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

  o Restore "--callchain graph" output, broken in recent cset to end
    up being the same as "fractal" (Namhyung Kim)

  o Allow profiling when kptr_restrict == 1 for non root users,
    kernel samples will just remain unresolved (Andi Kleen)

  o Allow configuring default options for callchains in config file (Namhyung Kim)

  o Fix line number in the config file error message (Jiri Olsa)

  o Fix --per-core on multi socket systems (Andi Kleen)

Cleanups:

  o Use ACCESS_ONCE() instead of volatile cast. (Pranith Kumar)

  o Modify error code for when perf_session__new() fails (Taeung Song)

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

tools/perf/builtin-annotate.c

@@ -340,7 +340,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	annotate.session = perf_session__new(&file, false, &annotate.tool);
 	if (annotate.session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	symbol_conf.priv_size = sizeof(struct annotation);
 	symbol_conf.try_vmlinux_path = true;

tools/perf/builtin-diff.c

@@ -683,7 +683,7 @@ static int __cmd_diff(void)
 		d->session = perf_session__new(&d->file, false, &tool);
 		if (!d->session) {
 			pr_err("Failed to open %s\n", d->file.path);
-			ret = -ENOMEM;
+			ret = -1;
 			goto out_delete;
 		}
 

tools/perf/builtin-evlist.c

@@ -28,7 +28,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 
 	session = perf_session__new(&file, 0, NULL);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	evlist__for_each(session->evlist, pos)
 		perf_evsel__fprintf(pos, details, stdout);

tools/perf/builtin-inject.c

@@ -460,7 +460,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	file.path = inject.input_name;
 	inject.session = perf_session__new(&file, true, &inject.tool);
 	if (inject.session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (symbol__init(&inject.session->header.env) < 0)
 		return -1;

tools/perf/builtin-kmem.c

@@ -698,7 +698,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	symbol__init(&session->header.env);
 

tools/perf/builtin-kvm.c

@@ -1058,7 +1058,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	kvm->session = perf_session__new(&file, false, &kvm->tool);
 	if (!kvm->session) {
 		pr_err("Initializing perf session failed\n");
-		return -EINVAL;
+		return -1;
 	}
 
 	symbol__init(&kvm->session->header.env);
@@ -1361,7 +1361,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	 */
 	kvm->session = perf_session__new(&file, false, &kvm->tool);
 	if (kvm->session == NULL) {
-		err = -ENOMEM;
+		err = -1;
 		goto out;
 	}
 	kvm->session->evlist = kvm->evlist;

tools/perf/builtin-lock.c

@@ -862,7 +862,7 @@ static int __cmd_report(bool display_info)
 	session = perf_session__new(&file, false, &eops);
 	if (!session) {
 		pr_err("Initializing perf session failed\n");
-		return -ENOMEM;
+		return -1;
 	}
 
 	symbol__init(&session->header.env);

tools/perf/builtin-mem.c

@@ -124,7 +124,7 @@ static int report_raw_events(struct perf_mem *mem)
 							 &mem->tool);
 
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,

tools/perf/builtin-record.c

@@ -624,145 +624,56 @@ parse_branch_stack(const struct option *opt, const char *str, int unset)
 	return ret;
 }
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-static int get_stack_size(char *str, unsigned long *_size)
-{
-	char *endptr;
-	unsigned long size;
-	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
-	size = strtoul(str, &endptr, 0);
-
-	do {
-		if (*endptr)
-			break;
-
-		size = round_up(size, sizeof(u64));
-		if (!size || size > max_size)
-			break;
-
-		*_size = size;
-		return 0;
-
-	} while (0);
-
-	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
-	       max_size, str);
-	return -1;
-}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-
-int record_parse_callchain(const char *arg, struct record_opts *opts)
-{
-	char *tok, *name, *saveptr = NULL;
-	char *buf;
-	int ret = -1;
-
-	/* We need buffer that we know we can write to. */
-	buf = malloc(strlen(arg) + 1);
-	if (!buf)
-		return -ENOMEM;
-
-	strcpy(buf, arg);
-
-	tok = strtok_r((char *)buf, ",", &saveptr);
-	name = tok ? : (char *)buf;
-
-	do {
-		/* Framepointer style */
-		if (!strncmp(name, "fp", sizeof("fp"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				opts->call_graph = CALLCHAIN_FP;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-				       "needed for -g fp\n");
-			break;
-
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-		/* Dwarf style */
-		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
-			const unsigned long default_stack_dump_size = 8192;
-
-			ret = 0;
-			opts->call_graph = CALLCHAIN_DWARF;
-			opts->stack_dump_size = default_stack_dump_size;
-
-			tok = strtok_r(NULL, ",", &saveptr);
-			if (tok) {
-				unsigned long size = 0;
-
-				ret = get_stack_size(tok, &size);
-				opts->stack_dump_size = size;
-			}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-		} else {
-			pr_err("callchain: Unknown --call-graph option "
-			       "value: %s\n", arg);
-			break;
-		}
-
-	} while (0);
-
-	free(buf);
-	return ret;
-}
-
-static void callchain_debug(struct record_opts *opts)
+static void callchain_debug(void)
 {
 	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
 
-	pr_debug("callchain: type %s\n", str[opts->call_graph]);
+	pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
 
-	if (opts->call_graph == CALLCHAIN_DWARF)
+	if (callchain_param.record_mode == CALLCHAIN_DWARF)
 		pr_debug("callchain: stack dump size %d\n",
-			 opts->stack_dump_size);
+			 callchain_param.dump_size);
 }
 
-int record_parse_callchain_opt(const struct option *opt,
+int record_parse_callchain_opt(const struct option *opt __maybe_unused,
 			       const char *arg,
 			       int unset)
 {
-	struct record_opts *opts = opt->value;
 	int ret;
 
-	opts->call_graph_enabled = !unset;
+	callchain_param.enabled = !unset;
 
 	/* --no-call-graph */
 	if (unset) {
-		opts->call_graph = CALLCHAIN_NONE;
+		callchain_param.record_mode = CALLCHAIN_NONE;
 		pr_debug("callchain: disabled\n");
 		return 0;
 	}
 
-	ret = record_parse_callchain(arg, opts);
+	ret = parse_callchain_record_opt(arg);
 	if (!ret)
-		callchain_debug(opts);
+		callchain_debug();
 
 	return ret;
 }
 
-int record_callchain_opt(const struct option *opt,
+int record_callchain_opt(const struct option *opt __maybe_unused,
 			 const char *arg __maybe_unused,
 			 int unset __maybe_unused)
 {
-	struct record_opts *opts = opt->value;
+	callchain_param.enabled = true;
 
-	opts->call_graph_enabled = !unset;
+	if (callchain_param.record_mode == CALLCHAIN_NONE)
+		callchain_param.record_mode = CALLCHAIN_FP;
 
-	if (opts->call_graph == CALLCHAIN_NONE)
-		opts->call_graph = CALLCHAIN_FP;
-
-	callchain_debug(opts);
+	callchain_debug();
 	return 0;
 }
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
-	struct record *rec = cb;
-
 	if (!strcmp(var, "record.call-graph"))
-		return record_parse_callchain(value, &rec->opts);
+		var = "call-graph.record-mode"; /* fall-through */
 
 	return perf_default_config(var, value, cb);
 }

tools/perf/builtin-report.c

@@ -720,7 +720,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 repeat:
 	session = perf_session__new(&file, false, &report.tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (report.queue_size) {
 		ordered_events__set_alloc_size(&session->ordered_events,

tools/perf/builtin-script.c

@@ -1744,7 +1744,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	session = perf_session__new(&file, false, &script.tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (header || header_only) {
 		perf_session__fprintf_info(session, stdout, show_full_info);

tools/perf/builtin-stat.c

@@ -732,7 +732,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
@@ -741,7 +741,7 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
 
-	aggr_printout(evsel, cpu, nr);
+	aggr_printout(evsel, id, nr);
 
 	scnprintf(name, sizeof(name), "%s%s",
 		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
@@ -947,11 +947,12 @@ static void print_ll_cache_misses(int cpu,
 	fprintf(output, " of all LL-cache hits   ");
 }
 
-static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0, total2;
 	double sc =  evsel->scale;
 	const char *fmt;
+	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -962,7 +963,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
 	}
 
-	aggr_printout(evsel, cpu, nr);
+	aggr_printout(evsel, id, nr);
 
 	if (aggr_mode == AGGR_GLOBAL)
 		cpu = 0;

tools/perf/builtin-timechart.c

@@ -1605,7 +1605,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 	int ret = -EINVAL;
 
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	symbol__init(&session->header.env);
 

tools/perf/builtin-top.c

@@ -929,7 +929,7 @@ static int __cmd_top(struct perf_top *top)
 
 	top->session = perf_session__new(NULL, false, NULL);
 	if (top->session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	machines__set_symbol_filter(&top->session->machines, symbol_filter);
 
@@ -1020,10 +1020,8 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 
 static int perf_top_config(const char *var, const char *value, void *cb)
 {
-	struct perf_top *top = cb;
-
 	if (!strcmp(var, "top.call-graph"))
-		return record_parse_callchain(value, &top->record_opts);
+		var = "call-graph.record-mode"; /* fall-through */
 	if (!strcmp(var, "top.children")) {
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;

tools/perf/builtin-trace.c

@@ -2250,7 +2250,7 @@ static int trace__replay(struct trace *trace)
 
 	session = perf_session__new(&file, false, &trace->tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (symbol__init(&session->header.env) < 0)
 		goto out;

tools/perf/perf.h

@@ -41,8 +41,6 @@ void pthread__unblock_sigwinch(void);
 
 struct record_opts {
 	struct target target;
-	int	     call_graph;
-	bool         call_graph_enabled;
 	bool	     group;
 	bool	     inherit_stat;
 	bool	     no_buffering;
@@ -60,7 +58,6 @@ struct record_opts {
 	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
-	u16	     stack_dump_size;
 	bool	     sample_transaction;
 	unsigned     initial_delay;
 };

tools/perf/ui/browsers/hists.c

@@ -804,9 +804,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
-		if (symbol_conf.cumulate_callchain)
-			total = entry->stat_acc->period;
-
 		printed += hist_browser__show_callchain(browser,
 					&entry->sorted_chain, 1, row, total,
 					hist_browser__show_callchain_entry, &arg,