Re: [PATCH] mtd: rawnand: arasan: Fix double assertion of chip-select

From: Miquel Raynal <miquel.raynal@bootlin.com>
To: Maciej Andrzejewski <maciej.andrzejewski@m-works.net>
Cc: Michal Simek <michal.simek@amd.com>,
	 Jinjie Ruan <ruanjinjie@huawei.com>,
	 Punnaiah Choudary Kalluri <punnaia@xilinx.com>,
	Naga Sureshkumar Relli <nagasure@xilinx.com>,
	linux-mtd@lists.infradead.org
Subject: Re: [PATCH] mtd: rawnand: arasan: Fix double assertion of chip-select
Date: Sun, 24 Nov 2024 12:54:36 +0100	[thread overview]
Message-ID: <87wmgsdeyr.fsf@bootlin.com> (raw)
In-Reply-To: <Z0Iq9ex25MkwC_Cm@UBUNTU-PF54DSY0> (Maciej Andrzejewski's message of "Sat, 23 Nov 2024 20:20:21 +0100")

Hi Maciej,

On 23/11/2024 at 20:20:21 +01, Maciej Andrzejewski <maciej.andrzejewski@m-works.net> wrote:

> When two chip-selects are configured in the device tree, and the second is
> a non-native GPIO, both the GPIO-based chip-select and the first native
> chip-select may be asserted simultaneously. This double assertion causes
> incorrect read and write operations.
>
> The issue occurs because when nfc->ncs <= 2, nfc->spare_cs is always
> initialized to 0 due to static initialization. Consequently, when the
> second chip-select (GPIO-based) is selected in anfc_assert_cs(), it is
> detected by anfc_is_gpio_cs(), and nfc->native_cs is assigned the value 0.
> This results in both the GPIO-based chip-select being asserted and the
> NAND controller register receiving 0, erroneously selecting the native
> chip-select.
>
> This patch resolves the issue, as confirmed by oscilloscope testing with
> configurations involving two or more chip-selects in the device tree.
>

Ok to me, can you please send a v2 with correct Fixes and Cc: stable
tags, please?

Thanks,
Miquèl

______________________________________________________
Linux MTD discussion mailing list
http://lists.infradead.org/mailman/listinfo/linux-mtd/