From mboxrd@z Thu Jan  1 00:00:00 1970
Date: Tue, 27 May 2014 14:30:18 -0700
From: Nick Owens <mischief@9.offblast.org>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Message-ID: <20140527213018.GQ3763@iota.offblast.org>
References: <20140527201016.GP3763@iota.offblast.org>
	<0e05f8946ce2cff4a4ad7d2e044b984d@ladd.quanstro.net>
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha1;
	protocol="application/pgp-signature"; boundary="BouVgDkIlpb7X6Bk"
Content-Disposition: inline
In-Reply-To: <0e05f8946ce2cff4a4ad7d2e044b984d@ladd.quanstro.net>
User-Agent: Mutt/1.5.21 (2010-09-15)
Subject: Re: [9fans] 8l -e
Topicbox-Message-UUID: f2dc67c4-ead8-11e9-9d60-3106f5b1d025


--BouVgDkIlpb7X6Bk
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Tue, May 27, 2014 at 04:16:24PM -0400, erik quanstrom wrote:
> > you can see there is a JMP over _tracein and a RET before _traceout.
> > what gives?
>=20
> ah, that's the magic!  the idea is to be able to enable and disable these=
 tracepoints
> at runtime in a multiprocessor environment without any locking.
>=20
> - erik
>=20

ok. i'm beginning to understand better. is there a specific use case,
such as the kernel or userland?

i didn't see anything like a tool that could poke nops into the right
places. i started to write an acid function to put the nops in one
 named function, and then i realized that the ret can appear several
 times in one function and i would need to search for and patch them
 out. but only the *first* ret, not second, e.g.:

 setvar+0x3a 0x0000adf5	RET			<--- should be NOP
 setvar+0x3b 0x0000adf6	CALL	_traceout(SB)
 setvar+0x40 0x0000adfb	RET			<--- should not be NOP

 i was able to patch the JMP, and the RET but only in the case where it
 appears at the bottom of a function.

defn traceon(fn){
	bound =3D fnbound(fn);

	// nop first jmp
	*(bound[0]) =3D 0x90\b;
	*(bound[0]+1) =3D 0x90\b;

	// and the ret
	// XXX should search for ret
	*(bound[1]-7) =3D 0x90\b;
}


maybe these were not the droids i was looking for.
my real goal is to make timing statistics for function calls in a program.
perhaps this goal is better fulfilled simply by prof!


--BouVgDkIlpb7X6Bk
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.13 (OpenBSD)
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=8eXT
-----END PGP SIGNATURE-----

--BouVgDkIlpb7X6Bk--