Re: [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL

On Jan 15, 2019, at 9:56 AM, Arnaldo Carvalho de Melo [off-list ref] wrote:

Em Thu, Jan 10, 2019 at 04:19:31PM -0800, Song Liu escreveu:

quoted

This patch handles PERF_RECORD_KSYMBOL in perf record/report.
Specifically, map and symbol are created for ksymbol register, and
removed for ksymbol unregister.

This patch also set perf_event_attr.ksymbol properly. The flag is
ON by default.

Signed-off-by: Song Liu <redacted>
---
tools/perf/util/event.c   | 21 +++++++++++++++
tools/perf/util/event.h   | 20 ++++++++++++++
tools/perf/util/evsel.c   |  9 +++++++
tools/perf/util/evsel.h   |  1 +
tools/perf/util/machine.c | 57 +++++++++++++++++++++++++++++++++++++++
tools/perf/util/machine.h |  3 +++
tools/perf/util/session.c |  4 +++
tools/perf/util/tool.h    |  4 ++-
8 files changed, 118 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 937a5a4f71cc..3c8a6a8dd260 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c

@@ -24,6 +24,7 @@

#include "symbol/kallsyms.h"
#include "asm/bug.h"
#include "stat.h"
+#include "session.h"

#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500

@@ -45,6 +46,7 @@ static const char *perf_event__names[] = {

	[PERF_RECORD_SWITCH]			= "SWITCH",
	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
+	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",

@@ -1329,6 +1331,14 @@ int perf_event__process_switch(struct perf_tool *tool __maybe_unused,

	return machine__process_switch_event(machine, event);
}

+int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine)
+{
+	return machine__process_ksymbol(machine, event, sample);
+}
+
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",

@@ -1461,6 +1471,14 @@ static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)

	return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
}

+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " ksymbol event with addr %lx len %u type %u flags 0x%x name %s\n",
+		       event->ksymbol_event.addr, event->ksymbol_event.len,
+		       event->ksymbol_event.ksym_type,
+		       event->ksymbol_event.flags, event->ksymbol_event.name);
+}
+
size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
	size_t ret = fprintf(fp, "PERF_RECORD_%s",

@@ -1496,6 +1514,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)

	case PERF_RECORD_LOST:
		ret += perf_event__fprintf_lost(event, fp);
		break;
+	case PERF_RECORD_KSYMBOL:
+		ret += perf_event__fprintf_ksymbol(event, fp);
+		break;
	default:
		ret += fprintf(fp, "\n");
	}

diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index eb95f3384958..018322f2a13e 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h

@@ -5,6 +5,7 @@

#include <limits.h>
#include <stdio.h>
#include <linux/kernel.h>
+#include <linux/bpf.h>

#include "../perf.h"
#include "build-id.h"

@@ -84,6 +85,19 @@ struct throttle_event {

	u64 stream_id;
};

+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+struct ksymbol_event {
+	struct perf_event_header header;
+	u64 addr;
+	u32 len;
+	u16 ksym_type;
+	u16 flags;
+	char name[KSYM_NAME_LEN];
+};
+
#define PERF_SAMPLE_MASK				\
	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\

@@ -651,6 +665,7 @@ union perf_event {

	struct stat_round_event		stat_round;
	struct time_conv_event		time_conv;
	struct feature_event		feat;
+	struct ksymbol_event		ksymbol_event;
};

void perf_event__print_totals(void);

@@ -748,6 +763,10 @@ int perf_event__process_exit(struct perf_tool *tool,

			     union perf_event *event,
			     struct perf_sample *sample,
			     struct machine *machine);
+int perf_event__process_ksymbol(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine);
int perf_tool__process_synth_event(struct perf_tool *tool,
				   union perf_event *event,
				   struct machine *machine,

@@ -811,6 +830,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);

size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);

int kallsyms__get_function_start(const char *kallsyms_filename,

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbc0466db368..de34ce875648 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c

@@ -1035,6 +1035,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,

	attr->mmap  = track;
	attr->mmap2 = track && !perf_missing_features.mmap2;
	attr->comm  = track;
+	attr->ksymbol = track && !perf_missing_features.ksymbol;

	if (opts->record_namespaces)
		attr->namespaces  = track;

@@ -1652,6 +1653,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,

	PRINT_ATTRf(context_switch, p_unsigned);
	PRINT_ATTRf(write_backward, p_unsigned);
	PRINT_ATTRf(namespaces, p_unsigned);
+	PRINT_ATTRf(ksymbol, p_unsigned);

	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
	PRINT_ATTRf(bp_type, p_unsigned);

@@ -1811,6 +1813,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,

				     PERF_SAMPLE_BRANCH_NO_CYCLES);
	if (perf_missing_features.group_read && evsel->attr.inherit)
		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
+	if (perf_missing_features.ksymbol)
+		evsel->attr.ksymbol = 0;
retry_sample_id:
	if (perf_missing_features.sample_id_all)
		evsel->attr.sample_id_all = 0;

@@ -1955,6 +1959,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,

		perf_missing_features.exclude_guest = true;
		pr_debug2("switching off exclude_guest, exclude_host\n");
		goto fallback_missing_features;
+	} else if (!perf_missing_features.ksymbol &&
+		   evsel->attr.ksymbol) {
+		perf_missing_features.ksymbol = true;
+		pr_debug2("switching off ksymbol\n");
+		goto fallback_missing_features;

Please move this to the top, see the comment there:

	if (err != -EINVAL || cpu > 0 || thread > 0)
		goto out_close;

	/*
	 * Must probe features in the order they were added to the
	 * perf_event_attr interface.
	 */
	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
		perf_missing_features.write_backward = true;
		pr_debug2("switching off write_backward\n");
		goto out_close;
	} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
		perf_missing_features.clockid_wrong = true;
		pr_debug2("switching off clockid\n");
		goto fallback_missing_features;


So that when one asks for, say, attr.write_backward _and_ attr.ksymbol,
we first disable attr.ksymbol, to try the fallback, as it was added
after attr.write_backward.

Think about an older kernel where attr.write_backward is present but not
attr.ksymbol.

Ditto for the attr.bpf_event.

Thanks Arnaldo!

I will include the fix in next version.

Song