Re: [v4 11/17] vt-d: Add API to update IRTE when VT-d PI is used

["Wu, Feng" <feng.wu@intel.com>]

> -----Original Message-----
> From: Andrew Cooper [mailto:andrew.cooper3@citrix.com]
> Sent: Thursday, July 23, 2015 9:52 PM
> To: Wu, Feng; xen-devel@lists.xen.org
> Cc: Zhang, Yang Z; Tian, Kevin; Keir Fraser; Jan Beulich
> Subject: Re: [v4 11/17] vt-d: Add API to update IRTE when VT-d PI is used
> 
> On 23/07/15 12:35, Feng Wu wrote:
> > +    GET_IREMAP_ENTRY(ir_ctrl->iremap_maddr, remap_index,
> iremap_entries, p);
> > +
> > +    old_ire = new_ire = *p;
> > +
> > +    /* Setup/Update interrupt remapping table entry. */
> > +    setup_posted_irte(&new_ire, pi_desc, gvec);
> > +    ret = cmpxchg16b(p, &old_ire, &new_ire);
> > +
> > +    ASSERT(ret == *(__uint128_t *)&old_ire);
> 
> This cannot be correct.  Either the cmpxchg() is required and you must
> cope with it failing, or the cmpxchg() is not required and this should
> be a plain write.

In fact, Jan gave some comments about this before. The only thing here we
need to do is to atomically update the 128-bit IRTE, so we need use cmpxchg16b,
and there is no race condition here, which means the IRTE cannot be changed
behind us, so the return value should be the same as the old one, right?

Thanks,
Feng

> 
> It looks as if the cmpxchg() is required.
> 
> ~Andrew