Re: [PATCH] mtd: rawnand: gpmi: fix MX28 bus master lockup problem

From: Boris Brezillon <boris.brezillon@collabora.com>
To: Miquel Raynal <miquel.raynal@bootlin.com>
Cc: Manfred Schlaegl <manfred.schlaegl@ginzinger.com>,
	richard@nod.at,
	Martin Kepplinger <martin.kepplinger@ginzinger.com>,
	linux-kernel@vger.kernel.org, marek.vasut@gmail.com,
	linux-mtd@lists.infradead.org,
	Martin Kepplinger <martink@posteo.de>,
	han.xu@nxp.com, computersforpeace@gmail.com, dwmw2@infradead.org
Subject: Re: [PATCH] mtd: rawnand: gpmi: fix MX28 bus master lockup problem
Date: Tue, 5 Feb 2019 15:14:37 +0100	[thread overview]
Message-ID: <20190205151437.33f4d990@collabora.com> (raw)
In-Reply-To: <20190205135946.64eda55c@xps13>

On Tue, 5 Feb 2019 13:59:46 +0100
Miquel Raynal <miquel.raynal@bootlin.com> wrote:

> Hi Martin,
> 
> Martin Kepplinger <martink@posteo.de> wrote on Tue, 29 Jan 2019
> 16:37:00 +0100:
> 
> > From: Martin Kepplinger <martin.kepplinger@ginzinger.com>
> > 
> > Disable BCH soft reset according to MX23 erratum #2847 ("BCH soft
> > reset may cause bus master lock up") for MX28 too. It has the same
> > problem.
> > 
> > Observed problem: once per 100,000+ MX28 reboots NAND read failed on
> > DMA timeout errors:
> > [    1.770823] UBI: attaching mtd3 to ubi0
> > [    2.768088] gpmi_nand: DMA timeout, last DMA :1
> > [    3.958087] gpmi_nand: BCH timeout, last DMA :1
> > [    4.156033] gpmi_nand: Error in ECC-based read: -110
> > [    4.161136] UBI warning: ubi_io_read: error -110 while reading 64
> > bytes from PEB 0:0, read only 0 bytes, retry
> > [    4.171283] step 1 error
> > [    4.173846] gpmi_nand: Chip: 0, Error -1
> > 
> > Without BCH soft reset we successfully executed 1,000,000 MX28
> > reboots.
> > 
> > I have a quote from NXP regarding this problem, from July 18th 2016:
> > 
> > "As the i.MX23 and i.MX28 are of the same generation, they share
> > many characteristics. Unfortunately, also the erratas may be shared.
> > In case of the documented erratas and the workarounds, you can also
> > apply the workaround solution of one device on the other one. This
> > have been reported, but I’m afraid that there are not an estimated
> > date for updating the Errata documents.
> > Please accept our apologies for any inconveniences this may cause."
> > 
> > Signed-off-by: Manfred Schlaegl <manfred.schlaegl@ginzinger.com>
> > Signed-off-by: Martin Kepplinger <martin.kepplinger@ginzinger.com>
> > ---
> > 
> > This is something we have in our tree for years and is running on
> > production systems and I hope that this helps others too.
> > 
> > thanks
> >                               martin  
> 
> Thanks for sharing this.
> 
> On my side the patch looks ok, maybe an Acked-by from Han would be
> great?
> 
> Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
> 
> Boris, do you want to take this? If you don't have more fixes to send
> I can queue it to nand/next.

I'll take it.

______________________________________________________
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/