Re: [PATCH v6 1/3] PCI/DOE: Expose the DOE features via sysfs

[Chaitanya Kulkarni <chaitanyak@nvidia.com>]

On 8/17/23 16:58, Alistair Francis wrote:
> The PCIe 6 specification added support for the Data Object Exchange (DOE).
> When DOE is supported the Discovery Data Object Protocol must be
> implemented. The protocol allows a requester to obtain information about
> the other DOE features supported by the device.
>
> The kernel is already querying the DOE features supported and cacheing
> the values. This patch exposes the values via sysfs. This will allow
> userspace to determine which DOE features are supported by the PCIe
> device.
>
> By exposing the information to userspace tools like lspci can relay the
> information to users. By listing all of the supported features we can
> allow userspace to parse and support the list, which might include
> vendor specific features as well as yet to be supported features.
>
> Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
> ---
> v6:
>   - Use "feature" instead of protocol
>   - Don't use any devm_* functions
>   - Add two more patches to the series
> v5:
>   - Return the file name as the file contents
>   - Code cleanups and simplifications
> v4:
>   - Fixup typos in the documentation
>   - Make it clear that the file names contain the information
>   - Small code cleanups
>   - Remove most #ifdefs
>   - Remove extra NULL assignment
> v3:
>   - Expose each DOE feature as a separate file
> v2:
>   - Add documentation
>   - Code cleanups
>
> This patch will create a doe_features directory for all
> PCIe devices without the next two patches
>
>   Documentation/ABI/testing/sysfs-bus-pci |  11 +++
>   drivers/pci/doe.c                       | 112 ++++++++++++++++++++++++
>   drivers/pci/pci-sysfs.c                 |  10 +++
>   drivers/pci/pci.h                       |   3 +
>   include/linux/pci-doe.h                 |   1 +
>   5 files changed, 137 insertions(+)
>
> diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
> index ecf47559f495..199ee5d27d9d 100644
> --- a/Documentation/ABI/testing/sysfs-bus-pci
> +++ b/Documentation/ABI/testing/sysfs-bus-pci
> @@ -500,3 +500,14 @@ Description:
>   		console drivers from the device.  Raw users of pci-sysfs
>   		resourceN attributes must be terminated prior to resizing.
>   		Success of the resizing operation is not guaranteed.
> +
> +What:		/sys/bus/pci/devices/.../doe_features
> +Date:		August 2023
> +Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
> +Description:
> +		This directory contains a list of the supported
> +		Data Object Exchange (DOE) features. The feature values are in the

overly long line above ...

> +		file name. The contents of each file are the same as the name.
> +		The value comes from the device and specifies the vendor and
> +		data object type supported. The lower byte is the data object
> +		type and the next two bytes are the vendor ID.
> diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c
> index 1b97a5ab71a9..316aac60ccd5 100644
> --- a/drivers/pci/doe.c
> +++ b/drivers/pci/doe.c
> @@ -56,6 +56,8 @@ struct pci_doe_mb {
>   	wait_queue_head_t wq;
>   	struct workqueue_struct *work_queue;
>   	unsigned long flags;
> +
> +	struct device_attribute *sysfs_attrs;

above naked declaration without CONFIG_SYSFS seems really odd
especially following code is under CONFIG_SYSFS, unless it is
accessed outside of CONFIG_SYSFS (which I don't think it is
a right interface) then ignore this comment ..

>   };
>   
>   struct pci_doe_protocol {
> @@ -92,6 +94,116 @@ struct pci_doe_task {
>   	struct pci_doe_mb *doe_mb;
>   };
>   
> +#ifdef CONFIG_SYSFS
> +static umode_t pci_doe_sysfs_attr_is_visible(struct kobject *kobj,
> +					     struct attribute *a, int n)
> +{
> +	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
> +	unsigned long total_features = 0;
> +	struct pci_doe_mb *doe_mb;
> +	unsigned long index, j;
> +	void *entry;
> +
> +	xa_for_each(&pdev->doe_mbs, index, doe_mb) {
> +		xa_for_each(&doe_mb->prots, j, entry)
> +			total_features++;
> +	}
> +
> +	if (total_features == 0)
> +		return 0;
> +
> +	return a->mode;
> +}
> +

this removes the need for extra variable to avoids unnecessary
loop iterations unless there is bug in this suggestion, why not following ?

static umode_t pci_doe_sysfs_attr_is_visible(struct kobject *kobj,
					     struct attribute *a, int n)
{
	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
	struct pci_doe_mb *doe_mb;
	unsigned long index, j;
	void *entry;

	xa_for_each(&pdev->doe_mbs, index, doe_mb) {
		xa_for_each(&doe_mb->prots, j, entry)
			return a->mode;
	}

	return 0;
}


> +static struct attribute *pci_dev_doe_feature_attrs[] = {
> +	NULL,
> +};
> +
> +const struct attribute_group pci_dev_doe_feature_group = {
> +	.name	= "doe_features",
> +	.attrs	= pci_dev_doe_feature_attrs,
> +	.is_visible = pci_doe_sysfs_attr_is_visible,
> +};
> +
> +static ssize_t pci_doe_sysfs_feature_show(struct device *dev,
> +					  struct device_attribute *attr,
> +					  char *buf)
> +{
> +	return sysfs_emit(buf, "%s\n", attr->attr.name);
> +}
> +
> +static int pci_doe_sysfs_feature_supports(struct pci_dev *pdev,
> +					  struct pci_doe_mb *doe_mb)
> +{
> +	struct device *dev = &pdev->dev;
> +	struct device_attribute *attrs;
> +	unsigned long num_features = 0;
> +	unsigned long vid, type;
> +	unsigned long i;
> +	void *entry;
> +	int ret;
> +
> +	xa_for_each(&doe_mb->prots, i, entry)
> +		num_features++;
> +
> +	attrs = kcalloc(num_features, sizeof(*attrs), GFP_KERNEL);
> +	if (!attrs)
> +		return -ENOMEM;
> +
> +	doe_mb->sysfs_attrs = attrs;
> +	xa_for_each(&doe_mb->prots, i, entry) {
> +		sysfs_attr_init(&attrs[i].attr);
> +		vid = xa_to_value(entry) >> 8;
> +		type = xa_to_value(entry) & 0xFF;
> +		attrs[i].attr.name = kasprintf(GFP_KERNEL,
> +					       "0x%04lX:%02lX", vid, type);
> +		if (!attrs[i].attr.name) {
> +			ret = -ENOMEM;
> +			goto fail;
> +		}
> +
> +		attrs[i].attr.mode = 0444;
> +		attrs[i].show = pci_doe_sysfs_feature_show;
> +
> +		ret = sysfs_add_file_to_group(&dev->kobj, &attrs[i].attr,
> +					      pci_dev_doe_feature_group.name);
> +		if (ret)
> +			goto fail;
> +	}
> +
> +	return 0;
> +
> +fail:
> +	doe_mb->sysfs_attrs = NULL;
> +	xa_for_each(&doe_mb->prots, i, entry) {
> +		if (attrs[i].show)
> +			sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr,
> +						     pci_dev_doe_feature_group.name);
> +		kfree(attrs[i].attr.name);
> +	}
> +
> +	kfree(attrs);
> +
> +	return ret;
> +}
> +
> +int doe_sysfs_init(struct pci_dev *pdev)
> +{
> +	struct pci_doe_mb *doe_mb;
> +	unsigned long index;
> +	int ret;
> +
> +	xa_for_each(&pdev->doe_mbs, index, doe_mb) {
> +		ret = pci_doe_sysfs_feature_supports(pdev, doe_mb);
> +
> +		if (ret)
> +			return ret;
> +	}
> +
> +	return 0;
> +}
> +#endif
> +
>   static int pci_doe_wait(struct pci_doe_mb *doe_mb, unsigned long timeout)
>   {
>   	if (wait_event_timeout(doe_mb->wq,
> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index ab32a91f287b..3f5104cf78b6 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
> @@ -16,6 +16,7 @@
>   #include <linux/kernel.h>
>   #include <linux/sched.h>
>   #include <linux/pci.h>
> +#include <linux/pci-doe.h>
>   #include <linux/stat.h>
>   #include <linux/export.h>
>   #include <linux/topology.h>
> @@ -1226,6 +1227,12 @@ static int pci_create_resource_files(struct pci_dev *pdev)
>   	int i;
>   	int retval;
>   
> +	if (IS_ENABLED(CONFIG_PCI_DOE)) {
> +		retval = doe_sysfs_init(pdev);
> +		if (retval)
> +			return retval;
> +	}
> +
>   	/* Expose the PCI resources from this device as files */
>   	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
>   
> @@ -1651,6 +1658,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
>   #endif
>   #ifdef CONFIG_PCIEASPM
>   	&aspm_ctrl_attr_group,
> +#endif
> +#ifdef CONFIG_PCI_DOE
> +	&pci_dev_doe_feature_group,
>   #endif
>   	NULL,
>   };
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index a4c397434057..139d37a0d4cd 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -180,6 +180,9 @@ extern const struct attribute_group *pci_dev_groups[];
>   extern const struct attribute_group *pcibus_groups[];
>   extern const struct device_type pci_dev_type;
>   extern const struct attribute_group *pci_bus_groups[];
> +#ifdef CONFIG_SYSFS
> +extern const struct attribute_group pci_dev_doe_feature_group;
> +#endif
>   
>   extern unsigned long pci_hotplug_io_size;
>   extern unsigned long pci_hotplug_mmio_size;
> diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h
> index 1f14aed4354b..4cc13d9ccb50 100644
> --- a/include/linux/pci-doe.h
> +++ b/include/linux/pci-doe.h
> @@ -22,4 +22,5 @@ int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type,
>   	    const void *request, size_t request_sz,
>   	    void *response, size_t response_sz);
>   
> +int doe_sysfs_init(struct pci_dev *pci_dev);
>   #endif