perf tools: Add Intel BTS support

Intel BTS support fits within the new auxtrace infrastructure.  Recording is
supporting by identifying the Intel BTS PMU, parsing options and setting up
events.

Decoding is supported by queuing up trace data by thread and then decoding
synchronously delivering synthesized event samples into the session processing
for tools to consume.

Committer note:

E.g:

  [root@felicio ~]# perf record --per-thread -e intel_bts// ls
  anaconda-ks.cfg  apctest.output  bin  kernel-rt-3.10.0-298.rt56.171.el7.x86_64.rpm  libexec  lock_page.bpf.c  perf.data  perf.data.old
  [ perf record: Woken up 3 times to write data ]
  [ perf record: Captured and wrote 4.367 MB perf.data ]
  [root@felicio ~]# perf evlist -v
  intel_bts//: type: 6, size: 112, { sample_period, sample_freq }: 1, sample_type: IP|TID|IDENTIFIER, read_format: ID, disabled: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1
  dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|IDENTIFIER, read_format: ID, disabled: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1
  [root@felicio ~]# perf script # the navigate in the pager to some interesting place:
    ls 1843 1 branches: ffffffff810a60cb flush_signal_handlers ([kernel.kallsyms]) => ffffffff8121a522 setup_new_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8121a529 setup_new_exec ([kernel.kallsyms]) => ffffffff8122fa30 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa5d do_close_on_exec ([kernel.kallsyms]) => ffffffff81767ae0 _raw_spin_lock ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff81767af4 _raw_spin_lock ([kernel.kallsyms]) => ffffffff8122fa62 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fa8e do_close_on_exec ([kernel.kallsyms]) => ffffffff8122faf0 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122faf7 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fa8b do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fac9 do_close_on_exec ([kernel.kallsyms]) => ffffffff8122fad2 do_close_on_exec ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8122fadd do_close_on_exec ([kernel.kallsyms]) => ffffffff8120fc80 filp_close ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8120fcaf filp_close ([kernel.kallsyms]) => ffffffff8120fcb6 filp_close ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8120fcc2 filp_close ([kernel.kallsyms]) => ffffffff812547f0 dnotify_flush ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff81254823 dnotify_flush ([kernel.kallsyms]) => ffffffff8120fcc7 filp_close ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8120fccd filp_close ([kernel.kallsyms]) => ffffffff81261790 locks_remove_posix ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff812617a3 locks_remove_posix ([kernel.kallsyms]) => ffffffff812617b9 locks_remove_posix ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff812617b9 locks_remove_posix ([kernel.kallsyms]) => ffffffff8120fcd2 filp_close ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8120fcd5 filp_close ([kernel.kallsyms]) => ffffffff812142c0 fput ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff812142d6 fput ([kernel.kallsyms]) => ffffffff812142df fput ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff8121430c fput ([kernel.kallsyms]) => ffffffff810b6580 task_work_add ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff810b65ad task_work_add ([kernel.kallsyms]) => ffffffff810b65b1 task_work_add ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff810b65c1 task_work_add ([kernel.kallsyms]) => ffffffff810bc710 kick_process ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff810bc725 kick_process ([kernel.kallsyms]) => ffffffff810bc742 kick_process ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff810bc742 kick_process ([kernel.kallsyms]) => ffffffff810b65c6 task_work_add ([kernel.kallsyms])
    ls 1843 1 branches: ffffffff810b65c9 task_work_add ([kernel.kallsyms]) => ffffffff81214311 fput ([kernel.kallsyms])
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1437150840-31811-9-git-send-email-adrian.hunter@intel.com
[ Merged sample->time fix for bug found after first round of testing on slightly older kernel ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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/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/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/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/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/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