Merge tag 'perf-core-for-mingo-5.1-20190220' 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:

perf report:

  He Kuang:

  - Don't shadow inlined symbol with different addr range.

perf script:

  Jiri Olsa:

  - Allow +- operator to ask for -F to add/remove fields to
    the default set, for instance to ask for the removal of the
    'cpu' field in tracepoint events, adding 'period' to that
    kind of events, etc.

perf test:

  Thomas Richter:

  - Fix scheduler tracepoint signedness of COMM fields failure of
    'evsel-tp-sched' test on s390 and other arches.

  Tommi Rantala:

  - Skip trace+probe_vfs_getname.sh when 'perf trace' is not built.

perf trace:

  Arnaldo Carvalho de Melo:

  - Add initial BPF map dumper, initially just for the current, minimal
    needs of the augmented_raw_syscalls BPF example used to collect
    pointer args payloads that uses BPF maps for pid and syscall filtering,
    but will in time have features similar to 'perf stat' --interval-print,
    --interval-clear, ways to signal from a BPF event that a specific
    map (or range of that map) should be printed, optionally as a
    histogram, etc.

General:

  Jiri Olsa:

  - Add CPU and NUMA topologies classes for further reuse, fixing some
    issues in the process.

  - Fixup some warnings and debug levels.

  - Make rm_rf() remove single file, not just directories.

Documentation:

  Jonas Rabenstein:

  - Fix HEADER_CMDLINE description in perf.data documentation.

  - Fix documentation of the Flags section in perf.data.

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

21 files changed, 530 insertions, 256 deletions

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 9e4def08d569..2e19fd7ffe35 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -159,6 +159,12 @@ OPTIONS
 	the override, and the result of the above is that only S/W and H/W
 	events are displayed with the given fields.
 
+	It's possible tp add/remove fields only for specific event type:
+
+		-Fsw:-cpu,-period
+
+	removes cpu and period from software events.
+
 	For the 'wildcard' option if a user selected field is invalid for an
 	event type, a message is displayed to the user that the option is
 	ignored for that type. For example:
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 631e687be4eb..fc6e43262c41 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -210,6 +210,14 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	may happen, for instance, when a thread gets migrated to a different CPU
 	while processing a syscall.
 
+--map-dump::
+	Dump BPF maps setup by events passed via -e, for instance the augmented_raw_syscalls
+	living in tools/perf/examples/bpf/augmented_raw_syscalls.c. For now this
+	dumps just boolean map values and integer keys, in time this will print in hex
+	by default and use BTF when available, as well as use functions to do pretty
+	printing using the existing 'perf trace' syscall arg beautifiers to map integer
+	arguments to strings (pid to comm, syscall id to syscall name, etc).
+
 
 PAGEFAULTS
 ----------
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index dfb218feaad9..593ef49b273c 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -43,11 +43,10 @@ struct perf_file_section {
 
 Flags section:
 
-The header is followed by different optional headers, described by the bits set
-in flags. Only headers for which the bit is set are included. Each header
-consists of a perf_file_section located after the initial header.
-The respective perf_file_section points to the data of the additional
-header and defines its size.
+For each of the optional features a perf_file_section it placed after the data
+section if the feature bit is set in the perf_header flags bitset. The
+respective perf_file_section points to the data of the additional header and
+defines its size.
 
 Some headers consist of strings, which are defined like this:
 
@@ -131,7 +130,7 @@ An uint64_t with the total memory in bytes.
 
 	HEADER_CMDLINE = 11,
 
-A perf_header_string with the perf command line used to collect the data.
+A perf_header_string_list with the perf arg-vector used to collect the data.
 
 	HEADER_EVENT_DESC = 12,
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8d5fe092525c..373ea151dc60 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2560,6 +2560,10 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			pr_warning("Overriding previous field request for %s events.\n",
 				   event_type(type));
 
+		/* Don't override defaults for +- */
+		if (strchr(tok, '+') || strchr(tok, '-'))
+			goto parse;
+
 		output[type].fields = 0;
 		output[type].user_set = true;
 		output[type].wildcard_set = false;
@@ -2644,6 +2648,10 @@ parse:
 				rc = -EINVAL;
 				goto out;
 			}
+			if (change == REMOVE)
+				output[type].fields &= ~all_output_options[i].field;
+			else
+				output[type].fields |= all_output_options[i].field;
 			output[type].user_set = true;
 			output[type].wildcard_set = true;
 		}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 68a01e624ad3..1a11fe656afc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,7 @@
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include <bpf/bpf.h>
+#include "util/bpf_map.h"
 #include "builtin.h"
 #include "util/cgroup.h"
 #include "util/color.h"
@@ -87,6 +88,9 @@ struct trace {
 					  *augmented;
 		}		events;
 	} syscalls;
+	struct {
+		struct bpf_map *map;
+	} dump;
 	struct record_opts	opts;
 	struct perf_evlist	*evlist;
 	struct machine		*host;
@@ -2997,6 +3001,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_apply_filters;
 
+	if (trace->dump.map)
+		bpf_map__fprintf(trace->dump.map, trace->output);
+
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
 	if (err < 0)
 		goto out_error_mmap;
@@ -3686,6 +3693,7 @@ int cmd_trace(int argc, const char **argv)
 		.max_stack = UINT_MAX,
 		.max_events = ULONG_MAX,
 	};
+	const char *map_dump_str = NULL;
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
 	OPT_CALLBACK('e', "event", &trace, "event",
@@ -3718,6 +3726,9 @@ int cmd_trace(int argc, const char **argv)
 	OPT_CALLBACK(0, "duration", &trace, "float",
 		     "show only events with duration > N.M ms",
 		     trace__set_duration),
+#ifdef HAVE_LIBBPF_SUPPORT
+	OPT_STRING(0, "map-dump", &map_dump_str, "BPF map", "BPF map to periodically dump"),
+#endif
 	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_BOOLEAN('T', "time", &trace.full_time,
@@ -3812,6 +3823,14 @@ int cmd_trace(int argc, const char **argv)
 
 	err = -1;
 
+	if (map_dump_str) {
+		trace.dump.map = bpf__find_map_by_name(map_dump_str);
+		if (trace.dump.map == NULL) {
+			pr_err("ERROR: BPF map \"%s\" not found\n", map_dump_str);
+			goto out;
+		}
+	}
+
 	if (trace.trace_pgfaults) {
 		trace.opts.sample_address = true;
 		trace.opts.sample_time = true;
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 5cbba70bcdd0..ea7acf403727 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -43,7 +43,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 		return -1;
 	}
 
-	if (perf_evsel__test_field(evsel, "prev_comm", 16, true))
+	if (perf_evsel__test_field(evsel, "prev_comm", 16, false))
 		ret = -1;
 
 	if (perf_evsel__test_field(evsel, "prev_pid", 4, true))
@@ -55,7 +55,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 	if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "next_comm", 16, true))
+	if (perf_evsel__test_field(evsel, "next_comm", 16, false))
 		ret = -1;
 
 	if (perf_evsel__test_field(evsel, "next_pid", 4, true))
@@ -73,7 +73,7 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 		return -1;
 	}
 
-	if (perf_evsel__test_field(evsel, "comm", 16, true))
+	if (perf_evsel__test_field(evsel, "comm", 16, false))
 		ret = -1;
 
 	if (perf_evsel__test_field(evsel, "pid", 4, true))
diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh
index 6293cc660947..e37787be672b 100644
--- a/tools/perf/tests/shell/lib/probe.sh
+++ b/tools/perf/tests/shell/lib/probe.sh
@@ -4,3 +4,8 @@ skip_if_no_perf_probe() {
 	perf probe 2>&1 | grep -q 'is not a perf-command' && return 2
 	return 0
 }
+
+skip_if_no_perf_trace() {
+	perf trace -h 2>&1 | grep -q -e 'is not a perf-command' -e 'trace command not available' && return 2
+	return 0
+}
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 50109f27ca07..147efeb6b195 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -12,6 +12,7 @@
 . $(dirname $0)/lib/probe.sh
 
 skip_if_no_perf_probe || exit 2
+skip_if_no_perf_trace || exit 2
 
 . $(dirname $0)/lib/probe_vfs_getname.sh
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ca0741c91903..8dd3102301ea 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -69,6 +69,7 @@ perf-y += hist.o
 perf-y += util.o
 perf-y += xyarray.o
 perf-y += cpumap.o
+perf-y += cputopo.o
 perf-y += cgroup.o
 perf-y += target.o
 perf-y += rblist.o
@@ -114,6 +115,7 @@ perf-y += branch.o
 perf-y += mem2node.o
 
 perf-$(CONFIG_LIBBPF) += bpf-loader.o
+perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 62dda96b0096..028c8ec1f62a 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -233,7 +233,7 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
 				err = 0;
 				break;
 			}
-			pr_debug("%s: can't get next program: %s%s",
+			pr_debug("%s: can't get next program: %s%s\n",
 				 __func__, strerror(errno),
 				 errno == EINVAL ? " -- kernel too old?" : "");
 			/* don't report error on old kernel or EPERM  */
diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c
new file mode 100644
index 000000000000..eb853ca67cf4
--- /dev/null
+++ b/tools/perf/util/bpf_map.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include "util/bpf_map.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def)
+{
+	return def->type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+	       def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
+}
+
+static void *bpf_map_def__alloc_value(const struct bpf_map_def *def)
+{
+	if (bpf_map_def__is_per_cpu(def))
+		return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF));
+
+	return malloc(def->value_size);
+}
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp)
+{
+	const struct bpf_map_def *def = bpf_map__def(map);
+	void *prev_key = NULL, *key, *value;
+	int fd = bpf_map__fd(map), err;
+	int printed = 0;
+
+	if (fd < 0)
+		return fd;
+
+	if (IS_ERR(def))
+		return PTR_ERR(def);
+
+	err = -ENOMEM;
+	key = malloc(def->key_size);
+	if (key == NULL)
+		goto out;
+
+	value = bpf_map_def__alloc_value(def);
+	if (value == NULL)
+		goto out_free_key;
+
+	while ((err = bpf_map_get_next_key(fd, prev_key, key) == 0)) {
+		int intkey = *(int *)key;
+
+		if (!bpf_map_lookup_elem(fd, key, value)) {
+			bool boolval = *(bool *)value;
+			if (boolval)
+				printed += fprintf(fp, "[%d] = %d,\n", intkey, boolval);
+		} else {
+			printed += fprintf(fp, "[%d] = ERROR,\n", intkey);
+		}
+
+		prev_key = key;
+	}
+
+	if (err == ENOENT)
+		err = printed;
+
+	free(value);
+out_free_key:
+	free(key);
+out:
+	return err;
+}
diff --git a/tools/perf/util/bpf_map.h b/tools/perf/util/bpf_map.h
new file mode 100644
index 000000000000..d6abd5e47af8
--- /dev/null
+++ b/tools/perf/util/bpf_map.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#ifndef __PERF_BPF_MAP_H
+#define __PERF_BPF_MAP_H 1
+
+#include <stdio.h>
+#include <linux/compiler.h>
+struct bpf_map;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp);
+
+#else
+
+static inline int bpf_map__fprintf(struct bpf_map *map __maybe_unused, FILE *fp __maybe_unused)
+{
+	return 0;
+}
+
+#endif // HAVE_LIBBPF_SUPPORT
+
+#endif // __PERF_BPF_MAP_H
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0bbc3feb0894..0b599229bc7e 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -681,7 +681,7 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
 
 #undef COMMA
 
-	pr_debug("cpumask list: %s\n", buf);
+	pr_debug2("cpumask list: %s\n", buf);
 	return ret;
 }
 
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
new file mode 100644
index 000000000000..ece0710249d4
--- /dev/null
+++ b/tools/perf/util/cputopo.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/param.h>
+#include <inttypes.h>
+#include <api/fs/fs.h>
+
+#include "cputopo.h"
+#include "cpumap.h"
+#include "util.h"
+#include "env.h"
+
+
+#define CORE_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define THRD_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
+#define NODE_ONLINE_FMT \
+	"%s/devices/system/node/online"
+#define NODE_MEMINFO_FMT \
+	"%s/devices/system/node/node%d/meminfo"
+#define NODE_CPULIST_FMT \
+	"%s/devices/system/node/node%d/cpulist"
+
+static int build_cpu_topology(struct cpu_topology *tp, int cpu)
+{
+	FILE *fp;
+	char filename[MAXPATHLEN];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	ssize_t sret;
+	u32 i = 0;
+	int ret = -1;
+
+	scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT,
+		  sysfs__mountpoint(), cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto try_threads;
+
+	sret = getline(&buf, &len, fp);
+	fclose(fp);
+	if (sret <= 0)
+		goto try_threads;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->core_sib; i++) {
+		if (!strcmp(buf, tp->core_siblings[i]))
+			break;
+	}
+	if (i == tp->core_sib) {
+		tp->core_siblings[i] = buf;
+		tp->core_sib++;
+		buf = NULL;
+		len = 0;
+	}
+	ret = 0;
+
+try_threads:
+	scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+		  sysfs__mountpoint(), cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto done;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->thread_sib; i++) {
+		if (!strcmp(buf, tp->thread_siblings[i]))
+			break;
+	}
+	if (i == tp->thread_sib) {
+		tp->thread_siblings[i] = buf;
+		tp->thread_sib++;
+		buf = NULL;
+	}
+	ret = 0;
+done:
+	if (fp)
+		fclose(fp);
+	free(buf);
+	return ret;
+}
+
+void cpu_topology__delete(struct cpu_topology *tp)
+{
+	u32 i;
+
+	if (!tp)
+		return;
+
+	for (i = 0 ; i < tp->core_sib; i++)
+		zfree(&tp->core_siblings[i]);
+
+	for (i = 0 ; i < tp->thread_sib; i++)
+		zfree(&tp->thread_siblings[i]);
+
+	free(tp);
+}
+
+struct cpu_topology *cpu_topology__new(void)
+{
+	struct cpu_topology *tp = NULL;
+	void *addr;
+	u32 nr, i;
+	size_t sz;
+	long ncpus;
+	int ret = -1;
+	struct cpu_map *map;
+
+	ncpus = cpu__max_present_cpu();
+
+	/* build online CPU map */
+	map = cpu_map__new(NULL);
+	if (map == NULL) {
+		pr_debug("failed to get system cpumap\n");
+		return NULL;
+	}
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	sz = nr * sizeof(char *);
+	addr = calloc(1, sizeof(*tp) + 2 * sz);
+	if (!addr)
+		goto out_free;
+
+	tp = addr;
+	addr += sizeof(*tp);
+	tp->core_siblings = addr;
+	addr += sz;
+	tp->thread_siblings = addr;
+
+	for (i = 0; i < nr; i++) {
+		if (!cpu_map__has(map, i))
+			continue;
+
+		ret = build_cpu_topology(tp, i);
+		if (ret < 0)
+			break;
+	}
+
+out_free:
+	cpu_map__put(map);
+	if (ret) {
+		cpu_topology__delete(tp);
+		tp = NULL;
+	}
+	return tp;
+}
+
+static int load_numa_node(struct numa_topology_node *node, int nr)
+{
+	char str[MAXPATHLEN];
+	char field[32];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	int ret = -1;
+	FILE *fp;
+	u64 mem;
+
+	node->node = (u32) nr;
+
+	scnprintf(str, MAXPATHLEN, NODE_MEMINFO_FMT,
+		  sysfs__mountpoint(), nr);
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
+
+	while (getline(&buf, &len, fp) > 0) {
+		/* skip over invalid lines */
+		if (!strchr(buf, ':'))
+			continue;
+		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
+			goto err;
+		if (!strcmp(field, "MemTotal:"))
+			node->mem_total = mem;
+		if (!strcmp(field, "MemFree:"))
+			node->mem_free = mem;
+		if (node->mem_total && node->mem_free)
+			break;
+	}
+
+	fclose(fp);
+	fp = NULL;
+
+	scnprintf(str, MAXPATHLEN, NODE_CPULIST_FMT,
+		  sysfs__mountpoint(), nr);
+
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto err;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	node->cpus = buf;
+	fclose(fp);
+	return 0;
+
+err:
+	free(buf);
+	if (fp)
+		fclose(fp);
+	return ret;
+}
+
+struct numa_topology *numa_topology__new(void)
+{
+	struct cpu_map *node_map = NULL;
+	struct numa_topology *tp = NULL;
+	char path[MAXPATHLEN];
+	char *buf = NULL;
+	size_t len = 0;
+	u32 nr, i;
+	FILE *fp;
+	char *c;
+
+	scnprintf(path, MAXPATHLEN, NODE_ONLINE_FMT,
+		  sysfs__mountpoint());
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return NULL;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto out;
+
+	c = strchr(buf, '\n');
+	if (c)
+		*c = '\0';
+
+	node_map = cpu_map__new(buf);
+	if (!node_map)
+		goto out;
+
+	nr = (u32) node_map->nr;
+
+	tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0])*nr);
+	if (!tp)
+		goto out;
+
+	tp->nr = nr;
+
+	for (i = 0; i < nr; i++) {
+		if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+			numa_topology__delete(tp);
+			tp = NULL;
+			break;
+		}
+	}
+
+out:
+	free(buf);
+	fclose(fp);
+	cpu_map__put(node_map);
+	return tp;
+}
+
+void numa_topology__delete(struct numa_topology *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->nr; i++)
+		free(tp->nodes[i].cpus);
+
+	free(tp);
+}
diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h
new file mode 100644
index 000000000000..47a97e71acdf
--- /dev/null
+++ b/tools/perf/util/cputopo.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_CPUTOPO_H
+#define __PERF_CPUTOPO_H
+
+#include <linux/types.h>
+#include "env.h"
+
+struct cpu_topology {
+	u32	  core_sib;
+	u32	  thread_sib;
+	char	**core_siblings;
+	char	**thread_siblings;
+};
+
+struct numa_topology_node {
+	char		*cpus;
+	u32		 node;
+	u64		 mem_total;
+	u64		 mem_free;
+};
+
+struct numa_topology {
+	u32				nr;
+	struct numa_topology_node	nodes[0];
+};
+
+struct cpu_topology *cpu_topology__new(void);
+void cpu_topology__delete(struct cpu_topology *tp);
+
+struct numa_topology *numa_topology__new(void);
+void numa_topology__delete(struct numa_topology *tp);
+
+#endif /* __PERF_CPUTOPO_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 684c893ca6bc..dfe2958e6287 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -956,6 +956,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
+
+		/*
+		 * We don't get sample for slave events, we make them
+		 * when delivering group leader sample. Set the slave
+		 * event to follow the master sample_type to ease up
+		 * report.
+		 */
+		attr->sample_type = leader->attr.sample_type;
 	}
 
 	if (opts->no_samples)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 61ce197c5362..a2323d777dae 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -39,6 +39,7 @@
 #include "tool.h"
 #include "time-utils.h"
 #include "units.h"
+#include "cputopo.h"
 
 #include "sane_ctype.h"
 
@@ -557,158 +558,15 @@ static int write_cmdline(struct feat_fd *ff,
 	return 0;
 }
 
-#define CORE_SIB_FMT \
-	"/sys/devices/system/cpu/cpu%d/topology/core_siblings_list"
-#define THRD_SIB_FMT \
-	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
-
-struct cpu_topo {
-	u32 core_sib;
-	u32 thread_sib;
-	char **core_siblings;
-	char **thread_siblings;
-};
-
-static int build_cpu_topo(struct cpu_topo *tp, int cpu)
-{
-	FILE *fp;
-	char filename[MAXPATHLEN];
-	char *buf = NULL, *p;
-	size_t len = 0;
-	ssize_t sret;
-	u32 i = 0;
-	int ret = -1;
-
-	sprintf(filename, CORE_SIB_FMT, cpu);
-	fp = fopen(filename, "r");
-	if (!fp)
-		goto try_threads;
-
-	sret = getline(&buf, &len, fp);
-	fclose(fp);
-	if (sret <= 0)
-		goto try_threads;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	for (i = 0; i < tp->core_sib; i++) {
-		if (!strcmp(buf, tp->core_siblings[i]))
-			break;
-	}
-	if (i == tp->core_sib) {
-		tp->core_siblings[i] = buf;
-		tp->core_sib++;
-		buf = NULL;
-		len = 0;
-	}
-	ret = 0;
-
-try_threads:
-	sprintf(filename, THRD_SIB_FMT, cpu);
-	fp = fopen(filename, "r");
-	if (!fp)
-		goto done;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	for (i = 0; i < tp->thread_sib; i++) {
-		if (!strcmp(buf, tp->thread_siblings[i]))
-			break;
-	}
-	if (i == tp->thread_sib) {
-		tp->thread_siblings[i] = buf;
-		tp->thread_sib++;
-		buf = NULL;
-	}
-	ret = 0;
-done:
-	if(fp)
-		fclose(fp);
-	free(buf);
-	return ret;
-}
-
-static void free_cpu_topo(struct cpu_topo *tp)
-{
-	u32 i;
-
-	if (!tp)
-		return;
-
-	for (i = 0 ; i < tp->core_sib; i++)
-		zfree(&tp->core_siblings[i]);
-
-	for (i = 0 ; i < tp->thread_sib; i++)
-		zfree(&tp->thread_siblings[i]);
-
-	free(tp);
-}
-
-static struct cpu_topo *build_cpu_topology(void)
-{
-	struct cpu_topo *tp = NULL;
-	void *addr;
-	u32 nr, i;
-	size_t sz;
-	long ncpus;
-	int ret = -1;
-	struct cpu_map *map;
-
-	ncpus = cpu__max_present_cpu();
-
-	/* build online CPU map */
-	map = cpu_map__new(NULL);
-	if (map == NULL) {
-		pr_debug("failed to get system cpumap\n");
-		return NULL;
-	}
-
-	nr = (u32)(ncpus & UINT_MAX);
-
-	sz = nr * sizeof(char *);
-	addr = calloc(1, sizeof(*tp) + 2 * sz);
-	if (!addr)
-		goto out_free;
-
-	tp = addr;
-	addr += sizeof(*tp);
-	tp->core_siblings = addr;
-	addr += sz;
-	tp->thread_siblings = addr;
-
-	for (i = 0; i < nr; i++) {
-		if (!cpu_map__has(map, i))
-			continue;
-
-		ret = build_cpu_topo(tp, i);
-		if (ret < 0)
-			break;
-	}
-
-out_free:
-	cpu_map__put(map);
-	if (ret) {
-		free_cpu_topo(tp);
-		tp = NULL;
-	}
-	return tp;
-}
 
 static int write_cpu_topology(struct feat_fd *ff,
 			      struct perf_evlist *evlist __maybe_unused)
 {
-	struct cpu_topo *tp;
+	struct cpu_topology *tp;
 	u32 i;
 	int ret, j;
 
-	tp = build_cpu_topology();
+	tp = cpu_topology__new();
 	if (!tp)
 		return -1;
 
@@ -746,7 +604,7 @@ static int write_cpu_topology(struct feat_fd *ff,
 			return ret;
 	}
 done:
-	free_cpu_topo(tp);
+	cpu_topology__delete(tp);
 	return ret;
 }
 
@@ -781,112 +639,45 @@ static int write_total_mem(struct feat_fd *ff,
 	return ret;
 }
 
-static int write_topo_node(struct feat_fd *ff, int node)
-{
-	char str[MAXPATHLEN];
-	char field[32];
-	char *buf = NULL, *p;
-	size_t len = 0;
-	FILE *fp;
-	u64 mem_total, mem_free, mem;
-	int ret = -1;
-
-	sprintf(str, "/sys/devices/system/node/node%d/meminfo", node);
-	fp = fopen(str, "r");
-	if (!fp)
-		return -1;
-
-	while (getline(&buf, &len, fp) > 0) {
-		/* skip over invalid lines */
-		if (!strchr(buf, ':'))
-			continue;
-		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
-			goto done;
-		if (!strcmp(field, "MemTotal:"))
-			mem_total = mem;
-		if (!strcmp(field, "MemFree:"))
-			mem_free = mem;
-	}
-
-	fclose(fp);
-	fp = NULL;
-
-	ret = do_write(ff, &mem_total, sizeof(u64));
-	if (ret)
-		goto done;
-
-	ret = do_write(ff, &mem_free, sizeof(u64));
-	if (ret)
-		goto done;
-
-	ret = -1;
-	sprintf(str, "/sys/devices/system/node/node%d/cpulist", node);
-
-	fp = fopen(str, "r");
-	if (!fp)
-		goto done;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	ret = do_write_string(ff, buf);
-done:
-	free(buf);
-	if (fp)
-		fclose(fp);
-	return ret;
-}
-
 static int write_numa_topology(struct feat_fd *ff,
 			       struct perf_evlist *evlist __maybe_unused)
 {
-	char *buf = NULL;
-	size_t len = 0;
-	FILE *fp;
-	struct cpu_map *node_map = NULL;
-	char *c;
-	u32 nr, i, j;
+	struct numa_topology *tp;
 	int ret = -1;
+	u32 i;
 
-	fp = fopen("/sys/devices/system/node/online", "r");
-	if (!fp)
-		return -1;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
+	tp = numa_topology__new();
+	if (!tp)
+		return -ENOMEM;
 
-	c = strchr(buf, '\n');
-	if (c)
-		*c = '\0';
+	ret = do_write(ff, &tp->nr, sizeof(u32));
+	if (ret < 0)
+		goto err;
 
-	node_map = cpu_map__new(buf);
-	if (!node_map)
-		goto done;
+	for (i = 0; i < tp->nr; i++) {
+		struct numa_topology_node *n = &tp->nodes[i];
 
-	nr = (u32)node_map->nr;
+		ret = do_write(ff, &n->node, sizeof(u32));
+		if (ret < 0)
+			goto err;
 
-	ret = do_write(ff, &nr, sizeof(nr));
-	if (ret < 0)
-		goto done;
+		ret = do_write(ff, &n->mem_total, sizeof(u64));
+		if (ret)
+			goto err;
 
-	for (i = 0; i < nr; i++) {
-		j = (u32)node_map->map[i];
-		ret = do_write(ff, &j, sizeof(j));
-		if (ret < 0)
-			break;
+		ret = do_write(ff, &n->mem_free, sizeof(u64));
+		if (ret)
+			goto err;
 
-		ret = write_topo_node(ff, i);
+		ret = do_write_string(ff, n->cpus);
 		if (ret < 0)
-			break;
+			goto err;
 	}
-done:
-	free(buf);
-	fclose(fp);
-	cpu_map__put(node_map);
+
+	ret = 0;
+
+err:
+	numa_topology__delete(tp);
 	return ret;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 18fb9c8cbf9c..c764bbc91009 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1202,6 +1202,13 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 		return 0;
 	}
 
+	/*
+	 * There's no reason to deliver sample
+	 * for zero period, bail out.
+	 */
+	if (!sample->period)
+		return 0;
+
 	return tool->sample(tool, event, sample, sid->evsel, machine);
 }
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2b6c1ccb878c..d2299e912e59 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -231,8 +231,14 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 	if (sym_l == sym_r)
 		return 0;
 
-	if (sym_l->inlined || sym_r->inlined)
-		return strcmp(sym_l->name, sym_r->name);
+	if (sym_l->inlined || sym_r->inlined) {
+		int ret = strcmp(sym_l->name, sym_r->name);
+
+		if (ret)
+			return ret;
+		if ((sym_l->start <= sym_r->end) && (sym_l->end >= sym_r->start))
+			return 0;
+	}
 
 	if (sym_l->start != sym_r->start)
 		return (int64_t)(sym_r->start - sym_l->start);
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 00f215580b5a..10ca1533937e 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -104,7 +104,7 @@ static struct symbol *new_inline_sym(struct dso *dso,
 	} else {
 		/* create a fake symbol for the inline frame */
 		inline_sym = symbol__new(base_sym ? base_sym->start : 0,
-					 base_sym ? base_sym->end : 0,
+					 base_sym ? (base_sym->end - base_sym->start) : 0,
 					 base_sym ? base_sym->binding : 0,
 					 base_sym ? base_sym->type : 0,
 					 funcname);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 320b0fef249a..3ee410fc047a 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -120,16 +120,26 @@ int mkdir_p(char *path, mode_t mode)
 int rm_rf(const char *path)
 {
 	DIR *dir;
-	int ret = 0;
+	int ret;
 	struct dirent *d;
 	char namebuf[PATH_MAX];
+	struct stat statbuf;
 
+	/* Do not fail if there's no file. */
+	ret = lstat(path, &statbuf);
+	if (ret)
+		return 0;
+
+	/* Try to remove any file we get. */
+	if (!(statbuf.st_mode & S_IFDIR))
+		return unlink(path);
+
+	/* We have directory in path. */
 	dir = opendir(path);
 	if (dir == NULL)
-		return 0;
+		return -1;
 
 	while ((d = readdir(dir)) != NULL && !ret) {
-		struct stat statbuf;
 
 		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
 			continue;