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:

User visible changes:

  - Fix segfault using 'perf script --show-mmap-events', affects
    only current perf/core. (Adrian Hunter)

  - /proc/kcore requires CAP_SYS_RAWIO message too noisy, make it
    debug only. (Adrian Hunter)

  - Fix Intel PT timestamp handling. (Adrian Hunter)

  - Add Intel BTS support, with a call-graph script to show it and
    PT in use in a GUI using 'perf script' python scripting with
    postgresql and Qt. (Adrian Hunter)

  - Add checks for returned EVENT_ERROR type in libtraceevent, fixing
    a bug that surfaced on arm64 systems. (Dean Nelson)

  - Fallback to using kallsyms when libdw fails to handle a vmlinux file,
    that can happen, for instance, when perf is statically linked and
    then libdw fails to load libebl_{arch}.so. (Wang Nan)

Infrastructure changes:

  - Initialize reference counts in map__clone(). (Arnaldo Carvalho de Melo)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/lib/traceevent/event-parse.c

@@ -1745,6 +1745,9 @@ process_cond(struct event_format *event, struct print_arg *top, char **tok)
 	type = process_arg(event, left, &token);
 
  again:
+	if (type == EVENT_ERROR)
+		goto out_free;
+
 	/* Handle other operations in the arguments */
 	if (type == EVENT_OP && strcmp(token, ":") != 0) {
 		type = process_op(event, left, &token);
@@ -2004,6 +2007,12 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 			goto out_warn_free;
 
 		type = process_arg_token(event, right, tok, type);
+		if (type == EVENT_ERROR) {
+			free_arg(right);
+			/* token was freed in process_arg_token() via *tok */
+			token = NULL;
+			goto out_free;
+		}
 
 		if (right->type == PRINT_OP &&
 		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {

tools/perf/Documentation/intel-bts.txt

+Intel Branch Trace Store
+========================
+
+Overview
+========
+
+Intel BTS could be regarded as a predecessor to Intel PT and has some
+similarities because it can also identify every branch a program takes.  A
+notable difference is that Intel BTS has no timing information and as a
+consequence the present implementation is limited to per-thread recording.
+
+While decoding Intel BTS does not require walking the object code, the object
+code is still needed to pair up calls and returns correctly, consequently much
+of the Intel PT documentation applies also to Intel BTS.  Refer to the Intel PT
+documentation and consider that the PMU 'intel_bts' can usually be used in
+place of 'intel_pt' in the examples provided, with the proviso that per-thread
+recording must also be stipulated i.e. the --per-thread option for
+'perf record'.
+
+
+perf record
+===========
+
+new event
+---------
+
+The Intel BTS kernel driver creates a new PMU for Intel BTS.  The perf record
+option is:
+
+	-e intel_bts//
+
+Currently Intel BTS is limited to per-thread tracing so the --per-thread option
+is also needed.
+
+
+snapshot option
+---------------
+
+The snapshot option is the same as Intel PT (refer Intel PT documentation).
+
+
+auxtrace mmap size option
+-----------------------
+
+The mmap size option is the same as Intel PT (refer Intel PT documentation).
+
+
+perf script
+===========
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by option --itrace.  The --itrace option is
+the same as Intel PT (refer Intel PT documentation) except that neither
+"instructions" events nor "transactions" events (and consequently call
+chains) are supported.
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+
+dump option
+-----------
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel BTS packets are displayed.
+
+To disable the display of Intel BTS packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+===========
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script.
+
+
+perf inject
+===========
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+	perf inject --itrace -i perf.data -o perf.data.new

tools/perf/Documentation/itrace.txt

+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.

tools/perf/Documentation/perf-inject.txt

@@ -48,28 +48,7 @@ OPTIONS
 	Decode Instruction Tracing data, replacing it with synthesized events.
 	Options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 SEE ALSO
 --------

tools/perf/Documentation/perf-report.txt

@@ -331,28 +331,7 @@ OPTIONS
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 	To disable decoding entirely, use --no-itrace.
 

tools/perf/Documentation/perf-script.txt

@@ -235,28 +235,7 @@ OPTIONS
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 
-		i	synthesize instructions events
-		b	synthesize branches events
-		c	synthesize branches events (calls only)
-		r	synthesize branches events (returns only)
-		x	synthesize transactions events
-		e	synthesize error events
-		d	create a debug log
-		g	synthesize a call chain (use with i or x)
-
-	The default is all events i.e. the same as --itrace=ibxe
-
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
-
-		i	instructions
-		t	ticks
-		ms	milliseconds
-		us	microseconds
-		ns	nanoseconds (default)
-
-	Also the call chain size (default 16, max. 1024) for instructions or
-	transactions events can be specified.
+include::itrace.txt[]
 
 	To disable decoding entirely, use --no-itrace.
 

tools/perf/arch/x86/util/Build

@@ -10,3 +10,4 @@ libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
+libperf-$(CONFIG_AUXTRACE) += intel-bts.o

tools/perf/arch/x86/util/auxtrace.c

@@ -13,11 +13,56 @@
  *
  */
 
+#include <stdbool.h>
+
 #include "../../util/header.h"
+#include "../../util/debug.h"
+#include "../../util/pmu.h"
 #include "../../util/auxtrace.h"
 #include "../../util/intel-pt.h"
+#include "../../util/intel-bts.h"
+#include "../../util/evlist.h"
+
+static
+struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
+						    int *err)
+{
+	struct perf_pmu *intel_pt_pmu;
+	struct perf_pmu *intel_bts_pmu;
+	struct perf_evsel *evsel;
+	bool found_pt = false;
+	bool found_bts = false;
+
+	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+
+	if (evlist) {
+		evlist__for_each(evlist, evsel) {
+			if (intel_pt_pmu &&
+			    evsel->attr.type == intel_pt_pmu->type)
+				found_pt = true;
+			if (intel_bts_pmu &&
+			    evsel->attr.type == intel_bts_pmu->type)
+				found_bts = true;
+		}
+	}
+
+	if (found_pt && found_bts) {
+		pr_err("intel_pt and intel_bts may not be used together\n");
+		*err = -EINVAL;
+		return NULL;
+	}
+
+	if (found_pt)
+		return intel_pt_recording_init(err);
+
+	if (found_bts)
+		return intel_bts_recording_init(err);
 
-struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+	return NULL;
+}
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
 					      int *err)
 {
 	char buffer[64];
@@ -32,7 +77,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe
 	}
 
 	if (!strncmp(buffer, "GenuineIntel,", 13))
-		return intel_pt_recording_init(err);
+		return auxtrace_record__init_intel(evlist, err);
 
 	return NULL;
 }

tools/perf/arch/x86/util/pmu.c

@@ -3,6 +3,7 @@
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
+#include "../../util/intel-bts.h"
 #include "../../util/pmu.h"
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
@@ -10,6 +11,8 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __mayb
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
 		return intel_pt_pmu_default_config(pmu);
+	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME))
+		pmu->selectable = true;
 #endif
 	return NULL;
 }

tools/perf/scripts/python/export-to-postgresql.py

@@ -15,6 +15,53 @@ import sys
 import struct
 import datetime
 
+# To use this script you will need to have installed package python-pyside which
+# provides LGPL-licensed Python bindings for Qt.  You will also need the package
+# libqt4-sql-psql for Qt postgresql support.
+#
+# The script assumes postgresql is running on the local machine and that the
+# user has postgresql permissions to create databases. Examples of installing
+# postgresql and adding such a user are:
+#
+# fedora:
+#
+#	$ sudo yum install postgresql postgresql-server python-pyside qt-postgresql
+#	$ sudo su - postgres -c initdb
+#	$ sudo service postgresql start
+#	$ sudo su - postgres
+#	$ createuser <your user id here>
+#	Shall the new role be a superuser? (y/n) y
+#
+# ubuntu:
+#
+#	$ sudo apt-get install postgresql
+#	$ sudo su - postgres
+#	$ createuser <your user id here>
+#	Shall the new role be a superuser? (y/n) y
+#
+# An example of using this script with Intel PT:
+#
+#	$ perf record -e intel_pt//u ls
+#	$ perf script -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py pt_example branches calls
+#	2015-05-29 12:49:23.464364 Creating database...
+#	2015-05-29 12:49:26.281717 Writing to intermediate files...
+#	2015-05-29 12:49:27.190383 Copying to database...
+#	2015-05-29 12:49:28.140451 Removing intermediate files...
+#	2015-05-29 12:49:28.147451 Adding primary keys
+#	2015-05-29 12:49:28.655683 Adding foreign keys
+#	2015-05-29 12:49:29.365350 Done
+#
+# To browse the database, psql can be used e.g.
+#
+#	$ psql pt_example
+#	pt_example=# select * from samples_view where id < 100;
+#	pt_example=# \d+
+#	pt_example=# \d+ samples_view
+#	pt_example=# \q
+#
+# An example of using the database is provided by the script
+# call-graph-from-postgresql.py.  Refer to that script for details.
+
 from PySide.QtSql import *
 
 # Need to access PostgreSQL C library directly to use COPY FROM STDIN

tools/perf/util/Build

@@ -80,6 +80,7 @@ libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 libperf-$(CONFIG_AUXTRACE) += intel-pt.o
+libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o

tools/perf/util/annotate.c

@@ -1126,6 +1126,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 		dso->annotate_warned = 1;
 		pr_err("Can't annotate %s:\n\n"
 		       "No vmlinux file%s\nwas found in the path.\n\n"
+		       "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
 		       "Please use:\n\n"
 		       "  perf buildid-cache -vu vmlinux\n\n"
 		       "or:\n\n"

tools/perf/util/auxtrace.c

@@ -48,6 +48,7 @@
 #include "parse-options.h"
 
 #include "intel-pt.h"
+#include "intel-bts.h"
 
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
@@ -888,6 +889,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	switch (type) {
 	case PERF_AUXTRACE_INTEL_PT:
 		return intel_pt_process_auxtrace_info(event, session);
+	case PERF_AUXTRACE_INTEL_BTS:
+		return intel_bts_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

tools/perf/util/auxtrace.h

@@ -40,6 +40,7 @@ struct events_stats;
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
 	PERF_AUXTRACE_INTEL_PT,
+	PERF_AUXTRACE_INTEL_BTS,
 };
 
 enum itrace_period_type {

tools/perf/util/evlist.c

@@ -573,7 +573,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 {
 	struct perf_sample_id *sid;
 
-	if (evlist->nr_entries == 1)
+	if (evlist->nr_entries == 1 || !id)
 		return perf_evlist__first(evlist);
 
 	sid = perf_evlist__id2sid(evlist, id);

tools/perf/util/intel-bts.h

+/*
+ * intel-bts.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef INCLUDE__PERF_INTEL_BTS_H__
+#define INCLUDE__PERF_INTEL_BTS_H__
+
+#define INTEL_BTS_PMU_NAME "intel_bts"
+
+enum {
+	INTEL_BTS_PMU_TYPE,
+	INTEL_BTS_TIME_SHIFT,
+	INTEL_BTS_TIME_MULT,
+	INTEL_BTS_TIME_ZERO,
+	INTEL_BTS_CAP_USER_TIME_ZERO,
+	INTEL_BTS_SNAPSHOT_MODE,
+	INTEL_BTS_AUXTRACE_PRIV_MAX,
+};
+
+#define INTEL_BTS_AUXTRACE_PRIV_SIZE (INTEL_BTS_AUXTRACE_PRIV_MAX * sizeof(u64))
+
+struct auxtrace_record;
+struct perf_tool;
+union perf_event;
+struct perf_session;
+
+struct auxtrace_record *intel_bts_recording_init(int *err);
+
+int intel_bts_process_auxtrace_info(union perf_event *event,
+				    struct perf_session *session);
+
+#endif

tools/perf/util/intel-pt.c

@@ -1450,7 +1450,7 @@ static int intel_pt_process_event(struct perf_session *session,
 		return -EINVAL;
 	}
 
-	if (sample->time)
+	if (sample->time && sample->time != (u64)-1)
 		timestamp = perf_time_to_tsc(sample->time, &pt->tc);
 	else
 		timestamp = 0;

tools/perf/util/map.c

@@ -348,9 +348,18 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 	return dso__find_symbol_by_name(map->dso, map->type, name);
 }
 
-struct map *map__clone(struct map *map)
+struct map *map__clone(struct map *from)
 {
-	return memdup(map, sizeof(*map));
+	struct map *map = memdup(from, sizeof(*map));
+
+	if (map != NULL) {
+		atomic_set(&map->refcnt, 1);
+		RB_CLEAR_NODE(&map->rb_node);
+		dso__get(map->dso);
+		map->groups = NULL;
+	}
+
+	return map;
 }
 
 int map__overlap(struct map *l, struct map *r)

tools/perf/util/pmu.c

@@ -462,10 +462,6 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
-	/* No support for intel_bts so disallow it */
-	if (!strcmp(name, "intel_bts"))
-		return NULL;
-
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right

tools/perf/util/probe-event.c

@@ -705,9 +705,10 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	}
 	/* Error path : ntevs < 0 */
 	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-	if (ntevs == -EBADF) {
-		pr_warning("Warning: No dwarf info found in the vmlinux - "
-			"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
+	if (ntevs < 0) {
+		if (ntevs == -EBADF)
+			pr_warning("Warning: No dwarf info found in the vmlinux - "
+				"please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
 		if (!need_dwarf) {
 			pr_debug("Trying to use symbols.\n");
 			return 0;

tools/perf/util/symbol.c

@@ -1138,8 +1138,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 	fd = open(kcore_filename, O_RDONLY);
 	if (fd < 0) {
-		pr_err("%s requires CAP_SYS_RAWIO capability to access.\n",
-			kcore_filename);
+		pr_debug("Failed to open %s. Note /proc/kcore requires CAP_SYS_RAWIO capability to access.\n",
+			 kcore_filename);
 		return -EINVAL;
 	}