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/intel-bts.c

+/*
+ * intel-bts.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, 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.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../util/cpumap.h"
+#include "../../util/evsel.h"
+#include "../../util/evlist.h"
+#include "../../util/session.h"
+#include "../../util/util.h"
+#include "../../util/pmu.h"
+#include "../../util/debug.h"
+#include "../../util/tsc.h"
+#include "../../util/auxtrace.h"
+#include "../../util/intel-bts.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+#define INTEL_BTS_DFLT_SAMPLE_SIZE	KiB(4)
+
+#define INTEL_BTS_MAX_SAMPLE_SIZE	KiB(60)
+
+struct intel_bts_snapshot_ref {
+	void	*ref_buf;
+	size_t	ref_offset;
+	bool	wrapped;
+};
+
+struct intel_bts_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*intel_bts_pmu;
+	struct perf_evlist		*evlist;
+	bool				snapshot_mode;
+	size_t				snapshot_size;
+	int				snapshot_ref_cnt;
+	struct intel_bts_snapshot_ref	*snapshot_refs;
+};
+
+struct branch {
+	u64 from;
+	u64 to;
+	u64 misc;
+};
+
+static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+{
+	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
+}
+
+static int intel_bts_info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct perf_event_mmap_page *pc;
+	struct perf_tsc_conversion tc = { .time_mult = 0, };
+	bool cap_user_time_zero = false;
+	int err;
+
+	if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->nr_mmaps)
+		return -EINVAL;
+
+	pc = session->evlist->mmap[0].base;
+	if (pc) {
+		err = perf_read_tsc_conversion(pc, &tc);
+		if (err) {
+			if (err != -EOPNOTSUPP)
+				return err;
+		} else {
+			cap_user_time_zero = tc.time_mult != 0;
+		}
+		if (!cap_user_time_zero)
+			ui__warning("Intel BTS: TSC not available\n");
+	}
+
+	auxtrace_info->type = PERF_AUXTRACE_INTEL_BTS;
+	auxtrace_info->priv[INTEL_BTS_PMU_TYPE] = intel_bts_pmu->type;
+	auxtrace_info->priv[INTEL_BTS_TIME_SHIFT] = tc.time_shift;
+	auxtrace_info->priv[INTEL_BTS_TIME_MULT] = tc.time_mult;
+	auxtrace_info->priv[INTEL_BTS_TIME_ZERO] = tc.time_zero;
+	auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+	auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE] = btsr->snapshot_mode;
+
+	return 0;
+}
+
+static int intel_bts_recording_options(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist,
+				       struct record_opts *opts)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct perf_evsel *evsel, *intel_bts_evsel = NULL;
+	const struct cpu_map *cpus = evlist->cpus;
+	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+
+	btsr->evlist = evlist;
+	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type == intel_bts_pmu->type) {
+			if (intel_bts_evsel) {
+				pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
+				return -EINVAL;
+			}
+			evsel->attr.freq = 0;
+			evsel->attr.sample_period = 1;
+			intel_bts_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+		pr_err("Snapshot mode (-S option) requires " INTEL_BTS_PMU_NAME " PMU event (-e " INTEL_BTS_PMU_NAME ")\n");
+		return -EINVAL;
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	if (opts->full_auxtrace && !cpu_map__empty(cpus)) {
+		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
+		return -EINVAL;
+	}
+
+	/* Set default sizes for snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages = KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+			   opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+		if (!opts->auxtrace_snapshot_size)
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+		pr_debug2("Intel BTS snapshot size: %zu\n",
+			  opts->auxtrace_snapshot_size);
+	}
+
+	/* Set default sizes for full trace mode */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz;
+
+		if (opts->auxtrace_snapshot_mode)
+			min_sz = KiB(4);
+		else
+			min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for Intel BTS: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+	if (intel_bts_evsel) {
+		/*
+		 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+		 * must come first.
+		 */
+		perf_evlist__to_front(evlist, intel_bts_evsel);
+		/*
+		 * In the case of per-cpu mmaps, we need the CPU on the
+		 * AUX event.
+		 */
+		if (!cpu_map__empty(cpus))
+			perf_evsel__set_sample_bit(intel_bts_evsel, CPU);
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct perf_evsel *tracking_evsel;
+		int err;
+
+		err = parse_events(evlist, "dummy:u", NULL);
+		if (err)
+			return err;
+
+		tracking_evsel = perf_evlist__last(evlist);
+
+		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+		tracking_evsel->attr.freq = 0;
+		tracking_evsel->attr.sample_period = 1;
+	}
+
+	return 0;
+}
+
+static int intel_bts_parse_snapshot_options(struct auxtrace_record *itr,
+					    struct record_opts *opts,
+					    const char *str)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	btsr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static u64 intel_bts_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return rdtsc();
+}
+
+static int intel_bts_alloc_snapshot_refs(struct intel_bts_recording *btsr,
+					 int idx)
+{
+	const size_t sz = sizeof(struct intel_bts_snapshot_ref);
+	int cnt = btsr->snapshot_ref_cnt, new_cnt = cnt * 2;
+	struct intel_bts_snapshot_ref *refs;
+
+	if (!new_cnt)
+		new_cnt = 16;
+
+	while (new_cnt <= idx)
+		new_cnt *= 2;
+
+	refs = calloc(new_cnt, sz);
+	if (!refs)
+		return -ENOMEM;
+
+	memcpy(refs, btsr->snapshot_refs, cnt * sz);
+
+	btsr->snapshot_refs = refs;
+	btsr->snapshot_ref_cnt = new_cnt;
+
+	return 0;
+}
+
+static void intel_bts_free_snapshot_refs(struct intel_bts_recording *btsr)
+{
+	int i;
+
+	for (i = 0; i < btsr->snapshot_ref_cnt; i++)
+		zfree(&btsr->snapshot_refs[i].ref_buf);
+	zfree(&btsr->snapshot_refs);
+}
+
+static void intel_bts_recording_free(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+
+	intel_bts_free_snapshot_refs(btsr);
+	free(btsr);
+}
+
+static int intel_bts_snapshot_start(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(btsr->evlist, evsel) {
+		if (evsel->attr.type == btsr->intel_bts_pmu->type)
+			return perf_evlist__disable_event(btsr->evlist, evsel);
+	}
+	return -EINVAL;
+}
+
+static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(btsr->evlist, evsel) {
+		if (evsel->attr.type == btsr->intel_bts_pmu->type)
+			return perf_evlist__enable_event(btsr->evlist, evsel);
+	}
+	return -EINVAL;
+}
+
+static bool intel_bts_first_wrap(u64 *data, size_t buf_size)
+{
+	int i, a, b;
+
+	b = buf_size >> 3;
+	a = b - 512;
+	if (a < 0)
+		a = 0;
+
+	for (i = a; i < b; i++) {
+		if (data[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm, unsigned char *data,
+				   u64 *head, u64 *old)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	bool wrapped;
+	int err;
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head);
+
+	if (idx >= btsr->snapshot_ref_cnt) {
+		err = intel_bts_alloc_snapshot_refs(btsr, idx);
+		if (err)
+			goto out_err;
+	}
+
+	wrapped = btsr->snapshot_refs[idx].wrapped;
+	if (!wrapped && intel_bts_first_wrap((u64 *)data, mm->len)) {
+		btsr->snapshot_refs[idx].wrapped = true;
+		wrapped = true;
+	}
+
+	/*
+	 * In full trace mode 'head' continually increases.  However in snapshot
+	 * mode 'head' is an offset within the buffer.  Here 'old' and 'head'
+	 * are adjusted to match the full trace case which expects that 'old' is
+	 * always less than 'head'.
+	 */
+	if (wrapped) {
+		*old = *head;
+		*head += mm->len;
+	} else {
+		if (mm->mask)
+			*old &= mm->mask;
+		else
+			*old %= mm->len;
+		if (*old > *head)
+			*head += mm->len;
+	}
+
+	pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+		  __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+	return 0;
+
+out_err:
+	pr_err("%s: failed, error %d\n", __func__, err);
+	return err;
+}
+
+static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(btsr->evlist, evsel) {
+		if (evsel->attr.type == btsr->intel_bts_pmu->type)
+			return perf_evlist__enable_event_idx(btsr->evlist,
+							     evsel, idx);
+	}
+	return -EINVAL;
+}
+
+struct auxtrace_record *intel_bts_recording_init(int *err)
+{
+	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
+	struct intel_bts_recording *btsr;
+
+	if (!intel_bts_pmu)
+		return NULL;
+
+	btsr = zalloc(sizeof(struct intel_bts_recording));
+	if (!btsr) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.recording_options = intel_bts_recording_options;
+	btsr->itr.info_priv_size = intel_bts_info_priv_size;
+	btsr->itr.info_fill = intel_bts_info_fill;
+	btsr->itr.free = intel_bts_recording_free;
+	btsr->itr.snapshot_start = intel_bts_snapshot_start;
+	btsr->itr.snapshot_finish = intel_bts_snapshot_finish;
+	btsr->itr.find_snapshot = intel_bts_find_snapshot;
+	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
+	btsr->itr.reference = intel_bts_reference;
+	btsr->itr.read_finish = intel_bts_read_finish;
+	btsr->itr.alignment = sizeof(struct branch);
+	return &btsr->itr;
+}

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.c

+/*
+ * intel-bts.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, 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.
+ *
+ */
+
+#include <endian.h>
+#include <byteswap.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "cpumap.h"
+#include "color.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "session.h"
+#include "util.h"
+#include "thread.h"
+#include "thread-stack.h"
+#include "debug.h"
+#include "tsc.h"
+#include "auxtrace.h"
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
+#include "intel-bts.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+#define INTEL_BTS_ERR_NOINSN  5
+#define INTEL_BTS_ERR_LOST    9
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define le64_to_cpu bswap_64
+#else
+#define le64_to_cpu
+#endif
+
+struct intel_bts {
+	struct auxtrace			auxtrace;
+	struct auxtrace_queues		queues;
+	struct auxtrace_heap		heap;
+	u32				auxtrace_type;
+	struct perf_session		*session;
+	struct machine			*machine;
+	bool				sampling_mode;
+	bool				snapshot_mode;
+	bool				data_queued;
+	u32				pmu_type;
+	struct perf_tsc_conversion	tc;
+	bool				cap_user_time_zero;
+	struct itrace_synth_opts	synth_opts;
+	bool				sample_branches;
+	u32				branches_filter;
+	u64				branches_sample_type;
+	u64				branches_id;
+	size_t				branches_event_size;
+	bool				synth_needs_swap;
+};
+
+struct intel_bts_queue {
+	struct intel_bts	*bts;
+	unsigned int		queue_nr;
+	struct auxtrace_buffer	*buffer;
+	bool			on_heap;
+	bool			done;
+	pid_t			pid;
+	pid_t			tid;
+	int			cpu;
+	u64			time;
+	struct intel_pt_insn	intel_pt_insn;
+	u32			sample_flags;
+};
+
+struct branch {
+	u64 from;
+	u64 to;
+	u64 misc;
+};
+
+static void intel_bts_dump(struct intel_bts *bts __maybe_unused,
+			   unsigned char *buf, size_t len)
+{
+	struct branch *branch;
+	size_t i, pos = 0, br_sz = sizeof(struct branch), sz;
+	const char *color = PERF_COLOR_BLUE;
+
+	color_fprintf(stdout, color,
+		      ". ... Intel BTS data: size %zu bytes\n",
+		      len);
+
+	while (len) {
+		if (len >= br_sz)
+			sz = br_sz;
+		else
+			sz = len;
+		printf(".");
+		color_fprintf(stdout, color, "  %08x: ", pos);
+		for (i = 0; i < sz; i++)
+			color_fprintf(stdout, color, " %02x", buf[i]);
+		for (; i < br_sz; i++)
+			color_fprintf(stdout, color, "   ");
+		if (len >= br_sz) {
+			branch = (struct branch *)buf;
+			color_fprintf(stdout, color, " %"PRIx64" -> %"PRIx64" %s\n",
+				      le64_to_cpu(branch->from),
+				      le64_to_cpu(branch->to),
+				      le64_to_cpu(branch->misc) & 0x10 ?
+							"pred" : "miss");
+		} else {
+			color_fprintf(stdout, color, " Bad record!\n");
+		}
+		pos += sz;
+		buf += sz;
+		len -= sz;
+	}
+}
+
+static void intel_bts_dump_event(struct intel_bts *bts, unsigned char *buf,
+				 size_t len)
+{
+	printf(".\n");
+	intel_bts_dump(bts, buf, len);
+}
+
+static int intel_bts_lost(struct intel_bts *bts, struct perf_sample *sample)
+{
+	union perf_event event;
+	int err;
+
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     INTEL_BTS_ERR_LOST, sample->cpu, sample->pid,
+			     sample->tid, 0, "Lost trace data");
+
+	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
+	if (err)
+		pr_err("Intel BTS: failed to deliver error event, error %d\n",
+		       err);
+
+	return err;
+}
+
+static struct intel_bts_queue *intel_bts_alloc_queue(struct intel_bts *bts,
+						     unsigned int queue_nr)
+{
+	struct intel_bts_queue *btsq;
+
+	btsq = zalloc(sizeof(struct intel_bts_queue));
+	if (!btsq)
+		return NULL;
+
+	btsq->bts = bts;
+	btsq->queue_nr = queue_nr;
+	btsq->pid = -1;
+	btsq->tid = -1;
+	btsq->cpu = -1;
+
+	return btsq;
+}
+
+static int intel_bts_setup_queue(struct intel_bts *bts,
+				 struct auxtrace_queue *queue,
+				 unsigned int queue_nr)
+{
+	struct intel_bts_queue *btsq = queue->priv;
+
+	if (list_empty(&queue->head))
+		return 0;
+
+	if (!btsq) {
+		btsq = intel_bts_alloc_queue(bts, queue_nr);
+		if (!btsq)
+			return -ENOMEM;
+		queue->priv = btsq;
+
+		if (queue->cpu != -1)
+			btsq->cpu = queue->cpu;
+		btsq->tid = queue->tid;
+	}
+
+	if (bts->sampling_mode)
+		return 0;
+
+	if (!btsq->on_heap && !btsq->buffer) {
+		int ret;
+
+		btsq->buffer = auxtrace_buffer__next(queue, NULL);
+		if (!btsq->buffer)
+			return 0;
+
+		ret = auxtrace_heap__add(&bts->heap, queue_nr,
+					 btsq->buffer->reference);
+		if (ret)
+			return ret;
+		btsq->on_heap = true;
+	}
+
+	return 0;
+}
+
+static int intel_bts_setup_queues(struct intel_bts *bts)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < bts->queues.nr_queues; i++) {
+		ret = intel_bts_setup_queue(bts, &bts->queues.queue_array[i],
+					    i);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static inline int intel_bts_update_queues(struct intel_bts *bts)
+{
+	if (bts->queues.new_data) {
+		bts->queues.new_data = false;
+		return intel_bts_setup_queues(bts);
+	}
+	return 0;
+}
+
+static unsigned char *intel_bts_find_overlap(unsigned char *buf_a, size_t len_a,
+					     unsigned char *buf_b, size_t len_b)
+{
+	size_t offs, len;
+
+	if (len_a > len_b)
+		offs = len_a - len_b;
+	else
+		offs = 0;
+
+	for (; offs < len_a; offs += sizeof(struct branch)) {
+		len = len_a - offs;
+		if (!memcmp(buf_a + offs, buf_b, len))
+			return buf_b + len;
+	}
+
+	return buf_b;
+}
+
+static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
+				    struct auxtrace_buffer *b)
+{
+	struct auxtrace_buffer *a;
+	void *start;
+
+	if (b->list.prev == &queue->head)
+		return 0;
+	a = list_entry(b->list.prev, struct auxtrace_buffer, list);
+	start = intel_bts_find_overlap(a->data, a->size, b->data, b->size);
+	if (!start)
+		return -EINVAL;
+	b->use_size = b->data + b->size - start;
+	b->use_data = start;
+	return 0;
+}
+
+static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
+					 struct branch *branch)
+{
+	int ret;
+	struct intel_bts *bts = btsq->bts;
+	union perf_event event;
+	struct perf_sample sample = { .ip = 0, };
+
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = PERF_RECORD_MISC_USER;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
+	sample.ip = le64_to_cpu(branch->from);
+	sample.pid = btsq->pid;
+	sample.tid = btsq->tid;
+	sample.addr = le64_to_cpu(branch->to);
+	sample.id = btsq->bts->branches_id;
+	sample.stream_id = btsq->bts->branches_id;
+	sample.period = 1;
+	sample.cpu = btsq->cpu;
+	sample.flags = btsq->sample_flags;
+	sample.insn_len = btsq->intel_pt_insn.length;
+
+	if (bts->synth_opts.inject) {
+		event.sample.header.size = bts->branches_event_size;
+		ret = perf_event__synthesize_sample(&event,
+						    bts->branches_sample_type,
+						    0, &sample,
+						    bts->synth_needs_swap);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(bts->session, &event, &sample);
+	if (ret)
+		pr_err("Intel BTS: failed to deliver branch event, error %d\n",
+		       ret);
+
+	return ret;
+}
+
+static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
+{
+	struct machine *machine = btsq->bts->machine;
+	struct thread *thread;
+	struct addr_location al;
+	unsigned char buf[1024];
+	size_t bufsz;
+	ssize_t len;
+	int x86_64;
+	uint8_t cpumode;
+	int err = -1;
+
+	bufsz = intel_pt_insn_max_size();
+
+	if (machine__kernel_ip(machine, ip))
+		cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		cpumode = PERF_RECORD_MISC_USER;
+
+	thread = machine__find_thread(machine, -1, btsq->tid);
+	if (!thread)
+		return -1;
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
+	if (!al.map || !al.map->dso)
+		goto out_put;
+
+	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz);
+	if (len <= 0)
+		goto out_put;
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map, machine->symbol_filter);
+
+	x86_64 = al.map->dso->is_64_bit;
+
+	if (intel_pt_get_insn(buf, len, x86_64, &btsq->intel_pt_insn))
+		goto out_put;
+
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
+}
+
+static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
+				 pid_t tid, u64 ip)
+{
+	union perf_event event;
+	int err;
+
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     INTEL_BTS_ERR_NOINSN, cpu, pid, tid, ip,
+			     "Failed to get instruction");
+
+	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
+	if (err)
+		pr_err("Intel BTS: failed to deliver error event, error %d\n",
+		       err);
+
+	return err;
+}
+
+static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
+				     struct branch *branch)
+{
+	int err;
+
+	if (!branch->from) {
+		if (branch->to)
+			btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_TRACE_BEGIN;
+		else
+			btsq->sample_flags = 0;
+		btsq->intel_pt_insn.length = 0;
+	} else if (!branch->to) {
+		btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+				     PERF_IP_FLAG_TRACE_END;
+		btsq->intel_pt_insn.length = 0;
+	} else {
+		err = intel_bts_get_next_insn(btsq, branch->from);
+		if (err) {
+			btsq->sample_flags = 0;
+			btsq->intel_pt_insn.length = 0;
+			if (!btsq->bts->synth_opts.errors)
+				return 0;
+			err = intel_bts_synth_error(btsq->bts, btsq->cpu,
+						    btsq->pid, btsq->tid,
+						    branch->from);
+			return err;
+		}
+		btsq->sample_flags = intel_pt_insn_type(btsq->intel_pt_insn.op);
+		/* Check for an async branch into the kernel */
+		if (!machine__kernel_ip(btsq->bts->machine, branch->from) &&
+		    machine__kernel_ip(btsq->bts->machine, branch->to) &&
+		    btsq->sample_flags != (PERF_IP_FLAG_BRANCH |
+					   PERF_IP_FLAG_CALL |
+					   PERF_IP_FLAG_SYSCALLRET))
+			btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_CALL |
+					     PERF_IP_FLAG_ASYNC |
+					     PERF_IP_FLAG_INTERRUPT;
+	}
+
+	return 0;
+}
+
+static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
+				    struct auxtrace_buffer *buffer)
+{
+	struct branch *branch;
+	size_t sz, bsz = sizeof(struct branch);
+	u32 filter = btsq->bts->branches_filter;
+	int err = 0;
+
+	if (buffer->use_data) {
+		sz = buffer->use_size;
+		branch = buffer->use_data;
+	} else {
+		sz = buffer->size;
+		branch = buffer->data;
+	}
+
+	if (!btsq->bts->sample_branches)
+		return 0;
+
+	for (; sz > bsz; branch += 1, sz -= bsz) {
+		if (!branch->from && !branch->to)
+			continue;
+		intel_bts_get_branch_type(btsq, branch);
+		if (filter && !(filter & btsq->sample_flags))
+			continue;
+		err = intel_bts_synth_branch_sample(btsq, branch);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
+{
+	struct auxtrace_buffer *buffer = btsq->buffer, *old_buffer = buffer;
+	struct auxtrace_queue *queue;
+	struct thread *thread;
+	int err;
+
+	if (btsq->done)
+		return 1;
+
+	if (btsq->pid == -1) {
+		thread = machine__find_thread(btsq->bts->machine, -1,
+					      btsq->tid);
+		if (thread)
+			btsq->pid = thread->pid_;
+	} else {
+		thread = machine__findnew_thread(btsq->bts->machine, btsq->pid,
+						 btsq->tid);
+	}
+
+	queue = &btsq->bts->queues.queue_array[btsq->queue_nr];
+
+	if (!buffer)
+		buffer = auxtrace_buffer__next(queue, NULL);
+
+	if (!buffer) {
+		if (!btsq->bts->sampling_mode)
+			btsq->done = 1;
+		err = 1;
+		goto out_put;
+	}
+
+	/* Currently there is no support for split buffers */
+	if (buffer->consecutive) {
+		err = -EINVAL;
+		goto out_put;
+	}
+
+	if (!buffer->data) {
+		int fd = perf_data_file__fd(btsq->bts->session->file);
+
+		buffer->data = auxtrace_buffer__get_data(buffer, fd);
+		if (!buffer->data) {
+			err = -ENOMEM;
+			goto out_put;
+		}
+	}
+
+	if (btsq->bts->snapshot_mode && !buffer->consecutive &&
+	    intel_bts_do_fix_overlap(queue, buffer)) {
+		err = -ENOMEM;
+		goto out_put;
+	}
+
+	if (!btsq->bts->synth_opts.callchain && thread &&
+	    (!old_buffer || btsq->bts->sampling_mode ||
+	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
+		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
+
+	err = intel_bts_process_buffer(btsq, buffer);
+
+	auxtrace_buffer__drop_data(buffer);
+
+	btsq->buffer = auxtrace_buffer__next(queue, buffer);
+	if (btsq->buffer) {
+		if (timestamp)
+			*timestamp = btsq->buffer->reference;
+	} else {
+		if (!btsq->bts->sampling_mode)
+			btsq->done = 1;
+	}
+out_put:
+	thread__put(thread);
+	return err;
+}
+
+static int intel_bts_flush_queue(struct intel_bts_queue *btsq)
+{
+	u64 ts = 0;
+	int ret;
+
+	while (1) {
+		ret = intel_bts_process_queue(btsq, &ts);
+		if (ret < 0)
+			return ret;
+		if (ret)
+			break;
+	}
+	return 0;
+}
+
+static int intel_bts_process_tid_exit(struct intel_bts *bts, pid_t tid)
+{
+	struct auxtrace_queues *queues = &bts->queues;
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct auxtrace_queue *queue = &bts->queues.queue_array[i];
+		struct intel_bts_queue *btsq = queue->priv;
+
+		if (btsq && btsq->tid == tid)
+			return intel_bts_flush_queue(btsq);
+	}
+	return 0;
+}
+
+static int intel_bts_process_queues(struct intel_bts *bts, u64 timestamp)
+{
+	while (1) {
+		unsigned int queue_nr;
+		struct auxtrace_queue *queue;
+		struct intel_bts_queue *btsq;
+		u64 ts = 0;
+		int ret;
+
+		if (!bts->heap.heap_cnt)
+			return 0;
+
+		if (bts->heap.heap_array[0].ordinal > timestamp)
+			return 0;
+
+		queue_nr = bts->heap.heap_array[0].queue_nr;
+		queue = &bts->queues.queue_array[queue_nr];
+		btsq = queue->priv;
+
+		auxtrace_heap__pop(&bts->heap);
+
+		ret = intel_bts_process_queue(btsq, &ts);
+		if (ret < 0) {
+			auxtrace_heap__add(&bts->heap, queue_nr, ts);
+			return ret;
+		}
+
+		if (!ret) {
+			ret = auxtrace_heap__add(&bts->heap, queue_nr, ts);
+			if (ret < 0)
+				return ret;
+		} else {
+			btsq->on_heap = false;
+		}
+	}
+
+	return 0;
+}
+
+static int intel_bts_process_event(struct perf_session *session,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct perf_tool *tool)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+	u64 timestamp;
+	int err;
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events) {
+		pr_err("Intel BTS requires ordered events\n");
+		return -EINVAL;
+	}
+
+	if (sample->time && sample->time != (u64)-1)
+		timestamp = perf_time_to_tsc(sample->time, &bts->tc);
+	else
+		timestamp = 0;
+
+	err = intel_bts_update_queues(bts);
+	if (err)
+		return err;
+
+	err = intel_bts_process_queues(bts, timestamp);
+	if (err)
+		return err;
+	if (event->header.type == PERF_RECORD_EXIT) {
+		err = intel_bts_process_tid_exit(bts, event->comm.tid);
+		if (err)
+			return err;
+	}
+
+	if (event->header.type == PERF_RECORD_AUX &&
+	    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
+	    bts->synth_opts.errors)
+		err = intel_bts_lost(bts, sample);
+
+	return err;
+}
+
+static int intel_bts_process_auxtrace_event(struct perf_session *session,
+					    union perf_event *event,
+					    struct perf_tool *tool __maybe_unused)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+
+	if (bts->sampling_mode)
+		return 0;
+
+	if (!bts->data_queued) {
+		struct auxtrace_buffer *buffer;
+		off_t data_offset;
+		int fd = perf_data_file__fd(session->file);
+		int err;
+
+		if (perf_data_file__is_pipe(session->file)) {
+			data_offset = 0;
+		} else {
+			data_offset = lseek(fd, 0, SEEK_CUR);
+			if (data_offset == -1)
+				return -errno;
+		}
+
+		err = auxtrace_queues__add_event(&bts->queues, session, event,
+						 data_offset, &buffer);
+		if (err)
+			return err;
+
+		/* Dump here now we have copied a piped trace out of the pipe */
+		if (dump_trace) {
+			if (auxtrace_buffer__get_data(buffer, fd)) {
+				intel_bts_dump_event(bts, buffer->data,
+						     buffer->size);
+				auxtrace_buffer__put_data(buffer);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int intel_bts_flush(struct perf_session *session __maybe_unused,
+			   struct perf_tool *tool __maybe_unused)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+	int ret;
+
+	if (dump_trace || bts->sampling_mode)
+		return 0;
+
+	if (!tool->ordered_events)
+		return -EINVAL;
+
+	ret = intel_bts_update_queues(bts);
+	if (ret < 0)
+		return ret;
+
+	return intel_bts_process_queues(bts, MAX_TIMESTAMP);
+}
+
+static void intel_bts_free_queue(void *priv)
+{
+	struct intel_bts_queue *btsq = priv;
+
+	if (!btsq)
+		return;
+	free(btsq);
+}
+
+static void intel_bts_free_events(struct perf_session *session)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+	struct auxtrace_queues *queues = &bts->queues;
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		intel_bts_free_queue(queues->queue_array[i].priv);
+		queues->queue_array[i].priv = NULL;
+	}
+	auxtrace_queues__free(queues);
+}
+
+static void intel_bts_free(struct perf_session *session)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+
+	auxtrace_heap__free(&bts->heap);
+	intel_bts_free_events(session);
+	session->auxtrace = NULL;
+	free(bts);
+}
+
+struct intel_bts_synth {
+	struct perf_tool dummy_tool;
+	struct perf_session *session;
+};
+
+static int intel_bts_event_synth(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_sample *sample __maybe_unused,
+				 struct machine *machine __maybe_unused)
+{
+	struct intel_bts_synth *intel_bts_synth =
+			container_of(tool, struct intel_bts_synth, dummy_tool);
+
+	return perf_session__deliver_synth_event(intel_bts_synth->session,
+						 event, NULL);
+}
+
+static int intel_bts_synth_event(struct perf_session *session,
+				 struct perf_event_attr *attr, u64 id)
+{
+	struct intel_bts_synth intel_bts_synth;
+
+	memset(&intel_bts_synth, 0, sizeof(struct intel_bts_synth));
+	intel_bts_synth.session = session;
+
+	return perf_event__synthesize_attr(&intel_bts_synth.dummy_tool, attr, 1,
+					   &id, intel_bts_event_synth);
+}
+
+static int intel_bts_synth_events(struct intel_bts *bts,
+				  struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	bool found = false;
+	u64 id;
+	int err;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type == bts->pmu_type && evsel->ids) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_debug("There are no selected events with Intel BTS data\n");
+		return 0;
+	}
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.size = sizeof(struct perf_event_attr);
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+			    PERF_SAMPLE_PERIOD;
+	attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+	attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
+	attr.exclude_user = evsel->attr.exclude_user;
+	attr.exclude_kernel = evsel->attr.exclude_kernel;
+	attr.exclude_hv = evsel->attr.exclude_hv;
+	attr.exclude_host = evsel->attr.exclude_host;
+	attr.exclude_guest = evsel->attr.exclude_guest;
+	attr.sample_id_all = evsel->attr.sample_id_all;
+	attr.read_format = evsel->attr.read_format;
+
+	id = evsel->id[0] + 1000000000;
+	if (!id)
+		id = 1;
+
+	if (bts->synth_opts.branches) {
+		attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+		attr.sample_period = 1;
+		attr.sample_type |= PERF_SAMPLE_ADDR;
+		pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+			 id, (u64)attr.sample_type);
+		err = intel_bts_synth_event(session, &attr, id);
+		if (err) {
+			pr_err("%s: failed to synthesize 'branches' event type\n",
+			       __func__);
+			return err;
+		}
+		bts->sample_branches = true;
+		bts->branches_sample_type = attr.sample_type;
+		bts->branches_id = id;
+		/*
+		 * We only use sample types from PERF_SAMPLE_MASK so we can use
+		 * __perf_evsel__sample_size() here.
+		 */
+		bts->branches_event_size = sizeof(struct sample_event) +
+				__perf_evsel__sample_size(attr.sample_type);
+	}
+
+	bts->synth_needs_swap = evsel->needs_swap;
+
+	return 0;
+}
+
+static const char * const intel_bts_info_fmts[] = {
+	[INTEL_BTS_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
+	[INTEL_BTS_TIME_SHIFT]		= "  Time Shift         %"PRIu64"\n",
+	[INTEL_BTS_TIME_MULT]		= "  Time Muliplier     %"PRIu64"\n",
+	[INTEL_BTS_TIME_ZERO]		= "  Time Zero          %"PRIu64"\n",
+	[INTEL_BTS_CAP_USER_TIME_ZERO]	= "  Cap Time Zero      %"PRId64"\n",
+	[INTEL_BTS_SNAPSHOT_MODE]	= "  Snapshot mode      %"PRId64"\n",
+};
+
+static void intel_bts_print_info(u64 *arr, int start, int finish)
+{
+	int i;
+
+	if (!dump_trace)
+		return;
+
+	for (i = start; i <= finish; i++)
+		fprintf(stdout, intel_bts_info_fmts[i], arr[i]);
+}
+
+u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE];
+
+int intel_bts_process_auxtrace_info(union perf_event *event,
+				    struct perf_session *session)
+{
+	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	size_t min_sz = sizeof(u64) * INTEL_BTS_SNAPSHOT_MODE;
+	struct intel_bts *bts;
+	int err;
+
+	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+					min_sz)
+		return -EINVAL;
+
+	bts = zalloc(sizeof(struct intel_bts));
+	if (!bts)
+		return -ENOMEM;
+
+	err = auxtrace_queues__init(&bts->queues);
+	if (err)
+		goto err_free;
+
+	bts->session = session;
+	bts->machine = &session->machines.host; /* No kvm support */
+	bts->auxtrace_type = auxtrace_info->type;
+	bts->pmu_type = auxtrace_info->priv[INTEL_BTS_PMU_TYPE];
+	bts->tc.time_shift = auxtrace_info->priv[INTEL_BTS_TIME_SHIFT];
+	bts->tc.time_mult = auxtrace_info->priv[INTEL_BTS_TIME_MULT];
+	bts->tc.time_zero = auxtrace_info->priv[INTEL_BTS_TIME_ZERO];
+	bts->cap_user_time_zero =
+			auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO];
+	bts->snapshot_mode = auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE];
+
+	bts->sampling_mode = false;
+
+	bts->auxtrace.process_event = intel_bts_process_event;
+	bts->auxtrace.process_auxtrace_event = intel_bts_process_auxtrace_event;
+	bts->auxtrace.flush_events = intel_bts_flush;
+	bts->auxtrace.free_events = intel_bts_free_events;
+	bts->auxtrace.free = intel_bts_free;
+	session->auxtrace = &bts->auxtrace;
+
+	intel_bts_print_info(&auxtrace_info->priv[0], INTEL_BTS_PMU_TYPE,
+			     INTEL_BTS_SNAPSHOT_MODE);
+
+	if (dump_trace)
+		return 0;
+
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set)
+		bts->synth_opts = *session->itrace_synth_opts;
+	else
+		itrace_synth_opts__set_default(&bts->synth_opts);
+
+	if (bts->synth_opts.calls)
+		bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+					PERF_IP_FLAG_TRACE_END;
+	if (bts->synth_opts.returns)
+		bts->branches_filter |= PERF_IP_FLAG_RETURN |
+					PERF_IP_FLAG_TRACE_BEGIN;
+
+	err = intel_bts_synth_events(bts, session);
+	if (err)
+		goto err_free_queues;
+
+	err = auxtrace_queues__process_index(&bts->queues, session);
+	if (err)
+		goto err_free_queues;
+
+	if (bts->queues.populated)
+		bts->data_queued = true;
+
+	return 0;
+
+err_free_queues:
+	auxtrace_queues__free(&bts->queues);
+	session->auxtrace = NULL;
+err_free:
+	free(bts);
+	return err;
+}

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