Re: x86 setup rewrite tree ready for flamage^W review

"H. Peter Anvin" <hpa@xxxxxxxxx> writes:

Eric W. Biederman wrote:

HPA is both right and wrong on this. The safe sequence for entering
protected mode requires a jump immediately after setting PE in %cr0.
To serialize the instruction stream and to be on an execution that
is tested and guaranteed to work in cpus.


Eric, that's complete nonsense. What Intel documents and what Intel
tests are two very different things.

Likely.

Intel appears to be afraid of what they call "the crack", but the
semantics of the transition are quite well understood.

Regardless not putting a jump in there violates the principle of
be conservative in what you send.

A lot of the Intel manuals are boilerplate written by technical writers.
Once you're used to them you can spot it quite easily because it's
carried from generation to generation with little change, even when it's
blatantly obsoleted.

Even on 386 and 486 class cpus?

To some extent if the rules don't change it makes sense for them to
copy the information from one generation to the next of the architecture.
Even if the current cpus don't really care.

I guess I just don't see the sense in taking chances if we don't have
to, and I don't see any real advantage of doing a data segment reload
before the jump.

Eric
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: [RFC patch 08/18] cnt32_to_63 should use smp_rmb()
    ... macro expects _perfect_ order of timestamps, no skew whatsoever, or ... otherwise time could jump. ... two cycle counter values appear to go backward between CPUs? ...
    (Linux-Kernel)
  • Re: 8.5... end of sept?
    ... I think you are probably right to be a little concerned about going to a 64bit OS - as you say there are limited 64 bit apps at present and all your devices will need 64 bit drivers - everything. ... My personal thinking is that when I go dual core I will get a big jump in speed anyway (CPUs are faster than my existing one and I get two of them for rendering), I will get 2 CPUs allowing me to do some serious ... I will most likely leave WinX64 for now but jump to Vista 64 in a year, 18 months time when it comes out. ... 64bit and a nice new OS - I have to admit I really enjoy moving to brand new generation OS's when they ...
    (comp.graphics.apps.lightwave)
  • Re: 8.5... end of sept?
    ... I can jump to the full-on 64XP when more apps comply and more drivers comply. ... Either way, I know that things are moving in the 64bit direction anyway, so I won't have a system I can't use. ... My personal thinking is that when I go dual core I will get a big jump in speed anyway (CPUs are faster than my existing one and I get two of them for rendering), I will get 2 CPUs allowing me to do some serious ...
    (comp.graphics.apps.lightwave)
  • [GIT PULL] x86 setup: correct booting on 486 (revised)
    ... add a near jump to serialize %cr0 on 386/486 ... commit 142a92e61f9c405a114cb2bfaf3ce3f537a48a89 ...
    (Linux-Kernel)