Hi Martin,
On Tue, 5 Feb 2019 16:52:51 +0100 Martin Kepplinger martin.kepplinger@ginzinger.com 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")
Please make sure this Fixes line is not wrapped next time.
Thanks,
Boris