PCI: Allow all bus devices to use the same slot

A PCIe hotplug slot applies to the entire secondary bus. Thus, pciehp only
allocates a single hotplug_slot for the bridge to that bus. The existing
PCI slot, though, would only match to functions on device 0, meaning any
devices beyond that, e.g., ARI functions, are not matched to any slot even
though they share it. A slot reset will break all the missing devices
because the handling skips them.

For example, ARI devices with more than 8 functions fail because their
state is not properly handled, nor is the attached driver notified of the
reset. In the best case, the device will appear unresponsive to the driver,
resulting in unexpected errors. A worse possibility may panic the kernel if
in-flight transactions trigger hardware reported errors like this real
observation:

  vfio-pci 0000:01:00.0: resetting
  vfio-pci 0000:01:00.0: reset done
  {1}[Hardware Error]:  Error 1, type: fatal
  {1}[Hardware Error]:   section_type: PCIe error
  {1}[Hardware Error]:   port_type: 0, PCIe end point
  {1}[Hardware Error]:   version: 0.2
  {1}[Hardware Error]:   command: 0x0140, status: 0x0010
  {1}[Hardware Error]:   device_id: 0000:01:01.0
  {1}[Hardware Error]:   slot: 0
  {1}[Hardware Error]:   secondary_bus: 0x00
  {1}[Hardware Error]:   vendor_id: 0x1d9b, device_id: 0x0207
  {1}[Hardware Error]:   class_code: 020000
  {1}[Hardware Error]:   bridge: secondary_status: 0x0000, control: 0x0000
  {1}[Hardware Error]:   aer_cor_status: 0x00008000, aer_cor_mask: 0x00002000
  {1}[Hardware Error]:   aer_uncor_status: 0x00010000, aer_uncor_mask: 0x00100000
  {1}[Hardware Error]:   aer_uncor_severity: 0x006f6030
  {1}[Hardware Error]:   TLP Header: 0a412800 00192080 60000004 00000004
  GHES: Fatal hardware error but panic disabled
  Kernel panic - not syncing: GHES: Fatal hardware error

Allow a slot to be created to claim all devices on a bus, not just a
matching device. This is done by introducing a sentinel value, named
PCI_SLOT_ALL_DEVICES, which then has the PCI slot match to any device on
the bus. This fixes slot resets for pciehp.

Since 0xff already has special meaning, the chosen value for this new
feature is 0xfe. This will not clash with any actual slot number since they
are limited to 5 bits.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260217160836.2709885-3-kbusch@meta.com

3 files changed, 38 insertions, 6 deletions

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 1e9158d7bac7..2cafd3b26f34 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -79,7 +79,8 @@ static int init_slot(struct controller *ctrl)
 	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
 
 	retval = pci_hp_initialize(&ctrl->hotplug_slot,
-				   ctrl->pcie->port->subordinate, 0, name);
+				   ctrl->pcie->port->subordinate,
+				   PCI_SLOT_ALL_DEVICES, name);
 	if (retval) {
 		ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval);
 		kfree(ops);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 787311614e5b..e0b7fb43423c 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -42,6 +42,15 @@ static ssize_t address_read_file(struct pci_slot *slot, char *buf)
 				  pci_domain_nr(slot->bus),
 				  slot->bus->number);
 
+	/*
+	 * Preserve legacy ABI expectations that hotplug drivers that manage
+	 * multiple devices per slot emit 0 for the device number.
+	 */
+	if (slot->number == PCI_SLOT_ALL_DEVICES)
+		return sysfs_emit(buf, "%04x:%02x:00\n",
+				  pci_domain_nr(slot->bus),
+				  slot->bus->number);
+
 	return sysfs_emit(buf, "%04x:%02x:%02x\n",
 			  pci_domain_nr(slot->bus),
 			  slot->bus->number,
@@ -73,7 +82,8 @@ static void pci_slot_release(struct kobject *kobj)
 
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &slot->bus->devices, bus_list)
-		if (PCI_SLOT(dev->devfn) == slot->number)
+		if (slot->number == PCI_SLOT_ALL_DEVICES ||
+		    PCI_SLOT(dev->devfn) == slot->number)
 			dev->slot = NULL;
 	up_read(&pci_bus_sem);
 
@@ -166,7 +176,8 @@ void pci_dev_assign_slot(struct pci_dev *dev)
 
 	mutex_lock(&pci_slot_mutex);
 	list_for_each_entry(slot, &dev->bus->slots, list)
-		if (PCI_SLOT(dev->devfn) == slot->number)
+		if (slot->number == PCI_SLOT_ALL_DEVICES ||
+		    PCI_SLOT(dev->devfn) == slot->number)
 			dev->slot = slot;
 	mutex_unlock(&pci_slot_mutex);
 }
@@ -188,7 +199,8 @@ static struct pci_slot *get_slot(struct pci_bus *parent, int slot_nr)
 /**
  * pci_create_slot - create or increment refcount for physical PCI slot
  * @parent: struct pci_bus of parent bridge
- * @slot_nr: PCI_SLOT(pci_dev->devfn) or -1 for placeholder
+ * @slot_nr: PCI_SLOT(pci_dev->devfn), -1 for placeholder, or
+ *	PCI_SLOT_ALL_DEVICES
  * @name: user visible string presented in /sys/bus/pci/slots/<name>
  * @hotplug: set if caller is hotplug driver, NULL otherwise
  *
@@ -222,6 +234,16 @@ static struct pci_slot *get_slot(struct pci_bus *parent, int slot_nr)
  * consist solely of a dddd:bb tuple, where dddd is the PCI domain of the
  * %struct pci_bus and bb is the bus number. In other words, the devfn of
  * the 'placeholder' slot will not be displayed.
+ *
+ * Bus-wide slots:
+ * For PCIe hotplug, the physical slot encompasses the entire secondary
+ * bus, not just a single device number. If the device supports ARI and ARI
+ * Forwarding is enabled in the upstream bridge, a multi-function device
+ * may include functions that appear to have several different device
+ * numbers, i.e., PCI_SLOT() values.  Pass @slot_nr == PCI_SLOT_ALL_DEVICES
+ * to create a slot that matches all devices on the bus. Unlike placeholder
+ * slots, bus-wide slots go through normal slot lookup and reuse existing
+ * slots if present.
  */
 struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 				 const char *name,
@@ -285,7 +307,8 @@ placeholder:
 
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &parent->devices, bus_list)
-		if (PCI_SLOT(dev->devfn) == slot_nr)
+		if (slot_nr == PCI_SLOT_ALL_DEVICES ||
+		    PCI_SLOT(dev->devfn) == slot_nr)
 			dev->slot = slot;
 	up_read(&pci_bus_sem);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1c270f1d5123..5ae2dfdb2d6f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -72,12 +72,20 @@
 /* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */
 #define PCI_BUS_NUM(x) (((x) >> 8) & 0xff)
 
+/*
+ * PCI_SLOT_ALL_DEVICES indicates a slot that covers all devices on the bus.
+ * Used for PCIe hotplug where the physical slot is the entire secondary bus,
+ * and, if ARI Forwarding is enabled, functions may appear to be on multiple
+ * devices.
+ */
+#define PCI_SLOT_ALL_DEVICES	0xfe
+
 /* 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;		/* PCI_SLOT(pci_dev->devfn) */
+	unsigned char		number;		/* Device nr, or PCI_SLOT_ALL_DEVICES */
 	struct kobject		kobj;
 };