Re: [PATCH 6/8] dmaengine: tegra: Use iommu-map for stream ID

[Akhil R <akhilrajeev@nvidia.com>]

On Tue, 24 Feb 2026 16:59:44 -0500 Frank Li wrote:
> On Tue, Feb 24, 2026 at 11:55:43AM +0530, Akhil R wrote:
>> On Tue, 17 Feb 2026 14:52:17 -0500, Frank Li wrote:
>>> On Tue, Feb 17, 2026 at 11:04:55PM +0530, Akhil R wrote:
>>>> Use iommu-map, when provided, to get the stream ID to be programmed
>>>> for each channel. Register each channel separately for allowing it
>>>> to use a separate IOMMU domain for the transfer.
>>>>
>>>> Channels will continue to use the same global stream ID if iommu-map
>>>> property is not present in the device tree.
>>>>
>>>> Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
>>>> ---
>>>>  drivers/dma/tegra186-gpc-dma.c | 62 +++++++++++++++++++++++++++-------
>>>>  1 file changed, 49 insertions(+), 13 deletions(-)
>>>>
>>>> diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
>>>> index ce3b1dd52bb3..b8ca269fa3ba 100644
>>>> --- a/drivers/dma/tegra186-gpc-dma.c
>>>> +++ b/drivers/dma/tegra186-gpc-dma.c
>>>> @@ -15,6 +15,7 @@
>>>>  #include <linux/module.h>
>>>>  #include <linux/of.h>
>>>>  #include <linux/of_dma.h>
>>>> +#include <linux/of_device.h>
>>>>  #include <linux/platform_device.h>
>>>>  #include <linux/reset.h>
>>>>  #include <linux/slab.h>
>>>> @@ -1403,9 +1404,12 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
>>>>  static int tegra_dma_probe(struct platform_device *pdev)
>>>>  {
>>>>  	const struct tegra_dma_chip_data *cdata = NULL;
>>>> +	struct tegra_dma_channel *tdc;
>>>> +	struct tegra_dma *tdma;
>>>> +	struct dma_chan *chan;
>>>> +	bool use_iommu_map = false;
>>>>  	unsigned int i;
>>>>  	u32 stream_id;
>>>> -	struct tegra_dma *tdma;
>>>>  	int ret;
>>>>
>>>>  	cdata = of_device_get_match_data(&pdev->dev);
>>>> @@ -1433,9 +1437,12 @@ static int tegra_dma_probe(struct platform_device *pdev)
>>>>
>>>>  	tdma->dma_dev.dev = &pdev->dev;
>>>>
>>>> -	if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
>>>> -		dev_err(&pdev->dev, "Missing iommu stream-id\n");
>>>> -		return -EINVAL;
>>>> +	use_iommu_map = of_property_present(pdev->dev.of_node, "iommu-map");
>>>> +	if (!use_iommu_map) {
>>>> +		if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
>>>> +			dev_err(&pdev->dev, "Missing iommu stream-id\n");
>>>> +			return -EINVAL;
>>>> +		}
>>>>  	}
>>>>
>>>>  	ret = device_property_read_u32(&pdev->dev, "dma-channel-mask",
>>>> @@ -1449,7 +1456,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
>>>>
>>>>  	INIT_LIST_HEAD(&tdma->dma_dev.channels);
>>>>  	for (i = 0; i < cdata->nr_channels; i++) {
>>>> -		struct tegra_dma_channel *tdc = &tdma->channels[i];
>>>> +		tdc = &tdma->channels[i];
>>>>
>>>>  		/* Check for channel mask */
>>>>  		if (!(tdma->chan_mask & BIT(i)))
>>>> @@ -1469,10 +1476,6 @@ static int tegra_dma_probe(struct platform_device *pdev)
>>>>
>>>>  		vchan_init(&tdc->vc, &tdma->dma_dev);
>>>>  		tdc->vc.desc_free = tegra_dma_desc_free;
>>>> -
>>>> -		/* program stream-id for this channel */
>>>> -		tegra_dma_program_sid(tdc, stream_id);
>>>> -		tdc->stream_id = stream_id;
>>>>  	}
>>>>
>>>>  	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(cdata->addr_bits));
>>>> @@ -1517,20 +1520,53 @@ static int tegra_dma_probe(struct platform_device *pdev)
>>>>  		return ret;
>>>>  	}
>>>>
>>>> +	list_for_each_entry(chan, &tdma->dma_dev.channels, device_node) {
>>>> +		struct device *chdev = &chan->dev->device;
>>>>
>>> why no use
>>> 	for (i = 0; i < cdata->nr_channels; i++) {
>>> 		struct tegra_dma_channel *tdc = &tdma->channels[i];
>>
>> I thought this would ensure that we try to configure only the channels
>> where the chan_dev and vchan are initialized. I understand that it is
>> not probable in the current implementation that we will have channels
>> which are uninitialized, but I felt this a better approach.
>> Do you see any disadvantage in using the channels list?
> 
> not big issue, just strange, previous code use
> for (i = 0; i < cdata->nr_channels; i++) {
> }
> 
> why need enumerate it again and use difference method.

I think we will not get to use chan->dev->device before
async_device_register() and thats why I added a separate loop to
configure the channels.

I can add a comment on why we need this loop. Do you suggest
changing it to a for-loop itself? Let me know your thoughts.

Regards,
Akhil