Re: port-amd64/47967: DTrace does not work while running under QEMU

[Jukka Ruohonen <jruohonen%iki.fi@localhost>]

The following reply was made to PR port-amd64/47967; it has been noted by GNATS.

From: Jukka Ruohonen <jruohonen%iki.fi@localhost>
To: gnats-bugs%NetBSD.org@localhost
Cc: 
Subject: Re: port-amd64/47967: DTrace does not work while running under QEMU
Date: Thu, 27 Jun 2013 03:01:28 +0300

 Sorry, 
 
 wrote before thinking, which is usual, sorry. But nevertheless.
 
 On Wed, Jun 26, 2013 at 10:30:01PM +0000, Christos Zoulas wrote:
 > The following reply was made to PR port-amd64/47967; it has been noted by 
 > GNATS.
 
 >  +   if (rdmsr(MSR_TSC) != 0)
 >  +           return;
 >   
 >  -       /* if QEMU does not implement MSR_TSC, disable the TSC */
 >  -       ci->ci_feat_val[0] &= ~CPUID_MSR;
 >  -       cpu_feature[0] &= ~CPUID_MSR;
 >  +   aprint_error_dev(ci->ci_dev, "Bad MSR_TSC support");
 >  +   cpu_msr_tsc = 0;
 
 This hardly seems right. Now TSC determines whether something is capable of
 MSRs? Those are just registers, even for emulators.  TM: fixing bugs in the
 kernel that are not really bugs, i.e.  never has there been in NetBSD actual
 x86 hardware for which this wouldn't work.
 
 - Jukka.