Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Includes smaller fixes and improvements plus the exclude_{host,guest} feature
test and fallback to handle older kernels.

Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Ingo Molnar

tools/perf/Documentation/perf-record.txt

@@ -52,11 +52,11 @@ OPTIONS
 
 -p::
 --pid=::
-	Record events on existing process ID.
+	Record events on existing process ID (comma separated list).
 
 -t::
 --tid=::
-        Record events on existing thread ID.
+        Record events on existing thread ID (comma separated list).
 
 -u::
 --uid=::

tools/perf/Documentation/perf-stat.txt

@@ -35,11 +35,11 @@ OPTIONS
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing process id
+        stat events on existing process id (comma separated list)
 
 -t::
 --tid=<tid>::
-        stat events on existing thread id
+        stat events on existing thread id (comma separated list)
 
 
 -a::

tools/perf/Documentation/perf-top.txt

@@ -72,11 +72,11 @@ Default is to monitor all CPUS.
 
 -p <pid>::
 --pid=<pid>::
-	Profile events on existing Process ID.
+	Profile events on existing Process ID (comma separated list).
 
 -t <tid>::
 --tid=<tid>::
-        Profile events on existing thread ID.
+        Profile events on existing thread ID (comma separated list).
 
 -u::
 --uid=::

tools/perf/MANIFEST

@@ -9,6 +9,7 @@ lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/lib/memcpy*.S
+arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h

tools/perf/Makefile

@@ -183,7 +183,10 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
-$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
+
+$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
@@ -256,6 +259,7 @@ LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
+LIB_H += util/sysfs.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
@@ -302,6 +306,7 @@ LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
+LIB_OBJS += $(OUTPUT)util/sysfs.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o

tools/perf/builtin-record.c

@@ -205,8 +205,11 @@ static void perf_record__open(struct perf_record *rec)
 
 		if (opts->group && pos != first)
 			group_fd = first->fd;
+fallback_missing_features:
+		if (opts->exclude_guest_missing)
+			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-		attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+		attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
 				     opts->group, group_fd) < 0) {
@@ -218,15 +221,23 @@ static void perf_record__open(struct perf_record *rec)
 			} else if (err ==  ENODEV && opts->cpu_list) {
 				die("No such device - did you specify"
 					" an out-of-range profile CPU?\n");
-			} else if (err == EINVAL && opts->sample_id_all_avail) {
-				/*
-				 * Old kernel, no attr->sample_id_type_all field
-				 */
-				opts->sample_id_all_avail = false;
-				if (!opts->sample_time && !opts->raw_samples && !time_needed)
-					attr->sample_type &= ~PERF_SAMPLE_TIME;
-
-				goto retry_sample_id;
+			} else if (err == EINVAL) {
+				if (!opts->exclude_guest_missing &&
+				    (attr->exclude_guest || attr->exclude_host)) {
+					pr_debug("Old kernel, cannot exclude "
+						 "guest or host samples.\n");
+					opts->exclude_guest_missing = true;
+					goto fallback_missing_features;
+				} else if (!opts->sample_id_all_missing) {
+					/*
+					 * Old kernel, no attr->sample_id_type_all field
+					 */
+					opts->sample_id_all_missing = true;
+					if (!opts->sample_time && !opts->raw_samples && !time_needed)
+						attr->sample_type &= ~PERF_SAMPLE_TIME;
+
+					goto retry_sample_id;
+				}
 			}
 
 			/*
@@ -494,9 +505,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 			return err;
 	}
 
-	if (!!rec->no_buildid
+	if (!rec->no_buildid
 	    && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
-		pr_err("Couldn't generating buildids. "
+		pr_err("Couldn't generate buildids. "
 		       "Use --no-buildid to profile anyway.\n");
 		return -1;
 	}
@@ -645,13 +656,10 @@ static const char * const record_usage[] = {
  */
 static struct perf_record record = {
 	.opts = {
-		.target_pid	     = -1,
-		.target_tid	     = -1,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
 		.freq		     = 1000,
-		.sample_id_all_avail = true,
 	},
 	.write_mode = WRITE_FORCE,
 	.file_new   = true,
@@ -670,9 +678,9 @@ const struct option record_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
-	OPT_INTEGER('p', "pid", &record.opts.target_pid,
+	OPT_STRING('p', "pid", &record.opts.target_pid, "pid",
 		    "record events on existing process id"),
-	OPT_INTEGER('t', "tid", &record.opts.target_tid,
+	OPT_STRING('t', "tid", &record.opts.target_tid, "tid",
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &record.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
@@ -739,7 +747,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 &&
+	if (!argc && !rec->opts.target_pid && !rec->opts.target_tid &&
 		!rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str)
 		usage_with_options(record_usage, record_options);
 
@@ -785,7 +793,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 	if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1)
 		goto out_free_fd;
 
-	if (rec->opts.target_pid != -1)
+	if (rec->opts.target_pid)
 		rec->opts.target_tid = rec->opts.target_pid;
 
 	if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,

tools/perf/builtin-stat.c

@@ -182,8 +182,8 @@ static int			run_count			=  1;
 static bool			no_inherit			= false;
 static bool			scale				=  true;
 static bool			no_aggr				= false;
-static pid_t			target_pid			= -1;
-static pid_t			target_tid			= -1;
+static const char		*target_pid;
+static const char		*target_tid;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -296,7 +296,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (system_wide)
 		return perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
 						group, group_fd);
-	if (target_pid == -1 && target_tid == -1) {
+	if (!target_pid && !target_tid) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
@@ -446,7 +446,7 @@ static int run_perf_stat(int argc __used, const char **argv)
 			exit(-1);
 		}
 
-		if (target_tid == -1 && target_pid == -1 && !system_wide)
+		if (!target_tid && !target_pid && !system_wide)
 			evsel_list->threads->map[0] = child_pid;
 
 		/*
@@ -968,14 +968,14 @@ static void print_stat(int argc, const char **argv)
 	if (!csv_output) {
 		fprintf(output, "\n");
 		fprintf(output, " Performance counter stats for ");
-		if(target_pid == -1 && target_tid == -1) {
+		if (!target_pid && !target_tid) {
 			fprintf(output, "\'%s", argv[0]);
 			for (i = 1; i < argc; i++)
 				fprintf(output, " %s", argv[i]);
-		} else if (target_pid != -1)
-			fprintf(output, "process id \'%d", target_pid);
+		} else if (target_pid)
+			fprintf(output, "process id \'%s", target_pid);
 		else
-			fprintf(output, "thread id \'%d", target_tid);
+			fprintf(output, "thread id \'%s", target_tid);
 
 		fprintf(output, "\'");
 		if (run_count > 1)
@@ -1049,10 +1049,10 @@ static const struct option options[] = {
 		     "event filter", parse_filter),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
 		    "child tasks do not inherit counters"),
-	OPT_INTEGER('p', "pid", &target_pid,
-		    "stat events on existing process id"),
-	OPT_INTEGER('t', "tid", &target_tid,
-		    "stat events on existing thread id"),
+	OPT_STRING('p', "pid", &target_pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target_tid, "tid",
+		   "stat events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_BOOLEAN('g', "group", &group,
@@ -1190,7 +1190,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
-	if (!argc && target_pid == -1 && target_tid == -1)
+	if (!argc && !target_pid && !target_tid)
 		usage_with_options(stat_usage, options);
 	if (run_count <= 0)
 		usage_with_options(stat_usage, options);
@@ -1206,10 +1206,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	if (add_default_attributes())
 		goto out;
 
-	if (target_pid != -1)
+	if (target_pid)
 		target_tid = target_pid;
 
-	evsel_list->threads = thread_map__new(target_pid, target_tid, UINT_MAX);
+	evsel_list->threads = thread_map__new_str(target_pid,
+						  target_tid, UINT_MAX);
 	if (evsel_list->threads == NULL) {
 		pr_err("Problems finding threads of monitor\n");
 		usage_with_options(stat_usage, options);

tools/perf/builtin-test.c

@@ -1010,12 +1010,9 @@ static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t **maskp,
 static int test__PERF_RECORD(void)
 {
 	struct perf_record_opts opts = {
-		.target_pid = -1,
-		.target_tid = -1,
 		.no_delay   = true,
 		.freq	    = 10,
 		.mmap_pages = 256,
-		.sample_id_all_avail = true,
 	};
 	cpu_set_t *cpu_mask = NULL;
 	size_t cpu_mask_size = 0;

tools/perf/builtin-top.c

@@ -677,6 +677,12 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		return;
 	}
 
+	if (!machine) {
+		pr_err("%u unprocessable samples recorded.",
+		       top->session->hists.stats.nr_unprocessable_samples++);
+		return;
+	}
+
 	if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
 		top->exact_samples++;
 
@@ -866,8 +872,11 @@ static void perf_top__start_counters(struct perf_top *top)
 		attr->mmap = 1;
 		attr->comm = 1;
 		attr->inherit = top->inherit;
+fallback_missing_features:
+		if (top->exclude_guest_missing)
+			attr->exclude_guest = attr->exclude_host = 0;
 retry_sample_id:
-		attr->sample_id_all = top->sample_id_all_avail ? 1 : 0;
+		attr->sample_id_all = top->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads, top->group,
@@ -877,12 +886,20 @@ static void perf_top__start_counters(struct perf_top *top)
 			if (err == EPERM || err == EACCES) {
 				ui__error_paranoid();
 				goto out_err;
-			} else if (err == EINVAL && top->sample_id_all_avail) {
-				/*
-				 * Old kernel, no attr->sample_id_type_all field
-				 */
-				top->sample_id_all_avail = false;
-				goto retry_sample_id;
+			} else if (err == EINVAL) {
+				if (!top->exclude_guest_missing &&
+				    (attr->exclude_guest || attr->exclude_host)) {
+					pr_debug("Old kernel, cannot exclude "
+						 "guest or host samples.\n");
+					top->exclude_guest_missing = true;
+					goto fallback_missing_features;
+				} else if (!top->sample_id_all_missing) {
+					/*
+					 * Old kernel, no attr->sample_id_type_all field
+					 */
+					top->sample_id_all_missing = true;
+					goto retry_sample_id;
+				}
 			}
 			/*
 			 * If it's cycles then fall back to hrtimer
@@ -965,7 +982,7 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
-	if (top->target_tid != -1 || top->uid != UINT_MAX)
+	if (top->target_tid || top->uid != UINT_MAX)
 		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
 						  perf_event__process,
 						  &top->session->host_machine);
@@ -1103,11 +1120,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 	struct perf_top top = {
 		.count_filter	     = 5,
 		.delay_secs	     = 2,
-		.target_pid	     = -1,
-		.target_tid	     = -1,
 		.uid		     = UINT_MAX,
 		.freq		     = 1000, /* 1 KHz */
-		.sample_id_all_avail = true,
 		.mmap_pages	     = 128,
 		.sym_pcnt_filter     = 5,
 	};
@@ -1118,9 +1132,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		     parse_events_option),
 	OPT_INTEGER('c', "count", &top.default_interval,
 		    "event period to sample"),
-	OPT_INTEGER('p', "pid", &top.target_pid,
+	OPT_STRING('p', "pid", &top.target_pid, "pid",
 		    "profile events on existing process id"),
-	OPT_INTEGER('t', "tid", &top.target_tid,
+	OPT_STRING('t', "tid", &top.target_tid, "tid",
 		    "profile events on existing thread id"),
 	OPT_BOOLEAN('a', "all-cpus", &top.system_wide,
 			    "system-wide collection from all CPUs"),
@@ -1210,13 +1224,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 		goto out_delete_evlist;
 
 	/* CPU and PID are mutually exclusive */
-	if (top.target_tid > 0 && top.cpu_list) {
+	if (top.target_tid && top.cpu_list) {
 		printf("WARNING: PID switch overriding CPU\n");
 		sleep(1);
 		top.cpu_list = NULL;
 	}
 
-	if (top.target_pid != -1)
+	if (top.target_pid)
 		top.target_tid = top.target_pid;
 
 	if (perf_evlist__create_maps(top.evlist, top.target_pid,