Messages in this thread |  | | | Date | Wed, 30 Dec 1998 11:00:29 -0800 (PST) | | From | Linus Torvalds <> | | Subject | Re: 2.2.0pre1 OOPS on boot. |
| |
On Wed, 30 Dec 1998, Alan Cox wrote: > > > - CONFIG_M386: Runs on anything > > - CONFIG_M486: requires "invlpg" and a working supervisor mode WP bit > > - CONFIG_M586: requires "rdtsc" > > - CONFIG_M686: requires a non-broken local APIC when running SMP > > > > and now all machine configuration options actually have real meaning for > > the behaviour of the kernel apart from just some alignment hints to the > > compiler. > > The alignment hints are wrong for most non intel chips without RDTSC if you > try and tie alignment to CPU info. The 'requires rdtsc' for 586+ isnt needed > except for SMP systems - which are all intel for x86 so the problem doesn't > arise for that case.
The "rdtsc" thing _is_ needed even for UP systems.
Look at the code generated for do_gettimeofday() some time - it's a worthwhile optimization to do statically.
(And if you wonder why I care about gettimeofday(), just look at the system call distribution for a lot of programs, including most X programs).
As I mentioned in my email, it may be a valid thing to expand the choices a bit (ie add a choice between i486 and i586), but the static "rdtsc" thing definitely stays.
Linus
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
|  |