Re: [PATCH v4 2/3] drm/panthor: Revisit reqs_lock handling in flush/reset paths

[Steven Price <steven.price@arm.com>]

On 12/08/2026 15:07, Nicolas Frattaroli wrote:
> panthor_gpu_flush_caches() and panthor_gpu_soft_reset() acquire their
> reqs_lock spinlock with the IRQ-disabling variants of the spinlocking
> functions. This isn't necessary, as the lock is never taken from an
> atomic context, as Panthor uses threaded interrupt handlers. The result
> of this overly strict locking is that IRQs may be disabled more
> frequently and for longer than they should be, resulting in increased
> system latency.
> 
> Switch the locking to use non-IRQ-disabling scoped_guard statements for
> locking. The wait_event_timeout read of pending_reqs outside of the
> spinlock is fine as wait_event_timeout is a memory barrier according to
> the Linux Memory Model.
> 
> Fixes: 5cd894e258c4 ("drm/panthor: Add the GPU logical block")
> Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
> Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>

Reviewed-by: Steven Price <steven.price@arm.com>

Although one minor formatting nit below.

> ---
>  drivers/gpu/drm/panthor/panthor_gpu.c | 72 ++++++++++++++++-------------------
>  1 file changed, 33 insertions(+), 39 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
> index 7088371c6d64..55e33f145b40 100644
> --- a/drivers/gpu/drm/panthor/panthor_gpu.c
> +++ b/drivers/gpu/drm/panthor/panthor_gpu.c
> @@ -345,41 +345,36 @@ int panthor_gpu_flush_caches(struct panthor_device *ptdev,
>  			     u32 l2, u32 lsc, u32 other)
>  {
>  	struct panthor_gpu *gpu = ptdev->gpu;
> -	unsigned long flags;
>  	u64 start = 0;
>  	int ret = 0;
>  
>  	/* Serialize cache flush operations. */
>  	guard(mutex)(&ptdev->gpu->cache_flush_lock);
>  
> -	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
> -
> -	if (tracepoint_enabled(gpu_cache_flush))
> -		start = ktime_get_ns();
> -
> -	if (!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) {
> -		ptdev->gpu->pending_reqs |= GPU_IRQ_CLEAN_CACHES_COMPLETED;
> -		gpu_write(gpu->iomem, GPU_CMD, GPU_FLUSH_CACHES(l2, lsc, other));
> -	} else {
> -		ret = -EIO;
> -	}
> -	spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
> -
> -	if (ret) {
> -		panthor_gpu_emit_flush_caches_tp(ptdev, start, l2, lsc, other, ret);
> -		return ret;
> +	scoped_guard(spinlock, &ptdev->gpu->reqs_lock) {
> +		if (tracepoint_enabled(gpu_cache_flush))
> +			start = ktime_get_ns();
> +
> +		if (!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED)) {
> +			ptdev->gpu->pending_reqs |= GPU_IRQ_CLEAN_CACHES_COMPLETED;
> +			gpu_write(gpu->iomem, GPU_CMD, GPU_FLUSH_CACHES(l2, lsc, other));
> +		} else {
> +			panthor_gpu_emit_flush_caches_tp(ptdev, start, l2, lsc,
> +							 other, -EIO);
> +			return -EIO;
> +		}
>  	}
>  
>  	if (!wait_event_timeout(ptdev->gpu->reqs_acked,
>  				!(ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED),
>  				msecs_to_jiffies(100))) {
> -		spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
> -		if ((ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED) != 0 &&
> -		    !(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_CLEAN_CACHES_COMPLETED))
> -			ret = -ETIMEDOUT;
> -		else
> -			ptdev->gpu->pending_reqs &= ~GPU_IRQ_CLEAN_CACHES_COMPLETED;
> -		spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
> +		scoped_guard(spinlock, &ptdev->gpu->reqs_lock) {
> +			if ((ptdev->gpu->pending_reqs & GPU_IRQ_CLEAN_CACHES_COMPLETED) != 0 &&
> +			!(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_CLEAN_CACHES_COMPLETED))

NIT: This isn't aligned correctly with the if() above any more.

To be honest what we really need here is a helper for this sequence as
there's basically the same code again in panthor_gpu_soft_reset() below.

> +				ret = -ETIMEDOUT;
> +			else
> +				ptdev->gpu->pending_reqs &= ~GPU_IRQ_CLEAN_CACHES_COMPLETED;
> +		}
>  	}
>  
>  	panthor_gpu_emit_flush_caches_tp(ptdev, start, l2, lsc, other, ret);
> @@ -402,27 +397,26 @@ int panthor_gpu_soft_reset(struct panthor_device *ptdev)
>  {
>  	struct panthor_gpu *gpu = ptdev->gpu;
>  	bool timedout = false;
> -	unsigned long flags;
>  
> -	spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
> -	if (!drm_WARN_ON(&ptdev->base,
> -			 ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED)) {
> -		ptdev->gpu->pending_reqs |= GPU_IRQ_RESET_COMPLETED;
> -		gpu_write(gpu->irq.iomem, INT_CLEAR, GPU_IRQ_RESET_COMPLETED);
> -		gpu_write(gpu->iomem, GPU_CMD, GPU_SOFT_RESET);
> +	scoped_guard(spinlock, &ptdev->gpu->reqs_lock) {
> +		if (!drm_WARN_ON(&ptdev->base,
> +				ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED)) {
> +			ptdev->gpu->pending_reqs |= GPU_IRQ_RESET_COMPLETED;
> +			gpu_write(gpu->irq.iomem, INT_CLEAR, GPU_IRQ_RESET_COMPLETED);
> +			gpu_write(gpu->iomem, GPU_CMD, GPU_SOFT_RESET);
> +		}
>  	}
> -	spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
>  
>  	if (!wait_event_timeout(ptdev->gpu->reqs_acked,
>  				!(ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED),
>  				msecs_to_jiffies(100))) {
> -		spin_lock_irqsave(&ptdev->gpu->reqs_lock, flags);
> -		if ((ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED) != 0 &&
> -		    !(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_RESET_COMPLETED))
> -			timedout = true;
> -		else
> -			ptdev->gpu->pending_reqs &= ~GPU_IRQ_RESET_COMPLETED;
> -		spin_unlock_irqrestore(&ptdev->gpu->reqs_lock, flags);
> +		scoped_guard(spinlock, &ptdev->gpu->reqs_lock) {
> +			if ((ptdev->gpu->pending_reqs & GPU_IRQ_RESET_COMPLETED) != 0 &&
> +			!(gpu_read(gpu->irq.iomem, INT_RAWSTAT) & GPU_IRQ_RESET_COMPLETED))

NIT: Same issue here.

Thanks,
Steve

> +				timedout = true;
> +			else
> +				ptdev->gpu->pending_reqs &= ~GPU_IRQ_RESET_COMPLETED;
> +		}
>  	}
>  
>  	if (timedout) {
>