linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wang Nan <wangnan0@huawei.com>
To: <acme@kernel.org>, <ast@plumgrid.com>
Cc: <linux-kernel@vger.kernel.org>, <lizefan@huawei.com>,
	<hekuang@huawei.com>, <xiakaixu@huawei.com>, <pi3orama@163.com>
Subject: [PATCH v11 33/39] perf record: Probe at kprobe points
Date: Wed, 8 Jul 2015 13:14:22 +0000	[thread overview]
Message-ID: <1436361268-234530-34-git-send-email-wangnan0@huawei.com> (raw)
In-Reply-To: <1436361268-234530-1-git-send-email-wangnan0@huawei.com>

In this patch, kprobe points are created using add_perf_probe_events.
Since all events are already grouped together in an array, calling
add_perf_probe_events() creates all of them.

probe_conf.max_probes is set to MAX_PROBES to support glob matching.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
---
 tools/perf/builtin-record.c  | 18 ++++++++++++++++-
 tools/perf/util/bpf-loader.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-loader.h |  4 ++++
 3 files changed, 69 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 283fe96..33b213a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -29,6 +29,7 @@
 #include "util/data.h"
 #include "util/auxtrace.h"
 #include "util/parse-branch-options.h"
+#include "util/bpf-loader.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -1111,7 +1112,21 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (err)
 		return err;
 
-	err = -ENOMEM;
+	/*
+	 * bpf__probe must be called before symbol__init() because we
+	 * need init_symbol_maps. If called after symbol__init,
+	 * symbol_conf.sort_by_name won't take effect.
+	 *
+	 * bpf__unprobe() is safe even if bpf__probe() failed, and it
+	 * also calls symbol__init. Therefore, goto out_symbol_exit
+	 * is safe when probe failed.
+	 */
+	err = bpf__probe();
+	if (err) {
+		pr_err("Probing at events in BPF object failed.\n");
+		pr_err("Try perf probe -d '*' to remove existing probe events.\n");
+		goto out_symbol_exit;
+	}
 
 	symbol__init(NULL);
 
@@ -1172,6 +1187,7 @@ out_symbol_exit:
 	perf_evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
+	bpf__unprobe();
 	return err;
 }
 
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index e810d05..df3f471 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -193,3 +193,51 @@ void bpf__clear(void)
 	bpf_object__for_each_safe(obj, tmp)
 		bpf_object__close(obj);
 }
+
+static bool is_probing;
+
+int bpf__unprobe(void)
+{
+	struct strfilter *delfilter;
+	int ret;
+
+	if (!is_probing)
+		return 0;
+
+	delfilter = strfilter__new(PERF_BPF_PROBE_GROUP ":*", NULL);
+	if (!delfilter) {
+		pr_err("Failed to create delfilter when unprobing\n");
+		return -ENOMEM;
+	}
+
+	ret = del_perf_probe_events(delfilter);
+	strfilter__delete(delfilter);
+	if (ret < 0 && is_probing)
+		pr_err("Error: failed to delete events: %s\n",
+			strerror(-ret));
+	else
+		is_probing = false;
+	return ret < 0 ? ret : 0;
+}
+
+int bpf__probe(void)
+{
+	int err;
+
+	if (nr_probe_events <= 0)
+		return 0;
+
+	probe_conf.max_probes = MAX_PROBES;
+	/* Let add_perf_probe_events keeps probe_trace_event */
+	err = add_perf_probe_events(probe_event_array,
+				    nr_probe_events,
+				    false);
+
+	/* add_perf_probe_events return negative when fail */
+	if (err < 0)
+		pr_err("bpf probe: failed to probe events\n");
+	else
+		is_probing = true;
+
+	return err < 0 ? err : 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 5a3c954..374aec0 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -12,6 +12,8 @@
 
 #ifdef HAVE_LIBBPF_SUPPORT
 int bpf__prepare_load(const char *filename, bool source);
+int bpf__probe(void);
+int bpf__unprobe(void);
 
 void bpf__clear(void);
 #else
@@ -22,6 +24,8 @@ static inline int bpf__prepare_load(const char *filename __maybe_unused,
 	return -1;
 }
 
+static inline int bpf__probe(void) { return 0; }
+static inline int bpf__unprobe(void) { return 0; }
 static inline void bpf__clear(void) { }
 #endif
 #endif
-- 
1.8.3.4


  parent reply	other threads:[~2015-07-08 13:16 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-08 13:13 [PATCH v11 00/39] perf tools: filtering events using eBPF programs - part1 Wang Nan
2015-07-08 13:13 ` [PATCH v11 01/39] bpf: Use correct #ifdef controller for trace_call_bpf() Wang Nan
2015-07-08 13:13 ` [PATCH v11 02/39] tracing, perf: Implement BPF programs attached to uprobes Wang Nan
2015-07-08 13:13 ` [PATCH v11 03/39] bpf tools: Introduce 'bpf' library and add bpf feature check Wang Nan
2015-07-08 13:13 ` [PATCH v11 04/39] bpf tools: Allow caller to set printing function Wang Nan
2015-07-08 13:13 ` [PATCH v11 05/39] bpf tools: Open eBPF object file and do basic validation Wang Nan
2015-07-08 13:13 ` [PATCH v11 06/39] bpf tools: Read eBPF object from buffer Wang Nan
2015-07-08 13:13 ` [PATCH v11 07/39] bpf tools: Check endianness and make libbpf fail early Wang Nan
2015-07-08 13:13 ` [PATCH v11 08/39] bpf tools: Iterate over ELF sections to collect information Wang Nan
2015-07-08 13:13 ` [PATCH v11 09/39] bpf tools: Collect version and license from ELF sections Wang Nan
2015-07-08 13:13 ` [PATCH v11 10/39] bpf tools: Collect map definitions from 'maps' section Wang Nan
2015-07-08 13:14 ` [PATCH v11 11/39] bpf tools: Collect symbol table from SHT_SYMTAB section Wang Nan
2015-07-08 13:14 ` [PATCH v11 12/39] bpf tools: Collect eBPF programs from their own sections Wang Nan
2015-07-08 13:14 ` [PATCH v11 13/39] bpf tools: Collect relocation sections from SHT_REL sections Wang Nan
2015-07-08 13:14 ` [PATCH v11 14/39] bpf tools: Record map accessing instructions for each program Wang Nan
2015-07-08 13:14 ` [PATCH v11 15/39] bpf tools: Add bpf.c/h for common bpf operations Wang Nan
2015-07-08 13:14 ` [PATCH v11 16/39] bpf tools: Create eBPF maps defined in an object file Wang Nan
2015-07-08 13:14 ` [PATCH v11 17/39] bpf tools: Relocate eBPF programs Wang Nan
2015-07-08 13:14 ` [PATCH v11 18/39] bpf tools: Introduce bpf_load_program() to bpf.c Wang Nan
2015-07-08 13:14 ` [PATCH v11 19/39] bpf tools: Load eBPF programs in object files into kernel Wang Nan
2015-07-08 13:14 ` [PATCH v11 20/39] bpf tools: Introduce accessors for struct bpf_program Wang Nan
2015-07-08 13:14 ` [PATCH v11 21/39] bpf tools: Introduce accessors for struct bpf_object Wang Nan
2015-07-08 13:14 ` [PATCH v11 22/39] bpf tools: Link all bpf objects onto a list Wang Nan
2015-07-08 13:14 ` [PATCH v11 23/39] perf tools: Introduce llvm config options Wang Nan
2015-07-08 13:14 ` [PATCH v11 24/39] perf tools: Call clang to compile C source to object code Wang Nan
2015-07-08 13:14 ` [PATCH v11 25/39] perf tools: Auto detecting kernel build directory Wang Nan
2015-07-08 13:14 ` [PATCH v11 26/39] perf tools: Auto detecting kernel include options Wang Nan
2015-07-08 13:14 ` [PATCH v11 27/39] perf tests: Add LLVM test for eBPF on-the-fly compiling Wang Nan
2015-07-08 13:14 ` [PATCH v11 28/39] perf tools: Make perf depend on libbpf Wang Nan
2015-07-08 19:44   ` Arnaldo Carvalho de Melo
2015-07-08 13:14 ` [PATCH v11 29/39] perf record: Enable passing bpf object file to --event Wang Nan
2015-07-08 13:14 ` [PATCH v11 30/39] perf record: Compile scriptlets if pass '.c' " Wang Nan
2015-07-08 13:14 ` [PATCH v11 31/39] perf tools: Parse probe points of eBPF programs during preparation Wang Nan
2015-07-08 13:14 ` [PATCH v11 32/39] perf probe: Attach trace_probe_event with perf_probe_event Wang Nan
2015-07-08 13:14 ` Wang Nan [this message]
2015-07-08 13:14 ` [PATCH v11 34/39] perf record: Load all eBPF object into kernel Wang Nan
2015-07-08 13:14 ` [PATCH v11 35/39] perf tools: Add bpf_fd field to evsel and config it Wang Nan
2015-07-08 13:14 ` [PATCH v11 36/39] perf tools: Attach eBPF program to perf event Wang Nan
2015-07-08 13:14 ` [PATCH v11 37/39] perf tools: Suppress probing messages when probing by BPF loading Wang Nan
2015-07-08 13:14 ` [PATCH v11 38/39] perf record: Add clang options for compiling BPF scripts Wang Nan
2015-07-08 13:14 ` [PATCH v11 39/39] bpf tools: Load a program with different instance using preprocessor Wang Nan
2015-07-08 14:03 ` [PATCH v11 00/39] perf tools: filtering events using eBPF programs - part1 Arnaldo Carvalho de Melo
2015-07-08 15:57   ` pi3orama
2015-07-08 19:12     ` Arnaldo Carvalho de Melo
2015-07-08 20:53     ` Arnaldo Carvalho de Melo

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=1436361268-234530-34-git-send-email-wangnan0@huawei.com \
    --to=wangnan0@huawei.com \
    --cc=acme@kernel.org \
    --cc=ast@plumgrid.com \
    --cc=hekuang@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=pi3orama@163.com \
    --cc=xiakaixu@huawei.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).