Re: [PATCH v7 04/12] iommu/mediatek: Add device_link between the consumer and the larb devices

[Dafna Hirschfeld <dafna.hirschfeld@collabora.com>]

On 30.07.21 04:52, Yong Wu wrote:
> MediaTek IOMMU-SMI diagram is like below. all the consumer connect with
> smi-larb, then connect with smi-common.
> 
>          M4U
>           |
>      smi-common
>           |
>    -------------
>    |         |    ...
>    |         |
> larb1     larb2
>    |         |
> vdec       venc
> 
> When the consumer works, it should enable the smi-larb's power which
> also need enable the smi-common's power firstly.
> 
> Thus, First of all, use the device link connect the consumer and the
> smi-larbs. then add device link between the smi-larb and smi-common.
> 
> This patch adds device_link between the consumer and the larbs.
> 
> When device_link_add, I add the flag DL_FLAG_STATELESS to avoid calling
> pm_runtime_xx to keep the original status of clocks. It can avoid two
> issues:
> 1) Display HW show fastlogo abnormally reported in [1]. At the beggining,
> all the clocks are enabled before entering kernel, but the clocks for
> display HW(always in larb0) will be gated after clk_enable and clk_disable
> called from device_link_add(->pm_runtime_resume) and rpm_idle. The clock
> operation happened before display driver probe. At that time, the display
> HW will be abnormal.
> 
> 2) A deadlock issue reported in [2]. Use DL_FLAG_STATELESS to skip
> pm_runtime_xx to avoid the deadlock.
> 
> Corresponding, DL_FLAG_AUTOREMOVE_CONSUMER can't be added, then
> device_link_removed should be added explicitly.
> 
> [1] https://lore.kernel.org/linux-mediatek/1564213888.22908.4.camel@mhfsdcap03/
> [2] https://lore.kernel.org/patchwork/patch/1086569/
> 
> Suggested-by: Tomasz Figa <tfiga@chromium.org>
> Signed-off-by: Yong Wu <yong.wu@mediatek.com>
> Tested-by: Dafna Hirschfeld <dafna.hirschfeld@collabora.com> # on mt8173

Hi, unfortunately, I have to take back the Tested-by tag.
I am now testing the mtk-vcodec with latest kernel + patches sent from the mailing list:
https://gitlab.collabora.com/eballetbo/linux/-/commits/topic/chromeos/chromeos-5.14
which includes this patchset.

On chromeos I open a video conference with googl-meet which cause the mtk-vcodec vp8 encoder to run.
If I kill it with `killall -9 chrome` I get some page fault messages from the iommu:

[  837.255952] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.265696] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.282367] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.299028] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.315683] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.332345] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.349004] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.365665] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.382329] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read
[  837.400002] mtk-iommu 10205000.iommu: fault type=0x5 iova=0xfcff0001 pa=0x0 larb=0 port=0 layer=1 read

In addition, running the encoder tests from the shell:

sudo --user=#1000 /usr/local/libexec/chrome-binary-tests/video_encode_accelerator_tests --gtest_filter=VideoEncoderTest.FlushAtEndOfStream_Multiple*  --codec=vp8 /usr/local/share/tast/data/chromiumos/tast/local/bundles/cros/video/data/tulip2-320x180.yuv --disable_validator

At some point it fails with the error

[ 5472.161821] [MTK_V4L2][ERROR] mtk_vcodec_wait_for_done_ctx:32: [290] ctx->type=1, cmd=1, wait_event_interruptible_timeout time=1000ms out 0 0!
[ 5472.174678] [MTK_VCODEC][ERROR][290]: vp8_enc_encode_frame() irq_status=0 failed
[ 5472.182687] [MTK_V4L2][ERROR] mtk_venc_worker:1239: venc_if_encode failed=-5


If you have any idea of what might be the problem or how to debug?

Thanks,
Dafna

> ---
>   drivers/iommu/mtk_iommu.c    | 22 ++++++++++++++++++++++
>   drivers/iommu/mtk_iommu_v1.c | 20 +++++++++++++++++++-
>   2 files changed, 41 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
> index a02dde094788..ee742900cf4b 100644
> --- a/drivers/iommu/mtk_iommu.c
> +++ b/drivers/iommu/mtk_iommu.c
> @@ -571,22 +571,44 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
>   {
>   	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
>   	struct mtk_iommu_data *data;
> +	struct device_link *link;
> +	struct device *larbdev;
> +	unsigned int larbid;
>   
>   	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
>   		return ERR_PTR(-ENODEV); /* Not a iommu client device */
>   
>   	data = dev_iommu_priv_get(dev);
>   
> +	/*
> +	 * Link the consumer device with the smi-larb device(supplier)
> +	 * The device in each a larb is a independent HW. thus only link
> +	 * one larb here.
> +	 */
> +	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
> +	larbdev = data->larb_imu[larbid].dev;
> +	link = device_link_add(dev, larbdev,
> +			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
> +	if (!link)
> +		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
>   	return &data->iommu;
>   }
>   
>   static void mtk_iommu_release_device(struct device *dev)
>   {
>   	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
> +	struct mtk_iommu_data *data;
> +	struct device *larbdev;
> +	unsigned int larbid;
>   
>   	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
>   		return;
>   
> +	data = dev_iommu_priv_get(dev);
> +	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
> +	larbdev = data->larb_imu[larbid].dev;
> +	device_link_remove(dev, larbdev);
> +
>   	iommu_fwspec_free(dev);
>   }
>   
> diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
> index c259433f1130..806d4200665b 100644
> --- a/drivers/iommu/mtk_iommu_v1.c
> +++ b/drivers/iommu/mtk_iommu_v1.c
> @@ -424,7 +424,9 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
>   	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
>   	struct of_phandle_args iommu_spec;
>   	struct mtk_iommu_data *data;
> -	int err, idx = 0;
> +	int err, idx = 0, larbid;
> +	struct device_link *link;
> +	struct device *larbdev;
>   
>   	/*
>   	 * In the deferred case, free the existed fwspec if the dev already has,
> @@ -454,6 +456,14 @@ static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
>   
>   	data = dev_iommu_priv_get(dev);
>   
> +	/* Link the consumer device with the smi-larb device(supplier) */
> +	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
> +	larbdev = data->larb_imu[larbid].dev;
> +	link = device_link_add(dev, larbdev,
> +			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
> +	if (!link)
> +		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
> +
>   	return &data->iommu;
>   }
>   
> @@ -474,10 +484,18 @@ static void mtk_iommu_probe_finalize(struct device *dev)
>   static void mtk_iommu_release_device(struct device *dev)
>   {
>   	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
> +	struct mtk_iommu_data *data;
> +	struct device *larbdev;
> +	unsigned int larbid;
>   
>   	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
>   		return;
>   
> +	data = dev_iommu_priv_get(dev);
> +	larbid = mt2701_m4u_to_larb(fwspec->ids[0]);
> +	larbdev = data->larb_imu[larbid].dev;
> +	device_link_remove(dev, larbdev);
> +
>   	iommu_fwspec_free(dev);
>   }
>   
>