perf/core improvements and fixes:

User visible:
 
 - 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:
 
 - 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)
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJVidGtAAoJENZQFvNTUqpA+9oP/0oyGi7AaY0TFBt0rOeT3sJD
 lN/+DAZtrMdjAWyxAx6v2pJnhWq79bA2/PAPb5W+SqEsY/QfLJMWegujj5oFzhD6
 yWxwhWNfYO72B/nChMeOmKf3ZRwuRoYDfTKldTAUoOKK6Zh4ANCYu1ycakj8QALU
 9E9UAelmSSSJAOCDb6PjtCxhqbUSKaaopMhZsadjThdQjVmpxhZGfjOMmPa2EAac
 2TT7KO62lQouOOLH+6OTDcXn3DVSPlNpccFqKe5yV2Z10ceiE41tZm0gGZdQOf5p
 IgsKFcTJvq3fVKZCIUhkyojObb4JBneOgjumdFxA8Rh08ljFro5dqxt9WaQR4h5D
 iaVP6x3HEpESpDkJ1W2rRmqdGwKsQKLhYgXjIy7cy16EhPtTaefmfTNFn8u/1aXO
 oF7xlkP1/uiNRHjx7pnhWPBjTn7SvUlU6ELOoiz6gI6Ix4RCs8tu06b0Dt2m19Tx
 C2chblxMf6YoUTTWpn0IcpQSKSnXWamGYEvWAuSxPbgXwNiitectTMEiTgXof51B
 CUo4LEnaTLZOiRyI/8t/CNvEReoP3/uJL/phV5lc5+YTyyHIN9g9zcRg9WFXSYTj
 TxEBlK4bmXkwyMpd6R3/Hqpilp/w1GBdxPga4I40E1noEKS1pk5GYiuk91oeSozi
 r1poumPYnT5TdVqSUR6N
 =0d3E
 -----END PGP SIGNATURE-----

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:

  - 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 changes:

  - 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)

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

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/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)  {
+	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
-		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+				      top->min_percent,
-							top->min_percent,
+				      &top->session->header.env);
-							&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;
-		}
-	}
 
 	done = 1;
 	return NULL;

tools/perf/builtin-trace.c

@@ -2325,7 +2325,7 @@ 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 +2343,7 @@ 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:

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/openat-syscall-tp-fields.c

@@ -45,7 +45,7 @@ int test__syscall_openat_tp_fields(void)
 
 	perf_evsel__config(evsel, &opts);
 
-	evlist->threads->map[0] = getpid();
+	thread_map__set_pid(evlist->threads, 0, getpid());
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {

tools/perf/ui/browsers/hists.c

@@ -1902,8 +1902,23 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case CTRL('c'):
 			goto out_free_stack;
 		case 'f':
-			if (!is_report_browser(hbt))
+			if (!is_report_browser(hbt)) {
-				goto out_free_stack;
+				struct perf_top *top = hbt->arg;
+
+				perf_evlist__toggle_enable(top->evlist);
+				/*
+				 * No need to refresh, resort/decay histogram
+				 * entries if we are not collecting samples:
+				 */
+				if (top->evlist->enabled) {
+					helpline = "Press 'f' to disable the events or 'h' to see other hotkeys";
+					hbt->refresh = delay_secs;
+				} else {
+					helpline = "Press 'f' again to re-enable the events";
+					hbt->refresh = 0;
+				}
+				continue;
+			}
 			/* Fall thru */
 		default:
 			helpline = "Press '?' for help on key bindings";

tools/perf/util/auxtrace.c

@@ -119,12 +119,12 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 	if (per_cpu) {
 		mp->cpu = evlist->cpus->map[idx];
 		if (evlist->threads)
-			mp->tid = evlist->threads->map[0];
+			mp->tid = thread_map__pid(evlist->threads, 0);
 		else
 			mp->tid = -1;
 	} else {
 		mp->cpu = -1;
-		mp->tid = evlist->threads->map[idx];
+		mp->tid = thread_map__pid(evlist->threads, idx);
 	}
 }
 
@@ -1182,6 +1182,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 		data2 = NULL;
 	}
 
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
 	padding = size & 7;
 	if (padding)

tools/perf/util/auxtrace.h

@@ -303,6 +303,7 @@ struct auxtrace_record {
 				      const char *str);
 	u64 (*reference)(struct auxtrace_record *itr);
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
 };
 
 #ifdef HAVE_AUXTRACE_SUPPORT

tools/perf/util/event.c

@@ -504,7 +504,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
 					       fork_event,
-					       threads->map[thread], 0,
+					       thread_map__pid(threads, thread), 0,
 					       process, tool, machine,
 					       mmap_data, proc_map_timeout)) {
 			err = -1;
@@ -515,12 +515,12 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 		 * comm.pid is set to thread group id by
 		 * perf_event__synthesize_comm
 		 */
-		if ((int) comm_event->comm.pid != threads->map[thread]) {
+		if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
 			bool need_leader = true;
 
 			/* is thread group leader in thread_map? */
 			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == threads->map[j]) {
+				if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
 					need_leader = false;
 					break;
 				}

tools/perf/util/evlist.c

@@ -548,7 +548,7 @@ static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
 	else
 		sid->cpu = -1;
 	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = evlist->threads->map[thread];
+		sid->tid = thread_map__pid(evlist->threads, thread);
 	else
 		sid->tid = -1;
 }
@@ -1475,7 +1475,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 				__func__, __LINE__);
 			goto out_close_pipes;
 		}
-		evlist->threads->map[0] = evlist->workload.pid;
+		thread_map__set_pid(evlist->threads, 0, evlist->workload.pid);
 	}
 
 	close(child_ready_pipe[1]);

tools/perf/util/evsel.c

@@ -1167,7 +1167,7 @@ retry_sample_id:
 			int group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
-				pid = threads->map[thread];
+				pid = thread_map__pid(threads, thread);
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:

tools/perf/util/parse-events.l

@@ -119,8 +119,8 @@ event		[^,{}/]+
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?]*
+name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -165,7 +165,6 @@ modifier_bp	[rwx]{1,3}
 			return PE_EVENT_NAME;
 		}
 
-.		|
 <<EOF>>		{
 			BEGIN(INITIAL);
 			REWIND(0);

tools/perf/util/pmu.c

@@ -1,4 +1,5 @@
 #include <linux/list.h>
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
@@ -205,17 +206,12 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
+				 char *desc __maybe_unused, char *val)
 {
 	struct perf_pmu_alias *alias;
-	char buf[256];
 	int ret;
 
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-	buf[ret] = 0;
-
 	alias = malloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
@@ -225,26 +221,43 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
 
-	ret = parse_events_terms(&alias->terms, buf);
+	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
+		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
 	alias->name = strdup(name);
-	/*
+	if (dir) {
-	 * load unit name and scale if available
+		/*
-	 */
+		 * load unit name and scale if available
-	perf_pmu__parse_unit(alias, dir, name);
+		 */
-	perf_pmu__parse_scale(alias, dir, name);
+		perf_pmu__parse_unit(alias, dir, name);
-	perf_pmu__parse_per_pkg(alias, dir, name);
+		perf_pmu__parse_scale(alias, dir, name);
-	perf_pmu__parse_snapshot(alias, dir, name);
+		perf_pmu__parse_per_pkg(alias, dir, name);
+		perf_pmu__parse_snapshot(alias, dir, name);
+	}
 
 	list_add_tail(&alias->list, list);
 
 	return 0;
 }
 
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
+{
+	char buf[256];
+	int ret;
+
+	ret = fread(buf, 1, sizeof(buf), file);
+	if (ret == 0)
+		return -EINVAL;
+
+	buf[ret] = 0;
+
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf);
+}
+
 static inline bool pmu_alias_info_file(char *name)
 {
 	size_t len;
@@ -436,7 +449,7 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
-struct perf_event_attr *__attribute__((weak))
+struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
 	return NULL;

tools/perf/util/probe-event.c

@@ -249,8 +249,12 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 static bool kprobe_blacklist__listed(unsigned long address);
 static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 {
+	u64 etext_addr;
+
 	/* Get the address of _etext for checking non-probable text symbol */
-	if (kernel_get_symbol_address_by_name("_etext", false) < address)
+	etext_addr = kernel_get_symbol_address_by_name("_etext", false);
+
+	if (etext_addr != 0 && etext_addr < address)
 		pr_warning("%s is out of .text, skip it.\n", symbol);
 	else if (kprobe_blacklist__listed(address))
 		pr_warning("%s is blacklisted function, skip it.\n", symbol);

tools/perf/util/session.c

@@ -686,6 +686,8 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused,
 				  union perf_event *event __maybe_unused,
 				  struct ordered_events *oe)
 {
+	if (dump_trace)
+		fprintf(stdout, "\n");
 	return ordered_events__flush(oe, OE_FLUSH__ROUND);
 }
 
@@ -1726,7 +1728,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
 		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
 
-	ret = fprintf(fp, "Aggregated stats:%s\n", msg);
+	ret = fprintf(fp, "\nAggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;

tools/perf/util/thread_map.c

@@ -45,7 +45,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
 	}
 
@@ -61,8 +61,8 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0] = tid;
+		thread_map__set_pid(threads, 0, tid);
-		threads->nr	= 1;
+		threads->nr = 1;
 	}
 
 	return threads;
@@ -123,8 +123,10 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 			threads = tmp;
 		}
 
-		for (i = 0; i < items; i++)
+		for (i = 0; i < items; i++) {
-			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, threads->nr + i,
+					    atoi(namelist[i]->d_name));
+		}
 
 		for (i = 0; i < items; i++)
 			zfree(&namelist[i]);
@@ -201,7 +203,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			threads->map[j++] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -227,8 +229,8 @@ struct thread_map *thread_map__new_dummy(void)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0]	= -1;
+		thread_map__set_pid(threads, 0, -1);
-		threads->nr	= 1;
+		threads->nr = 1;
 	}
 	return threads;
 }
@@ -267,8 +269,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			goto out_free_threads;
 
 		threads = nt;
-		threads->map[ntasks - 1] = tid;
+		thread_map__set_pid(threads, ntasks - 1, tid);
-		threads->nr		 = ntasks;
+		threads->nr = ntasks;
 	}
 out:
 	return threads;
@@ -301,7 +303,7 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }

tools/perf/util/thread_map.h

@@ -4,9 +4,13 @@
 #include <sys/types.h>
 #include <stdio.h>
 
+struct thread_map_data {
+	pid_t    pid;
+};
+
 struct thread_map {
 	int nr;
-	pid_t map[];
+	struct thread_map_data map[];
 };
 
 struct thread_map *thread_map__new_dummy(void);
@@ -27,4 +31,14 @@ static inline int thread_map__nr(struct thread_map *threads)
 	return threads ? threads->nr : 1;
 }
 
+static inline pid_t thread_map__pid(struct thread_map *map, int thread)
+{
+	return map->map[thread].pid;
+}
+
+static inline void
+thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
+{
+	map->map[thread].pid = pid;
+}
 #endif	/* __PERF_THREAD_MAP_H */