Re: [RFC] global page support

[Samuel Thibault]

Thomas Schwinge, le Sat 13 Oct 2007 22:48:44 +0200, a écrit :
> On Thu, Dec 21, 2006 at 12:45:11AM +0100, Samuel Thibault wrote:
> > --- i386/i386at/model_dep.c 26 Nov 2006 20:01:47 -0000      1.9.2.10
> 
> >     kernel_page_dir[lin2pdenum(0)] =
> >             kernel_page_dir[lin2pdenum(LINEAR_MIN_KERNEL_ADDRESS)];
> >     set_cr3((unsigned)kernel_page_dir);
> > +   if (CPU_HAS_FEATURE(CPU_FEATURE_PGE))
> > +           set_cr4(get_cr4() | CR4_PGE);
> >     set_cr0(get_cr0() | CR0_PG | CR0_WP);
> >     flush_instr_queue();
> 
> Intel says that ``when enabling the global page feature, paging must be
> enabled (by setting the PG flag in control register CR0) before the PGE
> flag is set.  Reversing this sequence may affect program correctness, and
> processor performance will be impacted.''  Aren't we currently doing it
> the wrong way round?

Ah, I didn't see that. Feel free to try, check and commit.

Samuel