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>

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:

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
 ----------

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,
 

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 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 				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;
 		}

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;

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))

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
+}

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
 

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

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  */

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;
+}

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

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;
 }