PCI/DOE: Expose DOE features via sysfs

PCIe r6.0 added support for Data Object Exchange (DOE).  When DOE is
supported, the DOE Discovery Feature must be implemented per PCIe r6.1, sec
6.30.1.1. DOE allows a requester to obtain information about the other DOE
features supported by the device.

The kernel already queries the DOE features supported and caches the
values.  Expose the values in sysfs to allow user space 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 the list, which might include vendor specific features
as well as yet to be supported features.

As the DOE Discovery feature must always be supported we treat it as a
special named attribute case. This allows the usual PCI attribute_group
handling to correctly create the doe_features directory when registering
pci_doe_sysfs_group (otherwise it doesn't and sysfs_add_file_to_group()
will seg fault).

After this patch is supported you can see something like this when
attaching a DOE device:

  $ ls /sys/devices/pci0000:00/0000:00:02.0//doe*
  0001:01        0001:02        doe_discovery

Link: https://lore.kernel.org/r/20250306075211.1855177-3-alistair@alistair23.me
Signed-off-by: Alistair Francis <alistair@alistair23.me>
[bhelgaas: drop pci_doe_sysfs_init() stub return, make
DEVICE_ATTR_RO(doe_discovery) static]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

6 files changed, 197 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 5da6a14dc326..69f952fffec7 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -583,3 +583,32 @@ Description:
 		enclosure-specific indications "specific0" to "specific7",
 		hence the corresponding led class devices are unavailable if
 		the DSM interface is used.
+
+What:		/sys/bus/pci/devices/.../doe_features
+Date:		March 2025
+Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
+Description:
+		This directory contains a list of the supported Data Object
+		Exchange (DOE) features. The features are the file name.
+		The contents of each file is the raw Vendor ID and data
+		object feature values.
+
+		The value comes from the device and specifies the vendor and
+		data object type supported. The lower (RHS of the colon) is
+		the data object type in hex. The upper (LHS of the colon)
+		is the vendor ID.
+
+		As all DOE devices must support the DOE discovery feature,
+		if DOE is supported you will at least see the doe_discovery
+		file, with this contents:
+
+		  # cat doe_features/doe_discovery
+		  0001:00
+
+		If the device supports other features you will see other
+		files as well. For example if CMA/SPDM and secure CMA/SPDM
+		are supported the doe_features directory will look like
+		this:
+
+		  # ls doe_features
+		  0001:01        0001:02        doe_discovery
diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c
index f4508d75ce69..aae9a8a00406 100644
--- a/drivers/pci/doe.c
+++ b/drivers/pci/doe.c
@@ -14,10 +14,12 @@
 
 #include <linux/bitfield.h>
 #include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/jiffies.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/pci-doe.h>
+#include <linux/sysfs.h>
 #include <linux/workqueue.h>
 
 #include "pci.h"
@@ -47,6 +49,7 @@
  * @wq: Wait queue for work item
  * @work_queue: Queue of pci_doe_work items
  * @flags: Bit array of PCI_DOE_FLAG_* flags
+ * @sysfs_attrs: Array of sysfs device attributes
  */
 struct pci_doe_mb {
 	struct pci_dev *pdev;
@@ -56,6 +59,10 @@ struct pci_doe_mb {
 	wait_queue_head_t wq;
 	struct workqueue_struct *work_queue;
 	unsigned long flags;
+
+#ifdef CONFIG_SYSFS
+	struct device_attribute *sysfs_attrs;
+#endif
 };
 
 struct pci_doe_feature {
@@ -92,6 +99,152 @@ struct pci_doe_task {
 	struct pci_doe_mb *doe_mb;
 };
 
+#ifdef CONFIG_SYSFS
+static ssize_t doe_discovery_show(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	return sysfs_emit(buf, "0001:00\n");
+}
+static DEVICE_ATTR_RO(doe_discovery);
+
+static struct attribute *pci_doe_sysfs_feature_attrs[] = {
+	&dev_attr_doe_discovery.attr,
+	NULL
+};
+
+static bool pci_doe_features_sysfs_group_visible(struct kobject *kobj)
+{
+	struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
+
+	return !xa_empty(&pdev->doe_mbs);
+}
+DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(pci_doe_features_sysfs)
+
+const struct attribute_group pci_doe_sysfs_group = {
+	.name	    = "doe_features",
+	.attrs	    = pci_doe_sysfs_feature_attrs,
+	.is_visible = SYSFS_GROUP_VISIBLE(pci_doe_features_sysfs),
+};
+
+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 void pci_doe_sysfs_feature_remove(struct pci_dev *pdev,
+					 struct pci_doe_mb *doe_mb)
+{
+	struct device_attribute *attrs = doe_mb->sysfs_attrs;
+	struct device *dev = &pdev->dev;
+	unsigned long i;
+	void *entry;
+
+	if (!attrs)
+		return;
+
+	doe_mb->sysfs_attrs = NULL;
+	xa_for_each(&doe_mb->feats, i, entry) {
+		if (attrs[i].show)
+			sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr,
+						     pci_doe_sysfs_group.name);
+		kfree(attrs[i].attr.name);
+	}
+	kfree(attrs);
+}
+
+static int pci_doe_sysfs_feature_populate(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->feats, i, entry)
+		num_features++;
+
+	attrs = kcalloc(num_features, sizeof(*attrs), GFP_KERNEL);
+	if (!attrs) {
+		pci_warn(pdev, "Failed allocating the device_attribute array\n");
+		return -ENOMEM;
+	}
+
+	doe_mb->sysfs_attrs = attrs;
+	xa_for_each(&doe_mb->feats, i, entry) {
+		sysfs_attr_init(&attrs[i].attr);
+		vid = xa_to_value(entry) >> 8;
+		type = xa_to_value(entry) & 0xFF;
+
+		if (vid == PCI_VENDOR_ID_PCI_SIG &&
+		    type == PCI_DOE_FEATURE_DISCOVERY) {
+
+			/*
+			 * DOE Discovery, manually displayed by
+			 * `dev_attr_doe_discovery`
+			 */
+			continue;
+		}
+
+		attrs[i].attr.name = kasprintf(GFP_KERNEL,
+					       "%04lx:%02lx", vid, type);
+		if (!attrs[i].attr.name) {
+			ret = -ENOMEM;
+			pci_warn(pdev, "Failed allocating the attribute name\n");
+			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_doe_sysfs_group.name);
+		if (ret) {
+			attrs[i].show = NULL;
+			if (ret != -EEXIST) {
+				pci_warn(pdev, "Failed adding %s to sysfs group\n",
+					 attrs[i].attr.name);
+				goto fail;
+			} else
+				kfree(attrs[i].attr.name);
+		}
+	}
+
+	return 0;
+
+fail:
+	pci_doe_sysfs_feature_remove(pdev, doe_mb);
+	return ret;
+}
+
+void pci_doe_sysfs_teardown(struct pci_dev *pdev)
+{
+	struct pci_doe_mb *doe_mb;
+	unsigned long index;
+
+	xa_for_each(&pdev->doe_mbs, index, doe_mb)
+		pci_doe_sysfs_feature_remove(pdev, doe_mb);
+}
+
+void pci_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_populate(pdev, doe_mb);
+		if (ret)
+			return;
+	}
+}
+#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 b46ce1a2c554..5e3874eaa3c1 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1805,5 +1805,8 @@ const struct attribute_group *pci_dev_attr_groups[] = {
 #ifdef CONFIG_PCIEASPM
 	&aspm_ctrl_attr_group,
 #endif
+#ifdef CONFIG_PCI_DOE
+	&pci_doe_sysfs_group,
+#endif
 	NULL,
 };
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 01e51db8d285..9b956dc53adb 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -253,6 +253,7 @@ extern const struct attribute_group *pci_dev_groups[];
 extern const struct attribute_group *pci_dev_attr_groups[];
 extern const struct attribute_group *pcibus_groups[];
 extern const struct attribute_group *pci_bus_groups[];
+extern const struct attribute_group pci_doe_sysfs_group;
 #else
 static inline int pci_create_sysfs_dev_files(struct pci_dev *pdev) { return 0; }
 static inline void pci_remove_sysfs_dev_files(struct pci_dev *pdev) { }
@@ -456,6 +457,14 @@ static inline void pci_npem_create(struct pci_dev *dev) { }
 static inline void pci_npem_remove(struct pci_dev *dev) { }
 #endif
 
+#if defined(CONFIG_PCI_DOE) && defined(CONFIG_SYSFS)
+void pci_doe_sysfs_init(struct pci_dev *pci_dev);
+void pci_doe_sysfs_teardown(struct pci_dev *pdev);
+#else
+static inline void pci_doe_sysfs_init(struct pci_dev *pdev) { }
+static inline void pci_doe_sysfs_teardown(struct pci_dev *pdev) { }
+#endif
+
 /**
  * pci_dev_set_io_state - Set the new error state if possible.
  *
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index b6536ed599c3..7cf1a727748d 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2661,6 +2661,8 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 	WARN_ON(ret < 0);
 
 	pci_npem_create(dev);
+
+	pci_doe_sysfs_init(dev);
 }
 
 struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn)
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index efc37fcb73e2..5813726214e6 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -53,6 +53,7 @@ static void pci_destroy_dev(struct pci_dev *dev)
 	if (pci_dev_test_and_set_removed(dev))
 		return;
 
+	pci_doe_sysfs_teardown(dev);
 	pci_npem_remove(dev);
 
 	device_del(&dev->dev);