This is the mail archive of the systemtap@sourceware.org mailing list for the systemtap project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH -tip v4 0/6] kprobes: introduce NOKPROBE_SYMBOL() and fixes crash bugs


(2013/12/05 22:08), Sandeepa Prabhu wrote:
>> OK, I think the kprobe is like a strong medicine, not a toy,
>> since it can intercept most of the kernel functions which
>> may process a sensitive user private data. Thus even if we
>> fix all bugs and make it safe, I don't think we can open
>> it for all users (of course, there should be a knob to open
>> for any or restricted users.)
>>
>>> So we need both a maintainable and a sane/safe solution, and I'd like
>>> to apply the whole thing at once and be at ease that the solution is
>>> round. We should have done this years ago.
>>
>> For the safeness of kprobes, I have an idea; introduce a whitelist
>> for dynamic events. AFAICS, the biggest unstable issue of kprobes
>> comes from putting *many* probes on the functions called from tracers.
>>
>> It doesn't crash the kernel but slows down so much, because every
>> probes hit many other nested miss-hit probes. This gives us a big
>> performance impact. However, on the other side, this kind of feature
>> can be used *for debugging* static trace events by dynamic one if we
>> carefully use a small number of probes on such functions. :)
>>
>> Thus, I think we can restrict users from probing such functions by
>> using a whitelist which ftrace does already have;
>>  available_filter_functions :)
> I am not sure if this question is related, uprobes or ftrace code does
> not  define __kprobes, so is it safe to place kprobe on uprobes or
> ftrace code? 

Yes, it is "safe" in qualitative meaning. But for ftrace code, it could
give a performance impact by miss-hitting. Since uprobe is independent
from kprobe, it should work.

> Is it expected from arch code to support such cases?

Yes, the arch dependent implementation is the key. If it shares some
code which can be called from miss-hit path, it should be blacklisted.

Thank you,

-- 
Masami HIRAMATSU
IT Management Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com



Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]