On Tue, 20 Mar 2001, Bruce Evans wrote:
> On Mon, 19 Mar 2001, John Baldwin wrote:
>
> > Hmmm. An eip of 0 is bad. This could be just another instance of the bzero
> > bug just in another place. You probably want to change the code that actually
> > sets *bzero to i586_bzero (and same for any other ops that use floating point).
> > The code in question for this lies in i386/isa/npx.c. It seems we use the fp
> > regs for copyin/copyout and bcopy as well. I would just change line 458 of
> > npx.c to say '#ifdef I586_CPU_XXX' for now as your temporary patch (then you
> > don't need to patch pmap_zero_page() anymore.)
>
> There is no need to change anything. Just disable the fp optimizations
> using the npx flags.
Actually, there may be. The bandwidth test gets run on 586's even if
the flags say not to use the result. This is to provide a "free"
bandwidth test. It was harmless when the fp code wasn't broken. The
flags are mainly for disabling using the fp code for accesses to broken
device memory (bcopy and/or bzero were (are?) abuses to access device
memory, and some device memory doesn't like 64-bit accesses).
Bruce
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message
