From: Aleksa Sarai <cyphar@cyphar.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>,
Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
"David S. Miller" <davem@davemloft.net>,
Masami Hiramatsu <mhiramat@kernel.org>,
Jonathan Corbet <corbet@lwn.net>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Shuah Khan <shuah@kernel.org>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Brendan Gregg <bgregg@netflix.com>,
Christian Brauner <christian@brauner.io>,
Aleksa Sarai <asarai@suse.de>,
netdev@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
Josh Poimboeuf <jpoimboe@redhat.com>
Subject: Re: [PATCH v3 1/2] kretprobe: produce sane stack traces
Date: Sat, 3 Nov 2018 18:02:53 +1100 [thread overview]
Message-ID: <20181103070253.ajrqzs5xu2vf5stu@yavin> (raw)
In-Reply-To: <20181102091658.1bc979a4@gandalf.local.home>
[-- Attachment #1: Type: text/plain, Size: 3337 bytes --]
On 2018-11-02, Steven Rostedt <rostedt@goodmis.org> wrote:
> > As an aside, I just tested with the frame unwinder and it isn't thrown
> > off-course by kretprobe_trampoline (though obviously the stack is still
> > wrong). So I think we just need to hook into the ORC unwinder to get it
> > to continue skipping up the stack, as well as add the rewriting code for
> > the stack traces (for all unwinders I guess -- though ideally we should
>
> I agree that this is the right solution.
>
> > do this without having to add the same code to every architecture).
>
> True, and there's an art to consolidating the code between
> architectures.
>
> I'm currently looking at function graph and seeing if I can consolidate
> it too. And I'm also trying to get multiple uses to hook into its
> infrastructure. I think I finally figured out a way to do so.
>
> The reason it is difficult, is that you need to maintain state between
> the entry of a function and the exit for each task and callback that is
> registered. Hence, it's a 3x tuple (function stack, task, callbacks).
> And this must be maintained with preemption. A task may sleep for
> minutes, and the state needs to be retained.
>
> The only state that must be retained is the function stack with the
> task, because if that gets out of sync, the system crashes. But the
> callback state can be removed.
>
> Here's what is there now:
>
> When something is registered with the function graph tracer, every
> task gets a shadowed stack. A hook is added to fork to add shadow
> stacks to new tasks. Once a shadow stack is added to a task, that
> shadow stack is never removed until the task exits.
>
> When the function is entered, the real return code is stored in the
> shadow stack and the trampoline address is put in its place.
>
> On return, the trampoline is called, and it will pop off the return
> code from the shadow stack and return to that.
I was playing with a toy version of this using the existing kretprobe
architecture (by borrowing the shadow stack concept of storing the
stack_addr() -- though it's actually stored inside the existing
kretprobe_instance and thus doesn't need separate push-pop code).
The rewriting of kretprobe_trampoline in the stack unwinder *works* on
x86 now except for the regs handling (the current function is still
incorrectly shown as kretprobe_trampoline). This is actually a general
bug in ftrace as well, because (for instance) while the unwinder calls
into ftrace_graph_ret_addr() while walking up the stack this isn't used
to correct regs->ip in perf_callchain_kernel(). I think this is the
cause of the bug in ftrace-graph (if you switch to the "frame" unwinder
you might be able to see it more clearly) -- but when trying to fix it
I'm having trouble figuring out what retp should be (stack_addr(regs)
doesn't give the right result for some reason).
I will try to fix it up and attach it, but if you're already working on
a prototype the unifies all the users that works too. The patch I have
at the moment duplicates each of the key ftrace_graph_return_addr
invocations with a matching kretprobe_return_addr (though there's only
three of these).
--
Aleksa Sarai
Senior Software Engineer (Containers)
SUSE Linux GmbH
<https://www.cyphar.com/>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2018-11-03 7:03 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-01 8:35 [PATCH v3 0/2] kretprobe: produce sane stack traces Aleksa Sarai
2018-11-01 8:35 ` [PATCH v3 1/2] " Aleksa Sarai
2018-11-01 15:20 ` Masami Hiramatsu
2018-11-01 21:13 ` Aleksa Sarai
2018-11-02 3:04 ` Masami Hiramatsu
2018-11-02 4:37 ` Aleksa Sarai
2018-11-03 12:47 ` Masami Hiramatsu
2018-11-02 0:47 ` Steven Rostedt
2018-11-02 5:05 ` Aleksa Sarai
2018-11-02 6:59 ` Aleksa Sarai
2018-11-02 13:16 ` Steven Rostedt
2018-11-02 15:43 ` Josh Poimboeuf
2018-11-02 16:13 ` Steven Rostedt
2018-11-03 13:00 ` Masami Hiramatsu
2018-11-03 13:13 ` Steven Rostedt
2018-11-03 16:34 ` Masami Hiramatsu
2018-11-03 17:30 ` Steven Rostedt
2018-11-03 17:33 ` Steven Rostedt
2018-11-04 2:25 ` Masami Hiramatsu
2018-11-03 7:02 ` Aleksa Sarai [this message]
2018-11-04 11:59 ` Aleksa Sarai
2018-11-06 22:15 ` Steven Rostedt
2018-11-08 7:46 ` Aleksa Sarai
2018-11-08 8:04 ` Aleksa Sarai
2018-11-08 14:44 ` Josh Poimboeuf
2018-11-09 7:26 ` Masami Hiramatsu
2018-11-09 15:10 ` Aleksa Sarai
2018-11-09 7:15 ` Masami Hiramatsu
2018-11-09 15:06 ` Aleksa Sarai
2018-11-10 15:31 ` Masami Hiramatsu
2018-11-12 10:38 ` Aleksa Sarai
2018-11-03 13:23 ` Masami Hiramatsu
2018-11-02 7:58 ` Aleksa Sarai
2018-11-02 4:01 ` kbuild test robot
2018-11-01 8:35 ` [PATCH v3 2/2] trace: remove kretprobed checks Aleksa Sarai
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=20181103070253.ajrqzs5xu2vf5stu@yavin \
--to=cyphar@cyphar.com \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=anil.s.keshavamurthy@intel.com \
--cc=asarai@suse.de \
--cc=ast@kernel.org \
--cc=bgregg@netflix.com \
--cc=christian@brauner.io \
--cc=corbet@lwn.net \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=jolsa@redhat.com \
--cc=jpoimboe@redhat.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=naveen.n.rao@linux.vnet.ibm.com \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=shuah@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).