[PATCH 4.4 098/143] mtd: rawnand: gpmi: fix MX28 bus master lockup problem

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Martin Kepplinger <martin.kepplinger@xxxxxxxxxxxxx>

commit d5d27fd9826b59979b184ec288e4812abac0e988 upstream.

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 Iâm 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>
Signed-off-by: Boris Brezillon <bbrezillon@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/mtd/nand/gpmi-nand/gpmi-lib.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

--- 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 *thi
 
 	/*
 	 * 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;
 
@@ -274,13 +275,11 @@ int bch_set_geometry(struct gpmi_nand_da
 
 	/*
 	* 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;