Re: [PATCH v3 1/4] media: wave5: handle remaining decoder runtime resume failures

[Brandon Brnich <b-brnich@ti.com>]

Hi Jiale

Thanks for the patch.

On 10/21/26 10:15, Jiale Yao wrote:
> Several decoder callbacks continue into firmware commands after
> pm_runtime_resume_and_get() fails. The runtime resume callback can fail
> while enabling the VPU clocks, so those commands may access registers
> while the device is unavailable. The matching runtime PM puts can also
> be issued without a reference.
> 
> Check the remaining resume results. Propagate errors from callbacks that
> can return them, complete buffers or jobs from void callbacks, and avoid
> firmware access and unmatched puts on failure.
> 
> Fixes: 2092b3833487 ("media: chips-media: wave5: Support runtime suspend/resume")
> Fixes: cbb9c0d50e47 ("media: chips-media: wave5: Fix SError of kernel panic when closed")
> Fixes: a52e6f7923c1 ("media: chips-media: wave5: Resume device before setting EOS flag")
> Signed-off-by: Jiale Yao <yaojiale02@163.com>
> ---
>   .../chips-media/wave5/wave5-vpu-dec.c         | 47 +++++++++++++++++--
>   1 file changed, 42 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
> index 86bc36ee17..320b40581b 100644
> --- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
> +++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
> @@ -829,7 +829,10 @@ static int wave5_vpu_dec_stop(struct vpu_instance *inst)
>   		 * accesses VPU registers via send_firmware_command(), so the
>   		 * device must be resumed first to avoid an asynchronous SError.
>   		 */
> -		pm_runtime_resume_and_get(inst->dev->dev);
> +		ret = pm_runtime_resume_and_get(inst->dev->dev);
> +		if (ret < 0)
> +			return ret;
> +
>   		ret = wave5_vpu_dec_set_eos_on_firmware(inst);
>   		pm_runtime_put_autosuspend(inst->dev->dev);
>   		if (ret)
> @@ -1392,7 +1395,11 @@ static int wave5_vpu_dec_start_streaming(struct vb2_queue *q, unsigned int count
>   	int ret = 0;
>   
>   	dev_dbg(inst->dev->dev, "%s: type: %u\n", __func__, q->type);
> -	pm_runtime_resume_and_get(inst->dev->dev);
> +	ret = pm_runtime_resume_and_get(inst->dev->dev);
> +	if (ret < 0) {
> +		wave5_return_bufs(q, VB2_BUF_STATE_QUEUED);
> +		return ret;
> +	}
>   
>   	v4l2_m2m_update_start_streaming_state(m2m_ctx, q);
>   
> @@ -1556,9 +1563,28 @@ static void wave5_vpu_dec_stop_streaming(struct vb2_queue *q)
>   	struct vpu_instance *inst = vb2_get_drv_priv(q);
>   	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
>   	unsigned long timeout;
> +	int ret;
>   
>   	dev_dbg(inst->dev->dev, "%s: type: %u\n", __func__, q->type);
> -	pm_runtime_resume_and_get(inst->dev->dev);
> +	ret = pm_runtime_resume_and_get(inst->dev->dev);
> +	if (ret < 0) {
> +		if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
> +			struct vpu_src_buffer *vpu_buf;
> +
> +			inst->retry = false;
> +			inst->queuing_num = 0;
> +			while ((vpu_buf = inst_src_buf_remove(inst)) != NULL)
> +				;
> +			inst->eos = false;
> +		}
> +
> +		v4l2_m2m_update_stop_streaming_state(m2m_ctx, q);
> +		wave5_return_bufs(q, VB2_BUF_STATE_ERROR);
> +		inst->empty_queue = false;
> +		inst->sent_eos = false;
> +		return;
> +	}
> +
>   	inst->empty_queue = true;
>   
>   	timeout = jiffies + msecs_to_jiffies(VPU_DEC_STOP_TIMEOUT);
> @@ -1675,7 +1701,13 @@ static void wave5_vpu_dec_device_run(void *priv)
>   	bool cmd_issued = false;
>   
>   	dev_dbg(inst->dev->dev, "%s: Fill the ring buffer with new bitstream data", __func__);
> -	pm_runtime_resume_and_get(inst->dev->dev);
> +	ret = pm_runtime_resume_and_get(inst->dev->dev);
> +	if (ret < 0) {
> +		dev_err(inst->dev->dev, "Failed to resume VPU: %d\n", ret);
> +		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
> +		return;
> +	}
> +

Wouldn't this lead to an infinite loop in the m2m scheduler? looking 
around other drivers (rockchip and hantro) they handle this case with 
failing the buffers and then marking the job as finished. Similar to 
what you did in the encoder path. Maybe you can make a helper so both 
device runs can use?

Best,
Brandon

>   	if (!inst->retry) {
>   		ret = fill_ringbuffer(inst);
>   		if (ret < 0) {
> @@ -1818,7 +1850,11 @@ static void wave5_vpu_dec_job_abort(void *priv)
>   	 * device must be resumed first; otherwise the register access faults
>   	 * with an asynchronous SError.
>   	 */
> -	pm_runtime_resume_and_get(inst->dev->dev);
> +	ret = pm_runtime_resume_and_get(inst->dev->dev);
> +	if (ret < 0) {
> +		dev_warn(inst->dev->dev, "Failed to resume VPU: %d\n", ret);
> +		goto finish_job;
> +	}
>   
>   	ret = wave5_vpu_dec_set_eos_on_firmware(inst);
>   	if (ret)
> @@ -1827,6 +1863,7 @@ static void wave5_vpu_dec_job_abort(void *priv)
>   
>   	pm_runtime_put_autosuspend(inst->dev->dev);
>   
> +finish_job:
>   	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
>   }
>