From mboxrd@z Thu Jan  1 00:00:00 1970
From: benh@kernel.crashing.org (Benjamin Herrenschmidt)
Date: Wed, 28 Oct 2015 12:20:58 +0900
Subject: [PATCH 2/7 v2] powerpc/dma-mapping: override dma_get_page_shift
In-Reply-To: <20151028023028.GI7716@linux.vnet.ibm.com>
References: <20151023205420.GA10197@linux.vnet.ibm.com>
 <20151023205718.GC10197@linux.vnet.ibm.com> <562F1368.1030204@ozlabs.ru>
 <20151027222706.GF7716@linux.vnet.ibm.com> <56301E24.1060304@ozlabs.ru>
 <20151028015451.GH7716@linux.vnet.ibm.com>
 <1445998805.1856.24.camel@kernel.crashing.org>
 <20151028023028.GI7716@linux.vnet.ibm.com>
Message-ID: <1446002458.1856.25.camel@kernel.crashing.org>

On Tue, 2015-10-27@19:30 -0700, Nishanth Aravamudan wrote:
> On 28.10.2015 [11:20:05 +0900], Benjamin Herrenschmidt wrote:
> > On Tue, 2015-10-27@18:54 -0700, Nishanth Aravamudan wrote:
> > > 
> > > In "bypass" mode, what TCE size is used? Is it guaranteed to be
> > > 4K?
> > 
> > None :-) The TCEs are completely bypassed. You get a N:M linear
> > mapping
> > of all memory starting at 1<<59 PCI side.
> 
> Err, duh, sorry! Ok, so in that case, DMA page shift is PAGE_SHIFT,
> then?

I think so.

Cheers,
Ben.