On Sat, Sep 26, 2015 at 7:15 PM, Richard Henderson <r...@twiddle.net> wrote:
> On 09/24/2015 01:32 AM, Alvise Rigo wrote:
> > + if (cpu == smp_cpus) {
> > + if (smp_cpus >= EXCL_BITMAP_CELL_SZ) {
> > + return bitmap[EXCL_BITMAP_GET_BYTE_OFFSET(addr)];
> > + } else {
> > + return bitmap[EXCL_BITMAP_GET_BYTE_OFFSET(addr)] &
> > + ((1 << smp_cpus) - 1);
> > + }
> > + } else {
> > + return bitmap[EXCL_BITMAP_GET_BYTE_OFFSET(addr)] & (1 <<
> EXCL_IDX(cpu));
> > + }
>
> How can more than one cpu have the same address exclusively?
>
The bitmap is used to track which cpus have the EXCL flag set for that
particular page.
A bit set to 0 assures that all the corresponding cpus are following the
slow-path in that page.
>
> Isn't this scheme giving a whole page to a cpu, not a cacheline?
>
The actual exclusive range in set in CPUArchState, this is the information
that we evaluate to see whether there was a conflict or not.
Regards,
alvise
> That's going to cause ll/sc conflicts where real hardware wouldn't.
>
>
>
> r~
>
