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

[Fabio Estevam]

On Tue, Feb 5, 2019 at 11:00 AM Miquel Raynal <miquel.raynal@xxxxxxxxxxx> wrote:
>
> Hi Martin,
>
> Martin Kepplinger <martink@xxxxxxxxx> wrote on Tue, 29 Jan 2019
> 16:37:00 +0100:
>
> > From: Martin Kepplinger <martin.kepplinger@xxxxxxxxxxxxx>
> >
> > 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 Iâm 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@xxxxxxxxxxxxx>
> > Signed-off-by: Martin Kepplinger <martin.kepplinger@xxxxxxxxxxxxx>

Does this also need a Fixes tag so that it can be backported to stable?

Thanks