Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "This tree includes an x86 PMU scheduling fix, but most changes are
  late breaking tooling fixes and updates:

  User visible fixes:

   - Create config.detected into OUTPUT directory, fixing parallel
     builds sharing the same source directory (Aaro Kiskinen)

   - Allow to specify custom linker command, fixing some MIPS64 builds.
     (Aaro Kiskinen)

   - Fix to show proper convergence stats in 'perf bench numa' (Srikar
     Dronamraju)

  User visible changes:

   - Validate syscall list passed via -e argument to 'perf trace'.
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf stat --per-thread' (Jiri Olsa)

   - Check access permission for --kallsyms and --vmlinux (Li Zhang)

   - Move toggling event logic from 'perf top' and into hists browser,
     allowing freeze/unfreeze with event lists with more than one entry
     (Namhyung Kim)

   - Add missing newlines when dumping PERF_RECORD_FINISHED_ROUND and
     showing the Aggregated stats in 'perf report -D' (Adrian Hunter)

  Infrastructure fixes:

   - Add missing break for PERF_RECORD_ITRACE_START, which caused those
     events samples to be parsed as well as PERF_RECORD_LOST_SAMPLES.
     ITRACE_START only appears when Intel PT or BTS are present, so..
     (Jiri Olsa)

   - Call the perf_session destructor when bailing out in the inject,
     kmem, report, kvm and mem tools (Taeung Song)

  Infrastructure changes:

   - Move stuff out of 'perf stat' and into the lib for further use
     (Jiri Olsa)

   - Reference count the cpu_map and thread_map classes (Jiri Olsa)

   - Set evsel->{cpus,threads} from the evlist, if not set, allowing the
     generalization of some 'perf stat' functions that previously were
     accessing private static evlist variable (Jiri Olsa)

   - Delete an unnecessary check before the calling free_event_desc()
     (Markus Elfring)

   - Allow auxtrace data alignment (Adrian Hunter)

   - Allow events with dot (Andi Kleen)

   - Fix failure to 'perf probe' events on arm (He Kuang)

   - Add testing for Makefile.perf (Jiri Olsa)

   - Add test for make install with prefix (Jiri Olsa)

   - Fix single target build dependency check (Jiri Olsa)

   - Access thread_map entries via accessors, prep patch to hold more
     info per entry, for ongoing 'perf stat --per-thread' work (Jiri
     Olsa)

   - Use __weak definition from compiler.h (Sukadev Bhattiprolu)

   - Split perf_pmu__new_alias() (Sukadev Bhattiprolu)"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  perf tools: Allow to specify custom linker command
  perf tools: Create config.detected into OUTPUT directory
  perf mem: Fill in the missing session freeing after an error occurs
  perf kvm: Fill in the missing session freeing after an error occurs
  perf report: Fill in the missing session freeing after an error occurs
  perf kmem: Fill in the missing session freeing after an error occurs
  perf inject: Fill in the missing session freeing after an error occurs
  perf tools: Add missing break for PERF_RECORD_ITRACE_START
  perf/x86: Fix 'active_events' imbalance
  perf symbols: Check access permission when reading symbol files
  perf stat: Introduce --per-thread option
  perf stat: Introduce print_counters function
  perf stat: Using init_stats instead of memset
  perf stat: Rename print_interval to process_interval
  perf stat: Remove perf_evsel__read_cb function
  perf stat: Move perf_stat initialization counter process code
  perf stat: Move zero_per_pkg into counter process code
  perf stat: Separate counters reading and processing
  perf stat: Introduce read_counters function
  perf stat: Introduce perf_evsel__read function
  ...

tools/build/Makefile.build

@@ -25,7 +25,7 @@ build-dir := $(srctree)/tools/build
 include $(build-dir)/Build.include
 
 # do not force detected configuration
--include .config-detected
+-include $(OUTPUT).config-detected
 
 # Init all relevant variables used in build files so
 # 1) they have correct type

tools/perf/Documentation/perf-stat.txt

@@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to

tools/perf/Makefile

@@ -83,8 +83,8 @@ build-test:
 #
 # All other targets get passed through:
 #
-%:
+%: FORCE
 	$(print_msg)
 	$(make)
 
-.PHONY: tags TAGS
+.PHONY: tags TAGS FORCE Makefile

tools/perf/Makefile.perf

@@ -110,7 +110,7 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
 CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
+LD ?= $(CROSS_COMPILE)ld
 AR = $(CROSS_COMPILE)ar
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
@@ -545,7 +545,7 @@ config-clean:
 clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
-	$(Q)$(RM) .config-detected
+	$(Q)$(RM) $(OUTPUT).config-detected
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean

tools/perf/builtin-inject.c

@@ -630,12 +630,13 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (inject.session == NULL)
 		return -1;
 
-	if (symbol__init(&inject.session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&inject.session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	ret = __cmd_inject(&inject);
 
+out_delete:
 	perf_session__delete(inject.session);
-
 	return ret;
 }

tools/perf/builtin-kmem.c

@@ -1916,7 +1916,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
 							  "kmem:kmalloc")) {
 			pr_err(errmsg, "slab", "slab");
-			return -1;
+			goto out_delete;
 		}
 	}
 
@@ -1927,7 +1927,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 							     "kmem:mm_page_alloc");
 		if (evsel == NULL) {
 			pr_err(errmsg, "page", "page");
-			return -1;
+			goto out_delete;
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);

tools/perf/builtin-kvm.c

@@ -1061,8 +1061,10 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 	symbol__init(&kvm->session->header.env);
 
-	if (!perf_session__has_traces(kvm->session, "kvm record"))
-		return -EINVAL;
+	if (!perf_session__has_traces(kvm->session, "kvm record")) {
+		ret = -EINVAL;
+		goto out_delete;
+	}
 
 	/*
 	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
@@ -1070,9 +1072,13 @@ static int read_events(struct perf_kvm_stat *kvm)
 	 */
 	ret = cpu_isa_config(kvm);
 	if (ret < 0)
-		return ret;
+		goto out_delete;
 
-	return perf_session__process_events(kvm->session);
+	ret = perf_session__process_events(kvm->session);
+
+out_delete:
+	perf_session__delete(kvm->session);
+	return ret;
 }
 
 static int parse_target_str(struct perf_kvm_stat *kvm)

tools/perf/builtin-mem.c

@@ -124,7 +124,6 @@ static int report_raw_events(struct perf_mem *mem)
 		.mode = PERF_DATA_MODE_READ,
 		.force = mem->force,
 	};
-	int err = -EINVAL;
 	int ret;
 	struct perf_session *session = perf_session__new(&file, false,
 							 &mem->tool);
@@ -135,24 +134,21 @@ static int report_raw_events(struct perf_mem *mem)
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
-		if (ret)
+		if (ret < 0)
 			goto out_delete;
 	}
 
-	if (symbol__init(&session->header.env) < 0)
-		return -1;
+	ret = symbol__init(&session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
-	err = perf_session__process_events(session);
-	if (err)
-		return err;
-
-	return 0;
+	ret = perf_session__process_events(session);
 
 out_delete:
 	perf_session__delete(session);
-	return err;
+	return ret;
 }
 
 static int report_events(int argc, const char **argv, struct perf_mem *mem)

tools/perf/builtin-report.c

@@ -742,6 +742,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (symbol_conf.vmlinux_name &&
+	    access(symbol_conf.vmlinux_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
+		return -EINVAL;
+	}
+	if (symbol_conf.kallsyms_name &&
+	    access(symbol_conf.kallsyms_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
+		return -EINVAL;
+	}
+
 	if (report.use_stdio)
 		use_browser = 0;
 	else if (report.use_tui)
@@ -828,8 +839,10 @@ repeat:
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
-		if (report.header_only)
-			return 0;
+		if (report.header_only) {
+			ret = 0;
+			goto error;
+		}
 	} else if (use_browser == 0) {
 		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
 		      stdout);

tools/perf/builtin-top.c

@@ -586,27 +586,9 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	while (true)  {
-		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
-							top->min_percent,
-							&top->session->header.env);
-
-		if (key != 'f')
-			break;
-
-		perf_evlist__toggle_enable(top->evlist);
-		/*
-		 * No need to refresh, resort/decay histogram entries
-		 * if we are not collecting samples:
-		 */
-		if (top->evlist->enabled) {
-			hbt.refresh = top->delay_secs;
-			help = "Press 'f' to disable the events or 'h' to see other hotkeys";
-		} else {
-			help = "Press 'f' again to re-enable the events";
-			hbt.refresh = 0;
-		}
-	}
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+				      top->min_percent,
+				      &top->session->header.env);
 
 	done = 1;
 	return NULL;

tools/perf/builtin-trace.c

@@ -1617,6 +1617,34 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	return syscall__set_arg_fmts(sc);
 }
 
+static int trace__validate_ev_qualifier(struct trace *trace)
+{
+	int err = 0;
+	struct str_node *pos;
+
+	strlist__for_each(pos, trace->ev_qualifier) {
+		const char *sc = pos->s;
+
+		if (audit_name_to_syscall(sc, trace->audit.machine) < 0) {
+			if (err == 0) {
+				fputs("Error:\tInvalid syscall ", trace->output);
+				err = -EINVAL;
+			} else {
+				fputs(", ", trace->output);
+			}
+
+			fputs(sc, trace->output);
+		}
+	}
+
+	if (err < 0) {
+		fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
+		      "\nHint:\tand: 'man syscalls'\n", trace->output);
+	}
+
+	return err;
+}
+
 /*
  * args is to be interpreted as a series of longs but we need to handle
  * 8-byte unaligned accesses. args points to raw_data within the event
@@ -2325,7 +2353,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	 */
 	if (trace->filter_pids.nr > 0)
 		err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
-	else if (evlist->threads->map[0] == -1)
+	else if (thread_map__pid(evlist->threads, 0) == -1)
 		err = perf_evlist__set_filter_pid(evlist, getpid());
 
 	if (err < 0) {
@@ -2343,7 +2371,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (forks)
 		perf_evlist__start_workload(evlist);
 
-	trace->multiple_threads = evlist->threads->map[0] == -1 ||
+	trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
 				  evlist->threads->nr > 1 ||
 				  perf_evlist__first(evlist)->attr.inherit;
 again:
@@ -2862,6 +2890,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			err = -ENOMEM;
 			goto out_close;
 		}
+
+		err = trace__validate_ev_qualifier(&trace);
+		if (err)
+			goto out_close;
 	}
 
 	err = target__validate(&trace.opts.target);

tools/perf/config/Makefile

@@ -11,9 +11,9 @@ ifneq ($(obj-perf),)
 obj-perf := $(abspath $(obj-perf))/
 endif
 
-$(shell echo -n > .config-detected)
-detected     = $(shell echo "$(1)=y"       >> .config-detected)
-detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected)
+$(shell echo -n > $(OUTPUT).config-detected)
+detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
+detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 

tools/perf/tests/Build

@@ -31,6 +31,7 @@ perf-y += code-reading.o
 perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
+perf-y += thread-map.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 

tools/perf/tests/builtin-test.c

@@ -170,6 +170,10 @@ static struct test {
 		.desc = "Test kmod_path__parse function",
 		.func = test__kmod_path__parse,
 	},
+	{
+		.desc = "Test thread map",
+		.func = test__thread_map,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/tests/code-reading.c

@@ -545,8 +545,8 @@ out_err:
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);

tools/perf/tests/keep-tracking.c

@@ -144,8 +144,8 @@ out_err:
 		perf_evlist__disable(evlist);
 		perf_evlist__delete(evlist);
 	} else {
-		cpu_map__delete(cpus);
-		thread_map__delete(threads);
+		cpu_map__put(cpus);
+		thread_map__put(threads);
 	}
 
 	return err;

tools/perf/tests/make

@@ -1,5 +1,16 @@
+ifndef MK
+ifeq ($(MAKECMDGOALS),)
+# no target specified, trigger the whole suite
+all:
+	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile
+	@echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf
+else
+# run only specific test over 'Makefile'
+%:
+	@echo "Testing Makefile";      $(MAKE) -sf tests/make MK=Makefile $@
+endif
+else
 PERF := .
-MK   := Makefile
 
 include config/Makefile.arch
 
@@ -47,6 +58,7 @@ make_install_man    := install-man
 make_install_html   := install-html
 make_install_info   := install-info
 make_install_pdf    := install-pdf
+make_install_prefix := install prefix=/tmp/krava
 make_static         := LDFLAGS=-static
 
 # all the NO_* variable combined
@@ -57,7 +69,12 @@ make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
 
 # $(run) contains all available tests
 run := make_pure
+# Targets 'clean all' can be run together only through top level
+# Makefile because we detect clean target in Makefile.perf and
+# disable features detection
+ifeq ($(MK),Makefile)
 run += make_clean_all
+endif
 run += make_python_perf_so
 run += make_debug
 run += make_no_libperl
@@ -83,6 +100,7 @@ run += make_util_map_o
 run += make_util_pmu_bison_o
 run += make_install
 run += make_install_bin
+run += make_install_prefix
 # FIXME 'install-*' commented out till they're fixed
 # run += make_install_doc
 # run += make_install_man
@@ -157,6 +175,12 @@ test_make_install_O     := $(call test_dest_files,$(installed_files_all))
 test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
 test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
 
+# We prefix all installed files for make_install_prefix
+# with '/tmp/krava' to match installed/prefix-ed files.
+installed_files_all_prefix := $(addprefix /tmp/krava/,$(installed_files_all))
+test_make_install_prefix   := $(call test_dest_files,$(installed_files_all_prefix))
+test_make_install_prefix_O := $(call test_dest_files,$(installed_files_all_prefix))
+
 # FIXME nothing gets installed
 test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
 test_make_install_man_O  := $(test_make_install_man)
@@ -226,13 +250,13 @@ tarpkg:
 	( eval $$cmd ) >> $@ 2>&1
 
 make_kernelsrc:
-	@echo " - make -C <kernelsrc> tools/perf"
+	@echo "- make -C <kernelsrc> tools/perf"
 	$(call clean); \
 	(make -C ../.. tools/perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
 
 make_kernelsrc_tools:
-	@echo " - make -C <kernelsrc>/tools perf"
+	@echo "- make -C <kernelsrc>/tools perf"
 	$(call clean); \
 	(make -C ../../tools perf) > $@ 2>&1 && \
 	test -x perf && rm -f $@ || (cat $@ ; false)
@@ -244,3 +268,4 @@ out: $(run_O)
 	@echo OK
 
 .PHONY: all $(run) $(run_O) tarpkg clean
+endif # ifndef MK

tools/perf/tests/mmap-basic.c

@@ -140,8 +140,8 @@ out_delete_evlist:
 	cpus	= NULL;
 	threads = NULL;
 out_free_cpus:
-	cpu_map__delete(cpus);
+	cpu_map__put(cpus);
 out_free_threads:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }

tools/perf/tests/mmap-thread-lookup.c

@@ -143,7 +143,7 @@ static int synth_process(struct machine *machine)
 						perf_event__process,
 						machine, 0, 500);
 
-	thread_map__delete(map);
+	thread_map__put(map);
 	return err;
 }