Merge tag 'perf-core-for-mingo' of...

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:

. Fix some leaks in exit paths.

. Use memdup where applicable

. Remove some die() calls, allowing callers to handle exit paths
  gracefully.

. Correct typo in tools Makefile, fix from Borislav Petkov.

. Add 'perf bench numa mem' NUMA performance measurement suite, from Ingo Molnar.

. Handle dynamic array's element size properly, fix from Jiri Olsa.

. Fix memory leaks on evsel->counts, from Namhyung Kim.

. Make numa benchmark optional, allowing the build in machines where required
  numa libraries are not present, fix from Peter Hurley.

. Add interval printing in 'perf stat', from Stephane Eranian.

. Fix compile warnings in tests/attr.c, from Sukadev Bhattiprolu.

. Fix double free, pclose instead of fclose, leaks and double fclose errors
  found with the cppcheck tool, from Thomas Jarosch.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

tools/Makefile

@@ -15,7 +15,7 @@ help:
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
 	@echo ''
 	@echo 'You can do:'
-	@echo ' $$ make -C tools/<tool>_install'
+	@echo ' $$ make -C tools/ <tool>_install'
 	@echo ''
 	@echo '  from the kernel command line to build and install one of'
 	@echo '  the tools above'

tools/lib/traceevent/event-parse.c

@@ -1223,6 +1223,34 @@ static int field_is_long(struct format_field *field)
 	return 0;
 }
 
+static unsigned int type_size(const char *name)
+{
+	/* This covers all FIELD_IS_STRING types. */
+	static struct {
+		const char *type;
+		unsigned int size;
+	} table[] = {
+		{ "u8",   1 },
+		{ "u16",  2 },
+		{ "u32",  4 },
+		{ "u64",  8 },
+		{ "s8",   1 },
+		{ "s16",  2 },
+		{ "s32",  4 },
+		{ "s64",  8 },
+		{ "char", 1 },
+		{ },
+	};
+	int i;
+
+	for (i = 0; table[i].type; i++) {
+		if (!strcmp(table[i].type, name))
+			return table[i].size;
+	}
+
+	return 0;
+}
+
 static int event_read_fields(struct event_format *event, struct format_field **fields)
 {
 	struct format_field *field = NULL;
@@ -1232,6 +1260,8 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 	int count = 0;
 
 	do {
+		unsigned int size_dynamic = 0;
+
 		type = read_token(&token);
 		if (type == EVENT_NEWLINE) {
 			free_token(token);
@@ -1390,6 +1420,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				field->type = new_type;
 				strcat(field->type, " ");
 				strcat(field->type, field->name);
+				size_dynamic = type_size(field->name);
 				free_token(field->name);
 				strcat(field->type, brackets);
 				field->name = token;
@@ -1478,10 +1509,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		if (field->flags & FIELD_IS_ARRAY) {
 			if (field->arraylen)
 				field->elementsize = field->size / field->arraylen;
+			else if (field->flags & FIELD_IS_DYNAMIC)
+				field->elementsize = size_dynamic;
 			else if (field->flags & FIELD_IS_STRING)
 				field->elementsize = 1;
-			else
-				field->elementsize = event->pevent->long_size;
+			else if (field->flags & FIELD_IS_LONG)
+				field->elementsize = event->pevent ?
+						     event->pevent->long_size :
+						     sizeof(long);
 		} else
 			field->elementsize = field->size;
 

tools/perf/Documentation/perf-stat.txt

@@ -114,6 +114,10 @@ with it.  --append may be used here.  Examples:
 
 perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
 
+-I msecs::
+--interval-print msecs::
+	print count deltas every N milliseconds (minimum: 100ms)
+	example: perf stat -I 1000 -e cycles -a sleep 5
 
 EXAMPLES
 --------

tools/perf/Makefile

@@ -47,6 +47,8 @@ include config/utilities.mak
 # backtrace post unwind.
 #
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
+#
+# Define NO_LIBNUMA if you do not want numa perf benchmark
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -838,6 +840,17 @@ ifndef NO_BACKTRACE
        endif
 endif
 
+ifndef NO_LIBNUMA
+	FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma
+	ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+		msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+	else
+		BASIC_CFLAGS += -DLIBNUMA_SUPPORT
+		BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+		EXTLIBS += -lnuma
+	endif
+endif
+
 ifdef ASCIIDOC8
 	export ASCIIDOC8
 endif

tools/perf/arch/common.c

@@ -155,6 +155,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 		if (lookup_path(buf))
 			goto out;
 		free(buf);
+		buf = NULL;
 	}
 
 	if (!strcmp(arch, "arm"))

tools/perf/bench/bench.h

 #ifndef BENCH_H
 #define BENCH_H
 
+extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv,

tools/perf/builtin-bench.c

@@ -35,6 +35,18 @@ struct bench_suite {
 /* sentinel: easy for help */
 #define suite_all { "all", "Test all benchmark suites", NULL }
 
+#ifdef LIBNUMA_SUPPORT
+static struct bench_suite numa_suites[] = {
+	{ "mem",
+	  "Benchmark for NUMA workloads",
+	  bench_numa },
+	suite_all,
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+#endif
+
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
 	  "Benchmark for scheduler and IPC mechanisms",
@@ -68,6 +80,11 @@ struct bench_subsys {
 };
 
 static struct bench_subsys subsystems[] = {
+#ifdef LIBNUMA_SUPPORT
+	{ "numa",
+	  "NUMA scheduling and MM behavior",
+	  numa_suites },
+#endif
 	{ "sched",
 	  "scheduler and IPC mechanism",
 	  sched_suites },

tools/perf/builtin-kmem.c

@@ -17,6 +17,7 @@
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
+#include <linux/string.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
@@ -618,12 +619,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = malloc(sizeof(*sort));
+			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
 			if (!sort) {
-				pr_err("%s: malloc failed\n", __func__);
+				pr_err("%s: memdup failed\n", __func__);
 				return -1;
 			}
-			memcpy(sort, avail_sorts[i], sizeof(*sort));
 			list_add_tail(&sort->list, list);
 			return 0;
 		}

tools/perf/builtin-stat.c

@@ -65,6 +65,10 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
+static void print_stat(int argc, const char **argv);
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
+static void print_counter(struct perf_evsel *counter, char *prefix);
+
 static struct perf_evlist	*evsel_list;
 
 static struct perf_target	target = {
@@ -87,6 +91,8 @@ static FILE			*output				= NULL;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
+static unsigned int		interval			= 0;
+static struct timespec		ref_time;
 
 static volatile int done = 0;
 
@@ -94,6 +100,28 @@ struct perf_stat {
 	struct stats	  res_stats[3];
 };
 
+static inline void diff_timespec(struct timespec *r, struct timespec *a,
+				 struct timespec *b)
+{
+	r->tv_sec = a->tv_sec - b->tv_sec;
+	if (a->tv_nsec < b->tv_nsec) {
+		r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
+		r->tv_sec--;
+	} else {
+		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
+	}
+}
+
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
@@ -106,14 +134,27 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 	evsel->priv = NULL;
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+	void *addr;
+	size_t sz;
+
+	sz = sizeof(*evsel->counts) +
+	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+
+	addr = zalloc(sz);
+	if (!addr)
+		return -ENOMEM;
+
+	evsel->prev_raw_counts =  addr;
+
+	return 0;
 }
 
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return perf_evsel__cpus(evsel)->nr;
+	free(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
 }
 
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
@@ -245,16 +286,69 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
+static void print_interval(void)
+{
+	static int num_print_interval;
+	struct perf_evsel *counter;
+	struct perf_stat *ps;
+	struct timespec ts, rs;
+	char prefix[64];
+
+	if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter(counter);
+		}
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter_aggr(counter);
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		if (no_aggr)
+			fprintf(output, "#           time CPU                 counts events\n");
+		else
+			fprintf(output, "#           time             counts events\n");
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+
+	if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter(counter, prefix);
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter_aggr(counter, prefix);
+	}
+}
+
 static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 {
 	char msg[512];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
+	struct timespec ts;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
 	char buf;
 
+	if (interval) {
+		ts.tv_sec  = interval / 1000;
+		ts.tv_nsec = (interval % 1000) * 1000000;
+	} else {
+		ts.tv_sec  = 1;
+		ts.tv_nsec = 0;
+	}
+
 	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
 		return -1;
@@ -347,14 +441,25 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 	 * Enable counters and exec the command:
 	 */
 	t0 = rdclock();
+	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
 		close(go_pipe[1]);
+		if (interval) {
+			while (!waitpid(child_pid, &status, WNOHANG)) {
+				nanosleep(&ts, NULL);
+				print_interval();
+			}
+		}
 		wait(&status);
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
-		while(!done) sleep(1);
+		while (!done) {
+			nanosleep(&ts, NULL);
+			if (interval)
+				print_interval();
+		}
 	}
 
 	t1 = rdclock();
@@ -440,7 +545,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
@@ -654,12 +759,11 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[cpu]);
-
 		if (total)
 			ratio = avg / total;
 
@@ -753,12 +857,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
  */
-static void print_counter_aggr(struct perf_evsel *counter)
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	struct perf_stat *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
 
+	if (prefix)
+		fprintf(output, "%s", prefix);
+
 	if (scaled == -1) {
 		fprintf(output, "%*s%s%*s",
 			csv_output ? 0 : 18,
@@ -801,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
  */
-static void print_counter(struct perf_evsel *counter)
+static void print_counter(struct perf_evsel *counter, char *prefix)
 {
 	u64 ena, run, val;
 	int cpu;
@@ -810,6 +917,10 @@ static void print_counter(struct perf_evsel *counter)
 		val = counter->counts->cpu[cpu].val;
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
 		if (run == 0 || ena == 0) {
 			fprintf(output, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
@@ -871,10 +982,10 @@ static void print_stat(int argc, const char **argv)
 
 	if (no_aggr) {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter(counter);
+			print_counter(counter, NULL);
 	} else {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter_aggr(counter);
+			print_counter_aggr(counter, NULL);
 	}
 
 	if (!csv_output) {
@@ -895,7 +1006,7 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
-	if(child_pid == -1)
+	if ((child_pid == -1) || interval)
 		done = 1;
 
 	signr = signo;
@@ -1115,6 +1226,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 			"command to run prior to the measured command"),
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &interval,
+		    "print counts at regular interval in ms (>= 100)"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
@@ -1215,12 +1328,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(stat_usage, options);
 		return -1;
 	}
+	if (interval && interval < 100) {
+		pr_err("print interval must be >= 100ms\n");
+		usage_with_options(stat_usage, options);
+		return -1;
+	}
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
 		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
 		    perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)
 			goto out_free_fd;
 	}
+	if (interval) {
+		list_for_each_entry(pos, &evsel_list->entries, node) {
+			if (perf_evsel__alloc_prev_raw_counts(pos) < 0)
+				goto out_free_fd;
+		}
+	}
 
 	/*
 	 * We dont want to block the signals - that would cause
@@ -1230,6 +1354,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	 */
 	atexit(sig_atexit);
 	signal(SIGINT,  skip_signal);
+	signal(SIGCHLD, skip_signal);
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
@@ -1242,11 +1367,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		status = run_perf_stat(argc, argv);
 	}
 
-	if (status != -1)
+	if (status != -1 && !interval)
 		print_stat(argc, argv);
 out_free_fd:
-	list_for_each_entry(pos, &evsel_list->entries, node)
+	list_for_each_entry(pos, &evsel_list->entries, node) {
 		perf_evsel__free_stat_priv(pos);
+		perf_evsel__free_counts(pos);
+		perf_evsel__free_prev_raw_counts(pos);
+	}
 	perf_evlist__delete_maps(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);

tools/perf/config/feature-tests.mak

@@ -225,3 +225,14 @@ int main(void)
 	return on_exit(NULL, NULL);
 }
 endef
+
+define SOURCE_LIBNUMA
+#include <numa.h>
+#include <numaif.h>
+
+int main(void)
+{
+	numa_available();
+	return 0;
+}
+endef
\ No newline at end of file

tools/perf/tests/attr.c

@@ -19,6 +19,11 @@
  * permissions. All the event text files are stored there.
  */
 
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
 #include <inttypes.h>

tools/perf/tests/open-syscall-all-cpus.c

@@ -98,6 +98,7 @@ int test__open_syscall_event_on_all_cpus(void)
 		}
 	}
 
+	perf_evsel__free_counts(evsel);
 out_close_fd:
 	perf_evsel__close_fd(evsel, 1, threads->nr);
 out_evsel_delete:

tools/perf/tests/perf-record.c

@@ -96,7 +96,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__prepare_workload(evlist, &opts, argv);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -111,7 +111,7 @@ int test__PERF_RECORD(void)
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	cpu = err;
@@ -121,7 +121,7 @@ int test__PERF_RECORD(void)
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -131,7 +131,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -142,7 +142,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -305,6 +305,8 @@ int test__PERF_RECORD(void)
 	}
 out_err:
 	perf_evlist__munmap(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:

tools/perf/tests/vmlinux-kallsyms.c

@@ -44,7 +44,7 @@ int test__vmlinux_matches_kallsyms(void)
 	 */
 	if (machine__create_kernel_maps(&kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps ");
-		return -1;
+		goto out;
 	}
 
 	/*
@@ -227,5 +227,7 @@ int test__vmlinux_matches_kallsyms(void)
 			map__fprintf(pos, stderr);
 	}
 out:
+	machine__exit(&kallsyms);
+	machine__exit(&vmlinux);
 	return err;
 }

tools/perf/ui/browser.c

@@ -273,6 +273,8 @@ void ui_browser__hide(struct ui_browser *browser __maybe_unused)
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
+	free(browser->helpline);
+	browser->helpline = NULL;
 	pthread_mutex_unlock(&ui__lock);
 }
 

tools/perf/util/event.c

@@ -476,8 +476,10 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		}
 	}
 
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
+	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
+		free(event);
 		return -ENOENT;
+	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),

tools/perf/util/evsel.c

@@ -640,6 +640,11 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	free(evsel->counts);
+}
+
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
@@ -659,6 +664,28 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
+static inline void compute_deltas(struct perf_evsel *evsel,
+				  int cpu,
+				  struct perf_counts_values *count)
+{
+	struct perf_counts_values tmp;
+
+	if (!evsel->prev_raw_counts)
+		return;
+
+	if (cpu == -1) {
+		tmp = evsel->prev_raw_counts->aggr;
+		evsel->prev_raw_counts->aggr = *count;
+	} else {
+		tmp = evsel->prev_raw_counts->cpu[cpu];
+		evsel->prev_raw_counts->cpu[cpu] = *count;
+	}
+
+	count->val = count->val - tmp.val;
+	count->ena = count->ena - tmp.ena;
+	count->run = count->run - tmp.run;
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
@@ -674,6 +701,8 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
+	compute_deltas(evsel, cpu, &count);
+
 	if (scale) {
 		if (count.run == 0)
 			count.val = 0;
@@ -712,6 +741,8 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 		}
 	}
 
+	compute_deltas(evsel, -1, aggr);
+
 	evsel->counts->scaled = 0;
 	if (scale) {
 		if (aggr->run == 0) {

tools/perf/util/evsel.h

@@ -53,6 +53,7 @@ struct perf_evsel {
 	struct xyarray		*sample_id;
 	u64			*id;
 	struct perf_counts	*counts;
+	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
 	struct hists		hists;
@@ -116,6 +117,7 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,

tools/perf/util/header.c

@@ -313,7 +313,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (is_kallsyms) {
 		if (symbol_conf.kptr_restrict) {
 			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			return 0;
+			err = 0;
+			goto out_free;
 		}
 		realname = (char *) name;
 	} else
@@ -954,6 +955,7 @@ static int write_topo_node(int fd, int node)
 	}
 
 	fclose(fp);
+	fp = NULL;
 
 	ret = do_write(fd, &mem_total, sizeof(u64));
 	if (ret)
@@ -980,7 +982,8 @@ static int write_topo_node(int fd, int node)
 	ret = do_write_string(fd, buf);
 done:
 	free(buf);
-	fclose(fp);
+	if (fp)
+		fclose(fp);
 	return ret;
 }
 
@@ -2921,16 +2924,22 @@ int perf_event__process_tracing_data(union perf_event *event,
 				 session->repipe);
 	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
-	if (readn(session->fd, buf, padding) < 0)
-		die("reading input file");
+	if (readn(session->fd, buf, padding) < 0) {
+		pr_err("%s: reading input file", __func__);
+		return -1;
+	}
 	if (session->repipe) {
 		int retw = write(STDOUT_FILENO, buf, padding);
-		if (retw <= 0 || retw != padding)
-			die("repiping tracing data padding");
+		if (retw <= 0 || retw != padding) {
+			pr_err("%s: repiping tracing data padding", __func__);
+			return -1;
+		}
 	}
 
-	if (size_read + padding != size)
-		die("tracing data size mismatch");
+	if (size_read + padding != size) {
+		pr_err("%s: tracing data size mismatch", __func__);
+		return -1;
+	}
 
 	perf_evlist__prepare_tracepoint_events(session->evlist,
 					       session->pevent);

tools/perf/util/map.c

@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -29,29 +30,29 @@ static inline int is_no_dso_memory(const char *filename)
 	       !strcmp(filename, "[heap]");
 }
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	self->type     = type;
-	self->start    = start;
-	self->end      = end;
-	self->pgoff    = pgoff;
-	self->dso      = dso;
-	self->map_ip   = map__map_ip;
-	self->unmap_ip = map__unmap_ip;
-	RB_CLEAR_NODE(&self->rb_node);
-	self->groups   = NULL;
-	self->referenced = false;
-	self->erange_warned = false;
+	map->type     = type;
+	map->start    = start;
+	map->end      = end;
+	map->pgoff    = pgoff;
+	map->dso      = dso;
+	map->map_ip   = map__map_ip;
+	map->unmap_ip = map__unmap_ip;
+	RB_CLEAR_NODE(&map->rb_node);
+	map->groups   = NULL;
+	map->referenced = false;
+	map->erange_warned = false;
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type)
 {
-	struct map *self = malloc(sizeof(*self));
+	struct map *map = malloc(sizeof(*map));
 
-	if (self != NULL) {
+	if (map != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon, no_dso, vdso;
@@ -74,10 +75,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, start, start + len, pgoff, dso);
+		map__init(map, type, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			self->map_ip = self->unmap_ip = identity__map_ip;
+			map->map_ip = map->unmap_ip = identity__map_ip;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -85,12 +86,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			 * unnecessary map__load warning.
 			 */
 			if (no_dso)
-				dso__set_loaded(dso, self->type);
+				dso__set_loaded(dso, map->type);
 		}
 	}
-	return self;
+	return map;
 out_delete:
-	free(self);
+	free(map);
 	return NULL;
 }
 
@@ -113,48 +114,48 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
-void map__delete(struct map *self)
+void map__delete(struct map *map)
 {
-	free(self);
+	free(map);
 }
 
-void map__fixup_start(struct map *self)
+void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->start = sym->start;
+		map->start = sym->start;
 	}
 }
 
-void map__fixup_end(struct map *self)
+void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->end = sym->end;
+		map->end = sym->end;
 	}
 }
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *self, symbol_filter_t filter)
+int map__load(struct map *map, symbol_filter_t filter)
 {
-	const char *name = self->dso->long_name;
+	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(self->dso, self->type))
+	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(self->dso, self, filter);
+	nr = dso__load(map->dso, map, filter);
 	if (nr < 0) {
-		if (self->dso->has_build_id) {
+		if (map->dso->has_build_id) {
 			char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-			build_id__sprintf(self->dso->build_id,
-					  sizeof(self->dso->build_id),
+			build_id__sprintf(map->dso->build_id,
+					  sizeof(map->dso->build_id),
 					  sbuild_id);
 			pr_warning("%s with build id %s not found",
 				   name, sbuild_id);
@@ -184,43 +185,36 @@ int map__load(struct map *self, symbol_filter_t filter)
 	 * Only applies to the kernel, as its symtabs aren't relative like the
 	 * module ones.
 	 */
-	if (self->dso->kernel)
-		map__reloc_vmlinux(self);
+	if (map->dso->kernel)
+		map__reloc_vmlinux(map);
 
 	return 0;
 }
 
-struct symbol *map__find_symbol(struct map *self, u64 addr,
+struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	return dso__find_symbol(self->dso, self->type, addr);
+	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(self->dso, self->type))
-		dso__sort_by_name(self->dso, self->type);
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
 
-	return dso__find_symbol_by_name(self->dso, self->type, name);
+	return dso__find_symbol_by_name(map->dso, map->type, name);
 }
 
-struct map *map__clone(struct map *self)
+struct map *map__clone(struct map *map)
 {
-	struct map *map = malloc(sizeof(*self));
-
-	if (!map)
-		return NULL;
-
-	memcpy(map, self, sizeof(*self));
-
-	return map;
+	return memdup(map, sizeof(*map));
 }
 
 int map__overlap(struct map *l, struct map *r)
@@ -237,10 +231,10 @@ int map__overlap(struct map *l, struct map *r)
 	return 0;
 }
 
-size_t map__fprintf(struct map *self, FILE *fp)
+size_t map__fprintf(struct map *map, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
-		       self->start, self->end, self->pgoff, self->dso->name);
+		       map->start, map->end, map->pgoff, map->dso->name);
 }
 
 size_t map__fprintf_dsoname(struct map *map, FILE *fp)
@@ -528,9 +522,9 @@ static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
 	return ip - (s64)map->pgoff;
 }
 
-void map__reloc_vmlinux(struct map *self)
+void map__reloc_vmlinux(struct map *map)
 {
-	struct kmap *kmap = map__kmap(self);
+	struct kmap *kmap = map__kmap(map);
 	s64 reloc;
 
 	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
@@ -542,9 +536,9 @@ void map__reloc_vmlinux(struct map *self)
 	if (!reloc)
 		return;
 
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
+	map->map_ip   = map__reloc_map_ip;
+	map->unmap_ip = map__reloc_unmap_ip;
+	map->pgoff    = reloc;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -567,9 +561,9 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	rb_insert_color(&map->rb_node, maps);
 }
 
-void maps__remove(struct rb_root *self, struct map *map)
+void maps__remove(struct rb_root *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, self);
+	rb_erase(&map->rb_node, maps);
 }
 
 struct map *maps__find(struct rb_root *maps, u64 ip)

tools/perf/util/map.h

@@ -57,9 +57,9 @@ struct map_groups {
 	struct machine	 *machine;
 };
 
-static inline struct kmap *map__kmap(struct map *self)
+static inline struct kmap *map__kmap(struct map *map)
 {
-	return (struct kmap *)(self + 1);
+	return (struct kmap *)(map + 1);
 }
 
 static inline u64 map__map_ip(struct map *map, u64 ip)
@@ -85,27 +85,27 @@ struct symbol;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-void map__delete(struct map *self);
-struct map *map__clone(struct map *self);
+void map__delete(struct map *map);
+struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
-size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 
-int map__load(struct map *self, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *self,
+int map__load(struct map *map, symbol_filter_t filter);
+struct symbol *map__find_symbol(struct map *map,
 				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter);
-void map__fixup_start(struct map *self);
-void map__fixup_end(struct map *self);
+void map__fixup_start(struct map *map);
+void map__fixup_end(struct map *map);
 
-void map__reloc_vmlinux(struct map *self);
+void map__reloc_vmlinux(struct map *map);
 
 size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);

tools/perf/util/sort.c

@@ -249,7 +249,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 					size_t size,
 					unsigned int width __maybe_unused)
 {
-	FILE *fp;
+	FILE *fp = NULL;
 	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
 	size_t line_len;
 
@@ -270,7 +270,6 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 
 	if (getline(&path, &line_len, fp) < 0 || !line_len)
 		goto out_ip;
-	fclose(fp);
 	self->srcline = strdup(path);
 	if (self->srcline == NULL)
 		goto out_ip;
@@ -280,8 +279,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 		*nl = '\0';
 	path = self->srcline;
 out_path:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%s", path);
 out_ip:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
 }
 

tools/perf/util/strlist.c

@@ -35,11 +35,11 @@ struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
 	return NULL;
 }
 
-static void str_node__delete(struct str_node *self, bool dupstr)
+static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		free((void *)self->s);
-	free(self);
+		free((void *)snode->s);
+	free(snode);
 }
 
 static
@@ -59,12 +59,12 @@ static int strlist__node_cmp(struct rb_node *rb_node, const void *entry)
 	return strcmp(snode->s, str);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+int strlist__add(struct strlist *slist, const char *new_entry)
 {
-	return rblist__add_node(&self->rblist, new_entry);
+	return rblist__add_node(&slist->rblist, new_entry);
 }
 
-int strlist__load(struct strlist *self, const char *filename)
+int strlist__load(struct strlist *slist, const char *filename)
 {
 	char entry[1024];
 	int err;
@@ -80,7 +80,7 @@ int strlist__load(struct strlist *self, const char *filename)
 			continue;
 		entry[len - 1] = '\0';
 
-		err = strlist__add(self, entry);
+		err = strlist__add(slist, entry);
 		if (err != 0)
 			goto out;
 	}
@@ -107,56 +107,56 @@ struct str_node *strlist__find(struct strlist *slist, const char *entry)
 	return snode;
 }
 
-static int strlist__parse_list_entry(struct strlist *self, const char *s)
+static int strlist__parse_list_entry(struct strlist *slist, const char *s)
 {
 	if (strncmp(s, "file://", 7) == 0)
-		return strlist__load(self, s + 7);
+		return strlist__load(slist, s + 7);
 
-	return strlist__add(self, s);
+	return strlist__add(slist, s);
 }
 
-int strlist__parse_list(struct strlist *self, const char *s)
+int strlist__parse_list(struct strlist *slist, const char *s)
 {
 	char *sep;
 	int err;
 
 	while ((sep = strchr(s, ',')) != NULL) {
 		*sep = '\0';
-		err = strlist__parse_list_entry(self, s);
+		err = strlist__parse_list_entry(slist, s);
 		*sep = ',';
 		if (err != 0)
 			return err;
 		s = sep + 1;
 	}
 
-	return *s ? strlist__parse_list_entry(self, s) : 0;
+	return *s ? strlist__parse_list_entry(slist, s) : 0;
 }
 
-struct strlist *strlist__new(bool dupstr, const char *slist)
+struct strlist *strlist__new(bool dupstr, const char *list)
 {
-	struct strlist *self = malloc(sizeof(*self));
+	struct strlist *slist = malloc(sizeof(*slist));
 
-	if (self != NULL) {
-		rblist__init(&self->rblist);
-		self->rblist.node_cmp    = strlist__node_cmp;
-		self->rblist.node_new    = strlist__node_new;
-		self->rblist.node_delete = strlist__node_delete;
+	if (slist != NULL) {
+		rblist__init(&slist->rblist);
+		slist->rblist.node_cmp    = strlist__node_cmp;
+		slist->rblist.node_new    = strlist__node_new;
+		slist->rblist.node_delete = strlist__node_delete;
 
-		self->dupstr	 = dupstr;
-		if (slist && strlist__parse_list(self, slist) != 0)
+		slist->dupstr	 = dupstr;
+		if (slist && strlist__parse_list(slist, list) != 0)
 			goto out_error;
 	}
 
-	return self;
+	return slist;
 out_error:
-	free(self);
+	free(slist);
 	return NULL;
 }
 
-void strlist__delete(struct strlist *self)
+void strlist__delete(struct strlist *slist)
 {
-	if (self != NULL)
-		rblist__delete(&self->rblist);
+	if (slist != NULL)
+		rblist__delete(&slist->rblist);
 }
 
 struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)

tools/perf/util/strlist.h

@@ -17,34 +17,34 @@ struct strlist {
 };
 
 struct strlist *strlist__new(bool dupstr, const char *slist);
-void strlist__delete(struct strlist *self);
+void strlist__delete(struct strlist *slist);
 
-void strlist__remove(struct strlist *self, struct str_node *sn);
-int strlist__load(struct strlist *self, const char *filename);
-int strlist__add(struct strlist *self, const char *str);
+void strlist__remove(struct strlist *slist, struct str_node *sn);
+int strlist__load(struct strlist *slist, const char *filename);
+int strlist__add(struct strlist *slist, const char *str);
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx);
-struct str_node *strlist__find(struct strlist *self, const char *entry);
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx);
+struct str_node *strlist__find(struct strlist *slist, const char *entry);
 
-static inline bool strlist__has_entry(struct strlist *self, const char *entry)
+static inline bool strlist__has_entry(struct strlist *slist, const char *entry)
 {
-	return strlist__find(self, entry) != NULL;
+	return strlist__find(slist, entry) != NULL;
 }
 
-static inline bool strlist__empty(const struct strlist *self)
+static inline bool strlist__empty(const struct strlist *slist)
 {
-	return rblist__empty(&self->rblist);
+	return rblist__empty(&slist->rblist);
 }
 
-static inline unsigned int strlist__nr_entries(const struct strlist *self)
+static inline unsigned int strlist__nr_entries(const struct strlist *slist)
 {
-	return rblist__nr_entries(&self->rblist);
+	return rblist__nr_entries(&slist->rblist);
 }
 
 /* For strlist iteration */
-static inline struct str_node *strlist__first(struct strlist *self)
+static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&self->rblist.entries);
+	struct rb_node *rn = rb_first(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
@@ -59,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn)
 /**
  * strlist_for_each      - iterate over a strlist
  * @pos:	the &struct str_node to use as a loop cursor.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, self)	\
-	for (pos = strlist__first(self); pos; pos = strlist__next(pos))
+#define strlist__for_each(pos, slist)	\
+	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
  * strlist_for_each_safe - iterate over a strlist safe against removal of
  *                         str_node
  * @pos:	the &struct str_node to use as a loop cursor.
  * @n:		another &struct str_node to use as temporary storage.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, self)	\
-	for (pos = strlist__first(self), n = strlist__next(pos); pos;\
+#define strlist__for_each_safe(pos, n, slist)	\
+	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 
-int strlist__parse_list(struct strlist *self, const char *s);
+int strlist__parse_list(struct strlist *slist, const char *s);
 #endif /* __PERF_STRLIST_H */