Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Daniel Palmer <daniel@0x0f.com>
To:     miquel.raynal@bootlin.com, richard@nod.at
Cc:     linux-mtd@lists.infradead.org, linux-kernel@vger.kernel.org,
        Daniel Palmer <daniel@0x0f.com>
Subject: [RFC PATCH] mtd: spinand: core: Properly fill the OOB area.
Date:   Thu, 17 Jun 2021 20:08:42 +0900
Message-Id: <20210617110842.2358461-1-daniel@0x0f.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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@0x0f.com>
---
 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);
 }
-- 
2.32.0.rc0