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."
[backport of commit d5d27fd9826b ("mtd: rawnand: gpmi: fix MX28 bus master lockup problem")]
Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid NAND startup problems") Signed-off-by: Martin Kepplinger martin.kepplinger@ginzinger.com ---
I'm actually not sure about the correct form. This is in reply to Sasha's autmated email with failed builds for old kernels. This should apply to 4.14 and older stable trees.
I'll point to this over there and please say so in case you need Tags or something else.
thanks
martin
drivers/mtd/nand/gpmi-nand/gpmi-lib.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c index 97787246af41..55e369b6b862 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c @@ -168,9 +168,10 @@ int gpmi_init(struct gpmi_nand_data *this)
/* * Reset BCH here, too. We got failures otherwise :( - * See later BCH reset for explanation of MX23 handling + * See later BCH reset for explanation of MX23 and MX28 handling */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out;
@@ -275,13 +276,11 @@ int bch_set_geometry(struct gpmi_nand_data *this)
/* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this - * chip, otherwise it will lock up. So we skip resetting BCH on the MX23. - * On the other hand, the MX28 needs the reset, because one case has been - * seen where the BCH produced ECC errors constantly after 10000 - * consecutive reboots. The latter case has not been seen on the MX23 - * yet, still we don't know if it could happen there as well. + * chip, otherwise it will lock up. So we skip resetting BCH on the MX23 + * and MX28. */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out;