diff mbox series

[v3,1/6] drm/panfrost: Perform hard reset to recover GPU if soft reset fails

Message ID 20231109102543.42971-2-angelogioacchino.delregno@collabora.com (mailing list archive)
State New, archived
Headers show
Series drm/panfrost: Turn off clocks and regulators in PM | expand

Commit Message

AngeloGioacchino Del Regno Nov. 9, 2023, 10:25 a.m. UTC
Even though soft reset should ideally never fail, during development of
some power management features I managed to get some bits wrong: this
resulted in GPU soft reset failures, where the GPU was never able to
recover, not even after suspend/resume cycles, meaning that the only
way to get functionality back was to reboot the machine.

Perform a hard reset after a soft reset failure to be able to recover
the GPU during runtime (so, without any machine reboot).

Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/gpu/drm/panfrost/panfrost_gpu.c  | 13 ++++++++++---
 drivers/gpu/drm/panfrost/panfrost_regs.h |  1 +
 2 files changed, 11 insertions(+), 3 deletions(-)

Comments

Steven Price Nov. 10, 2023, 2:03 p.m. UTC | #1
On 09/11/2023 10:25, AngeloGioacchino Del Regno wrote:
> Even though soft reset should ideally never fail, during development of
> some power management features I managed to get some bits wrong: this
> resulted in GPU soft reset failures, where the GPU was never able to
> recover, not even after suspend/resume cycles, meaning that the only
> way to get functionality back was to reboot the machine.
> 
> Perform a hard reset after a soft reset failure to be able to recover
> the GPU during runtime (so, without any machine reboot).
> 
> Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>

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

> ---
>  drivers/gpu/drm/panfrost/panfrost_gpu.c  | 13 ++++++++++---
>  drivers/gpu/drm/panfrost/panfrost_regs.h |  1 +
>  2 files changed, 11 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
> index f0be7e19b13e..ae3f7d97bb47 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
> @@ -60,14 +60,21 @@ int panfrost_gpu_soft_reset(struct panfrost_device *pfdev)
>  
>  	gpu_write(pfdev, GPU_INT_MASK, 0);
>  	gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_RESET_COMPLETED);
> -	gpu_write(pfdev, GPU_CMD, GPU_CMD_SOFT_RESET);
>  
> +	gpu_write(pfdev, GPU_CMD, GPU_CMD_SOFT_RESET);
>  	ret = readl_relaxed_poll_timeout(pfdev->iomem + GPU_INT_RAWSTAT,
>  		val, val & GPU_IRQ_RESET_COMPLETED, 100, 10000);
>  
>  	if (ret) {
> -		dev_err(pfdev->dev, "gpu soft reset timed out\n");
> -		return ret;
> +		dev_err(pfdev->dev, "gpu soft reset timed out, attempting hard reset\n");
> +
> +		gpu_write(pfdev, GPU_CMD, GPU_CMD_HARD_RESET);
> +		ret = readl_relaxed_poll_timeout(pfdev->iomem + GPU_INT_RAWSTAT, val,
> +						 val & GPU_IRQ_RESET_COMPLETED, 100, 10000);
> +		if (ret) {
> +			dev_err(pfdev->dev, "gpu hard reset timed out\n");
> +			return ret;
> +		}
>  	}
>  
>  	gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_MASK_ALL);
> diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
> index 55ec807550b3..c25743b05c55 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_regs.h
> +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
> @@ -44,6 +44,7 @@
>  	 GPU_IRQ_MULTIPLE_FAULT)
>  #define GPU_CMD				0x30
>  #define   GPU_CMD_SOFT_RESET		0x01
> +#define   GPU_CMD_HARD_RESET		0x02
>  #define   GPU_CMD_PERFCNT_CLEAR		0x03
>  #define   GPU_CMD_PERFCNT_SAMPLE	0x04
>  #define   GPU_CMD_CYCLE_COUNT_START	0x05
diff mbox series

Patch

diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f0be7e19b13e..ae3f7d97bb47 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -60,14 +60,21 @@  int panfrost_gpu_soft_reset(struct panfrost_device *pfdev)
 
 	gpu_write(pfdev, GPU_INT_MASK, 0);
 	gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_RESET_COMPLETED);
-	gpu_write(pfdev, GPU_CMD, GPU_CMD_SOFT_RESET);
 
+	gpu_write(pfdev, GPU_CMD, GPU_CMD_SOFT_RESET);
 	ret = readl_relaxed_poll_timeout(pfdev->iomem + GPU_INT_RAWSTAT,
 		val, val & GPU_IRQ_RESET_COMPLETED, 100, 10000);
 
 	if (ret) {
-		dev_err(pfdev->dev, "gpu soft reset timed out\n");
-		return ret;
+		dev_err(pfdev->dev, "gpu soft reset timed out, attempting hard reset\n");
+
+		gpu_write(pfdev, GPU_CMD, GPU_CMD_HARD_RESET);
+		ret = readl_relaxed_poll_timeout(pfdev->iomem + GPU_INT_RAWSTAT, val,
+						 val & GPU_IRQ_RESET_COMPLETED, 100, 10000);
+		if (ret) {
+			dev_err(pfdev->dev, "gpu hard reset timed out\n");
+			return ret;
+		}
 	}
 
 	gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_MASK_ALL);
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index 55ec807550b3..c25743b05c55 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -44,6 +44,7 @@ 
 	 GPU_IRQ_MULTIPLE_FAULT)
 #define GPU_CMD				0x30
 #define   GPU_CMD_SOFT_RESET		0x01
+#define   GPU_CMD_HARD_RESET		0x02
 #define   GPU_CMD_PERFCNT_CLEAR		0x03
 #define   GPU_CMD_PERFCNT_SAMPLE	0x04
 #define   GPU_CMD_CYCLE_COUNT_START	0x05