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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 5 Feb 2019 13:59:46 +0100
From:   Miquel Raynal <miquel.raynal@...tlin.com>
To:     Martin Kepplinger <martink@...teo.de>
Cc:     han.xu@....com, bbrezillon@...nel.org, richard@....at,
        dwmw2@...radead.org, computersforpeace@...il.com,
        marek.vasut@...il.com, linux-mtd@...ts.infradead.org,
        linux-kernel@...r.kernel.org,
        Martin Kepplinger <martin.kepplinger@...zinger.com>,
        Manfred Schlaegl <manfred.schlaegl@...zinger.com>
Subject: Re: [PATCH] mtd: rawnand: gpmi: fix MX28 bus master lockup problem

Hi Martin,

Martin Kepplinger <martink@...teo.de> wrote on Tue, 29 Jan 2019
16:37:00 +0100:

> From: Martin Kepplinger <martin.kepplinger@...zinger.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@...zinger.com>
> Signed-off-by: Martin Kepplinger <martin.kepplinger@...zinger.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@...tlin.com>

Boris, do you want to take this? If you don't have more fixes to send I
can queue it to nand/next.

Thanks,
Miquèl