Re: [PATCH v3] ad7877: keep dma rx buffers in seperate cache lines

From: Paul Mundt <lethal@linux-sh.org>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Mike Frysinger <vapier.adi@gmail.com>,
	Christoph Lameter <cl@linux.com>, Matt Mackall <mpm@selenic.com>,
	Dmitry Torokhov <dmitry.torokhov@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Oskar Schirmer <os@emlix.com>,
	Michael Hennerich <Michael.Hennerich@analog.com>,
	linux-input@vger.kernel.org, linux-kernel@vger.kernel.org,
	Daniel Gl??ckner <dg@emlix.com>,
	Oliver Schneidewind <osw@emlix.com>,
	Johannes Weiner <jw@emlix.com>, Nick Piggin <npiggin@suse.de>,
	David Rientjes <rientjes@google.com>,
	David Brownell <dbrownell@users.sourceforge.net>,
	Grant Likely <grant.likely@secretlab.ca>
Subject: Re: [PATCH v3] ad7877: keep dma rx buffers in seperate cache lines
Date: Thu, 13 May 2010 15:21:43 +0900	[thread overview]
Message-ID: <20100513062143.GB9920@linux-sh.org> (raw)
In-Reply-To: <4BE9C258.10706@cs.helsinki.fi>

On Tue, May 11, 2010 at 11:47:20PM +0300, Pekka Enberg wrote:
> Mike Frysinger wrote:
> >On Tue, May 11, 2010 at 16:38, Pekka Enberg wrote:
> >>Mike Frysinger wrote:
> >>>that is a question for David/Grant.  i'm not the SPI core maintainer,
> >>>i'm merely watching over some SPI drivers.  however, this answer also
> >>>doesnt sound like it's thinking big enough because what you're
> >>>proposing isnt specific to the SPI bus -- any time a DMA safe buffer
> >>>is needed dynamically, this function could be used.
> >>Well, we have dma_alloc_coherent(), shouldn't you be using that instead?
> >
> >my understanding is that dma_alloc_coherent() gives you a buffer that
> >is always coherent.  the SPI layers take care of flushing and such on
> >the fly which means allocating coherent memory is overkill and bad for
> >performance.
> 
> OK, I'm out of my expert area here but if dma_alloc_coherent() doesn't 
> work for you, you should probably extend the DMA API, not kmalloc().
> 
Note that the DMA API already has dma_alloc_noncoherent() for these
sorts of cases. If the driver is taking care of cache maintenance then
dma_alloc_noncoherent() is certainly a reasonable way to go.

Most architectures today simply wrap dma_alloc_noncoherent() to
dma_alloc_coherent(), but if there were more users of the API then
that would quickly change.