Message-ID: <c9c98d61-f404-14bd-b274-758326827f90@xilinx.com>
Date:   Wed, 9 Feb 2022 15:53:54 +0530
From:   Tanmay Shah <tanmay.shah@...inx.com>
To:     Mathieu Poirier <mathieu.poirier@...aro.org>
CC:     Bjorn Andersson <bjorn.andersson@...aro.org>,
        Rob Herring <robh+dt@...nel.org>,
        Michal Simek <michal.simek@...inx.com>,
        Laurent Pinchart <laurent.pinchart@...asonboard.com>,
        Ben Levinsky <ben.levinsky@...inx.com>,
        Bill Mills <bill.mills@...aro.org>,
        Sergei Korneichuk <sergei.korneichuk@...inx.com>,
        <linux-remoteproc@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <devicetree@...r.kernel.org>,
        <linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH v2 6/6] drivers: remoteproc: Add Xilinx r5 remoteproc
 driver


On 2/8/22 10:24 PM, Mathieu Poirier wrote:
> Hi Tanmay,
>
> [...]
>
>>> I am done reviewing this set - the overall structure is sound but there is a
>>> fair amount of work to be done.  There is no need to rush another revision as I
>>> won't have time to review it before the holidays.  On that front, change
>>> _only_ the things I have commented on.  We can address other issues as we move
>>> forward.  Last but not least, please run the sparse checker on your work.
>>>
>>> Thanks,
>>> Mathieu
>> Hi Mathieu,
>>
>> I am ready to post v3 in this patch series.
>>
>> I have developed v3 based on rproc-next. However, when I rebased my work on
>> tip of linux-next branch,
> Are the merge conflicts related to drivers/remoteproc or drivers/rpmsg?  That
> would be surprising since the code that is in rproc-next and rpmsg-next is also
> in linux-next.

Merge conflict is in Xilinx firmware driver related code. i.e. file 
"include/linux/firmware/xlnx-zynqmp.h"

>
> In any case I would suggest to base your v3 on _today's_ for-next branch [1] and
> explicitly mention any dependency in the cover letter.  From there I might be
> able to see where the problems are and advise further.
>
> [1]. https://git.kernel.org/pub/scm/linux/kernel/git/remoteproc/linux.git/log/?h=for-next

Sure I will do the same.

I found that following two patches are available in linux-next and not 
in rproc-next/for-next:

https://lore.kernel.org/all/20211025082350.10881-2-abhyuday.godhasara@xilinx.com/

https://lore.kernel.org/all/20211026042525.26612-4-abhyuday.godhasara@xilinx.com/

>> I faced merge-conflicts.
>>
>> What is preferred way to proceed in such case? Should I post my patch based
>> on rproc-next or linux-next?
>>
>> Or any other way to proceed further?
>>
>>
>>>> +
>>>> +	dev = r5_core->dev;
>>>> +
>>>> +	ret = add_tcm_banks(rproc);
>>>> +	if (ret) {
>>>> +		dev_err(dev, "failed to get TCM banks, err %d\n", ret);
>>>> +		return ret;
>>>> +	}
>>>> +
>>>> +	ret = add_mem_regions(rproc);
>>>> +	if (ret)
>>>> +		dev_warn(dev, "failed to get reserve mem regions %d\n", ret);
>>>> +
>>>> +	ret = rproc_elf_load_rsc_table(rproc, fw);
>>>> +	if (ret == -EINVAL) {
>>>> +		/*
>>>> +		 * resource table only required for IPC.
>>>> +		 * if not present, this is not necessarily an error;
>>>> +		 * for example, loading r5 hello world application
>>>> +		 * so simply inform user and keep going.
>>>> +		 */
>>>> +		dev_info(&rproc->dev, "no resource table found.\n");
>>>> +		ret = 0;
>>>> +	}
>>>> +	return ret;
>>>> +}
>>>> +
>>>> +static struct rproc_ops zynqmp_r5_rproc_ops = {
>>>> +	.start		= zynqmp_r5_rproc_start,
>>>> +	.stop		= zynqmp_r5_rproc_stop,
>>>> +	.load		= rproc_elf_load_segments,
>>>> +	.parse_fw	= zynqmp_r5_parse_fw,
>>>> +	.find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table,
>>>> +	.sanity_check	= rproc_elf_sanity_check,
>>>> +	.get_boot_addr	= rproc_elf_get_boot_addr,
>>>> +};
>>>> +
>>>> +static void zynqmp_r5_print_dt_node_info(struct zynqmp_r5_cluster *cluster)
>>>> +{
>>>> +	int i, j, k;
>>>> +	struct zynqmp_r5_core *r5_core;
>>>> +
>>>> +	dev_dbg(cluster->dev, "Printing dt node info\n");
>>>> +
>>>> +	pr_debug("cluster mode = %d\n", cluster->mode);
>>>> +	pr_debug("r5f cluster in %s mode\n", (cluster->mode == 0) ? "SPLIT" :
>>>> +		 cluster->mode == 1 ? "LOCKSTEP" : "SINGLE_CPU");
>>>> +	pr_debug("r5f num cores = %d\n", cluster->core_count);
>>>> +
>>>> +	for (i = 0; i < cluster->core_count; i++) {
>>>> +		r5_core = &cluster->r5_cores[i];
>>>> +		if (!r5_core) {
>>>> +			pr_err("can't get r5_core\n");
>>>> +			continue;
>>>> +		}
>>>> +
>>>> +		pr_debug("r5 core %d nodes\n", i);
>>>> +		pr_debug("TCM banks = %d\n", r5_core->tcm_bank_count);
>>>> +		for (k = 0; k < r5_core->tcm_bank_count; k++) {
>>>> +			pr_debug("tcm %d addr=0x%llx size=0x%lx, pm_id=%d, %s\n",
>>>> +				 k, r5_core->tcm_banks[k].addr,
>>>> +				 r5_core->tcm_banks[k].size,
>>>> +				 r5_core->tcm_banks[k].pm_domain_id,
>>>> +				 r5_core->tcm_banks[k].bank_name);
>>>> +		}
>>>> +
>>>> +		pr_debug("reserve mem regions = %d\n", r5_core->res_mem_count);
>>>> +
>>>> +		for (j = 0; j < r5_core->res_mem_count; j++) {
>>>> +			pr_debug("mem %d addr=0x%llx, size=0x%llx, name=%s\n",
>>>> +				 j, r5_core->res_mem[j].base,
>>>> +				 r5_core->res_mem[j].size,
>>>> +				 r5_core->res_mem[j].name);
>>>> +		}
>>>> +	}
>>>> +}
>>>> +
>>>> +/**
>>>> + * zynqmp_r5_add_rproc_core() - Probes ZynqMP R5 processor device node
>>>> + *		       this is called for each individual R5 core to
>>>> + *		       set up mailbox, Xilinx platform manager unique ID,
>>>> + *		       add to rproc core
>>>> + *
>>>> + * @r5_core: zynqmp_r5_core r5 core object to initialize
>>>> + *
>>>> + * Return: 0 for success, negative value for failure.
>>>> + */
>>>> +static int zynqmp_r5_add_rproc_core(struct zynqmp_r5_core *r5_core)
>>>> +{
>>>> +	int ret;
>>>> +	struct rproc *r5_rproc;
>>>> +	struct device *dev;
>>>> +
>>>> +	dev = r5_core->dev;
>>>> +
>>>> +	/* Set up DMA mask */
>>>> +	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
>>>> +	if (ret)
>>>> +		return ret;
>>>> +
>>>> +	/* Allocate remoteproc instance */
>>>> +	r5_rproc = devm_rproc_alloc(dev, dev_name(dev), &zynqmp_r5_rproc_ops,
>>>> +				    NULL, sizeof(struct zynqmp_r5_core));
>>>> +	if (IS_ERR_OR_NULL(r5_rproc))
>>>> +		return -ENOMEM;
>>>> +
>>>> +	r5_rproc->auto_boot = false;
>>>> +	r5_rproc->priv = r5_core;
>>>> +
>>>> +	/* Add R5 remoteproc */
>>>> +	ret = devm_rproc_add(dev, r5_rproc);
>>>> +	if (ret) {
>>>> +		pr_err("failed to add r5 remoteproc\n");
>>>> +		return ret;
>>>> +	}
>>>> +
>>>> +	return 0;
>>>> +}
>>>> +
>>>> +static int zynqmp_r5_get_tcm_node(struct zynqmp_r5_cluster *cluster)
>>>> +{
>>>> +	int tcm_bank_count, tcm_node;
>>>> +	int i = 0, j;
>>>> +	struct zynqmp_r5_core *r5_core;
>>>> +	const struct mem_bank_data *tcm = zynqmp_tcm_banks;
>>>> +	struct device *dev = cluster->dev;
>>>> +
>>>> +	/* ToDo: Use predefined TCM address space values from driver until
>>>> +	 * system-dt spec is not final fot TCM
>>>> +	 */
>>>> +	tcm_bank_count = ARRAY_SIZE(zynqmp_tcm_banks);
>>>> +
>>>> +	/* count per core tcm banks */
>>>> +	tcm_bank_count = tcm_bank_count / cluster->core_count;
>>>> +
>>>> +	/* r5 core 0 will use all of TCM banks in lockstep mode.
>>>> +	 * In split mode, r5 core0 will use 128k and r5 core1 will use another
>>>> +	 * 128k. Assign TCM banks to each core accordingly
>>>> +	 */
>>>> +	tcm_node = 0;
>>>> +	for (j = 0; j < cluster->core_count; j++) {
>>>> +		r5_core = &cluster->r5_cores[j];
>>>> +		r5_core->tcm_banks = devm_kzalloc(dev, sizeof(struct mem_bank_data) *
>>>> +						  tcm_bank_count, GFP_KERNEL);
>>>> +		if (IS_ERR_OR_NULL(r5_core->tcm_banks))
>>>> +			return -ENOMEM;
>>>> +
>>>> +		for (i = 0; i < tcm_bank_count; i++) {
>>>> +			/* Use pre-defined TCM reg values.
>>>> +			 * Eventually this should be replaced by values
>>>> +			 * parsed from dts.
>>>> +			 */
>>>> +			r5_core->tcm_banks[i].addr = tcm[tcm_node].addr;
>>>> +			r5_core->tcm_banks[i].size = tcm[tcm_node].size;
>>>> +			r5_core->tcm_banks[i].pm_domain_id = tcm[tcm_node].pm_domain_id;
>>>> +			r5_core->tcm_banks[i].bank_name = tcm[tcm_node].bank_name;
>>>> +			tcm_node++;
>>>> +		}
>>>> +
>>>> +		r5_core->tcm_bank_count = tcm_bank_count;
>>>> +	}
>>>> +
>>>> +	return 0;
>>>> +}
>>>> +
>>>> +static int zynqmp_r5_get_mem_region_node(struct zynqmp_r5_core *r5_core)
>>>> +{
>>>> +	int res_mem_count, i;
>>>> +	struct device *dev;
>>>> +	struct device_node *np, *rmem_np;
>>>> +	struct reserved_mem *rmem;
>>>> +
>>>> +	dev = r5_core->dev;
>>>> +
>>>> +	np = r5_core->np;
>>>> +	if (IS_ERR_OR_NULL(np)) {
>>>> +		pr_err("invalid device node of r5 core\n");
>>>> +		return -EINVAL;
>>>> +	}
>>>> +
>>>> +	res_mem_count = of_property_count_elems_of_size(np, "memory-region",
>>>> +							sizeof(phandle));
>>>> +	if (res_mem_count <= 0) {
>>>> +		dev_warn(dev, "failed to get memory-region property %d\n",
>>>> +			 res_mem_count);
>>>> +		return -EINVAL;
>>>> +	}
>>>> +
>>>> +	r5_core->res_mem = devm_kzalloc(dev,
>>>> +					res_mem_count * sizeof(struct reserved_mem),
>>>> +					GFP_KERNEL);
>>>> +	if (!r5_core->res_mem) {
>>>> +		dev_err(dev, "failed to allocate mem region memory\n");
>>>> +		return -ENOMEM;
>>>> +	}
>>>> +
>>>> +	for (i = 0; i < res_mem_count; i++) {
>>>> +		rmem_np = of_parse_phandle(np, "memory-region", i);
>>>> +		if (!rmem_np)
>>>> +			return -EINVAL;
>>>> +
>>>> +		rmem = of_reserved_mem_lookup(rmem_np);
>>>> +		if (!rmem) {
>>>> +			of_node_put(rmem_np);
>>>> +			return -EINVAL;
>>>> +		}
>>>> +
>>>> +		memcpy(&r5_core->res_mem[i], rmem,
>>>> +		       sizeof(struct reserved_mem));
>>>> +		of_node_put(rmem_np);
>>>> +	}
>>>> +
>>>> +	r5_core->res_mem_count = res_mem_count;
>>>> +
>>>> +	return 0;
>>>> +}
>>>> +
>>>> +static int zynqmp_r5_core_init(struct zynqmp_r5_cluster *cluster)
>>>> +{
>>>> +	int ret, i;
>>>> +	struct zynqmp_r5_core *r5_core;
>>>> +	struct device *dev = cluster->dev;
>>>> +
>>>> +	ret = zynqmp_r5_get_tcm_node(cluster);
>>>> +	if (ret < 0) {
>>>> +		dev_err(dev, "can't get tcm node, err %d\n", ret);
>>>> +		return ret;
>>>> +	}
>>>> +
>>>> +	for (i = 0; i < cluster->core_count; i++) {
>>>> +		r5_core = &cluster->r5_cores[i];
>>>> +		if (!r5_core) {
>>>> +			pr_err("invalid r5 core\n");
>>>> +			return -EINVAL;
>>>> +		}
>>>> +
>>>> +		ret = zynqmp_r5_get_mem_region_node(r5_core);
>>>> +		if (ret)
>>>> +			dev_warn(dev, "memory-region prop failed %d\n", ret);
>>>> +
>>>> +		ret = of_property_read_u32_index(r5_core->np, "power-domains",
>>>> +						 1, &r5_core->pm_domain_id);
>>>> +		if (ret) {
>>>> +			dev_err(dev, "failed to get power-domains property\n");
>>>> +			return ret;
>>>> +		}
>>>> +
>>>> +		ret = zynqmp_r5_set_mode(r5_core, cluster->mode);
>>>> +		if (ret)
>>>> +			return ret;
>>>> +
>>>> +		ret = zynqmp_r5_add_rproc_core(r5_core);
>>>> +		if (ret) {
>>>> +			dev_err(dev, "failed to init r5 core %d\n", i);
>>>> +			return ret;
>>>> +		}
>>>> +	}
>>>> +
>>>> +	return 0;
>>>> +}
>>>> +
>>>> +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;
>>>> +	}
>>>> +
>>>> +	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;
>>>> +	}
>>>> +
>>>> +	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_kzalloc(dev, sizeof(struct zynqmp_r5_core) *
>>>> +						 core_count, GFP_KERNEL);
>>>> +	if (IS_ERR_OR_NULL(r5_cores)) {
>>>> +		dev_err(dev, "can't allocate memory for cores\n");
>>>> +		return -ENOMEM;
>>>> +	}
>>>> +
>>>> +	i = 0;
>>>> +	for_each_available_child_of_node(dev_node, child) {
>>>> +		child_pdev = of_find_device_by_node(child);
>>>> +		if (!child_pdev)
>>>> +			return -ENODEV;
>>>> +
>>>> +		r5_cores[i].dev = &child_pdev->dev;
>>>> +		if (!r5_cores[i].dev) {
>>>> +			pr_err("can't get device for r5 core %d\n", i);
>>>> +			return -ENODEV;
>>>> +		}
>>>> +
>>>> +		r5_cores[i].np = dev_of_node(r5_cores[i].dev);
>>>> +		if (!r5_cores[i].np) {
>>>> +			pr_err("can't get device node for r5 core %d\n", i);
>>>> +			return -ENODEV;
>>>> +		}
>>>> +
>>>> +		i++;
>>>> +		if (i == core_count)
>>>> +			break;
>>>> +	}
>>>> +
>>>> +	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;
>>>> +	}
>>>> +
>>>> +	zynqmp_r5_print_dt_node_info(cluster);
>>>> +
>>>> +	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 (IS_ERR_OR_NULL(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;
>>>> +	}
>>>> +
>>>> +	dev_info(dev, "Xilinx r5f remoteproc driver probe success\n");
>>>> +	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
>>>>

Powered by blists - more mailing lists