Date: Fri, 8 Aug 2008 21:51:33 +0300 From: Kostik Belousov <kostikbel@gmail.com> To: John Baldwin <jhb@freebsd.org> Cc: Stanislav Sedov <stas@freebsd.org>, cvs-src@freebsd.org, src-committers@freebsd.org, cvs-all@freebsd.org Subject: Re: cvs commit: src/share/man/man4 Makefile cpuctl.4 src/sys/amd64/amd64 support.S src/sys/amd64/conf NOTES src/sys/amd64/include cpufunc.h specialreg.h src/sys/conf files.amd64 files.i386 src/sys/dev/cpuctl cpuctl.c ... Message-ID: <20080808185133.GG97161@deviant.kiev.zoral.com.ua> In-Reply-To: <200808081427.42536.jhb@freebsd.org> References: <200808081631.m78GVG9i088754@repoman.freebsd.org> <200808081251.17686.jhb@freebsd.org> <20080808181052.GF97161@deviant.kiev.zoral.com.ua> <200808081427.42536.jhb@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--2uZVBGM+62ujkrHk
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Fri, Aug 08, 2008 at 02:27:42PM -0400, John Baldwin wrote:
> On Friday 08 August 2008 02:10:52 pm Kostik Belousov wrote:
> > On Fri, Aug 08, 2008 at 12:51:17PM -0400, John Baldwin wrote:
> > > On Friday 08 August 2008 12:26:53 pm Stanislav Sedov wrote:
> > > > stas 2008-08-08 16:26:53 UTC
> > > >=20
> > > > FreeBSD src repository
> > > >=20
> > > > Modified files:
> > > > share/man/man4 Makefile=20
> > > > sys/amd64/amd64 support.S=20
> > > > sys/amd64/conf NOTES=20
> > > > sys/amd64/include cpufunc.h specialreg.h=20
> > > > sys/conf files.amd64 files.i386=20
> > > > sys/i386/conf NOTES=20
> > > > sys/i386/i386 support.s=20
> > > > sys/i386/include cpufunc.h specialreg.h=20
> > > > sys/modules Makefile=20
> > > > sys/sys priv.h=20
> > > > usr.sbin Makefile=20
> > > > Added files:
> > > > share/man/man4 cpuctl.4=20
> > > > sys/dev/cpuctl cpuctl.c=20
> > > > sys/modules/cpuctl Makefile=20
> > > > sys/sys cpuctl.h=20
> > > > usr.sbin/cpucontrol Makefile amd.c amd.h cpucontrol.8=20
> > > > cpucontrol.c cpucontrol.h intel.c intel.h=
=20
> > > > Log:
> > > > SVN rev 181430 on 2008-08-08 16:26:53Z by stas
> > > > =20
> > > > - Add cpuctl(4) pseudo-device driver to provide access to some=20
> low-level
> > > > features of CPUs like reading/writing machine-specific register=
s,
> > > > retrieving cpuid data, and updating microcode.
> > > > - Add cpucontrol(8) utility, that provides userland access to
> > > > the features of cpuctl(4).
> > > > - Add subsequent manpages.
> > > > =20
> > > > The cpuctl(4) device operates as follows. The pseudo-device node=
=20
> cpuctlX
> > > > is created for each cpu present in the systems. The pseudo-device=
=20
> minor
> > > > number corresponds to the cpu number in the system. The cpuctl(4)=
=20
> pseudo-
> > > > device allows a number of ioctl to be preformed, namely=20
> RDMSR/WRMSR/CPUID
> > > > and UPDATE. The first pair alows the caller to read/write=20
> machine-specific
> > > > registers from the correspondent CPU. cpuid data could be retriev=
ed=20
> using
> > > > the CPUID call, and microcode updates are applied via UPDATE.
> > > > =20
> > > > The permissions are inforced based on the pseudo-device file=20
> permissions.
> > > > RDMSR/CPUID will be allowed when the caller has read access to th=
e=20
> device
> > > > node, while WRMSR/UPDATE will be granted only when the node is op=
ened
> > > > for writing. There're also a number of priv(9) checks.
> > > > =20
> > > > The cpucontrol(8) utility is intened to provide userland access to
> > > > the cpuctl(4) device features. The utility also allows one to app=
ly
> > > > cpu microcode updates.
> > > > =20
> > > > Currently only Intel and AMD cpus are supported and were tested.
> > >=20
> > > Note that cpuid isn't a privileged instruction, so I'm not sure it's=
=20
> really=20
> > > worth having an ioctl for that particular case.
> >=20
> > It was discussed when patch was reviewed on current@. The ioctl allows
> > to get cpuid information for specific processor, as opposed to some
> > random core curthread happens to run ATM.
>=20
> You can achieve that now with cpuset. :) (See my ping-pong test program=
=20
> recently which used cpuid to fetch the APIC ID to test for ping-ponging i=
n=20
> the scheduler.)
If this is a backout request (for cpuid functionality) then we will do it.
But I considered it much easier and cleaner to do
fd =3D open("/dev/cpuctlN", O_RDWR);
ioctl(fd, CPUCTL_CPUID, &x);
if (x.y)
ioctl(fd, CPUCTL_WRMSR, ...);
close(fd);
then
fd =3D open("/dev/cpuctlN", O_RDWR);
cpuset(...); /* bind to cpu */
__asm__("cpuid" : =3D0 (x));
if (x.y)
ioctl(fd, CPUCTL_WRMSR, ...);
cpuset(...); /* restore prev mask */
close(fd);
--2uZVBGM+62ujkrHk
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (FreeBSD)
iEYEARECAAYFAkiclbMACgkQC3+MBN1Mb4i96QCdERqfA4BL+ItjAgsHJzGsk9DB
hmUAoNm3B3USd4GdVGND+QQx3AiZclaH
=JJ6n
-----END PGP SIGNATURE-----
--2uZVBGM+62ujkrHk--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080808185133.GG97161>