Date: Sun, 25 Feb 2001 00:45:51 -0800 (PST) From: Matt Dillon <dillon@earth.backplane.com> To: Peter Wemm <peter@netplex.com.au> Cc: Bruce Evans <bde@zeta.org.au>, Jake Burkholder <jake@FreeBSD.ORG>, cvs-committers@FreeBSD.ORG, cvs-all@FreeBSD.ORG Subject: Re: cvs commit: src/sys/i386/i386 db_trace.c exception.s machdep.c trap.c src/sys/i386/include asnames.h Message-ID: <200102250845.f1P8jp412754@earth.backplane.com> References: <200102250736.f1P7aVi01775@mobile.wemm.org>
next in thread | previous in thread | raw e-mail | index | archive | help
:>
:> This breaks profiling and pessimizes Xsyscall a little. Please back this
:> out.
:
:Are you sure? The X*syscall stubs dont seem to be profiled..
Yes, that's what the FAKE_MCOUNT() macro does.
:Obviously I could easily be misunderstanding things, but the FAKE_MCOUNT
:pulls the caller off the stack, right? How does this all tie in?
:Would this change imply that the cpu time of the lcall version would be
:applied to the int0x80 version?
FAKE_MCOUNT tells __mcount where the caller trapframe really started.
It doesn't pull anything off the stack. If you have two
entry points both intersecting at the same FAKE_MCOUNT without using
the special macros to handle the jump then the profiling code will
get really confused in regards to the entry point.
-Matt
:
:Cheers,
:-Peter
:--
:Peter Wemm - peter@FreeBSD.org; peter@yahoo-inc.com; peter@netplex.com.au
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200102250845.f1P8jp412754>