[PATCH v3 6/6] drivers: remoteproc: Add Xilinx r5 remoteproc driver

[Mathieu Poirier]

[...]

> > > + * zynqmp_r5_cluster_init()
> > > + * Create and initialize zynqmp_r5_cluster type object
> > > + *
> > > + * @cluster: pointer to zynqmp_r5_cluster type object
> > > + *
> > > + * Return: 0 for success and error code for failure.
> > > + */
> > > +static int zynqmp_r5_cluster_init(struct zynqmp_r5_cluster *cluster)
> > > +{
> > > +	struct device *dev = cluster->dev;
> > > +	struct device_node *dev_node = dev_of_node(dev);
> > > +	struct device_node *child;
> > > +	struct platform_device *child_pdev;
> > > +	int core_count = 0, ret, i;
> > > +	enum zynqmp_r5_cluster_mode cluster_mode = LOCKSTEP_MODE;
> > > +	struct zynqmp_r5_core **r5_cores;
> > > +
> > > +	ret = of_property_read_u32(dev_node, "xlnx,cluster-mode", &cluster_mode);
> > > +
> > > +	/*
> > > +	 * on success returns 0, if not defined then returns -EINVAL,
> > > +	 * In that case, default is LOCKSTEP mode
> > > +	 */
> > > +	if (ret != -EINVAL && ret != 0) {
> > > +		dev_err(dev, "Invalid xlnx,cluster-mode property\n");
> > > +		return -EINVAL;
> > > +	}
> > > +
> > > +	/*
> > > +	 * For now driver only supports split mode and lockstep mode.
> > > +	 * fail driver probe if either of that is not set in dts
> > > +	 */
> > > +	if (cluster_mode == SINGLE_CPU_MODE) {
> > > +		dev_err(dev, "driver does not support single cpu mode\n");
> > > +		return -EINVAL;
> > > +	} else if ((cluster_mode != SPLIT_MODE &&
> > > +		   cluster_mode != LOCKSTEP_MODE)) {
> > > +		dev_err(dev, "Invalid cluster mode\n");
> > > +		return -EINVAL;
> > > +	}
> > > +
> > > +	/*
> > > +	 * Number of cores is decided by number of child nodes of
> > > +	 * r5f subsystem node in dts. If Split mode is used in dts
> > > +	 * 2 child nodes are expected.
> > > +	 * In lockstep mode if two child nodes are available,
> > > +	 * only use first child node and consider it as core0
> > > +	 * and ignore core1 dt node.
> > > +	 */
> > > +	core_count = of_get_available_child_count(dev_node);
> > > +	if (core_count <= 0) {
> > > +		dev_err(dev, "Invalid number of r5 cores %d", core_count);
> > > +		return -EINVAL;
> > > +	} else if (cluster_mode == SPLIT_MODE && core_count != 2) {
> > > +		dev_err(dev, "Invalid number of r5 cores for split mode\n");
> > > +		return -EINVAL;
> > > +	} else if (cluster_mode == LOCKSTEP_MODE && core_count == 2) {
> > > +		dev_warn(dev, "Only r5 core0 will be used\n");
> > > +		core_count = 1;
> > > +	}
> > > +
> > > +	r5_cores = devm_kcalloc(dev, core_count,
> > > +				sizeof(struct zynqmp_r5_core *), GFP_KERNEL);
> > > +	if (!r5_cores)
> > > +		return -ENOMEM;
> > > +
> > > +	i = 0;
> > > +	for_each_available_child_of_node(dev_node, child) {
> > > +		child_pdev = of_find_device_by_node(child);
> > > +		if (!child_pdev) {
> > > +			of_node_put(child);
> > > +			return -ENODEV;
> > > +		}
> > > +
> > > +		/* create and add remoteproc instance of type struct rproc */
> > > +		r5_cores[i] = zynqmp_r5_add_rproc_core(&child_pdev->dev);
> > Function zynqmp_r5_add_rproc_core() returns an error code on error that is never
> > checked.
> > 
> > > +		r5_cores[i]->dev = &child_pdev->dev;
> > This will result in a kernel stack trace if zynqmp_r5_add_rproc_core() fails.
> Sure I will fix it.
> > > +		if (!r5_cores[i]->dev) {
> > > +			dev_err(dev, "can't get device for r5 core %d\n", i);
> > > +			of_node_put(child);
> > > +			return -ENODEV;
> > > +		}
> > And here the validity of child_pdev->dev is checked _after_ it has been passed
> > to zynqmp_r5_add_rproc_core().  This check should not be needed if proper
> > error handling is done above.
> I agree.
> > > +
> > > +		r5_cores[i]->np = dev_of_node(r5_cores[i]->dev);
> > > +		if (!r5_cores[i]->np) {
> > > +			dev_err(dev, "can't get device node for r5 core %d\n", i);
> > > +			of_node_put(child);
> > As mention in the documentation for of_find_device_by_node(), the function takes
> > a reference to child_pdev->dev that needs to be released with put_device().  In
> > fact I don't see the reference dropped anywhere, even when the driver is
> > released.
> 
> I agree. I want to use r5_cores[i]->dev throughout driver so,
> 
> Is it fine if I use put_device() during driver release i.e. function
> zynqmp_r5_cluster_exit( ) ?
> 

Yes, that would be the right place to do it.

> > Moreover, if we end up here for r5_cores[1], resources acquired for r5_core[0]
> > are not released.
> 
> Most of the resources (such as zynqmp_r5_rproc_ops and r5_rproc objects) for
> r5_core[0] are allocated using devm_* API,
> 
> so I believe it will be de-allocated when driver probe fails and driver
> exits.
> 
> If r5_cores[1] fails, then r5_cores[0]->np needs to be released here. I will
> find out mechanism to take care of this.
> 
> Please let me know if I am missing anything here.
> 

I'll take another look in your next revision.

> > > +			return -ENODEV;
> > > +		}
> > > +
> > > +		i++;
> > > +
> > > +		/*
> > > +		 * If two child nodes are available in dts in lockstep mode,
> > > +		 * then ignore second child node.
> > > +		 */
> > > +		if (i == core_count) {
> > > +			of_node_put(child);
> > > +			break;
> > > +		}
> > > +		of_node_put(child);
> > This one is not needed as it is already done by the
> > for_each_available_child_of_node() loop.
> 
> Ok I will remove it.
> 
> > More comments tomorrow.
> > 
> > Thanks,
> > Mathieu
> > 
> > > +	}
> > > +
> > > +	cluster->mode = cluster_mode;
> > > +	cluster->core_count = core_count;
> > > +	cluster->r5_cores = r5_cores;
> > > +
> > > +	ret = zynqmp_r5_core_init(cluster);
> > > +	if (ret < 0) {
> > > +		dev_err(dev, "failed to init r5 core err %d\n", ret);
> > > +		return ret;
> > > +	}
> > > +
> > > +	return 0;
> > > +}
> > > +
> > > +static void zynqmp_r5_cluster_exit(void *data)
> > > +{
> > > +	struct platform_device *pdev = (struct platform_device *)data;
> > > +
> > > +	platform_set_drvdata(pdev, NULL);
> > > +
> > > +	pr_info("Exit r5f subsystem driver\n");
> > > +}
> > > +
> > > +/*
> > > + * zynqmp_r5_remoteproc_probe()
> > > + *
> > > + * @pdev: domain platform device for R5 cluster
> > > + *
> > > + * called when driver is probed, for each R5 core specified in DT,
> > > + * setup as needed to do remoteproc-related operations
> > > + *
> > > + * Return: 0 for success, negative value for failure.
> > > + */
> > > +static int zynqmp_r5_remoteproc_probe(struct platform_device *pdev)
> > > +{
> > > +	int ret;
> > > +	struct zynqmp_r5_cluster *cluster;
> > > +	struct device *dev = &pdev->dev;
> > > +
> > > +	cluster = devm_kzalloc(dev, sizeof(*cluster), GFP_KERNEL);
> > > +	if (!cluster)
> > > +		return -ENOMEM;
> > > +
> > > +	cluster->dev = dev;
> > > +
> > > +	ret = devm_of_platform_populate(dev);
> > > +	if (ret) {
> > > +		dev_err(dev, "failed to populate platform dev %d\n", ret);
> > > +		return ret;
> > > +	}
> > > +
> > > +	/* wire in so each core can be cleaned up at driver remove */
> > > +	platform_set_drvdata(pdev, cluster);
> > > +
> > > +	ret = devm_add_action_or_reset(dev, zynqmp_r5_cluster_exit, pdev);
> > > +	if (ret)
> > > +		return ret;
> > > +
> > > +	ret = zynqmp_r5_cluster_init(cluster);
> > > +	if (ret) {
> > > +		dev_err(dev, "Invalid r5f subsystem device tree\n");
> > > +		return ret;
> > > +	}
> > > +
> > > +	return 0;
> > > +}
> > > +
> > > +/* Match table for OF platform binding */
> > > +static const struct of_device_id zynqmp_r5_remoteproc_match[] = {
> > > +	{ .compatible = "xlnx,zynqmp-r5fss", },
> > > +	{ /* end of list */ },
> > > +};
> > > +MODULE_DEVICE_TABLE(of, zynqmp_r5_remoteproc_match);
> > > +
> > > +static struct platform_driver zynqmp_r5_remoteproc_driver = {
> > > +	.probe = zynqmp_r5_remoteproc_probe,
> > > +	.driver = {
> > > +		.name = "zynqmp_r5_remoteproc",
> > > +		.of_match_table = zynqmp_r5_remoteproc_match,
> > > +	},
> > > +};
> > > +module_platform_driver(zynqmp_r5_remoteproc_driver);
> > > +
> > > +MODULE_DESCRIPTION("Xilinx R5F remote processor driver");
> > > +MODULE_AUTHOR("Xilinx Inc.");
> > > +MODULE_LICENSE("GPL v2");
> > > -- 
> > > 2.25.1
> > >