Re: [PATCH v8 RFC 1/3] sparc: Break up monolithic iommu table/lock into finer graularity pools and lock

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Fri, 2015-04-03 at 14:28 -0400, Sowmini Varadhan wrote:
> 
> Just want to confirm:
> 
> > > + again:
> > > +	if (pass == 0 && handle && *handle &&
> > > +	    (*handle >= pool->start) && (*handle < pool->end))
> > > +		start = *handle;
> > > +	else
> > > +		start = pool->hint;
> > 
> > Now this means "handle" might be < pool->hint, in that case you also
> > need a lazy flush. Or rather only if the resulting alloc is. My
>          :
> 
> > > +		} else {
> > > +			/* give up */
> > > +			n = DMA_ERROR_CODE;
> > > +			goto bail;
> > > +		}
> > > +	}
> > 
> > Here, make this something like:
> > 
> > 	} else if (end < pool->hint)
> > 		need_flush = true;
> 
> you mean 
> 
>  	} else if (start < pool->hint)
> 
> right?  (so I'm not missing some corner-case that you are thinking
> about here)

No, I meant "n < pool->hint", ie, the start of the newly allocated
block.

"end" hasn't been adjusted yet at that point but we don't want to
compare "end" anyway (which will be n + npages), we really want n, ie if
the *beginning* of the newly allocated chunk is before the end of the
previous one (after all they may even overlap if the previous one has
been freed).

Ben.

> --Sowmini
>