Merge tag 'perf-core-for-mingo-20160520' of git://git.kernel.org/pub/…

…scm/linux/kernel/git/acme/linux into perf/urgent

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

User visible changes:

- We should not use the current value of the kernel.perf_event_max_stack as the
  default value for --max-stack in tools that can process perf.data files, they
  will only match if that sysctl wasn't changed from its default value at the
  time the perf.data file was recorded, fix it.

  This fixes a bug where a 'perf record -a --call-graph dwarf ; perf report'
  produces a glibc invalid free backtrace (Arnaldo Carvalho de Melo)

- Provide a better warning when running 'perf trace' on a system where the
  kernel.kptr_restrict is set to 1, similar to the one produced by 'perf record',
  noticed on ubuntu 16.04 where this is the default kptr_restrict setting.
  (Arnaldo Carvalho de Melo)

- Fix ordering of instructions in the annotation code, noticed when annotating
  ARM binaries, now that table is auto-ordered at first use, to avoid more such
  problems (Chris Ryder)

- Set buildid dir under symfs when --symfs is provided (He Kuang)

- Fix the 'exit_group()' syscall output in 'perf trace' (Arnaldo Carvalho de Melo)

- Only auto set call-graph to "dwarf" in 'perf trace' when syscalls are being
  traced (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-report.txt

@@ -248,7 +248,7 @@ OPTIONS
 	Note that when using the --itrace option the synthesized callchain size
 	will override this value if the synthesized callchain size is bigger.
 
-	Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+	Default: 127
 
 -G::
 --inverted::

tools/perf/Documentation/perf-script.txt

@@ -267,7 +267,7 @@ include::itrace.txt[]
         Note that when using the --itrace option the synthesized callchain size
         will override this value if the synthesized callchain size is bigger.
 
-        Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+        Default: 127
 
 --ns::
 	Use 9 decimal places when displaying time (i.e. show the nanoseconds)

tools/perf/Documentation/perf-trace.txt

@@ -143,7 +143,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
         Implies '--call-graph dwarf' when --call-graph not present on the
         command line, on systems where DWARF unwinding was built in.
 
-        Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+        Default: /proc/sys/kernel/perf_event_max_stack when present for
+                 live sessions (without --input/-i), 127 otherwise.
 
 --min-stack::
         Set the stack depth limit when parsing the callchain, anything

tools/perf/builtin-annotate.c

@@ -324,8 +324,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		   "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,

tools/perf/builtin-diff.c

@@ -812,8 +812,9 @@ static const struct option options[] = {
 	OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
 		   "separator for columns, no spaces will be added between "
 		   "columns '.' is reserved."),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),

tools/perf/builtin-report.c

@@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
-		.max_stack		 = sysctl_perf_event_max_stack,
+		.max_stack		 = PERF_MAX_STACK_DEPTH,
 		.pretty_printing_style	 = "normal",
 		.socket_filter		 = -1,
 	};
@@ -770,8 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "columns '.' is reserved."),
 	OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved,
 		    "Only display entries resolved to a symbol"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
 		   "list of cpus to profile"),
 	OPT_BOOLEAN('I', "show-info", &report.show_full_info,

tools/perf/builtin-script.c

@@ -2010,8 +2010,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "kallsyms pathname"),
 	OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
 		    "When printing symbols do not display call chain"),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
@@ -2067,8 +2068,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
-	scripting_max_stack = sysctl_perf_event_max_stack;
-
 	setup_scripting();
 
 	argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,

tools/perf/builtin-timechart.c

@@ -1945,8 +1945,9 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
-	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
-		    "Look for files with symbols relative to this directory"),
+	OPT_CALLBACK(0, "symfs", NULL, "directory",
+		     "Look for files with symbols relative to this directory",
+		     symbol__config_symfs),
 	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
 		    "min. number of tasks to print"),
 	OPT_BOOLEAN('t', "topology", &tchart.topology,

tools/perf/builtin-top.c

@@ -732,7 +732,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
-	if (!top->kptr_restrict_warned &&
+	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
 		ui__warning(
@@ -743,7 +743,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);
-		top->kptr_restrict_warned = true;
+		machine->kptr_restrict_warned = true;
 	}
 
 	if (al.sym == NULL) {
@@ -759,7 +759,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		 * --hide-kernel-symbols, even if the user specifies an
 		 * invalid --vmlinux ;-)
 		 */
-		if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
+		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
 		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
 		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
 			if (symbol_conf.vmlinux_name) {

tools/perf/builtin-trace.c

@@ -1160,6 +1160,24 @@ static int trace__tool_process(struct perf_tool *tool,
 	return trace__process_event(trace, machine, event, sample);
 }
 
+static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
+{
+	struct machine *machine = vmachine;
+
+	if (machine->kptr_restrict_warned)
+		return NULL;
+
+	if (symbol_conf.kptr_restrict) {
+		pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+			   "Check /proc/sys/kernel/kptr_restrict.\n\n"
+			   "Kernel samples will not be resolved.\n");
+		machine->kptr_restrict_warned = true;
+		return NULL;
+	}
+
+	return machine__resolve_kernel_addr(vmachine, addrp, modp);
+}
+
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
 	int err = symbol__init(NULL);
@@ -1171,7 +1189,7 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, machine__resolve_kernel_addr) < 0)
+	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
 		return -errno;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
@@ -1534,7 +1552,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
 			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
-			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
+			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
 		ttrace->entry_pending = true;
@@ -2887,12 +2905,12 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
 		max_stack_user_set = false;
 	}
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+	if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
 		record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
 #endif
 

tools/perf/util/annotate.c

@@ -354,9 +354,6 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
-/*
- * Must be sorted by name!
- */
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
@@ -372,8 +369,8 @@ static struct ins instructions[] = {
 	{ .name = "bgt",   .ops  = &jump_ops, },
 	{ .name = "bhi",   .ops  = &jump_ops, },
 	{ .name = "bl",    .ops  = &call_ops, },
-	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
 	{ .name = "blx",   .ops  = &call_ops, },
 	{ .name = "bne",   .ops  = &jump_ops, },
 #endif
@@ -449,18 +446,39 @@ static struct ins instructions[] = {
 	{ .name = "xbeginq", .ops  = &jump_ops, },
 };
 
-static int ins__cmp(const void *name, const void *insp)
+static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
 
 	return strcmp(name, ins->name);
 }
 
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(instructions);
+
+	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
 static struct ins *ins__find(const char *name)
 {
 	const int nmemb = ARRAY_SIZE(instructions);
+	static bool sorted;
+
+	if (!sorted) {
+		ins__sort();
+		sorted = true;
+	}
 
-	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp);
+	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
 }
 
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)

tools/perf/util/db-export.c

@@ -298,8 +298,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	 */
 	callchain_param.order = ORDER_CALLER;
 	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
-					sample, NULL, NULL,
-					sysctl_perf_event_max_stack);
+					sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
 	if (err) {
 		callchain_param.order = saved_order;
 		return NULL;

tools/perf/util/dso.c

@@ -63,9 +63,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-		/* skip the locally configured cache if a symfs is given */
-		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, filename, size) == NULL))
+		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
 		break;
 

tools/perf/util/machine.c

@@ -43,6 +43,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 
@@ -1135,10 +1136,10 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_running_kernel_start(machine, &name);
+	u64 addr;
 	int ret;
 
-	if (!addr || kernel == NULL)
+	if (kernel == NULL)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
@@ -1160,8 +1161,9 @@ int machine__create_kernel_maps(struct machine *machine)
 	 */
 	map_groups__fixup_end(&machine->kmaps);
 
-	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
-					     addr)) {
+	addr = machine__get_running_kernel_start(machine, &name);
+	if (!addr) {
+	} else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 		machine__destroy_kernel_maps(machine);
 		return -1;
 	}
@@ -1769,11 +1771,6 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		 */
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
-		if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
-			pr_warning("corrupted callchain. skipping...\n");
-			return 0;
-		}
-
 		for (j = 0; j < mix_chain_nr; j++) {
 			if (callchain_param.order == ORDER_CALLEE) {
 				if (j < i + 1)
@@ -1813,7 +1810,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err, nr_entries, nr_contexts;
+	int i, j, err, nr_entries;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1828,8 +1825,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain_nr < sysctl_perf_event_max_stack)
-		skip_idx = arch_skip_callchain_idx(thread, chain);
+	skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
 	 * Add branches to call stack for easier browsing. This gives
@@ -1889,7 +1885,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	for (i = first_call, nr_entries = 0, nr_contexts = 0;
+	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
@@ -1904,13 +1900,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 #endif
 		ip = chain->ips[j];
 
-		if (ip >= PERF_CONTEXT_MAX) {
-			if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
-				goto out_corrupted_callchain;
-		} else {
-			if (++nr_entries > sysctl_perf_event_max_stack)
-				goto out_corrupted_callchain;
-		}
+		if (ip < PERF_CONTEXT_MAX)
+                       ++nr_entries;
 
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
@@ -1919,10 +1910,6 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 	return 0;
-
-out_corrupted_callchain:
-	pr_warning("corrupted callchain. skipping...\n");
-	return 0;
 }
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)

tools/perf/util/machine.h

@@ -28,6 +28,7 @@ struct machine {
 	pid_t		  pid;
 	u16		  id_hdr_size;
 	bool		  comm_exec;
+	bool		  kptr_restrict_warned;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	pthread_rwlock_t  threads_lock;

tools/perf/util/scripting-engines/trace-event-perl.c

@@ -264,8 +264,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 		goto exit;
 
 	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-				      sample, NULL, NULL,
-				      sysctl_perf_event_max_stack) != 0) {
+				      sample, NULL, NULL, scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}