mtd: rawnand: gpmi: fix MX28 bus master lockup problem

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@vger.kernel.org
Signed-off-by: Manfred Schlaegl <manfred.schlaegl@ginzinger.com>
Signed-off-by: Martin Kepplinger <martin.kepplinger@ginzinger.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Acked-by: Han Xu <han.xu@nxp.com>
Signed-off-by: Boris Brezillon <bbrezillon@kernel.org>

diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
index bd4cfac6b5aa69e8dbc6cec34c02ca59a8399912..a4768df5083f9633a965bf85f12dce4b1d6ad35c 100644 (file)
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
@@ -155,9 +155,10 @@ 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;
 
@@ -263,12 +264,10 @@ 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.
+       * 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;