linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Martin KaFai Lau <kafai@fb.com>, Yonghong Song <yhs@fb.com>
Subject: [PATCH 10/17] perf bpf: Add bpf_map dumper
Date: Wed, 20 Feb 2019 22:25:42 -0300	[thread overview]
Message-ID: <20190221012549.4069-11-acme@kernel.org> (raw)
In-Reply-To: <20190221012549.4069-1-acme@kernel.org>

From: Arnaldo Carvalho de Melo <acme@redhat.com>

At some point I'll suggest moving this to libbpf, for now I'll
experiment with ways to dump BPF maps set by events in 'perf trace',
starting with a very basic dumper for the current very limited needs
of the augmented_raw_syscalls code: dumping booleans.

Having functions that apply to the map keys and values and do table
lookup in things like syscall id to string tables should come next.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-lz14w0esqyt1333aon05jpwc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/Build     |  1 +
 tools/perf/util/bpf_map.c | 72 +++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf_map.h | 22 ++++++++++++
 3 files changed, 95 insertions(+)
 create mode 100644 tools/perf/util/bpf_map.c
 create mode 100644 tools/perf/util/bpf_map.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3008d49fa587..8dd3102301ea 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -115,6 +115,7 @@ perf-y += branch.o
 perf-y += mem2node.o
 
 perf-$(CONFIG_LIBBPF) += bpf-loader.o
+perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c
new file mode 100644
index 000000000000..eb853ca67cf4
--- /dev/null
+++ b/tools/perf/util/bpf_map.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include "util/bpf_map.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def)
+{
+	return def->type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+	       def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
+}
+
+static void *bpf_map_def__alloc_value(const struct bpf_map_def *def)
+{
+	if (bpf_map_def__is_per_cpu(def))
+		return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF));
+
+	return malloc(def->value_size);
+}
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp)
+{
+	const struct bpf_map_def *def = bpf_map__def(map);
+	void *prev_key = NULL, *key, *value;
+	int fd = bpf_map__fd(map), err;
+	int printed = 0;
+
+	if (fd < 0)
+		return fd;
+
+	if (IS_ERR(def))
+		return PTR_ERR(def);
+
+	err = -ENOMEM;
+	key = malloc(def->key_size);
+	if (key == NULL)
+		goto out;
+
+	value = bpf_map_def__alloc_value(def);
+	if (value == NULL)
+		goto out_free_key;
+
+	while ((err = bpf_map_get_next_key(fd, prev_key, key) == 0)) {
+		int intkey = *(int *)key;
+
+		if (!bpf_map_lookup_elem(fd, key, value)) {
+			bool boolval = *(bool *)value;
+			if (boolval)
+				printed += fprintf(fp, "[%d] = %d,\n", intkey, boolval);
+		} else {
+			printed += fprintf(fp, "[%d] = ERROR,\n", intkey);
+		}
+
+		prev_key = key;
+	}
+
+	if (err == ENOENT)
+		err = printed;
+
+	free(value);
+out_free_key:
+	free(key);
+out:
+	return err;
+}
diff --git a/tools/perf/util/bpf_map.h b/tools/perf/util/bpf_map.h
new file mode 100644
index 000000000000..d6abd5e47af8
--- /dev/null
+++ b/tools/perf/util/bpf_map.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#ifndef __PERF_BPF_MAP_H
+#define __PERF_BPF_MAP_H 1
+
+#include <stdio.h>
+#include <linux/compiler.h>
+struct bpf_map;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp);
+
+#else
+
+static inline int bpf_map__fprintf(struct bpf_map *map __maybe_unused, FILE *fp __maybe_unused)
+{
+	return 0;
+}
+
+#endif // HAVE_LIBBPF_SUPPORT
+
+#endif // __PERF_BPF_MAP_H
-- 
2.19.1


  parent reply	other threads:[~2019-02-21  1:26 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-21  1:25 [GIT PULL 00/17] perf/core improvements and fixes Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 01/17] perf tests shell: Skip trace+probe_vfs_getname.sh if built without trace support Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 02/17] perf header: Fix wrong node write in NUMA_TOPOLOGY feature Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 03/17] perf tools: Add cpu_topology object Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 04/17] perf tools: Add numa_topology object Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 05/17] perf tools: Use sysfs__mountpoint() when reading cpu topology Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 06/17] perf report: Don't shadow inlined symbol with different addr range Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 07/17] perf doc: Fix HEADER_CMDLINE description in perf.data documentation Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 08/17] perf doc: Fix documentation of the Flags section in perf.data Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 09/17] perf test: Fix failure of 'evsel-tp-sched' test on s390 Arnaldo Carvalho de Melo
2019-02-21  1:25 ` Arnaldo Carvalho de Melo [this message]
2019-02-21  1:25 ` [PATCH 11/17] perf trace: Allow dumping a BPF map after setting up BPF events Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 12/17] perf session: Don't report zero period samples for slave events Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 13/17] perf evsel: Force sample_type " Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 14/17] perf script: Allow +- operator for type specific fields option Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 15/17] perf bpf-event: Add missing new line into pr_debug call Arnaldo Carvalho de Melo
2019-02-21  7:12   ` Song Liu
2019-02-21  1:25 ` [PATCH 16/17] perf cpumap: Increase debug level for cpu_map__snprint verbose output Arnaldo Carvalho de Melo
2019-02-21  1:25 ` [PATCH 17/17] perf tools: Make rm_rf() remove single file Arnaldo Carvalho de Melo
2019-02-28  7:28 ` [GIT PULL 00/17] perf/core improvements and fixes Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190221012549.4069-11-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=ast@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=jolsa@kernel.org \
    --cc=kafai@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=williams@redhat.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).