Re: [PATCH v3 3/3] media: verisilicon: Avoid G2 bus error while decoding H.264 and HEVC

[Frank Li <Frank.li@nxp.com>]

On Thu, Dec 04, 2025 at 05:08:11PM +0800, ming.qian@oss.nxp.com wrote:
> From: Ming Qian <ming.qian@oss.nxp.com>
>
> For the i.MX8MQ platform, there is a hardware limitation: the g1 VPU and
> g2 VPU cannot decode simultaneously; otherwise, it will cause below bus
> error and produce corrupted pictures, even potentially lead to system hang.
>
> [  110.527986] hantro-vpu 38310000.video-codec: frame decode timed out.
> [  110.583517] hantro-vpu 38310000.video-codec: bus error detected.
>
> Therefore, it is necessary to ensure that g1 and g2 operate alternately.
> This allows for successful multi-instance decoding of H.264 and HEVC.
>
> To achieve this, we can have g1 and g2 share the same v4l2_m2m_dev, and
> then the v4l2_m2m_dev can handle the scheduling.

To achieve this, g1 and g2 share the same v4l2_m2m_dev, ...

>
> Fixes: cb5dd5a0fa518 ("media: hantro: Introduce G2/HEVC decoder")
> Co-developed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
> Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
> Signed-off-by: Ming Qian <ming.qian@oss.nxp.com>
> ---
> v3
> - Apply Nicolas's approach that use an array list to define the shared
>   devices
>
> v2
> - Abandon the waiting approach.
> - Switch to a shared v4l2_m2m_dev solution.
>
>  drivers/media/platform/verisilicon/hantro.h   |  2 +
>  .../media/platform/verisilicon/hantro_drv.c   | 42 +++++++++++++++++--
>  .../media/platform/verisilicon/imx8m_vpu_hw.c |  8 ++++
>  3 files changed, 49 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/media/platform/verisilicon/hantro.h b/drivers/media/platform/verisilicon/hantro.h
> index e0fdc4535b2d..0353de154a1e 100644
> --- a/drivers/media/platform/verisilicon/hantro.h
> +++ b/drivers/media/platform/verisilicon/hantro.h
> @@ -77,6 +77,7 @@ struct hantro_irq {
>   * @double_buffer:		core needs double buffering
>   * @legacy_regs:		core uses legacy register set
>   * @late_postproc:		postproc must be set up at the end of the job
> + * @shared_devices:		an array of device ids that cannot run concurrently
>   */
>  struct hantro_variant {
>  	unsigned int enc_offset;
> @@ -101,6 +102,7 @@ struct hantro_variant {
>  	unsigned int double_buffer : 1;
>  	unsigned int legacy_regs : 1;
>  	unsigned int late_postproc : 1;
> +	const struct of_device_id *shared_devices;
>  };
>
>  /**
> diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
> index 60b95b5d8565..70160eaf3d15 100644
> --- a/drivers/media/platform/verisilicon/hantro_drv.c
> +++ b/drivers/media/platform/verisilicon/hantro_drv.c
> @@ -13,6 +13,7 @@
>  #include <linux/clk.h>
>  #include <linux/module.h>
>  #include <linux/of.h>
> +#include <linux/of_platform.h>
>  #include <linux/platform_device.h>
>  #include <linux/pm.h>
>  #include <linux/pm_runtime.h>
> @@ -1035,6 +1036,41 @@ static int hantro_disable_multicore(struct hantro_dev *vpu)
>  	return 0;
>  }
>
> +static struct v4l2_m2m_dev *hantro_get_v4l2_m2m_dev(struct hantro_dev *vpu)
> +{
> +	struct device_node *node;
> +	struct hantro_dev *shared_vpu;
> +
> +	if (!vpu->variant || !vpu->variant->shared_devices)
> +		goto init_new_m2m_dev;

I found only use shared_devices here, how to  ensure that g1 and g2 operate
alternately by using shared_devices?

Frank

> +
> +	for_each_matching_node(node, vpu->variant->shared_devices) {
> +		struct platform_device *pdev;
> +		struct v4l2_m2m_dev *m2m_dev;
> +
> +		pdev = of_find_device_by_node(node);
> +		of_node_put(node);
> +
> +		if (!pdev)
> +			continue;
> +
> +		shared_vpu = platform_get_drvdata(pdev);
> +		if (IS_ERR_OR_NULL(shared_vpu) || shared_vpu == vpu) {
> +			platform_device_put(pdev);
> +			continue;
> +		}
> +
> +		v4l2_m2m_get(shared_vpu->m2m_dev);
> +		m2m_dev = shared_vpu->m2m_dev;
> +		platform_device_put(pdev);
> +
> +		return m2m_dev;
> +	}
> +
> +init_new_m2m_dev:
> +	return v4l2_m2m_init(&vpu_m2m_ops);
> +}
> +
>  static int hantro_probe(struct platform_device *pdev)
>  {
>  	const struct of_device_id *match;
> @@ -1186,7 +1222,7 @@ static int hantro_probe(struct platform_device *pdev)
>  	}
>  	platform_set_drvdata(pdev, vpu);
>
> -	vpu->m2m_dev = v4l2_m2m_init(&vpu_m2m_ops);
> +	vpu->m2m_dev = hantro_get_v4l2_m2m_dev(vpu);
>  	if (IS_ERR(vpu->m2m_dev)) {
>  		v4l2_err(&vpu->v4l2_dev, "Failed to init mem2mem device\n");
>  		ret = PTR_ERR(vpu->m2m_dev);
> @@ -1225,7 +1261,7 @@ static int hantro_probe(struct platform_device *pdev)
>  	hantro_remove_enc_func(vpu);
>  err_m2m_rel:
>  	media_device_cleanup(&vpu->mdev);
> -	v4l2_m2m_release(vpu->m2m_dev);
> +	v4l2_m2m_put(vpu->m2m_dev);
>  err_v4l2_unreg:
>  	v4l2_device_unregister(&vpu->v4l2_dev);
>  err_clk_unprepare:
> @@ -1248,7 +1284,7 @@ static void hantro_remove(struct platform_device *pdev)
>  	hantro_remove_dec_func(vpu);
>  	hantro_remove_enc_func(vpu);
>  	media_device_cleanup(&vpu->mdev);
> -	v4l2_m2m_release(vpu->m2m_dev);
> +	v4l2_m2m_put(vpu->m2m_dev);
>  	v4l2_device_unregister(&vpu->v4l2_dev);
>  	clk_bulk_unprepare(vpu->variant->num_clocks, vpu->clocks);
>  	reset_control_assert(vpu->resets);
> diff --git a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
> index 5be0e2e76882..6f8e43b7f157 100644
> --- a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
> +++ b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
> @@ -343,6 +343,12 @@ const struct hantro_variant imx8mq_vpu_variant = {
>  	.num_regs = ARRAY_SIZE(imx8mq_reg_names)
>  };
>
> +static const struct of_device_id imx8mq_vpu_shared_resources[] __initconst = {
> +	{ .compatible = "nxp,imx8mq-vpu-g1", },
> +	{ .compatible = "nxp,imx8mq-vpu-g2", },
> +	{ /* sentinel */ }
> +};
> +
>  const struct hantro_variant imx8mq_vpu_g1_variant = {
>  	.dec_fmts = imx8m_vpu_dec_fmts,
>  	.num_dec_fmts = ARRAY_SIZE(imx8m_vpu_dec_fmts),
> @@ -356,6 +362,7 @@ const struct hantro_variant imx8mq_vpu_g1_variant = {
>  	.num_irqs = ARRAY_SIZE(imx8mq_irqs),
>  	.clk_names = imx8mq_g1_clk_names,
>  	.num_clocks = ARRAY_SIZE(imx8mq_g1_clk_names),
> +	.shared_devices = imx8mq_vpu_shared_resources,
>  };
>
>  const struct hantro_variant imx8mq_vpu_g2_variant = {
> @@ -371,6 +378,7 @@ const struct hantro_variant imx8mq_vpu_g2_variant = {
>  	.num_irqs = ARRAY_SIZE(imx8mq_g2_irqs),
>  	.clk_names = imx8mq_g2_clk_names,
>  	.num_clocks = ARRAY_SIZE(imx8mq_g2_clk_names),
> +	.shared_devices = imx8mq_vpu_shared_resources,
>  };
>
>  const struct hantro_variant imx8mm_vpu_g1_variant = {
> --
> 2.52.0
>