[PATCH 21/44] perf tools: Add AUX area tracing index

[Adrian Hunter <adrian.hunter@intel.com>]

Add an index of AUX area tracing events within
a perf.data file.

perf record uses a special user event
PERF_RECORD_FINISHED_ROUND to enable sorting of
events in chunks instead of having to sort all
events altogether.

AUX area tracing events contain data that can
span back to the very beginning of the recording
period. i.e. they do not obey the rules of
PERF_RECORD_FINISHED_ROUND.

By adding an index, AUX area tracing events
can be found in advance and the
PERF_RECORD_FINISHED_ROUND approach works as
usual.

The index is recorded with the auxtrace feature
in the perf.data file.  A session reads the index
but does not process it.  An AUX area
decoder can queue all the AUX area data
in advance using auxtrace_queues__process_index()
or otherwise process the index in some custom
manner.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-inject.c |  15 +++
 tools/perf/builtin-record.c |  15 +++
 tools/perf/util/auxtrace.c  | 216 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/auxtrace.h  |  35 +++++++
 tools/perf/util/header.c    |  31 ++++++-
 tools/perf/util/session.c   |   2 +
 tools/perf/util/session.h   |   1 +
 7 files changed, 311 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index fc22249..cfb129a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -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);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 009ec31..8d6c2cb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -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)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 434e394..02468b1 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -344,6 +344,33 @@ out_err:
 	return err;
 }
 
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+					      struct perf_session *session,
+					      off_t file_offset, size_t sz)
+{
+	union perf_event *event;
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &event, NULL);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_AUXTRACE) {
+		if (event->header.size != sizeof(struct auxtrace_event) ||
+		    event->header.size != sz) {
+			err = -EINVAL;
+			goto out;
+		}
+		file_offset += event->header.size;
+		err = auxtrace_queues__add_event(queues, session, event,
+						 file_offset, NULL);
+	}
+out:
+	return err;
+}
+
 void auxtrace_queues__free(struct auxtrace_queues *queues)
 {
 	unsigned int i;
@@ -500,6 +527,195 @@ auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
 	return NULL;
 }
 
+static int auxtrace_index__alloc(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+
+	auxtrace_index = malloc(sizeof(struct auxtrace_index));
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	auxtrace_index->nr = 0;
+	INIT_LIST_HEAD(&auxtrace_index->list);
+
+	list_add_tail(&auxtrace_index->list, head);
+
+	return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index, *n;
+
+	list_for_each_entry_safe(auxtrace_index, n, head, list) {
+		list_del(&auxtrace_index->list);
+		free(auxtrace_index);
+	}
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	int err;
+
+	if (list_empty(head)) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+	}
+
+	auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+	if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+		auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+					    list);
+	}
+
+	return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+				   union perf_event *event, off_t file_offset)
+{
+	struct auxtrace_index *auxtrace_index;
+	size_t nr;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	nr = auxtrace_index->nr;
+	auxtrace_index->entries[nr].file_offset = file_offset;
+	auxtrace_index->entries[nr].sz = event->header.size;
+	auxtrace_index->nr += 1;
+
+	return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+				    struct auxtrace_index *auxtrace_index)
+{
+	struct auxtrace_index_entry index;
+	size_t i;
+
+	for (i = 0; i < auxtrace_index->nr; i++) {
+		index.file_offset = auxtrace_index->entries[i].file_offset;
+		index.sz = auxtrace_index->entries[i].sz;
+		if (writen(fd, &index, sizeof(index)) != sizeof(index))
+			return -errno;
+	}
+	return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	u64 total = 0;
+	int err;
+
+	list_for_each_entry(auxtrace_index, head, list)
+		total += auxtrace_index->nr;
+
+	if (writen(fd, &total, sizeof(total)) != sizeof(total))
+		return -errno;
+
+	list_for_each_entry(auxtrace_index, head, list) {
+		err = auxtrace_index__do_write(fd, auxtrace_index);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+					 bool needs_swap)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry index;
+	size_t nr;
+
+	if (readn(fd, &index, sizeof(index)) != sizeof(index))
+		return -1;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -1;
+
+	nr = auxtrace_index->nr;
+	if (needs_swap) {
+		auxtrace_index->entries[nr].file_offset =
+						bswap_64(index.file_offset);
+		auxtrace_index->entries[nr].sz = bswap_64(index.sz);
+	} else {
+		auxtrace_index->entries[nr].file_offset = index.file_offset;
+		auxtrace_index->entries[nr].sz = index.sz;
+	}
+
+	auxtrace_index->nr = nr + 1;
+
+	return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap)
+{
+	struct list_head *head = &session->auxtrace_index;
+	u64 nr;
+
+	if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+		return -1;
+
+	if (needs_swap)
+		nr = bswap_64(nr);
+
+	if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) != size)
+		return -1;
+
+	while (nr--) {
+		int err;
+
+		err = auxtrace_index__process_entry(fd, head, needs_swap);
+		if (err)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+						struct perf_session *session,
+						struct auxtrace_index_entry *index)
+{
+	return auxtrace_queues__add_indexed_event(queues, session,
+						  index->file_offset,
+						  index->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry *index;
+	size_t i;
+	int err;
+
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			index = &auxtrace_index->entries[i];
+			err = auxtrace_queues__process_index_entry(queues,
+								   session,
+								   index);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
 struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
 					      struct auxtrace_buffer *buffer)
 {
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 53b60a6..b9e4b9d 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -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);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a93c466..a1f4316 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -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 {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b08bf15..93833d0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -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);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9ed5135..b44afc7 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -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;
-- 
1.9.1