Date: Tue, 12 May 2015 10:12:05 -0500
From: Josh Cartwright <joshc@ni.com>
To: Michal Simek <michal.simek@xilinx.com>
Cc: linux-arm-kernel@lists.infradead.org,
        Thomas Betker <thomas.betker@rohde-schwarz.com>,
        S?ren Brinkmann <soren.brinkmann@xilinx.com>, monstr@monstr.eu,
        Steffen Trumtrar <s.trumtrar@pengutronix.de>,
        linux-kernel@vger.kernel.org,
        Peter Crosthwaite <peter.crosthwaite@xilinx.com>,
        Russell King <linux@arm.linux.org.uk>,
        Rob Herring <robherring2@gmail.com>
Subject: Re: [PATCH] ARM: zynq: Set bit 22 in PL310 AuxCtrl register (6395/1)
Message-ID: <20150512151205.GS669@jcartwri.amer.corp.natinst.com>
References: <812979c5a158a3306d8036e7f9731947c58a3ab7.1431411716.git.michal.simek@xilinx.com>
MIME-Version: 1.0
In-Reply-To: <812979c5a158a3306d8036e7f9731947c58a3ab7.1431411716.git.michal.simek@xilinx.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Content-Type: multipart/signed; micalg=pgp-sha256;
	protocol="application/pgp-signature"; boundary="jcwRHPSxFqmwpRFb"
Content-Disposition: inline
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2455
Lines: 64


--jcwRHPSxFqmwpRFb
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

Something tells me that Russell's patch system won't like to accept a
patch with a duplicate ID (although, I could be wrong).

On Tue, May 12, 2015 at 08:22:01AM +0200, Michal Simek wrote:
> From: Thomas Betker <thomas.betker@rohde-schwarz.com>
>=20
> This patch is based on the
> commit 1a8e41cd672f ("ARM: 6395/1: VExpress: Set bit 22 in the PL310
> (cache controller) AuxCtlr register")
>=20
> Clearing bit 22 in the PL310 Auxiliary Control register (shared
> attribute override enable) has the side effect of transforming Normal
> Shared Non-cacheable reads into Cacheable no-allocate reads.
>=20
> Coherent DMA buffers in Linux always have a cacheable alias via the
> kernel linear mapping and the processor can speculatively load cache
> lines into the PL310 controller. With bit 22 cleared, Non-cacheable
> reads would unexpectedly hit such cache lines leading to buffer
> corruption.
>=20
> For Zynq, this fix avoids memory inconsistencies between Gigabit
> Ethernet controller (GEM) and CPU when DMA_CMA is disabled.

In practice, we've seen corruption not only with the GEM but also the
UDC (and likely other things as well).  So, this patch is welcome!

> Suggested-by: Punnaiah Choudary Kalluri <punnaia@xilinx.com>
> Signed-off-by: Thomas Betker <thomas.betker@rohde-schwarz.com>
> Signed-off-by: Michal Simek <michal.simek@xilinx.com>

This feels like stable material as well, to me.  (Although, I'd expect a
bit of manual work to get it backported, with the fairly recent L2
reworking).

Thanks,
  Josh

--jcwRHPSxFqmwpRFb
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2

iQEcBAABCAAGBQJVUhhCAAoJEKp7ZBKwQFArtX0H/Az2miQKX22Z77T8r75eRRsl
04dD0xP+irNblxxBpp/2XDvV89JcQJ9mp4igAo6XPDSiAcf0REUKqbp3Fm/FOfqI
sNaX+rt7fbSY3xDFcPooq8PRuXRjiReZ8K5hfDLz3Yo8PrIrArAfkDJaQ9QMShqR
oob1H7JNlr+9qdkDICQH5vYy/NXc1COWQf6uEA9l86l5HmAnxIzV1slzlIAPogPD
oa84zBLLPqS7UQ8U4hWERMFQqNx7w2ZDtJKs/OnR73Vr31KT+J5R7n2RWuO+R5Dj
LqXBjjldLcRvTW7d6seJd+wgzI+WVQxDZisU7MVvc8+lJTggDuuQxcF5dZZv5+8=
=fJYm
-----END PGP SIGNATURE-----

--jcwRHPSxFqmwpRFb--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/