perf tools: Introduce an abstraction for AUX Area and Instruction Tracing

index 0ec8c3b..7ec1bf9 100644
@@ -695,7 +695,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
-	return perf_mmap__read_head(md) == md->prev;
+	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)

index 3664aba..8eea2d6 100644
@@ -148,9 +148,10 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
-				   u64 sample_type, const char *sample_msg,
-				   enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+				      u64 sample_type, const char *sample_msg,
+				      enum perf_output_field field,
+				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int type = attr->type;

@@ -160,6 +161,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 		return 0;
 
 	if (output[type].user_set) {
+		if (allow_user_set)
+			return 0;
 		evname = perf_evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",

@@ -177,10 +180,22 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 	return 0;
 }
 
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
+{
+	return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+					  false);
+}
+
 static int perf_evsel__check_attr(struct perf_evsel *evsel,
 				  struct perf_session *session)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool allow_user_set;
+
+	allow_user_set = perf_header__has_feat(&session->header,
+					       HEADER_AUXTRACE);
 
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))

@@ -193,8 +208,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
-					PERF_OUTPUT_ADDR))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {

@@ -231,8 +246,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
-					PERF_OUTPUT_CPU))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					   PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(PERIOD) &&

index 476cdf7..625c913 100644
@@ -36,6 +36,8 @@
 #include "util/data.h"
 #include "arch/common.h"
 
+#include "util/auxtrace.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 

@@ -585,6 +587,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = {0};
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;

@@ -607,6 +610,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},

@@ -717,6 +723,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
+	OPT_CALLBACK_OPTARG('Z', "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	struct perf_data_file file = {

@@ -761,6 +770,8 @@ repeat:
 					       report.queue_size);
 	}
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,

index c5f6515..6d4bbde 100644
@@ -122,6 +122,18 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 						  tool);
 	int ret;
 
+	if (!inject->output.is_pipe) {
+		off_t offset;
+
+		offset = lseek(inject->output.fd, 0, SEEK_CUR);
+		if (offset == -1)
+			return -errno;
+		ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+						     event, offset);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
 		ret = output_bytes(inject, event, event->header.size);
 		if (ret < 0)

@@ -487,6 +499,9 @@ static int __cmd_inject(struct perf_inject *inject)
 		output_data_offset = 4096;
 	}
 
+	if (!inject->itrace_synth_opts.set)
+		auxtrace_index__free(&session->auxtrace_index);
+
 	if (!file_out->is_pipe)
 		lseek(fd, output_data_offset, SEEK_SET);
 

index 4c9aaa1..c8c784c 100644
@@ -117,9 +117,24 @@ static int record__process_auxtrace(struct perf_tool *tool,
 				    size_t len1, void *data2, size_t len2)
 {
 	struct record *rec = container_of(tool, struct record, tool);
+	struct perf_data_file *file = &rec->file;
 	size_t padding;
 	u8 pad[8] = {0};
 
+	if (!perf_data_file__is_pipe(file)) {
+		off_t file_offset;
+		int fd = perf_data_file__fd(file);
+		int err;
+
+		file_offset = lseek(fd, 0, SEEK_CUR);
+		if (file_offset == -1)
+			return -1;
+		err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+						     event, file_offset);
+		if (err)
+			return err;
+	}
+
 	/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
 	padding = (len1 + len2) & 7;
 	if (padding)

228 lines not on this page · raw message

index 53b60a6..b9e4b9d 100644
@@ -80,6 +80,32 @@ struct itrace_synth_opts {
 };
 
 /**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+	u64			file_offset;
+	u64			sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+	struct list_head	list;
+	size_t			nr;
+	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
  * struct auxtrace - session callbacks to allow AUX area data decoding.
  * @process_event: lets the decoder see all session events
  * @flush_events: process any remaining data

@@ -321,6 +347,8 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 			       union perf_event *event, off_t data_offset,
 			       struct auxtrace_buffer **buffer_ptr);
 void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session);
 struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
 					      struct auxtrace_buffer *buffer);
 void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);

@@ -361,6 +389,13 @@ int auxtrace_record__info_fill(struct auxtrace_record *itr,
 void auxtrace_record__free(struct auxtrace_record *itr);
 u64 auxtrace_record__reference(struct auxtrace_record *itr);
 
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+				   off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
 void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
 			  const char *msg);

index 589c280..3f0d809 100644
@@ -869,11 +869,18 @@ static int write_branch_stack(int fd __maybe_unused,
 	return 0;
 }
 
-static int write_auxtrace(int fd __maybe_unused,
-			  struct perf_header *h __maybe_unused,
+static int write_auxtrace(int fd, struct perf_header *h,
 			  struct perf_evlist *evlist __maybe_unused)
 {
-	return 0;
+	struct perf_session *session;
+	int err;
+
+	session = container_of(h, struct perf_session, header);
+
+	err = auxtrace_index__write(fd, &session->auxtrace_index);
+	if (err < 0)
+		pr_err("Failed to write auxtrace index\n");
+	return err;
 }
 
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,

@@ -1834,6 +1841,22 @@ out_free:
 	return ret;
 }
 
+static int process_auxtrace(struct perf_file_section *section,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(ph, struct perf_session, header);
+
+	err = auxtrace_index__process(fd, section->size, session,
+				      ph->needs_swap);
+	if (err < 0)
+		pr_err("Failed to process auxtrace index\n");
+	return err;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);

@@ -1874,7 +1897,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
-	FEAT_OPA(HEADER_AUXTRACE,	auxtrace),
+	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 };
 
 struct header_print_data {

index 90fa567..b6972b1 100644
@@ -120,6 +120,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 
 	session->repipe = repipe;
 	session->tool   = tool;
+	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
 	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 

@@ -187,6 +188,7 @@ static void perf_session_env__delete(struct perf_session_env *env)
 void perf_session__delete(struct perf_session *session)
 {
 	auxtrace__free(session);
+	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
 	perf_session_env__delete(&session->header.env);

index 9ed5135..b44afc7 100644
@@ -24,6 +24,7 @@ struct perf_session {
 	struct perf_evlist	*evlist;
 	struct auxtrace		*auxtrace;
 	struct itrace_synth_opts *itrace_synth_opts;
+	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
 	bool			repipe;
 	bool			one_mmap;

index feb420f..9fe93c8 100644
@@ -69,6 +69,15 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
+
+	/*
+	 * We take all buildids when the file contains AUX area tracing data
+	 * because we do not decode the trace because it would take too long.
+	 */
+	if (!perf_data_file__is_pipe(&file) &&
+	    perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		with_hits = false;
+
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID

index 6d4bbde..cc905f1 100644
@@ -27,6 +27,7 @@ struct perf_inject {
 	struct perf_session	*session;
 	bool			build_ids;
 	bool			sched_stat;
+	bool			have_auxtrace;
 	const char		*input_name;
 	struct perf_data_file	output;
 	u64			bytes_written;

@@ -122,6 +123,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 						  tool);
 	int ret;
 
+	inject->have_auxtrace = true;
+
 	if (!inject->output.is_pipe) {
 		off_t offset;
 

@@ -508,9 +511,12 @@ static int __cmd_inject(struct perf_inject *inject)
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids)
+		if (inject->build_ids) {
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
+			if (inject->have_auxtrace)
+				dsos__hit_all(session);
+		}
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag.

index c8c784c..4d0ebbb 100644
@@ -620,8 +620,16 @@ out_child:
 	if (!err && !file->is_pipe) {
 		rec->session->header.data_size += rec->bytes_written;
 
-		if (!rec->no_buildid)
+		if (!rec->no_buildid) {
 			process_buildids(rec);
+			/*
+			 * We take all buildids when the file contains
+			 * AUX area tracing data because we do not decode the
+			 * trace because it would take too long.
+			 */
+			if (rec->opts.full_auxtrace)
+				dsos__hit_all(rec->session);
+		}
 		perf_session__write_header(rec->session, rec->evlist, fd, true);
 	}
 

71 lines not on this page · raw message

index 4d0ebbb..dbb2c02 100644
@@ -112,6 +112,8 @@ out:
 	return rc;
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+
 static int record__process_auxtrace(struct perf_tool *tool,
 				    union perf_event *event, void *data1,
 				    size_t len1, void *data2, size_t len2)

@@ -165,6 +167,17 @@ static int record__auxtrace_mmap_read(struct record *rec,
 	return 0;
 }
 
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+			       struct auxtrace_mmap *mm __maybe_unused)
+{
+	return 0;
+}
+
+#endif
+
 static volatile int done = 0;
 static volatile int signr = -1;
 static volatile int child_finished = 0;

144 lines not on this page · raw message

index f94af20..2883376 100644
@@ -889,6 +889,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 {
 	synth_opts->instructions = true;
 	synth_opts->branches = true;
+	synth_opts->transactions = true;
 	synth_opts->errors = true;
 	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;

@@ -961,6 +962,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'b':
 			synth_opts->branches = true;
 			break;
+		case 'x':
+			synth_opts->transactions = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;

@@ -976,7 +980,6 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			synth_opts->returns = true;
 			break;
 		case 'g':
-			synth_opts->instructions = true;
 			synth_opts->callchain = true;
 			synth_opts->callchain_sz =
 					PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;

index 77b4699..8c6cbb1 100644
@@ -54,6 +54,7 @@ enum itrace_period_type {
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
  * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log

@@ -69,6 +70,7 @@ struct itrace_synth_opts {
 	bool			inject;
 	bool			instructions;
 	bool			branches;
+	bool			transactions;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;

index 7c7a7ee..3e8f730 100644
@@ -558,6 +558,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,
 			.lost		= perf_event__repipe,
+			.aux		= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,

index 32323e5..724ffde 100644
@@ -23,6 +23,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_FORK]			= "FORK",
 	[PERF_RECORD_READ]			= "READ",
 	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_AUX]			= "AUX",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",

@@ -695,6 +696,14 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_event(machine, event, sample);
 }
 
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample __maybe_unused,
+			    struct machine *machine)
+{
+	return machine__process_aux_event(machine, event);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",

@@ -758,6 +767,15 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 	return machine__process_exit_event(machine, event, sample);
 }
 
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+		       event->aux.aux_offset, event->aux.aux_size,
+		       event->aux.flags,
+		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",

@@ -777,6 +795,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
+	case PERF_RECORD_AUX:
+		ret += perf_event__fprintf_aux(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}

index 80e9f59..b3c350e 100644
@@ -323,6 +323,13 @@ struct auxtrace_error_event {
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
+struct aux_event {
+	struct perf_event_header header;
+	u64	aux_offset;
+	u64	aux_size;
+	u64	flags;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;

@@ -341,6 +348,7 @@ union perf_event {
 	struct auxtrace_info_event	auxtrace_info;
 	struct auxtrace_event		auxtrace;
 	struct auxtrace_error_event	auxtrace_error;
+	struct aux_event		aux;
 };
 
 void perf_event__print_totals(void);

@@ -376,6 +384,10 @@ int perf_event__process_lost(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,

@@ -433,6 +445,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,

index 527e032..a7ad511 100644
@@ -486,6 +486,14 @@ machine__module_dso(struct machine *machine, struct kmod_path *m,
 	return dso;
 }
 
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+			       union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_aux(event, stdout);
+	return 0;
+}
+
 struct map *machine__new_module(struct machine *machine, u64 start,
 				const char *filename)
 {

@@ -1331,6 +1339,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_exit_event(machine, event, sample); break;
 	case PERF_RECORD_LOST:
 		ret = machine__process_lost_event(machine, event, sample); break;
+	case PERF_RECORD_AUX:
+		ret = machine__process_aux_event(machine, event); break;
 	default:
 		ret = -1;
 		break;

index 6d64ced..fc5432a 100644
@@ -81,6 +81,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_lost_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+			       union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,

index b6972b1..0b4646c 100644
@@ -325,6 +325,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->exit = process_event_stub;
 	if (tool->lost == NULL)
 		tool->lost = perf_event__process_lost;
+	if (tool->aux == NULL)
+		tool->aux = perf_event__process_aux;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)

@@ -443,6 +445,16 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+	event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+	event->aux.aux_size   = bswap_64(event->aux.aux_size);
+	event->aux.flags      = bswap_64(event->aux.flags);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->aux + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {

@@ -580,6 +592,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,

@@ -1029,6 +1042,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
+	case PERF_RECORD_AUX:
+		return tool->aux(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;

index 20afe19..8288caf 100644
@@ -43,6 +43,7 @@ struct perf_tool {
 			fork,
 			exit,
 			lost,
+			aux,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;

index 3e8f730..d6a47e8 100644
@@ -559,6 +559,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.exit		= perf_event__repipe,
 			.lost		= perf_event__repipe,
 			.aux		= perf_event__repipe,
+			.itrace_start	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,

index 724ffde..db52609 100644
@@ -24,6 +24,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_READ]			= "READ",
 	[PERF_RECORD_SAMPLE]			= "SAMPLE",
 	[PERF_RECORD_AUX]			= "AUX",
+	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",

@@ -704,6 +705,14 @@ int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
 	return machine__process_aux_event(machine, event);
 }
 
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine)
+{
+	return machine__process_itrace_start_event(machine, event);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",

@@ -776,6 +785,12 @@ size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
 }
 
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " pid: %u tid: %u\n",
+		       event->itrace_start.pid, event->itrace_start.tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",

@@ -798,6 +813,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_AUX:
 		ret += perf_event__fprintf_aux(event, fp);
 		break;
+	case PERF_RECORD_ITRACE_START:
+		ret += perf_event__fprintf_itrace_start(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}

index b3c350e..7eecd5e 100644
@@ -330,6 +330,11 @@ struct aux_event {
 	u64	flags;
 };
 
+struct itrace_start_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;

@@ -349,6 +354,7 @@ union perf_event {
 	struct auxtrace_event		auxtrace;
 	struct auxtrace_error_event	auxtrace_error;
 	struct aux_event		aux;
+	struct itrace_start_event	itrace_start;
 };
 
 void perf_event__print_totals(void);

@@ -388,6 +394,10 @@ int perf_event__process_aux(struct perf_tool *tool,
 			    union perf_event *event,
 			    struct perf_sample *sample,
 			    struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,

@@ -446,6 +456,7 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,

index a7ad511..2f47110 100644
@@ -494,6 +494,14 @@ int machine__process_aux_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+					union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_itrace_start(event, stdout);
+	return 0;
+}
+
 struct map *machine__new_module(struct machine *machine, u64 start,
 				const char *filename)
 {

@@ -1341,6 +1349,9 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_lost_event(machine, event, sample); break;
 	case PERF_RECORD_AUX:
 		ret = machine__process_aux_event(machine, event); break;
+	case PERF_RECORD_ITRACE_START:
+		ret = machine__process_itrace_start_event(machine, event);
+		break;
 	default:
 		ret = -1;
 		break;

index fc5432a..1d99296 100644
@@ -83,6 +83,8 @@ int machine__process_lost_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_aux_event(struct machine *machine,
 			       union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+					union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,

index 0b4646c..e722107 100644
@@ -327,6 +327,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->lost = perf_event__process_lost;
 	if (tool->aux == NULL)
 		tool->aux = perf_event__process_aux;
+	if (tool->itrace_start == NULL)
+		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)

@@ -455,6 +457,16 @@ static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->aux + 1);
 }
 
+static void perf_event__itrace_start_swap(union perf_event *event,
+					  bool sample_id_all)
+{
+	event->itrace_start.pid	 = bswap_32(event->itrace_start.pid);
+	event->itrace_start.tid	 = bswap_32(event->itrace_start.tid);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {

@@ -593,6 +605,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
 	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
+	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,

@@ -1044,6 +1057,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->unthrottle(tool, event, sample, machine);
 	case PERF_RECORD_AUX:
 		return tool->aux(tool, event, sample, machine);
+	case PERF_RECORD_ITRACE_START:
+		return tool->itrace_start(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;

index 8288caf..7f282ad 100644
@@ -44,6 +44,7 @@ struct perf_tool {
 			exit,
 			lost,
 			aux,
+			itrace_start,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;

index 5042093..aa79fb8 100644
@@ -55,6 +55,7 @@ struct record_opts {
 	bool	     sample_intr_regs;
 	bool	     running_time;
 	bool	     full_auxtrace;
+	bool	     auxtrace_snapshot_mode;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

@@ -62,6 +63,8 @@ struct record_opts {
 	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
+	size_t	     auxtrace_snapshot_size;
+	const char   *auxtrace_snapshot_opts;
 	bool	     sample_transaction;
 	unsigned     initial_delay;
 	bool         use_clockid;

127 lines not on this page · raw message

77 lines not on this page · raw message

231 lines not on this page · raw message

index f0bacb6..a5d0284 100644
@@ -564,6 +564,17 @@ int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
 }
 
 static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+				  struct record_opts *opts __maybe_unused,
+				  const char *str)
+{
+	if (!str)
+		return 0;
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
 int auxtrace__process_event(struct perf_session *session __maybe_unused,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample __maybe_unused,

index 59561fd..367d8b8 100644
@@ -123,6 +123,10 @@ struct option {
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }

index 4f024eb..81419c6 100644
@@ -885,6 +885,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 		fprintf(stdout, " type: %u\n", type);
 
 	switch (type) {
+	case PERF_AUXTRACE_INTEL_PT:
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

index a5d0284..ae1249a 100644
@@ -39,6 +39,7 @@ struct events_stats;
 
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
+	PERF_AUXTRACE_INTEL_PT,
 };
 
 enum itrace_period_type {

400 lines not on this page · raw message

64 lines not on this page · raw message

246 lines not on this page · raw message

65 lines not on this page · raw message

155 lines not on this page · raw message

52 lines not on this page · raw message

1,738 lines not on this page · raw message

89 lines not on this page · raw message

752 lines not on this page · raw message

1,891 lines not on this page · raw message

57 lines not on this page · raw message

new file mode 100644
index 0000000..e7654b5
@@ -0,0 +1,38 @@
+/*
+ * auxtrace.c: AUX area tracing 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.
+ *
+ */
+
+#include "../../util/header.h"
+#include "../../util/auxtrace.h"
+#include "../../util/intel-pt.h"
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+					      int *err)
+{
+	char buffer[64];
+	int ret;
+
+	*err = 0;
+
+	ret = get_cpuid(buffer, sizeof(buffer));
+	if (ret) {
+		*err = ret;
+		return NULL;
+	}
+
+	if (!strncmp(buffer, "GenuineIntel,", 13))
+		return intel_pt_recording_init(err);
+
+	return NULL;
+}

new file mode 100644
index 0000000..fd11cc3
@@ -0,0 +1,15 @@
+#include <string.h>
+
+#include <linux/perf_event.h>
+
+#include "../../util/intel-pt.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
+		return intel_pt_pmu_default_config(pmu);
+#endif
+	return NULL;
+}

index 81419c6..b81130c 100644
@@ -47,6 +47,8 @@
 #include "debug.h"
 #include "parse-options.h"
 
+#include "intel-pt.h"
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
 			void *userpg, int fd)

@@ -877,7 +879,7 @@ static bool auxtrace__dont_decode(struct perf_session *session)
 
 int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 				      union perf_event *event,
-				      struct perf_session *session __maybe_unused)
+				      struct perf_session *session)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 

@@ -886,6 +888,7 @@ 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_UNKNOWN:
 	default:
 		return -EINVAL;

index b81130c..58accf7 100644
@@ -1187,6 +1187,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 		data2 = NULL;
 	}
 
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
 	padding = size & 7;
 	if (padding)

index ae1249a..fb639c43 100644
@@ -304,6 +304,7 @@ struct auxtrace_record {
 				      const char *str);
 	u64 (*reference)(struct auxtrace_record *itr);
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
 };
 
 #ifdef HAVE_AUXTRACE_SUPPORT

65 lines not on this page · raw message

458 lines not on this page · raw message

index 58accf7..ef9a92a 100644
@@ -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,

@@ -889,6 +890,8 @@ 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;

index fb639c43..318414f 100644
@@ -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 {

790 lines not on this page · raw message

43 lines not on this page · raw message

index 8ba4ce7..cf6b442 100644
@@ -876,6 +876,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	sample.stream_id = ptq->pt->branches_id;
 	sample.period = 1;
 	sample.cpu = ptq->cpu;
+	sample.flags = ptq->flags;
+	sample.insn_len = ptq->insn_len;
 
 	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
 		return 0;

@@ -918,6 +920,8 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	sample.stream_id = ptq->pt->instructions_id;
 	sample.period = ptq->pt->instructions_sample_period;
 	sample.cpu = ptq->cpu;
+	sample.flags = ptq->flags;
+	sample.insn_len = ptq->insn_len;
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,

index 9b7dfec..4be1844 100644
@@ -30,6 +30,7 @@
 #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)

@@ -55,6 +56,7 @@ struct intel_bts {
 	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;

@@ -71,6 +73,8 @@ struct intel_bts_queue {
 	pid_t			tid;
 	int			cpu;
 	u64			time;
+	struct intel_pt_insn	intel_pt_insn;
+	u32			sample_flags;
 };
 
 struct branch {

@@ -278,6 +282,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	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;

@@ -297,11 +303,116 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	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;
+
+	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)
+		return -1;
+
+	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz);
+	if (len <= 0)
+		return -1;
+
+	/* 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))
+		return -1;
+
+	return 0;
+}
+
+static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
+				 pid_t tid, u64 ip)
+{
+	union perf_event event;
+	const char *msg = "Failed to get instruction";
+	int code = EILSEQ;
+	int err;
+
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     code, cpu, pid, tid, ip, msg);
+
+	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;
+	size_t sz, bsz = sizeof(struct branch);
+	u32 filter = btsq->bts->branches_filter;
 	int err = 0;
 
 	if (buffer->use_data) {

@@ -315,14 +426,15 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 	if (!btsq->bts->sample_branches)
 		return 0;
 
-	while (sz > sizeof(struct branch)) {
+	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;
-		branch += 1;
-		sz -= sizeof(struct branch);
 	}
 	return err;
 }

@@ -768,6 +880,13 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	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;

index cf6b442..b7c5578 100644
@@ -265,7 +265,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
 						      !buffer->consecutive)) {
 		b->consecutive = false;
-		b->trace_nr = buffer->buffer_nr;
+		b->trace_nr = buffer->buffer_nr + 1;
 	} else {
 		b->consecutive = true;
 	}

@@ -1065,6 +1065,8 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
+	else
+		thread_stack__set_trace_nr(ptq->thread, state->trace_nr);
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);

index 4be1844..84a7d53 100644
@@ -27,6 +27,8 @@
 #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"

@@ -441,19 +443,22 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 
 static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 {
-	struct auxtrace_buffer *buffer = btsq->buffer;
+	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) {
-		struct thread *thread;
-
-		thread = machine__find_thread(btsq->bts->machine, -1, btsq->tid);
+		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];

@@ -483,6 +488,11 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 	    intel_bts_do_fix_overlap(queue, buffer))
 		return -ENOMEM;
 
+	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);