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][kprobe]disallow kprobes on emulate_step function


Ananth N Mavinakayanahalli wrote:
On Tue, Oct 31, 2006 at 05:13:19PM +0800, Gui,Jian wrote:
Probing on emulate_step function will crash 2.6.18.1 when it is
triggered. This problem is powerpc dependent.

When kprobe is triggered, emulate_step is on its kernel path and
will cause recursive kprobe fault. This patch can disallow
kprobes on emulate_step function.

Looks good, but not complete :-) Even branch_taken() needs to be __kprobes as emulate_step() calls it.

Please add that and feel free to post the patch to linuxppc-dev
for upstream inclusion.

Ananth

Gui Jian mentioned branch_taken() in another thread: http://sources.redhat.com/ml/systemtap/2006-q4/msg00290.html

So now the questions is, shall we mark all functions appeared in the call path to kprobe with __kprobes? If so, then these functions will be put in __kprobe section. Will this have a negative performance impact because of the lower hit ratio of instruction cache?

- Guanglei


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