This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: [RFC PATCH tip/master 2/3] kprobes: Allocate kretprobe instance if its free list is empty
- From: Alban Crequy <alban at kinvolk dot io>
- To: Ingo Molnar <mingo at kernel dot org>
- Cc: Masami Hiramatsu <mhiramat at kernel dot org>, Steven Rostedt <rostedt at goodmis dot org>, Ingo Molnar <mingo at redhat dot com>, Alban Crequy <alban dot crequy at gmail dot com>, Alexei Starovoitov <ast at kernel dot org>, Jonathan Corbet <corbet at lwn dot net>, Arnaldo Carvalho de Melo <acme at redhat dot com>, Omar Sandoval <osandov at fb dot com>, linux-doc at vger dot kernel dot org, netdev at vger dot kernel dot org, linux-kernel at vger dot kernel dot org, Iago López Galeiras <iago at kinvolk dot io>, Michael Schubert <michael at kinvolk dot io>, Dorau Lukasz <lukasz dot dorau at intel dot com>, systemtap at sourceware dot org
- Date: Thu, 30 Mar 2017 15:03:11 +0200
- Subject: Re: [RFC PATCH tip/master 2/3] kprobes: Allocate kretprobe instance if its free list is empty
- Authentication-results: sourceware.org; auth=none
- References: <149076484118.24574.7083269903420611708.stgit@devbox> <149076498222.24574.679546540523044200.stgit@devbox> <20170329063005.GA12220@gmail.com> <20170329172510.e012406497fd38a54d5069b3@kernel.org> <20170330065332.GA30148@gmail.com>
On Thu, Mar 30, 2017 at 8:53 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> * Masami Hiramatsu <mhiramat@kernel.org> wrote:
>
>> > So this is something I missed while the original code was merged, but the concept
>> > looks a bit weird: why do we do any "allocation" while a handler is executing?
>> >
>> > That's fundamentally fragile. What's the maximum number of parallel
>> > 'kretprobe_instance' required per kretprobe - one per CPU?
>>
>> It depends on the place where we put the probe. If the probed function will be
>> blocked (yield to other tasks), then we need a same number of threads on
>> the system which can invoke the function. So, ultimately, it is same
>> as function_graph tracer, we need it for each thread.
>
> So then put it into task_struct (assuming there's no kretprobe-inside-kretprobe
> nesting allowed). There's just no way in hell we should be calling any complex
> kernel function from kernel probes!
Some kprobes are called from an interruption context. We have a kprobe
on tcp_set_state() and this is sometimes called when the network card
receives a packet.
> I mean, think about it, a kretprobe can be installed in a lot of places, and now
> we want to call get_free_pages() from it?? This would add a massive amount of
> fragility.
>
> Instrumentation must be _simple_, every patch that adds more complexity to the
> most fundamental code path of it should raise a red flag ...
>
> So let's make this more robust, ok?
>
> Thanks,
>
> Ingo
Thanks,
Alban