linux-kernel - Re: [PATCH 1/4] ASoC: rockchip: i2s-tdm: Strip out direct CRU use

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1782571.1Dz21PRzoM@phil>
Date:   Sat, 16 Oct 2021 17:50:22 +0200
From:   Heiko Stuebner <heiko@...ech.de>
To:     Nicolas Frattaroli <frattaroli.nicolas@...il.com>,
        Liam Girdwood <lgirdwood@...il.com>,
        Mark Brown <broonie@...nel.org>,
        Jaroslav Kysela <perex@...ex.cz>,
        Takashi Iwai <tiwai@...e.com>,
        Philipp Zabel <p.zabel@...gutronix.de>,
        Nicolas Frattaroli <frattaroli.nicolas@...il.com>
Cc:     linux-rockchip@...ts.infradead.org, alsa-devel@...a-project.org,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 1/4] ASoC: rockchip: i2s-tdm: Strip out direct CRU use

Am Samstag, 16. Oktober 2021, 12:53:50 CEST schrieb Nicolas Frattaroli:
> In cases where both rx and tx lrck are synced to the same source,
> the resets for rx and tx need to be triggered simultaneously,
> according to the downstream driver.
> 
> As there is no reset API to atomically bulk (de)assert two resets
> at once, what the driver did was implement half a reset controller
> specific to Rockchip, which tried to write the registers for the
> resets within one write ideally or several writes within an irqsave
> section.
> 
> This of course violates abstractions quite badly. The driver should
> not write to the CRU's registers directly.
> 
> In practice, for the cases I tested the driver with, which is audio
> playback, replacing the synchronised asserts with just individual
> ones does not seem to make any difference.
> 
> If it turns out that this breaks something in the future, it should
> be fixed through the specification and implementation of an atomic
> bulk reset API, not with a CRU hack.
> 
> Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@...il.com>

Reviewed-by: Heiko Stuebner <heiko@...ech.de>