1 files changed, 225 insertions, 23 deletions

diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index 573a41869c15..c5345bff9a55 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -3,12 +3,15 @@
  * PCI Hotplug Driver for PowerPC PowerNV platform.
  *
  * Copyright Gavin Shan, IBM Corporation 2016.
+ * Copyright (C) 2025 Raptor Engineering, LLC
+ * Copyright (C) 2025 Raptor Computing Systems, LLC
  */
 
 #include <linux/bitfield.h>
 #include <linux/libfdt.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/delay.h>
 #include <linux/pci_hotplug.h>
 #include <linux/of_fdt.h>
 
@@ -36,8 +39,10 @@ static void pnv_php_register(struct device_node *dn);
 static void pnv_php_unregister_one(struct device_node *dn);
 static void pnv_php_unregister(struct device_node *dn);
 
+static void pnv_php_enable_irq(struct pnv_php_slot *php_slot);
+
 static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
-				bool disable_device)
+				bool disable_device, bool disable_msi)
 {
 	struct pci_dev *pdev = php_slot->pdev;
 	u16 ctrl;
@@ -53,19 +58,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
 		php_slot->irq = 0;
 	}
 
-	if (php_slot->wq) {
-		destroy_workqueue(php_slot->wq);
-		php_slot->wq = NULL;
-	}
-
-	if (disable_device) {
+	if (disable_device || disable_msi) {
 		if (pdev->msix_enabled)
 			pci_disable_msix(pdev);
 		else if (pdev->msi_enabled)
 			pci_disable_msi(pdev);
+	}
 
+	if (disable_device)
 		pci_disable_device(pdev);
-	}
 }
 
 static void pnv_php_free_slot(struct kref *kref)
@@ -74,7 +75,8 @@ static void pnv_php_free_slot(struct kref *kref)
 					struct pnv_php_slot, kref);
 
 	WARN_ON(!list_empty(&php_slot->children));
-	pnv_php_disable_irq(php_slot, false);
+	pnv_php_disable_irq(php_slot, false, false);
+	destroy_workqueue(php_slot->wq);
 	kfree(php_slot->name);
 	kfree(php_slot);
 }
@@ -391,6 +393,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
 	return 0;
 }
 
+static int pcie_check_link_active(struct pci_dev *pdev)
+{
+	u16 lnk_status;
+	int ret;
+
+	ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status))
+		return -ENODEV;
+
+	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+
+	return ret;
+}
+
 static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
@@ -403,6 +419,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 	 */
 	ret = pnv_pci_get_presence_state(php_slot->id, &presence);
 	if (ret >= 0) {
+		if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM &&
+			presence == OPAL_PCI_SLOT_EMPTY) {
+			/*
+			 * Similar to pciehp_hpc, check whether the Link Active
+			 * bit is set to account for broken downstream bridges
+			 * that don't properly assert Presence Detect State, as
+			 * was observed on the Microsemi Switchtec PM8533 PFX
+			 * [11f8:8533].
+			 */
+			if (pcie_check_link_active(php_slot->pdev) > 0)
+				presence = OPAL_PCI_SLOT_PRESENT;
+		}
+
 		*state = presence;
 		ret = 0;
 	} else {
@@ -412,10 +441,23 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 	return ret;
 }
 
+static int pnv_php_get_raw_indicator_status(struct hotplug_slot *slot, u8 *state)
+{
+	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
+	struct pci_dev *bridge = php_slot->pdev;
+	u16 status;
+
+	pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &status);
+	*state = (status & (PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC)) >> 6;
+	return 0;
+}
+
+
 static int pnv_php_get_attention_state(struct hotplug_slot *slot, u8 *state)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
 
+	pnv_php_get_raw_indicator_status(slot, &php_slot->attention_state);
 	*state = php_slot->attention_state;
 	return 0;
 }
@@ -433,7 +475,7 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state)
 	mask = PCI_EXP_SLTCTL_AIC;
 
 	if (state)
-		new = PCI_EXP_SLTCTL_ATTN_IND_ON;
+		new = FIELD_PREP(PCI_EXP_SLTCTL_AIC, state);
 	else
 		new = PCI_EXP_SLTCTL_ATTN_IND_OFF;
 
@@ -442,6 +484,61 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state)
 	return 0;
 }
 
+static int pnv_php_activate_slot(struct pnv_php_slot *php_slot,
+				 struct hotplug_slot *slot)
+{
+	int ret, i;
+
+	/*
+	 * Issue initial slot activation command to firmware
+	 *
+	 * Firmware will power slot on, attempt to train the link, and
+	 * discover any downstream devices. If this process fails, firmware
+	 * will return an error code and an invalid device tree. Failure
+	 * can be caused for multiple reasons, including a faulty
+	 * downstream device, poor connection to the downstream device, or
+	 * a previously latched PHB fence.  On failure, issue fundamental
+	 * reset up to three times before aborting.
+	 */
+	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON);
+	if (ret) {
+		SLOT_WARN(
+			php_slot,
+			"PCI slot activation failed with error code %d, possible frozen PHB",
+			ret);
+		SLOT_WARN(
+			php_slot,
+			"Attempting complete PHB reset before retrying slot activation\n");
+		for (i = 0; i < 3; i++) {
+			/*
+			 * Slot activation failed, PHB may be fenced from a
+			 * prior device failure.
+			 *
+			 * Use the OPAL fundamental reset call to both try a
+			 * device reset and clear any potentially active PHB
+			 * fence / freeze.
+			 */
+			SLOT_WARN(php_slot, "Try %d...\n", i + 1);
+			pci_set_pcie_reset_state(php_slot->pdev,
+						 pcie_warm_reset);
+			msleep(250);
+			pci_set_pcie_reset_state(php_slot->pdev,
+						 pcie_deassert_reset);
+
+			ret = pnv_php_set_slot_power_state(
+				slot, OPAL_PCI_SLOT_POWER_ON);
+			if (!ret)
+				break;
+		}
+
+		if (i >= 3)
+			SLOT_WARN(php_slot,
+				  "Failed to bring slot online, aborting!\n");
+	}
+
+	return ret;
+}
+
 static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
 {
 	struct hotplug_slot *slot = &php_slot->slot;
@@ -504,7 +601,7 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan)
 		goto scan;
 
 	/* Power is off, turn it on and then scan the slot */
-	ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON);
+	ret = pnv_php_activate_slot(php_slot, slot);
 	if (ret)
 		return ret;
 
@@ -561,8 +658,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe)
 static int pnv_php_enable_slot(struct hotplug_slot *slot)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
+	u32 prop32;
+	int ret;
+
+	ret = pnv_php_enable(php_slot, true);
+	if (ret)
+		return ret;
+
+	/* (Re-)enable interrupt if the slot supports surprise hotplug */
+	ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable",
+				   &prop32);
+	if (!ret && prop32)
+		pnv_php_enable_irq(php_slot);
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all slots on the provided bus, as well as
+ * all downstream slots in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+	struct pci_slot *slot;
+
+	/* First go down child buses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	/* Disable IRQs for all pnv_php slots on this bus */
+	list_for_each_entry(slot, &bus->slots, list) {
+		struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug);
 
-	return pnv_php_enable(php_slot, true);
+		pnv_php_disable_irq(php_slot, false, true);
+	}
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all downstream slots on the provided
+ * bus in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+
+	/* Go down child buses, recursively deactivating their IRQs */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	return 0;
 }
 
 static int pnv_php_disable_slot(struct hotplug_slot *slot)
@@ -579,6 +726,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot)
 	    php_slot->state != PNV_PHP_STATE_REGISTERED)
 		return 0;
 
+	/*
+	 * Free all IRQ resources from all child slots before remove.
+	 * Note that we do not disable the root slot IRQ here as that
+	 * would also deactivate the slot hot (re)plug interrupt!
+	 */
+	pnv_php_disable_all_downstream_irqs(php_slot->bus);
+
 	/* Remove all devices behind the slot */
 	pci_lock_rescan_remove();
 	pci_hp_remove_devices(php_slot->bus);
@@ -647,6 +801,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 		return NULL;
 	}
 
+	/* Allocate workqueue for this slot's interrupt handling */
+	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
+	if (!php_slot->wq) {
+		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
+		kfree(php_slot->name);
+		kfree(php_slot);
+		return NULL;
+	}
+
 	if (dn->child && PCI_DN(dn->child))
 		php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn);
 	else
@@ -745,16 +908,63 @@ static int pnv_php_enable_msix(struct pnv_php_slot *php_slot)
 	return entry.vector;
 }
 
+static void
+pnv_php_detect_clear_suprise_removal_freeze(struct pnv_php_slot *php_slot)
+{
+	struct pci_dev *pdev = php_slot->pdev;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int i, rc;
+
+	/*
+	 * When a device is surprise removed from a downstream bridge slot,
+	 * the upstream bridge port can still end up frozen due to related EEH
+	 * events, which will in turn block the MSI interrupts for slot hotplug
+	 * detection.
+	 *
+	 * Detect and thaw any frozen upstream PE after slot deactivation.
+	 */
+	edev = pci_dev_to_eeh_dev(pdev);
+	pe = edev ? edev->pe : NULL;
+	rc = eeh_pe_get_state(pe);
+	if ((rc == -ENODEV) || (rc == -ENOENT)) {
+		SLOT_WARN(
+			php_slot,
+			"Upstream bridge PE state unknown, hotplug detect may fail\n");
+	} else {
+		if (pe->state & EEH_PE_ISOLATED) {
+			SLOT_WARN(
+				php_slot,
+				"Upstream bridge PE %02x frozen, thawing...\n",
+				pe->addr);
+			for (i = 0; i < 3; i++)
+				if (!eeh_unfreeze_pe(pe))
+					break;
+			if (i >= 3)
+				SLOT_WARN(
+					php_slot,
+					"Unable to thaw PE %02x, hotplug detect will fail!\n",
+					pe->addr);
+			else
+				SLOT_WARN(php_slot,
+					  "PE %02x thawed successfully\n",
+					  pe->addr);
+		}
+	}
+}
+
 static void pnv_php_event_handler(struct work_struct *work)
 {
 	struct pnv_php_event *event =
 		container_of(work, struct pnv_php_event, work);
 	struct pnv_php_slot *php_slot = event->php_slot;
 
-	if (event->added)
+	if (event->added) {
 		pnv_php_enable_slot(&php_slot->slot);
-	else
+	} else {
 		pnv_php_disable_slot(&php_slot->slot);
+		pnv_php_detect_clear_suprise_removal_freeze(php_slot);
+	}
 
 	kfree(event);
 }
@@ -843,14 +1053,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	u16 sts, ctrl;
 	int ret;
 
-	/* Allocate workqueue */
-	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
-	if (!php_slot->wq) {
-		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
-		pnv_php_disable_irq(php_slot, true);
-		return;
-	}
-
 	/* Check PDC (Presence Detection Change) is broken or not */
 	ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc",
 				   &broken_pdc);
@@ -869,7 +1071,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED,
 			  php_slot->name, php_slot);
 	if (ret) {
-		pnv_php_disable_irq(php_slot, true);
+		pnv_php_disable_irq(php_slot, true, true);
 		SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}