perf/core improvements and fixes

. Improve listing of accessible enum perf probe variables, from Hyeoncheol Lee.
 
 . Don't stop the build if the audit libraries are not installed, fix from Namhyung Kim.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJQZLyTAAoJENZQFvNTUqpAfgMQAIHFPCA2AHLzQae1kr6ApoXi
 4hwhT8MyvI6Rnaj19vlOjthxk8Ynjkx+5ZiNtYxy+K6aJvQ7ZgsmS6q9//oRdJx0
 //7zgRz29pmvq0ZOkd3lktyi77mrL6euVIIt53J2c1pjoExxN4KRiJ2QIYUsyBvL
 YsG7RXjuh3cACEZ+KMytxFFdbdXTGSicMmF4a5py5kuRydkuCZjmujt25N4Bzlrs
 jDxjLhXDBi14Dk0OXy2yUeTthAAa96kYIkJAetbduzbOricmfMHhMRgIGfQk2/K1
 QirrcbTZApZ78YBjbq1EAdNf6lSaTEA5YIG/NZBS6N2tTeHXi4meXzM6ke+Lb2J1
 42Gpy3xVDOkcG93Wgd4m1EO5x5E2kYhdJuYqUKf4jFl5b4qXCkX3qrllu2Tu4D46
 rr/V3FcItyzmuEclCZFcKrVefoy8vC5Kg1/szQ7C+c1anuO6cNTLMy68lTqb8wx/
 bnhuPmLS79dYdtDuKNwS9uTsFJD98U7GrIOW074GYV5o2mqdC/VyGWIIxL/vMlxo
 6AgWKmDTKvNa63n4fwkM+CDucJTk8pqFbrtAnq+yvr0JlypDEJqpM/0u5tZizrGc
 dScjB4YwtC17s3VjWGszwExtjxC39j+YXF0aFKkbxgYAUEHMefZuJ7Pxu9TDZ2BF
 P/A/ggGw5nUIDNn2FHmL
 =98/I
 -----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:

 * Improve listing of accessible enum perf probe variables, from Hyeoncheol Lee.

 * Don't stop the build if the audit libraries are not installed, fix from Namhyung Kim.

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

tools/perf/Documentation/perf-trace.txt

@@ -0,0 +1,53 @@
+perf-trace(1)
+=============
+
+NAME
+----
+perf-trace - strace inspired tool
+
+SYNOPSIS
+--------
+[verse]
+'perf trace'
+
+DESCRIPTION
+-----------
+This command will show the events associated with the target, initially
+syscalls, but other system events like pagefaults, task lifetime events,
+scheduling events, etc.
+
+Initially this is a live mode only tool, but eventually will work with
+perf.data files like the other tools, allowing a detached 'record' from
+analysis phases.
+
+OPTIONS
+-------
+
+--all-cpus::
+        System-wide collection from all CPUs.
+
+-p::
+--pid=::
+	Record events on existing process ID (comma separated list).
+
+--tid=::
+        Record events on existing thread ID (comma separated list).
+
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
+--no-inherit::
+	Child tasks do not inherit counters.
+
+--mmap-pages=::
+	Number of mmap data pages. Must be a power of two.
+
+--cpu::
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+In per-thread mode with inheritance mode on (default), Events are captured only when
+the thread executes on the designated CPUs. Default is to monitor all CPUs.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-script[1]

tools/perf/Makefile

@@ -559,6 +559,19 @@ else
 	LIB_OBJS += $(OUTPUT)util/unwind.o
 endif
 
+ifdef NO_LIBAUDIT
+	BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT
+else
+	FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit
+	ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT)),y)
+		msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev);
+		BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT
+	else
+		BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+		EXTLIBS += -laudit
+	endif
+endif
+
 ifdef NO_NEWT
 	BASIC_CFLAGS += -DNO_NEWT_SUPPORT
 else

tools/perf/builtin-record.c

@@ -320,7 +320,7 @@ try_again:
 		}
 	}
 
-	if (perf_evlist__set_filters(evlist)) {
+	if (perf_evlist__apply_filters(evlist)) {
 		error("failed to set filter with %d (%s)\n", errno,
 			strerror(errno));
 		rc = -1;

tools/perf/builtin-stat.c

@@ -478,7 +478,7 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv)
 		counter->supported = true;
 	}
 
-	if (perf_evlist__set_filters(evsel_list)) {
+	if (perf_evlist__apply_filters(evsel_list)) {
 		error("failed to set filter with %d (%s)\n", errno,
 			strerror(errno));
 		return -1;

tools/perf/builtin-test.c

@@ -564,7 +564,7 @@ static int test__basic_mmap(void)
 			goto out_munmap;
 		}
 
-		err = perf_evlist__parse_sample(evlist, event, &sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &sample);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
@@ -781,7 +781,7 @@ static int test__PERF_RECORD(void)
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_evlist__parse_sample(evlist, event, &sample, false);
+				err = perf_evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
 					if (verbose)
 						perf_event__fprintf(event, stderr);
@@ -1289,6 +1289,118 @@ static int perf_evsel__tp_sched_test(void)
 	return ret;
 }
 
+static int test__syscall_open_tp_fields(void)
+{
+	struct perf_record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.no_delay   = true,
+		.freq	    = 1,
+		.mmap_pages = 256,
+		.raw_samples = true,
+	};
+	const char *filename = "/etc/passwd";
+	int flags = O_RDONLY | O_DIRECTORY;
+	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evsel *evsel;
+	int err = -1, i, nr_events = 0, nr_polls = 0;
+
+	if (evlist == NULL) {
+		pr_debug("%s: perf_evlist__new\n", __func__);
+		goto out;
+	}
+
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
+	if (evsel == NULL) {
+		pr_debug("%s: perf_evsel__newtp\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__add(evlist, evsel);
+
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("%s: perf_evlist__create_maps\n", __func__);
+		goto out_delete_evlist;
+	}
+
+	perf_evsel__config(evsel, &opts, evsel);
+
+	evlist->threads->map[0] = getpid();
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+
+	/*
+ 	 * Generate the event:
+ 	 */
+	open(filename, flags);
+
+	while (1) {
+		int before = nr_events;
+
+		for (i = 0; i < evlist->nr_mmaps; i++) {
+			union perf_event *event;
+
+			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+				const u32 type = event->header.type;
+				int tp_flags;
+				struct perf_sample sample;
+
+				++nr_events;
+
+				if (type != PERF_RECORD_SAMPLE)
+					continue;
+
+				err = perf_evsel__parse_sample(evsel, event, &sample);
+				if (err) {
+					pr_err("Can't parse sample, err = %d\n", err);
+					goto out_munmap;
+				}
+
+				tp_flags = perf_evsel__intval(evsel, &sample, "flags");
+
+				if (flags != tp_flags) {
+					pr_debug("%s: Expected flags=%#x, got %#x\n",
+						 __func__, flags, tp_flags);
+					goto out_munmap;
+				}
+
+				goto out_ok;
+			}
+		}
+
+		if (nr_events == before)
+			poll(evlist->pollfd, evlist->nr_fds, 10);
+
+		if (++nr_polls > 5) {
+			pr_debug("%s: no events!\n", __func__);
+			goto out_munmap;
+		}
+	}
+out_ok:
+	err = 0;
+out_munmap:
+	perf_evlist__munmap(evlist);
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return err;
+}
+
 static struct test {
 	const char *desc;
 	int (*func)(void);
@@ -1339,6 +1451,10 @@ static struct test {
 		.desc = "Check parsing of sched tracepoints fields",
 		.func = perf_evsel__tp_sched_test,
 	},
+	{
+		.desc = "Generate and check syscalls:sys_enter_open event fields",
+		.func = test__syscall_open_tp_fields,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/builtin-top.c

@@ -823,7 +823,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	int ret;
 
 	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_evlist__parse_sample(top->evlist, event, &sample, false);
+		ret = perf_evlist__parse_sample(top->evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			continue;

tools/perf/builtin-trace.c

@@ -0,0 +1,310 @@
+#include "builtin.h"
+#include "util/evlist.h"
+#include "util/parse-options.h"
+#include "util/thread_map.h"
+#include "event-parse.h"
+
+#include <libaudit.h>
+#include <stdlib.h>
+
+static struct syscall_fmt {
+	const char *name;
+	const char *alias;
+	bool	   errmsg;
+	bool	   timeout;
+} syscall_fmts[] = {
+	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
+	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat", },
+	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat", },
+	{ .name	    = "futex",	    .errmsg = true, },
+	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "read",	    .errmsg = true, },
+	{ .name	    = "recvfrom",   .errmsg = true, },
+	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
+	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
+};
+
+static int syscall_fmt__cmp(const void *name, const void *fmtp)
+{
+	const struct syscall_fmt *fmt = fmtp;
+	return strcmp(name, fmt->name);
+}
+
+static struct syscall_fmt *syscall_fmt__find(const char *name)
+{
+	const int nmemb = ARRAY_SIZE(syscall_fmts);
+	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
+}
+
+struct syscall {
+	struct event_format *tp_format;
+	const char	    *name;
+	struct syscall_fmt  *fmt;
+};
+
+struct trace {
+	int			audit_machine;
+	struct {
+		int		max;
+		struct syscall  *table;
+	} syscalls;
+	struct perf_record_opts opts;
+};
+
+static int trace__read_syscall_info(struct trace *trace, int id)
+{
+	char tp_name[128];
+	struct syscall *sc;
+
+	if (id > trace->syscalls.max) {
+		struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
+
+		if (nsyscalls == NULL)
+			return -1;
+
+		if (trace->syscalls.max != -1) {
+			memset(nsyscalls + trace->syscalls.max + 1, 0,
+			       (id - trace->syscalls.max) * sizeof(*sc));
+		} else {
+			memset(nsyscalls, 0, (id + 1) * sizeof(*sc));
+		}
+
+		trace->syscalls.table = nsyscalls;
+		trace->syscalls.max   = id;
+	}
+
+	sc = trace->syscalls.table + id;
+	sc->name = audit_syscall_to_name(id, trace->audit_machine);
+	if (sc->name == NULL)
+		return -1;
+
+	sc->fmt = syscall_fmt__find(sc->name);
+
+	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
+	sc->tp_format = event_format__new("syscalls", tp_name);
+
+	if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
+		snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
+		sc->tp_format = event_format__new("syscalls", tp_name);
+	}
+
+	return sc->tp_format != NULL ? 0 : -1;
+}
+
+static size_t syscall__fprintf_args(struct syscall *sc, unsigned long *args, FILE *fp)
+{
+	int i = 0;
+	size_t printed = 0;
+
+	if (sc->tp_format != NULL) {
+		struct format_field *field;
+
+		for (field = sc->tp_format->format.fields->next; field; field = field->next) {
+			printed += fprintf(fp, "%s%s: %ld", printed ? ", " : "",
+					   field->name, args[i++]);
+		}
+	} else {
+		while (i < 6) {
+			printed += fprintf(fp, "%sarg%d: %ld", printed ? ", " : "", i, args[i]);
+			++i;
+		}
+	}
+
+	return printed;
+}
+
+static int trace__run(struct trace *trace)
+{
+	struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+	struct perf_evsel *evsel, *evsel_enter, *evsel_exit;
+	int err = -1, i, nr_events = 0, before;
+
+	if (evlist == NULL) {
+		printf("Not enough memory to run!\n");
+		goto out;
+	}
+
+	evsel_enter = perf_evsel__newtp("raw_syscalls", "sys_enter", 0);
+	if (evsel_enter == NULL) {
+		printf("Couldn't read the raw_syscalls:sys_enter tracepoint information!\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__add(evlist, evsel_enter);
+
+	evsel_exit = perf_evsel__newtp("raw_syscalls", "sys_exit", 1);
+	if (evsel_exit == NULL) {
+		printf("Couldn't read the raw_syscalls:sys_exit tracepoint information!\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__add(evlist, evsel_exit);
+
+	err = perf_evlist__create_maps(evlist, &trace->opts.target);
+	if (err < 0) {
+		printf("Problems parsing the target to trace, check your options!\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__config_attrs(evlist, &trace->opts);
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		printf("Couldn't create the events: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err < 0) {
+		printf("Couldn't mmap the events: %s\n", strerror(errno));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+again:
+	before = nr_events;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		union perf_event *event;
+
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			const u32 type = event->header.type;
+			struct syscall *sc;
+			struct perf_sample sample;
+			int id;
+
+			++nr_events;
+
+			switch (type) {
+			case PERF_RECORD_SAMPLE:
+				break;
+			case PERF_RECORD_LOST:
+				printf("LOST %" PRIu64 " events!\n", event->lost.lost);
+				continue;
+			default:
+				printf("Unexpected %s event, skipping...\n",
+					perf_event__name(type));
+				continue;
+			}
+
+			err = perf_evlist__parse_sample(evlist, event, &sample);
+			if (err) {
+				printf("Can't parse sample, err = %d, skipping...\n", err);
+				continue;
+			}
+
+			evsel = perf_evlist__id2evsel(evlist, sample.id);
+			if (evsel == NULL) {
+				printf("Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
+				continue;
+			}
+
+			id = perf_evsel__intval(evsel, &sample, "id");
+			if (id < 0) {
+				printf("Invalid syscall %d id, skipping...\n", id);
+				continue;
+			}
+
+			if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) &&
+			    trace__read_syscall_info(trace, id))
+				continue;
+
+			if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL))
+				continue;
+
+			sc = &trace->syscalls.table[id];
+
+			if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1)
+				printf("%d ", sample.tid);
+
+			if (evsel == evsel_enter) {
+				void *args = perf_evsel__rawptr(evsel, &sample, "args");
+
+				printf("%s(", sc->name);
+				syscall__fprintf_args(sc, args, stdout);
+			} else if (evsel == evsel_exit) {
+				int ret = perf_evsel__intval(evsel, &sample, "ret");
+
+				if (ret < 0 && sc->fmt && sc->fmt->errmsg) {
+					char bf[256];
+					const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
+						   *e = audit_errno_to_name(-ret);
+
+					printf(") = -1 %s %s", e, emsg);
+				} else if (ret == 0 && sc->fmt && sc->fmt->timeout)
+					printf(") = 0 Timeout");
+				else
+					printf(") = %d", ret);
+
+				putchar('\n');
+			}
+		}
+	}
+
+	if (nr_events == before)
+		poll(evlist->pollfd, evlist->nr_fds, -1);
+
+	goto again;
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+out:
+	return err;
+}
+
+int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const char * const trace_usage[] = {
+		"perf trace [<options>]",
+		NULL
+	};
+	struct trace trace = {
+		.audit_machine = audit_detect_machine(),
+		.syscalls = {
+			. max = -1,
+		},
+		.opts = {
+			.target = {
+				.uid	   = UINT_MAX,
+				.uses_mmap = true,
+			},
+			.user_freq     = UINT_MAX,
+			.user_interval = ULLONG_MAX,
+			.no_delay      = true,
+			.mmap_pages    = 1024,
+		},
+	};
+	const struct option trace_options[] = {
+	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
+		    "trace events on existing process id"),
+	OPT_STRING(0, "tid", &trace.opts.target.tid, "tid",
+		    "trace events on existing thread id"),
+	OPT_BOOLEAN(0, "all-cpus", &trace.opts.target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_STRING(0, "cpu", &trace.opts.target.cpu_list, "cpu",
+		    "list of cpus to monitor"),
+	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_UINTEGER(0, "mmap-pages", &trace.opts.mmap_pages,
+		     "number of mmap data pages"),
+	OPT_STRING(0, "uid", &trace.opts.target.uid_str, "user",
+		   "user to profile"),
+	OPT_END()
+	};
+	int err;
+
+	argc = parse_options(argc, argv, trace_options, trace_usage, 0);
+	if (argc)
+		usage_with_options(trace_usage, trace_options);
+
+	err = perf_target__parse_uid(&trace.opts.target);
+	if (err) {
+		char bf[BUFSIZ];
+		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+		printf("%s", bf);
+		return err;
+	}
+
+	return trace__run(&trace);
+}

tools/perf/builtin.h

@@ -34,6 +34,7 @@ extern int cmd_kmem(int argc, const char **argv, const char *prefix);
 extern int cmd_lock(int argc, const char **argv, const char *prefix);
 extern int cmd_kvm(int argc, const char **argv, const char *prefix);
 extern int cmd_test(int argc, const char **argv, const char *prefix);
+extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
 
 extern int find_scripts(char **scripts_array, char **scripts_path_array);

tools/perf/command-list.txt

@@ -17,6 +17,7 @@ perf-report			mainporcelain common
 perf-stat			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
+perf-trace			mainporcelain common
 perf-script			mainporcelain common
 perf-probe			mainporcelain full
 perf-kmem			mainporcelain common

tools/perf/config/feature-tests.mak

@@ -193,3 +193,14 @@ int main(void)
 }
 endef
 endif
+
+ifndef NO_LIBAUDIT
+define SOURCE_LIBAUDIT
+#include <libaudit.h>
+
+int main(void)
+{
+	return audit_open();
+}
+endef
+endif

tools/perf/perf.c

@@ -55,6 +55,9 @@ static struct cmd_struct commands[] = {
 	{ "lock",	cmd_lock,	0 },
 	{ "kvm",	cmd_kvm,	0 },
 	{ "test",	cmd_test,	0 },
+#ifndef NO_LIBAUDIT_SUPPORT
+	{ "trace",	cmd_trace,	0 },
+#endif
 	{ "inject",	cmd_inject,	0 },
 };
 

tools/perf/util/cpumap.h

@@ -2,6 +2,7 @@
 #define __PERF_CPUMAP_H
 
 #include <stdio.h>
+#include <stdbool.h>
 
 struct cpu_map {
 	int nr;
@@ -14,4 +15,14 @@ void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 
+static inline int cpu_map__nr(const struct cpu_map *map)
+{
+	return map ? map->nr : 1;
+}
+
+static inline bool cpu_map__all(const struct cpu_map *map)
+{
+	return map ? map->map[0] == -1 : true;
+}
+
 #endif /* __PERF_CPUMAP_H */

tools/perf/util/dwarf-aux.c

@@ -804,6 +804,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 			tmp = "union ";
 		else if (tag == DW_TAG_structure_type)
 			tmp = "struct ";
+		else if (tag == DW_TAG_enumeration_type)
+			tmp = "enum ";
 		/* Write a base name */
 		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
 		return (ret >= len) ? -E2BIG : ret;

tools/perf/util/evlist.c

@@ -304,7 +304,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int cpu, thread;
 	struct perf_evsel *pos;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
@@ -315,7 +315,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
+	int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries;
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -475,8 +475,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
-	evlist->nr_mmaps = evlist->cpus->nr;
+	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
-	if (evlist->cpus->map[0] == -1)
+	if (cpu_map__all(evlist->cpus))
 		evlist->nr_mmaps = evlist->threads->nr;
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
@@ -622,11 +622,11 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
-		    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
+		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
 			return -ENOMEM;
 	}
 
-	if (evlist->cpus->map[0] == -1)
+	if (cpu_map__all(cpus))
 		return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
 	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
@@ -666,32 +666,39 @@ void perf_evlist__delete_maps(struct perf_evlist *evlist)
 	evlist->threads = NULL;
 }
 
-int perf_evlist__set_filters(struct perf_evlist *evlist)
+int perf_evlist__apply_filters(struct perf_evlist *evlist)
 {
-	const struct thread_map *threads = evlist->threads;
-	const struct cpu_map *cpus = evlist->cpus;
 	struct perf_evsel *evsel;
-	char *filter;
+	int err = 0;
-	int thread;
+	const int ncpus = cpu_map__nr(evlist->cpus),
-	int cpu;
+		  nthreads = evlist->threads->nr;
-	int err;
-	int fd;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
-		filter = evsel->filter;
+		if (evsel->filter == NULL)
-		if (!filter)
 			continue;
-		for (cpu = 0; cpu < cpus->nr; cpu++) {
+
-			for (thread = 0; thread < threads->nr; thread++) {
+		err = perf_evsel__set_filter(evsel, ncpus, nthreads, evsel->filter);
-				fd = FD(evsel, cpu, thread);
+		if (err)
-				err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+			break;
-				if (err)
-					return err;
-			}
-		}
 	}
 
-	return 0;
+	return err;
+}
+
+int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
+{
+	struct perf_evsel *evsel;
+	int err = 0;
+	const int ncpus = cpu_map__nr(evlist->cpus),
+		  nthreads = evlist->threads->nr;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
+		if (err)
+			break;
+	}
+
+	return err;
 }
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
@@ -884,10 +891,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 }
 
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
-			      struct perf_sample *sample, bool swapped)
+			      struct perf_sample *sample)
 {
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
-	return perf_evsel__parse_sample(evsel, event, sample, swapped);
+	return perf_evsel__parse_sample(evsel, event, sample);
 }
 
 size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)

tools/perf/util/evlist.h

@@ -72,6 +72,8 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
 #define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
 	perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
 
+int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
+
 struct perf_evsel *
 perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
 
@@ -115,7 +117,7 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 int perf_evlist__create_maps(struct perf_evlist *evlist,
 			     struct perf_target *target);
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
-int perf_evlist__set_filters(struct perf_evlist *evlist);
+int perf_evlist__apply_filters(struct perf_evlist *evlist);
 
 void __perf_evlist__set_leader(struct list_head *list);
 void perf_evlist__set_leader(struct perf_evlist *evlist);
@@ -125,7 +127,7 @@ bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
-			      struct perf_sample *sample, bool swapped);
+			      struct perf_sample *sample);
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);

tools/perf/util/evsel.c

@@ -70,7 +70,7 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-static struct event_format *event_format__new(const char *sys, const char *name)
+struct event_format *event_format__new(const char *sys, const char *name)
 {
 	int fd, n;
 	char *filename;
@@ -117,21 +117,28 @@ struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx)
 
 	if (evsel != NULL) {
 		struct perf_event_attr attr = {
-			.type = PERF_TYPE_TRACEPOINT,
+			.type	       = PERF_TYPE_TRACEPOINT,
+			.sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
 		};
 
+		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
+			goto out_free;
+
 		evsel->tp_format = event_format__new(sys, name);
 		if (evsel->tp_format == NULL)
 			goto out_free;
 
+		event_attr_init(&attr);
 		attr.config = evsel->tp_format->id;
+		attr.sample_period = 1;
 		perf_evsel__init(evsel, &attr, idx);
-		evsel->name = evsel->tp_format->name;
 	}
 
 	return evsel;
 
 out_free:
+	free(evsel->name);
 	free(evsel);
 	return NULL;
 }
@@ -501,6 +508,24 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
+int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
+			   const char *filter)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < ncpus; cpu++) {
+		for (thread = 0; thread < nthreads; thread++) {
+			int fd = FD(evsel, cpu, thread),
+			    err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
@@ -562,10 +587,8 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	perf_evsel__exit(evsel);
 	close_cgroup(evsel->cgrp);
 	free(evsel->group_name);
-	if (evsel->tp_format && evsel->name == evsel->tp_format->name) {
+	if (evsel->tp_format)
-		evsel->name = NULL;
 		pevent_free_format(evsel->tp_format);
-	}
 	free(evsel->name);
 	free(evsel);
 }
@@ -763,11 +786,13 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
 	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
 }
 
-static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
+static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
-				       struct perf_sample *sample,
+				       const union perf_event *event,
-				       bool swapped)
+				       struct perf_sample *sample)
 {
+	u64 type = evsel->attr.sample_type;
 	const u64 *array = event->sample.array;
+	bool swapped = evsel->needs_swap;
 	union u64_swap u;
 
 	array += ((event->header.size -
@@ -828,10 +853,11 @@ static bool sample_overlap(const union perf_event *event,
 }
 
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
-			     struct perf_sample *data, bool swapped)
+			     struct perf_sample *data)
 {
 	u64 type = evsel->attr.sample_type;
 	u64 regs_user = evsel->attr.sample_regs_user;
+	bool swapped = evsel->needs_swap;
 	const u64 *array;
 
 	/*
@@ -848,7 +874,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
 			return 0;
-		return perf_event__parse_id_sample(event, type, data, swapped);
+		return perf_evsel__parse_id_sample(evsel, event, data);
 	}
 
 	array = event->sample.array;
@@ -1078,7 +1104,7 @@ struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *nam
 	return pevent_find_field(evsel->tp_format, name);
 }
 
-char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
+void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
 	struct format_field *field = perf_evsel__field(evsel, name);
@@ -1101,13 +1127,43 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
 	struct format_field *field = perf_evsel__field(evsel, name);
-	u64 val;
+	void *ptr;
+	u64 value;
 
 	if (!field)
 		return 0;
 
-	val = pevent_read_number(evsel->tp_format->pevent,
+	ptr = sample->raw_data + field->offset;
-				 sample->raw_data + field->offset, field->size);
-	return val;
 
+	switch (field->size) {
+	case 1:
+		return *(u8 *)ptr;
+	case 2:
+		value = *(u16 *)ptr;
+		break;
+	case 4:
+		value = *(u32 *)ptr;
+		break;
+	case 8:
+		value = *(u64 *)ptr;
+		break;
+	default:
+		return 0;
+	}
+
+	if (!evsel->needs_swap)
+		return value;
+
+	switch (field->size) {
+	case 2:
+		return bswap_16(value);
+	case 4:
+		return bswap_32(value);
+	case 8:
+		return bswap_64(value);
+	default:
+		return 0;
+	}
+
+	return 0;
 }

tools/perf/util/evsel.h

@@ -69,6 +69,7 @@ struct perf_evsel {
 	struct cpu_map		*cpus;
 	unsigned int		sample_size;
 	bool 			supported;
+	bool 			needs_swap;
 	/* parse modifier helper */
 	int			exclude_GH;
 	struct perf_evsel	*leader;
@@ -82,6 +83,9 @@ struct perf_record_opts;
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
 struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx);
+
+struct event_format *event_format__new(const char *sys, const char *name);
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
 void perf_evsel__exit(struct perf_evsel *evsel);
@@ -114,6 +118,9 @@ void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
+int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
+			   const char *filter);
+
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
 			     struct cpu_map *cpus);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
@@ -124,11 +131,18 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 struct perf_sample;
 
-char *perf_evsel__strval(struct perf_evsel *evsel, struct perf_sample *sample,
+void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name);
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name);
 
+static inline char *perf_evsel__strval(struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       const char *name)
+{
+	return perf_evsel__rawptr(evsel, sample, name);
+}
+
 struct format_field;
 
 struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
@@ -205,7 +219,7 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 void hists__init(struct hists *hists);
 
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
-			     struct perf_sample *sample, bool swapped);
+			     struct perf_sample *sample);
 
 static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
 {

tools/perf/util/header.c

@@ -1256,8 +1256,10 @@ read_event_desc(struct perf_header *ph, int fd)
 		if (ret != (ssize_t)sizeof(nr))
 			goto error;
 
-		if (ph->needs_swap)
+		if (ph->needs_swap) {
 			nr = bswap_32(nr);
+			evsel->needs_swap = true;
+		}
 
 		evsel->name = do_read_string(fd, ph);
 
@@ -2626,6 +2628,8 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
 		if (evsel == NULL)
 			goto out_delete_evlist;
+
+		evsel->needs_swap = header->needs_swap;
 		/*
 		 * Do it before so that if perf_evsel__alloc_id fails, this
 		 * entry gets purged too at perf_evlist__delete().

tools/perf/util/hist.c

@@ -410,8 +410,13 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
-			iter->period += he->period;
+			iter->period		+= he->period;
-			iter->nr_events += he->nr_events;
+			iter->period_sys	+= he->period_sys;
+			iter->period_us		+= he->period_us;
+			iter->period_guest_sys	+= he->period_guest_sys;
+			iter->period_guest_us	+= he->period_guest_us;
+			iter->nr_events		+= he->nr_events;
+
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
 				callchain_merge(&callchain_cursor,

tools/perf/util/parse-events.c

@@ -356,42 +356,28 @@ int parse_events_add_cache(struct list_head **list, int *idx,
 	return add_event(list, idx, &attr, name);
 }
 
-static int add_tracepoint(struct list_head **list, int *idx,
+static int add_tracepoint(struct list_head **listp, int *idx,
 			  char *sys_name, char *evt_name)
 {
-	struct perf_event_attr attr;
+	struct perf_evsel *evsel;
-	char name[MAX_NAME_LEN];
+	struct list_head *list = *listp;
-	char evt_path[MAXPATHLEN];
-	char id_buf[4];
-	u64 id;
-	int fd;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
+	if (!list) {
-		 sys_name, evt_name);
+		list = malloc(sizeof(*list));
-
+		if (!list)
-	fd = open(evt_path, O_RDONLY);
+			return -ENOMEM;
-	if (fd < 0)
+		INIT_LIST_HEAD(list);
-		return -1;
-
-	if (read(fd, id_buf, sizeof(id_buf)) < 0) {
-		close(fd);
-		return -1;
 	}
 
-	close(fd);
+	evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++);
-	id = atoll(id_buf);
+	if (!evsel) {
+		free(list);
+		return -ENOMEM;
+	}
 
-	memset(&attr, 0, sizeof(attr));
+	list_add_tail(&evsel->node, list);
-	attr.config = id;
+	*listp = list;
-	attr.type = PERF_TYPE_TRACEPOINT;
+	return 0;
-	attr.sample_type |= PERF_SAMPLE_RAW;
-	attr.sample_type |= PERF_SAMPLE_TIME;
-	attr.sample_type |= PERF_SAMPLE_CPU;
-	attr.sample_type |= PERF_SAMPLE_PERIOD;
-	attr.sample_period = 1;
-
-	snprintf(name, MAX_NAME_LEN, "%s:%s", sys_name, evt_name);
-	return add_event(list, idx, &attr, name);
 }
 
 static int add_tracepoint_multi(struct list_head **list, int *idx,

tools/perf/util/python.c

@@ -805,7 +805,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		err = perf_evlist__parse_sample(evlist, event, &pevent->sample, false);
+		err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);

tools/perf/util/session.c

@@ -722,8 +722,7 @@ static int flush_sample_queue(struct perf_session *s,
 		if (iter->timestamp > limit)
 			break;
 
-		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
-						s->header.needs_swap);
 		if (ret)
 			pr_err("Can't parse sample, err = %d\n", ret);
 		else {
@@ -1174,8 +1173,7 @@ static int perf_session__process_event(struct perf_session *session,
 	/*
 	 * For all kernel events we get the sample data
 	 */
-	ret = perf_evlist__parse_sample(session->evlist, event, &sample,
+	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
-					session->header.needs_swap);
 	if (ret)
 		return ret;