From: Masami Hiramatsu <mhiramat@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: "Frank Ch . Eigler" <fche@redhat.com>,
Aaron Merey <amerey@redhat.com>,
Daniel Thompson <daniel.thompson@linaro.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
linux-kernel@vger.kernel.org
Subject: [PATCH 0/2] perf probe: Support debuginfod client
Date: Thu, 17 Sep 2020 01:44:33 +0900 [thread overview]
Message-ID: <160027467316.803747.10741549521899847231.stgit@devnote2> (raw)
Hi,
Here is a couple of patches to enable debuginfod support on
perf probe command. This allows users to access debuginfo binary
from remote device.
Since the perf-probe heavily depends on the debuginfo, debuginfod
gives us many benefits on the perf probe command on remote
machine, especially for the embedded devices.
Here is an example (copied from [2/2])
1. at first you need to start debuginfod on the host machine.
-F option scans local debuginfo binary. (You don't need to pass
the source tree, but you must keep the source tree untouched)
(host) $ cd PATH/TO/KBUILD/DIR/
(host) $ debuginfod -F .
...
2. In the remote machine, you need to set DEBUGINFOD_URLS.
debuginfod uses 8002 tcp port.
(remote) # export DEBUGINFOD_URLS="http://$HOST_IP:8002/"
3. Then you can use the perf probe (it can refer the source code)
(remote) # perf probe -L vfs_read
<vfs_read@...>
0 ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
2 ssize_t ret;
if (!(file->f_mode & FMODE_READ))
return -EBADF;
6 if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
8 if (unlikely(!access_ok(buf, count)))
return -EFAULT;
11 ret = rw_verify_area(READ, file, pos, count);
12 if (ret)
return ret;
if (count > MAX_RW_COUNT)
...
(remote) # perf probe -a "vfs_read count"
Added new event:
probe:vfs_read (on vfs_read with count)
(remote) # perf probe -l
probe:vfs_read (on vfs_read@ksrc/linux/fs/read_write.c with count)
Thank you,
---
Masami Hiramatsu (2):
perf probe: Fix to adjust symbol address with correct reloc_sym address
perf probe: Fall back to debuginfod query if debuginfo and source not found
tools/perf/util/probe-event.c | 60 +++++++++++++++++++++++++++++++++++++---
tools/perf/util/probe-finder.c | 56 ++++++++++++++++++++++++++++++++++---
tools/perf/util/probe-finder.h | 7 +++--
3 files changed, 112 insertions(+), 11 deletions(-)
--
Masami Hiramatsu (Linaro) <mhiramat@kernel.org>
next reply other threads:[~2020-09-16 20:50 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-16 16:44 Masami Hiramatsu [this message]
2020-09-16 16:44 ` [PATCH 1/2] perf probe: Fix to adjust symbol address with correct reloc_sym address Masami Hiramatsu
2020-09-16 16:44 ` [PATCH 2/2] perf probe: Fall back to debuginfod query if debuginfo and source not found Masami Hiramatsu
2020-09-18 0:40 ` Arnaldo Carvalho de Melo
2020-09-18 2:47 ` Masami Hiramatsu
2020-09-18 12:26 ` Arnaldo Carvalho de Melo
2020-09-16 18:13 ` [PATCH 0/2] perf probe: Support debuginfod client Frank Ch. Eigler
2020-09-16 18:52 ` Arnaldo Carvalho de Melo
2020-09-16 20:17 ` Frank Ch. Eigler
2020-09-17 3:07 ` Masami Hiramatsu
2020-09-17 13:54 ` Frank Ch. Eigler
2020-09-17 19:56 ` 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=160027467316.803747.10741549521899847231.stgit@devnote2 \
--to=mhiramat@kernel.org \
--cc=acme@kernel.org \
--cc=acme@redhat.com \
--cc=amerey@redhat.com \
--cc=daniel.thompson@linaro.org \
--cc=fche@redhat.com \
--cc=linux-kernel@vger.kernel.org \
/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).