Re: ioremap_uc() followed by set_memory_wc() - burrying MTRR

From: Andy Lutomirski <luto@amacapital.net>
To: Andy Walls <awalls@md.metrocast.net>
Cc: "Luis R. Rodriguez" <mcgrof@suse.com>,
	"Toshi Kani" <toshi.kani@hp.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	"Ingo Molnar" <mingo@kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Hal Rosenstock" <hal.rosenstock@gmail.com>,
	"Sean Hefty" <sean.hefty@intel.com>,
	"Suresh Siddha" <sbsiddha@gmail.com>,
	"Rickard Strandqvist" <rickard_strandqvist@spectrumdigital.se>,
	"Mike Marciniszyn" <mike.marciniszyn@intel.com>,
	"Roland Dreier" <roland@purestorage.com>,
	"Juergen Gross" <jgross@suse.com>,
	"Mauro Carvalho Chehab" <mchehab@osg.samsung.com>,
	"Borislav Petkov" <bp@suse.de>, "Mel Gorman" <mgorman@suse.de>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	"Davidlohr Bueso" <dbueso@suse.de>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"Jean-Christophe Plagniol-Villard" <plagnioj@jcrosoft.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Ville Syrjälä" <syrjala@sci.fi>,
	"Linux Fbdev development list" <linux-fbdev@vger.kernel.org>,
	linux-media@vger.kernel.org, "X86 ML" <x86@kernel.org>
Subject: Re: ioremap_uc() followed by set_memory_wc() - burrying MTRR
Date: Wed, 15 Apr 2015 17:58:14 -0700	[thread overview]
Message-ID: <CALCETrWRjGYqcYPNizrbiVFwFHhrLf=8NTTCLVZh7Q6MgAWj=Q@mail.gmail.com> (raw)
In-Reply-To: <1429142387.1899.57.camel@palomino.walls.org>

On Wed, Apr 15, 2015 at 4:59 PM, Andy Walls <awalls@md.metrocast.net> wrote:
> On Wed, 2015-04-15 at 16:42 -0700, Andy Lutomirski wrote:
>> On Wed, Apr 15, 2015 at 3:38 PM, Andy Walls <awalls@md.metrocast.net> wrote:
>
>> >
>>
>> IMO the right solution would be to avoid ioremapping the whole bar at
>> startup.  Instead ioremap pieces once the driver learns what they are.
>> This wouldn't have any of these problems -- you'd ioremap() register
>> regions and you'd ioremap_wc() the framebuffer once you find it.  If
>> there are regions of unknown purpose, just don't map them all.
>>
>> Would this be feasible?
>
> Feasible? Maybe.
>
> Worth the time and effort for end-of-life, convential PCI hardware so I
> can have an optimally performing X display on a Standard Def Analog TV
> screen?   Nope. I don't have that level of nostalgia.
>

The point is actually to let us unexport or delete mtrr_add.  We can
either severely regress performance on ivtv on PAT-capable hardware if
we naively switch it to arch_phys_wc_add or we can do something else.
The something else remains to be determined.

>
> We sort of know where some things are in the MMIO space due to
> experimentation and past efforts examining the firmware binary.
>
> Documentation/video4linux/cx2341x/fw-*.txt documents some things.  The
> driver code actually codifies a little bit more knowledge.
>
> The driver code for doing transfers between host and card is complex and
> fragile with some streams that use DMA, other streams that use PIO,
> digging VBI data straight out of card memory, and scatter-gather being
> broken on newer firmwares.  Playing around with ioremapping will be hard
> to get right and likely cause something in the code to break for the
> primary use case of the ivtv supported cards.

Ick.

If the only thing that really wants WC is the esoteric framebuffer
thing, could we just switch to arch_phys_wc_add and assume that no one
will care about the regression on new CPUs with ivtv cards?

--Andy