
 };
 
 static int perf_evlist__max_name_len(struct perf_evlist *evlist)
@@ -717,7 +843,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int max = 0;
 
-	evlist__for_each(evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		int len = strlen(perf_evsel__name(evsel));
 
 		max = MAX(len, max);
@@ -810,7 +936,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-
+	print_insn(sample, attr);
 	printf("\n");
 }
 
@@ -891,6 +1017,9 @@ static int process_sample_event(struct perf_tool *tool,
 	struct perf_script *scr = container_of(tool, struct perf_script, tool);
 	struct addr_location al;
 
+	if (perf_time__skip_sample(&scr->ptime, sample->time))
+		return 0;
+
 	if (debug_mode) {
 		if (sample->time < last_timestamp) {
 			pr_err("Samples misordered, previous: %" PRIu64
@@ -942,7 +1071,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	if (evsel->attr.type >= PERF_TYPE_MAX)
 		return 0;
 
-	evlist__for_each(evlist, pos) {
+	evlist__for_each_entry(evlist, pos) {
 		if (pos->attr.type == evsel->attr.type && pos != evsel)
 			return 0;
 	}
@@ -1592,8 +1721,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
 	scripts_dir = opendir(scripts_path);
-	if (!scripts_dir)
-		return -1;
+	if (!scripts_dir) {
+		fprintf(stdout,
+			"open(%s) failed.\n"
+			"Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+			scripts_path);
+		exit(-1);
+	}
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
@@ -1668,7 +1802,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 			snprintf(evname, len + 1, "%s", p);
 
 			match = 0;
-			evlist__for_each(session->evlist, pos) {
+			evlist__for_each_entry(session->evlist, pos) {
 				if (!strcmp(perf_evsel__name(pos), evname)) {
 					match = 1;
 					break;
@@ -1870,7 +2004,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
 
-	evlist__for_each(session->evlist, counter) {
+	evlist__for_each_entry(session->evlist, counter) {
 		perf_stat_process_counter(&stat_config, counter);
 		process_stat(counter, round->time);
 	}
@@ -2017,11 +2151,14 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
+		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
 		   "only display events for these comms"),
@@ -2043,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
-	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2055,7 +2192,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			"Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 			"Enable kernel symbol demangling"),
-
+	OPT_STRING(0, "time", &script.time_str, "str",
+		   "Time span of interest (start,stop)"),
 	OPT_END()
 	};
 	const char * const script_subcommands[] = { "record", "report", NULL };
@@ -2074,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	file.path = input_name;
+	file.force = symbol_conf.force;
 
 	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
 		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -2256,6 +2395,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	script.session = session;
 	script__setup_sample_type(&script);
 
+	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+		itrace_synth_opts.thread_stack = true;
+
 	session->itrace_synth_opts = &itrace_synth_opts;
 
 	if (cpu_list) {
@@ -2331,6 +2473,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (err < 0)
 		goto out_delete;
 
+	/* needs to be parsed after looking up reference time */
+	if (perf_time__parse_str(&script.ptime, script.time_str) != 0) {
+		pr_err("Invalid time string\n");
+		return -EINVAL;
+	}
+
 	err = __cmd_script(&script);
 
 	flush_scripting();