Re: [PATCH] ASoC: sun4i-spdif: Use guard() for spin locks

[sashiko-bot@kernel.org]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Hardware State / PM Violation leading to bus hang
--

commit 0686001584788d984a0f16403183bcad78fe4176
Author: bui duc phuc <phucduc.bui@gmail.com>

ASoC: sun4i-spdif: Use guard() for spin locks

This commit refactors the locking in the sun4i-spdif driver to use the
guard() macro for spinlocks. It replaces manual spin_lock_irqsave() and
spin_unlock_irqrestore() calls with scope-based cleanup.

> diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c
> --- a/sound/soc/sunxi/sun4i-spdif.c
> +++ b/sound/soc/sunxi/sun4i-spdif.c
> @@ -427,10 +427,9 @@ static int sun4i_spdif_get_status(struct snd_kcontrol *kcontrol,
>  	struct snd_soc_dai *cpu_dai = snd_kcontrol_chip(kcontrol);
>  	struct sun4i_spdif_dev *host = snd_soc_dai_get_drvdata(cpu_dai);
>  	u8 *status = ucontrol->value.iec958.status;
> -	unsigned long flags;
>  	unsigned int reg;
>  
> -	spin_lock_irqsave(&host->lock, flags);
> +	guard(spinlock_irqsave)(&host->lock);
>  
>  	regmap_read(host->regmap, SUN4I_SPDIF_TXCHSTA0, &reg);

While this issue isn't new to this patch, does this code risk a bus hang if
the device is runtime-suspended?

The regmap configuration lacks a cache, and these ALSA kcontrols can be
accessed by userspace at any time. If the audio stream is idle, the device
will be runtime-suspended and its APB bus clock (apb_clk) will be disabled.

Accessing the physical registers with the clock disabled will trigger an
asynchronous external abort.

Would it make sense to ensure the device is runtime-resumed (perhaps via
pm_runtime_get_sync() outside the spinlock guard) before touching the
hardware?

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260513105003.81880-1-phucduc.bui@gmail.com?part=1