[RFC PATCH] mtd: spinand: core: Properly fill the OOB area.

[Miquel Raynal]

Hi Daniel,

Daniel Palmer <daniel at 0x0f.com> wrote on Thu, 17 Jun 2021 20:08:42
+0900:

> The comment in spinand_write_to_cache_op() says that
> spinand_ondie_ecc_prepare_io_req() should 0xff fill the OOB
> area but it doesn't.
> 
> This causes the OOB area to get filled with zeros
> and anytime the first page in a block the bad block marker
> is cleared and it becomes a bad block on the next boot.
> 
> This was observed on Longsys FORSEE branded parts and
> might be specific to these parts.
> 
> Signed-off-by: Daniel Palmer <daniel at 0x0f.com>

This change looks fine, I'll use spinand->oobbuf instead of databuf +
offset (will update when applying).

> ---
>  drivers/mtd/nand/spi/core.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
> index 6f2d39f9bb06..f1c76fa0e220 100644
> --- a/drivers/mtd/nand/spi/core.c
> +++ b/drivers/mtd/nand/spi/core.c
> @@ -281,6 +281,9 @@ static int spinand_ondie_ecc_prepare_io_req(struct nand_device *nand,
>  	struct spinand_device *spinand = nand_to_spinand(nand);
>  	bool enable = (req->mode != MTD_OPS_RAW);
>  
> +	memset(spinand->databuf + nanddev_page_size(nand),
> +			0xff, nanddev_per_page_oobsize(nand));
> +
>  	/* Only enable or disable the engine */
>  	return spinand_ecc_enable(spinand, enable);
>  }

Thanks,
Miquèl