--4Ckj6UjgE2iN1+kY
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On 2006.01.16 19:14:47 +0100, Anders Mundt Due wrote:
| Have a thinkpad (x41) laptop with a Pentium M cpu in, so naturally
| looked for speedstepping. It gets detected but not quite as it should
| when I've got it hooked up with a PSU:
|=20
| cpu0 at mainbus0: apid 0 (boot processor)
| cpu0: Intel Pentium M (Dothan) (686-class), 1496.34 MHz, id 0x6d8
| cpu0: features
| afe9fbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR>
| cpu0: features afe9fbff<PGE,MCA,CMOV,PAT,CFLUSH,DS,ACPI,MMX>
| cpu0: features afe9fbff<FXSR,SSE,SSE2,SS,TM,SBF>
| cpu0: features2 180<EST,TM2>
| cpu0: "Intel(R) Pentium(R) M processor 1.50GHz"
| cpu0: I-cache 32 KB 64B/line 8-way, D-cache 32 KB 64B/line 8-way
| cpu0: L2 cache 2 MB 64B/line 8-way
| cpu0: using thermal monitor 2
| cpu0: Enhanced SpeedStep running at 1500 MHz (1116 mV)
| cpu0: Enhanced SpeedStep operating point not in table
|=20
| It would appear that Thinkpad X41 gets shipped with a Pentium M758 cpu
| and that is, for some reason wrapped in #if 0 blocks in
| src/sys/arch/i386/i386/est.c

The reason for that ifdef is that est.c matches CPUs by their cpu
brand. It makes the wrong assumption that no different CPUs speeds
will run at different voltages and that there's only one FSB value (!).
Of course this leads to all sorts of wrong or unidentified CPU voltages.

|=20
| Should I just send-pr it?

Perhaps it's better to send a PR, with a diff, for future users.

Thanks,
		-- Rui Paulo

--4Ckj6UjgE2iN1+kY
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.2 (NetBSD)

iD8DBQFDzA/PZPqyxs9FH4QRAuFvAJ0dI8FlEOgwvMBRt8eJ7erekC4FowCgob5L
sw9r8reZU6f+EVBSy4rO0Rc=
=ifx7
-----END PGP SIGNATURE-----

--4Ckj6UjgE2iN1+kY--