PCI: Allow per function PCI slots to fix slot reset on s390

On s390 systems, which use a machine level hypervisor, PCI devices are
always accessed through a form of PCI pass-through which fundamentally
operates on a per PCI function granularity. This is also reflected in the
s390 PCI hotplug driver which creates hotplug slots for individual PCI
functions. Its reset_slot() function, which is a wrapper for
zpci_hot_reset_device(), thus also resets individual functions.

Currently, the pci_create_slot() assigns the same pci_slot object to
multifunction devices. This approach worked fine on s390 systems that only
exposed virtual functions as individual PCI domains to the operating
system.  Since commit 44510d6fa0c0 ("s390/pci: Handling multifunctions")
s390 supports exposing the topology of multifunction PCI devices by
grouping them in a shared PCI domain. This creates a problem when resetting
a function through the hotplug driver's slot_reset() interface.

When attempting to reset a function through the hotplug driver, the shared
slot assignment causes the wrong function to be reset instead of the
intended one. It also leaks memory as we do create a pci_slot object for
the function, but don't correctly free it in pci_slot_release().

Add a flag for struct pci_slot to allow per function PCI slots for
functions managed through a hypervisor, which exposes individual PCI
functions while retaining the topology. Since we can use all 8 bits for
slot 'number' (for ARI devices), change slot 'number' u16 to account for
special values PCI_SLOT_PLACEHOLDER and PCI_SLOT_ALL_DEVICES.

Fixes: 44510d6fa0c0 ("s390/pci: Handling multifunctions")
Suggested-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260805165518.794-3-alifm@linux.ibm.com

3 files changed, 30 insertions, 11 deletions

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 77b17b13ee61..350bae907ebf 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4897,8 +4897,9 @@ static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, bool probe)
 
 static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe)
 {
-	if (dev->multifunction || dev->subordinate || !dev->slot ||
-	    dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
+	if (dev->subordinate || !dev->slot ||
+	    dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+	    (dev->multifunction && !dev->slot->per_func_slot))
 		return -ENOTTY;
 
 	return pci_reset_hotplug_slot(dev->slot->hotplug, probe);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 42ff66461f74..897223f01f6a 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -72,6 +72,23 @@ static ssize_t cur_speed_read_file(struct pci_slot *slot, char *buf)
 	return bus_speed_read(slot->bus->cur_bus_speed, buf);
 }
 
+static bool pci_dev_matches_slot(struct pci_dev *dev, struct pci_slot *slot)
+{
+	if (slot->per_func_slot)
+		return dev->devfn == slot->number;
+
+	return slot->number == PCI_SLOT_ALL_DEVICES ||
+		PCI_SLOT(dev->devfn) == slot->number;
+}
+
+static bool pci_slot_enabled_per_func(void)
+{
+	if (IS_ENABLED(CONFIG_S390))
+		return true;
+
+	return false;
+}
+
 static void pci_slot_release(struct kobject *kobj)
 {
 	struct pci_dev *dev;
@@ -82,8 +99,7 @@ static void pci_slot_release(struct kobject *kobj)
 
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &slot->bus->devices, bus_list)
-		if (slot->number == PCI_SLOT_ALL_DEVICES ||
-		    PCI_SLOT(dev->devfn) == slot->number)
+		if (pci_dev_matches_slot(dev, slot))
 			dev->slot = NULL;
 	up_read(&pci_bus_sem);
 
@@ -187,8 +203,7 @@ void pci_dev_assign_slot(struct pci_dev *dev)
 
 	mutex_lock(&pci_slot_mutex);
 	list_for_each_entry(slot, &dev->bus->slots, list)
-		if (slot->number == PCI_SLOT_ALL_DEVICES ||
-		    PCI_SLOT(dev->devfn) == slot->number)
+		if (pci_dev_matches_slot(dev, slot))
 			dev->slot = slot;
 	mutex_unlock(&pci_slot_mutex);
 }
@@ -299,6 +314,9 @@ placeholder:
 	slot->bus = pci_bus_get(parent);
 	slot->number = slot_nr;
 
+	if (pci_slot_enabled_per_func())
+		slot->per_func_slot = 1;
+
 	slot->kobj.kset = pci_slots_kset;
 
 	slot_name = make_slot_name(name);
@@ -319,8 +337,7 @@ placeholder:
 
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &parent->devices, bus_list)
-		if (slot_nr == PCI_SLOT_ALL_DEVICES ||
-		    PCI_SLOT(dev->devfn) == slot_nr)
+		if (pci_dev_matches_slot(dev, slot))
 			dev->slot = slot;
 	up_read(&pci_bus_sem);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 3824a8dd551e..8593384489db 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -79,17 +79,18 @@
  * and, if ARI Forwarding is enabled, functions may appear to be on multiple
  * devices.
  */
-#define PCI_SLOT_ALL_DEVICES	0xfe
+#define PCI_SLOT_ALL_DEVICES	0xfeff
 
 /* Used to identify a slot as a placeholder */
-#define PCI_SLOT_PLACEHOLDER	0xff
+#define PCI_SLOT_PLACEHOLDER	0xffff
 
 /* pci_slot represents a physical slot */
 struct pci_slot {
 	struct pci_bus		*bus;		/* Bus this slot is on */
 	struct list_head	list;		/* Node in list of slots */
 	struct hotplug_slot	*hotplug;	/* Hotplug info (move here) */
-	unsigned char		number;		/* Device nr, or PCI_SLOT_ALL_DEVICES */
+	u16			number;		/* Device nr, or PCI_SLOT_ALL_DEVICES */
+	unsigned int		per_func_slot:1; /* Allow per function slot */
 	struct kobject		kobj;
 };