perf tools: Add feature header record to pipe-mode

Add header record types to pipe-mode, reusing the functions
used in file-mode and leveraging the new struct feat_fd.

For alignment, check that synthesized events don't exceed
pagesize.

Add the perf_event__synthesize_feature event call back to
process the new header records.

Before this patch:

  $ perf record -o - -e cycles sleep 1 | perf report --stdio --header
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.000 MB - ]
  ...

After this patch:
  $ perf record -o - -e cycles sleep 1 | perf report --stdio --header
  # ========
  # captured on: Mon May 22 16:33:43 2017
  # ========
  #
  # hostname : my_hostname
  # os release : 4.11.0-dbx-up_perf
  # perf version : 4.11.rc6.g6277c80
  # arch : x86_64
  # nrcpus online : 72
  # nrcpus avail : 72
  # cpudesc : Intel(R) Xeon(R) CPU E5-2696 v3 @ 2.30GHz
  # cpuid : GenuineIntel,6,63,2
  # total memory : 263457192 kB
  # cmdline : /root/perf record -o - -e cycles -c 100000 sleep 1
  # HEADER_CPU_TOPOLOGY info available, use -I to display
  # HEADER_NUMA_TOPOLOGY info available, use -I to display
  # pmu mappings: intel_bts = 6, uncore_imc_4 = 22, uncore_sbox_1 = 47, uncore_cbox_5 = 33, uncore_ha_0 = 16, uncore_cbox
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.000 MB - ]
  ...

Support added for the subcommands: report, inject, annotate and script.

Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Simon Que <sque@chromium.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20170718042549.145161-16-davidcc@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf.data-file-format.txt

@@ -398,6 +398,11 @@ struct auxtrace_error_event {
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
+	PERF_RECORD_HEADER_FEATURE		= 80,
+
+Describes a header feature. These are records used in pipe-mode that
+contain information that otherwise would be in perf.data file's header.
+
 Event types
 
 Define the event attributes with their IDs.
@@ -422,8 +427,9 @@ struct perf_pipe_file_header {
 };
 
 The information about attrs, data, and event_types is instead in the
-synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and
-PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode.
+synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
+PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
+that are generated by perf record in pipe-mode.
 
 
 References:

tools/perf/builtin-annotate.c

@@ -397,6 +397,7 @@ int cmd_annotate(int argc, const char **argv)
 			.namespaces = perf_event__process_namespaces,
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
+			.feature	= perf_event__process_feature,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},

tools/perf/builtin-inject.c

@@ -770,6 +770,7 @@ int cmd_inject(int argc, const char **argv)
 			.finished_round	= perf_event__repipe_oe_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 			.id_index	= perf_event__repipe_op2_synth,
+			.feature	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
 		.samples = LIST_HEAD_INIT(inject.samples),

tools/perf/builtin-record.c

@@ -799,6 +799,13 @@ static int record__synthesize(struct record *rec, bool tail)
 		return 0;
 
 	if (file->is_pipe) {
+		err = perf_event__synthesize_features(
+			tool, session, rec->evlist, process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize features.\n");
+			return err;
+		}
+
 		err = perf_event__synthesize_attrs(tool, session,
 						   process_synthesized_event);
 		if (err < 0) {

tools/perf/builtin-report.c

@@ -718,6 +718,7 @@ int cmd_report(int argc, const char **argv)
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
+			.feature	 = perf_event__process_feature,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},

tools/perf/builtin-script.c

@@ -2682,6 +2682,7 @@ int cmd_script(int argc, const char **argv)
 			.attr		 = process_attr,
 			.event_update   = perf_event__process_event_update,
 			.tracing_data	 = perf_event__process_tracing_data,
+			.feature	 = perf_event__process_feature,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,

tools/perf/util/event.c

@@ -57,6 +57,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
 	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
+	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
 };
 
 static const char *perf_ns__names[] = {

tools/perf/util/event.h

@@ -244,6 +244,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_STAT_ROUND			= 77,
 	PERF_RECORD_EVENT_UPDATE		= 78,
 	PERF_RECORD_TIME_CONV			= 79,
+	PERF_RECORD_HEADER_FEATURE		= 80,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -609,6 +610,12 @@ struct time_conv_event {
 	u64 time_zero;
 };
 
+struct feature_event {
+	struct perf_event_header 	header;
+	u64				feat_id;
+	char				data[];
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -639,6 +646,7 @@ union perf_event {
 	struct stat_event		stat;
 	struct stat_round_event		stat_round;
 	struct time_conv_event		time_conv;
+	struct feature_event		feat;
 };
 
 void perf_event__print_totals(void);

tools/perf/util/header.c

@@ -35,6 +35,7 @@
 #include "data.h"
 #include <api/fs/fs.h>
 #include "asm/bug.h"
+#include "tool.h"
 
 #include "sane_ctype.h"
 
@@ -2982,6 +2983,103 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+				    struct perf_session *session,
+				    struct perf_evlist *evlist,
+				    perf_event__handler_t process)
+{
+	struct perf_header *header = &session->header;
+	struct feat_fd ff;
+	struct feature_event *fe;
+	size_t sz, sz_hdr;
+	int feat, ret;
+
+	sz_hdr = sizeof(fe->header);
+	sz = sizeof(union perf_event);
+	/* get a nice alignment */
+	sz = PERF_ALIGN(sz, page_size);
+
+	memset(&ff, 0, sizeof(ff));
+
+	ff.buf = malloc(sz);
+	if (!ff.buf)
+		return -ENOMEM;
+
+	ff.size = sz - sz_hdr;
+
+	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+		if (!feat_ops[feat].synthesize) {
+			pr_debug("No record header feature for header :%d\n", feat);
+			continue;
+		}
+
+		ff.offset = sizeof(*fe);
+
+		ret = feat_ops[feat].write(&ff, evlist);
+		if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
+			pr_debug("Error writing feature\n");
+			continue;
+		}
+		/* ff.buf may have changed due to realloc in do_write() */
+		fe = ff.buf;
+		memset(fe, 0, sizeof(*fe));
+
+		fe->feat_id = feat;
+		fe->header.type = PERF_RECORD_HEADER_FEATURE;
+		fe->header.size = ff.offset;
+
+		ret = process(tool, ff.buf, NULL, NULL);
+		if (ret) {
+			free(ff.buf);
+			return ret;
+		}
+	}
+	free(ff.buf);
+	return 0;
+}
+
+int perf_event__process_feature(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_session *session __maybe_unused)
+{
+	struct feat_fd ff = { .fd = 0 };
+	struct feature_event *fe = (struct feature_event *)event;
+	int type = fe->header.type;
+	u64 feat = fe->feat_id;
+
+	if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
+		pr_warning("invalid record type %d in pipe-mode\n", type);
+		return 0;
+	}
+	if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+		pr_warning("invalid record type %d in pipe-mode\n", type);
+		return -1;
+	}
+
+	if (!feat_ops[feat].process)
+		return 0;
+
+	ff.buf  = (void *)fe->data;
+	ff.size = event->header.size - sizeof(event->header);
+	ff.ph = &session->header;
+
+	if (feat_ops[feat].process(&ff, NULL))
+		return -1;
+
+	if (!feat_ops[feat].print || !tool->show_feat_hdr)
+		return 0;
+
+	if (!feat_ops[feat].full_only ||
+	    tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
+		feat_ops[feat].print(&ff, stdout);
+	} else {
+		fprintf(stdout, "# %s info available, use -I to display\n",
+			feat_ops[feat].name);
+	}
+
+	return 0;
+}
+
 static struct event_update_event *
 event_update_event__new(size_t size, u64 type, u64 id)
 {

tools/perf/util/header.h

@@ -101,6 +101,15 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+				    struct perf_session *session,
+				    struct perf_evlist *evlist,
+				    perf_event__handler_t process);
+
+int perf_event__process_feature(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_session *session);
+
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);

tools/perf/util/session.c

@@ -428,6 +428,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->stat_round = process_stat_round_stub;
 	if (tool->time_conv == NULL)
 		tool->time_conv = process_event_op2_stub;
+	if (tool->feature == NULL)
+		tool->feature = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -1371,6 +1373,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
 		return tool->time_conv(tool, event, session);
+	case PERF_RECORD_HEADER_FEATURE:
+		return tool->feature(tool, event, session);
 	default:
 		return -EINVAL;
 	}

tools/perf/util/tool.h

@@ -69,7 +69,8 @@ struct perf_tool {
 			cpu_map,
 			stat_config,
 			stat,
-			stat_round;
+			stat_round,
+			feature;
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;