Date: Wed, 4 Jul 2007 05:52:28 +1000 From: Peter Jeremy <peterjeremy@optushome.com.au> To: Robert Watson <rwatson@freebsd.org> Cc: cvs-src@freebsd.org, src-committers@freebsd.org, cvs-all@freebsd.org Subject: Re: cvs commit: src/sys/sys socketvar.h Message-ID: <20070703195228.GP15680@turion.vk2pj.dyndns.org> In-Reply-To: <200707031014.l63AEE9Y026819@repoman.freebsd.org> References: <200707031014.l63AEE9Y026819@repoman.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--pE2VAHO2njSJCslu
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On 2007-Jul-03 10:14:13 +0000, Robert Watson <rwatson@freebsd.org> wrote:
> Fix a bug in sblock() that has existed since revision 1.1 from BSD:
> correctly return an error if M_NOWAIT is passed to sblock() and the
> operation might block. This remarkably subtle macro bug appears to
> be responsible for quite a few undiagnosed socket buffer corruption
> and mbuf-related kernel panics.
This bug would appear to be a classic example of the dangers of trying
to force force multiple C statements into a single statement. IMHO,
it (and many of the other macros in socketvar.h) should be inline
functions, rather than macros.
IMHO, the following is far more legible:
static __inline int
sblock(struct sockbuf *sb, int wf)
{
if (sb->sb_flags & SB_LOCK)
return ((wf =3D=3D M_WAITOK) ? sb_lock(sb) : EWOULDBLOCK);
else {
sb->sb_flags |=3D SB_LOCK;
return (0);
}
}
--=20
Peter Jeremy
--pE2VAHO2njSJCslu
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (FreeBSD)
iD8DBQFGiqj8/opHv/APuIcRArpaAKC2NEu4WSZCp1SfpMQMZtZkeOyB6wCeNpKM
rLx8sl952WKNhYYL4aSercU=
=UNvf
-----END PGP SIGNATURE-----
--pE2VAHO2njSJCslu--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070703195228.GP15680>