This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: Question regarding userspace tracing memcpy in glibc
- From: fche at redhat dot com (Frank Ch. Eigler)
- To: Holger Hans Peter Freyther <holger at freyther dot de>
- Cc: "Ariel Shaqed (Scolnicov)" <ariels at correlix dot com>, systemtap at sources dot redhat dot com
- Date: Tue, 04 Jan 2011 13:06:32 -0500
- Subject: Re: Question regarding userspace tracing memcpy in glibc
- References: <loom.20101126T174831-857@post.gmane.org> <y0mfwung32s.fsf@fche.csb> <AANLkTi=u3vUTnMU+4C0-0mS2t5hzDjz1Q+DLZ-Ku+c7d@mail.gmail.com> <y0mbp4tldqd.fsf@fche.csb> <4D131DFA.7010009@freyther.de>
Holger Hans Peter Freyther <holger@freyther.de> writes:
> [...]
> if we leave out the case where the compiler knows the amount to copy, what
> would be the way forward to be able to intercept ASM stubs? Get hand written
> DWARF2 symbols into the glibc code?
That's one possibility. Another is running "as -g --gdwarf-2", which
I believe glibc does not use that in its build of .s files. Another
one is http://sourceware.org/PR10208.
> Do you normally discuss these things in bug reports or the
> mailinglist?
Here is a good start. It does involve other tools too, so we may want
to bring in glibc / gdb types too.
- FChE