From: Your Name <patch-notifications@xxxxxxxxxxxxxxx>
On Tue, 2019-02-05 at 15:52:51 UTC, Martin Kepplinger wrote:
> 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."
>
> Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid
> NAND startup problems")
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Manfred Schlaegl <manfred.schlaegl@xxxxxxxxxxxxx>
> Signed-off-by: Martin Kepplinger <martin.kepplinger@xxxxxxxxxxxxx>
> Reviewed-by: Miquel Raynal <miquel.raynal@xxxxxxxxxxx>
> Reviewed-by: Fabio Estevam <festevam@xxxxxxxxx>
> Acked-by: Han Xu <han.xu@xxxxxxx>
Applied to http://git.infradead.org/linux-mtd.git mtd/fixes, thanks.
y'all come back now!
